Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Ingo Molnar:
"The main changes in this cycle were:
- Implement wraparound-safe refcount_t and kref_t types based on
generic atomic primitives (Peter Zijlstra)
- Improve and fix the ww_mutex code (Nicolai Hähnle)
- Add self-tests to the ww_mutex code (Chris Wilson)
- Optimize percpu-rwsems with the 'rcuwait' mechanism (Davidlohr
Bueso)
- Micro-optimize the current-task logic all around the core kernel
(Davidlohr Bueso)
- Tidy up after recent optimizations: remove stale code and APIs,
clean up the code (Waiman Long)
- ... plus misc fixes, updates and cleanups"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
fork: Fix task_struct alignment
locking/spinlock/debug: Remove spinlock lockup detection code
lockdep: Fix incorrect condition to print bug msgs for MAX_LOCKDEP_CHAIN_HLOCKS
lkdtm: Convert to refcount_t testing
kref: Implement 'struct kref' using refcount_t
refcount_t: Introduce a special purpose refcount type
sched/wake_q: Clarify queue reinit comment
sched/wait, rcuwait: Fix typo in comment
locking/mutex: Fix lockdep_assert_held() fail
locking/rtmutex: Flip unlikely() branch to likely() in __rt_mutex_slowlock()
locking/rwsem: Reinit wake_q after use
locking/rwsem: Remove unnecessary atomic_long_t casts
jump_labels: Move header guard #endif down where it belongs
locking/atomic, kref: Implement kref_put_lock()
locking/ww_mutex: Turn off __must_check for now
locking/atomic, kref: Avoid more abuse
locking/atomic, kref: Use kref_get_unless_zero() more
locking/atomic, kref: Kill kref_sub()
locking/atomic, kref: Add kref_read()
locking/atomic, kref: Add KREF_INIT()
...
diff --git a/CREDITS b/CREDITS
index c585607..c5626bf 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2478,12 +2478,11 @@
S: Germany
N: Arnaldo Carvalho de Melo
-E: acme@ghostprotocols.net
+E: acme@kernel.org
E: arnaldo.melo@gmail.com
E: acme@redhat.com
-W: http://oops.ghostprotocols.net:81/blog/
P: 1024D/9224DF01 D5DF E3BB E3C8 BCBB F8AD 841A B6AB 4681 9224 DF01
-D: IPX, LLC, DCCP, cyc2x, wl3501_cs, net/ hacks
+D: tools/, IPX, LLC, DCCP, cyc2x, wl3501_cs, net/ hacks
S: Brazil
N: Karsten Merker
diff --git a/Documentation/ABI/testing/sysfs-devices-deferred_probe b/Documentation/ABI/testing/sysfs-devices-deferred_probe
deleted file mode 100644
index 58553d7..0000000
--- a/Documentation/ABI/testing/sysfs-devices-deferred_probe
+++ /dev/null
@@ -1,12 +0,0 @@
-What: /sys/devices/.../deferred_probe
-Date: August 2016
-Contact: Ben Hutchings <ben.hutchings@codethink.co.uk>
-Description:
- The /sys/devices/.../deferred_probe attribute is
- present for all devices. If a driver detects during
- probing a device that a related device is not yet
- ready, it may defer probing of the first device. The
- kernel will retry probing the first device after any
- other device is successfully probed. This attribute
- reads as 1 if probing of this device is currently
- deferred, or 0 otherwise.
diff --git a/Documentation/ABI/testing/sysfs-devices-edac b/Documentation/ABI/testing/sysfs-devices-edac
index 6568e00..46ff929 100644
--- a/Documentation/ABI/testing/sysfs-devices-edac
+++ b/Documentation/ABI/testing/sysfs-devices-edac
@@ -138,3 +138,20 @@
Description: This attribute file will display what type of memory is
currently on this csrow. Normally, either buffered or
unbuffered memory (for example, Unbuffered-DDR3).
+
+What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_ce_count
+Date: October 2016
+Contact: linux-edac@vger.kernel.org
+Description: This attribute file displays the total count of correctable
+ errors that have occurred on this DIMM. This count is very important
+ to examine. CEs provide early indications that a DIMM is beginning
+ to fail. This count field should be monitored for non-zero values
+ and report such information to the system administrator.
+
+What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_ue_count
+Date: October 2016
+Contact: linux-edac@vger.kernel.org
+Description: This attribute file displays the total count of uncorrectable
+ errors that have occurred on this DIMM. If panic_on_ue is set, this
+ counter will not have a chance to increment, since EDAC will panic the
+ system
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
index 7eb47ac..d583c65 100644
--- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html
+++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
@@ -4,7 +4,7 @@
<head><title>A Tour Through TREE_RCU's Data Structures [LWN.net]</title>
<meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">
- <p>January 27, 2016</p>
+ <p>December 18, 2016</p>
<p>This article was contributed by Paul E. McKenney</p>
<h3>Introduction</h3>
@@ -31,9 +31,6 @@
Accessor Functions</a>
</ol>
-At the end we have the
-<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>.
-
<h3><a name="Data-Structure Relationships">Data-Structure Relationships</a></h3>
<p>RCU is for all intents and purposes a large state machine, and its
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/ExpRCUFlow.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpRCUFlow.svg
new file mode 100644
index 0000000..7c6c90b
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpRCUFlow.svg
@@ -0,0 +1,830 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Creator: fig2dev Version 3.2 Patchlevel 5e -->
+
+<!-- CreationDate: Wed Dec 9 17:39:46 2015 -->
+
+<!-- Magnification: 3.000 -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="952.6817"
+ height="1219.6219"
+ viewBox="-66 -66 12729.905 16296.808"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="ExpRCUFlow.svg">
+ <metadata
+ id="metadata94">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <defs
+ id="defs92">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path4146"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow1Mend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow1Mend"
+ style="overflow:visible">
+ <path
+ id="path3852"
+ d="M 0,0 5,-5 -12.5,0 5,5 0,0 z"
+ style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt"
+ transform="matrix(-0.4,0,0,-0.4,-4,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow1Mend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow1Mend-9"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path3852-7"
+ d="M 0,0 5,-5 -12.5,0 5,5 0,0 z"
+ style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt"
+ transform="matrix(-0.4,0,0,-0.4,-4,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-7"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-6"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-1"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-16"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-8"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-160"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-5"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-78"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-66"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-8"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-56"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-19"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-89"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-85"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-3"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-73"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-55"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-5"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-88"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-198"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-2"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-22"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="marker5072"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path5074"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-87"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-63"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-6"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-26"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-0"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-51"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1"
+ objecttolerance="10"
+ gridtolerance="10"
+ guidetolerance="10"
+ inkscape:pageopacity="0"
+ inkscape:pageshadow="2"
+ inkscape:window-width="1090"
+ inkscape:window-height="1148"
+ id="namedview90"
+ showgrid="true"
+ inkscape:zoom="0.80021373"
+ inkscape:cx="462.49289"
+ inkscape:cy="623.19585"
+ inkscape:window-x="557"
+ inkscape:window-y="24"
+ inkscape:window-maximized="0"
+ inkscape:current-layer="g4"
+ inkscape:snap-grids="false"
+ fit-margin-top="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5"
+ fit-margin-left="5" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4"
+ transform="translate(23.312813,523.41305)">
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 11475 2250 - 11475 3465-->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 11475 5625 - 11475 6840-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 7875 225 - 10665 225-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 9675 675 - 7785 675-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 9675 4725 - 10665 4725-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 9225 5175 - 10665 5175-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 8775 11475 - 10665 11475-->
+ <!-- Line: box -->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 11475 9000 - 11475 10215-->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <g
+ id="g4104"
+ transform="translate(-1068.9745,0)">
+ <rect
+ transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)"
+ y="-7383.8755"
+ x="-6124.8989"
+ height="1966.2251"
+ width="1953.6969"
+ id="rect3032-1-0"
+ style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4098"
+ y="818.40338"
+ x="8168.2671"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="818.40338"
+ x="8168.2671"
+ id="tspan4100"
+ sodipodi:role="line">Idle or</tspan><tspan
+ id="tspan4102"
+ y="1152.4579"
+ x="8168.2671"
+ sodipodi:role="line">offline?</tspan></text>
+ </g>
+ <g
+ id="g4114"
+ transform="translate(0,147.96969)">
+ <rect
+ id="rect6"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1475.6636"
+ width="4401.7612"
+ y="0"
+ x="0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110"
+ y="835.11212"
+ x="2206.4917"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="835.11212"
+ x="2206.4917"
+ id="tspan4112"
+ sodipodi:role="line">CPU N Start</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="M 4432.5052,897.4924 5684.8749,880.79414"
+ id="path4119"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="M 8503.0006,874.12161 9755.3703,857.42334"
+ id="path4119-8"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <text
+ xml:space="preserve"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="8617.0977"
+ y="705.50983"
+ id="text4593"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4595"
+ x="8617.0977"
+ y="705.50983">Y</tspan></text>
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9"
+ transform="translate(9722.4732,131.27105)">
+ <rect
+ id="rect6-0"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="0"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5"
+ y="835.11212"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="835.11212"
+ x="1460.1007"
+ id="tspan4112-9"
+ sodipodi:role="line">Done</tspan></text>
+ </g>
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-5"
+ transform="translate(0,3705.3456)">
+ <rect
+ id="rect6-1"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1475.6636"
+ width="4401.7612"
+ y="0"
+ x="0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-9"
+ y="835.11212"
+ x="2206.4917"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="835.11212"
+ x="2206.4917"
+ sodipodi:role="line"
+ id="tspan4776">Send IPI to CPU N</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="M 7102.5627,2263.5171 4430.8404,3682.8694"
+ id="path4119-3"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4104-1"
+ transform="translate(-1065.3349,6403.5782)">
+ <rect
+ transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)"
+ y="-7383.8755"
+ x="-6124.8989"
+ height="1966.2251"
+ width="1953.6969"
+ id="rect3032-1-0-6"
+ style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4098-3"
+ y="482.00006"
+ x="8168.2671"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ id="tspan4102-8"
+ y="482.00006"
+ x="8168.2671"
+ sodipodi:role="line">In RCU</tspan><tspan
+ y="816.05457"
+ x="8168.2671"
+ sodipodi:role="line"
+ id="tspan4833">read-side</tspan><tspan
+ y="1150.109"
+ x="8168.2671"
+ sodipodi:role="line"
+ id="tspan4835">critical</tspan><tspan
+ y="1484.1636"
+ x="8168.2671"
+ sodipodi:role="line"
+ id="tspan4837">section?</tspan></text>
+ </g>
+ <text
+ xml:space="preserve"
+ style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="6463.0864"
+ y="2285.6765"
+ id="text4593-0"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4595-6"
+ x="6463.0864"
+ y="2285.6765">N</tspan></text>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654108, 80.17308215;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 2189.1897,5219.361 16.6983,1252.3697"
+ id="path4119-0"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-5-2"
+ transform="translate(0,6551.5479)">
+ <rect
+ id="rect6-1-7"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1475.6636"
+ width="4401.7612"
+ y="0"
+ x="0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-9-5"
+ y="835.11212"
+ x="2206.4917"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="835.11212"
+ x="2206.4917"
+ sodipodi:role="line"
+ id="tspan4776-5">IPI Handler</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="m 4432.5052,7297.9678 1252.3697,-16.6982"
+ id="path4119-2"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="m 8503.0013,7278.6595 1252.369,-16.6982"
+ id="path4119-8-7"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <text
+ xml:space="preserve"
+ style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="8617.0977"
+ y="7110.0186"
+ id="text4593-4"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4595-0"
+ x="8617.0977"
+ y="7110.0186">N</tspan></text>
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3"
+ transform="translate(9722.4732,6535.809)">
+ <rect
+ id="rect6-0-7"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7"
+ y="503.71591"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="503.71591"
+ x="1460.1007"
+ id="tspan4112-9-0"
+ sodipodi:role="line">Report CPU</tspan><tspan
+ y="837.77039"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4923">Quiescent</tspan><tspan
+ y="1171.825"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925">State</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654335, 80.17308669;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 7102.5627,8725.7454 16.6983,1252.3697"
+ id="path4119-0-0"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <text
+ xml:space="preserve"
+ style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="6797.0522"
+ y="9018.6807"
+ id="text4593-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4595-2"
+ x="6797.0522"
+ y="9018.6807">Y</tspan></text>
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-8"
+ transform="translate(-80.17308,11381.108)">
+ <rect
+ id="rect6-0-7-5"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-6"
+ y="841.88086"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="841.88086"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-1">rcu_read_unlock()</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654562, 80.17309124;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 1362.6256,10071.26 16.6983,1252.369"
+ id="path4119-0-0-7"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 1362.6256,12883.919 16.6983,1252.369"
+ id="path4119-0-0-7-7"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-8-1"
+ transform="translate(9722.4732,11389.458)">
+ <rect
+ id="rect6-0-7-5-1"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-6-2"
+ y="841.88086"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="841.88086"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-1-2">Context Switch</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654789, 80.17309578;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 11165.272,10071.26 16.698,1252.369"
+ id="path4119-0-0-7-8"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-9"
+ transform="translate(-80.17308,14163.046)">
+ <rect
+ id="rect6-0-7-1"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-3"
+ y="503.71591"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="503.71591"
+ x="1460.1007"
+ id="tspan4112-9-0-4"
+ sodipodi:role="line">Report CPU</tspan><tspan
+ y="837.77039"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4923-3">and Task</tspan><tspan
+ y="1171.825"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-9">Quiescent States</tspan></text>
+ </g>
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-8-1-8"
+ transform="translate(5663.2978,11389.458)">
+ <rect
+ id="rect6-0-7-5-1-1"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-6-2-4"
+ y="841.88086"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="841.88086"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-1-2-4">Enqueue Task</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="M 9827.612,12141.988 8575.243,12125.29"
+ id="path4119-8-7-5"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 7106.0965,12818.962 16.6983,1252.369"
+ id="path4119-0-0-7-7-5"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-9-2"
+ transform="translate(5663.2978,14098.088)">
+ <rect
+ id="rect6-0-7-1-8"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-3-4"
+ y="503.71591"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="503.71591"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4923-3-2">Report CPU</tspan><tspan
+ y="837.77039"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-9-9">Quiescent</tspan><tspan
+ y="1171.825"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan5239">State</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654562, 80.17309124;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="M 5733.305,14095.542 2761.014,12809.774"
+ id="path4119-0-0-2"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654107, 80.17308214;stroke-dashoffset:0"
+ d="m 1353.3524,10079.499 9701.6916,0 100.189,-16.698"
+ id="path5265"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="ccc" />
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg
new file mode 100644
index 0000000..e4233ac
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg
@@ -0,0 +1,826 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Creator: fig2dev Version 3.2 Patchlevel 5e -->
+
+<!-- CreationDate: Wed Dec 9 17:39:46 2015 -->
+
+<!-- Magnification: 3.000 -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="952.6817"
+ height="1425.6191"
+ viewBox="-66 -66 12729.905 19049.38"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="ExpSchedFlow.svg">
+ <metadata
+ id="metadata94">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <defs
+ id="defs92">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path4146"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow1Mend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow1Mend"
+ style="overflow:visible">
+ <path
+ id="path3852"
+ d="M 0,0 5,-5 -12.5,0 5,5 0,0 z"
+ style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt"
+ transform="matrix(-0.4,0,0,-0.4,-4,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow1Mend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow1Mend-9"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path3852-7"
+ d="M 0,0 5,-5 -12.5,0 5,5 0,0 z"
+ style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt"
+ transform="matrix(-0.4,0,0,-0.4,-4,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-7"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-6"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-1"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-16"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-8"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-160"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-5"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-78"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-66"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-8"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-56"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-19"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-89"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-85"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-3"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-73"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-55"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-5"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-88"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-198"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-2"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-22"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="marker5072"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path5074"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-87"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-63"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-6"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-26"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-0"
+ style="overflow:visible">
+ <path
+ inkscape:connector-curvature="0"
+ id="path4146-51"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-58"
+ style="overflow:visible">
+ <path
+ id="path4146-61"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1"
+ objecttolerance="10"
+ gridtolerance="10"
+ guidetolerance="10"
+ inkscape:pageopacity="0"
+ inkscape:pageshadow="2"
+ inkscape:window-width="1090"
+ inkscape:window-height="1148"
+ id="namedview90"
+ showgrid="true"
+ inkscape:zoom="0.80021373"
+ inkscape:cx="462.49289"
+ inkscape:cy="473.6718"
+ inkscape:window-x="770"
+ inkscape:window-y="24"
+ inkscape:window-maximized="0"
+ inkscape:current-layer="g4114-9-3-9"
+ inkscape:snap-grids="false"
+ fit-margin-top="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5"
+ fit-margin-left="5" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4"
+ transform="translate(23.312814,523.41265)">
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 11475 2250 - 11475 3465-->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line: box -->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 11475 5625 - 11475 6840-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 7875 225 - 10665 225-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 9675 675 - 7785 675-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 9675 4725 - 10665 4725-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 9225 5175 - 10665 5175-->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 8775 11475 - 10665 11475-->
+ <!-- Line: box -->
+ <!-- Line -->
+ <!-- Arrowhead on XXXpoint 11475 9000 - 11475 10215-->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <!-- Text -->
+ <g
+ id="g4104"
+ transform="translate(-1068.9745,0)">
+ <rect
+ transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)"
+ y="-7383.8755"
+ x="-6124.8989"
+ height="1966.2251"
+ width="1953.6969"
+ id="rect3032-1-0"
+ style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4098"
+ y="818.40338"
+ x="8168.2671"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="818.40338"
+ x="8168.2671"
+ id="tspan4100"
+ sodipodi:role="line">Idle or</tspan><tspan
+ id="tspan4102"
+ y="1152.4579"
+ x="8168.2671"
+ sodipodi:role="line">offline?</tspan></text>
+ </g>
+ <g
+ id="g4114"
+ transform="translate(0,147.96969)">
+ <rect
+ id="rect6"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1475.6636"
+ width="4401.7612"
+ y="0"
+ x="0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110"
+ y="835.11212"
+ x="2206.4917"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="835.11212"
+ x="2206.4917"
+ id="tspan4112"
+ sodipodi:role="line">CPU N Start</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="M 4432.5052,897.4924 5684.8749,880.79414"
+ id="path4119"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="M 8503.0006,874.12161 9755.3703,857.42334"
+ id="path4119-8"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <text
+ xml:space="preserve"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="8617.0977"
+ y="705.50983"
+ id="text4593"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4595"
+ x="8617.0977"
+ y="705.50983">Y</tspan></text>
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9"
+ transform="translate(9722.4732,131.27105)">
+ <rect
+ id="rect6-0"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="0"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5"
+ y="835.11212"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="835.11212"
+ x="1460.1007"
+ id="tspan4112-9"
+ sodipodi:role="line">Done</tspan></text>
+ </g>
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-5"
+ transform="translate(0,3705.3456)">
+ <rect
+ id="rect6-1"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1475.6636"
+ width="4401.7612"
+ y="0"
+ x="0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-9"
+ y="835.11212"
+ x="2206.4917"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="835.11212"
+ x="2206.4917"
+ sodipodi:role="line"
+ id="tspan4776">Send IPI to CPU N</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="M 7102.5627,2263.5171 4430.8404,3682.8694"
+ id="path4119-3"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4104-1"
+ transform="translate(-1065.3349,6403.5782)">
+ <rect
+ transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)"
+ y="-7383.8755"
+ x="-6124.8989"
+ height="1966.2251"
+ width="1953.6969"
+ id="rect3032-1-0-6"
+ style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4098-3"
+ y="985.4306"
+ x="8168.2671"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="985.4306"
+ x="8168.2671"
+ sodipodi:role="line"
+ id="tspan3109">CPU idle?</tspan></text>
+ </g>
+ <text
+ xml:space="preserve"
+ style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="6463.0864"
+ y="2285.6765"
+ id="text4593-0"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4595-6"
+ x="6463.0864"
+ y="2285.6765">N</tspan></text>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654108, 80.17308215;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 2189.1897,5219.361 16.6983,1252.3697"
+ id="path4119-0"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-5-2"
+ transform="translate(0,6551.5479)">
+ <rect
+ id="rect6-1-7"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1475.6636"
+ width="4401.7612"
+ y="0"
+ x="0" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-9-5"
+ y="835.11212"
+ x="2206.4917"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="835.11212"
+ x="2206.4917"
+ sodipodi:role="line"
+ id="tspan4776-5">IPI Handler</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="m 4432.5052,7297.9678 1252.3697,-16.6982"
+ id="path4119-2"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+ d="m 8503.0013,7278.6595 1252.369,-16.6982"
+ id="path4119-8-7"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <text
+ xml:space="preserve"
+ style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="8617.0977"
+ y="7110.0186"
+ id="text4593-4"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4595-0"
+ x="8617.0977"
+ y="7110.0186">Y</tspan></text>
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3"
+ transform="translate(9722.4732,6535.809)">
+ <rect
+ id="rect6-0-7"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7"
+ y="503.71591"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="503.71591"
+ x="1460.1007"
+ id="tspan4112-9-0"
+ sodipodi:role="line">Report CPU</tspan><tspan
+ y="837.77039"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4923">Quiescent</tspan><tspan
+ y="1171.825"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925">State</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654335, 80.17308669;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 7102.5627,11478.337 16.6983,1252.35"
+ id="path4119-0-0"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <text
+ xml:space="preserve"
+ style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="6797.0522"
+ y="9018.6807"
+ id="text4593-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4595-2"
+ x="6797.0522"
+ y="9018.6807">N</tspan></text>
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-8"
+ transform="translate(-80.17308,14133.68)">
+ <rect
+ id="rect6-0-7-5"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-6"
+ y="841.88086"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="841.88086"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-1">Context Switch</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654562, 80.17309124;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 1362.6256,12823.832 16.6983,1252.369"
+ id="path4119-0-0-7"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 1362.6256,15636.491 16.6983,1252.369"
+ id="path4119-0-0-7-7"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-8-1"
+ transform="translate(9722.4732,14142.03)">
+ <rect
+ id="rect6-0-7-5-1"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-6-2"
+ y="841.88086"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="841.88086"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-1-2">CPU Offline</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654789, 80.17309578;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 11165.272,12823.832 16.698,1252.369"
+ id="path4119-0-0-7-8"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-9"
+ transform="translate(-80.17308,16915.618)">
+ <rect
+ id="rect6-0-7-1"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-3"
+ y="505.47754"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="505.47754"
+ x="1460.1007"
+ id="tspan4112-9-0-4"
+ sodipodi:role="line">Report CPU</tspan><tspan
+ y="839.53204"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-9">Quiescent</tspan><tspan
+ y="1173.5865"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan3168">State</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 11165.272,15571.534 16.698,1252.369"
+ id="path4119-0-0-7-7-5"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-9-2"
+ transform="translate(9722.4732,16850.66)">
+ <rect
+ id="rect6-0-7-1-8"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-3-4"
+ y="503.71591"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="503.71591"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4923-3-2">Report CPU</tspan><tspan
+ y="837.77039"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-9-9">Quiescent</tspan><tspan
+ y="1171.825"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan5239">State</tspan></text>
+ </g>
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654107, 80.17308214;stroke-dashoffset:0"
+ d="m 1353.3524,12832.071 9701.6916,0 100.189,-16.698"
+ id="path5265"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="ccc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+ d="m 7112.6465,8669.1867 16.6983,1252.369"
+ id="path4119-0-0-7-7-5-7"
+ inkscape:connector-curvature="0"
+ sodipodi:nodetypes="cc" />
+ <g
+ style="fill:none;stroke-width:0.025in"
+ id="g4114-9-3-8-1-8-3"
+ transform="translate(5663.1399,9972.3627)">
+ <rect
+ id="rect6-0-7-5-1-1-9"
+ style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+ rx="0"
+ height="1425.5687"
+ width="2748.6331"
+ y="29.467337"
+ x="80.17308" />
+ <text
+ sodipodi:linespacing="125%"
+ id="text4110-5-7-6-2-4-0"
+ y="841.88086"
+ x="1460.1007"
+ style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ xml:space="preserve"><tspan
+ y="841.88086"
+ x="1460.1007"
+ sodipodi:role="line"
+ id="tspan4925-1-2-4-5">reched_cpu()</tspan></text>
+ </g>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
new file mode 100644
index 0000000..7a3194c
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
@@ -0,0 +1,626 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+ "http://www.w3.org/TR/html4/loose.dtd">
+ <html>
+ <head><title>A Tour Through TREE_RCU's Expedited Grace Periods</title>
+ <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">
+
+<h2>Introduction</h2>
+
+This document describes RCU's expedited grace periods.
+Unlike RCU's normal grace periods, which accept long latencies to attain
+high efficiency and minimal disturbance, expedited grace periods accept
+lower efficiency and significant disturbance to attain shorter latencies.
+
+<p>
+There are three flavors of RCU (RCU-bh, RCU-preempt, and RCU-sched),
+but only two flavors of expedited grace periods because the RCU-bh
+expedited grace period maps onto the RCU-sched expedited grace period.
+Each of the remaining two implementations is covered in its own section.
+
+<ol>
+<li> <a href="#Expedited Grace Period Design">
+ Expedited Grace Period Design</a>
+<li> <a href="#RCU-preempt Expedited Grace Periods">
+ RCU-preempt Expedited Grace Periods</a>
+<li> <a href="#RCU-sched Expedited Grace Periods">
+ RCU-sched Expedited Grace Periods</a>
+<li> <a href="#Expedited Grace Period and CPU Hotplug">
+ Expedited Grace Period and CPU Hotplug</a>
+<li> <a href="#Expedited Grace Period Refinements">
+ Expedited Grace Period Refinements</a>
+</ol>
+
+<h2><a name="Expedited Grace Period Design">
+Expedited Grace Period Design</a></h2>
+
+<p>
+The expedited RCU grace periods cannot be accused of being subtle,
+given that they for all intents and purposes hammer every CPU that
+has not yet provided a quiescent state for the current expedited
+grace period.
+The one saving grace is that the hammer has grown a bit smaller
+over time: The old call to <tt>try_stop_cpus()</tt> has been
+replaced with a set of calls to <tt>smp_call_function_single()</tt>,
+each of which results in an IPI to the target CPU.
+The corresponding handler function checks the CPU's state, motivating
+a faster quiescent state where possible, and triggering a report
+of that quiescent state.
+As always for RCU, once everything has spent some time in a quiescent
+state, the expedited grace period has completed.
+
+<p>
+The details of the <tt>smp_call_function_single()</tt> handler's
+operation depend on the RCU flavor, as described in the following
+sections.
+
+<h2><a name="RCU-preempt Expedited Grace Periods">
+RCU-preempt Expedited Grace Periods</a></h2>
+
+<p>
+The overall flow of the handling of a given CPU by an RCU-preempt
+expedited grace period is shown in the following diagram:
+
+<p><img src="ExpRCUFlow.svg" alt="ExpRCUFlow.svg" width="55%">
+
+<p>
+The solid arrows denote direct action, for example, a function call.
+The dotted arrows denote indirect action, for example, an IPI
+or a state that is reached after some time.
+
+<p>
+If a given CPU is offline or idle, <tt>synchronize_rcu_expedited()</tt>
+will ignore it because idle and offline CPUs are already residing
+in quiescent states.
+Otherwise, the expedited grace period will use
+<tt>smp_call_function_single()</tt> to send the CPU an IPI, which
+is handled by <tt>sync_rcu_exp_handler()</tt>.
+
+<p>
+However, because this is preemptible RCU, <tt>sync_rcu_exp_handler()</tt>
+can check to see if the CPU is currently running in an RCU read-side
+critical section.
+If not, the handler can immediately report a quiescent state.
+Otherwise, it sets flags so that the outermost <tt>rcu_read_unlock()</tt>
+invocation will provide the needed quiescent-state report.
+This flag-setting avoids the previous forced preemption of all
+CPUs that might have RCU read-side critical sections.
+In addition, this flag-setting is done so as to avoid increasing
+the overhead of the common-case fastpath through the scheduler.
+
+<p>
+Again because this is preemptible RCU, an RCU read-side critical section
+can be preempted.
+When that happens, RCU will enqueue the task, which will the continue to
+block the current expedited grace period until it resumes and finds its
+outermost <tt>rcu_read_unlock()</tt>.
+The CPU will report a quiescent state just after enqueuing the task because
+the CPU is no longer blocking the grace period.
+It is instead the preempted task doing the blocking.
+The list of blocked tasks is managed by <tt>rcu_preempt_ctxt_queue()</tt>,
+which is called from <tt>rcu_preempt_note_context_switch()</tt>, which
+in turn is called from <tt>rcu_note_context_switch()</tt>, which in
+turn is called from the scheduler.
+
+<table>
+<tr><th> </th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+ Why not just have the expedited grace period check the
+ state of all the CPUs?
+ After all, that would avoid all those real-time-unfriendly IPIs.
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+ Because we want the RCU read-side critical sections to run fast,
+ which means no memory barriers.
+ Therefore, it is not possible to safely check the state from some
+ other CPU.
+ And even if it was possible to safely check the state, it would
+ still be necessary to IPI the CPU to safely interact with the
+ upcoming <tt>rcu_read_unlock()</tt> invocation, which means that
+ the remote state testing would not help the worst-case
+ latency that real-time applications care about.
+
+ <p><font color="ffffff">One way to prevent your real-time
+ application from getting hit with these IPIs is to
+ build your kernel with <tt>CONFIG_NO_HZ_FULL=y</tt>.
+ RCU would then perceive the CPU running your application
+ as being idle, and it would be able to safely detect that
+ state without needing to IPI the CPU.
+</font></td></tr>
+<tr><td> </td></tr>
+</table>
+
+<p>
+Please note that this is just the overall flow:
+Additional complications can arise due to races with CPUs going idle
+or offline, among other things.
+
+<h2><a name="RCU-sched Expedited Grace Periods">
+RCU-sched Expedited Grace Periods</a></h2>
+
+<p>
+The overall flow of the handling of a given CPU by an RCU-sched
+expedited grace period is shown in the following diagram:
+
+<p><img src="ExpSchedFlow.svg" alt="ExpSchedFlow.svg" width="55%">
+
+<p>
+As with RCU-preempt's <tt>synchronize_rcu_expedited()</tt>,
+<tt>synchronize_sched_expedited()</tt> ignores offline and
+idle CPUs, again because they are in remotely detectable
+quiescent states.
+However, the <tt>synchronize_rcu_expedited()</tt> handler
+is <tt>sync_sched_exp_handler()</tt>, and because the
+<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
+leave no trace of their invocation, in general it is not possible to tell
+whether or not the current CPU is in an RCU read-side critical section.
+The best that <tt>sync_sched_exp_handler()</tt> can do is to check
+for idle, on the off-chance that the CPU went idle while the IPI
+was in flight.
+If the CPU is idle, then tt>sync_sched_exp_handler()</tt> reports
+the quiescent state.
+
+<p>
+Otherwise, the handler invokes <tt>resched_cpu()</tt>, which forces
+a future context switch.
+At the time of the context switch, the CPU reports the quiescent state.
+Should the CPU go offline first, it will report the quiescent state
+at that time.
+
+<h2><a name="Expedited Grace Period and CPU Hotplug">
+Expedited Grace Period and CPU Hotplug</a></h2>
+
+<p>
+The expedited nature of expedited grace periods require a much tighter
+interaction with CPU hotplug operations than is required for normal
+grace periods.
+In addition, attempting to IPI offline CPUs will result in splats, but
+failing to IPI online CPUs can result in too-short grace periods.
+Neither option is acceptable in production kernels.
+
+<p>
+The interaction between expedited grace periods and CPU hotplug operations
+is carried out at several levels:
+
+<ol>
+<li> The number of CPUs that have ever been online is tracked
+ by the <tt>rcu_state</tt> structure's <tt>->ncpus</tt>
+ field.
+ The <tt>rcu_state</tt> structure's <tt>->ncpus_snap</tt>
+ field tracks the number of CPUs that have ever been online
+ at the beginning of an RCU expedited grace period.
+ Note that this number never decreases, at least in the absence
+ of a time machine.
+<li> The identities of the CPUs that have ever been online is
+ tracked by the <tt>rcu_node</tt> structure's
+ <tt>->expmaskinitnext</tt> field.
+ The <tt>rcu_node</tt> structure's <tt>->expmaskinit</tt>
+ field tracks the identities of the CPUs that were online
+ at least once at the beginning of the most recent RCU
+ expedited grace period.
+ The <tt>rcu_state</tt> structure's <tt>->ncpus</tt> and
+ <tt>->ncpus_snap</tt> fields are used to detect when
+ new CPUs have come online for the first time, that is,
+ when the <tt>rcu_node</tt> structure's <tt>->expmaskinitnext</tt>
+ field has changed since the beginning of the last RCU
+ expedited grace period, which triggers an update of each
+ <tt>rcu_node</tt> structure's <tt>->expmaskinit</tt>
+ field from its <tt>->expmaskinitnext</tt> field.
+<li> Each <tt>rcu_node</tt> structure's <tt>->expmaskinit</tt>
+ field is used to initialize that structure's
+ <tt>->expmask</tt> at the beginning of each RCU
+ expedited grace period.
+ This means that only those CPUs that have been online at least
+ once will be considered for a given grace period.
+<li> Any CPU that goes offline will clear its bit in its leaf
+ <tt>rcu_node</tt> structure's <tt>->qsmaskinitnext</tt>
+ field, so any CPU with that bit clear can safely be ignored.
+ However, it is possible for a CPU coming online or going offline
+ to have this bit set for some time while <tt>cpu_online</tt>
+ returns <tt>false</tt>.
+<li> For each non-idle CPU that RCU believes is currently online, the grace
+ period invokes <tt>smp_call_function_single()</tt>.
+ If this succeeds, the CPU was fully online.
+ Failure indicates that the CPU is in the process of coming online
+ or going offline, in which case it is necessary to wait for a
+ short time period and try again.
+ The purpose of this wait (or series of waits, as the case may be)
+ is to permit a concurrent CPU-hotplug operation to complete.
+<li> In the case of RCU-sched, one of the last acts of an outgoing CPU
+ is to invoke <tt>rcu_report_dead()</tt>, which
+ reports a quiescent state for that CPU.
+ However, this is likely paranoia-induced redundancy. <!-- @@@ -->
+</ol>
+
+<table>
+<tr><th> </th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+ Why all the dancing around with multiple counters and masks
+ tracking CPUs that were once online?
+ Why not just have a single set of masks tracking the currently
+ online CPUs and be done with it?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+ Maintaining single set of masks tracking the online CPUs <i>sounds</i>
+ easier, at least until you try working out all the race conditions
+ between grace-period initialization and CPU-hotplug operations.
+ For example, suppose initialization is progressing down the
+ tree while a CPU-offline operation is progressing up the tree.
+ This situation can result in bits set at the top of the tree
+ that have no counterparts at the bottom of the tree.
+ Those bits will never be cleared, which will result in
+ grace-period hangs.
+ In short, that way lies madness, to say nothing of a great many
+ bugs, hangs, and deadlocks.
+
+ <p><font color="ffffff">
+ In contrast, the current multi-mask multi-counter scheme ensures
+ that grace-period initialization will always see consistent masks
+ up and down the tree, which brings significant simplifications
+ over the single-mask method.
+
+ <p><font color="ffffff">
+ This is an instance of
+ <a href="http://www.cs.columbia.edu/~library/TR-repository/reports/reports-1992/cucs-039-92.ps.gz"><font color="ffffff">
+ deferring work in order to avoid synchronization</a>.
+ Lazily recording CPU-hotplug events at the beginning of the next
+ grace period greatly simplifies maintenance of the CPU-tracking
+ bitmasks in the <tt>rcu_node</tt> tree.
+</font></td></tr>
+<tr><td> </td></tr>
+</table>
+
+<h2><a name="Expedited Grace Period Refinements">
+Expedited Grace Period Refinements</a></h2>
+
+<ol>
+<li> <a href="#Idle-CPU Checks">Idle-CPU checks</a>.
+<li> <a href="#Batching via Sequence Counter">
+ Batching via sequence counter</a>.
+<li> <a href="#Funnel Locking and Wait/Wakeup">
+ Funnel locking and wait/wakeup</a>.
+<li> <a href="#Use of Workqueues">Use of Workqueues</a>.
+<li> <a href="#Stall Warnings">Stall warnings</a>.
+</ol>
+
+<h3><a name="Idle-CPU Checks">Idle-CPU Checks</a></h3>
+
+<p>
+Each expedited grace period checks for idle CPUs when initially forming
+the mask of CPUs to be IPIed and again just before IPIing a CPU
+(both checks are carried out by <tt>sync_rcu_exp_select_cpus()</tt>).
+If the CPU is idle at any time between those two times, the CPU will
+not be IPIed.
+Instead, the task pushing the grace period forward will include the
+idle CPUs in the mask passed to <tt>rcu_report_exp_cpu_mult()</tt>.
+
+<p>
+For RCU-sched, there is an additional check for idle in the IPI
+handler, <tt>sync_sched_exp_handler()</tt>.
+If the IPI has interrupted the idle loop, then
+<tt>sync_sched_exp_handler()</tt> invokes <tt>rcu_report_exp_rdp()</tt>
+to report the corresponding quiescent state.
+
+<p>
+For RCU-preempt, there is no specific check for idle in the
+IPI handler (<tt>sync_rcu_exp_handler()</tt>), but because
+RCU read-side critical sections are not permitted within the
+idle loop, if <tt>sync_rcu_exp_handler()</tt> sees that the CPU is within
+RCU read-side critical section, the CPU cannot possibly be idle.
+Otherwise, <tt>sync_rcu_exp_handler()</tt> invokes
+<tt>rcu_report_exp_rdp()</tt> to report the corresponding quiescent
+state, regardless of whether or not that quiescent state was due to
+the CPU being idle.
+
+<p>
+In summary, RCU expedited grace periods check for idle when building
+the bitmask of CPUs that must be IPIed, just before sending each IPI,
+and (either explicitly or implicitly) within the IPI handler.
+
+<h3><a name="Batching via Sequence Counter">
+Batching via Sequence Counter</a></h3>
+
+<p>
+If each grace-period request was carried out separately, expedited
+grace periods would have abysmal scalability and
+problematic high-load characteristics.
+Because each grace-period operation can serve an unlimited number of
+updates, it is important to <i>batch</i> requests, so that a single
+expedited grace-period operation will cover all requests in the
+corresponding batch.
+
+<p>
+This batching is controlled by a sequence counter named
+<tt>->expedited_sequence</tt> in the <tt>rcu_state</tt> structure.
+This counter has an odd value when there is an expedited grace period
+in progress and an even value otherwise, so that dividing the counter
+value by two gives the number of completed grace periods.
+During any given update request, the counter must transition from
+even to odd and then back to even, thus indicating that a grace
+period has elapsed.
+Therefore, if the initial value of the counter is <tt>s</tt>,
+the updater must wait until the counter reaches at least the
+value <tt>(s+3)&~0x1</tt>.
+This counter is managed by the following access functions:
+
+<ol>
+<li> <tt>rcu_exp_gp_seq_start()</tt>, which marks the start of
+ an expedited grace period.
+<li> <tt>rcu_exp_gp_seq_end()</tt>, which marks the end of an
+ expedited grace period.
+<li> <tt>rcu_exp_gp_seq_snap()</tt>, which obtains a snapshot of
+ the counter.
+<li> <tt>rcu_exp_gp_seq_done()</tt>, which returns <tt>true</tt>
+ if a full expedited grace period has elapsed since the
+ corresponding call to <tt>rcu_exp_gp_seq_snap()</tt>.
+</ol>
+
+<p>
+Again, only one request in a given batch need actually carry out
+a grace-period operation, which means there must be an efficient
+way to identify which of many concurrent reqeusts will initiate
+the grace period, and that there be an efficient way for the
+remaining requests to wait for that grace period to complete.
+However, that is the topic of the next section.
+
+<h3><a name="Funnel Locking and Wait/Wakeup">
+Funnel Locking and Wait/Wakeup</a></h3>
+
+<p>
+The natural way to sort out which of a batch of updaters will initiate
+the expedited grace period is to use the <tt>rcu_node</tt> combining
+tree, as implemented by the <tt>exp_funnel_lock()</tt> function.
+The first updater corresponding to a given grace period arriving
+at a given <tt>rcu_node</tt> structure records its desired grace-period
+sequence number in the <tt>->exp_seq_rq</tt> field and moves up
+to the next level in the tree.
+Otherwise, if the <tt>->exp_seq_rq</tt> field already contains
+the sequence number for the desired grace period or some later one,
+the updater blocks on one of four wait queues in the
+<tt>->exp_wq[]</tt> array, using the second-from-bottom
+and third-from bottom bits as an index.
+An <tt>->exp_lock</tt> field in the <tt>rcu_node</tt> structure
+synchronizes access to these fields.
+
+<p>
+An empty <tt>rcu_node</tt> tree is shown in the following diagram,
+with the white cells representing the <tt>->exp_seq_rq</tt> field
+and the red cells representing the elements of the
+<tt>->exp_wq[]</tt> array.
+
+<p><img src="Funnel0.svg" alt="Funnel0.svg" width="75%">
+
+<p>
+The next diagram shows the situation after the arrival of Task A
+and Task B at the leftmost and rightmost leaf <tt>rcu_node</tt>
+structures, respectively.
+The current value of the <tt>rcu_state</tt> structure's
+<tt>->expedited_sequence</tt> field is zero, so adding three and
+clearing the bottom bit results in the value two, which both tasks
+record in the <tt>->exp_seq_rq</tt> field of their respective
+<tt>rcu_node</tt> structures:
+
+<p><img src="Funnel1.svg" alt="Funnel1.svg" width="75%">
+
+<p>
+Each of Tasks A and B will move up to the root
+<tt>rcu_node</tt> structure.
+Suppose that Task A wins, recording its desired grace-period sequence
+number and resulting in the state shown below:
+
+<p><img src="Funnel2.svg" alt="Funnel2.svg" width="75%">
+
+<p>
+Task A now advances to initiate a new grace period, while Task B
+moves up to the root <tt>rcu_node</tt> structure, and, seeing that
+its desired sequence number is already recorded, blocks on
+<tt>->exp_wq[1]</tt>.
+
+<table>
+<tr><th> </th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+ Why <tt>->exp_wq[1]</tt>?
+ Given that the value of these tasks' desired sequence number is
+ two, so shouldn't they instead block on <tt>->exp_wq[2]</tt>?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+ No.
+
+ <p><font color="ffffff">
+ Recall that the bottom bit of the desired sequence number indicates
+ whether or not a grace period is currently in progress.
+ It is therefore necessary to shift the sequence number right one
+ bit position to obtain the number of the grace period.
+ This results in <tt>->exp_wq[1]</tt>.
+</font></td></tr>
+<tr><td> </td></tr>
+</table>
+
+<p>
+If Tasks C and D also arrive at this point, they will compute the
+same desired grace-period sequence number, and see that both leaf
+<tt>rcu_node</tt> structures already have that value recorded.
+They will therefore block on their respective <tt>rcu_node</tt>
+structures' <tt>->exp_wq[1]</tt> fields, as shown below:
+
+<p><img src="Funnel3.svg" alt="Funnel3.svg" width="75%">
+
+<p>
+Task A now acquires the <tt>rcu_state</tt> structure's
+<tt>->exp_mutex</tt> and initiates the grace period, which
+increments <tt>->expedited_sequence</tt>.
+Therefore, if Tasks E and F arrive, they will compute
+a desired sequence number of 4 and will record this value as
+shown below:
+
+<p><img src="Funnel4.svg" alt="Funnel4.svg" width="75%">
+
+<p>
+Tasks E and F will propagate up the <tt>rcu_node</tt>
+combining tree, with Task F blocking on the root <tt>rcu_node</tt>
+structure and Task E wait for Task A to finish so that
+it can start the next grace period.
+The resulting state is as shown below:
+
+<p><img src="Funnel5.svg" alt="Funnel5.svg" width="75%">
+
+<p>
+Once the grace period completes, Task A
+starts waking up the tasks waiting for this grace period to complete,
+increments the <tt>->expedited_sequence</tt>,
+acquires the <tt>->exp_wake_mutex</tt> and then releases the
+<tt>->exp_mutex</tt>.
+This results in the following state:
+
+<p><img src="Funnel6.svg" alt="Funnel6.svg" width="75%">
+
+<p>
+Task E can then acquire <tt>->exp_mutex</tt> and increment
+<tt>->expedited_sequence</tt> to the value three.
+If new tasks G and H arrive and moves up the combining tree at the
+same time, the state will be as follows:
+
+<p><img src="Funnel7.svg" alt="Funnel7.svg" width="75%">
+
+<p>
+Note that three of the root <tt>rcu_node</tt> structure's
+waitqueues are now occupied.
+However, at some point, Task A will wake up the
+tasks blocked on the <tt>->exp_wq</tt> waitqueues, resulting
+in the following state:
+
+<p><img src="Funnel8.svg" alt="Funnel8.svg" width="75%">
+
+<p>
+Execution will continue with Tasks E and H completing
+their grace periods and carrying out their wakeups.
+
+<table>
+<tr><th> </th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+ What happens if Task A takes so long to do its wakeups
+ that Task E's grace period completes?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+ Then Task E will block on the <tt>->exp_wake_mutex</tt>,
+ which will also prevent it from releasing <tt>->exp_mutex</tt>,
+ which in turn will prevent the next grace period from starting.
+ This last is important in preventing overflow of the
+ <tt>->exp_wq[]</tt> array.
+</font></td></tr>
+<tr><td> </td></tr>
+</table>
+
+<h3><a name="Use of Workqueues">Use of Workqueues</a></h3>
+
+<p>
+In earlier implementations, the task requesting the expedited
+grace period also drove it to completion.
+This straightforward approach had the disadvantage of needing to
+account for signals sent to user tasks,
+so more recent implemementations use the Linux kernel's
+<a href="https://www.kernel.org/doc/Documentation/workqueue.txt">workqueues</a>.
+
+<p>
+The requesting task still does counter snapshotting and funnel-lock
+processing, but the task reaching the top of the funnel lock
+does a <tt>schedule_work()</tt> (from <tt>_synchronize_rcu_expedited()</tt>
+so that a workqueue kthread does the actual grace-period processing.
+Because workqueue kthreads do not accept signals, grace-period-wait
+processing need not allow for signals.
+
+In addition, this approach allows wakeups for the previous expedited
+grace period to be overlapped with processing for the next expedited
+grace period.
+Because there are only four sets of waitqueues, it is necessary to
+ensure that the previous grace period's wakeups complete before the
+next grace period's wakeups start.
+This is handled by having the <tt>->exp_mutex</tt>
+guard expedited grace-period processing and the
+<tt>->exp_wake_mutex</tt> guard wakeups.
+The key point is that the <tt>->exp_mutex</tt> is not released
+until the first wakeup is complete, which means that the
+<tt>->exp_wake_mutex</tt> has already been acquired at that point.
+This approach ensures that the previous grace period's wakeups can
+be carried out while the current grace period is in process, but
+that these wakeups will complete before the next grace period starts.
+This means that only three waitqueues are required, guaranteeing that
+the four that are provided are sufficient.
+
+<h3><a name="Stall Warnings">Stall Warnings</a></h3>
+
+<p>
+Expediting grace periods does nothing to speed things up when RCU
+readers take too long, and therefore expedited grace periods check
+for stalls just as normal grace periods do.
+
+<table>
+<tr><th> </th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+ But why not just let the normal grace-period machinery
+ detect the stalls, given that a given reader must block
+ both normal and expedited grace periods?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+ Because it is quite possible that at a given time there
+ is no normal grace period in progress, in which case the
+ normal grace period cannot emit a stall warning.
+</font></td></tr>
+<tr><td> </td></tr>
+</table>
+
+The <tt>synchronize_sched_expedited_wait()</tt> function loops waiting
+for the expedited grace period to end, but with a timeout set to the
+current RCU CPU stall-warning time.
+If this time is exceeded, any CPUs or <tt>rcu_node</tt> structures
+blocking the current grace period are printed.
+Each stall warning results in another pass through the loop, but the
+second and subsequent passes use longer stall times.
+
+<h3><a name="Summary">
+Summary</a></h3>
+
+<p>
+Expedited grace periods use a sequence-number approach to promote
+batching, so that a single grace-period operation can serve numerous
+requests.
+A funnel lock is used to efficiently identify the one task out of
+a concurrent group that will request the grace period.
+All members of the group will block on waitqueues provided in
+the <tt>rcu_node</tt> structure.
+The actual grace-period processing is carried out by a workqueue.
+
+<p>
+CPU-hotplug operations are noted lazily in order to prevent the need
+for tight synchronization between expedited grace periods and
+CPU-hotplug operations.
+The dyntick-idle counters are used to avoid sending IPIs to idle CPUs,
+at least in the common case.
+RCU-preempt and RCU-sched use different IPI handlers and different
+code to respond to the state changes carried out by those handlers,
+but otherwise use common code.
+
+<p>
+Quiescent states are tracked using the <tt>rcu_node</tt> tree,
+and once all necessary quiescent states have been reported,
+all tasks waiting on this expedited grace period are awakened.
+A pair of mutexes are used to allow one grace period's wakeups
+to proceed concurrently with the next grace period's processing.
+
+<p>
+This combination of mechanisms allows expedited grace periods to
+run reasonably efficiently.
+However, for non-time-critical tasks, normal grace periods should be
+used instead because their longer duration permits much higher
+degrees of batching, and thus much lower per-request overheads.
+
+</body></html>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel0.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel0.svg
new file mode 100644
index 0000000..98af665
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel0.svg
@@ -0,0 +1,275 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="490.05093"
+ height="125.78741"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="Funnel0.svg">
+ <defs
+ id="defs4">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path3792"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart"
+ style="overflow:visible">
+ <path
+ id="path3789"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart-4"
+ style="overflow:visible">
+ <path
+ id="path3789-9"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ id="path3792-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="1.3670394"
+ inkscape:cx="201.06495"
+ inkscape:cy="-86.548414"
+ inkscape:document-units="px"
+ inkscape:current-layer="layer1"
+ showgrid="false"
+ inkscape:window-width="1351"
+ inkscape:window-height="836"
+ inkscape:window-x="171"
+ inkscape:window-y="279"
+ inkscape:window-maximized="0"
+ fit-margin-top="5"
+ fit-margin-left="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5" />
+ <metadata
+ id="metadata7">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Layer 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-117.08462,-249.92053)">
+ <flowRoot
+ xml:space="preserve"
+ id="flowRoot2985"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+ id="flowRegion2987"><rect
+ id="rect2989"
+ width="82.85714"
+ height="11.428572"
+ x="240"
+ y="492.36218" /></flowRegion><flowPara
+ id="flowPara2991" /></flowRoot> <text
+ xml:space="preserve"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+ x="362.371"
+ y="262.51819"
+ id="text4441"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4443"
+ x="362.371"
+ y="262.51819">->expedited_sequence: 0</tspan></text>
+ <rect
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101"
+ width="43.158947"
+ height="26.33428"
+ x="253.55223"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3"
+ width="43.158947"
+ height="26.33428"
+ x="297.04141"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6"
+ width="43.158947"
+ height="26.33428"
+ x="427.509"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7"
+ width="43.158947"
+ height="26.33428"
+ x="384.01981"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7-5"
+ width="43.158947"
+ height="26.33428"
+ x="340.53061"
+ y="275.07489" />
+ <g
+ id="g3997"
+ transform="translate(-0.87295532,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.45404"
+ y="360.25174"
+ id="text3013"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015"
+ x="145.45404"
+ y="360.25174"
+ style="font-size:10px">:0</tspan></text>
+ </g>
+ <g
+ id="g3997-7"
+ transform="translate(260.06223,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35-0"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9-3"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1-6"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2-0"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.45404"
+ y="360.25174"
+ id="text3013-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6"
+ x="145.45404"
+ y="360.25174"
+ style="font-size:10px">:0</tspan></text>
+ </g>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel1.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel1.svg
new file mode 100644
index 0000000..e0184a3
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel1.svg
@@ -0,0 +1,275 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="490.05093"
+ height="125.78741"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="Funnel1.svg">
+ <defs
+ id="defs4">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path3792"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart"
+ style="overflow:visible">
+ <path
+ id="path3789"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart-4"
+ style="overflow:visible">
+ <path
+ id="path3789-9"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ id="path3792-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="1.3670394"
+ inkscape:cx="201.06495"
+ inkscape:cy="-86.548414"
+ inkscape:document-units="px"
+ inkscape:current-layer="g3997-7"
+ showgrid="false"
+ inkscape:window-width="1351"
+ inkscape:window-height="836"
+ inkscape:window-x="363"
+ inkscape:window-y="336"
+ inkscape:window-maximized="0"
+ fit-margin-top="5"
+ fit-margin-left="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5" />
+ <metadata
+ id="metadata7">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Layer 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-117.08462,-249.92053)">
+ <flowRoot
+ xml:space="preserve"
+ id="flowRoot2985"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+ id="flowRegion2987"><rect
+ id="rect2989"
+ width="82.85714"
+ height="11.428572"
+ x="240"
+ y="492.36218" /></flowRegion><flowPara
+ id="flowPara2991" /></flowRoot> <text
+ xml:space="preserve"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+ x="362.371"
+ y="262.51819"
+ id="text4441"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4443"
+ x="362.371"
+ y="262.51819">->expedited_sequence: 0</tspan></text>
+ <rect
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101"
+ width="43.158947"
+ height="26.33428"
+ x="253.55223"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3"
+ width="43.158947"
+ height="26.33428"
+ x="297.04141"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6"
+ width="43.158947"
+ height="26.33428"
+ x="427.509"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7"
+ width="43.158947"
+ height="26.33428"
+ x="384.01981"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7-5"
+ width="43.158947"
+ height="26.33428"
+ x="340.53061"
+ y="275.07489" />
+ <g
+ id="g3997"
+ transform="translate(-0.87295532,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="146.00092"
+ y="360.25174"
+ id="text3013"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015"
+ x="146.00092"
+ y="360.25174"
+ style="font-size:10px">A:2</tspan></text>
+ </g>
+ <g
+ id="g3997-7"
+ transform="translate(260.06223,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35-0"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9-3"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1-6"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2-0"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.54926"
+ y="360.25174"
+ id="text3013-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6"
+ x="145.54926"
+ y="360.25174"
+ style="font-size:10px">B:2</tspan></text>
+ </g>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel2.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel2.svg
new file mode 100644
index 0000000..1bc3fed
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel2.svg
@@ -0,0 +1,287 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="490.05093"
+ height="125.78741"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="Funnel2.svg">
+ <defs
+ id="defs4">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path3792"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart"
+ style="overflow:visible">
+ <path
+ id="path3789"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart-4"
+ style="overflow:visible">
+ <path
+ id="path3789-9"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ id="path3792-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="1.3670394"
+ inkscape:cx="114.01552"
+ inkscape:cy="-86.548414"
+ inkscape:document-units="px"
+ inkscape:current-layer="g3997-7"
+ showgrid="false"
+ inkscape:window-width="1351"
+ inkscape:window-height="836"
+ inkscape:window-x="363"
+ inkscape:window-y="336"
+ inkscape:window-maximized="0"
+ fit-margin-top="5"
+ fit-margin-left="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5" />
+ <metadata
+ id="metadata7">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Layer 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-117.08462,-249.92053)">
+ <flowRoot
+ xml:space="preserve"
+ id="flowRoot2985"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+ id="flowRegion2987"><rect
+ id="rect2989"
+ width="82.85714"
+ height="11.428572"
+ x="240"
+ y="492.36218" /></flowRegion><flowPara
+ id="flowPara2991" /></flowRoot> <text
+ xml:space="preserve"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+ x="362.371"
+ y="262.51819"
+ id="text4441"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4443"
+ x="362.371"
+ y="262.51819">->expedited_sequence: 0</tspan></text>
+ <rect
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101"
+ width="43.158947"
+ height="26.33428"
+ x="253.55223"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3"
+ width="43.158947"
+ height="26.33428"
+ x="297.04141"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6"
+ width="43.158947"
+ height="26.33428"
+ x="427.509"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7"
+ width="43.158947"
+ height="26.33428"
+ x="384.01981"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7-5"
+ width="43.158947"
+ height="26.33428"
+ x="340.53061"
+ y="275.07489" />
+ <g
+ id="g3997"
+ transform="translate(-0.87295532,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="146.00092"
+ y="360.25174"
+ id="text3013"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015"
+ x="146.00092"
+ y="360.25174"
+ style="font-size:10px">:2</tspan></text>
+ </g>
+ <g
+ id="g3997-7"
+ transform="translate(260.06223,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35-0"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9-3"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1-6"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2-0"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.54926"
+ y="360.25174"
+ id="text3013-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6"
+ x="145.54926"
+ y="360.25174"
+ style="font-size:10px">B:2</tspan></text>
+ </g>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="275.59558"
+ y="291.95297"
+ id="text3013-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-7"
+ x="275.59558"
+ y="291.95297"
+ style="font-size:10px">A:2</tspan></text>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel3.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel3.svg
new file mode 100644
index 0000000..6d8a1bf
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel3.svg
@@ -0,0 +1,323 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="490.05093"
+ height="125.78741"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="Funnel3.svg">
+ <defs
+ id="defs4">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path3792"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart"
+ style="overflow:visible">
+ <path
+ id="path3789"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart-4"
+ style="overflow:visible">
+ <path
+ id="path3789-9"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ id="path3792-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="1.3670394"
+ inkscape:cx="114.01552"
+ inkscape:cy="-86.548414"
+ inkscape:document-units="px"
+ inkscape:current-layer="layer1"
+ showgrid="false"
+ inkscape:window-width="1351"
+ inkscape:window-height="836"
+ inkscape:window-x="68"
+ inkscape:window-y="180"
+ inkscape:window-maximized="0"
+ fit-margin-top="5"
+ fit-margin-left="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5" />
+ <metadata
+ id="metadata7">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Layer 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-117.08462,-249.92053)">
+ <flowRoot
+ xml:space="preserve"
+ id="flowRoot2985"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+ id="flowRegion2987"><rect
+ id="rect2989"
+ width="82.85714"
+ height="11.428572"
+ x="240"
+ y="492.36218" /></flowRegion><flowPara
+ id="flowPara2991" /></flowRoot> <text
+ xml:space="preserve"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+ x="362.371"
+ y="262.51819"
+ id="text4441"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4443"
+ x="362.371"
+ y="262.51819">->expedited_sequence: 0 GP: A</tspan></text>
+ <rect
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101"
+ width="43.158947"
+ height="26.33428"
+ x="253.55223"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3"
+ width="43.158947"
+ height="26.33428"
+ x="297.04141"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6"
+ width="43.158947"
+ height="26.33428"
+ x="427.509"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7"
+ width="43.158947"
+ height="26.33428"
+ x="384.01981"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7-5"
+ width="43.158947"
+ height="26.33428"
+ x="340.53061"
+ y="275.07489" />
+ <g
+ id="g3997"
+ transform="translate(-0.87295532,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="146.00092"
+ y="360.25174"
+ id="text3013"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015"
+ x="146.00092"
+ y="360.25174"
+ style="font-size:10px">:2</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.51051"
+ y="360.18094"
+ id="text3013-3-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6"
+ x="232.51051"
+ y="360.18094"
+ style="font-size:10px">C</tspan></text>
+ </g>
+ <g
+ id="g3019"
+ transform="translate(260.06223,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35-0"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62-9"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9-3"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1-6"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2-0"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.54926"
+ y="360.25174"
+ id="text3013-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6"
+ x="145.54926"
+ y="360.25174"
+ style="font-size:10px">:2</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.31764"
+ y="360.18582"
+ id="text3013-3-3-7"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6-5"
+ x="232.31764"
+ y="360.18582"
+ style="font-size:10px">D</tspan></text>
+ </g>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="275.59558"
+ y="291.95297"
+ id="text3013-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-7"
+ x="275.59558"
+ y="291.95297"
+ style="font-size:10px">:2</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="361.97092"
+ y="291.88705"
+ id="text3013-3-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7"
+ x="361.97092"
+ y="291.88705"
+ style="font-size:10px">B</tspan></text>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel4.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel4.svg
new file mode 100644
index 0000000..44018fd
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel4.svg
@@ -0,0 +1,323 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="490.05093"
+ height="125.78741"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="Funnel4.svg">
+ <defs
+ id="defs4">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path3792"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart"
+ style="overflow:visible">
+ <path
+ id="path3789"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart-4"
+ style="overflow:visible">
+ <path
+ id="path3789-9"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ id="path3792-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="1.3670394"
+ inkscape:cx="114.01552"
+ inkscape:cy="-86.548414"
+ inkscape:document-units="px"
+ inkscape:current-layer="layer1"
+ showgrid="false"
+ inkscape:window-width="1351"
+ inkscape:window-height="836"
+ inkscape:window-x="68"
+ inkscape:window-y="180"
+ inkscape:window-maximized="0"
+ fit-margin-top="5"
+ fit-margin-left="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5" />
+ <metadata
+ id="metadata7">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Layer 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-117.08462,-249.92053)">
+ <flowRoot
+ xml:space="preserve"
+ id="flowRoot2985"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+ id="flowRegion2987"><rect
+ id="rect2989"
+ width="82.85714"
+ height="11.428572"
+ x="240"
+ y="492.36218" /></flowRegion><flowPara
+ id="flowPara2991" /></flowRoot> <text
+ xml:space="preserve"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+ x="362.371"
+ y="262.51819"
+ id="text4441"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4443"
+ x="362.371"
+ y="262.51819">->expedited_sequence: 1 GP: A</tspan></text>
+ <rect
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101"
+ width="43.158947"
+ height="26.33428"
+ x="253.55223"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3"
+ width="43.158947"
+ height="26.33428"
+ x="297.04141"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6"
+ width="43.158947"
+ height="26.33428"
+ x="427.509"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7"
+ width="43.158947"
+ height="26.33428"
+ x="384.01981"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7-5"
+ width="43.158947"
+ height="26.33428"
+ x="340.53061"
+ y="275.07489" />
+ <g
+ id="g3997"
+ transform="translate(-0.87295532,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="146.00092"
+ y="360.25174"
+ id="text3013"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015"
+ x="146.00092"
+ y="360.25174"
+ style="font-size:10px">E:4</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.51051"
+ y="360.18094"
+ id="text3013-3-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6"
+ x="232.51051"
+ y="360.18094"
+ style="font-size:10px">C</tspan></text>
+ </g>
+ <g
+ id="g3019"
+ transform="translate(260.06223,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35-0"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62-9"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9-3"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1-6"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2-0"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.54926"
+ y="360.25174"
+ id="text3013-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6"
+ x="145.54926"
+ y="360.25174"
+ style="font-size:10px">F:4</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.31764"
+ y="360.18582"
+ id="text3013-3-3-7"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6-5"
+ x="232.31764"
+ y="360.18582"
+ style="font-size:10px">D</tspan></text>
+ </g>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="275.59558"
+ y="291.95297"
+ id="text3013-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-7"
+ x="275.59558"
+ y="291.95297"
+ style="font-size:10px">:2</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="361.97092"
+ y="291.88705"
+ id="text3013-3-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7"
+ x="361.97092"
+ y="291.88705"
+ style="font-size:10px">B</tspan></text>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel5.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel5.svg
new file mode 100644
index 0000000..e5eef50
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel5.svg
@@ -0,0 +1,335 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="490.05093"
+ height="125.78741"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="Funnel5.svg">
+ <defs
+ id="defs4">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path3792"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart"
+ style="overflow:visible">
+ <path
+ id="path3789"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart-4"
+ style="overflow:visible">
+ <path
+ id="path3789-9"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ id="path3792-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="1.3670394"
+ inkscape:cx="114.01552"
+ inkscape:cy="-86.548414"
+ inkscape:document-units="px"
+ inkscape:current-layer="layer1"
+ showgrid="false"
+ inkscape:window-width="1351"
+ inkscape:window-height="836"
+ inkscape:window-x="68"
+ inkscape:window-y="180"
+ inkscape:window-maximized="0"
+ fit-margin-top="5"
+ fit-margin-left="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5" />
+ <metadata
+ id="metadata7">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Layer 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-117.08462,-249.92053)">
+ <flowRoot
+ xml:space="preserve"
+ id="flowRoot2985"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+ id="flowRegion2987"><rect
+ id="rect2989"
+ width="82.85714"
+ height="11.428572"
+ x="240"
+ y="492.36218" /></flowRegion><flowPara
+ id="flowPara2991" /></flowRoot> <text
+ xml:space="preserve"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+ x="362.371"
+ y="262.51819"
+ id="text4441"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4443"
+ x="362.371"
+ y="262.51819">->expedited_sequence: 1 GP: A,E</tspan></text>
+ <rect
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101"
+ width="43.158947"
+ height="26.33428"
+ x="253.55223"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3"
+ width="43.158947"
+ height="26.33428"
+ x="297.04141"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6"
+ width="43.158947"
+ height="26.33428"
+ x="427.509"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7"
+ width="43.158947"
+ height="26.33428"
+ x="384.01981"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7-5"
+ width="43.158947"
+ height="26.33428"
+ x="340.53061"
+ y="275.07489" />
+ <g
+ id="g3997"
+ transform="translate(-0.87295532,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="146.00092"
+ y="360.25174"
+ id="text3013"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015"
+ x="146.00092"
+ y="360.25174"
+ style="font-size:10px">:4</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.51051"
+ y="360.18094"
+ id="text3013-3-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6"
+ x="232.51051"
+ y="360.18094"
+ style="font-size:10px">C</tspan></text>
+ </g>
+ <g
+ id="g3019"
+ transform="translate(260.06223,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35-0"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62-9"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9-3"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1-6"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2-0"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.54926"
+ y="360.25174"
+ id="text3013-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6"
+ x="145.54926"
+ y="360.25174"
+ style="font-size:10px">:4</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.31764"
+ y="360.18582"
+ id="text3013-3-3-7"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6-5"
+ x="232.31764"
+ y="360.18582"
+ style="font-size:10px">D</tspan></text>
+ </g>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="275.59558"
+ y="291.95297"
+ id="text3013-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-7"
+ x="275.59558"
+ y="291.95297"
+ style="font-size:10px">:4</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="361.97092"
+ y="291.88705"
+ id="text3013-3-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7"
+ x="361.97092"
+ y="291.88705"
+ style="font-size:10px">B</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="405.40396"
+ y="291.88705"
+ id="text3013-3-36-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7-6"
+ x="405.40396"
+ y="291.88705"
+ style="font-size:10px">F</tspan></text>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel6.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel6.svg
new file mode 100644
index 0000000..fbd2c18
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel6.svg
@@ -0,0 +1,335 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="490.05093"
+ height="125.78741"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="Funnel6.svg">
+ <defs
+ id="defs4">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path3792"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart"
+ style="overflow:visible">
+ <path
+ id="path3789"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart-4"
+ style="overflow:visible">
+ <path
+ id="path3789-9"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ id="path3792-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="1.3670394"
+ inkscape:cx="114.01552"
+ inkscape:cy="-86.548414"
+ inkscape:document-units="px"
+ inkscape:current-layer="layer1"
+ showgrid="false"
+ inkscape:window-width="1351"
+ inkscape:window-height="836"
+ inkscape:window-x="68"
+ inkscape:window-y="180"
+ inkscape:window-maximized="0"
+ fit-margin-top="5"
+ fit-margin-left="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5" />
+ <metadata
+ id="metadata7">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Layer 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-117.08462,-249.92053)">
+ <flowRoot
+ xml:space="preserve"
+ id="flowRoot2985"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+ id="flowRegion2987"><rect
+ id="rect2989"
+ width="82.85714"
+ height="11.428572"
+ x="240"
+ y="492.36218" /></flowRegion><flowPara
+ id="flowPara2991" /></flowRoot> <text
+ xml:space="preserve"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+ x="362.371"
+ y="262.51819"
+ id="text4441"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4443"
+ x="362.371"
+ y="262.51819">->expedited_sequence: 2 GP: E Wakeup: A</tspan></text>
+ <rect
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101"
+ width="43.158947"
+ height="26.33428"
+ x="253.55223"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3"
+ width="43.158947"
+ height="26.33428"
+ x="297.04141"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6"
+ width="43.158947"
+ height="26.33428"
+ x="427.509"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7"
+ width="43.158947"
+ height="26.33428"
+ x="384.01981"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7-5"
+ width="43.158947"
+ height="26.33428"
+ x="340.53061"
+ y="275.07489" />
+ <g
+ id="g3997"
+ transform="translate(-0.87295532,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="146.00092"
+ y="360.25174"
+ id="text3013"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015"
+ x="146.00092"
+ y="360.25174"
+ style="font-size:10px">:4</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.51051"
+ y="360.18094"
+ id="text3013-3-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6"
+ x="232.51051"
+ y="360.18094"
+ style="font-size:10px">C</tspan></text>
+ </g>
+ <g
+ id="g3019"
+ transform="translate(260.06223,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35-0"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62-9"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9-3"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1-6"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2-0"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.54926"
+ y="360.25174"
+ id="text3013-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6"
+ x="145.54926"
+ y="360.25174"
+ style="font-size:10px">:4</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.31764"
+ y="360.18582"
+ id="text3013-3-3-7"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6-5"
+ x="232.31764"
+ y="360.18582"
+ style="font-size:10px">D</tspan></text>
+ </g>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="275.59558"
+ y="291.95297"
+ id="text3013-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-7"
+ x="275.59558"
+ y="291.95297"
+ style="font-size:10px">:4</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="361.97092"
+ y="291.88705"
+ id="text3013-3-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7"
+ x="361.97092"
+ y="291.88705"
+ style="font-size:10px">B</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="405.40396"
+ y="291.88705"
+ id="text3013-3-36-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7-6"
+ x="405.40396"
+ y="291.88705"
+ style="font-size:10px">F</tspan></text>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel7.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel7.svg
new file mode 100644
index 0000000..502e159
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel7.svg
@@ -0,0 +1,347 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="490.05093"
+ height="125.78741"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="Funnel7.svg">
+ <defs
+ id="defs4">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path3792"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart"
+ style="overflow:visible">
+ <path
+ id="path3789"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart-4"
+ style="overflow:visible">
+ <path
+ id="path3789-9"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ id="path3792-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="1.3670394"
+ inkscape:cx="114.01552"
+ inkscape:cy="-86.548414"
+ inkscape:document-units="px"
+ inkscape:current-layer="layer1"
+ showgrid="false"
+ inkscape:window-width="1351"
+ inkscape:window-height="836"
+ inkscape:window-x="68"
+ inkscape:window-y="180"
+ inkscape:window-maximized="0"
+ fit-margin-top="5"
+ fit-margin-left="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5" />
+ <metadata
+ id="metadata7">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Layer 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-117.08462,-249.92053)">
+ <flowRoot
+ xml:space="preserve"
+ id="flowRoot2985"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+ id="flowRegion2987"><rect
+ id="rect2989"
+ width="82.85714"
+ height="11.428572"
+ x="240"
+ y="492.36218" /></flowRegion><flowPara
+ id="flowPara2991" /></flowRoot> <text
+ xml:space="preserve"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+ x="362.371"
+ y="262.51819"
+ id="text4441"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4443"
+ x="362.371"
+ y="262.51819">->expedited_sequence: 3 GP: E,H Wakeup: A</tspan></text>
+ <rect
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101"
+ width="43.158947"
+ height="26.33428"
+ x="253.55223"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3"
+ width="43.158947"
+ height="26.33428"
+ x="297.04141"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101-3-6"
+ width="43.158947"
+ height="26.33428"
+ x="427.509"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7"
+ width="43.158947"
+ height="26.33428"
+ x="384.01981"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7-5"
+ width="43.158947"
+ height="26.33428"
+ x="340.53061"
+ y="275.07489" />
+ <g
+ id="g3997"
+ transform="translate(-0.87295532,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="146.00092"
+ y="360.25174"
+ id="text3013"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015"
+ x="146.00092"
+ y="360.25174"
+ style="font-size:10px">:4</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.51051"
+ y="360.18094"
+ id="text3013-3-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6"
+ x="232.51051"
+ y="360.18094"
+ style="font-size:10px">C</tspan></text>
+ </g>
+ <g
+ id="g3019"
+ transform="translate(260.06223,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35-0"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62-9"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9-3"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1-6"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2-0"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.54926"
+ y="360.25174"
+ id="text3013-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6"
+ x="145.54926"
+ y="360.25174"
+ style="font-size:10px">:6</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="232.31764"
+ y="360.18582"
+ id="text3013-3-3-7"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-6-5"
+ x="232.31764"
+ y="360.18582"
+ style="font-size:10px">D</tspan></text>
+ </g>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="275.59558"
+ y="291.95297"
+ id="text3013-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-7"
+ x="275.59558"
+ y="291.95297"
+ style="font-size:10px">:6</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="361.97092"
+ y="291.88705"
+ id="text3013-3-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7"
+ x="361.97092"
+ y="291.88705"
+ style="font-size:10px">B</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="405.40396"
+ y="291.88705"
+ id="text3013-3-36-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7-6"
+ x="405.40396"
+ y="291.88705"
+ style="font-size:10px">F</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="449.22031"
+ y="291.88217"
+ id="text3013-3-36-3-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7-6-6"
+ x="449.22031"
+ y="291.88217"
+ style="font-size:10px">G</tspan></text>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel8.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel8.svg
new file mode 100644
index 0000000..6774015
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel8.svg
@@ -0,0 +1,311 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="490.05093"
+ height="125.78741"
+ id="svg2"
+ version="1.1"
+ inkscape:version="0.48.4 r9939"
+ sodipodi:docname="Funnel8.svg">
+ <defs
+ id="defs4">
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend"
+ style="overflow:visible">
+ <path
+ id="path3792"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart"
+ style="overflow:visible">
+ <path
+ id="path3789"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lstart"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lstart-4"
+ style="overflow:visible">
+ <path
+ id="path3789-9"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(1.1,0,0,1.1,1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ <marker
+ inkscape:stockid="Arrow2Lend"
+ orient="auto"
+ refY="0"
+ refX="0"
+ id="Arrow2Lend-4"
+ style="overflow:visible">
+ <path
+ id="path3792-4"
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+ inkscape:connector-curvature="0" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="1.3670394"
+ inkscape:cx="114.01552"
+ inkscape:cy="-86.548414"
+ inkscape:document-units="px"
+ inkscape:current-layer="layer1"
+ showgrid="false"
+ inkscape:window-width="1351"
+ inkscape:window-height="836"
+ inkscape:window-x="68"
+ inkscape:window-y="180"
+ inkscape:window-maximized="0"
+ fit-margin-top="5"
+ fit-margin-left="5"
+ fit-margin-right="5"
+ fit-margin-bottom="5" />
+ <metadata
+ id="metadata7">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title />
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Layer 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-117.08462,-249.92053)">
+ <flowRoot
+ xml:space="preserve"
+ id="flowRoot2985"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+ id="flowRegion2987"><rect
+ id="rect2989"
+ width="82.85714"
+ height="11.428572"
+ x="240"
+ y="492.36218" /></flowRegion><flowPara
+ id="flowPara2991" /></flowRoot> <text
+ xml:space="preserve"
+ style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+ x="362.371"
+ y="262.51819"
+ id="text4441"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan4443"
+ x="362.371"
+ y="262.51819">->expedited_sequence: 3 GP: E,H</tspan></text>
+ <rect
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101"
+ width="43.158947"
+ height="26.33428"
+ x="253.55223"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3"
+ width="43.158947"
+ height="26.33428"
+ x="297.04141"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+ id="rect3101-3-6"
+ width="43.158947"
+ height="26.33428"
+ x="427.509"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7"
+ width="43.158947"
+ height="26.33428"
+ x="384.01981"
+ y="275.07489" />
+ <rect
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+ id="rect3101-3-6-7-5"
+ width="43.158947"
+ height="26.33428"
+ x="340.53061"
+ y="275.07489" />
+ <g
+ id="g3997"
+ transform="translate(-0.87295532,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2"
+ style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="146.00092"
+ y="360.25174"
+ id="text3013"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015"
+ x="146.00092"
+ y="360.25174"
+ style="font-size:10px">:4</tspan></text>
+ </g>
+ <g
+ id="g3019"
+ transform="translate(260.06223,0)">
+ <rect
+ y="343.37366"
+ x="123.95757"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-35-0"
+ style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="167.44673"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-62-9"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="297.91437"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-9-3"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="254.42516"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-1-6"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <rect
+ y="343.37366"
+ x="210.93593"
+ height="26.33428"
+ width="43.158947"
+ id="rect3101-3-6-7-5-2-0"
+ style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="145.54926"
+ y="360.25174"
+ id="text3013-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6"
+ x="145.54926"
+ y="360.25174"
+ style="font-size:10px">:6</tspan></text>
+ </g>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="275.59558"
+ y="291.95297"
+ id="text3013-36"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-7"
+ x="275.59558"
+ y="291.95297"
+ style="font-size:10px">:6</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="405.40396"
+ y="291.88705"
+ id="text3013-3-36-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7-6"
+ x="405.40396"
+ y="291.88705"
+ style="font-size:10px">F</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+ x="449.22031"
+ y="291.88217"
+ id="text3013-3-36-3-3"
+ sodipodi:linespacing="125%"><tspan
+ sodipodi:role="line"
+ id="tspan3015-6-7-6-6"
+ x="449.22031"
+ y="291.88217"
+ style="font-size:10px">G</tspan></text>
+ </g>
+</svg>
diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
index 39bcb74..2159349 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.html
+++ b/Documentation/RCU/Design/Requirements/Requirements.html
@@ -1480,7 +1480,7 @@
<p>
Furthermore, uncertainty about external state is inherent in many cases.
-For example, a pair of veternarians might use heartbeat to determine
+For example, a pair of veterinarians might use heartbeat to determine
whether or not a given cat was alive.
But how long should they wait after the last heartbeat to decide that
the cat is in fact dead?
@@ -1489,9 +1489,9 @@
and life more than 100 times per minute.
Moreover, just as with human beings, a cat's heart might stop for
some period of time, so the exact wait period is a judgment call.
-One of our pair of veternarians might wait 30 seconds before pronouncing
+One of our pair of veterinarians might wait 30 seconds before pronouncing
the cat dead, while the other might insist on waiting a full minute.
-The two veternarians would then disagree on the state of the cat during
+The two veterinarians would then disagree on the state of the cat during
the final 30 seconds of the minute following the last heartbeat.
<p>
@@ -1945,7 +1945,7 @@
<ol>
<li> It is all too easy to forget to use <tt>rcu_read_lock()</tt>
everywhere that it is needed, so kernels built with
- <tt>CONFIG_PROVE_RCU=y</tt> will spat if
+ <tt>CONFIG_PROVE_RCU=y</tt> will splat if
<tt>rcu_dereference()</tt> is used outside of an
RCU read-side critical section.
Update-side code can use <tt>rcu_dereference_protected()</tt>,
@@ -2421,7 +2421,7 @@
<li> Blocking is prohibited.
In practice, this is not a serious restriction given that idle
tasks are prohibited from blocking to begin with.
-<li> Although nesting <tt>RCU_NONIDLE()</tt> is permited, they cannot
+<li> Although nesting <tt>RCU_NONIDLE()</tt> is permitted, they cannot
nest indefinitely deeply.
However, given that they can be nested on the order of a million
deep, even on 32-bit systems, this should not be a serious
@@ -2885,7 +2885,7 @@
<h3><a name="Tasks RCU">Tasks RCU</a></h3>
<p>
-Some forms of tracing use “tramopolines” to handle the
+Some forms of tracing use “trampolines” to handle the
binary rewriting required to install different types of probes.
It would be good to be able to free old trampolines, which sounds
like a job for some form of RCU.
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 00a3a38..6549012 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -237,7 +237,7 @@
The output of "cat rcu/rcu_preempt/rcuexp" looks as follows:
-s=21872 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872
+s=21872 wd1=0 wd2=0 wd3=5 enq=0 sc=21872
These fields are as follows:
@@ -249,9 +249,6 @@
completed an expedited grace period that satisfies the attempted
request. "Our work is done."
-o "n" is number of times that a concurrent CPU-hotplug operation
- forced a fallback to a normal grace period.
-
o "enq" is the number of quiescent states still outstanding.
o "sc" is the number of times that the attempt to start a
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index be7c0d9..10d86d9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -549,15 +549,6 @@
loops can be debugged more effectively on production
systems.
- clocksource.arm_arch_timer.fsl-a008585=
- [ARM64]
- Format: <bool>
- Enable/disable the workaround of Freescale/NXP
- erratum A-008585. This can be useful for KVM
- guests, if the guest device tree doesn't show the
- erratum. If unspecified, the workaround is
- enabled based on the device tree.
-
clearcpuid=BITNUM [X86]
Disable CPUID feature X for the kernel. See
arch/x86/include/asm/cpufeatures.h for the valid bit
@@ -3278,6 +3269,13 @@
Lazy RCU callbacks are those which RCU can
prove do nothing more than free memory.
+ rcutree.rcu_kick_kthreads= [KNL]
+ Cause the grace-period kthread to get an extra
+ wake_up() if it sleeps three times longer than
+ it should at force-quiescent-state time.
+ This wake_up() will be accompanied by a
+ WARN_ONCE() splat and an ftrace_dump().
+
rcuperf.gp_exp= [KNL]
Measure performance of expedited synchronous
grace-period primitives.
diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/ras.rst
index d71340e8..9939348 100644
--- a/Documentation/admin-guide/ras.rst
+++ b/Documentation/admin-guide/ras.rst
@@ -438,11 +438,13 @@
│ │ ├── ce_count
│ │ ├── ce_noinfo_count
│ │ ├── dimm0
+ │ │ │ ├── dimm_ce_count
│ │ │ ├── dimm_dev_type
│ │ │ ├── dimm_edac_mode
│ │ │ ├── dimm_label
│ │ │ ├── dimm_location
│ │ │ ├── dimm_mem_type
+ │ │ │ ├── dimm_ue_count
│ │ │ ├── size
│ │ │ └── uevent
│ │ ├── max_location
@@ -457,11 +459,13 @@
│ │ ├── ce_count
│ │ ├── ce_noinfo_count
│ │ ├── dimm0
+ │ │ │ ├── dimm_ce_count
│ │ │ ├── dimm_dev_type
│ │ │ ├── dimm_edac_mode
│ │ │ ├── dimm_label
│ │ │ ├── dimm_location
│ │ │ ├── dimm_mem_type
+ │ │ │ ├── dimm_ue_count
│ │ │ ├── size
│ │ │ └── uevent
│ │ ├── max_location
@@ -483,6 +487,22 @@
This attribute file displays, in count of megabytes, the memory
that this csrow contains.
+- ``dimm_ue_count`` - Uncorrectable Errors count attribute file
+
+ This attribute file displays the total count of uncorrectable
+ errors that have occurred on this DIMM. If panic_on_ue is set
+ this counter will not have a chance to increment, since EDAC
+ will panic the system.
+
+- ``dimm_ce_count`` - Correctable Errors count attribute file
+
+ This attribute file displays the total count of correctable
+ errors that have occurred on this DIMM. This count is very
+ important to examine. CEs provide early indications that a
+ DIMM is beginning to fail. This count field should be
+ monitored for non-zero values and report such information
+ to the system administrator.
+
- ``dimm_dev_type`` - Device type attribute file
This attribute file will display what type of DRAM device is
diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt
index ad440a2..e926aea 100644
--- a/Documentation/devicetree/bindings/arm/arch_timer.txt
+++ b/Documentation/devicetree/bindings/arm/arch_timer.txt
@@ -31,6 +31,12 @@
This also affects writes to the tval register, due to the implicit
counter read.
+- hisilicon,erratum-161010101 : A boolean property. Indicates the
+ presence of Hisilicon erratum 161010101, which says that reading the
+ counters is unreliable in some cases, and reads may return a value 32
+ beyond the correct value. This also affects writes to the tval
+ registers, due to the implicit counter read.
+
** Optional properties:
- arm,cpu-registers-not-fw-configured : Firmware does not initialize
diff --git a/Documentation/devicetree/bindings/hwmon/adc128d818.txt b/Documentation/devicetree/bindings/hwmon/adc128d818.txt
new file mode 100644
index 0000000..08bab0e
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/adc128d818.txt
@@ -0,0 +1,38 @@
+TI ADC128D818 ADC System Monitor With Temperature Sensor
+--------------------------------------------------------
+
+Operation modes:
+
+ - Mode 0: 7 single-ended voltage readings (IN0-IN6),
+ 1 temperature reading (internal)
+ - Mode 1: 8 single-ended voltage readings (IN0-IN7),
+ no temperature
+ - Mode 2: 4 pseudo-differential voltage readings
+ (IN0-IN1, IN3-IN2, IN4-IN5, IN7-IN6),
+ 1 temperature reading (internal)
+ - Mode 3: 4 single-ended voltage readings (IN0-IN3),
+ 2 pseudo-differential voltage readings
+ (IN4-IN5, IN7-IN6),
+ 1 temperature reading (internal)
+
+If no operation mode is configured via device tree, the driver keeps the
+currently active chip operation mode (default is mode 0).
+
+
+Required node properties:
+
+ - compatible: must be set to "ti,adc128d818"
+ - reg: I2C address of the device
+
+Optional node properties:
+
+ - ti,mode: Operation mode (see above).
+
+
+Example (operation mode 2):
+
+ adc128d818@1d {
+ compatible = "ti,adc128d818";
+ reg = <0x1d>;
+ ti,mode = <2>;
+ };
diff --git a/Documentation/devicetree/bindings/hwmon/lm70.txt b/Documentation/devicetree/bindings/hwmon/lm70.txt
index e7fd921..ea417a0 100644
--- a/Documentation/devicetree/bindings/hwmon/lm70.txt
+++ b/Documentation/devicetree/bindings/hwmon/lm70.txt
@@ -4,6 +4,7 @@
- compatible: one of
"ti,lm70"
"ti,tmp121"
+ "ti,tmp122"
"ti,lm71"
"ti,lm74"
diff --git a/Documentation/devicetree/bindings/hwmon/lm90.txt b/Documentation/devicetree/bindings/hwmon/lm90.txt
index e863248..9758126 100644
--- a/Documentation/devicetree/bindings/hwmon/lm90.txt
+++ b/Documentation/devicetree/bindings/hwmon/lm90.txt
@@ -33,6 +33,11 @@
LM90 "-ALERT" pin output.
See interrupt-controller/interrupts.txt for the format.
+- #thermal-sensor-cells: should be set to 1. See thermal/thermal.txt for
+ details. See <include/dt-bindings/thermal/lm90.h> for the
+ definition of the local, remote and 2nd remote sensor index
+ constants.
+
Example LM90 node:
temp-sensor {
@@ -41,4 +46,5 @@
vcc-supply = <&palmas_ldo6_reg>;
interrupt-parent = <&gpio>;
interrupts = <TEGRA_GPIO(O, 4) IRQ_TYPE_LEVEL_LOW>;
+ #thermal-sensor-cells = <1>;
}
diff --git a/Documentation/devicetree/bindings/hwmon/sht15.txt b/Documentation/devicetree/bindings/hwmon/sht15.txt
new file mode 100644
index 0000000..6a80277
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/sht15.txt
@@ -0,0 +1,19 @@
+Sensirion SHT15 Humidity and Temperature Sensor
+
+Required properties:
+
+ - "compatible": must be "sensirion,sht15".
+ - "data-gpios": GPIO connected to the data line.
+ - "clk-gpios": GPIO connected to the clock line.
+ - "vcc-supply": regulator that drives the VCC pin.
+
+Example:
+
+ sensor {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_sensor>;
+ compatible = "sensirion,sht15";
+ clk-gpios = <&gpio4 12 0>;
+ data-gpios = <&gpio4 13 0>;
+ vcc-supply = <®_sht15>;
+ };
diff --git a/Documentation/devicetree/bindings/hwmon/stts751.txt b/Documentation/devicetree/bindings/hwmon/stts751.txt
new file mode 100644
index 0000000..3ee1dc3
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/stts751.txt
@@ -0,0 +1,15 @@
+* STTS751 thermometer.
+
+Required node properties:
+- compatible: "stts751"
+- reg: I2C bus address of the device
+
+Optional properties:
+- smbus-timeout-disable: when set, the smbus timeout function will be disabled
+
+Example stts751 node:
+
+temp-sensor {
+ compatible = "stts751";
+ reg = <0x48>;
+}
diff --git a/Documentation/devicetree/bindings/i2c/i2c.txt b/Documentation/devicetree/bindings/i2c/i2c.txt
index 5fa691e..cee9d50 100644
--- a/Documentation/devicetree/bindings/i2c/i2c.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c.txt
@@ -62,6 +62,9 @@
"irq" and "wakeup" names are recognized by I2C core, other names are
left to individual drivers.
+- host-notify
+ device uses SMBus host notify protocol instead of interrupt line.
+
- multi-master
states that there is another master active on this bus. The OS can use
this information to adapt power management to keep the arbitration awake
@@ -81,6 +84,11 @@
used by the device. I2C core will assign "irq" interrupt (or the very first
interrupt if not using interrupt names) as primary interrupt for the slave.
+Alternatively, devices supporting SMbus Host Notify, and connected to
+adapters that support this feature, may use "host-notify" property. I2C
+core will create a virtual interrupt for Host Notify and assign it as
+primary interrupt for the slave.
+
Also, if device is marked as a wakeup source, I2C core will set up "wakeup"
interrupt for the device. If "wakeup" interrupt name is not present in the
binding, then primary interrupt will be used as wakeup interrupt.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt b/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt
new file mode 100644
index 0000000..97c1167
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt
@@ -0,0 +1,22 @@
+* Cortina Systems Gemini interrupt controller
+
+This interrupt controller is found on the Gemini SoCs.
+
+Required properties:
+- compatible: must be "cortina,gemini-interrupt-controller"
+- reg: The register bank for the interrupt controller.
+- interrupt-controller: Identifies the node as an interrupt controller
+- #interrupt-cells: The number of cells to define the interrupts.
+ Must be 2 as the controller can specify level or rising edge
+ IRQs. The bindings follows the standard binding for controllers
+ with two cells specified in
+ interrupt-controller/interrupts.txt
+
+Example:
+
+interrupt-controller@48000000 {
+ compatible = "cortina,gemini-interrupt-controller";
+ reg = <0x48000000 0x1000>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
index 0dcb7c7..9446576 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
@@ -15,6 +15,9 @@
Second cell specifies the irq distribution mode to cores
0=Round Robin; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3
+ The second cell in interrupts property is deprecated and may be ignored by
+ the kernel.
+
intc accessed via the special ARC AUX register interface, hence "reg" property
is not specified.
diff --git a/Documentation/devicetree/bindings/mtd/aspeed-smc.txt b/Documentation/devicetree/bindings/mtd/aspeed-smc.txt
new file mode 100644
index 0000000..49f6528
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/aspeed-smc.txt
@@ -0,0 +1,51 @@
+* Aspeed Firmware Memory controller
+* Aspeed SPI Flash Memory Controller
+
+The Firmware Memory Controller in the Aspeed AST2500 SoC supports
+three chip selects, two of which are always of SPI type and the third
+can be SPI or NOR type flash. These bindings only describe SPI.
+
+The two SPI flash memory controllers in the AST2500 each support two
+chip selects.
+
+Required properties:
+ - compatible : Should be one of
+ "aspeed,ast2400-fmc" for the AST2400 Firmware Memory Controller
+ "aspeed,ast2400-spi" for the AST2400 SPI Flash memory Controller
+ "aspeed,ast2500-fmc" for the AST2500 Firmware Memory Controller
+ "aspeed,ast2500-spi" for the AST2500 SPI flash memory controllers
+
+ - reg : the first contains the control register location and length,
+ the second contains the memory window mapping address and length
+ - #address-cells : must be 1 corresponding to chip select child binding
+ - #size-cells : must be 0 corresponding to chip select child binding
+
+Optional properties:
+ - interrupts : Should contain the interrupt for the dma device if an
+ FMC
+
+The child nodes are the SPI flash modules which must have a compatible
+property as specified in bindings/mtd/jedec,spi-nor.txt
+
+Optionally, the child node can contain properties for SPI mode (may be
+ignored):
+ - spi-max-frequency - max frequency of spi bus
+
+
+Example:
+fmc: fmc@1e620000 {
+ compatible = "aspeed,ast2500-fmc";
+ reg = < 0x1e620000 0x94
+ 0x20000000 0x02000000 >;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ interrupts = <19>;
+ flash@0 {
+ reg = < 0 >;
+ compatible = "jedec,spi-nor";
+ /* spi-max-frequency = <>; */
+ /* m25p,fast-read; */
+ #address-cells = <1>;
+ #size-cells = <1>;
+ };
+};
diff --git a/Documentation/devicetree/bindings/mtd/common.txt b/Documentation/devicetree/bindings/mtd/common.txt
new file mode 100644
index 0000000..fc068b9
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/common.txt
@@ -0,0 +1,15 @@
+* Common properties of all MTD devices
+
+Optional properties:
+- label: user-defined MTD device name. Can be used to assign user
+ friendly names to MTD devices (instead of the flash model or flash
+ controller based name) in order to ease flash device identification
+ and/or describe what they are used for.
+
+Example:
+
+ flash@0 {
+ label = "System-firmware";
+
+ /* flash type specific properties */
+ };
diff --git a/Documentation/devicetree/bindings/mtd/cortina,gemini-flash.txt b/Documentation/devicetree/bindings/mtd/cortina,gemini-flash.txt
new file mode 100644
index 0000000..3fa1b34
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/cortina,gemini-flash.txt
@@ -0,0 +1,24 @@
+Flash device on Cortina Systems Gemini SoC
+
+This flash is regular CFI compatible (Intel or AMD extended) flash chips with
+some special bits that can be controlled by the machine's system controller.
+
+Required properties:
+- compatible : must be "cortina,gemini-flash", "cfi-flash";
+- reg : memory address for the flash chip
+- syscon : must be a phandle to the system controller
+- bank-width : width in bytes of flash interface, should be <2>
+
+For the rest of the properties, see mtd-physmap.txt.
+
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
+
+Example:
+
+flash@30000000 {
+ compatible = "cortina,gemini-flash", "cfi-flash";
+ reg = <0x30000000 0x01000000>;
+ syscon = <&syscon>;
+ bank-width = <2>;
+};
diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
index 2c91c03..3e920ec 100644
--- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
+++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
@@ -14,6 +14,8 @@
at25df641
at26df081a
mr25h256
+ mr25h10
+ mr25h40
mx25l4005a
mx25l1606e
mx25l6405d
diff --git a/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt b/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt
index fb314f0..5ded66a 100644
--- a/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt
+++ b/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt
@@ -1,7 +1,13 @@
* Serial NOR flash controller for MTK MT81xx (and similar)
Required properties:
-- compatible: should be "mediatek,mt8173-nor";
+- compatible: The possible values are:
+ "mediatek,mt2701-nor"
+ "mediatek,mt7623-nor"
+ "mediatek,mt8173-nor"
+ For mt8173, compatible should be "mediatek,mt8173-nor".
+ For every other SoC, should contain both the SoC-specific compatible string
+ and "mediatek,mt8173-nor".
- reg: physical base address and length of the controller's register
- clocks: the phandle of the clocks needed by the nor controller
- clock-names: the names of the clocks
diff --git a/Documentation/devicetree/bindings/mtd/tango-nand.txt b/Documentation/devicetree/bindings/mtd/tango-nand.txt
index ad5a02f..cd1bf2a 100644
--- a/Documentation/devicetree/bindings/mtd/tango-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/tango-nand.txt
@@ -5,7 +5,7 @@
- compatible: "sigma,smp8758-nand"
- reg: address/size of nfc_reg, nfc_mem, and pbus_reg
- dmas: reference to the DMA channel used by the controller
-- dma-names: "nfc_sbox"
+- dma-names: "rxtx"
- clocks: reference to the system clock
- #address-cells: <1>
- #size-cells: <0>
@@ -17,9 +17,9 @@
nandc: nand-controller@2c000 {
compatible = "sigma,smp8758-nand";
- reg = <0x2c000 0x30 0x2d000 0x800 0x20000 0x1000>;
+ reg = <0x2c000 0x30>, <0x2d000 0x800>, <0x20000 0x1000>;
dmas = <&dma0 3>;
- dma-names = "nfc_sbox";
+ dma-names = "rxtx";
clocks = <&clkgen SYS_CLK>;
#address-cells = <1>;
#size-cells = <0>;
diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt
index c010faf..c7194e8 100644
--- a/Documentation/devicetree/bindings/net/mediatek-net.txt
+++ b/Documentation/devicetree/bindings/net/mediatek-net.txt
@@ -7,7 +7,7 @@
* Ethernet controller node
Required properties:
-- compatible: Should be "mediatek,mt7623-eth"
+- compatible: Should be "mediatek,mt2701-eth"
- reg: Address and length of the register set for the device
- interrupts: Should contain the three frame engines interrupts in numeric
order. These are fe_int0, fe_int1 and fe_int2.
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index ff1bc4b..fb5056b 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -19,8 +19,9 @@
specifications. If neither of these are specified, the default is to
assume clause 22.
- If the phy's identifier is known then the list may contain an entry
- of the form: "ethernet-phy-idAAAA.BBBB" where
+ If the PHY reports an incorrect ID (or none at all) then the
+ "compatible" list may contain an entry with the correct PHY ID in the
+ form: "ethernet-phy-idAAAA.BBBB" where
AAAA - The value of the 16 bit Phy Identifier 1 register as
4 hex digits. This is the chip vendor OUI bits 3:18
BBBB - The value of the 16 bit Phy Identifier 2 register as
diff --git a/Documentation/devicetree/bindings/net/ti,dp83867.txt b/Documentation/devicetree/bindings/net/ti,dp83867.txt
index 85bf945..afe9630 100644
--- a/Documentation/devicetree/bindings/net/ti,dp83867.txt
+++ b/Documentation/devicetree/bindings/net/ti,dp83867.txt
@@ -3,9 +3,11 @@
Required properties:
- reg - The ID number for the phy, usually a small integer
- ti,rx-internal-delay - RGMII Receive Clock Delay - see dt-bindings/net/ti-dp83867.h
- for applicable values
+ for applicable values. Required only if interface type is
+ PHY_INTERFACE_MODE_RGMII_ID or PHY_INTERFACE_MODE_RGMII_RXID
- ti,tx-internal-delay - RGMII Transmit Clock Delay - see dt-bindings/net/ti-dp83867.h
- for applicable values
+ for applicable values. Required only if interface type is
+ PHY_INTERFACE_MODE_RGMII_ID or PHY_INTERFACE_MODE_RGMII_TXID
- ti,fifo-depth - Transmitt FIFO depth- see dt-bindings/net/ti-dp83867.h
for applicable values
diff --git a/Documentation/devicetree/bindings/power/supply/axp20x_ac_power.txt b/Documentation/devicetree/bindings/power/supply/axp20x_ac_power.txt
new file mode 100644
index 0000000..826e8a8
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/axp20x_ac_power.txt
@@ -0,0 +1,22 @@
+AXP20X and AXP22X PMICs' AC power supply
+
+Required Properties:
+ - compatible: One of:
+ "x-powers,axp202-ac-power-supply"
+ "x-powers,axp221-ac-power-supply"
+
+This node is a subnode of the axp20x PMIC.
+
+The AXP20X can read the current current and voltage supplied by AC by
+reading ADC channels from the AXP20X ADC.
+
+The AXP22X is only able to tell if an AC power supply is present and
+usable.
+
+Example:
+
+&axp209 {
+ ac_power_supply: ac-power-supply {
+ compatible = "x-powers,axp202-ac-power-supply";
+ };
+};
diff --git a/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt b/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt
index f1d7bee..ba8d35f 100644
--- a/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt
+++ b/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt
@@ -3,6 +3,11 @@
Required Properties:
-compatible: One of: "x-powers,axp202-usb-power-supply"
"x-powers,axp221-usb-power-supply"
+ "x-powers,axp223-usb-power-supply"
+
+The AXP223 PMIC shares most of its behaviour with the AXP221 but has slight
+variations such as the former being able to set the VBUS power supply max
+current to 100mA, unlike the latter.
This node is a subnode of the axp20x PMIC.
diff --git a/Documentation/devicetree/bindings/power/supply/bq27xxx.txt b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt
new file mode 100644
index 0000000..b0c95ef
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt
@@ -0,0 +1,36 @@
+Binding for TI BQ27XXX fuel gauge family
+
+Required properties:
+- compatible: Should contain one of the following:
+ * "ti,bq27200" - BQ27200
+ * "ti,bq27210" - BQ27210
+ * "ti,bq27500" - deprecated, use revision specific property below
+ * "ti,bq27510" - deprecated, use revision specific property below
+ * "ti,bq27520" - deprecated, use revision specific property below
+ * "ti,bq27500-1" - BQ27500/1
+ * "ti,bq27510g1" - BQ27510-g1
+ * "ti,bq27510g2" - BQ27510-g2
+ * "ti,bq27510g3" - BQ27510-g3
+ * "ti,bq27520g1" - BQ27520-g1
+ * "ti,bq27520g2" - BQ27520-g2
+ * "ti,bq27520g3" - BQ27520-g3
+ * "ti,bq27520g4" - BQ27520-g4
+ * "ti,bq27530" - BQ27530
+ * "ti,bq27531" - BQ27531
+ * "ti,bq27541" - BQ27541
+ * "ti,bq27542" - BQ27542
+ * "ti,bq27546" - BQ27546
+ * "ti,bq27742" - BQ27742
+ * "ti,bq27545" - BQ27545
+ * "ti,bq27421" - BQ27421
+ * "ti,bq27425" - BQ27425
+ * "ti,bq27441" - BQ27441
+ * "ti,bq27621" - BQ27621
+- reg: integer, i2c address of the device.
+
+Example:
+
+bq27510g3 {
+ compatible = "ti,bq27510g3";
+ reg = <0x55>;
+};
diff --git a/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt b/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt
index 65b88fa..06f8a5d 100644
--- a/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt
+++ b/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt
@@ -105,6 +105,22 @@
regulation must be done externally to fully comply with
the JEITA safety guidelines if this flag is set.
+- usb_otg_in-supply:
+ Usage: optional
+ Value type: <phandle>
+ Description: Reference to the regulator supplying power to the USB_OTG_IN
+ pin.
+
+child nodes:
+- otg-vbus:
+ Usage: optional
+ Description: This node defines a regulator used to control the direction
+ of VBUS voltage - specifically: whether to supply voltage
+ to VBUS for host mode operation of the OTG port, or allow
+ input voltage from external VBUS for charging. In the
+ hardware, the supply for this regulator comes from
+ usb_otg_in-supply.
+
EXAMPLE
charger@1000 {
compatible = "qcom,pm8941-charger";
@@ -128,4 +144,7 @@
qcom,fast-charge-current-limit = <1000000>;
qcom,dc-charge-current-limit = <1000000>;
+ usb_otg_in-supply = <&pm8941_5vs1>;
+
+ otg-vbus {};
};
diff --git a/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
new file mode 100644
index 0000000..a371962
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
@@ -0,0 +1,23 @@
+SBS sbs-charger
+~~~~~~~~~~
+
+Required properties:
+ - compatible: "<vendor>,<part-number>", "sbs,sbs-charger" as fallback. The part
+ number compatible string might be used in order to take care of vendor
+ specific registers.
+
+Optional properties:
+- interrupt-parent: Should be the phandle for the interrupt controller. Use in
+ conjunction with "interrupts".
+- interrupts: Interrupt mapping for GPIO IRQ. Use in conjunction with
+ "interrupt-parent". If an interrupt is not provided the driver will switch
+ automatically to polling.
+
+Example:
+
+ ltc4100@9 {
+ compatible = "lltc,ltc4100", "sbs,sbs-charger";
+ reg = <0x9>;
+ interrupt-parent = <&gpio6>;
+ interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+ };
diff --git a/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt b/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt
index 3bf5575..de45e1a 100644
--- a/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt
+++ b/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt
@@ -8,8 +8,10 @@
- interrupts : Specify the interrupt to be used to trigger when the AC
adapter is either plugged in or removed.
- ti,ac-detect-gpios : This GPIO is optionally used to read the AC adapter
- presence. This is a Host GPIO that is configured as an input and
- connected to the bq24735.
+ status. This is a Host GPIO that is configured as an input and connected
+ to the ACOK pin on the bq24735. Note: for backwards compatibility reasons,
+ the GPIO must be active on AC adapter absence despite ACOK being active
+ (high) on AC adapter presence.
- ti,charge-current : Used to control and set the charging current. This value
must be between 128mA and 8.128A with a 64mA step resolution. The POR value
is 0x0000h. This number is in mA (e.g. 8192), see spec for more information
@@ -25,6 +27,8 @@
- ti,external-control : Indicates that the charger is configured externally
and that the host should not attempt to enable/disable charging or set the
charge voltage/current.
+ - poll-interval : In case 'interrupts' is not specified, poll AC adapter
+ presence with this interval (milliseconds).
Example:
diff --git a/Documentation/devicetree/bindings/power_supply/maxim,max14656.txt b/Documentation/devicetree/bindings/power_supply/maxim,max14656.txt
new file mode 100644
index 0000000..e03e85a
--- /dev/null
+++ b/Documentation/devicetree/bindings/power_supply/maxim,max14656.txt
@@ -0,0 +1,25 @@
+Maxim MAX14656 / AL32 USB Charger Detector
+
+Required properties :
+- compatible : "maxim,max14656";
+- reg: i2c slave address
+- interrupt-parent: the phandle for the interrupt controller
+- interrupts: interrupt line
+
+Example:
+
+&i2c2 {
+ clock-frequency = <50000>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_i2c2>;
+ status = "okay";
+
+ max14656@35 {
+ compatible = "maxim,max14656";
+ reg = <0x35>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_charger_detect>;
+ interrupt-parent = <&gpio6>;
+ interrupts = <26 IRQ_TYPE_LEVEL_HIGH>;
+ };
+};
diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt
index da6614c..dc97506 100644
--- a/Documentation/devicetree/bindings/spi/sh-msiof.txt
+++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt
@@ -1,17 +1,23 @@
Renesas MSIOF spi controller
Required properties:
-- compatible : "renesas,msiof-<soctype>" for SoCs,
- "renesas,sh-msiof" for SuperH, or
- "renesas,sh-mobile-msiof" for SH Mobile series.
- Examples with soctypes are:
- "renesas,msiof-r8a7790" (R-Car H2)
+- compatible : "renesas,msiof-r8a7790" (R-Car H2)
"renesas,msiof-r8a7791" (R-Car M2-W)
"renesas,msiof-r8a7792" (R-Car V2H)
"renesas,msiof-r8a7793" (R-Car M2-N)
"renesas,msiof-r8a7794" (R-Car E2)
"renesas,msiof-r8a7796" (R-Car M3-W)
"renesas,msiof-sh73a0" (SH-Mobile AG5)
+ "renesas,sh-mobile-msiof" (generic SH-Mobile compatibile device)
+ "renesas,rcar-gen2-msiof" (generic R-Car Gen2 compatible device)
+ "renesas,rcar-gen3-msiof" (generic R-Car Gen3 compatible device)
+ "renesas,sh-msiof" (deprecated)
+
+ When compatible with the generic version, nodes
+ must list the SoC-specific version corresponding
+ to the platform first followed by the generic
+ version.
+
- reg : A list of offsets and lengths of the register sets for
the device.
If only one register set is present, it is to be used
@@ -61,7 +67,8 @@
Example:
msiof0: spi@e6e20000 {
- compatible = "renesas,msiof-r8a7791";
+ compatible = "renesas,msiof-r8a7791",
+ "renesas,rcar-gen2-msiof";
reg = <0 0xe6e20000 0 0x0064>;
interrupts = <0 156 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&mstp0_clks R8A7791_CLK_MSIOF0>;
diff --git a/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt b/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt
new file mode 100644
index 0000000..16ea1d3
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt
@@ -0,0 +1,22 @@
+Cortina Systems Gemini timer
+
+This timer is embedded in the Cortina Systems Gemini SoCs.
+
+Required properties:
+
+- compatible : Must be "cortina,gemini-timer"
+- reg : Should contain registers location and length
+- interrupts : Should contain the three timer interrupts with
+ flags for rising edge
+- syscon : a phandle to the global Gemini system controller
+
+Example:
+
+timer@43000000 {
+ compatible = "cortina,gemini-timer";
+ reg = <0x43000000 0x1000>;
+ interrupts = <14 IRQ_TYPE_EDGE_RISING>, /* Timer 1 */
+ <15 IRQ_TYPE_EDGE_RISING>, /* Timer 2 */
+ <16 IRQ_TYPE_EDGE_RISING>; /* Timer 3 */
+ syscon = <&syscon>;
+};
diff --git a/Documentation/devicetree/bindings/timer/renesas,ostm.txt b/Documentation/devicetree/bindings/timer/renesas,ostm.txt
new file mode 100644
index 0000000..be3ae0f
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/renesas,ostm.txt
@@ -0,0 +1,30 @@
+* Renesas OS Timer (OSTM)
+
+The OSTM is a multi-channel 32-bit timer/counter with fixed clock
+source that can operate in either interval count down timer or free-running
+compare match mode.
+
+Channels are independent from each other.
+
+Required Properties:
+
+ - compatible: must be one or more of the following:
+ - "renesas,r7s72100-ostm" for the r7s72100 OSTM
+ - "renesas,ostm" for any OSTM
+ This is a fallback for the above renesas,*-ostm entries
+
+ - reg: base address and length of the register block for a timer channel.
+
+ - interrupts: interrupt specifier for the timer channel.
+
+ - clocks: clock specifier for the timer channel.
+
+Example: R7S72100 (RZ/A1H) OSTM node
+
+ ostm0: timer@fcfec000 {
+ compatible = "renesas,r7s72100-ostm", "renesas,ostm";
+ reg = <0xfcfec000 0x30>;
+ interrupts = <GIC_SPI 102 IRQ_TYPE_EDGE_RISING>;
+ clocks = <&mstp5_clks R7S72100_CLK_OSTM0>;
+ power-domains = <&cpg_clocks>;
+ };
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index ca9d1eb..bf34d5b 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -306,6 +306,11 @@
devm_request_any_context_irq()
devm_request_irq()
devm_request_threaded_irq()
+ devm_irq_alloc_descs()
+ devm_irq_alloc_desc()
+ devm_irq_alloc_desc_at()
+ devm_irq_alloc_desc_from()
+ devm_irq_alloc_descs_from()
LED
devm_led_classdev_register()
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 72624a1..c94b467 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -212,10 +212,11 @@
snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
It's slow but very precise.
-Table 1-2: Contents of the status files (as of 4.1)
+Table 1-2: Contents of the status files (as of 4.8)
..............................................................................
Field Content
Name filename of the executable
+ Umask file mode creation mask
State state (R is running, S is sleeping, D is sleeping
in an uninterruptible wait, Z is zombie,
T is traced or stopped)
@@ -226,7 +227,6 @@
TracerPid PID of process tracing this process (0 if not)
Uid Real, effective, saved set, and file system UIDs
Gid Real, effective, saved set, and file system GIDs
- Umask file mode creation mask
FDSize number of file descriptor slots currently allocated
Groups supplementary group list
NStgid descendant namespace thread group ID hierarchy
@@ -236,6 +236,7 @@
VmPeak peak virtual memory size
VmSize total program size
VmLck locked memory size
+ VmPin pinned memory size
VmHWM peak resident set size ("high water mark")
VmRSS size of memory portions. It contains the three
following parts (VmRSS = RssAnon + RssFile + RssShmem)
diff --git a/Documentation/hwmon/hwmon-kernel-api.txt b/Documentation/hwmon/hwmon-kernel-api.txt
index 2505ae6..53a8066 100644
--- a/Documentation/hwmon/hwmon-kernel-api.txt
+++ b/Documentation/hwmon/hwmon-kernel-api.txt
@@ -89,6 +89,10 @@
hwmon_device_register_with_info and if the automatic (device managed)
removal would be too late.
+All supported hwmon device registration functions only accept valid device
+names. Device names including invalid characters (whitespace, '*', or '-')
+will be rejected. The 'name' parameter is mandatory.
+
Using devm_hwmon_device_register_with_info()
--------------------------------------------
diff --git a/Documentation/hwmon/lm70 b/Documentation/hwmon/lm70
index 1bb2db4..c3a1f2e 100644
--- a/Documentation/hwmon/lm70
+++ b/Documentation/hwmon/lm70
@@ -6,6 +6,8 @@
Datasheet: http://www.national.com/pf/LM/LM70.html
* Texas Instruments TMP121/TMP123
Information: http://focus.ti.com/docs/prod/folders/print/tmp121.html
+ * Texas Instruments TMP122/TMP124
+ Information: http://www.ti.com/product/tmp122
* National Semiconductor LM71
Datasheet: http://www.ti.com/product/LM71
* National Semiconductor LM74
@@ -35,8 +37,10 @@
with a "SPI master controller driver", see drivers/spi/spi_lm70llp.c
and its associated documentation.
-The LM74 and TMP121/TMP123 are very similar; main difference is 13-bit
-temperature data (0.0625 degrees celsius resolution).
+The LM74 and TMP121/TMP122/TMP123/TMP124 are very similar; main difference is
+13-bit temperature data (0.0625 degrees celsius resolution).
+
+The TMP122/TMP124 also feature configurable temperature thresholds.
The LM71 is also very similar; main difference is 14-bit temperature
data (0.03125 degrees celsius resolution).
diff --git a/Documentation/hwmon/sht21 b/Documentation/hwmon/sht21
index db17fda..47f4765 100644
--- a/Documentation/hwmon/sht21
+++ b/Documentation/hwmon/sht21
@@ -35,6 +35,7 @@
temp1_input - temperature input
humidity1_input - humidity input
+eic - Electronic Identification Code
Notes
-----
@@ -45,5 +46,5 @@
Celsius, the device should not be active for more than 10% of the time,
e.g. maximum two measurements per second at the given resolution.
-Different resolutions, the on-chip heater, using the CRC checksum and reading
-the serial number are not supported yet.
+Different resolutions, the on-chip heater, and using the CRC checksum
+are not supported yet.
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index 2cc95ad..fc337c3 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -86,8 +86,9 @@
name The chip name.
This should be a short, lowercase string, not containing
- spaces nor dashes, representing the chip name. This is
- the only mandatory attribute.
+ whitespace, dashes, or the wildcard character '*'.
+ This attribute represents the chip name. It is the only
+ mandatory attribute.
I2C devices get this attribute created automatically.
RO
diff --git a/Documentation/media/uapi/cec/cec-func-close.rst b/Documentation/media/uapi/cec/cec-func-close.rst
index 8267c31..895d9c2 100644
--- a/Documentation/media/uapi/cec/cec-func-close.rst
+++ b/Documentation/media/uapi/cec/cec-func-close.rst
@@ -33,11 +33,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
Closes the cec device. Resources associated with the file descriptor are
freed. The device configuration remain unchanged.
diff --git a/Documentation/media/uapi/cec/cec-func-ioctl.rst b/Documentation/media/uapi/cec/cec-func-ioctl.rst
index 9e8dbb1..7dcfd17 100644
--- a/Documentation/media/uapi/cec/cec-func-ioctl.rst
+++ b/Documentation/media/uapi/cec/cec-func-ioctl.rst
@@ -39,11 +39,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
The :c:func:`ioctl()` function manipulates cec device parameters. The
argument ``fd`` must be an open file descriptor.
diff --git a/Documentation/media/uapi/cec/cec-func-open.rst b/Documentation/media/uapi/cec/cec-func-open.rst
index af3f5b5..0304388 100644
--- a/Documentation/media/uapi/cec/cec-func-open.rst
+++ b/Documentation/media/uapi/cec/cec-func-open.rst
@@ -46,11 +46,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
To open a cec device applications call :c:func:`open()` with the
desired device name. The function has no side effects; the device
configuration remain unchanged.
diff --git a/Documentation/media/uapi/cec/cec-func-poll.rst b/Documentation/media/uapi/cec/cec-func-poll.rst
index cfb73e6..6a863cf 100644
--- a/Documentation/media/uapi/cec/cec-func-poll.rst
+++ b/Documentation/media/uapi/cec/cec-func-poll.rst
@@ -39,11 +39,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
With the :c:func:`poll()` function applications can wait for CEC
events.
diff --git a/Documentation/media/uapi/cec/cec-intro.rst b/Documentation/media/uapi/cec/cec-intro.rst
index 4a19ea5..07ee2b8 100644
--- a/Documentation/media/uapi/cec/cec-intro.rst
+++ b/Documentation/media/uapi/cec/cec-intro.rst
@@ -3,11 +3,6 @@
Introduction
============
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
HDMI connectors provide a single pin for use by the Consumer Electronics
Control protocol. This protocol allows different devices connected by an
HDMI cable to communicate. The protocol for CEC version 1.4 is defined
@@ -31,3 +26,15 @@
Drivers that support CEC will create a CEC device node (/dev/cecX) to
give userspace access to the CEC adapter. The
:ref:`CEC_ADAP_G_CAPS` ioctl will tell userspace what it is allowed to do.
+
+In order to check the support and test it, it is suggested to download
+the `v4l-utils <https://git.linuxtv.org/v4l-utils.git/>`_ package. It
+provides three tools to handle CEC:
+
+- cec-ctl: the Swiss army knife of CEC. Allows you to configure, transmit
+ and monitor CEC messages.
+
+- cec-compliance: does a CEC compliance test of a remote CEC device to
+ determine how compliant the CEC implementation is.
+
+- cec-follower: emulates a CEC follower.
diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst
index 2b0ddb1..a0e961f 100644
--- a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst
@@ -29,11 +29,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
All cec devices must support :ref:`ioctl CEC_ADAP_G_CAPS <CEC_ADAP_G_CAPS>`. To query
device information, applications call the ioctl with a pointer to a
struct :c:type:`cec_caps`. The driver fills the structure and
diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst
index b878637..09f09bb 100644
--- a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst
@@ -35,11 +35,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
To query the current CEC logical addresses, applications call
:ref:`ioctl CEC_ADAP_G_LOG_ADDRS <CEC_ADAP_G_LOG_ADDRS>` with a pointer to a
struct :c:type:`cec_log_addrs` where the driver stores the logical addresses.
diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst
index 3357deb..a3cdc75 100644
--- a/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst
@@ -35,11 +35,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
To query the current physical address applications call
:ref:`ioctl CEC_ADAP_G_PHYS_ADDR <CEC_ADAP_G_PHYS_ADDR>` with a pointer to a __u16 where the
driver stores the physical address.
diff --git a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
index e256c66..6e589a1 100644
--- a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
@@ -30,11 +30,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
CEC devices can send asynchronous events. These can be retrieved by
calling :c:func:`CEC_DQEVENT`. If the file descriptor is in
non-blocking mode and no event is pending, then it will return -1 and
diff --git a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst
index 4f5818b..e4ded9d 100644
--- a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst
@@ -31,11 +31,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
By default any filehandle can use :ref:`CEC_TRANSMIT`, but in order to prevent
applications from stepping on each others toes it must be possible to
obtain exclusive access to the CEC adapter. This ioctl sets the
diff --git a/Documentation/media/uapi/cec/cec-ioc-receive.rst b/Documentation/media/uapi/cec/cec-ioc-receive.rst
index bdf015b..dc2adb3 100644
--- a/Documentation/media/uapi/cec/cec-ioc-receive.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-receive.rst
@@ -34,11 +34,6 @@
Description
===========
-.. note::
-
- This documents the proposed CEC API. This API is not yet finalized
- and is currently only available as a staging kernel module.
-
To receive a CEC message the application has to fill in the
``timeout`` field of struct :c:type:`cec_msg` and pass it to
:ref:`ioctl CEC_RECEIVE <CEC_RECEIVE>`.
diff --git a/Documentation/media/uapi/v4l/pixfmt-007.rst b/Documentation/media/uapi/v4l/pixfmt-007.rst
index 44bb5a7..95a23a2 100644
--- a/Documentation/media/uapi/v4l/pixfmt-007.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-007.rst
@@ -211,7 +211,13 @@
The :ref:`srgb` standard defines the colorspace used by most webcams
and computer graphics. The default transfer function is
``V4L2_XFER_FUNC_SRGB``. The default Y'CbCr encoding is
-``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is full range.
+``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is limited range.
+
+Note that the :ref:`sycc` standard specifies full range quantization,
+however all current capture hardware supported by the kernel convert
+R'G'B' to limited range Y'CbCr. So choosing full range as the default
+would break how applications interpret the quantization range.
+
The chromaticities of the primary colors and the white reference are:
@@ -276,7 +282,7 @@
Y' is clamped to the range [0…1] and Cb and Cr are clamped to the range
[-0.5…0.5]. This transform is identical to one defined in SMPTE
-170M/BT.601. The Y'CbCr quantization is full range.
+170M/BT.601. The Y'CbCr quantization is limited range.
.. _col-adobergb:
@@ -288,10 +294,15 @@
graphics that use the AdobeRGB colorspace. This is also known as the
:ref:`oprgb` standard. The default transfer function is
``V4L2_XFER_FUNC_ADOBERGB``. The default Y'CbCr encoding is
-``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is full
-range. The chromaticities of the primary colors and the white reference
-are:
+``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is limited
+range.
+Note that the :ref:`oprgb` standard specifies full range quantization,
+however all current capture hardware supported by the kernel convert
+R'G'B' to limited range Y'CbCr. So choosing full range as the default
+would break how applications interpret the quantization range.
+
+The chromaticities of the primary colors and the white reference are:
.. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}|
@@ -344,7 +355,7 @@
Y' is clamped to the range [0…1] and Cb and Cr are clamped to the range
[-0.5…0.5]. This transform is identical to one defined in SMPTE
-170M/BT.601. The Y'CbCr quantization is full range.
+170M/BT.601. The Y'CbCr quantization is limited range.
.. _col-bt2020:
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index ba818ec..d2b0a8d 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -640,6 +640,10 @@
CONTROL DEPENDENCIES
--------------------
+Control dependencies can be a bit tricky because current compilers do
+not understand them. The purpose of this section is to help you prevent
+the compiler's ignorance from breaking your code.
+
A load-load control dependency requires a full read memory barrier, not
simply a data dependency barrier to make it work correctly. Consider the
following bit of code:
@@ -667,14 +671,15 @@
q = READ_ONCE(a);
if (q) {
- WRITE_ONCE(b, p);
+ WRITE_ONCE(b, 1);
}
-Control dependencies pair normally with other types of barriers. That
-said, please note that READ_ONCE() is not optional! Without the
-READ_ONCE(), the compiler might combine the load from 'a' with other
-loads from 'a', and the store to 'b' with other stores to 'b', with
-possible highly counterintuitive effects on ordering.
+Control dependencies pair normally with other types of barriers.
+That said, please note that neither READ_ONCE() nor WRITE_ONCE()
+are optional! Without the READ_ONCE(), the compiler might combine the
+load from 'a' with other loads from 'a'. Without the WRITE_ONCE(),
+the compiler might combine the store to 'b' with other stores to 'b'.
+Either can result in highly counterintuitive effects on ordering.
Worse yet, if the compiler is able to prove (say) that the value of
variable 'a' is always non-zero, it would be well within its rights
@@ -682,7 +687,7 @@
as follows:
q = a;
- b = p; /* BUG: Compiler and CPU can both reorder!!! */
+ b = 1; /* BUG: Compiler and CPU can both reorder!!! */
So don't leave out the READ_ONCE().
@@ -692,11 +697,11 @@
q = READ_ONCE(a);
if (q) {
barrier();
- WRITE_ONCE(b, p);
+ WRITE_ONCE(b, 1);
do_something();
} else {
barrier();
- WRITE_ONCE(b, p);
+ WRITE_ONCE(b, 1);
do_something_else();
}
@@ -705,12 +710,12 @@
q = READ_ONCE(a);
barrier();
- WRITE_ONCE(b, p); /* BUG: No ordering vs. load from a!!! */
+ WRITE_ONCE(b, 1); /* BUG: No ordering vs. load from a!!! */
if (q) {
- /* WRITE_ONCE(b, p); -- moved up, BUG!!! */
+ /* WRITE_ONCE(b, 1); -- moved up, BUG!!! */
do_something();
} else {
- /* WRITE_ONCE(b, p); -- moved up, BUG!!! */
+ /* WRITE_ONCE(b, 1); -- moved up, BUG!!! */
do_something_else();
}
@@ -723,10 +728,10 @@
q = READ_ONCE(a);
if (q) {
- smp_store_release(&b, p);
+ smp_store_release(&b, 1);
do_something();
} else {
- smp_store_release(&b, p);
+ smp_store_release(&b, 1);
do_something_else();
}
@@ -735,10 +740,10 @@
q = READ_ONCE(a);
if (q) {
- WRITE_ONCE(b, p);
+ WRITE_ONCE(b, 1);
do_something();
} else {
- WRITE_ONCE(b, r);
+ WRITE_ONCE(b, 2);
do_something_else();
}
@@ -751,10 +756,10 @@
q = READ_ONCE(a);
if (q % MAX) {
- WRITE_ONCE(b, p);
+ WRITE_ONCE(b, 1);
do_something();
} else {
- WRITE_ONCE(b, r);
+ WRITE_ONCE(b, 2);
do_something_else();
}
@@ -763,7 +768,7 @@
transform the above code into the following:
q = READ_ONCE(a);
- WRITE_ONCE(b, p);
+ WRITE_ONCE(b, 1);
do_something_else();
Given this transformation, the CPU is not required to respect the ordering
@@ -776,10 +781,10 @@
q = READ_ONCE(a);
BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
if (q % MAX) {
- WRITE_ONCE(b, p);
+ WRITE_ONCE(b, 1);
do_something();
} else {
- WRITE_ONCE(b, r);
+ WRITE_ONCE(b, 2);
do_something_else();
}
@@ -812,30 +817,28 @@
q = READ_ONCE(a);
if (q) {
- WRITE_ONCE(b, p);
+ WRITE_ONCE(b, 1);
} else {
- WRITE_ONCE(b, r);
+ WRITE_ONCE(b, 2);
}
- WRITE_ONCE(c, 1); /* BUG: No ordering against the read from "a". */
+ WRITE_ONCE(c, 1); /* BUG: No ordering against the read from 'a'. */
It is tempting to argue that there in fact is ordering because the
compiler cannot reorder volatile accesses and also cannot reorder
-the writes to "b" with the condition. Unfortunately for this line
-of reasoning, the compiler might compile the two writes to "b" as
+the writes to 'b' with the condition. Unfortunately for this line
+of reasoning, the compiler might compile the two writes to 'b' as
conditional-move instructions, as in this fanciful pseudo-assembly
language:
ld r1,a
- ld r2,p
- ld r3,r
cmp r1,$0
- cmov,ne r4,r2
- cmov,eq r4,r3
+ cmov,ne r4,$1
+ cmov,eq r4,$2
st r4,b
st $1,c
A weakly ordered CPU would have no dependency of any sort between the load
-from "a" and the store to "c". The control dependencies would extend
+from 'a' and the store to 'c'. The control dependencies would extend
only to the pair of cmov instructions and the store depending on them.
In short, control dependencies apply only to the stores in the then-clause
and else-clause of the if-statement in question (including functions
@@ -843,7 +846,7 @@
Finally, control dependencies do -not- provide transitivity. This is
demonstrated by two related examples, with the initial values of
-x and y both being zero:
+'x' and 'y' both being zero:
CPU 0 CPU 1
======================= =======================
@@ -915,6 +918,9 @@
(*) Control dependencies do -not- provide transitivity. If you
need transitivity, use smp_mb().
+ (*) Compilers do not understand control dependencies. It is therefore
+ your job to ensure that they do not break your code.
+
SMP BARRIER PAIRING
-------------------
diff --git a/Documentation/mtd/intel-spi.txt b/Documentation/mtd/intel-spi.txt
new file mode 100644
index 0000000..bc35772
--- /dev/null
+++ b/Documentation/mtd/intel-spi.txt
@@ -0,0 +1,88 @@
+Upgrading BIOS using intel-spi
+------------------------------
+
+Many Intel CPUs like Baytrail and Braswell include SPI serial flash host
+controller which is used to hold BIOS and other platform specific data.
+Since contents of the SPI serial flash is crucial for machine to function,
+it is typically protected by different hardware protection mechanisms to
+avoid accidental (or on purpose) overwrite of the content.
+
+Not all manufacturers protect the SPI serial flash, mainly because it
+allows upgrading the BIOS image directly from an OS.
+
+The intel-spi driver makes it possible to read and write the SPI serial
+flash, if certain protection bits are not set and locked. If it finds
+any of them set, the whole MTD device is made read-only to prevent
+partial overwrites. By default the driver exposes SPI serial flash
+contents as read-only but it can be changed from kernel command line,
+passing "intel-spi.writeable=1".
+
+Please keep in mind that overwriting the BIOS image on SPI serial flash
+might render the machine unbootable and requires special equipment like
+Dediprog to revive. You have been warned!
+
+Below are the steps how to upgrade MinnowBoard MAX BIOS directly from
+Linux.
+
+ 1) Download and extract the latest Minnowboard MAX BIOS SPI image
+ [1]. At the time writing this the latest image is v92.
+
+ 2) Install mtd-utils package [2]. We need this in order to erase the SPI
+ serial flash. Distros like Debian and Fedora have this prepackaged with
+ name "mtd-utils".
+
+ 3) Add "intel-spi.writeable=1" to the kernel command line and reboot
+ the board (you can also reload the driver passing "writeable=1" as
+ module parameter to modprobe).
+
+ 4) Once the board is up and running again, find the right MTD partition
+ (it is named as "BIOS"):
+
+ # cat /proc/mtd
+ dev: size erasesize name
+ mtd0: 00800000 00001000 "BIOS"
+
+ So here it will be /dev/mtd0 but it may vary.
+
+ 5) Make backup of the existing image first:
+
+ # dd if=/dev/mtd0ro of=bios.bak
+ 16384+0 records in
+ 16384+0 records out
+ 8388608 bytes (8.4 MB) copied, 10.0269 s, 837 kB/s
+
+ 6) Verify the backup
+
+ # sha1sum /dev/mtd0ro bios.bak
+ fdbb011920572ca6c991377c4b418a0502668b73 /dev/mtd0ro
+ fdbb011920572ca6c991377c4b418a0502668b73 bios.bak
+
+ The SHA1 sums must match. Otherwise do not continue any further!
+
+ 7) Erase the SPI serial flash. After this step, do not reboot the
+ board! Otherwise it will not start anymore.
+
+ # flash_erase /dev/mtd0 0 0
+ Erasing 4 Kibyte @ 7ff000 -- 100 % complete
+
+ 8) Once completed without errors you can write the new BIOS image:
+
+ # dd if=MNW2MAX1.X64.0092.R01.1605221712.bin of=/dev/mtd0
+
+ 9) Verify that the new content of the SPI serial flash matches the new
+ BIOS image:
+
+ # sha1sum /dev/mtd0ro MNW2MAX1.X64.0092.R01.1605221712.bin
+ 9b4df9e4be2057fceec3a5529ec3d950836c87a2 /dev/mtd0ro
+ 9b4df9e4be2057fceec3a5529ec3d950836c87a2 MNW2MAX1.X64.0092.R01.1605221712.bin
+
+ The SHA1 sums should match.
+
+ 10) Now you can reboot your board and observe the new BIOS starting up
+ properly.
+
+References
+----------
+
+[1] https://firmware.intel.com/sites/default/files/MinnowBoard.MAX_.X64.92.R01.zip
+[2] http://www.linux-mtd.infradead.org/
diff --git a/Documentation/power/states.txt b/Documentation/power/states.txt
index 8a39ce4..008ecb5 100644
--- a/Documentation/power/states.txt
+++ b/Documentation/power/states.txt
@@ -35,9 +35,7 @@
The default suspend mode (ie. the one to be used without writing anything into
/sys/power/mem_sleep) is either "deep" (if Suspend-To-RAM is supported) or
"s2idle", but it can be overridden by the value of the "mem_sleep_default"
-parameter in the kernel command line. On some ACPI-based systems, depending on
-the information in the FADT, the default may be "s2idle" even if Suspend-To-RAM
-is supported.
+parameter in the kernel command line.
The properties of all of the sleep states are described below.
diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt
index 8e37b0b..cbc1b46 100644
--- a/Documentation/scheduler/sched-deadline.txt
+++ b/Documentation/scheduler/sched-deadline.txt
@@ -408,6 +408,11 @@
* the new scheduling related syscalls that manipulate it, i.e.,
sched_setattr() and sched_getattr() are implemented.
+ For debugging purposes, the leftover runtime and absolute deadline of a
+ SCHED_DEADLINE task can be retrieved through /proc/<pid>/sched (entries
+ dl.runtime and dl.deadline, both values in ns). A programmatic way to
+ retrieve these values from production code is under discussion.
+
4.3 Default behavior
---------------------
@@ -476,6 +481,7 @@
Still missing:
+ - programmatic way to retrieve current runtime and absolute deadline
- refinements to deadline inheritance, especially regarding the possibility
of retaining bandwidth isolation among non-interacting tasks. This is
being studied from both theoretical and practical points of view, and
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index a03f0d9..d8fce3e 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -158,11 +158,11 @@
Consider two sibling groups A and B; both have 50% bandwidth, but A's
period is twice the length of B's.
-* group A: period=100000us, runtime=10000us
- - this runs for 0.01s once every 0.1s
+* group A: period=100000us, runtime=50000us
+ - this runs for 0.05s once every 0.1s
-* group B: period= 50000us, runtime=10000us
- - this runs for 0.01s twice every 0.1s (or once every 0.05 sec).
+* group B: period= 50000us, runtime=25000us
+ - this runs for 0.025s twice every 0.1s (or once every 0.05 sec).
This means that currently a while (1) loop in A will run for the full period of
B and can starve B's tasks (assuming they are of lower priority) for a whole
diff --git a/Documentation/timers/timer_stats.txt b/Documentation/timers/timer_stats.txt
deleted file mode 100644
index de835ee..0000000
--- a/Documentation/timers/timer_stats.txt
+++ /dev/null
@@ -1,73 +0,0 @@
-timer_stats - timer usage statistics
-------------------------------------
-
-timer_stats is a debugging facility to make the timer (ab)usage in a Linux
-system visible to kernel and userspace developers. If enabled in the config
-but not used it has almost zero runtime overhead, and a relatively small
-data structure overhead. Even if collection is enabled runtime all the
-locking is per-CPU and lookup is hashed.
-
-timer_stats should be used by kernel and userspace developers to verify that
-their code does not make unduly use of timers. This helps to avoid unnecessary
-wakeups, which should be avoided to optimize power consumption.
-
-It can be enabled by CONFIG_TIMER_STATS in the "Kernel hacking" configuration
-section.
-
-timer_stats collects information about the timer events which are fired in a
-Linux system over a sample period:
-
-- the pid of the task(process) which initialized the timer
-- the name of the process which initialized the timer
-- the function where the timer was initialized
-- the callback function which is associated to the timer
-- the number of events (callbacks)
-
-timer_stats adds an entry to /proc: /proc/timer_stats
-
-This entry is used to control the statistics functionality and to read out the
-sampled information.
-
-The timer_stats functionality is inactive on bootup.
-
-To activate a sample period issue:
-# echo 1 >/proc/timer_stats
-
-To stop a sample period issue:
-# echo 0 >/proc/timer_stats
-
-The statistics can be retrieved by:
-# cat /proc/timer_stats
-
-While sampling is enabled, each readout from /proc/timer_stats will see
-newly updated statistics. Once sampling is disabled, the sampled information
-is kept until a new sample period is started. This allows multiple readouts.
-
-Sample output of /proc/timer_stats:
-
-Timerstats sample period: 3.888770 s
- 12, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick)
- 15, 1 swapper hcd_submit_urb (rh_timer_func)
- 4, 959 kedac schedule_timeout (process_timeout)
- 1, 0 swapper page_writeback_init (wb_timer_fn)
- 28, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick)
- 22, 2948 IRQ 4 tty_flip_buffer_push (delayed_work_timer_fn)
- 3, 3100 bash schedule_timeout (process_timeout)
- 1, 1 swapper queue_delayed_work_on (delayed_work_timer_fn)
- 1, 1 swapper queue_delayed_work_on (delayed_work_timer_fn)
- 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer)
- 1, 2292 ip __netdev_watchdog_up (dev_watchdog)
- 1, 23 events/1 do_cache_clean (delayed_work_timer_fn)
-90 total events, 30.0 events/sec
-
-The first column is the number of events, the second column the pid, the third
-column is the name of the process. The forth column shows the function which
-initialized the timer and in parenthesis the callback function which was
-executed on expiry.
-
- Thomas, Ingo
-
-Added flag to indicate 'deferrable timer' in /proc/timer_stats. A deferrable
-timer will appear as follows
- 10D, 1 swapper queue_delayed_work_on (delayed_work_timer_fn)
-
diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt
index 95a4d34..b8527c6 100644
--- a/Documentation/x86/zero-page.txt
+++ b/Documentation/x86/zero-page.txt
@@ -31,6 +31,8 @@
1E9/001 ALL eddbuf_entries Number of entries in eddbuf (below)
1EA/001 ALL edd_mbr_sig_buf_entries Number of entries in edd_mbr_sig_buffer
(below)
+1EB/001 ALL kbd_status Numlock is enabled
+1EC/001 ALL secure_boot Secure boot is enabled in the firmware
1EF/001 ALL sentinel Used to detect broken bootloaders
290/040 ALL edd_mbr_sig_buffer EDD MBR signatures
2D0/A00 ALL e820_map E820 memory map table
diff --git a/MAINTAINERS b/MAINTAINERS
index 0277df8..6f39cf6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -643,7 +643,7 @@
F: drivers/gpio/gpio-altera.c
ALTERA SYSTEM RESOURCE DRIVER FOR ARRIA10 DEVKIT
-M: Thor Thayer <tthayer@opensource.altera.com>
+M: Thor Thayer <thor.thayer@linux.intel.com>
S: Maintained
F: drivers/gpio/gpio-altera-a10sr.c
F: drivers/mfd/altera-a10sr.c
@@ -877,8 +877,8 @@
F: drivers/hwmon/applesmc.c
APPLETALK NETWORK LAYER
-M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
-S: Maintained
+L: netdev@vger.kernel.org
+S: Odd fixes
F: drivers/net/appletalk/
F: net/appletalk/
@@ -976,6 +976,7 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
W: http://www.armlinux.org.uk/
S: Maintained
+T: git git://git.armlinux.org.uk/~rmk/linux-arm.git
F: arch/arm/
ARM SUB-ARCHITECTURES
@@ -1090,7 +1091,7 @@
F: drivers/*/*aspeed*
ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Nicolas Ferre <nicolas.ferre@microchip.com>
M: Alexandre Belloni <alexandre.belloni@free-electrons.com>
M: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1153,6 +1154,7 @@
M: Russell King <linux@armlinux.org.uk>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
+T: git git://git.armlinux.org.uk/~rmk/linux-arm.git clkdev
F: arch/arm/include/asm/clkdev.h
F: drivers/clk/clkdev.c
@@ -1688,6 +1690,7 @@
R: Javier Martinez Canillas <javier@osg.samsung.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
+Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/
S: Maintained
F: arch/arm/boot/dts/s3c*
F: arch/arm/boot/dts/s5p*
@@ -1770,7 +1773,7 @@
F: include/linux/soc/renesas/
ARM/SOCFPGA ARCHITECTURE
-M: Dinh Nguyen <dinguyen@opensource.altera.com>
+M: Dinh Nguyen <dinguyen@kernel.org>
S: Maintained
F: arch/arm/mach-socfpga/
F: arch/arm/boot/dts/socfpga*
@@ -1780,12 +1783,12 @@
T: git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git
ARM/SOCFPGA CLOCK FRAMEWORK SUPPORT
-M: Dinh Nguyen <dinguyen@opensource.altera.com>
+M: Dinh Nguyen <dinguyen@kernel.org>
S: Maintained
F: drivers/clk/socfpga/
ARM/SOCFPGA EDAC SUPPORT
-M: Thor Thayer <tthayer@opensource.altera.com>
+M: Thor Thayer <thor.thayer@linux.intel.com>
S: Maintained
F: drivers/edac/altera_edac.
@@ -2172,64 +2175,56 @@
F: include/uapi/linux/atm*
ATMEL AT91 / AT32 MCI DRIVER
-M: Ludovic Desroches <ludovic.desroches@atmel.com>
+M: Ludovic Desroches <ludovic.desroches@microchip.com>
S: Maintained
F: drivers/mmc/host/atmel-mci.c
ATMEL AT91 SAMA5D2-Compatible Shutdown Controller
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Nicolas Ferre <nicolas.ferre@microchip.com>
S: Supported
F: drivers/power/reset/at91-sama5d2_shdwc.c
ATMEL SAMA5D2 ADC DRIVER
-M: Ludovic Desroches <ludovic.desroches@atmel.com>
+M: Ludovic Desroches <ludovic.desroches@microchip.com>
L: linux-iio@vger.kernel.org
S: Supported
F: drivers/iio/adc/at91-sama5d2_adc.c
ATMEL Audio ALSA driver
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Nicolas Ferre <nicolas.ferre@microchip.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Supported
F: sound/soc/atmel
-ATMEL DMA DRIVER
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S: Supported
-F: drivers/dma/at_hdmac.c
-F: drivers/dma/at_hdmac_regs.h
-F: include/linux/platform_data/dma-atmel.h
-
ATMEL XDMA DRIVER
-M: Ludovic Desroches <ludovic.desroches@atmel.com>
+M: Ludovic Desroches <ludovic.desroches@microchip.com>
L: linux-arm-kernel@lists.infradead.org
L: dmaengine@vger.kernel.org
S: Supported
F: drivers/dma/at_xdmac.c
ATMEL I2C DRIVER
-M: Ludovic Desroches <ludovic.desroches@atmel.com>
+M: Ludovic Desroches <ludovic.desroches@microchip.com>
L: linux-i2c@vger.kernel.org
S: Supported
F: drivers/i2c/busses/i2c-at91.c
ATMEL ISI DRIVER
-M: Ludovic Desroches <ludovic.desroches@atmel.com>
+M: Ludovic Desroches <ludovic.desroches@microchip.com>
L: linux-media@vger.kernel.org
S: Supported
F: drivers/media/platform/soc_camera/atmel-isi.c
F: include/media/atmel-isi.h
ATMEL LCDFB DRIVER
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Nicolas Ferre <nicolas.ferre@microchip.com>
L: linux-fbdev@vger.kernel.org
S: Maintained
F: drivers/video/fbdev/atmel_lcdfb.c
F: include/video/atmel_lcdc.h
ATMEL MACB ETHERNET DRIVER
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Nicolas Ferre <nicolas.ferre@microchip.com>
S: Supported
F: drivers/net/ethernet/cadence/
@@ -2241,32 +2236,32 @@
F: drivers/mtd/nand/atmel_nand*
ATMEL SDMMC DRIVER
-M: Ludovic Desroches <ludovic.desroches@atmel.com>
+M: Ludovic Desroches <ludovic.desroches@microchip.com>
L: linux-mmc@vger.kernel.org
S: Supported
F: drivers/mmc/host/sdhci-of-at91.c
ATMEL SPI DRIVER
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Nicolas Ferre <nicolas.ferre@microchip.com>
S: Supported
F: drivers/spi/spi-atmel.*
ATMEL SSC DRIVER
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Nicolas Ferre <nicolas.ferre@microchip.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
F: drivers/misc/atmel-ssc.c
F: include/linux/atmel-ssc.h
ATMEL Timer Counter (TC) AND CLOCKSOURCE DRIVERS
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Nicolas Ferre <nicolas.ferre@microchip.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
F: drivers/misc/atmel_tclib.c
F: drivers/clocksource/tcb_clksrc.c
ATMEL USBA UDC DRIVER
-M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Nicolas Ferre <nicolas.ferre@microchip.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
F: drivers/usb/gadget/udc/atmel_usba_udc.*
@@ -3572,7 +3567,7 @@
F: include/uapi/rdma/cxgb3-abi.h
CXGB4 ETHERNET DRIVER (CXGB4)
-M: Hariprasad S <hariprasad@chelsio.com>
+M: Ganesh Goudar <ganeshgr@chelsio.com>
L: netdev@vger.kernel.org
W: http://www.chelsio.com
S: Supported
@@ -4105,12 +4100,18 @@
DRM DRIVER FOR BOCHS VIRTUAL GPU
M: Gerd Hoffmann <kraxel@redhat.com>
-S: Odd Fixes
+L: virtualization@lists.linux-foundation.org
+T: git git://git.kraxel.org/linux drm-qemu
+S: Maintained
F: drivers/gpu/drm/bochs/
DRM DRIVER FOR QEMU'S CIRRUS DEVICE
M: Dave Airlie <airlied@redhat.com>
-S: Odd Fixes
+M: Gerd Hoffmann <kraxel@redhat.com>
+L: virtualization@lists.linux-foundation.org
+T: git git://git.kraxel.org/linux drm-qemu
+S: Obsolete
+W: https://www.kraxel.org/blog/2014/10/qemu-using-cirrus-considered-harmful/
F: drivers/gpu/drm/cirrus/
RADEON and AMDGPU DRM DRIVERS
@@ -4152,7 +4153,7 @@
INTEL GVT-g DRIVERS (Intel GPU Virtualization)
M: Zhenyu Wang <zhenyuw@linux.intel.com>
M: Zhi Wang <zhi.a.wang@intel.com>
-L: igvt-g-dev@lists.01.org
+L: intel-gvt-dev@lists.freedesktop.org
L: intel-gfx@lists.freedesktop.org
W: https://01.org/igvt-g
T: git https://github.com/01org/gvt-linux.git
@@ -4303,7 +4304,10 @@
DRM DRIVER FOR QXL VIRTUAL GPU
M: Dave Airlie <airlied@redhat.com>
-S: Odd Fixes
+M: Gerd Hoffmann <kraxel@redhat.com>
+L: virtualization@lists.linux-foundation.org
+T: git git://git.kraxel.org/linux drm-qemu
+S: Maintained
F: drivers/gpu/drm/qxl/
F: include/uapi/drm/qxl_drm.h
@@ -6723,9 +6727,8 @@
F: drivers/tty/ipwireless/
IPX NETWORK LAYER
-M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
L: netdev@vger.kernel.org
-S: Maintained
+S: Odd fixes
F: include/net/ipx.h
F: include/uapi/linux/ipx.h
F: net/ipx/
@@ -7497,8 +7500,8 @@
F: drivers/misc/lkdtm*
LLC (802.2)
-M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
-S: Maintained
+L: netdev@vger.kernel.org
+S: Odd fixes
F: include/linux/llc.h
F: include/uapi/linux/llc.h
F: include/net/llc*
@@ -7531,6 +7534,7 @@
F: Documentation/hwmon/lm90
F: Documentation/devicetree/bindings/hwmon/lm90.txt
F: drivers/hwmon/lm90.c
+F: include/dt-bindings/thermal/lm90.h
LM95234 HARDWARE MONITOR DRIVER
M: Guenter Roeck <linux@roeck-us.net>
@@ -7705,8 +7709,10 @@
F: Documentation/devicetree/bindings/net/dsa/marvell.txt
MARVELL ARMADA DRM SUPPORT
-M: Russell King <rmk+kernel@armlinux.org.uk>
+M: Russell King <linux@armlinux.org.uk>
S: Maintained
+T: git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-armada-devel
+T: git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-armada-fixes
F: drivers/gpu/drm/armada/
F: include/uapi/drm/armada_drm.h
F: Documentation/devicetree/bindings/display/armada/
@@ -8178,6 +8184,15 @@
F: drivers/tty/serial/atmel_serial.c
F: include/linux/atmel_serial.h
+MICROCHIP / ATMEL DMA DRIVER
+M: Ludovic Desroches <ludovic.desroches@microchip.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L: dmaengine@vger.kernel.org
+S: Supported
+F: drivers/dma/at_hdmac.c
+F: drivers/dma/at_hdmac_regs.h
+F: include/linux/platform_data/dma-atmel.h
+
MICROCHIP / ATMEL ISC DRIVER
M: Songjun Wu <songjun.wu@microchip.com>
L: linux-media@vger.kernel.org
@@ -8902,8 +8917,10 @@
F: drivers/nfc/nxp-nci
NXP TDA998X DRM DRIVER
-M: Russell King <rmk+kernel@armlinux.org.uk>
+M: Russell King <linux@armlinux.org.uk>
S: Supported
+T: git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-devel
+T: git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-fixes
F: drivers/gpu/drm/i2c/tda998x_drv.c
F: include/drm/i2c/tda998x.h
@@ -9719,7 +9736,7 @@
F: drivers/pinctrl/pinctrl-at91.*
PIN CONTROLLER - ATMEL AT91 PIO4
-M: Ludovic Desroches <ludovic.desroches@atmel.com>
+M: Ludovic Desroches <ludovic.desroches@microchip.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-gpio@vger.kernel.org
S: Supported
@@ -10178,7 +10195,6 @@
QUALCOMM ATHEROS ATH9K WIRELESS DRIVER
M: QCA ath9k Development <ath9k-devel@qca.qualcomm.com>
L: linux-wireless@vger.kernel.org
-L: ath9k-devel@lists.ath9k.org
W: http://wireless.kernel.org/en/users/Drivers/ath9k
S: Supported
F: drivers/net/wireless/ath/ath9k/
@@ -13049,7 +13065,7 @@
F: include/uapi/linux/userio.h
VIRTIO CONSOLE DRIVER
-M: Amit Shah <amit.shah@redhat.com>
+M: Amit Shah <amit@kernel.org>
L: virtualization@lists.linux-foundation.org
S: Maintained
F: drivers/char/virtio_console.c
@@ -13084,6 +13100,7 @@
M: Gerd Hoffmann <kraxel@redhat.com>
L: dri-devel@lists.freedesktop.org
L: virtualization@lists.linux-foundation.org
+T: git git://git.kraxel.org/linux drm-qemu
S: Maintained
F: drivers/gpu/drm/virtio/
F: include/uapi/linux/virtio_gpu.h
@@ -13356,10 +13373,8 @@
F: drivers/input/misc/wistron_btns.c
WL3501 WIRELESS PCMCIA CARD DRIVER
-M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
L: linux-wireless@vger.kernel.org
-W: http://oops.ghostprotocols.net:81/blog
-S: Maintained
+S: Odd fixes
F: drivers/net/wireless/wl3501*
WOLFSON MICROELECTRONICS DRIVERS
@@ -13435,6 +13450,7 @@
X86 PLATFORM DRIVERS
M: Darren Hart <dvhart@infradead.org>
+M: Andy Shevchenko <andy@infradead.org>
L: platform-driver-x86@vger.kernel.org
T: git git://git.infradead.org/users/dvhart/linux-platform-drivers-x86.git
S: Maintained
@@ -13606,6 +13622,7 @@
ZBUD COMPRESSED PAGE ALLOCATOR
M: Seth Jennings <sjenning@redhat.com>
+M: Dan Streetman <ddstreet@ieee.org>
L: linux-mm@kvack.org
S: Maintained
F: mm/zbud.c
@@ -13661,6 +13678,7 @@
ZSWAP COMPRESSED SWAP CACHING
M: Seth Jennings <sjenning@redhat.com>
+M: Dan Streetman <ddstreet@ieee.org>
L: linux-mm@kvack.org
S: Maintained
F: mm/zswap.c
diff --git a/Makefile b/Makefile
index 5f1a847..4e2abc3 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
VERSION = 4
PATCHLEVEL = 10
SUBLEVEL = 0
-EXTRAVERSION = -rc3
-NAME = Roaring Lionus
+EXTRAVERSION =
+NAME = Fearless Coyote
# *DOCUMENTATION*
# To see a list of typical targets execute "make help"
@@ -87,10 +87,12 @@
ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4
ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
quiet=silent_
+ tools_silent=s
endif
else # make-3.8x
ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
quiet=silent_
+ tools_silent=-s
endif
endif
@@ -797,7 +799,7 @@
KBUILD_ARFLAGS := $(call ar-option,D)
# check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
endif
@@ -1607,11 +1609,11 @@
# Clear a bunch of variables before executing the submake
tools/: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/
tools/%: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $*
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $*
# Single targets
# ---------------------------------------------------------------------------
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index bf8475c..baa152b 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -1,7 +1,6 @@
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += exec.h
generic-y += export.h
generic-y += irq_work.h
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 54d8616..9d27a7d 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1145,7 +1145,7 @@
SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
{
struct rusage32 r;
- cputime_t utime, stime;
+ u64 utime, stime;
unsigned long utime_jiffies, stime_jiffies;
if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
@@ -1155,16 +1155,16 @@
switch (who) {
case RUSAGE_SELF:
task_cputime(current, &utime, &stime);
- utime_jiffies = cputime_to_jiffies(utime);
- stime_jiffies = cputime_to_jiffies(stime);
+ utime_jiffies = nsecs_to_jiffies(utime);
+ stime_jiffies = nsecs_to_jiffies(stime);
jiffies_to_timeval32(utime_jiffies, &r.ru_utime);
jiffies_to_timeval32(stime_jiffies, &r.ru_stime);
r.ru_minflt = current->min_flt;
r.ru_majflt = current->maj_flt;
break;
case RUSAGE_CHILDREN:
- utime_jiffies = cputime_to_jiffies(current->signal->cutime);
- stime_jiffies = cputime_to_jiffies(current->signal->cstime);
+ utime_jiffies = nsecs_to_jiffies(current->signal->cutime);
+ stime_jiffies = nsecs_to_jiffies(current->signal->cstime);
jiffies_to_timeval32(utime_jiffies, &r.ru_utime);
jiffies_to_timeval32(stime_jiffies, &r.ru_stime);
r.ru_minflt = current->signal->cmin_flt;
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index c75d290..283099c 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -29,7 +29,7 @@
select HAVE_KPROBES
select HAVE_KRETPROBES
select HAVE_MEMBLOCK
- select HAVE_MOD_ARCH_SPECIFIC if ARC_DW2_UNWIND
+ select HAVE_MOD_ARCH_SPECIFIC
select HAVE_OPROFILE
select HAVE_PERF_EVENTS
select HANDLE_DOMAIN_IRQ
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index c332604..63a0401 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -2,7 +2,6 @@
generic-y += bitsperlong.h
generic-y += bugs.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += device.h
generic-y += div64.h
generic-y += emergency-restart.h
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index b3410ff..5008021 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -67,7 +67,7 @@
#define ARC_REG_IC_PTAG_HI 0x1F
/* Bit val in IC_CTRL */
-#define IC_CTRL_CACHE_DISABLE 0x1
+#define IC_CTRL_DIS 0x1
/* Data cache related Auxiliary registers */
#define ARC_REG_DC_BCR 0x72 /* Build Config reg */
@@ -80,8 +80,9 @@
#define ARC_REG_DC_PTAG_HI 0x5F
/* Bit val in DC_CTRL */
-#define DC_CTRL_INV_MODE_FLUSH 0x40
-#define DC_CTRL_FLUSH_STATUS 0x100
+#define DC_CTRL_DIS 0x001
+#define DC_CTRL_INV_MODE_FLUSH 0x040
+#define DC_CTRL_FLUSH_STATUS 0x100
/*System-level cache (L2 cache) related Auxiliary registers */
#define ARC_REG_SLC_CFG 0x901
@@ -92,8 +93,8 @@
#define ARC_REG_SLC_RGN_END 0x916
/* Bit val in SLC_CONTROL */
+#define SLC_CTRL_DIS 0x001
#define SLC_CTRL_IM 0x040
-#define SLC_CTRL_DISABLE 0x001
#define SLC_CTRL_BUSY 0x100
#define SLC_CTRL_RGN_OP_INV 0x200
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index a36e860..d5da211 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -26,7 +26,9 @@
" lp 1f \n"
" nop \n"
"1: \n"
- : : "r"(loops));
+ :
+ : "r"(loops)
+ : "lp_count");
}
extern void __bad_udelay(void);
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index b5ff87e..aee1a77 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -16,6 +16,7 @@
;
; Now manually save: r12, sp, fp, gp, r25
+ PUSH r30
PUSH r12
; Saving pt_regs->sp correctly requires some extra work due to the way
@@ -72,6 +73,7 @@
POPAX AUX_USER_SP
1:
POP r12
+ POP r30
.endm
diff --git a/arch/arc/include/asm/module.h b/arch/arc/include/asm/module.h
index 6e91d8b..567590e 100644
--- a/arch/arc/include/asm/module.h
+++ b/arch/arc/include/asm/module.h
@@ -14,13 +14,13 @@
#include <asm-generic/module.h>
-#ifdef CONFIG_ARC_DW2_UNWIND
struct mod_arch_specific {
+#ifdef CONFIG_ARC_DW2_UNWIND
void *unw_info;
int unw_sec_idx;
+#endif
const char *secstr;
};
-#endif
#define MODULE_PROC_FAMILY "ARC700"
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 69095da..47111d5 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -84,7 +84,7 @@
unsigned long fp;
unsigned long sp; /* user/kernel sp depending on where we came from */
- unsigned long r12;
+ unsigned long r12, r30;
/*------- Below list auto saved by h/w -----------*/
unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h
index cb954cd..c568a9d 100644
--- a/arch/arc/include/asm/setup.h
+++ b/arch/arc/include/asm/setup.h
@@ -31,6 +31,7 @@
void setup_processor(void);
void __init setup_arch_memory(void);
+long __init arc_get_mem_sz(void);
/* Helpers used in arc_*_mumbojumbo routines */
#define IS_AVAIL1(v, s) ((v) ? s : "")
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 689dd86..8b90d25 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -71,14 +71,14 @@
GET_CPU_ID r5
cmp r5, 0
mov.nz r0, r5
-#ifdef CONFIG_ARC_SMP_HALT_ON_RESET
- ; Non-Master can proceed as system would be booted sufficiently
- jnz first_lines_of_secondary
-#else
+ bz .Lmaster_proceed
+
; Non-Masters wait for Master to boot enough and bring them up
- jnz arc_platform_smp_wait_to_boot
-#endif
- ; Master falls thru
+ ; when they resume, tail-call to entry point
+ mov blink, @first_lines_of_secondary
+ j arc_platform_smp_wait_to_boot
+
+.Lmaster_proceed:
#endif
; Clear BSS before updating any globals
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 994dca7..ecef0fb 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -77,20 +77,20 @@
static void arcv2_irq_mask(struct irq_data *data)
{
- write_aux_reg(AUX_IRQ_SELECT, data->irq);
+ write_aux_reg(AUX_IRQ_SELECT, data->hwirq);
write_aux_reg(AUX_IRQ_ENABLE, 0);
}
static void arcv2_irq_unmask(struct irq_data *data)
{
- write_aux_reg(AUX_IRQ_SELECT, data->irq);
+ write_aux_reg(AUX_IRQ_SELECT, data->hwirq);
write_aux_reg(AUX_IRQ_ENABLE, 1);
}
void arcv2_irq_enable(struct irq_data *data)
{
/* set default priority */
- write_aux_reg(AUX_IRQ_SELECT, data->irq);
+ write_aux_reg(AUX_IRQ_SELECT, data->hwirq);
write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
/*
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index ce9deb9..8c1fd5c 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -57,7 +57,7 @@
unsigned int ienb;
ienb = read_aux_reg(AUX_IENABLE);
- ienb &= ~(1 << data->irq);
+ ienb &= ~(1 << data->hwirq);
write_aux_reg(AUX_IENABLE, ienb);
}
@@ -66,7 +66,7 @@
unsigned int ienb;
ienb = read_aux_reg(AUX_IENABLE);
- ienb |= (1 << data->irq);
+ ienb |= (1 << data->hwirq);
write_aux_reg(AUX_IENABLE, ienb);
}
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 560c4af..9f6b68f 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -10,6 +10,7 @@
#include <linux/smp.h>
#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
#include <linux/spinlock.h>
#include <soc/arc/mcip.h>
#include <asm/irqflags-arcv2.h>
@@ -92,11 +93,10 @@
READ_BCR(ARC_REG_MCIP_BCR, mp);
sprintf(smp_cpuinfo_buf,
- "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n",
+ "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n",
mp.ver, mp.num_cores,
IS_AVAIL1(mp.ipi, "IPI "),
IS_AVAIL1(mp.idu, "IDU "),
- IS_AVAIL1(mp.llm, "LLM "),
IS_AVAIL1(mp.dbg, "DEBUG "),
IS_AVAIL1(mp.gfrc, "GFRC"));
@@ -174,7 +174,6 @@
raw_spin_unlock_irqrestore(&mcip_lock, flags);
}
-#ifdef CONFIG_SMP
static int
idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
bool force)
@@ -204,12 +203,27 @@
return IRQ_SET_MASK_OK;
}
-#endif
+
+static void idu_irq_enable(struct irq_data *data)
+{
+ /*
+ * By default send all common interrupts to all available online CPUs.
+ * The affinity of common interrupts in IDU must be set manually since
+ * in some cases the kernel will not call irq_set_affinity() by itself:
+ * 1. When the kernel is not configured with support of SMP.
+ * 2. When the kernel is configured with support of SMP but upper
+ * interrupt controllers does not support setting of the affinity
+ * and cannot propagate it to IDU.
+ */
+ idu_irq_set_affinity(data, cpu_online_mask, false);
+ idu_irq_unmask(data);
+}
static struct irq_chip idu_irq_chip = {
.name = "MCIP IDU Intc",
.irq_mask = idu_irq_mask,
.irq_unmask = idu_irq_unmask,
+ .irq_enable = idu_irq_enable,
#ifdef CONFIG_SMP
.irq_set_affinity = idu_irq_set_affinity,
#endif
@@ -221,10 +235,13 @@
static void idu_cascade_isr(struct irq_desc *desc)
{
struct irq_domain *idu_domain = irq_desc_get_handler_data(desc);
+ struct irq_chip *core_chip = irq_desc_get_chip(desc);
irq_hw_number_t core_hwirq = irqd_to_hwirq(irq_desc_get_irq_data(desc));
irq_hw_number_t idu_hwirq = core_hwirq - idu_first_hwirq;
+ chained_irq_enter(core_chip, desc);
generic_handle_irq(irq_find_mapping(idu_domain, idu_hwirq));
+ chained_irq_exit(core_chip, desc);
}
static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq)
@@ -239,36 +256,14 @@
const u32 *intspec, unsigned int intsize,
irq_hw_number_t *out_hwirq, unsigned int *out_type)
{
- irq_hw_number_t hwirq = *out_hwirq = intspec[0];
- int distri = intspec[1];
- unsigned long flags;
-
+ /*
+ * Ignore value of interrupt distribution mode for common interrupts in
+ * IDU which resides in intspec[1] since setting an affinity using value
+ * from Device Tree is deprecated in ARC.
+ */
+ *out_hwirq = intspec[0];
*out_type = IRQ_TYPE_NONE;
- /* XXX: validate distribution scheme again online cpu mask */
- if (distri == 0) {
- /* 0 - Round Robin to all cpus, otherwise 1 bit per core */
- raw_spin_lock_irqsave(&mcip_lock, flags);
- idu_set_dest(hwirq, BIT(num_online_cpus()) - 1);
- idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
- raw_spin_unlock_irqrestore(&mcip_lock, flags);
- } else {
- /*
- * DEST based distribution for Level Triggered intr can only
- * have 1 CPU, so generalize it to always contain 1 cpu
- */
- int cpu = ffs(distri);
-
- if (cpu != fls(distri))
- pr_warn("IDU irq %lx distri mode set to cpu %x\n",
- hwirq, cpu);
-
- raw_spin_lock_irqsave(&mcip_lock, flags);
- idu_set_dest(hwirq, cpu);
- idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_DEST);
- raw_spin_unlock_irqrestore(&mcip_lock, flags);
- }
-
return 0;
}
diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c
index 42e964d..3d99a60 100644
--- a/arch/arc/kernel/module.c
+++ b/arch/arc/kernel/module.c
@@ -32,8 +32,8 @@
#ifdef CONFIG_ARC_DW2_UNWIND
mod->arch.unw_sec_idx = 0;
mod->arch.unw_info = NULL;
- mod->arch.secstr = secstr;
#endif
+ mod->arch.secstr = secstr;
return 0;
}
@@ -113,8 +113,10 @@
}
+#ifdef CONFIG_ARC_DW2_UNWIND
if (strcmp(module->arch.secstr+sechdrs[tgtsec].sh_name, ".eh_frame") == 0)
module->arch.unw_sec_idx = tgtsec;
+#endif
return 0;
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 88674d9..2afbafa 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -90,22 +90,37 @@
*/
static volatile int wake_flag;
+#ifdef CONFIG_ISA_ARCOMPACT
+
+#define __boot_read(f) f
+#define __boot_write(f, v) f = v
+
+#else
+
+#define __boot_read(f) arc_read_uncached_32(&f)
+#define __boot_write(f, v) arc_write_uncached_32(&f, v)
+
+#endif
+
static void arc_default_smp_cpu_kick(int cpu, unsigned long pc)
{
BUG_ON(cpu == 0);
- wake_flag = cpu;
+
+ __boot_write(wake_flag, cpu);
}
void arc_platform_smp_wait_to_boot(int cpu)
{
- while (wake_flag != cpu)
+ /* for halt-on-reset, we've waited already */
+ if (IS_ENABLED(CONFIG_ARC_SMP_HALT_ON_RESET))
+ return;
+
+ while (__boot_read(wake_flag) != cpu)
;
- wake_flag = 0;
- __asm__ __volatile__("j @first_lines_of_secondary \n");
+ __boot_write(wake_flag, 0);
}
-
const char *arc_platform_smp_cpuinfo(void)
{
return plat_smp_ops.info ? : "";
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index abd961f..5f69c3b 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -241,8 +241,9 @@
if (state.fault)
goto fault;
+ /* clear any remanants of delay slot */
if (delay_mode(regs)) {
- regs->ret = regs->bta;
+ regs->ret = regs->bta & ~1U;
regs->status32 &= ~STATUS_DE_MASK;
} else {
regs->ret += state.instr_len;
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index ec86ac0..d408fa2 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -23,7 +23,7 @@
static int l2_line_sz;
static int ioc_exists;
-int slc_enable = 1, ioc_enable = 0;
+int slc_enable = 1, ioc_enable = 1;
unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */
unsigned long perip_end = 0xFFFFFFFF; /* legacy value */
@@ -271,7 +271,11 @@
/*
* For ARC700 MMUv3 I-cache and D-cache flushes
- * Also reused for HS38 aliasing I-cache configuration
+ * - ARC700 programming model requires paddr and vaddr be passed in seperate
+ * AUX registers (*_IV*L and *_PTAG respectively) irrespective of whether the
+ * caches actually alias or not.
+ * - For HS38, only the aliasing I-cache configuration uses the PTAG reg
+ * (non aliasing I-cache version doesn't; while D-cache can't possibly alias)
*/
static inline
void __cache_line_loop_v3(phys_addr_t paddr, unsigned long vaddr,
@@ -458,6 +462,21 @@
__after_dc_op(op);
}
+static inline void __dc_disable(void)
+{
+ const int r = ARC_REG_DC_CTRL;
+
+ __dc_entire_op(OP_FLUSH_N_INV);
+ write_aux_reg(r, read_aux_reg(r) | DC_CTRL_DIS);
+}
+
+static void __dc_enable(void)
+{
+ const int r = ARC_REG_DC_CTRL;
+
+ write_aux_reg(r, read_aux_reg(r) & ~DC_CTRL_DIS);
+}
+
/* For kernel mappings cache operation: index is same as paddr */
#define __dc_line_op_k(p, sz, op) __dc_line_op(p, p, sz, op)
@@ -483,6 +502,8 @@
#else
#define __dc_entire_op(op)
+#define __dc_disable()
+#define __dc_enable()
#define __dc_line_op(paddr, vaddr, sz, op)
#define __dc_line_op_k(paddr, sz, op)
@@ -597,6 +618,40 @@
#endif
}
+noinline static void slc_entire_op(const int op)
+{
+ unsigned int ctrl, r = ARC_REG_SLC_CTRL;
+
+ ctrl = read_aux_reg(r);
+
+ if (!(op & OP_FLUSH)) /* i.e. OP_INV */
+ ctrl &= ~SLC_CTRL_IM; /* clear IM: Disable flush before Inv */
+ else
+ ctrl |= SLC_CTRL_IM;
+
+ write_aux_reg(r, ctrl);
+
+ write_aux_reg(ARC_REG_SLC_INVALIDATE, 1);
+
+ /* Important to wait for flush to complete */
+ while (read_aux_reg(r) & SLC_CTRL_BUSY);
+}
+
+static inline void arc_slc_disable(void)
+{
+ const int r = ARC_REG_SLC_CTRL;
+
+ slc_entire_op(OP_FLUSH_N_INV);
+ write_aux_reg(r, read_aux_reg(r) | SLC_CTRL_DIS);
+}
+
+static inline void arc_slc_enable(void)
+{
+ const int r = ARC_REG_SLC_CTRL;
+
+ write_aux_reg(r, read_aux_reg(r) & ~SLC_CTRL_DIS);
+}
+
/***********************************************************
* Exported APIs
*/
@@ -923,21 +978,54 @@
return 0;
}
-void arc_cache_init(void)
+/*
+ * IO-Coherency (IOC) setup rules:
+ *
+ * 1. Needs to be at system level, so only once by Master core
+ * Non-Masters need not be accessing caches at that time
+ * - They are either HALT_ON_RESET and kick started much later or
+ * - if run on reset, need to ensure that arc_platform_smp_wait_to_boot()
+ * doesn't perturb caches or coherency unit
+ *
+ * 2. caches (L1 and SLC) need to be purged (flush+inv) before setting up IOC,
+ * otherwise any straggler data might behave strangely post IOC enabling
+ *
+ * 3. All Caches need to be disabled when setting up IOC to elide any in-flight
+ * Coherency transactions
+ */
+noinline void __init arc_ioc_setup(void)
{
- unsigned int __maybe_unused cpu = smp_processor_id();
- char str[256];
+ unsigned int ap_sz;
- printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
+ /* Flush + invalidate + disable L1 dcache */
+ __dc_disable();
+
+ /* Flush + invalidate SLC */
+ if (read_aux_reg(ARC_REG_SLC_BCR))
+ slc_entire_op(OP_FLUSH_N_INV);
+
+ /* IOC Aperture start: TDB: handle non default CONFIG_LINUX_LINK_BASE */
+ write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000);
/*
- * Only master CPU needs to execute rest of function:
- * - Assume SMP so all cores will have same cache config so
- * any geomtry checks will be same for all
- * - IOC setup / dma callbacks only need to be setup once
+ * IOC Aperture size:
+ * decoded as 2 ^ (SIZE + 2) KB: so setting 0x11 implies 512M
+ * TBD: fix for PGU + 1GB of low mem
+ * TBD: fix for PAE
*/
- if (cpu)
- return;
+ ap_sz = order_base_2(arc_get_mem_sz()/1024) - 2;
+ write_aux_reg(ARC_REG_IO_COH_AP0_SIZE, ap_sz);
+
+ write_aux_reg(ARC_REG_IO_COH_PARTIAL, 1);
+ write_aux_reg(ARC_REG_IO_COH_ENABLE, 1);
+
+ /* Re-enable L1 dcache */
+ __dc_enable();
+}
+
+void __init arc_cache_init_master(void)
+{
+ unsigned int __maybe_unused cpu = smp_processor_id();
if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
@@ -985,30 +1073,14 @@
}
}
- if (is_isa_arcv2() && l2_line_sz && !slc_enable) {
+ /* Note that SLC disable not formally supported till HS 3.0 */
+ if (is_isa_arcv2() && l2_line_sz && !slc_enable)
+ arc_slc_disable();
- /* IM set : flush before invalidate */
- write_aux_reg(ARC_REG_SLC_CTRL,
- read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_IM);
-
- write_aux_reg(ARC_REG_SLC_INVALIDATE, 1);
-
- /* Important to wait for flush to complete */
- while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
- write_aux_reg(ARC_REG_SLC_CTRL,
- read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_DISABLE);
- }
+ if (is_isa_arcv2() && ioc_enable)
+ arc_ioc_setup();
if (is_isa_arcv2() && ioc_enable) {
- /* IO coherency base - 0x8z */
- write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000);
- /* IO coherency aperture size - 512Mb: 0x8z-0xAz */
- write_aux_reg(ARC_REG_IO_COH_AP0_SIZE, 0x11);
- /* Enable partial writes */
- write_aux_reg(ARC_REG_IO_COH_PARTIAL, 1);
- /* Enable IO coherency */
- write_aux_reg(ARC_REG_IO_COH_ENABLE, 1);
-
__dma_cache_wback_inv = __dma_cache_wback_inv_ioc;
__dma_cache_inv = __dma_cache_inv_ioc;
__dma_cache_wback = __dma_cache_wback_ioc;
@@ -1022,3 +1094,20 @@
__dma_cache_wback = __dma_cache_wback_l1;
}
}
+
+void __ref arc_cache_init(void)
+{
+ unsigned int __maybe_unused cpu = smp_processor_id();
+ char str[256];
+
+ printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
+
+ /*
+ * Only master CPU needs to execute rest of function:
+ * - Assume SMP so all cores will have same cache config so
+ * any geomtry checks will be same for all
+ * - IOC setup / dma callbacks only need to be setup once
+ */
+ if (!cpu)
+ arc_cache_init_master();
+}
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 399e2f2..8c9415e 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -40,6 +40,11 @@
EXPORT_SYMBOL(node_data);
#endif
+long __init arc_get_mem_sz(void)
+{
+ return low_mem_sz;
+}
+
/* User can over-ride above with "mem=nnn[KkMm]" in cmdline */
static int __init setup_mem_sz(char *str)
{
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 7327250..01d178a 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -617,7 +617,7 @@
orion5x-lacie-ethernet-disk-mini-v2.dtb \
orion5x-linkstation-lsgl.dtb \
orion5x-linkstation-lswtgl.dtb \
- orion5x-lschl.dtb \
+ orion5x-linkstation-lschl.dtb \
orion5x-lswsgl.dtb \
orion5x-maxtor-shared-storage-2.dtb \
orion5x-netgear-wnr854t.dtb \
@@ -846,6 +846,7 @@
sun8i-a83t-allwinner-h8homlet-v2.dtb \
sun8i-a83t-cubietruck-plus.dtb \
sun8i-h3-bananapi-m2-plus.dtb \
+ sun8i-h3-nanopi-m1.dtb \
sun8i-h3-nanopi-neo.dtb \
sun8i-h3-orangepi-2.dtb \
sun8i-h3-orangepi-lite.dtb \
diff --git a/arch/arm/boot/dts/am335x-icev2.dts b/arch/arm/boot/dts/am335x-icev2.dts
index 1463df3..8ed46f9 100644
--- a/arch/arm/boot/dts/am335x-icev2.dts
+++ b/arch/arm/boot/dts/am335x-icev2.dts
@@ -170,7 +170,6 @@
AM33XX_IOPAD(0x8fc, PIN_INPUT_PULLUP | MUX_MODE0) /* (G16) mmc0_dat0.mmc0_dat0 */
AM33XX_IOPAD(0x900, PIN_INPUT_PULLUP | MUX_MODE0) /* (G17) mmc0_clk.mmc0_clk */
AM33XX_IOPAD(0x904, PIN_INPUT_PULLUP | MUX_MODE0) /* (G18) mmc0_cmd.mmc0_cmd */
- AM33XX_IOPAD(0x960, PIN_INPUT_PULLUP | MUX_MODE5) /* (C15) spi0_cs1.mmc0_sdcd */
>;
};
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index b6142bd..15f07f9 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -160,7 +160,7 @@
axi {
compatible = "simple-bus";
- ranges = <0x00000000 0x18000000 0x0011c40a>;
+ ranges = <0x00000000 0x18000000 0x0011c40c>;
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts
index 41de15f..78492a0 100644
--- a/arch/arm/boot/dts/da850-evm.dts
+++ b/arch/arm/boot/dts/da850-evm.dts
@@ -99,6 +99,7 @@
#size-cells = <1>;
compatible = "m25p64";
spi-max-frequency = <30000000>;
+ m25p,fast-read;
reg = <0>;
partition@0 {
label = "U-Boot-SPL";
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 1faf24a..5ba1616 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1378,6 +1378,7 @@
phy-names = "sata-phy";
clocks = <&sata_ref_clk>;
ti,hwmods = "sata";
+ ports-implemented = <0x1>;
};
rtc: rtc@48838000 {
diff --git a/arch/arm/boot/dts/dra72-evm-revc.dts b/arch/arm/boot/dts/dra72-evm-revc.dts
index c3d939c..3f808a4 100644
--- a/arch/arm/boot/dts/dra72-evm-revc.dts
+++ b/arch/arm/boot/dts/dra72-evm-revc.dts
@@ -75,6 +75,6 @@
ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
ti,tx-internal-delay = <DP83867_RGMIIDCTL_250_PS>;
ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_8_B_NIB>;
- ti,min-output-imepdance;
+ ti,min-output-impedance;
};
};
diff --git a/arch/arm/boot/dts/imx1.dtsi b/arch/arm/boot/dts/imx1.dtsi
index b792eee..2ee40bc 100644
--- a/arch/arm/boot/dts/imx1.dtsi
+++ b/arch/arm/boot/dts/imx1.dtsi
@@ -18,6 +18,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
gpio0 = &gpio1;
diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi
index ac2a9da..43ccbbf 100644
--- a/arch/arm/boot/dts/imx23.dtsi
+++ b/arch/arm/boot/dts/imx23.dtsi
@@ -16,6 +16,14 @@
#size-cells = <1>;
interrupt-parent = <&icoll>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
gpio0 = &gpio0;
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index 831d09a..acd4756 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -14,6 +14,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index 9d8b596..b397384 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -19,6 +19,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 3aabf65..d6a2190 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -17,6 +17,14 @@
#size-cells = <1>;
interrupt-parent = <&icoll>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &mac0;
diff --git a/arch/arm/boot/dts/imx31.dtsi b/arch/arm/boot/dts/imx31.dtsi
index 85cd8be..23b0d2c 100644
--- a/arch/arm/boot/dts/imx31.dtsi
+++ b/arch/arm/boot/dts/imx31.dtsi
@@ -12,6 +12,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
serial0 = &uart1;
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index 9f40e62..d0496c6 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -13,6 +13,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx50.dtsi b/arch/arm/boot/dts/imx50.dtsi
index fe0221e..ceae909 100644
--- a/arch/arm/boot/dts/imx50.dtsi
+++ b/arch/arm/boot/dts/imx50.dtsi
@@ -17,6 +17,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi
index 33526ca..1ee1d54 100644
--- a/arch/arm/boot/dts/imx51.dtsi
+++ b/arch/arm/boot/dts/imx51.dtsi
@@ -19,6 +19,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index ca51dc0..2e516f4 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -19,6 +19,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi
index 1ade195..7aa120f 100644
--- a/arch/arm/boot/dts/imx6dl.dtsi
+++ b/arch/arm/boot/dts/imx6dl.dtsi
@@ -137,7 +137,7 @@
&gpio4 {
gpio-ranges = <&iomuxc 5 136 1>, <&iomuxc 6 145 1>, <&iomuxc 7 150 1>,
<&iomuxc 8 146 1>, <&iomuxc 9 151 1>, <&iomuxc 10 147 1>,
- <&iomuxc 11 151 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>,
+ <&iomuxc 11 152 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>,
<&iomuxc 14 149 1>, <&iomuxc 15 154 1>, <&iomuxc 16 39 7>,
<&iomuxc 23 56 1>, <&iomuxc 24 61 7>, <&iomuxc 31 46 1>;
};
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
index 34887a1..47ba972 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
@@ -319,8 +319,6 @@
compatible = "fsl,imx6q-nitrogen6_max-sgtl5000",
"fsl,imx-audio-sgtl5000";
model = "imx6q-nitrogen6_max-sgtl5000";
- pinctrl-names = "default";
- pinctrl-0 = <&pinctrl_sgtl5000>;
ssi-controller = <&ssi1>;
audio-codec = <&codec>;
audio-routing =
@@ -402,6 +400,8 @@
codec: sgtl5000@0a {
compatible = "fsl,sgtl5000";
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_sgtl5000>;
reg = <0x0a>;
clocks = <&clks IMX6QDL_CLK_CKO>;
VDDA-supply = <®_2p5v>;
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi
index d80f21a..31d4cc6 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi
@@ -250,8 +250,6 @@
compatible = "fsl,imx6q-nitrogen6_som2-sgtl5000",
"fsl,imx-audio-sgtl5000";
model = "imx6q-nitrogen6_som2-sgtl5000";
- pinctrl-names = "default";
- pinctrl-0 = <&pinctrl_sgtl5000>;
ssi-controller = <&ssi1>;
audio-codec = <&codec>;
audio-routing =
@@ -320,6 +318,8 @@
codec: sgtl5000@0a {
compatible = "fsl,sgtl5000";
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_sgtl5000>;
reg = <0x0a>;
clocks = <&clks IMX6QDL_CLK_CKO>;
VDDA-supply = <®_2p5v>;
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 89b834f..e7d30f4 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -16,6 +16,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi
index 19cbd87..cc9572e 100644
--- a/arch/arm/boot/dts/imx6sl.dtsi
+++ b/arch/arm/boot/dts/imx6sl.dtsi
@@ -14,6 +14,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index 10f3330..dd4ec85 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -15,6 +15,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
can0 = &flexcan1;
diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi
index 39845a7..53d3f8e 100644
--- a/arch/arm/boot/dts/imx6ul.dtsi
+++ b/arch/arm/boot/dts/imx6ul.dtsi
@@ -15,6 +15,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
ethernet0 = &fec1;
diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi
index 8ff2cbdd..be33dfc 100644
--- a/arch/arm/boot/dts/imx7s.dtsi
+++ b/arch/arm/boot/dts/imx7s.dtsi
@@ -50,6 +50,14 @@
/ {
#address-cells = <1>;
#size-cells = <1>;
+ /*
+ * The decompressor and also some bootloaders rely on a
+ * pre-existing /chosen node to be available to insert the
+ * command line and merge other ATAGS info.
+ * Also for U-Boot there must be a pre-existing /memory node.
+ */
+ chosen {};
+ memory { device_type = "memory"; reg = <0 0>; };
aliases {
gpio0 = &gpio1;
diff --git a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
index da85984..38faa90 100644
--- a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
@@ -158,7 +158,7 @@
&mmc1 {
interrupts-extended = <&intc 83 &omap3_pmx_core 0x11a>;
pinctrl-names = "default";
- pinctrl-0 = <&mmc1_pins &mmc1_cd>;
+ pinctrl-0 = <&mmc1_pins>;
wp-gpios = <&gpio4 30 GPIO_ACTIVE_HIGH>; /* gpio_126 */
cd-gpios = <&gpio4 14 IRQ_TYPE_LEVEL_LOW>; /* gpio_110 */
vmmc-supply = <&vmmc1>;
@@ -193,7 +193,8 @@
OMAP3_CORE1_IOPAD(0x214a, PIN_INPUT | MUX_MODE0) /* sdmmc1_dat1.sdmmc1_dat1 */
OMAP3_CORE1_IOPAD(0x214c, PIN_INPUT | MUX_MODE0) /* sdmmc1_dat2.sdmmc1_dat2 */
OMAP3_CORE1_IOPAD(0x214e, PIN_INPUT | MUX_MODE0) /* sdmmc1_dat3.sdmmc1_dat3 */
- OMAP3_CORE1_IOPAD(0x2132, PIN_INPUT_PULLUP | MUX_MODE4) /* cam_strobe.gpio_126 sdmmc1_wp*/
+ OMAP3_CORE1_IOPAD(0x2132, PIN_INPUT_PULLUP | MUX_MODE4) /* cam_strobe.gpio_126 */
+ OMAP3_CORE1_IOPAD(0x212c, PIN_INPUT_PULLUP | MUX_MODE4) /* cam_d11.gpio_110 */
>;
};
@@ -242,12 +243,6 @@
OMAP3_WKUP_IOPAD(0x2a16, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4) /* sys_boot6.gpio_8 */
>;
};
-
- mmc1_cd: pinmux_mmc1_cd {
- pinctrl-single,pins = <
- OMAP3_WKUP_IOPAD(0x212c, PIN_INPUT_PULLUP | MUX_MODE4) /* cam_d11.gpio_110 */
- >;
- };
};
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 7cd92ba..0844737 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -988,6 +988,7 @@
phy-names = "sata-phy";
clocks = <&sata_ref_clk>;
ti,hwmods = "sata";
+ ports-implemented = <0x1>;
};
dss: dss@58000000 {
diff --git a/arch/arm/boot/dts/orion5x-lschl.dts b/arch/arm/boot/dts/orion5x-linkstation-lschl.dts
similarity index 97%
rename from arch/arm/boot/dts/orion5x-lschl.dts
rename to arch/arm/boot/dts/orion5x-linkstation-lschl.dts
index 9474092..ea6c881 100644
--- a/arch/arm/boot/dts/orion5x-lschl.dts
+++ b/arch/arm/boot/dts/orion5x-linkstation-lschl.dts
@@ -2,7 +2,7 @@
* Device Tree file for Buffalo Linkstation LS-CHLv3
*
* Copyright (C) 2016 Ash Hughes <ashley.hughes@blueyonder.co.uk>
- * Copyright (C) 2015, 2016
+ * Copyright (C) 2015-2017
* Roger Shimizu <rogershimizu@gmail.com>
*
* This file is dual-licensed: you can use it either under the terms
@@ -52,7 +52,7 @@
#include <dt-bindings/gpio/gpio.h>
/ {
- model = "Buffalo Linkstation Live v3 (LS-CHL)";
+ model = "Buffalo Linkstation LiveV3 (LS-CHL)";
compatible = "buffalo,lschl", "marvell,orion5x-88f5182", "marvell,orion5x";
memory { /* 128 MB */
diff --git a/arch/arm/boot/dts/qcom-mdm9615.dtsi b/arch/arm/boot/dts/qcom-mdm9615.dtsi
index 5ae4ec5..c852b69 100644
--- a/arch/arm/boot/dts/qcom-mdm9615.dtsi
+++ b/arch/arm/boot/dts/qcom-mdm9615.dtsi
@@ -357,7 +357,7 @@
};
amba {
- compatible = "arm,amba-bus";
+ compatible = "simple-bus";
#address-cells = <1>;
#size-cells = <1>;
ranges;
diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi
index c8b2944..ace97e8 100644
--- a/arch/arm/boot/dts/stih407-family.dtsi
+++ b/arch/arm/boot/dts/stih407-family.dtsi
@@ -680,6 +680,7 @@
phy-names = "usb2-phy", "usb3-phy";
phys = <&usb2_picophy0>,
<&phy_port2 PHY_TYPE_USB3>;
+ snps,dis_u3_susphy_quirk;
};
};
diff --git a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts
index 735914f..7cae328 100644
--- a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts
+++ b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts
@@ -140,6 +140,10 @@
cpu-supply = <®_dcdc3>;
};
+&de {
+ status = "okay";
+};
+
&ehci0 {
status = "okay";
};
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index 2b26175..e78faaf 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -234,6 +234,7 @@
de: display-engine {
compatible = "allwinner,sun6i-a31-display-engine";
allwinner,pipelines = <&fe0>;
+ status = "disabled";
};
soc@01c00000 {
diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts
index 5ea4915..10d3074 100644
--- a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts
+++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts
@@ -56,7 +56,7 @@
};
&pio {
- mmc2_pins_nrst: mmc2@0 {
+ mmc2_pins_nrst: mmc2-rst-pin {
allwinner,pins = "PC16";
allwinner,function = "gpio_out";
allwinner,drive = <SUN4I_PINCTRL_10_MA>;
diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig
index ea316c4..d3f1768 100644
--- a/arch/arm/configs/ezx_defconfig
+++ b/arch/arm/configs/ezx_defconfig
@@ -64,8 +64,8 @@
CONFIG_NETFILTER_NETLINK_QUEUE=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
CONFIG_NF_CONNTRACK_AMANDA=m
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig
index 18e59fe..7f479cd 100644
--- a/arch/arm/configs/imote2_defconfig
+++ b/arch/arm/configs/imote2_defconfig
@@ -56,8 +56,8 @@
CONFIG_NETFILTER_NETLINK_QUEUE=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
CONFIG_NF_CONNTRACK_AMANDA=m
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index b01a438..f57ec51 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -471,7 +471,7 @@
CONFIG_DW_WATCHDOG=y
CONFIG_DIGICOLOR_WATCHDOG=y
CONFIG_BCM2835_WDT=y
-CONFIG_BCM47XX_WATCHDOG=y
+CONFIG_BCM47XX_WDT=y
CONFIG_BCM7038_WDT=m
CONFIG_BCM_KONA_WDT=y
CONFIG_MFD_ACT8945A=y
@@ -824,6 +824,7 @@
CONFIG_QCOM_WCNSS_CTRL=m
CONFIG_ROCKCHIP_PM_DOMAINS=y
CONFIG_COMMON_CLK_QCOM=y
+CONFIG_QCOM_CLK_RPM=y
CONFIG_CHROME_PLATFORMS=y
CONFIG_STAGING_BOARD=y
CONFIG_CROS_EC_CHARDEV=m
@@ -893,7 +894,7 @@
CONFIG_RASPBERRYPI_FIRMWARE=y
CONFIG_EFI_VARS=m
CONFIG_EFI_CAPSULE_LOADER=m
-CONFIG_CONFIG_BCM47XX_NVRAM=y
+CONFIG_BCM47XX_NVRAM=y
CONFIG_BCM47XX_SPROM=y
CONFIG_EXT4_FS=y
CONFIG_AUTOFS4_FS=y
diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig
index 4364040..1e6c48d 100644
--- a/arch/arm/configs/s3c2410_defconfig
+++ b/arch/arm/configs/s3c2410_defconfig
@@ -86,9 +86,9 @@
CONFIG_NETFILTER=y
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
CONFIG_NF_CONNTRACK_AMANDA=m
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index efb2175..b14e8c7 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -2,7 +2,6 @@
generic-y += bitsperlong.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += early_ioremap.h
generic-y += emergency-restart.h
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 522b5fe..b62eaeb 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -94,6 +94,9 @@
#define ARM_CPU_XSCALE_ARCH_V2 0x4000
#define ARM_CPU_XSCALE_ARCH_V3 0x6000
+/* Qualcomm implemented cores */
+#define ARM_CPU_PART_SCORPION 0x510002d0
+
extern unsigned int processor_id;
#ifdef CONFIG_CPU_CP15
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 0b06f53..e4e6a9d6 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -55,6 +55,7 @@
#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
#define __efi_call_early(f, ...) f(__VA_ARGS__)
+#define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__)
#define efi_is_64bit() (false)
#define efi_call_proto(protocol, f, instance, ...) \
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index bfe2a2f..22b7311 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -54,6 +54,24 @@
#define ftrace_return_address(n) return_address(n)
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+
+static inline bool arch_syscall_match_sym_name(const char *sym,
+ const char *name)
+{
+ if (!strcmp(sym, "sys_mmap2"))
+ sym = "sys_mmap_pgoff";
+ else if (!strcmp(sym, "sys_statfs64_wrapper"))
+ sym = "sys_statfs64";
+ else if (!strcmp(sym, "sys_fstatfs64_wrapper"))
+ sym = "sys_fstatfs64";
+ else if (!strcmp(sym, "sys_arm_fadvise64_64"))
+ sym = "sys_fadvise64_64";
+
+ /* Ignore case since sym may start with "SyS" instead of "sys" */
+ return !strcasecmp(sym, name);
+}
+
#endif /* ifndef __ASSEMBLY__ */
#endif /* _ASM_ARM_FTRACE */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 1f59ea05..b7e0125 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -478,11 +478,10 @@
arm_copy_from_user(void *to, const void __user *from, unsigned long n);
static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
+__arch_copy_from_user(void *to, const void __user *from, unsigned long n)
{
unsigned int __ua_flags;
- check_object_size(to, n, false);
__ua_flags = uaccess_save_and_enable();
n = arm_copy_from_user(to, from, n);
uaccess_restore(__ua_flags);
@@ -495,18 +494,15 @@
__copy_to_user_std(void __user *to, const void *from, unsigned long n);
static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+__arch_copy_to_user(void __user *to, const void *from, unsigned long n)
{
#ifndef CONFIG_UACCESS_WITH_MEMCPY
unsigned int __ua_flags;
-
- check_object_size(from, n, true);
__ua_flags = uaccess_save_and_enable();
n = arm_copy_to_user(to, from, n);
uaccess_restore(__ua_flags);
return n;
#else
- check_object_size(from, n, true);
return arm_copy_to_user(to, from, n);
#endif
}
@@ -526,25 +522,49 @@
}
#else
-#define __copy_from_user(to, from, n) (memcpy(to, (void __force *)from, n), 0)
-#define __copy_to_user(to, from, n) (memcpy((void __force *)to, from, n), 0)
+#define __arch_copy_from_user(to, from, n) \
+ (memcpy(to, (void __force *)from, n), 0)
+#define __arch_copy_to_user(to, from, n) \
+ (memcpy((void __force *)to, from, n), 0)
#define __clear_user(addr, n) (memset((void __force *)addr, 0, n), 0)
#endif
-static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
+static inline unsigned long __must_check
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ check_object_size(to, n, false);
+ return __arch_copy_from_user(to, from, n);
+}
+
+static inline unsigned long __must_check
+copy_from_user(void *to, const void __user *from, unsigned long n)
{
unsigned long res = n;
+
+ check_object_size(to, n, false);
+
if (likely(access_ok(VERIFY_READ, from, n)))
- res = __copy_from_user(to, from, n);
+ res = __arch_copy_from_user(to, from, n);
if (unlikely(res))
memset(to + (n - res), 0, res);
return res;
}
-static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
{
+ check_object_size(from, n, true);
+
+ return __arch_copy_to_user(to, from, n);
+}
+
+static inline unsigned long __must_check
+copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ check_object_size(from, n, true);
+
if (access_ok(VERIFY_WRITE, to, n))
- n = __copy_to_user(to, from, n);
+ n = __arch_copy_to_user(to, from, n);
return n;
}
diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h
index a2e75b8..6dae195 100644
--- a/arch/arm/include/asm/virt.h
+++ b/arch/arm/include/asm/virt.h
@@ -80,6 +80,11 @@
return false;
}
+static inline bool has_vhe(void)
+{
+ return false;
+}
+
/* The section containing the hypervisor idmap text */
extern char __hyp_idmap_text_start[];
extern char __hyp_idmap_text_end[];
diff --git a/arch/arm/include/asm/types.h b/arch/arm/include/uapi/asm/types.h
similarity index 93%
rename from arch/arm/include/asm/types.h
rename to arch/arm/include/uapi/asm/types.h
index a53cdb8..9435a42 100644
--- a/arch/arm/include/asm/types.h
+++ b/arch/arm/include/uapi/asm/types.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_TYPES_H
-#define _ASM_TYPES_H
+#ifndef _UAPI_ASM_TYPES_H
+#define _UAPI_ASM_TYPES_H
#include <asm-generic/int-ll64.h>
@@ -37,4 +37,4 @@
#define __UINTPTR_TYPE__ unsigned long
#endif
-#endif /* _ASM_TYPES_H */
+#endif /* _UAPI_ASM_TYPES_H */
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 188180b..be3b3fb 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -1063,6 +1063,22 @@
return 0;
}
+ /*
+ * Scorpion CPUs (at least those in APQ8060) seem to set DBGPRSR.SPD
+ * whenever a WFI is issued, even if the core is not powered down, in
+ * violation of the architecture. When DBGPRSR.SPD is set, accesses to
+ * breakpoint and watchpoint registers are treated as undefined, so
+ * this results in boot time and runtime failures when these are
+ * accessed and we unexpectedly take a trap.
+ *
+ * It's not clear if/how this can be worked around, so we blacklist
+ * Scorpion CPUs to avoid these issues.
+ */
+ if (read_cpuid_part() == ARM_CPU_PART_SCORPION) {
+ pr_info("Scorpion CPU detected. Hardware breakpoints and watchpoints disabled\n");
+ return 0;
+ }
+
has_ossr = core_has_os_save_restore();
/* Determine how many BRPs/WRPs are available. */
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ce131ed..ae738a6 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -600,7 +600,7 @@
const void *kbuf, const void __user *ubuf)
{
int ret;
- struct pt_regs newregs;
+ struct pt_regs newregs = *task_pt_regs(target);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&newregs,
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 22313cb..9af0701 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -9,6 +9,7 @@
*/
#include <linux/preempt.h>
#include <linux/smp.h>
+#include <linux/uaccess.h>
#include <asm/smp_plat.h>
#include <asm/tlbflush.h>
@@ -40,8 +41,11 @@
static inline void ipi_flush_tlb_page(void *arg)
{
struct tlb_args *ta = (struct tlb_args *)arg;
+ unsigned int __ua_flags = uaccess_save_and_enable();
local_flush_tlb_page(ta->ta_vma, ta->ta_start);
+
+ uaccess_restore(__ua_flags);
}
static inline void ipi_flush_tlb_kernel_page(void *arg)
@@ -54,8 +58,11 @@
static inline void ipi_flush_tlb_range(void *arg)
{
struct tlb_args *ta = (struct tlb_args *)arg;
+ unsigned int __ua_flags = uaccess_save_and_enable();
local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+
+ uaccess_restore(__ua_flags);
}
static inline void ipi_flush_tlb_kernel_range(void *arg)
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 1167678..9d74464 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -1099,6 +1099,9 @@
__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
__cpu_init_stage2();
+ if (is_kernel_in_hyp_mode())
+ kvm_timer_init_vhe();
+
kvm_arm_init_debug();
}
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 8ecfd15..df73914 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -67,7 +67,7 @@
ENDPROC(__get_user_4)
ENTRY(__get_user_8)
- check_uaccess r0, 8, r1, r2, __get_user_bad
+ check_uaccess r0, 8, r1, r2, __get_user_bad8
#ifdef CONFIG_THUMB2_KERNEL
5: TUSER(ldr) r2, [r0]
6: TUSER(ldr) r3, [r0, #4]
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index 6991577..c03bf28 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -60,7 +60,6 @@
#define to_mmdc_pmu(p) container_of(p, struct mmdc_pmu, pmu)
-static enum cpuhp_state cpuhp_mmdc_state;
static int ddr_type;
struct fsl_mmdc_devtype_data {
@@ -82,6 +81,7 @@
#ifdef CONFIG_PERF_EVENTS
+static enum cpuhp_state cpuhp_mmdc_state;
static DEFINE_IDA(mmdc_ida);
PMU_EVENT_ATTR_STRING(total-cycles, mmdc_pmu_total_cycles, "event=0x00")
diff --git a/arch/arm/mach-omap1/dma.c b/arch/arm/mach-omap1/dma.c
index f6ba589..c821c1d 100644
--- a/arch/arm/mach-omap1/dma.c
+++ b/arch/arm/mach-omap1/dma.c
@@ -32,7 +32,6 @@
#include "soc.h"
#define OMAP1_DMA_BASE (0xfffed800)
-#define OMAP1_LOGICAL_DMA_CH_COUNT 17
static u32 enable_1510_mode;
@@ -348,8 +347,6 @@
goto exit_iounmap;
}
- d->lch_count = OMAP1_LOGICAL_DMA_CH_COUNT;
-
/* Valid attributes for omap1 plus processors */
if (cpu_is_omap15xx())
d->dev_caps = ENABLE_1510_MODE;
@@ -366,13 +363,14 @@
d->dev_caps |= CLEAR_CSR_ON_READ;
d->dev_caps |= IS_WORD_16;
- if (cpu_is_omap15xx())
- d->chan_count = 9;
- else if (cpu_is_omap16xx() || cpu_is_omap7xx()) {
- if (!(d->dev_caps & ENABLE_1510_MODE))
- d->chan_count = 16;
+ /* available logical channels */
+ if (cpu_is_omap15xx()) {
+ d->lch_count = 9;
+ } else {
+ if (d->dev_caps & ENABLE_1510_MODE)
+ d->lch_count = 9;
else
- d->chan_count = 9;
+ d->lch_count = 16;
}
p = dma_plat_info;
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 477910a..70c0047 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -161,7 +161,7 @@
.nshutdown_gpio = 162,
.dev_name = "/dev/ttyO1",
.flow_cntrl = 1,
- .baud_rate = 300000,
+ .baud_rate = 3000000,
};
static struct platform_device wl128x_device = {
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 2bb4b09..ad7d604 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -57,6 +57,7 @@
select PM
select PM_GENERIC_DOMAINS
select SYS_SUPPORTS_SH_MTU2
+ select RENESAS_OSTM
config ARCH_R8A73A4
bool "R-Mobile APE6 (R8A73A40)"
diff --git a/arch/arm/mach-ux500/pm.c b/arch/arm/mach-ux500/pm.c
index 8538910..a970e7f 100644
--- a/arch/arm/mach-ux500/pm.c
+++ b/arch/arm/mach-ux500/pm.c
@@ -134,8 +134,8 @@
*/
bool prcmu_is_cpu_in_wfi(int cpu)
{
- return readl(PRCM_ARM_WFI_STANDBY) & cpu ? PRCM_ARM_WFI_STANDBY_WFI1 :
- PRCM_ARM_WFI_STANDBY_WFI0;
+ return readl(PRCM_ARM_WFI_STANDBY) &
+ (cpu ? PRCM_ARM_WFI_STANDBY_WFI1 : PRCM_ARM_WFI_STANDBY_WFI0);
}
/*
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 3a2e678..0122ad1 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -610,9 +610,9 @@
void __init early_abt_enable(void)
{
- fsr_info[22].fn = early_abort_handler;
+ fsr_info[FSR_FS_AEA].fn = early_abort_handler;
local_abt_enable();
- fsr_info[22].fn = do_bad;
+ fsr_info[FSR_FS_AEA].fn = do_bad;
}
#ifndef CONFIG_ARM_LPAE
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index 67532f2..afc1f84 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -11,11 +11,15 @@
#define FSR_FS5_0 (0x3f)
#ifdef CONFIG_ARM_LPAE
+#define FSR_FS_AEA 17
+
static inline int fsr_fs(unsigned int fsr)
{
return fsr & FSR_FS5_0;
}
#else
+#define FSR_FS_AEA 22
+
static inline int fsr_fs(unsigned int fsr)
{
return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1117421..f7dfd6d5 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -96,7 +96,7 @@
select HAVE_RCU_TABLE_FREE
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_KPROBES
- select HAVE_KRETPROBES if HAVE_KPROBES
+ select HAVE_KRETPROBES
select IOMMU_DMA if IOMMU_SUPPORT
select IRQ_DOMAIN
select IRQ_FORCED_THREADING
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index eada0b5..0cbe24b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -55,6 +55,24 @@
#address-cells = <2>;
#size-cells = <2>;
+ reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ /* 16 MiB reserved for Hardware ROM Firmware */
+ hwrom_reserved: hwrom@0 {
+ reg = <0x0 0x0 0x0 0x1000000>;
+ no-map;
+ };
+
+ /* 2 MiB reserved for ARM Trusted Firmware (BL31) */
+ secmon_reserved: secmon@10000000 {
+ reg = <0x0 0x10000000 0x0 0x200000>;
+ no-map;
+ };
+ };
+
cpus {
#address-cells = <0x2>;
#size-cells = <0x0>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index 238fbea..c59403a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -137,6 +137,10 @@
};
};
+&scpi_clocks {
+ status = "disabled";
+};
+
&uart_AO {
status = "okay";
pinctrl-0 = <&uart_ao_a_pins>;
@@ -147,6 +151,18 @@
status = "okay";
pinctrl-0 = <ð_rgmii_pins>;
pinctrl-names = "default";
+ phy-handle = <ð_phy0>;
+
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ eth_phy0: ethernet-phy@0 {
+ reg = <0>;
+ eee-broken-1000t;
+ };
+ };
};
&ir {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 596240c..b353073 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -55,7 +55,7 @@
mboxes = <&mailbox 1 &mailbox 2>;
shmem = <&cpu_scp_lpri &cpu_scp_hpri>;
- clocks {
+ scpi_clocks: clocks {
compatible = "arm,scpi-clocks";
scpi_dvfs: scpi_clocks@0 {
diff --git a/arch/arm64/boot/dts/exynos/exynos5433.dtsi b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
index 64226d5..135890c 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
@@ -1367,7 +1367,7 @@
};
amba {
- compatible = "arm,amba-bus";
+ compatible = "simple-bus";
#address-cells = <1>;
#size-cells = <1>;
ranges;
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
index 3580896..ef1b9e5 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
@@ -27,7 +27,7 @@
stdout-path = "serial0:115200n8";
};
- memory {
+ memory@0 {
device_type = "memory";
reg = <0x0 0x0 0x0 0x40000000>;
};
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index 68a90833..54dc283 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -72,7 +72,7 @@
<1 10 0xf08>;
};
- amba_apu {
+ amba_apu: amba_apu@0 {
compatible = "simple-bus";
#address-cells = <2>;
#size-cells = <1>;
@@ -175,7 +175,7 @@
};
i2c0: i2c@ff020000 {
- compatible = "cdns,i2c-r1p10";
+ compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10";
status = "disabled";
interrupt-parent = <&gic>;
interrupts = <0 17 4>;
@@ -185,7 +185,7 @@
};
i2c1: i2c@ff030000 {
- compatible = "cdns,i2c-r1p10";
+ compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10";
status = "disabled";
interrupt-parent = <&gic>;
interrupts = <0 18 4>;
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index c53dbea..838dad5 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -193,15 +193,16 @@
cbz w6, .Lcbcencloop
ld1 {v0.16b}, [x5] /* get iv */
- enc_prepare w3, x2, x5
+ enc_prepare w3, x2, x6
.Lcbcencloop:
ld1 {v1.16b}, [x1], #16 /* get next pt block */
eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */
- encrypt_block v0, w3, x2, x5, w6
+ encrypt_block v0, w3, x2, x6, w7
st1 {v0.16b}, [x0], #16
subs w4, w4, #1
bne .Lcbcencloop
+ st1 {v0.16b}, [x5] /* return iv */
ret
AES_ENDPROC(aes_cbc_encrypt)
@@ -211,7 +212,7 @@
cbz w6, .LcbcdecloopNx
ld1 {v7.16b}, [x5] /* get iv */
- dec_prepare w3, x2, x5
+ dec_prepare w3, x2, x6
.LcbcdecloopNx:
#if INTERLEAVE >= 2
@@ -248,7 +249,7 @@
.Lcbcdecloop:
ld1 {v1.16b}, [x1], #16 /* get next ct block */
mov v0.16b, v1.16b /* ...and copy to v0 */
- decrypt_block v0, w3, x2, x5, w6
+ decrypt_block v0, w3, x2, x6, w7
eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */
mov v7.16b, v1.16b /* ct is next iv */
st1 {v0.16b}, [x0], #16
@@ -256,6 +257,7 @@
bne .Lcbcdecloop
.Lcbcdecout:
FRAME_POP
+ st1 {v7.16b}, [x5] /* return iv */
ret
AES_ENDPROC(aes_cbc_decrypt)
@@ -267,24 +269,15 @@
AES_ENTRY(aes_ctr_encrypt)
FRAME_PUSH
- cbnz w6, .Lctrfirst /* 1st time around? */
- umov x5, v4.d[1] /* keep swabbed ctr in reg */
- rev x5, x5
-#if INTERLEAVE >= 2
- cmn w5, w4 /* 32 bit overflow? */
- bcs .Lctrinc
- add x5, x5, #1 /* increment BE ctr */
- b .LctrincNx
-#else
- b .Lctrinc
-#endif
-.Lctrfirst:
+ cbz w6, .Lctrnotfirst /* 1st time around? */
enc_prepare w3, x2, x6
ld1 {v4.16b}, [x5]
- umov x5, v4.d[1] /* keep swabbed ctr in reg */
- rev x5, x5
+
+.Lctrnotfirst:
+ umov x8, v4.d[1] /* keep swabbed ctr in reg */
+ rev x8, x8
#if INTERLEAVE >= 2
- cmn w5, w4 /* 32 bit overflow? */
+ cmn w8, w4 /* 32 bit overflow? */
bcs .Lctrloop
.LctrloopNx:
subs w4, w4, #INTERLEAVE
@@ -292,11 +285,11 @@
#if INTERLEAVE == 2
mov v0.8b, v4.8b
mov v1.8b, v4.8b
- rev x7, x5
- add x5, x5, #1
+ rev x7, x8
+ add x8, x8, #1
ins v0.d[1], x7
- rev x7, x5
- add x5, x5, #1
+ rev x7, x8
+ add x8, x8, #1
ins v1.d[1], x7
ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */
do_encrypt_block2x
@@ -305,7 +298,7 @@
st1 {v0.16b-v1.16b}, [x0], #32
#else
ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */
- dup v7.4s, w5
+ dup v7.4s, w8
mov v0.16b, v4.16b
add v7.4s, v7.4s, v8.4s
mov v1.16b, v4.16b
@@ -323,18 +316,12 @@
eor v2.16b, v7.16b, v2.16b
eor v3.16b, v5.16b, v3.16b
st1 {v0.16b-v3.16b}, [x0], #64
- add x5, x5, #INTERLEAVE
+ add x8, x8, #INTERLEAVE
#endif
- cbz w4, .LctroutNx
-.LctrincNx:
- rev x7, x5
+ rev x7, x8
ins v4.d[1], x7
+ cbz w4, .Lctrout
b .LctrloopNx
-.LctroutNx:
- sub x5, x5, #1
- rev x7, x5
- ins v4.d[1], x7
- b .Lctrout
.Lctr1x:
adds w4, w4, #INTERLEAVE
beq .Lctrout
@@ -342,30 +329,39 @@
.Lctrloop:
mov v0.16b, v4.16b
encrypt_block v0, w3, x2, x6, w7
+
+ adds x8, x8, #1 /* increment BE ctr */
+ rev x7, x8
+ ins v4.d[1], x7
+ bcs .Lctrcarry /* overflow? */
+
+.Lctrcarrydone:
subs w4, w4, #1
bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */
ld1 {v3.16b}, [x1], #16
eor v3.16b, v0.16b, v3.16b
st1 {v3.16b}, [x0], #16
- beq .Lctrout
-.Lctrinc:
- adds x5, x5, #1 /* increment BE ctr */
- rev x7, x5
- ins v4.d[1], x7
- bcc .Lctrloop /* no overflow? */
+ bne .Lctrloop
+
+.Lctrout:
+ st1 {v4.16b}, [x5] /* return next CTR value */
+ FRAME_POP
+ ret
+
+.Lctrhalfblock:
+ ld1 {v3.8b}, [x1]
+ eor v3.8b, v0.8b, v3.8b
+ st1 {v3.8b}, [x0]
+ FRAME_POP
+ ret
+
+.Lctrcarry:
umov x7, v4.d[0] /* load upper word of ctr */
rev x7, x7 /* ... to handle the carry */
add x7, x7, #1
rev x7, x7
ins v4.d[0], x7
- b .Lctrloop
-.Lctrhalfblock:
- ld1 {v3.8b}, [x1]
- eor v3.8b, v0.8b, v3.8b
- st1 {v3.8b}, [x0]
-.Lctrout:
- FRAME_POP
- ret
+ b .Lctrcarrydone
AES_ENDPROC(aes_ctr_encrypt)
.ltorg
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 8365a84..a12f1af 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,6 +1,5 @@
generic-y += bugs.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += delay.h
generic-y += div64.h
generic-y += dma.h
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index eaa5bbe..b4b3400 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -29,41 +29,29 @@
#include <clocksource/arm_arch_timer.h>
-#if IS_ENABLED(CONFIG_FSL_ERRATUM_A008585)
+#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND)
extern struct static_key_false arch_timer_read_ool_enabled;
-#define needs_fsl_a008585_workaround() \
+#define needs_unstable_timer_counter_workaround() \
static_branch_unlikely(&arch_timer_read_ool_enabled)
#else
-#define needs_fsl_a008585_workaround() false
+#define needs_unstable_timer_counter_workaround() false
#endif
-u32 __fsl_a008585_read_cntp_tval_el0(void);
-u32 __fsl_a008585_read_cntv_tval_el0(void);
-u64 __fsl_a008585_read_cntvct_el0(void);
-/*
- * The number of retries is an arbitrary value well beyond the highest number
- * of iterations the loop has been observed to take.
- */
-#define __fsl_a008585_read_reg(reg) ({ \
- u64 _old, _new; \
- int _retries = 200; \
- \
- do { \
- _old = read_sysreg(reg); \
- _new = read_sysreg(reg); \
- _retries--; \
- } while (unlikely(_old != _new) && _retries); \
- \
- WARN_ON_ONCE(!_retries); \
- _new; \
-})
+struct arch_timer_erratum_workaround {
+ const char *id; /* Indicate the Erratum ID */
+ u32 (*read_cntp_tval_el0)(void);
+ u32 (*read_cntv_tval_el0)(void);
+ u64 (*read_cntvct_el0)(void);
+};
+
+extern const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround;
#define arch_timer_reg_read_stable(reg) \
({ \
u64 _val; \
- if (needs_fsl_a008585_workaround()) \
- _val = __fsl_a008585_read_##reg(); \
+ if (needs_unstable_timer_counter_workaround()) \
+ _val = timer_unstable_counter_workaround->read_##reg();\
else \
_val = read_sysreg(reg); \
_val; \
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 446f6c4..3a43011 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -164,22 +164,25 @@
/*
* Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where
- * <symbol> is within the range +/- 4 GB of the PC.
+ * <symbol> is within the range +/- 4 GB of the PC when running
+ * in core kernel context. In module context, a movz/movk sequence
+ * is used, since modules may be loaded far away from the kernel
+ * when KASLR is in effect.
*/
/*
* @dst: destination register (64 bit wide)
* @sym: name of the symbol
- * @tmp: optional scratch register to be used if <dst> == sp, which
- * is not allowed in an adrp instruction
*/
- .macro adr_l, dst, sym, tmp=
- .ifb \tmp
+ .macro adr_l, dst, sym
+#ifndef MODULE
adrp \dst, \sym
add \dst, \dst, :lo12:\sym
- .else
- adrp \tmp, \sym
- add \dst, \tmp, :lo12:\sym
- .endif
+#else
+ movz \dst, #:abs_g3:\sym
+ movk \dst, #:abs_g2_nc:\sym
+ movk \dst, #:abs_g1_nc:\sym
+ movk \dst, #:abs_g0_nc:\sym
+#endif
.endm
/*
@@ -190,6 +193,7 @@
* the address
*/
.macro ldr_l, dst, sym, tmp=
+#ifndef MODULE
.ifb \tmp
adrp \dst, \sym
ldr \dst, [\dst, :lo12:\sym]
@@ -197,6 +201,15 @@
adrp \tmp, \sym
ldr \dst, [\tmp, :lo12:\sym]
.endif
+#else
+ .ifb \tmp
+ adr_l \dst, \sym
+ ldr \dst, [\dst]
+ .else
+ adr_l \tmp, \sym
+ ldr \dst, [\tmp]
+ .endif
+#endif
.endm
/*
@@ -206,8 +219,13 @@
* while <src> needs to be preserved.
*/
.macro str_l, src, sym, tmp
+#ifndef MODULE
adrp \tmp, \sym
str \src, [\tmp, :lo12:\sym]
+#else
+ adr_l \tmp, \sym
+ str \src, [\tmp]
+#endif
.endm
/*
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 0b6b163..e744528 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -50,6 +50,7 @@
#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
#define __efi_call_early(f, ...) f(__VA_ARGS__)
+#define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__)
#define efi_is_64bit() (true)
#define efi_call_proto(protocol, f, instance, ...) \
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index bfe6328..90c39a6 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -222,7 +222,7 @@
#define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
#else
#define __virt_to_pgoff(kaddr) (((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
-#define __page_to_voff(page) (((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
+#define __page_to_voff(kaddr) (((u64)(kaddr) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
#define page_to_virt(page) ((void *)((__page_to_voff(page)) | PAGE_OFFSET))
#define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index fea1073..439f6b5 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -47,6 +47,7 @@
#include <asm/ptrace.h>
#include <asm/sections.h>
#include <asm/sysreg.h>
+#include <asm/cpufeature.h>
/*
* __boot_cpu_mode records what mode CPUs were booted in.
@@ -80,6 +81,14 @@
return read_sysreg(CurrentEL) == CurrentEL_EL2;
}
+static inline bool has_vhe(void)
+{
+ if (cpus_have_const_cap(ARM64_HAS_VIRT_HOST_EXTN))
+ return true;
+
+ return false;
+}
+
#ifdef CONFIG_ARM64_VHE
extern void verify_cpu_run_el(void);
#else
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index b5c3933..d1ff83d 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -77,6 +77,7 @@
__uint128_t vregs[32];
__u32 fpsr;
__u32 fpcr;
+ __u32 __reserved[2];
};
struct user_hwdebug_state {
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 923841f..43512d4 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -683,7 +683,7 @@
mov x0, sp
mov x1, #BAD_SYNC
mov x2, x25
- bl bad_mode
+ bl bad_el0_sync
b ret_to_user
ENDPROC(el0_sync)
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index fc35e06..a22161c 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -551,6 +551,8 @@
/* (address, ctrl) registers */
limit = regset->n * regset->size;
while (count && offset < limit) {
+ if (count < PTRACE_HBP_ADDR_SZ)
+ return -EINVAL;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr,
offset, offset + PTRACE_HBP_ADDR_SZ);
if (ret)
@@ -560,6 +562,8 @@
return ret;
offset += PTRACE_HBP_ADDR_SZ;
+ if (!count)
+ break;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl,
offset, offset + PTRACE_HBP_CTRL_SZ);
if (ret)
@@ -596,7 +600,7 @@
const void *kbuf, const void __user *ubuf)
{
int ret;
- struct user_pt_regs newregs;
+ struct user_pt_regs newregs = task_pt_regs(target)->user_regs;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1);
if (ret)
@@ -626,7 +630,8 @@
const void *kbuf, const void __user *ubuf)
{
int ret;
- struct user_fpsimd_state newstate;
+ struct user_fpsimd_state newstate =
+ target->thread.fpsimd_state.user_fpsimd;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
if (ret)
@@ -650,7 +655,7 @@
const void *kbuf, const void __user *ubuf)
{
int ret;
- unsigned long tls;
+ unsigned long tls = target->thread.tp_value;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
if (ret)
@@ -676,7 +681,8 @@
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- int syscallno, ret;
+ int syscallno = task_pt_regs(target)->syscallno;
+ int ret;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1);
if (ret)
@@ -948,7 +954,7 @@
const void __user *ubuf)
{
int ret;
- compat_ulong_t tls;
+ compat_ulong_t tls = target->thread.tp_value;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
if (ret)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 23e9e13..655e65f 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -11,6 +11,7 @@
* for more details.
*/
+#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/init.h>
@@ -209,7 +210,12 @@
static int __init register_cpufreq_notifier(void)
{
- if (cap_parsing_failed)
+ /*
+ * on ACPI-based systems we need to use the default cpu capacity
+ * until we have the necessary code to parse the cpu capacity, so
+ * skip registering cpufreq notifier.
+ */
+ if (!acpi_disabled || cap_parsing_failed)
return -EINVAL;
if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 5b830be..659b2e6 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -604,17 +604,34 @@
}
/*
- * bad_mode handles the impossible case in the exception vector.
+ * bad_mode handles the impossible case in the exception vector. This is always
+ * fatal.
*/
asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
{
- siginfo_t info;
- void __user *pc = (void __user *)instruction_pointer(regs);
console_verbose();
pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
handler[reason], smp_processor_id(), esr,
esr_get_class_string(esr));
+
+ die("Oops - bad mode", regs, 0);
+ local_irq_disable();
+ panic("bad mode");
+}
+
+/*
+ * bad_el0_sync handles unexpected, but potentially recoverable synchronous
+ * exceptions taken from EL0. Unlike bad_mode, this returns.
+ */
+asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+{
+ siginfo_t info;
+ void __user *pc = (void __user *)instruction_pointer(regs);
+ console_verbose();
+
+ pr_crit("Bad EL0 synchronous exception detected on CPU%d, code 0x%08x -- %s\n",
+ smp_processor_id(), esr, esr_get_class_string(esr));
__show_regs(regs);
info.si_signo = SIGILL;
@@ -622,7 +639,10 @@
info.si_code = ILL_ILLOPC;
info.si_addr = pc;
- arm64_notify_die("Oops - bad mode", regs, &info, 0);
+ current->thread.fault_address = 0;
+ current->thread.fault_code = 0;
+
+ force_sig_info(info.si_signo, &info, current);
}
void __pte_error(const char *file, int line, unsigned long val)
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 964b754..e25584d 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -239,7 +239,7 @@
ncontig = find_num_contig(vma->vm_mm, addr, cpte,
*cpte, &pgsize);
for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) {
- changed = ptep_set_access_flags(vma, addr, cpte,
+ changed |= ptep_set_access_flags(vma, addr, cpte,
pfn_pte(pfn,
hugeprot),
dirty);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 716d122..380ebe7 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -404,6 +404,8 @@
if (swiotlb_force == SWIOTLB_FORCE ||
max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
swiotlb_init(1);
+ else
+ swiotlb_force = SWIOTLB_NO_FORCE;
set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 241b9b9..3d7ef2c 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -1,6 +1,5 @@
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += delay.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 2fb67b5..d6fa60b 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -2,7 +2,6 @@
generic-y += auxvec.h
generic-y += bitsperlong.h
generic-y += bugs.h
-generic-y += cputime.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 64465e7..4e9f574 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -5,7 +5,6 @@
generic-y += bitsperlong.h
generic-y += bugs.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 1778805..9f19e19 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -4,7 +4,6 @@
generic-y += bitsperlong.h
generic-y += clkdev.h
generic-y += cmpxchg.h
-generic-y += cputime.h
generic-y += device.h
generic-y += div64.h
generic-y += errno.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 1fa084c..0f5b0d5 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -1,6 +1,5 @@
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += exec.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 1c2a5e2..e93c949 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -139,7 +139,7 @@
#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0)
#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
#define atomic64_inc_and_test(v) (atomic64_inc_return((v)) == 0)
-
+#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
#define atomic_cmpxchg(v, old, new) (cmpxchg(&(v)->counter, old, new))
#define atomic_xchg(v, new) (xchg(&(v)->counter, new))
@@ -161,6 +161,39 @@
return c;
}
+static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
+{
+ long long c, old;
+
+ c = atomic64_read(v);
+ for (;;) {
+ if (unlikely(c == u))
+ break;
+ old = atomic64_cmpxchg(v, c, c + i);
+ if (likely(old == c))
+ break;
+ c = old;
+ }
+ return c != u;
+}
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+ long long c, old, dec;
+
+ c = atomic64_read(v);
+ for (;;) {
+ dec = c - 1;
+ if (unlikely(dec < 0))
+ break;
+ old = atomic64_cmpxchg((v), c, dec);
+ if (likely(old == c))
+ break;
+ c = old;
+ }
+ return dec;
+}
+
#define ATOMIC_OP(op) \
static inline int atomic_fetch_##op(int i, atomic_t *v) \
{ \
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 373cb23..5efd0c8 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -5,7 +5,6 @@
generic-y += cacheflush.h
generic-y += checksum.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += delay.h
generic-y += device.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index db8ddab..a43a7c9 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -6,7 +6,6 @@
generic-y += bug.h
generic-y += bugs.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h
index e2d3f5b..3d665c0 100644
--- a/arch/ia64/include/asm/cputime.h
+++ b/arch/ia64/include/asm/cputime.h
@@ -18,11 +18,7 @@
#ifndef __IA64_CPUTIME_H
#define __IA64_CPUTIME_H
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-# include <asm-generic/cputime.h>
-#else
-# include <asm/processor.h>
-# include <asm-generic/cputime_nsecs.h>
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
extern void arch_vtime_task_switch(struct task_struct *tsk);
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index c702642..8742d74 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -27,6 +27,12 @@
mm_segment_t addr_limit; /* user-level address space limit */
int preempt_count; /* 0=premptable, <0=BUG; will also serve as bh-counter */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+ __u64 utime;
+ __u64 stime;
+ __u64 gtime;
+ __u64 hardirq_time;
+ __u64 softirq_time;
+ __u64 idle_time;
__u64 ac_stamp;
__u64 ac_leave;
__u64 ac_stime;
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index c9b5e94..3204fdd 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -1031,7 +1031,7 @@
END(ia64_native_sched_clock)
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-GLOBAL_ENTRY(cycle_to_cputime)
+GLOBAL_ENTRY(cycle_to_nsec)
alloc r16=ar.pfs,1,0,0,0
addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
;;
@@ -1047,7 +1047,7 @@
;;
shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
br.ret.sptk.many rp
-END(cycle_to_cputime)
+END(cycle_to_nsec)
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
#ifdef CONFIG_IA64_BRL_EMU
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 7ec7acc..c483ece 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -619,6 +619,8 @@
check_sal_cache_flush();
#endif
paging_init();
+
+ clear_sched_clock_stable();
}
/*
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 71775b95..faa1168 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -21,6 +21,7 @@
#include <linux/timex.h>
#include <linux/timekeeper_internal.h>
#include <linux/platform_device.h>
+#include <linux/cputime.h>
#include <asm/machvec.h>
#include <asm/delay.h>
@@ -59,18 +60,43 @@
#include <linux/kernel_stat.h>
-extern cputime_t cycle_to_cputime(u64 cyc);
+extern u64 cycle_to_nsec(u64 cyc);
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
{
- cputime_t delta_utime;
struct thread_info *ti = task_thread_info(tsk);
+ u64 delta;
- if (ti->ac_utime) {
- delta_utime = cycle_to_cputime(ti->ac_utime);
- account_user_time(tsk, delta_utime);
- ti->ac_utime = 0;
+ if (ti->utime)
+ account_user_time(tsk, cycle_to_nsec(ti->utime));
+
+ if (ti->gtime)
+ account_guest_time(tsk, cycle_to_nsec(ti->gtime));
+
+ if (ti->idle_time)
+ account_idle_time(cycle_to_nsec(ti->idle_time));
+
+ if (ti->stime) {
+ delta = cycle_to_nsec(ti->stime);
+ account_system_index_time(tsk, delta, CPUTIME_SYSTEM);
}
+
+ if (ti->hardirq_time) {
+ delta = cycle_to_nsec(ti->hardirq_time);
+ account_system_index_time(tsk, delta, CPUTIME_IRQ);
+ }
+
+ if (ti->softirq_time) {
+ delta = cycle_to_nsec(ti->softirq_time));
+ account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ);
+ }
+
+ ti->utime = 0;
+ ti->gtime = 0;
+ ti->idle_time = 0;
+ ti->stime = 0;
+ ti->hardirq_time = 0;
+ ti->softirq_time = 0;
}
/*
@@ -83,7 +109,7 @@
struct thread_info *pi = task_thread_info(prev);
struct thread_info *ni = task_thread_info(current);
- pi->ac_stamp = ni->ac_stamp;
+ ni->ac_stamp = pi->ac_stamp;
ni->ac_stime = ni->ac_utime = 0;
}
@@ -91,18 +117,15 @@
* Account time for a transition between system, hard irq or soft irq state.
* Note that this function is called with interrupts enabled.
*/
-static cputime_t vtime_delta(struct task_struct *tsk)
+static __u64 vtime_delta(struct task_struct *tsk)
{
struct thread_info *ti = task_thread_info(tsk);
- cputime_t delta_stime;
- __u64 now;
+ __u64 now, delta_stime;
WARN_ON_ONCE(!irqs_disabled());
now = ia64_get_itc();
-
- delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
- ti->ac_stime = 0;
+ delta_stime = now - ti->ac_stamp;
ti->ac_stamp = now;
return delta_stime;
@@ -110,15 +133,25 @@
void vtime_account_system(struct task_struct *tsk)
{
- cputime_t delta = vtime_delta(tsk);
+ struct thread_info *ti = task_thread_info(tsk);
+ __u64 stime = vtime_delta(tsk);
- account_system_time(tsk, 0, delta);
+ if ((tsk->flags & PF_VCPU) && !irq_count())
+ ti->gtime += stime;
+ else if (hardirq_count())
+ ti->hardirq_time += stime;
+ else if (in_serving_softirq())
+ ti->softirq_time += stime;
+ else
+ ti->stime += stime;
}
EXPORT_SYMBOL_GPL(vtime_account_system);
void vtime_account_idle(struct task_struct *tsk)
{
- account_idle_time(vtime_delta(tsk));
+ struct thread_info *ti = task_thread_info(tsk);
+
+ ti->idle_time += vtime_delta(tsk);
}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index 860e440..652100b 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -1,6 +1,5 @@
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += exec.h
generic-y += irq_work.h
generic-y += kvm_para.h
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 1f2e5d3..6c76d6c 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,7 +1,6 @@
generic-y += barrier.h
generic-y += bitsperlong.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += device.h
generic-y += emergency-restart.h
generic-y += errno.h
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 167150c..d3731f0 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -2,7 +2,6 @@
generic-y += bitsperlong.h
generic-y += bugs.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += device.h
generic-y += dma.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index b0ae88c..6275eb0 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -1,7 +1,6 @@
generic-y += barrier.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += device.h
generic-y += exec.h
generic-y += irq_work.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 3269b74..994b1c4 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1,7 +1,6 @@
# MIPS headers
generic-(CONFIG_GENERIC_CSUM) += checksum.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += dma-contiguous.h
generic-y += emergency-restart.h
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index 9c7f3e1..4a2ff39 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -99,15 +99,7 @@
#undef TASK_SIZE
#define TASK_SIZE TASK_SIZE32
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-static __inline__ void
-cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
-{
- unsigned long jiffies = cputime_to_jiffies(cputime);
-
- value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
- value->tv_sec = jiffies / HZ;
-}
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
#include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 1ab3432..3916404 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -102,15 +102,7 @@
#undef TASK_SIZE
#define TASK_SIZE TASK_SIZE32
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-static __inline__ void
-cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
-{
- unsigned long jiffies = cputime_to_jiffies(cputime);
-
- value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
- value->tv_sec = jiffies / HZ;
-}
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
#include "../../../fs/binfmt_elf.c"
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 1c8dd0f..97f64c7 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -1,7 +1,6 @@
generic-y += barrier.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += exec.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
diff --git a/arch/mn10300/include/asm/switch_to.h b/arch/mn10300/include/asm/switch_to.h
index 393d311..67e333a 100644
--- a/arch/mn10300/include/asm/switch_to.h
+++ b/arch/mn10300/include/asm/switch_to.h
@@ -16,7 +16,7 @@
struct task_struct;
struct thread_struct;
-#if !defined(CONFIG_LAZY_SAVE_FPU)
+#if defined(CONFIG_FPU) && !defined(CONFIG_LAZY_SAVE_FPU)
struct fpu_state_struct;
extern asmlinkage void fpu_save(struct fpu_state_struct *);
#define switch_fpu(prev, next) \
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index d63330e..35b0e88 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -6,7 +6,6 @@
generic-y += bug.h
generic-y += bugs.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 2832f03..ef8d1cc 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -12,7 +12,6 @@
generic-y += clkdev.h
generic-y += cmpxchg-local.h
generic-y += cmpxchg.h
-generic-y += cputime.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 91f53c0..4e179d7 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -2,7 +2,6 @@
generic-y += auxvec.h
generic-y += barrier.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += device.h
generic-y += div64.h
generic-y += emergency-restart.h
diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h
index 3f9406d..da87943 100644
--- a/arch/parisc/include/asm/bitops.h
+++ b/arch/parisc/include/asm/bitops.h
@@ -6,7 +6,7 @@
#endif
#include <linux/compiler.h>
-#include <asm/types.h> /* for BITS_PER_LONG/SHIFT_PER_LONG */
+#include <asm/types.h>
#include <asm/byteorder.h>
#include <asm/barrier.h>
#include <linux/atomic.h>
@@ -17,6 +17,12 @@
* to include/asm-i386/bitops.h or kerneldoc
*/
+#if __BITS_PER_LONG == 64
+#define SHIFT_PER_LONG 6
+#else
+#define SHIFT_PER_LONG 5
+#endif
+
#define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
diff --git a/arch/parisc/include/uapi/asm/bitsperlong.h b/arch/parisc/include/uapi/asm/bitsperlong.h
index e0a23c7..07fa7e5 100644
--- a/arch/parisc/include/uapi/asm/bitsperlong.h
+++ b/arch/parisc/include/uapi/asm/bitsperlong.h
@@ -3,10 +3,8 @@
#if defined(__LP64__)
#define __BITS_PER_LONG 64
-#define SHIFT_PER_LONG 6
#else
#define __BITS_PER_LONG 32
-#define SHIFT_PER_LONG 5
#endif
#include <asm-generic/bitsperlong.h>
diff --git a/arch/parisc/include/uapi/asm/swab.h b/arch/parisc/include/uapi/asm/swab.h
index e78403b..928e1bb 100644
--- a/arch/parisc/include/uapi/asm/swab.h
+++ b/arch/parisc/include/uapi/asm/swab.h
@@ -1,6 +1,7 @@
#ifndef _PARISC_SWAB_H
#define _PARISC_SWAB_H
+#include <asm/bitsperlong.h>
#include <linux/types.h>
#include <linux/compiler.h>
@@ -38,7 +39,7 @@
}
#define __arch_swab32 __arch_swab32
-#if BITS_PER_LONG > 32
+#if __BITS_PER_LONG > 32
/*
** From "PA-RISC 2.0 Architecture", HP Professional Books.
** See Appendix I page 8 , "Endian Byte Swapping".
@@ -61,6 +62,6 @@
return x;
}
#define __arch_swab64 __arch_swab64
-#endif /* BITS_PER_LONG > 32 */
+#endif /* __BITS_PER_LONG > 32 */
#endif /* _PARISC_SWAB_H */
diff --git a/arch/parisc/kernel/binfmt_elf32.c b/arch/parisc/kernel/binfmt_elf32.c
index 00dc66f..f2adcf3 100644
--- a/arch/parisc/kernel/binfmt_elf32.c
+++ b/arch/parisc/kernel/binfmt_elf32.c
@@ -91,14 +91,7 @@
current->thread.map_base = DEFAULT_MAP_BASE32; \
current->thread.task_size = DEFAULT_TASK_SIZE32 \
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-static __inline__ void
-cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
-{
- unsigned long jiffies = cputime_to_jiffies(cputime);
- value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
- value->tv_sec = jiffies / HZ;
-}
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
#include "../../../fs/binfmt_elf.c"
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 2e66a88..068ed36 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -36,6 +36,7 @@
#undef PCI_DEBUG
#include <linux/proc_fs.h>
#include <linux/export.h>
+#include <linux/sched.h>
#include <asm/processor.h>
#include <asm/sections.h>
@@ -176,6 +177,7 @@
conswitchp = &dummy_con; /* we use do_take_over_console() later ! */
#endif
+ clear_sched_clock_stable();
}
/*
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a8ee573..281f4f1 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -164,7 +164,6 @@
select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_KERNEL_GZIP
- select HAVE_CC_STACKPROTECTOR
config GENERIC_CSUM
def_bool CPU_LITTLE_ENDIAN
@@ -484,6 +483,7 @@
bool "Build a relocatable kernel"
depends on (PPC64 && !COMPILE_TEST) || (FLATMEM && (44x || FSL_BOOKE))
select NONSTATIC_KERNEL
+ select MODULE_REL_CRCS if MODVERSIONS
help
This builds a kernel image that is capable of running at the
location the kernel is loaded at. For ppc32, there is no any
diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
index c744569..a97296c 100644
--- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
@@ -678,5 +678,6 @@
compatible = "fsl,t2080-l2-cache-controller";
reg = <0xc20000 0x40000>;
next-level-cache = <&cpc>;
+ interrupts = <16 2 1 9>;
};
};
diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h
index c133246..3abcf98 100644
--- a/arch/powerpc/include/asm/accounting.h
+++ b/arch/powerpc/include/asm/accounting.h
@@ -12,9 +12,17 @@
/* Stuff for accurate time accounting */
struct cpu_accounting_data {
- unsigned long user_time; /* accumulated usermode TB ticks */
- unsigned long system_time; /* accumulated system TB ticks */
- unsigned long user_time_scaled; /* accumulated usermode SPURR ticks */
+ /* Accumulated cputime values to flush on ticks*/
+ unsigned long utime;
+ unsigned long stime;
+ unsigned long utime_scaled;
+ unsigned long stime_scaled;
+ unsigned long gtime;
+ unsigned long hardirq_time;
+ unsigned long softirq_time;
+ unsigned long steal_time;
+ unsigned long idle_time;
+ /* Internal counters */
unsigned long starttime; /* TB value snapshot */
unsigned long starttime_user; /* TB value on exit to usermode */
unsigned long startspurr; /* SPURR value snapshot */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 1c64bc6..0c4e470 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -36,12 +36,13 @@
#ifdef CONFIG_HUGETLB_PAGE
static inline int hash__hugepd_ok(hugepd_t hpd)
{
+ unsigned long hpdval = hpd_val(hpd);
/*
* if it is not a pte and have hugepd shift mask
* set, then it is a hugepd directory pointer
*/
- if (!(hpd.pd & _PAGE_PTE) &&
- ((hpd.pd & HUGEPD_SHIFT_MASK) != 0))
+ if (!(hpdval & _PAGE_PTE) &&
+ ((hpdval & HUGEPD_SHIFT_MASK) != 0))
return true;
return false;
}
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index f61cad3..4c935f75 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -201,6 +201,10 @@
unsigned long phys);
extern void hash__vmemmap_remove_mapping(unsigned long start,
unsigned long page_size);
+
+int hash__create_section_mapping(unsigned long start, unsigned long end);
+int hash__remove_section_mapping(unsigned long start, unsigned long end);
+
#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */
diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index b312b15..6e834ca 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -23,7 +23,9 @@
{
int i;
+#ifndef __clang__ /* clang can't cope with this */
BUILD_BUG_ON(!__builtin_constant_p(feature));
+#endif
#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
if (!static_key_initialized) {
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index aa2e6a3..99b5418 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -16,12 +16,7 @@
#ifndef __POWERPC_CPUTIME_H
#define __POWERPC_CPUTIME_H
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-#include <asm-generic/cputime.h>
-#ifdef __KERNEL__
-static inline void setup_cputime_one_jiffy(void) { }
-#endif
-#else
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
#include <linux/types.h>
#include <linux/time.h>
@@ -36,65 +31,6 @@
#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
#ifdef __KERNEL__
-
-/*
- * One jiffy in timebase units computed during initialization
- */
-extern cputime_t cputime_one_jiffy;
-
-/*
- * Convert cputime <-> jiffies
- */
-extern u64 __cputime_jiffies_factor;
-
-static inline unsigned long cputime_to_jiffies(const cputime_t ct)
-{
- return mulhdu((__force u64) ct, __cputime_jiffies_factor);
-}
-
-static inline cputime_t jiffies_to_cputime(const unsigned long jif)
-{
- u64 ct;
- unsigned long sec;
-
- /* have to be a little careful about overflow */
- ct = jif % HZ;
- sec = jif / HZ;
- if (ct) {
- ct *= tb_ticks_per_sec;
- do_div(ct, HZ);
- }
- if (sec)
- ct += (cputime_t) sec * tb_ticks_per_sec;
- return (__force cputime_t) ct;
-}
-
-static inline void setup_cputime_one_jiffy(void)
-{
- cputime_one_jiffy = jiffies_to_cputime(1);
-}
-
-static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
-{
- u64 ct;
- u64 sec = jif;
-
- /* have to be a little careful about overflow */
- ct = do_div(sec, HZ);
- if (ct) {
- ct *= tb_ticks_per_sec;
- do_div(ct, HZ);
- }
- if (sec)
- ct += (u64) sec * tb_ticks_per_sec;
- return (__force cputime64_t) ct;
-}
-
-static inline u64 cputime64_to_jiffies64(const cputime_t ct)
-{
- return mulhdu((__force u64) ct, __cputime_jiffies_factor);
-}
-
/*
* Convert cputime <-> microseconds
*/
@@ -105,117 +41,6 @@
return mulhdu((__force u64) ct, __cputime_usec_factor);
}
-static inline cputime_t usecs_to_cputime(const unsigned long us)
-{
- u64 ct;
- unsigned long sec;
-
- /* have to be a little careful about overflow */
- ct = us % 1000000;
- sec = us / 1000000;
- if (ct) {
- ct *= tb_ticks_per_sec;
- do_div(ct, 1000000);
- }
- if (sec)
- ct += (cputime_t) sec * tb_ticks_per_sec;
- return (__force cputime_t) ct;
-}
-
-#define usecs_to_cputime64(us) usecs_to_cputime(us)
-
-/*
- * Convert cputime <-> seconds
- */
-extern u64 __cputime_sec_factor;
-
-static inline unsigned long cputime_to_secs(const cputime_t ct)
-{
- return mulhdu((__force u64) ct, __cputime_sec_factor);
-}
-
-static inline cputime_t secs_to_cputime(const unsigned long sec)
-{
- return (__force cputime_t)((u64) sec * tb_ticks_per_sec);
-}
-
-/*
- * Convert cputime <-> timespec
- */
-static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
-{
- u64 x = (__force u64) ct;
- unsigned int frac;
-
- frac = do_div(x, tb_ticks_per_sec);
- p->tv_sec = x;
- x = (u64) frac * 1000000000;
- do_div(x, tb_ticks_per_sec);
- p->tv_nsec = x;
-}
-
-static inline cputime_t timespec_to_cputime(const struct timespec *p)
-{
- u64 ct;
-
- ct = (u64) p->tv_nsec * tb_ticks_per_sec;
- do_div(ct, 1000000000);
- return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
-}
-
-/*
- * Convert cputime <-> timeval
- */
-static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
-{
- u64 x = (__force u64) ct;
- unsigned int frac;
-
- frac = do_div(x, tb_ticks_per_sec);
- p->tv_sec = x;
- x = (u64) frac * 1000000;
- do_div(x, tb_ticks_per_sec);
- p->tv_usec = x;
-}
-
-static inline cputime_t timeval_to_cputime(const struct timeval *p)
-{
- u64 ct;
-
- ct = (u64) p->tv_usec * tb_ticks_per_sec;
- do_div(ct, 1000000);
- return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
-}
-
-/*
- * Convert cputime <-> clock_t (units of 1/USER_HZ seconds)
- */
-extern u64 __cputime_clockt_factor;
-
-static inline unsigned long cputime_to_clock_t(const cputime_t ct)
-{
- return mulhdu((__force u64) ct, __cputime_clockt_factor);
-}
-
-static inline cputime_t clock_t_to_cputime(const unsigned long clk)
-{
- u64 ct;
- unsigned long sec;
-
- /* have to be a little careful about overflow */
- ct = clk % USER_HZ;
- sec = clk / USER_HZ;
- if (ct) {
- ct *= tb_ticks_per_sec;
- do_div(ct, USER_HZ);
- }
- if (sec)
- ct += (u64) sec * tb_ticks_per_sec;
- return (__force cputime_t) ct;
-}
-
-#define cputime64_to_clock_t(ct) cputime_to_clock_t((cputime_t)(ct))
-
/*
* PPC64 uses PACA which is task independent for storing accounting data while
* PPC32 uses struct thread_info, therefore at task switch the accounting data
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index ede2151..7f4025a 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -21,12 +21,12 @@
* We have only four bits to encode, MMU page size
*/
BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
- return __va(hpd.pd & HUGEPD_ADDR_MASK);
+ return __va(hpd_val(hpd) & HUGEPD_ADDR_MASK);
}
static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)
{
- return (hpd.pd & HUGEPD_SHIFT_MASK) >> 2;
+ return (hpd_val(hpd) & HUGEPD_SHIFT_MASK) >> 2;
}
static inline unsigned int hugepd_shift(hugepd_t hpd)
@@ -52,18 +52,20 @@
{
BUG_ON(!hugepd_ok(hpd));
#ifdef CONFIG_PPC_8xx
- return (pte_t *)__va(hpd.pd & ~(_PMD_PAGE_MASK | _PMD_PRESENT_MASK));
+ return (pte_t *)__va(hpd_val(hpd) &
+ ~(_PMD_PAGE_MASK | _PMD_PRESENT_MASK));
#else
- return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | PD_HUGE);
+ return (pte_t *)((hpd_val(hpd) &
+ ~HUGEPD_SHIFT_MASK) | PD_HUGE);
#endif
}
static inline unsigned int hugepd_shift(hugepd_t hpd)
{
#ifdef CONFIG_PPC_8xx
- return ((hpd.pd & _PMD_PAGE_MASK) >> 1) + 17;
+ return ((hpd_val(hpd) & _PMD_PAGE_MASK) >> 1) + 17;
#else
- return hpd.pd & HUGEPD_SHIFT_MASK;
+ return hpd_val(hpd) & HUGEPD_SHIFT_MASK;
#endif
}
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index a34c764..233a7e8 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -160,7 +160,9 @@
{
int i;
+#ifndef __clang__ /* clang can't cope with this */
BUILD_BUG_ON(!__builtin_constant_p(feature));
+#endif
#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
if (!static_key_initialized) {
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index cc12c61..5388551 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -90,9 +90,5 @@
}
#endif
-#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64)
-#define ARCH_RELOCATES_KCRCTAB
-#define reloc_start PHYSICAL_START
-#endif
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_MODULE_H */
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 1728497..0cd8a38 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -227,9 +227,10 @@
static inline int hugepd_ok(hugepd_t hpd)
{
#ifdef CONFIG_PPC_8xx
- return ((hpd.pd & 0x4) != 0);
+ return ((hpd_val(hpd) & 0x4) != 0);
#else
- return (hpd.pd > 0);
+ /* We clear the top bit to indicate hugepd */
+ return ((hpd_val(hpd) & PD_HUGE) == 0);
#endif
}
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 6a6792b..708c3e5 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -187,7 +187,6 @@
/* Stuff for accurate time accounting */
struct cpu_accounting_data accounting;
- u64 stolen_time; /* TB ticks taken by hypervisor */
u64 dtl_ridx; /* read index in dispatch log */
struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 56398e7..47120bf 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -294,15 +294,12 @@
#include <asm/pgtable-types.h>
#endif
-typedef struct { signed long pd; } hugepd_t;
#ifndef CONFIG_HUGETLB_PAGE
#define is_hugepd(pdep) (0)
#define pgd_huge(pgd) (0)
#endif /* CONFIG_HUGETLB_PAGE */
-#define __hugepd(x) ((hugepd_t) { (x) })
-
struct page;
extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
extern void copy_user_page(void *to, void *from, unsigned long vaddr,
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index e157489..ae0a230 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -65,6 +65,7 @@
#define PPMU_HAS_SSLOT 0x00000020 /* Has sampled slot in MMCRA */
#define PPMU_HAS_SIER 0x00000040 /* Has SIER */
#define PPMU_ARCH_207S 0x00000080 /* PMC is architecture v2.07S */
+#define PPMU_NO_SIAR 0x00000100 /* Do not use SIAR */
/*
* Values for flags to get_alternatives()
diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h
index 49c0a5a..9c0f5db 100644
--- a/arch/powerpc/include/asm/pgtable-be-types.h
+++ b/arch/powerpc/include/asm/pgtable-be-types.h
@@ -104,4 +104,12 @@
return pmd_raw(old) == prev;
}
+typedef struct { __be64 pdbe; } hugepd_t;
+#define __hugepd(x) ((hugepd_t) { cpu_to_be64(x) })
+
+static inline unsigned long hpd_val(hugepd_t x)
+{
+ return be64_to_cpu(x.pdbe);
+}
+
#endif /* _ASM_POWERPC_PGTABLE_BE_TYPES_H */
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index e7f4f3e..8bd3b13 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -66,4 +66,11 @@
}
#endif
+typedef struct { unsigned long pd; } hugepd_t;
+#define __hugepd(x) ((hugepd_t) { (x) })
+static inline unsigned long hpd_val(hugepd_t x)
+{
+ return x.pd;
+}
+
#endif /* _ASM_POWERPC_PGTABLE_TYPES_H */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index c56ea8c..c4ced1d 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -157,7 +157,7 @@
#define PPC_INST_MCRXR 0x7c000400
#define PPC_INST_MCRXR_MASK 0xfc0007fe
#define PPC_INST_MFSPR_PVR 0x7c1f42a6
-#define PPC_INST_MFSPR_PVR_MASK 0xfc1fffff
+#define PPC_INST_MFSPR_PVR_MASK 0xfc1ffffe
#define PPC_INST_MFTMR 0x7c0002dc
#define PPC_INST_MSGSND 0x7c00019c
#define PPC_INST_MSGCLR 0x7c0001dc
@@ -174,13 +174,13 @@
#define PPC_INST_RFDI 0x4c00004e
#define PPC_INST_RFMCI 0x4c00004c
#define PPC_INST_MFSPR_DSCR 0x7c1102a6
-#define PPC_INST_MFSPR_DSCR_MASK 0xfc1fffff
+#define PPC_INST_MFSPR_DSCR_MASK 0xfc1ffffe
#define PPC_INST_MTSPR_DSCR 0x7c1103a6
-#define PPC_INST_MTSPR_DSCR_MASK 0xfc1fffff
+#define PPC_INST_MTSPR_DSCR_MASK 0xfc1ffffe
#define PPC_INST_MFSPR_DSCR_USER 0x7c0302a6
-#define PPC_INST_MFSPR_DSCR_USER_MASK 0xfc1fffff
+#define PPC_INST_MFSPR_DSCR_USER_MASK 0xfc1ffffe
#define PPC_INST_MTSPR_DSCR_USER 0x7c0303a6
-#define PPC_INST_MTSPR_DSCR_USER_MASK 0xfc1fffff
+#define PPC_INST_MTSPR_DSCR_USER_MASK 0xfc1ffffe
#define PPC_INST_MFVSRD 0x7c000066
#define PPC_INST_MTVSRD 0x7c000166
#define PPC_INST_SLBFEE 0x7c0007a7
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 0d4531a..dff7979 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -649,9 +649,10 @@
#define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */
#define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */
#define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */
-#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 */
+#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 and 9 */
#define SRR1_WAKESYSERR 0x00300000 /* System error */
#define SRR1_WAKEEE 0x00200000 /* External interrupt */
+#define SRR1_WAKEHVI 0x00240000 /* Hypervisor Virtualization Interrupt (P9) */
#define SRR1_WAKEMT 0x00280000 /* mtctrl */
#define SRR1_WAKEHMI 0x00280000 /* Hypervisor maintenance */
#define SRR1_WAKEDEC 0x00180000 /* Decrementer interrupt */
diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h
deleted file mode 100644
index 6720190..0000000
--- a/arch/powerpc/include/asm/stackprotector.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- * GCC stack protector support.
- *
- * Stack protector works by putting predefined pattern at the start of
- * the stack frame and verifying that it hasn't been overwritten when
- * returning from the function. The pattern is called stack canary
- * and gcc expects it to be defined by a global variable called
- * "__stack_chk_guard" on PPC. This unfortunately means that on SMP
- * we cannot have a different canary value per task.
- */
-
-#ifndef _ASM_STACKPROTECTOR_H
-#define _ASM_STACKPROTECTOR_H
-
-#include <linux/random.h>
-#include <linux/version.h>
-#include <asm/reg.h>
-
-extern unsigned long __stack_chk_guard;
-
-/*
- * Initialize the stackprotector canary value.
- *
- * NOTE: this must only be called from functions that never return,
- * and it must always be inlined.
- */
-static __always_inline void boot_init_stack_canary(void)
-{
- unsigned long canary;
-
- /* Try to get a semi random initial value. */
- get_random_bytes(&canary, sizeof(canary));
- canary ^= mftb();
- canary ^= LINUX_VERSION_CODE;
-
- current->stack_canary = canary;
- __stack_chk_guard = current->stack_canary;
-}
-
-#endif /* _ASM_STACKPROTECTOR_H */
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index f0b2385..e0b9e57 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -44,6 +44,7 @@
#ifdef CONFIG_PPC_POWERNV
extern int icp_opal_init(void);
+extern void icp_opal_flush_interrupt(void);
#else
static inline int icp_opal_init(void) { return -ENODEV; }
#endif
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 23f8082..f4c2b52 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -19,10 +19,6 @@
CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
-# -fstack-protector triggers protection checks in this code,
-# but it is being used too early to link to meaningful stack_chk logic.
-CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector)
-
ifdef CONFIG_FUNCTION_TRACER
# Do not trace early boot code
CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0601e6a..9e8e771 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -91,9 +91,6 @@
DEFINE(TI_livepatch_sp, offsetof(struct thread_info, livepatch_sp));
#endif
-#ifdef CONFIG_CC_STACKPROTECTOR
- DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary));
-#endif
DEFINE(KSP, offsetof(struct thread_struct, ksp));
DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
#ifdef CONFIG_BOOKE
@@ -252,9 +249,9 @@
DEFINE(ACCOUNT_STARTTIME_USER,
offsetof(struct paca_struct, accounting.starttime_user));
DEFINE(ACCOUNT_USER_TIME,
- offsetof(struct paca_struct, accounting.user_time));
+ offsetof(struct paca_struct, accounting.utime));
DEFINE(ACCOUNT_SYSTEM_TIME,
- offsetof(struct paca_struct, accounting.system_time));
+ offsetof(struct paca_struct, accounting.stime));
DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso));
@@ -265,9 +262,9 @@
DEFINE(ACCOUNT_STARTTIME_USER,
offsetof(struct thread_info, accounting.starttime_user));
DEFINE(ACCOUNT_USER_TIME,
- offsetof(struct thread_info, accounting.user_time));
+ offsetof(struct thread_info, accounting.utime));
DEFINE(ACCOUNT_SYSTEM_TIME,
- offsetof(struct thread_info, accounting.system_time));
+ offsetof(struct thread_info, accounting.stime));
#endif
#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 8180bfd..9de7f79 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -298,9 +298,17 @@
*
* For pHyp, we have to enable IO for log retrieval. Otherwise,
* 0xFF's is always returned from PCI config space.
+ *
+ * When the @severity is EEH_LOG_PERM, the PE is going to be
+ * removed. Prior to that, the drivers for devices included in
+ * the PE will be closed. The drivers rely on working IO path
+ * to bring the devices to quiet state. Otherwise, PCI traffic
+ * from those devices after they are removed is like to cause
+ * another unexpected EEH error.
*/
if (!(pe->type & EEH_PE_PHB)) {
- if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
+ if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) ||
+ severity == EEH_LOG_PERM)
eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
/*
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index d88573b..b948871 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -545,7 +545,7 @@
static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
{
struct eeh_pe *pe = (struct eeh_pe *)data;
- bool *clear_sw_state = flag;
+ bool clear_sw_state = *(bool *)flag;
int i, rc = 1;
for (i = 0; rc && i < 3; i++)
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 5742dbd..3841d74 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -674,11 +674,7 @@
mtspr SPRN_SPEFSCR,r0 /* restore SPEFSCR reg */
END_FTR_SECTION_IFSET(CPU_FTR_SPE)
#endif /* CONFIG_SPE */
-#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
- lwz r0,TSK_STACK_CANARY(r2)
- lis r4,__stack_chk_guard@ha
- stw r0,__stack_chk_guard@l(r4)
-#endif
+
lwz r0,_CCR(r1)
mtcrf 0xFF,r0
/* r3-r12 are destroyed -- Cort */
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index bb18071..0b0f896 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -286,14 +286,6 @@
for (end = (void *)vers + size; vers < end; vers++)
if (vers->name[0] == '.') {
memmove(vers->name, vers->name+1, strlen(vers->name));
-#ifdef ARCH_RELOCATES_KCRCTAB
- /* The TOC symbol has no CRC computed. To avoid CRC
- * check failing, we must force it to the expected
- * value (see CRC check in module.c).
- */
- if (!strcmp(vers->name, "TOC."))
- vers->crc = -(unsigned long)reloc_start;
-#endif
}
}
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 04885ce..5dd056d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -64,12 +64,6 @@
#include <linux/kprobes.h>
#include <linux/kdebug.h>
-#ifdef CONFIG_CC_STACKPROTECTOR
-#include <linux/stackprotector.h>
-unsigned long __stack_chk_guard __read_mostly;
-EXPORT_SYMBOL(__stack_chk_guard);
-#endif
-
/* Transactional Memory debug */
#ifdef TM_DEBUG_SW
#define TM_DEBUG(x...) printk(KERN_INFO x)
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index ec47a93..ac83eb0 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2834,6 +2834,9 @@
cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu);
+ if (!PHANDLE_VALID(cpu_pkg))
+ return;
+
prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval));
prom.cpu = be32_to_cpu(rval);
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index e4744ff..925a4ef 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -463,6 +463,10 @@
flush_fp_to_thread(target);
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.TS_FPR(i);
+ buf[32] = target->thread.fp_state.fpscr;
+
/* copy to local buffer then write that out */
i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
if (i)
@@ -672,6 +676,9 @@
flush_altivec_to_thread(target);
flush_vsx_to_thread(target);
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
buf, 0, 32 * sizeof(double));
if (!ret)
@@ -1019,6 +1026,10 @@
flush_fp_to_thread(target);
flush_altivec_to_thread(target);
+ for (i = 0; i < 32; i++)
+ buf[i] = target->thread.TS_CKFPR(i);
+ buf[32] = target->thread.ckfp_state.fpscr;
+
/* copy to local buffer then write that out */
i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
if (i)
@@ -1283,6 +1294,9 @@
flush_altivec_to_thread(target);
flush_vsx_to_thread(target);
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
buf, 0, 32 * sizeof(double));
if (!ret)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index bc2e08d..14e4855 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -57,6 +57,7 @@
#include <linux/clk-provider.h>
#include <linux/suspend.h>
#include <linux/rtc.h>
+#include <linux/cputime.h>
#include <asm/trace.h>
#include <asm/io.h>
@@ -72,7 +73,6 @@
#include <asm/smp.h>
#include <asm/vdso_datapage.h>
#include <asm/firmware.h>
-#include <asm/cputime.h>
#include <asm/asm-prototypes.h>
/* powerpc clocksource/clockevent code */
@@ -152,20 +152,11 @@
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
/*
- * Factors for converting from cputime_t (timebase ticks) to
- * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds).
- * These are all stored as 0.64 fixed-point binary fractions.
+ * Factor for converting from cputime_t (timebase ticks) to
+ * microseconds. This is stored as 0.64 fixed-point binary fraction.
*/
-u64 __cputime_jiffies_factor;
-EXPORT_SYMBOL(__cputime_jiffies_factor);
u64 __cputime_usec_factor;
EXPORT_SYMBOL(__cputime_usec_factor);
-u64 __cputime_sec_factor;
-EXPORT_SYMBOL(__cputime_sec_factor);
-u64 __cputime_clockt_factor;
-EXPORT_SYMBOL(__cputime_clockt_factor);
-
-cputime_t cputime_one_jiffy;
#ifdef CONFIG_PPC_SPLPAR
void (*dtl_consumer)(struct dtl_entry *, u64);
@@ -181,14 +172,8 @@
{
struct div_result res;
- div128_by_32(HZ, 0, tb_ticks_per_sec, &res);
- __cputime_jiffies_factor = res.result_low;
div128_by_32(1000000, 0, tb_ticks_per_sec, &res);
__cputime_usec_factor = res.result_low;
- div128_by_32(1, 0, tb_ticks_per_sec, &res);
- __cputime_sec_factor = res.result_low;
- div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res);
- __cputime_clockt_factor = res.result_low;
}
/*
@@ -271,25 +256,19 @@
sst = scan_dispatch_log(acct->starttime_user);
ust = scan_dispatch_log(acct->starttime);
- acct->system_time -= sst;
- acct->user_time -= ust;
- local_paca->stolen_time += ust + sst;
+ acct->stime -= sst;
+ acct->utime -= ust;
+ acct->steal_time += ust + sst;
local_paca->soft_enabled = save_soft_enabled;
}
static inline u64 calculate_stolen_time(u64 stop_tb)
{
- u64 stolen = 0;
+ if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx))
+ return scan_dispatch_log(stop_tb);
- if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
- stolen = scan_dispatch_log(stop_tb);
- get_paca()->accounting.system_time -= stolen;
- }
-
- stolen += get_paca()->stolen_time;
- get_paca()->stolen_time = 0;
- return stolen;
+ return 0;
}
#else /* CONFIG_PPC_SPLPAR */
@@ -305,28 +284,27 @@
* or soft irq state.
*/
static unsigned long vtime_delta(struct task_struct *tsk,
- unsigned long *sys_scaled,
- unsigned long *stolen)
+ unsigned long *stime_scaled,
+ unsigned long *steal_time)
{
unsigned long now, nowscaled, deltascaled;
- unsigned long udelta, delta, user_scaled;
+ unsigned long stime;
+ unsigned long utime, utime_scaled;
struct cpu_accounting_data *acct = get_accounting(tsk);
WARN_ON_ONCE(!irqs_disabled());
now = mftb();
nowscaled = read_spurr(now);
- acct->system_time += now - acct->starttime;
+ stime = now - acct->starttime;
acct->starttime = now;
deltascaled = nowscaled - acct->startspurr;
acct->startspurr = nowscaled;
- *stolen = calculate_stolen_time(now);
+ *steal_time = calculate_stolen_time(now);
- delta = acct->system_time;
- acct->system_time = 0;
- udelta = acct->user_time - acct->utime_sspurr;
- acct->utime_sspurr = acct->user_time;
+ utime = acct->utime - acct->utime_sspurr;
+ acct->utime_sspurr = acct->utime;
/*
* Because we don't read the SPURR on every kernel entry/exit,
@@ -338,62 +316,105 @@
* the user ticks get saved up in paca->user_time_scaled to be
* used by account_process_tick.
*/
- *sys_scaled = delta;
- user_scaled = udelta;
- if (deltascaled != delta + udelta) {
- if (udelta) {
- *sys_scaled = deltascaled * delta / (delta + udelta);
- user_scaled = deltascaled - *sys_scaled;
+ *stime_scaled = stime;
+ utime_scaled = utime;
+ if (deltascaled != stime + utime) {
+ if (utime) {
+ *stime_scaled = deltascaled * stime / (stime + utime);
+ utime_scaled = deltascaled - *stime_scaled;
} else {
- *sys_scaled = deltascaled;
+ *stime_scaled = deltascaled;
}
}
- acct->user_time_scaled += user_scaled;
+ acct->utime_scaled += utime_scaled;
- return delta;
+ return stime;
}
void vtime_account_system(struct task_struct *tsk)
{
- unsigned long delta, sys_scaled, stolen;
+ unsigned long stime, stime_scaled, steal_time;
+ struct cpu_accounting_data *acct = get_accounting(tsk);
- delta = vtime_delta(tsk, &sys_scaled, &stolen);
- account_system_time(tsk, 0, delta);
- tsk->stimescaled += sys_scaled;
- if (stolen)
- account_steal_time(stolen);
+ stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+
+ stime -= min(stime, steal_time);
+ acct->steal_time += steal_time;
+
+ if ((tsk->flags & PF_VCPU) && !irq_count()) {
+ acct->gtime += stime;
+ acct->utime_scaled += stime_scaled;
+ } else {
+ if (hardirq_count())
+ acct->hardirq_time += stime;
+ else if (in_serving_softirq())
+ acct->softirq_time += stime;
+ else
+ acct->stime += stime;
+
+ acct->stime_scaled += stime_scaled;
+ }
}
EXPORT_SYMBOL_GPL(vtime_account_system);
void vtime_account_idle(struct task_struct *tsk)
{
- unsigned long delta, sys_scaled, stolen;
+ unsigned long stime, stime_scaled, steal_time;
+ struct cpu_accounting_data *acct = get_accounting(tsk);
- delta = vtime_delta(tsk, &sys_scaled, &stolen);
- account_idle_time(delta + stolen);
+ stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+ acct->idle_time += stime + steal_time;
}
/*
- * Transfer the user time accumulated in the paca
- * by the exception entry and exit code to the generic
- * process user time records.
+ * Account the whole cputime accumulated in the paca
* Must be called with interrupts disabled.
* Assumes that vtime_account_system/idle() has been called
* recently (i.e. since the last entry from usermode) so that
* get_paca()->user_time_scaled is up to date.
*/
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
{
- cputime_t utime, utimescaled;
struct cpu_accounting_data *acct = get_accounting(tsk);
- utime = acct->user_time;
- utimescaled = acct->user_time_scaled;
- acct->user_time = 0;
- acct->user_time_scaled = 0;
+ if (acct->utime)
+ account_user_time(tsk, cputime_to_nsecs(acct->utime));
+
+ if (acct->utime_scaled)
+ tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
+
+ if (acct->gtime)
+ account_guest_time(tsk, cputime_to_nsecs(acct->gtime));
+
+ if (acct->steal_time)
+ account_steal_time(cputime_to_nsecs(acct->steal_time));
+
+ if (acct->idle_time)
+ account_idle_time(cputime_to_nsecs(acct->idle_time));
+
+ if (acct->stime)
+ account_system_index_time(tsk, cputime_to_nsecs(acct->stime),
+ CPUTIME_SYSTEM);
+ if (acct->stime_scaled)
+ tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
+
+ if (acct->hardirq_time)
+ account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time),
+ CPUTIME_IRQ);
+ if (acct->softirq_time)
+ account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time),
+ CPUTIME_SOFTIRQ);
+
+ acct->utime = 0;
+ acct->utime_scaled = 0;
acct->utime_sspurr = 0;
- account_user_time(tsk, utime);
- tsk->utimescaled += utimescaled;
+ acct->gtime = 0;
+ acct->steal_time = 0;
+ acct->idle_time = 0;
+ acct->stime = 0;
+ acct->stime_scaled = 0;
+ acct->hardirq_time = 0;
+ acct->softirq_time = 0;
}
#ifdef CONFIG_PPC32
@@ -407,8 +428,7 @@
struct cpu_accounting_data *acct = get_accounting(current);
acct->starttime = get_accounting(prev)->starttime;
- acct->system_time = 0;
- acct->user_time = 0;
+ acct->startspurr = get_accounting(prev)->startspurr;
}
#endif /* CONFIG_PPC32 */
@@ -1018,7 +1038,6 @@
tb_ticks_per_sec = ppc_tb_freq;
tb_ticks_per_usec = ppc_tb_freq / 1000000;
calc_cputime_factors();
- setup_cputime_one_jiffy();
/*
* Compute scale factor for sched_clock.
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 6fd30ac..62a50d6 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -253,8 +253,11 @@
if (unlikely(debugger_fault_handler(regs)))
goto bail;
- /* On a kernel SLB miss we can only check for a valid exception entry */
- if (!user_mode(regs) && (address >= TASK_SIZE)) {
+ /*
+ * The kernel should never take an execute fault nor should it
+ * take a page fault to a kernel address.
+ */
+ if (!user_mode(regs) && (is_exec || (address >= TASK_SIZE))) {
rc = SIGSEGV;
goto bail;
}
@@ -391,20 +394,6 @@
if (is_exec) {
/*
- * An execution fault + no execute ?
- *
- * On CPUs that don't have CPU_FTR_COHERENT_ICACHE we
- * deliberately create NX mappings, and use the fault to do the
- * cache flush. This is usually handled in hash_page_do_lazy_icache()
- * but we could end up here if that races with a concurrent PTE
- * update. In that case we need to fall through here to the VMA
- * check below.
- */
- if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE) &&
- (regs->msr & SRR1_ISI_N_OR_G))
- goto bad_area;
-
- /*
* Allow execution from readable areas if the MMU does not
* provide separate controls over reading and executing.
*
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 8033493..67e19a0 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -747,7 +747,7 @@
}
#ifdef CONFIG_MEMORY_HOTPLUG
-int create_section_mapping(unsigned long start, unsigned long end)
+int hash__create_section_mapping(unsigned long start, unsigned long end)
{
int rc = htab_bolt_mapping(start, end, __pa(start),
pgprot_val(PAGE_KERNEL), mmu_linear_psize,
@@ -761,7 +761,7 @@
return rc;
}
-int remove_section_mapping(unsigned long start, unsigned long end)
+int hash__remove_section_mapping(unsigned long start, unsigned long end)
{
int rc = htab_remove_mapping(start, end, mmu_linear_psize,
mmu_kernel_ssize);
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index d5026f3..37b5f91 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -125,11 +125,14 @@
int hugepd_ok(hugepd_t hpd)
{
bool is_hugepd;
+ unsigned long hpdval;
+
+ hpdval = hpd_val(hpd);
/*
* We should not find this format in page directory, warn otherwise.
*/
- is_hugepd = (((hpd.pd & 0x3) == 0x0) && ((hpd.pd & HUGEPD_SHIFT_MASK) != 0));
+ is_hugepd = (((hpdval & 0x3) == 0x0) && ((hpdval & HUGEPD_SHIFT_MASK) != 0));
WARN(is_hugepd, "Found wrong page directory format\n");
return 0;
}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 289df38..8c3389c 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -53,7 +53,7 @@
static unsigned nr_gpages;
#endif
-#define hugepd_none(hpd) ((hpd).pd == 0)
+#define hugepd_none(hpd) (hpd_val(hpd) == 0)
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
@@ -103,24 +103,24 @@
for (i = 0; i < num_hugepd; i++, hpdp++) {
if (unlikely(!hugepd_none(*hpdp)))
break;
- else
+ else {
#ifdef CONFIG_PPC_BOOK3S_64
- hpdp->pd = __pa(new) |
- (shift_to_mmu_psize(pshift) << 2);
+ *hpdp = __hugepd(__pa(new) |
+ (shift_to_mmu_psize(pshift) << 2));
#elif defined(CONFIG_PPC_8xx)
- hpdp->pd = __pa(new) |
- (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M :
- _PMD_PAGE_512K) |
- _PMD_PRESENT;
+ *hpdp = __hugepd(__pa(new) |
+ (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M :
+ _PMD_PAGE_512K) | _PMD_PRESENT);
#else
/* We use the old format for PPC_FSL_BOOK3E */
- hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
+ *hpdp = __hugepd(((unsigned long)new & ~PD_HUGE) | pshift);
#endif
+ }
}
/* If we bailed from the for loop early, an error occurred, clean up */
if (i < num_hugepd) {
for (i = i - 1 ; i >= 0; i--, hpdp--)
- hpdp->pd = 0;
+ *hpdp = __hugepd(0);
kmem_cache_free(cachep, new);
}
spin_unlock(&mm->page_table_lock);
@@ -454,7 +454,7 @@
return;
for (i = 0; i < num_hugepd; i++, hpdp++)
- hpdp->pd = 0;
+ *hpdp = __hugepd(0);
if (shift >= pdshift)
hugepd_free(tlb, hugepte);
@@ -810,12 +810,8 @@
* if we have pdshift and shift value same, we don't
* use pgt cache for hugepd.
*/
- if (pdshift > shift) {
+ if (pdshift > shift)
pgtable_cache_add(pdshift - shift, NULL);
- if (!PGT_CACHE(pdshift - shift))
- panic("hugetlbpage_init(): could not create "
- "pgtable cache for %d bit pagesize\n", shift);
- }
#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
else if (!hugepte_cache) {
/*
@@ -852,9 +848,6 @@
else if (mmu_psize_defs[MMU_PAGE_2M].shift)
HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_2M].shift;
#endif
- else
- panic("%s: Unable to set default huge page size\n", __func__);
-
return 0;
}
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index a175cd8..f2108c4 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -78,8 +78,12 @@
align = max_t(unsigned long, align, minalign);
name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
new = kmem_cache_create(name, table_size, align, 0, ctor);
+ if (!new)
+ panic("Could not allocate pgtable cache for order %d", shift);
+
kfree(name);
pgtable_cache[shift - 1] = new;
+
pr_debug("Allocated pgtable cache for order %d\n", shift);
}
@@ -88,7 +92,7 @@
{
pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
- if (PMD_INDEX_SIZE && !PGT_CACHE(PMD_INDEX_SIZE))
+ if (PMD_CACHE_INDEX && !PGT_CACHE(PMD_CACHE_INDEX))
pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
/*
* In all current configs, when the PUD index exists it's the
@@ -97,11 +101,4 @@
*/
if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor);
-
- if (!PGT_CACHE(PGD_INDEX_SIZE))
- panic("Couldn't allocate pgd cache");
- if (PMD_INDEX_SIZE && !PGT_CACHE(PMD_INDEX_SIZE))
- panic("Couldn't allocate pmd pgtable caches");
- if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
- panic("Couldn't allocate pud pgtable caches");
}
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 93abf8a..8e15880 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -347,7 +347,8 @@
void __init mmu_early_init_devtree(void)
{
/* Disable radix mode based on kernel command line. */
- if (disable_radix)
+ /* We don't yet have the machinery to do radix as a guest. */
+ if (disable_radix || !(mfmsr() & MSR_HV))
cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
if (early_radix_enabled())
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index ebf9782..653ff6c 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -126,3 +126,21 @@
else if (mmu_hash_ops.hpte_clear_all)
mmu_hash_ops.hpte_clear_all();
}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int create_section_mapping(unsigned long start, unsigned long end)
+{
+ if (radix_enabled())
+ return -ENODEV;
+
+ return hash__create_section_mapping(start, end);
+}
+
+int remove_section_mapping(unsigned long start, unsigned long end)
+{
+ if (radix_enabled())
+ return -ENODEV;
+
+ return hash__remove_section_mapping(start, end);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index cfa53cc..34f1a0d 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -65,7 +65,7 @@
if (!pmdp)
return -ENOMEM;
if (map_page_size == PMD_SIZE) {
- ptep = (pte_t *)pudp;
+ ptep = pmdp_ptep(pmdp);
goto set_the_pte;
}
ptep = pte_alloc_kernel(pmdp, ea);
@@ -90,7 +90,7 @@
}
pmdp = pmd_offset(pudp, ea);
if (map_page_size == PMD_SIZE) {
- ptep = (pte_t *)pudp;
+ ptep = pmdp_ptep(pmdp);
goto set_the_pte;
}
if (!pmd_present(*pmdp)) {
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 61b7911..952713d 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -50,9 +50,7 @@
for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
__tlbiel_pid(pid, set, ric);
}
- if (cpu_has_feature(CPU_FTR_POWER9_DD1))
- asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
- return;
+ asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
}
static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
@@ -85,8 +83,6 @@
asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
: : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
asm volatile("ptesync": : :"memory");
- if (cpu_has_feature(CPU_FTR_POWER9_DD1))
- asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
}
static inline void _tlbie_va(unsigned long va, unsigned long pid,
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index fd3e403..270eb9b 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -295,6 +295,8 @@
*/
if (TRAP(regs) != 0xf00)
use_siar = 0;
+ else if ((ppmu->flags & PPMU_NO_SIAR))
+ use_siar = 0;
else if (marked)
use_siar = 1;
else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING))
diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h
index 6447dc1..929b56d 100644
--- a/arch/powerpc/perf/power9-events-list.h
+++ b/arch/powerpc/perf/power9-events-list.h
@@ -16,7 +16,7 @@
EVENT(PM_ICT_NOSLOT_CYC, 0x100f8)
EVENT(PM_CMPLU_STALL, 0x1e054)
EVENT(PM_INST_CMPL, 0x00002)
-EVENT(PM_BRU_CMPL, 0x40060)
+EVENT(PM_BRU_CMPL, 0x10012)
EVENT(PM_BR_MPRED_CMPL, 0x400f6)
/* All L1 D cache load references counted at finish, gated by reject */
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 346010e..7332634 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -384,7 +384,7 @@
.bhrb_filter_map = power9_bhrb_filter_map,
.get_constraint = isa207_get_constraint,
.disable_pmc = isa207_disable_pmc,
- .flags = PPMU_HAS_SIER | PPMU_ARCH_207S,
+ .flags = PPMU_NO_SIAR | PPMU_ARCH_207S,
.n_generic = ARRAY_SIZE(power9_generic_events),
.generic_events = power9_generic_events,
.cache_events = &power9_cache_events,
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index c789258..eec0e8d 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -155,8 +155,10 @@
wmask = SRR1_WAKEMASK_P8;
idle_states = pnv_get_supported_cpuidle_states();
+
/* We don't want to take decrementer interrupts while we are offline,
- * so clear LPCR:PECE1. We keep PECE2 enabled.
+ * so clear LPCR:PECE1. We keep PECE2 (and LPCR_PECE_HVEE on P9)
+ * enabled as to let IPIs in.
*/
mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
@@ -206,8 +208,12 @@
* contains 0.
*/
if (((srr1 & wmask) == SRR1_WAKEEE) ||
+ ((srr1 & wmask) == SRR1_WAKEHVI) ||
(local_paca->irq_happened & PACA_IRQ_EE)) {
- icp_native_flush_interrupt();
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ icp_opal_flush_interrupt();
+ else
+ icp_native_flush_interrupt();
} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
@@ -221,6 +227,8 @@
if (srr1 && !generic_check_cpu_restart(cpu))
DBG("CPU%d Unexpected exit while offline !\n", cpu);
}
+
+ /* Re-enable decrementer interrupts */
mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1);
DBG("CPU%d coming online...\n", cpu);
}
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index d38e86f..f9670ea 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -20,6 +20,7 @@
#include <asm/xics.h>
#include <asm/io.h>
#include <asm/opal.h>
+#include <asm/kvm_ppc.h>
static void icp_opal_teardown_cpu(void)
{
@@ -39,7 +40,26 @@
* Should we be flagging idle loop instead?
* Or creating some task to be scheduled?
*/
- opal_int_eoi((0x00 << 24) | XICS_IPI);
+ if (opal_int_eoi((0x00 << 24) | XICS_IPI) > 0)
+ force_external_irq_replay();
+}
+
+static unsigned int icp_opal_get_xirr(void)
+{
+ unsigned int kvm_xirr;
+ __be32 hw_xirr;
+ int64_t rc;
+
+ /* Handle an interrupt latched by KVM first */
+ kvm_xirr = kvmppc_get_xics_latch();
+ if (kvm_xirr)
+ return kvm_xirr;
+
+ /* Then ask OPAL */
+ rc = opal_int_get_xirr(&hw_xirr, false);
+ if (rc < 0)
+ return 0;
+ return be32_to_cpu(hw_xirr);
}
static unsigned int icp_opal_get_irq(void)
@@ -47,12 +67,8 @@
unsigned int xirr;
unsigned int vec;
unsigned int irq;
- int64_t rc;
- rc = opal_int_get_xirr(&xirr, false);
- if (rc < 0)
- return 0;
- xirr = be32_to_cpu(xirr);
+ xirr = icp_opal_get_xirr();
vec = xirr & 0x00ffffff;
if (vec == XICS_IRQ_SPURIOUS)
return 0;
@@ -67,7 +83,8 @@
xics_mask_unknown_vec(vec);
/* We might learn about it later, so EOI it */
- opal_int_eoi(xirr);
+ if (opal_int_eoi(xirr) > 0)
+ force_external_irq_replay();
return 0;
}
@@ -103,18 +120,49 @@
{
int hw_cpu = get_hard_smp_processor_id(cpu);
+ kvmppc_set_host_ipi(cpu, 1);
opal_int_set_mfrr(hw_cpu, IPI_PRIORITY);
}
static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id)
{
- int hw_cpu = hard_smp_processor_id();
+ int cpu = smp_processor_id();
- opal_int_set_mfrr(hw_cpu, 0xff);
+ kvmppc_set_host_ipi(cpu, 0);
+ opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff);
return smp_ipi_demux();
}
+/*
+ * Called when an interrupt is received on an off-line CPU to
+ * clear the interrupt, so that the CPU can go back to nap mode.
+ */
+void icp_opal_flush_interrupt(void)
+{
+ unsigned int xirr;
+ unsigned int vec;
+
+ do {
+ xirr = icp_opal_get_xirr();
+ vec = xirr & 0x00ffffff;
+ if (vec == XICS_IRQ_SPURIOUS)
+ break;
+ if (vec == XICS_IPI) {
+ /* Clear pending IPI */
+ int cpu = smp_processor_id();
+ kvmppc_set_host_ipi(cpu, 0);
+ opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff);
+ } else {
+ pr_err("XICS: hw interrupt 0x%x to offline cpu, "
+ "disabling\n", vec);
+ xics_mask_unknown_vec(vec);
+ }
+
+ /* EOI the interrupt */
+ } while (opal_int_eoi(xirr) > 0);
+}
+
#endif /* CONFIG_SMP */
static const struct icp_ops icp_opal_ops = {
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 9c0e17c..3f864c3 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2287,14 +2287,14 @@
DUMP(p, subcore_sibling_mask, "x");
#endif
- DUMP(p, accounting.user_time, "llx");
- DUMP(p, accounting.system_time, "llx");
- DUMP(p, accounting.user_time_scaled, "llx");
+ DUMP(p, accounting.utime, "llx");
+ DUMP(p, accounting.stime, "llx");
+ DUMP(p, accounting.utime_scaled, "llx");
DUMP(p, accounting.starttime, "llx");
DUMP(p, accounting.starttime_user, "llx");
DUMP(p, accounting.startspurr, "llx");
DUMP(p, accounting.utime_sspurr, "llx");
- DUMP(p, stolen_time, "llx");
+ DUMP(p, accounting.steal_time, "llx");
#undef DUMP
catch_memory_errors = 0;
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 69b23b2..08b9e94 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -113,21 +113,21 @@
j = 0;
for_each_online_cpu(i) {
os_data->os_cpu[j].per_cpu_user =
- cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
+ nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
os_data->os_cpu[j].per_cpu_nice =
- cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
+ nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
os_data->os_cpu[j].per_cpu_system =
- cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
+ nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
os_data->os_cpu[j].per_cpu_idle =
- cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
+ nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
os_data->os_cpu[j].per_cpu_irq =
- cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
+ nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
os_data->os_cpu[j].per_cpu_softirq =
- cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
+ nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
os_data->os_cpu[j].per_cpu_iowait =
- cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
+ nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
os_data->os_cpu[j].per_cpu_steal =
- cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
+ nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
os_data->os_cpu[j].cpu_id = i;
j++;
}
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index e659daf..e0097536 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -69,7 +69,7 @@
CONFIG_CMA_DEBUG=y
CONFIG_CMA_DEBUGFS=y
CONFIG_MEM_SOFT_DIRTY=y
-CONFIG_ZPOOL=m
+CONFIG_ZSWAP=y
CONFIG_ZBUD=m
CONFIG_ZSMALLOC=m
CONFIG_ZSMALLOC_STAT=y
@@ -141,8 +141,6 @@
CONFIG_NF_CONNTRACK_EVENTS=y
CONFIG_NF_CONNTRACK_TIMEOUT=y
CONFIG_NF_CONNTRACK_TIMESTAMP=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
CONFIG_NF_CONNTRACK_AMANDA=m
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_H323=m
@@ -159,13 +157,12 @@
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_CT=m
-CONFIG_NFT_RBTREE=m
-CONFIG_NFT_HASH=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_NAT=m
CONFIG_NFT_COMPAT=m
+CONFIG_NFT_HASH=m
CONFIG_NETFILTER_XT_SET=m
CONFIG_NETFILTER_XT_TARGET_AUDIT=m
CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -219,7 +216,6 @@
CONFIG_NETFILTER_XT_MATCH_RATEEST=m
CONFIG_NETFILTER_XT_MATCH_REALM=m
CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_SOCKET=m
CONFIG_NETFILTER_XT_MATCH_STATE=m
CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -258,7 +254,6 @@
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
CONFIG_NF_CONNTRACK_IPV4=m
-# CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
CONFIG_NF_TABLES_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
@@ -436,7 +431,6 @@
CONFIG_IFB=m
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
-CONFIG_IPVLAN=m
CONFIG_VXLAN=m
CONFIG_TUN=m
CONFIG_VETH=m
@@ -480,6 +474,7 @@
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_ENCRYPTION=y
CONFIG_JBD2_DEBUG=y
CONFIG_JFS_FS=m
CONFIG_JFS_POSIX_ACL=y
@@ -592,14 +587,12 @@
CONFIG_DEBUG_LOCKDEP=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
-CONFIG_DEBUG_LIST=y
CONFIG_DEBUG_SG=y
CONFIG_DEBUG_NOTIFIERS=y
CONFIG_DEBUG_CREDENTIALS=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=300
CONFIG_NOTIFIER_ERROR_INJECTION=m
-CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
CONFIG_PM_NOTIFIER_ERROR_INJECT=m
CONFIG_FAULT_INJECTION=y
CONFIG_FAILSLAB=y
@@ -618,6 +611,7 @@
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_UPROBE_EVENT=y
CONFIG_FUNCTION_PROFILER=y
+CONFIG_HIST_TRIGGERS=y
CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_LKDTM=m
CONFIG_TEST_LIST_SORT=y
@@ -630,6 +624,7 @@
CONFIG_TEST_KSTRTOX=y
CONFIG_DMA_API_DEBUG=y
CONFIG_TEST_BPF=m
+CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_S390_PTDUMP=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
@@ -640,16 +635,18 @@
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_IMA=y
CONFIG_IMA_APPRAISE=y
+CONFIG_CRYPTO_RSA=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_USER=m
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
CONFIG_CRYPTO_CRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CCM=m
CONFIG_CRYPTO_GCM=m
-CONFIG_CRYPTO_CTS=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
@@ -673,11 +670,13 @@
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
+CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
CONFIG_ZCRYPT=m
CONFIG_CRYPTO_SHA1_S390=m
CONFIG_CRYPTO_SHA256_S390=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index 95ceac5..f05d2d6 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -12,6 +12,7 @@
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_NUMA_BALANCING=y
+# CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
CONFIG_BLK_CGROUP=y
@@ -54,8 +55,9 @@
CONFIG_UNIXWARE_DISKLABEL=y
CONFIG_CFQ_GROUP_IOSCHED=y
CONFIG_DEFAULT_DEADLINE=y
+CONFIG_LIVEPATCH=y
CONFIG_TUNE_ZEC12=y
-CONFIG_NR_CPUS=256
+CONFIG_NR_CPUS=512
CONFIG_NUMA=y
CONFIG_HZ_100=y
CONFIG_MEMORY_HOTPLUG=y
@@ -65,6 +67,7 @@
CONFIG_CLEANCACHE=y
CONFIG_FRONTSWAP=y
CONFIG_CMA=y
+CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
CONFIG_ZBUD=m
CONFIG_ZSMALLOC=m
@@ -136,8 +139,6 @@
CONFIG_NF_CONNTRACK_EVENTS=y
CONFIG_NF_CONNTRACK_TIMEOUT=y
CONFIG_NF_CONNTRACK_TIMESTAMP=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
CONFIG_NF_CONNTRACK_AMANDA=m
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_H323=m
@@ -154,13 +155,12 @@
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_CT=m
-CONFIG_NFT_RBTREE=m
-CONFIG_NFT_HASH=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_NAT=m
CONFIG_NFT_COMPAT=m
+CONFIG_NFT_HASH=m
CONFIG_NETFILTER_XT_SET=m
CONFIG_NETFILTER_XT_TARGET_AUDIT=m
CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -214,7 +214,6 @@
CONFIG_NETFILTER_XT_MATCH_RATEEST=m
CONFIG_NETFILTER_XT_MATCH_REALM=m
CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_SOCKET=m
CONFIG_NETFILTER_XT_MATCH_STATE=m
CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -253,7 +252,6 @@
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
CONFIG_NF_CONNTRACK_IPV4=m
-# CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
CONFIG_NF_TABLES_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
@@ -430,7 +428,6 @@
CONFIG_IFB=m
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
-CONFIG_IPVLAN=m
CONFIG_VXLAN=m
CONFIG_TUN=m
CONFIG_VETH=m
@@ -460,6 +457,7 @@
CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
+# CONFIG_HWMON is not set
CONFIG_WATCHDOG=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
@@ -473,6 +471,7 @@
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_ENCRYPTION=y
CONFIG_JBD2_DEBUG=y
CONFIG_JFS_FS=m
CONFIG_JFS_POSIX_ACL=y
@@ -495,6 +494,7 @@
CONFIG_FUSE_FS=y
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
+CONFIG_OVERLAY_FS_REDIRECT_DIR=y
CONFIG_FSCACHE=m
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=y
@@ -551,25 +551,27 @@
CONFIG_UNUSED_SYMBOLS=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
CONFIG_PANIC_ON_OOPS=y
CONFIG_TIMER_STATS=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=60
-CONFIG_NOTIFIER_ERROR_INJECTION=m
-CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
-CONFIG_PM_NOTIFIER_ERROR_INJECT=m
CONFIG_LATENCYTOP=y
+CONFIG_SCHED_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
-# CONFIG_KPROBE_EVENT is not set
+CONFIG_UPROBE_EVENT=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_HIST_TRIGGERS=y
CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_LKDTM=m
-CONFIG_RBTREE_TEST=m
-CONFIG_INTERVAL_TREE_TEST=m
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BPF=m
+CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_S390_PTDUMP=y
+CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
@@ -577,18 +579,25 @@
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_INTEGRITY_SIGNATURE=y
+CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA=y
+CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_USER=m
# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_PCRYPT=m
CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CCM=m
CONFIG_CRYPTO_GCM=m
-CONFIG_CRYPTO_CTS=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
@@ -598,6 +607,7 @@
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
@@ -612,10 +622,13 @@
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
+CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
CONFIG_ZCRYPT=m
CONFIG_CRYPTO_SHA1_S390=m
CONFIG_CRYPTO_SHA256_S390=m
@@ -624,9 +637,6 @@
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_ASYMMETRIC_KEY_TYPE=y
-CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_X509_CERTIFICATE_PARSER=m
CONFIG_CRC7=m
CONFIG_CRC8=m
CONFIG_CORDIC=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index bc7b176..2cf8734 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -65,6 +65,7 @@
CONFIG_CLEANCACHE=y
CONFIG_FRONTSWAP=y
CONFIG_CMA=y
+CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
CONFIG_ZBUD=m
CONFIG_ZSMALLOC=m
@@ -136,8 +137,6 @@
CONFIG_NF_CONNTRACK_EVENTS=y
CONFIG_NF_CONNTRACK_TIMEOUT=y
CONFIG_NF_CONNTRACK_TIMESTAMP=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
CONFIG_NF_CONNTRACK_AMANDA=m
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_H323=m
@@ -154,13 +153,12 @@
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_CT=m
-CONFIG_NFT_RBTREE=m
-CONFIG_NFT_HASH=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_NAT=m
CONFIG_NFT_COMPAT=m
+CONFIG_NFT_HASH=m
CONFIG_NETFILTER_XT_SET=m
CONFIG_NETFILTER_XT_TARGET_AUDIT=m
CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -214,7 +212,6 @@
CONFIG_NETFILTER_XT_MATCH_RATEEST=m
CONFIG_NETFILTER_XT_MATCH_REALM=m
CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_SOCKET=m
CONFIG_NETFILTER_XT_MATCH_STATE=m
CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -253,7 +250,6 @@
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
CONFIG_NF_CONNTRACK_IPV4=m
-# CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
CONFIG_NF_TABLES_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=m
@@ -430,7 +426,6 @@
CONFIG_IFB=m
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
-CONFIG_IPVLAN=m
CONFIG_VXLAN=m
CONFIG_TUN=m
CONFIG_VETH=m
@@ -474,6 +469,7 @@
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_ENCRYPTION=y
CONFIG_JBD2_DEBUG=y
CONFIG_JFS_FS=m
CONFIG_JFS_POSIX_ACL=y
@@ -496,6 +492,7 @@
CONFIG_FUSE_FS=y
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
+CONFIG_OVERLAY_FS_REDIRECT_DIR=y
CONFIG_FSCACHE=m
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=y
@@ -563,12 +560,16 @@
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_UPROBE_EVENT=y
CONFIG_FUNCTION_PROFILER=y
+CONFIG_HIST_TRIGGERS=y
CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_LKDTM=m
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BPF=m
+CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_S390_PTDUMP=y
+CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
@@ -576,18 +577,25 @@
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_INTEGRITY_SIGNATURE=y
+CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA=y
+CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_USER=m
# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_PCRYPT=m
CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CCM=m
CONFIG_CRYPTO_GCM=m
-CONFIG_CRYPTO_CTS=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
@@ -597,6 +605,7 @@
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_ANUBIS=m
@@ -611,10 +620,13 @@
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
+CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
CONFIG_ZCRYPT=m
CONFIG_CRYPTO_SHA1_S390=m
CONFIG_CRYPTO_SHA256_S390=m
@@ -623,9 +635,6 @@
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_ASYMMETRIC_KEY_TYPE=y
-CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_X509_CERTIFICATE_PARSER=m
CONFIG_CRC7=m
CONFIG_CRC8=m
CONFIG_CORDIC=m
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 2d40ef0..d00e368 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -38,7 +38,6 @@
CONFIG_STATIC_KEYS_SELFTEST=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
@@ -130,8 +129,11 @@
CONFIG_EQUALIZER=m
CONFIG_TUN=m
CONFIG_VIRTIO_NET=y
+# CONFIG_NET_VENDOR_ALACRITECH is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_INPUT is not set
# CONFIG_SERIO is not set
+CONFIG_DEVKMEM=y
CONFIG_RAW_DRIVER=m
CONFIG_VIRTIO_BALLOON=y
CONFIG_EXT4_FS=y
@@ -183,7 +185,6 @@
CONFIG_KPROBES_SANITY_TEST=y
CONFIG_S390_PTDUMP=y
CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_AUTHENC=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CCM=m
CONFIG_CRYPTO_GCM=m
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index 221b454..d1c407d 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -25,33 +25,6 @@
return n / base;
}
-#define cputime_one_jiffy jiffies_to_cputime(1)
-
-/*
- * Convert cputime to jiffies and back.
- */
-static inline unsigned long cputime_to_jiffies(const cputime_t cputime)
-{
- return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / HZ);
-}
-
-static inline cputime_t jiffies_to_cputime(const unsigned int jif)
-{
- return (__force cputime_t)(jif * (CPUTIME_PER_SEC / HZ));
-}
-
-static inline u64 cputime64_to_jiffies64(cputime64_t cputime)
-{
- unsigned long long jif = (__force unsigned long long) cputime;
- do_div(jif, CPUTIME_PER_SEC / HZ);
- return jif;
-}
-
-static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
-{
- return (__force cputime64_t)(jif * (CPUTIME_PER_SEC / HZ));
-}
-
/*
* Convert cputime to microseconds and back.
*/
@@ -60,88 +33,8 @@
return (__force unsigned long long) cputime >> 12;
}
-static inline cputime_t usecs_to_cputime(const unsigned int m)
-{
- return (__force cputime_t)(m * CPUTIME_PER_USEC);
-}
-#define usecs_to_cputime64(m) usecs_to_cputime(m)
-
-/*
- * Convert cputime to milliseconds and back.
- */
-static inline unsigned int cputime_to_secs(const cputime_t cputime)
-{
- return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / 2) >> 1;
-}
-
-static inline cputime_t secs_to_cputime(const unsigned int s)
-{
- return (__force cputime_t)(s * CPUTIME_PER_SEC);
-}
-
-/*
- * Convert cputime to timespec and back.
- */
-static inline cputime_t timespec_to_cputime(const struct timespec *value)
-{
- unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC;
- return (__force cputime_t)(ret + __div(value->tv_nsec * CPUTIME_PER_USEC, NSEC_PER_USEC));
-}
-
-static inline void cputime_to_timespec(const cputime_t cputime,
- struct timespec *value)
-{
- unsigned long long __cputime = (__force unsigned long long) cputime;
- value->tv_nsec = (__cputime % CPUTIME_PER_SEC) * NSEC_PER_USEC / CPUTIME_PER_USEC;
- value->tv_sec = __cputime / CPUTIME_PER_SEC;
-}
-
-/*
- * Convert cputime to timeval and back.
- * Since cputime and timeval have the same resolution (microseconds)
- * this is easy.
- */
-static inline cputime_t timeval_to_cputime(const struct timeval *value)
-{
- unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC;
- return (__force cputime_t)(ret + value->tv_usec * CPUTIME_PER_USEC);
-}
-
-static inline void cputime_to_timeval(const cputime_t cputime,
- struct timeval *value)
-{
- unsigned long long __cputime = (__force unsigned long long) cputime;
- value->tv_usec = (__cputime % CPUTIME_PER_SEC) / CPUTIME_PER_USEC;
- value->tv_sec = __cputime / CPUTIME_PER_SEC;
-}
-
-/*
- * Convert cputime to clock and back.
- */
-static inline clock_t cputime_to_clock_t(cputime_t cputime)
-{
- unsigned long long clock = (__force unsigned long long) cputime;
- do_div(clock, CPUTIME_PER_SEC / USER_HZ);
- return clock;
-}
-
-static inline cputime_t clock_t_to_cputime(unsigned long x)
-{
- return (__force cputime_t)(x * (CPUTIME_PER_SEC / USER_HZ));
-}
-
-/*
- * Convert cputime64 to clock.
- */
-static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
-{
- unsigned long long clock = (__force unsigned long long) cputime;
- do_div(clock, CPUTIME_PER_SEC / USER_HZ);
- return clock;
-}
-
-cputime64_t arch_cpu_idle_time(int cpu);
+u64 arch_cpu_idle_time(int cpu);
#define arch_idle_time(cpu) arch_cpu_idle_time(cpu)
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index d7697ab..8e136b88 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -15,7 +15,9 @@
BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\
asm volatile( \
" lctlg %1,%2,%0\n" \
- : : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high));\
+ : \
+ : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high) \
+ : "memory"); \
}
#define __ctl_store(array, low, high) { \
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 9bfad2a..61261e0 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -85,53 +85,56 @@
__u64 mcck_enter_timer; /* 0x02c0 */
__u64 exit_timer; /* 0x02c8 */
__u64 user_timer; /* 0x02d0 */
- __u64 system_timer; /* 0x02d8 */
- __u64 steal_timer; /* 0x02e0 */
- __u64 last_update_timer; /* 0x02e8 */
- __u64 last_update_clock; /* 0x02f0 */
- __u64 int_clock; /* 0x02f8 */
- __u64 mcck_clock; /* 0x0300 */
- __u64 clock_comparator; /* 0x0308 */
+ __u64 guest_timer; /* 0x02d8 */
+ __u64 system_timer; /* 0x02e0 */
+ __u64 hardirq_timer; /* 0x02e8 */
+ __u64 softirq_timer; /* 0x02f0 */
+ __u64 steal_timer; /* 0x02f8 */
+ __u64 last_update_timer; /* 0x0300 */
+ __u64 last_update_clock; /* 0x0308 */
+ __u64 int_clock; /* 0x0310 */
+ __u64 mcck_clock; /* 0x0318 */
+ __u64 clock_comparator; /* 0x0320 */
/* Current process. */
- __u64 current_task; /* 0x0310 */
- __u8 pad_0x318[0x320-0x318]; /* 0x0318 */
- __u64 kernel_stack; /* 0x0320 */
+ __u64 current_task; /* 0x0328 */
+ __u8 pad_0x318[0x320-0x318]; /* 0x0330 */
+ __u64 kernel_stack; /* 0x0338 */
/* Interrupt, panic and restart stack. */
- __u64 async_stack; /* 0x0328 */
- __u64 panic_stack; /* 0x0330 */
- __u64 restart_stack; /* 0x0338 */
+ __u64 async_stack; /* 0x0340 */
+ __u64 panic_stack; /* 0x0348 */
+ __u64 restart_stack; /* 0x0350 */
/* Restart function and parameter. */
- __u64 restart_fn; /* 0x0340 */
- __u64 restart_data; /* 0x0348 */
- __u64 restart_source; /* 0x0350 */
+ __u64 restart_fn; /* 0x0358 */
+ __u64 restart_data; /* 0x0360 */
+ __u64 restart_source; /* 0x0368 */
/* Address space pointer. */
- __u64 kernel_asce; /* 0x0358 */
- __u64 user_asce; /* 0x0360 */
+ __u64 kernel_asce; /* 0x0370 */
+ __u64 user_asce; /* 0x0378 */
/*
* The lpp and current_pid fields form a
* 64-bit value that is set as program
* parameter with the LPP instruction.
*/
- __u32 lpp; /* 0x0368 */
- __u32 current_pid; /* 0x036c */
+ __u32 lpp; /* 0x0380 */
+ __u32 current_pid; /* 0x0384 */
/* SMP info area */
- __u32 cpu_nr; /* 0x0370 */
- __u32 softirq_pending; /* 0x0374 */
- __u64 percpu_offset; /* 0x0378 */
- __u64 vdso_per_cpu_data; /* 0x0380 */
- __u64 machine_flags; /* 0x0388 */
- __u32 preempt_count; /* 0x0390 */
- __u8 pad_0x0394[0x0398-0x0394]; /* 0x0394 */
- __u64 gmap; /* 0x0398 */
- __u32 spinlock_lockval; /* 0x03a0 */
- __u32 fpu_flags; /* 0x03a4 */
- __u8 pad_0x03a8[0x0400-0x03a8]; /* 0x03a8 */
+ __u32 cpu_nr; /* 0x0388 */
+ __u32 softirq_pending; /* 0x038c */
+ __u64 percpu_offset; /* 0x0390 */
+ __u64 vdso_per_cpu_data; /* 0x0398 */
+ __u64 machine_flags; /* 0x03a0 */
+ __u32 preempt_count; /* 0x03a8 */
+ __u8 pad_0x03ac[0x03b0-0x03ac]; /* 0x03ac */
+ __u64 gmap; /* 0x03b0 */
+ __u32 spinlock_lockval; /* 0x03b8 */
+ __u32 fpu_flags; /* 0x03bc */
+ __u8 pad_0x03c0[0x0400-0x03c0]; /* 0x03c0 */
/* Per cpu primary space access list */
__u32 paste[16]; /* 0x0400 */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 6bca916..977a5b6 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -111,7 +111,10 @@
unsigned int acrs[NUM_ACRS];
unsigned long ksp; /* kernel stack pointer */
unsigned long user_timer; /* task cputime in user space */
+ unsigned long guest_timer; /* task cputime in kvm guest */
unsigned long system_timer; /* task cputime in kernel space */
+ unsigned long hardirq_timer; /* task cputime in hardirq context */
+ unsigned long softirq_timer; /* task cputime in softirq context */
unsigned long sys_call_table; /* system call table address */
mm_segment_t mm_segment;
unsigned long gmap_addr; /* address of last gmap fault. */
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 7a55c29..d3bf69e 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -12,7 +12,7 @@
#include <linux/notifier.h>
#include <linux/init.h>
#include <linux/cpu.h>
-#include <asm/cputime.h>
+#include <linux/cputime.h>
#include <asm/nmi.h>
#include <asm/smp.h>
#include "entry.h"
@@ -43,7 +43,7 @@
idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
idle->idle_time += idle_time;
idle->idle_count++;
- account_idle_time(idle_time);
+ account_idle_time(cputime_to_nsecs(idle_time));
write_seqcount_end(&idle->seqcount);
}
NOKPROBE_SYMBOL(enabled_wait);
@@ -84,7 +84,7 @@
}
DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
-cputime64_t arch_cpu_idle_time(int cpu)
+u64 arch_cpu_idle_time(int cpu)
{
struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
unsigned long long now, idle_enter, idle_exit;
@@ -96,7 +96,8 @@
idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
} while (read_seqcount_retry(&idle->seqcount, seq));
- return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
+
+ return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0);
}
void arch_cpu_idle_enter(void)
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 7447ba5..12020b5 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -963,6 +963,11 @@
if (target == current)
save_fpu_regs();
+ if (MACHINE_HAS_VX)
+ convert_vx_to_fp(fprs, target->thread.fpu.vxrs);
+ else
+ memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
+
/* If setting FPC, must validate it first. */
if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
@@ -1067,6 +1072,9 @@
if (target == current)
save_fpu_regs();
+ for (i = 0; i < __NUM_VXRS_LOW; i++)
+ vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1);
+
rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
if (rc == 0)
for (i = 0; i < __NUM_VXRS_LOW; i++)
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 1b5c5ee..b4a3e9e 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -6,13 +6,13 @@
*/
#include <linux/kernel_stat.h>
+#include <linux/cputime.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/timex.h>
#include <linux/types.h>
#include <linux/time.h>
-#include <asm/cputime.h>
#include <asm/vtimer.h>
#include <asm/vtime.h>
#include <asm/cpu_mf.h>
@@ -90,14 +90,41 @@
__this_cpu_write(mt_scaling_jiffies, jiffies_64);
}
+static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new)
+{
+ u64 delta;
+
+ delta = new - *tsk_vtime;
+ *tsk_vtime = new;
+ return delta;
+}
+
+
+static inline u64 scale_vtime(u64 vtime)
+{
+ u64 mult = __this_cpu_read(mt_scaling_mult);
+ u64 div = __this_cpu_read(mt_scaling_div);
+
+ if (smp_cpu_mtid)
+ return vtime * mult / div;
+ return vtime;
+}
+
+static void account_system_index_scaled(struct task_struct *p,
+ cputime_t cputime, cputime_t scaled,
+ enum cpu_usage_stat index)
+{
+ p->stimescaled += cputime_to_nsecs(scaled);
+ account_system_index_time(p, cputime_to_nsecs(cputime), index);
+}
+
/*
* Update process times based on virtual cpu times stored by entry.S
* to the lowcore fields user_timer, system_timer & steal_clock.
*/
static int do_account_vtime(struct task_struct *tsk)
{
- u64 timer, clock, user, system, steal;
- u64 user_scaled, system_scaled;
+ u64 timer, clock, user, guest, system, hardirq, softirq, steal;
timer = S390_lowcore.last_update_timer;
clock = S390_lowcore.last_update_clock;
@@ -110,53 +137,76 @@
#endif
: "=m" (S390_lowcore.last_update_timer),
"=m" (S390_lowcore.last_update_clock));
- S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
- S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock;
+ clock = S390_lowcore.last_update_clock - clock;
+ timer -= S390_lowcore.last_update_timer;
+
+ if (hardirq_count())
+ S390_lowcore.hardirq_timer += timer;
+ else
+ S390_lowcore.system_timer += timer;
/* Update MT utilization calculation */
if (smp_cpu_mtid &&
time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
update_mt_scaling();
- user = S390_lowcore.user_timer - tsk->thread.user_timer;
- S390_lowcore.steal_timer -= user;
- tsk->thread.user_timer = S390_lowcore.user_timer;
+ /* Calculate cputime delta */
+ user = update_tsk_timer(&tsk->thread.user_timer,
+ READ_ONCE(S390_lowcore.user_timer));
+ guest = update_tsk_timer(&tsk->thread.guest_timer,
+ READ_ONCE(S390_lowcore.guest_timer));
+ system = update_tsk_timer(&tsk->thread.system_timer,
+ READ_ONCE(S390_lowcore.system_timer));
+ hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
+ READ_ONCE(S390_lowcore.hardirq_timer));
+ softirq = update_tsk_timer(&tsk->thread.softirq_timer,
+ READ_ONCE(S390_lowcore.softirq_timer));
+ S390_lowcore.steal_timer +=
+ clock - user - guest - system - hardirq - softirq;
- system = S390_lowcore.system_timer - tsk->thread.system_timer;
- S390_lowcore.steal_timer -= system;
- tsk->thread.system_timer = S390_lowcore.system_timer;
-
- user_scaled = user;
- system_scaled = system;
- /* Do MT utilization scaling */
- if (smp_cpu_mtid) {
- u64 mult = __this_cpu_read(mt_scaling_mult);
- u64 div = __this_cpu_read(mt_scaling_div);
-
- user_scaled = (user_scaled * mult) / div;
- system_scaled = (system_scaled * mult) / div;
+ /* Push account value */
+ if (user) {
+ account_user_time(tsk, cputime_to_nsecs(user));
+ tsk->utimescaled += cputime_to_nsecs(scale_vtime(user));
}
- account_user_time(tsk, user);
- tsk->utimescaled += user_scaled;
- account_system_time(tsk, 0, system);
- tsk->stimescaled += system_scaled;
+
+ if (guest) {
+ account_guest_time(tsk, cputime_to_nsecs(guest));
+ tsk->utimescaled += cputime_to_nsecs(scale_vtime(guest));
+ }
+
+ if (system)
+ account_system_index_scaled(tsk, system, scale_vtime(system),
+ CPUTIME_SYSTEM);
+ if (hardirq)
+ account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq),
+ CPUTIME_IRQ);
+ if (softirq)
+ account_system_index_scaled(tsk, softirq, scale_vtime(softirq),
+ CPUTIME_SOFTIRQ);
steal = S390_lowcore.steal_timer;
if ((s64) steal > 0) {
S390_lowcore.steal_timer = 0;
- account_steal_time(steal);
+ account_steal_time(cputime_to_nsecs(steal));
}
- return virt_timer_forward(user + system);
+ return virt_timer_forward(user + guest + system + hardirq + softirq);
}
void vtime_task_switch(struct task_struct *prev)
{
do_account_vtime(prev);
prev->thread.user_timer = S390_lowcore.user_timer;
+ prev->thread.guest_timer = S390_lowcore.guest_timer;
prev->thread.system_timer = S390_lowcore.system_timer;
+ prev->thread.hardirq_timer = S390_lowcore.hardirq_timer;
+ prev->thread.softirq_timer = S390_lowcore.softirq_timer;
S390_lowcore.user_timer = current->thread.user_timer;
+ S390_lowcore.guest_timer = current->thread.guest_timer;
S390_lowcore.system_timer = current->thread.system_timer;
+ S390_lowcore.hardirq_timer = current->thread.hardirq_timer;
+ S390_lowcore.softirq_timer = current->thread.softirq_timer;
}
/*
@@ -164,7 +214,7 @@
* accounting system time in order to correctly compute
* the stolen time accounting.
*/
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
{
if (do_account_vtime(tsk))
virt_timer_expire();
@@ -176,32 +226,22 @@
*/
void vtime_account_irq_enter(struct task_struct *tsk)
{
- u64 timer, system, system_scaled;
+ u64 timer;
timer = S390_lowcore.last_update_timer;
S390_lowcore.last_update_timer = get_vtimer();
- S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
+ timer -= S390_lowcore.last_update_timer;
- /* Update MT utilization calculation */
- if (smp_cpu_mtid &&
- time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
- update_mt_scaling();
+ if ((tsk->flags & PF_VCPU) && (irq_count() == 0))
+ S390_lowcore.guest_timer += timer;
+ else if (hardirq_count())
+ S390_lowcore.hardirq_timer += timer;
+ else if (in_serving_softirq())
+ S390_lowcore.softirq_timer += timer;
+ else
+ S390_lowcore.system_timer += timer;
- system = S390_lowcore.system_timer - tsk->thread.system_timer;
- S390_lowcore.steal_timer -= system;
- tsk->thread.system_timer = S390_lowcore.system_timer;
- system_scaled = system;
- /* Do MT utilization scaling */
- if (smp_cpu_mtid) {
- u64 mult = __this_cpu_read(mt_scaling_mult);
- u64 div = __this_cpu_read(mt_scaling_div);
-
- system_scaled = (system_scaled * mult) / div;
- }
- account_system_time(tsk, 0, system);
- tsk->stimescaled += system_scaled;
-
- virt_timer_forward(system);
+ virt_timer_forward(timer);
}
EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index bec71e9..6484a25 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -916,7 +916,7 @@
memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
- S390_ARCH_FAC_LIST_SIZE_BYTE);
+ sizeof(S390_lowcore.stfle_fac_list));
if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
ret = -EFAULT;
kfree(mach);
@@ -1437,7 +1437,7 @@
/* Populate the facility mask initially. */
memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
- S390_ARCH_FAC_LIST_SIZE_BYTE);
+ sizeof(S390_lowcore.stfle_fac_list));
for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
if (i < kvm_s390_fac_list_mask_size())
kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 7a1897c..d56ef26 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -202,7 +202,7 @@
return pgste;
}
-static inline void ptep_xchg_commit(struct mm_struct *mm,
+static inline pte_t ptep_xchg_commit(struct mm_struct *mm,
unsigned long addr, pte_t *ptep,
pgste_t pgste, pte_t old, pte_t new)
{
@@ -220,6 +220,7 @@
} else {
*ptep = new;
}
+ return old;
}
pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr,
@@ -231,7 +232,7 @@
preempt_disable();
pgste = ptep_xchg_start(mm, addr, ptep);
old = ptep_flush_direct(mm, addr, ptep);
- ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+ old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
preempt_enable();
return old;
}
@@ -246,7 +247,7 @@
preempt_disable();
pgste = ptep_xchg_start(mm, addr, ptep);
old = ptep_flush_lazy(mm, addr, ptep);
- ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+ old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
preempt_enable();
return old;
}
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index a05218f..51970bb 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -4,7 +4,6 @@
generic-y += barrier.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 751c337..cf2a750 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -1,7 +1,6 @@
generic-y += bitsperlong.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += delay.h
generic-y += div64.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 0569bfa..e9e837b 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -2,7 +2,6 @@
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += div64.h
generic-y += emergency-restart.h
generic-y += exec.h
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index b84be67..d031799 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -35,15 +35,15 @@
static inline void tsb_context_switch(struct mm_struct *mm)
{
__tsb_context_switch(__pa(mm->pgd),
- &mm->context.tsb_block[0],
+ &mm->context.tsb_block[MM_TSB_BASE],
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- (mm->context.tsb_block[1].tsb ?
- &mm->context.tsb_block[1] :
+ (mm->context.tsb_block[MM_TSB_HUGE].tsb ?
+ &mm->context.tsb_block[MM_TSB_HUGE] :
NULL)
#else
NULL
#endif
- , __pa(&mm->context.tsb_descr[0]));
+ , __pa(&mm->context.tsb_descr[MM_TSB_BASE]));
}
void tsb_grow(struct mm_struct *mm,
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 3bebf39..4d0248a 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1021,7 +1021,7 @@
unsigned long order = get_order(size);
unsigned long p;
- p = __get_free_pages(GFP_KERNEL, order);
+ p = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
if (!p) {
prom_printf("SUN4V: Error, cannot allocate queue.\n");
prom_halt();
diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c
index c59af54..3caed40 100644
--- a/arch/sparc/kernel/sstate.c
+++ b/arch/sparc/kernel/sstate.c
@@ -43,8 +43,8 @@
"Linux powering off";
static const char rebooting_msg[32] __attribute__((aligned(32))) =
"Linux rebooting";
-static const char panicing_msg[32] __attribute__((aligned(32))) =
- "Linux panicing";
+static const char panicking_msg[32] __attribute__((aligned(32))) =
+ "Linux panicking";
static int sstate_reboot_call(struct notifier_block *np, unsigned long type, void *_unused)
{
@@ -76,7 +76,7 @@
static int sstate_panic_event(struct notifier_block *n, unsigned long event, void *ptr)
{
- do_set_sstate(HV_SOFT_STATE_TRANSITION, panicing_msg);
+ do_set_sstate(HV_SOFT_STATE_TRANSITION, panicking_msg);
return NOTIFY_DONE;
}
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 4bc10e4..dfc97a4 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2051,6 +2051,73 @@
atomic_inc(&sun4v_resum_oflow_cnt);
}
+/* Given a set of registers, get the virtual addressi that was being accessed
+ * by the faulting instructions at tpc.
+ */
+static unsigned long sun4v_get_vaddr(struct pt_regs *regs)
+{
+ unsigned int insn;
+
+ if (!copy_from_user(&insn, (void __user *)regs->tpc, 4)) {
+ return compute_effective_address(regs, insn,
+ (insn >> 25) & 0x1f);
+ }
+ return 0;
+}
+
+/* Attempt to handle non-resumable errors generated from userspace.
+ * Returns true if the signal was handled, false otherwise.
+ */
+bool sun4v_nonresum_error_user_handled(struct pt_regs *regs,
+ struct sun4v_error_entry *ent) {
+
+ unsigned int attrs = ent->err_attrs;
+
+ if (attrs & SUN4V_ERR_ATTRS_MEMORY) {
+ unsigned long addr = ent->err_raddr;
+ siginfo_t info;
+
+ if (addr == ~(u64)0) {
+ /* This seems highly unlikely to ever occur */
+ pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory error detected in unknown location!\n");
+ } else {
+ unsigned long page_cnt = DIV_ROUND_UP(ent->err_size,
+ PAGE_SIZE);
+
+ /* Break the unfortunate news. */
+ pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory failed at %016lX\n",
+ addr);
+ pr_emerg("SUN4V NON-RECOVERABLE ERROR: Claiming %lu ages.\n",
+ page_cnt);
+
+ while (page_cnt-- > 0) {
+ if (pfn_valid(addr >> PAGE_SHIFT))
+ get_page(pfn_to_page(addr >> PAGE_SHIFT));
+ addr += PAGE_SIZE;
+ }
+ }
+ info.si_signo = SIGKILL;
+ info.si_errno = 0;
+ info.si_trapno = 0;
+ force_sig_info(info.si_signo, &info, current);
+
+ return true;
+ }
+ if (attrs & SUN4V_ERR_ATTRS_PIO) {
+ siginfo_t info;
+
+ info.si_signo = SIGBUS;
+ info.si_code = BUS_ADRERR;
+ info.si_addr = (void __user *)sun4v_get_vaddr(regs);
+ force_sig_info(info.si_signo, &info, current);
+
+ return true;
+ }
+
+ /* Default to doing nothing */
+ return false;
+}
+
/* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate.
* Log the event, clear the first word of the entry, and die.
*/
@@ -2075,6 +2142,12 @@
put_cpu();
+ if (!(regs->tstate & TSTATE_PRIV) &&
+ sun4v_nonresum_error_user_handled(regs, &local_copy)) {
+ /* DON'T PANIC: This userspace error was handled. */
+ return;
+ }
+
#ifdef CONFIG_PCI
/* Check for the special PCI poke sequence. */
if (pci_poke_in_progress && pci_poke_cpu == cpu) {
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 2d1f563..aa48b6e 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -4,8 +4,6 @@
generic-y += bug.h
generic-y += bugs.h
generic-y += clkdev.h
-generic-y += cputime.h
-generic-y += div64.h
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
diff --git a/arch/tile/include/asm/div64.h b/arch/tile/include/asm/div64.h
new file mode 100644
index 0000000..9f765cd
--- /dev/null
+++ b/arch/tile/include/asm/div64.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_TILE_DIV64_H
+#define _ASM_TILE_DIV64_H
+
+#include <linux/types.h>
+
+#ifdef __tilegx__
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+ return __insn_mul_lu_lu(a, b);
+}
+#define mul_u32_u32 mul_u32_u32
+#endif
+
+#include <asm-generic/div64.h>
+
+#endif /* _ASM_TILE_DIV64_H */
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index d89b701..e279572 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -111,7 +111,7 @@
const void *kbuf, const void __user *ubuf)
{
int ret;
- struct pt_regs regs;
+ struct pt_regs regs = *task_pt_regs(target);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0,
sizeof(regs));
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 052f7f6..90c281c 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,7 +1,6 @@
generic-y += barrier.h
generic-y += bug.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += delay.h
generic-y += device.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 256c45b..5d51ade 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -4,7 +4,6 @@
generic-y += bitsperlong.h
generic-y += bugs.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e487493..7b6fd68 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1070,7 +1070,7 @@
def_bool y
config X86_MCE_INJECT
- depends on X86_MCE
+ depends on X86_MCE && X86_LOCAL_APIC
tristate "Machine check injector support"
---help---
Provide support for injecting machine checks for testing purposes.
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ff01c8f..801c7a1 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -32,160 +32,13 @@
\
table = (typeof(table))sys_table; \
\
+ c->runtime_services = table->runtime; \
c->boot_services = table->boottime; \
c->text_output = table->con_out; \
}
BOOT_SERVICES(32);
BOOT_SERVICES(64);
-void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
-
-static efi_status_t
-__file_size32(void *__fh, efi_char16_t *filename_16,
- void **handle, u64 *file_sz)
-{
- efi_file_handle_32_t *h, *fh = __fh;
- efi_file_info_t *info;
- efi_status_t status;
- efi_guid_t info_guid = EFI_FILE_INFO_ID;
- u32 info_sz;
-
- status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
- EFI_FILE_MODE_READ, (u64)0);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to open file: ");
- efi_char16_printk(sys_table, filename_16);
- efi_printk(sys_table, "\n");
- return status;
- }
-
- *handle = h;
-
- info_sz = 0;
- status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
- &info_sz, NULL);
- if (status != EFI_BUFFER_TOO_SMALL) {
- efi_printk(sys_table, "Failed to get file info size\n");
- return status;
- }
-
-grow:
- status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
- info_sz, (void **)&info);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc mem for file info\n");
- return status;
- }
-
- status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
- &info_sz, info);
- if (status == EFI_BUFFER_TOO_SMALL) {
- efi_call_early(free_pool, info);
- goto grow;
- }
-
- *file_sz = info->file_size;
- efi_call_early(free_pool, info);
-
- if (status != EFI_SUCCESS)
- efi_printk(sys_table, "Failed to get initrd info\n");
-
- return status;
-}
-
-static efi_status_t
-__file_size64(void *__fh, efi_char16_t *filename_16,
- void **handle, u64 *file_sz)
-{
- efi_file_handle_64_t *h, *fh = __fh;
- efi_file_info_t *info;
- efi_status_t status;
- efi_guid_t info_guid = EFI_FILE_INFO_ID;
- u64 info_sz;
-
- status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
- EFI_FILE_MODE_READ, (u64)0);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to open file: ");
- efi_char16_printk(sys_table, filename_16);
- efi_printk(sys_table, "\n");
- return status;
- }
-
- *handle = h;
-
- info_sz = 0;
- status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
- &info_sz, NULL);
- if (status != EFI_BUFFER_TOO_SMALL) {
- efi_printk(sys_table, "Failed to get file info size\n");
- return status;
- }
-
-grow:
- status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
- info_sz, (void **)&info);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc mem for file info\n");
- return status;
- }
-
- status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
- &info_sz, info);
- if (status == EFI_BUFFER_TOO_SMALL) {
- efi_call_early(free_pool, info);
- goto grow;
- }
-
- *file_sz = info->file_size;
- efi_call_early(free_pool, info);
-
- if (status != EFI_SUCCESS)
- efi_printk(sys_table, "Failed to get initrd info\n");
-
- return status;
-}
-efi_status_t
-efi_file_size(efi_system_table_t *sys_table, void *__fh,
- efi_char16_t *filename_16, void **handle, u64 *file_sz)
-{
- if (efi_early->is64)
- return __file_size64(__fh, filename_16, handle, file_sz);
-
- return __file_size32(__fh, filename_16, handle, file_sz);
-}
-
-efi_status_t
-efi_file_read(void *handle, unsigned long *size, void *addr)
-{
- unsigned long func;
-
- if (efi_early->is64) {
- efi_file_handle_64_t *fh = handle;
-
- func = (unsigned long)fh->read;
- return efi_early->call(func, handle, size, addr);
- } else {
- efi_file_handle_32_t *fh = handle;
-
- func = (unsigned long)fh->read;
- return efi_early->call(func, handle, size, addr);
- }
-}
-
-efi_status_t efi_file_close(void *handle)
-{
- if (efi_early->is64) {
- efi_file_handle_64_t *fh = handle;
-
- return efi_early->call((unsigned long)fh->close, handle);
- } else {
- efi_file_handle_32_t *fh = handle;
-
- return efi_early->call((unsigned long)fh->close, handle);
- }
-}
-
static inline efi_status_t __open_volume32(void *__image, void **__fh)
{
efi_file_io_interface_t *io;
@@ -249,30 +102,8 @@
void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
{
- unsigned long output_string;
- size_t offset;
-
- if (efi_early->is64) {
- struct efi_simple_text_output_protocol_64 *out;
- u64 *func;
-
- offset = offsetof(typeof(*out), output_string);
- output_string = efi_early->text_output + offset;
- out = (typeof(out))(unsigned long)efi_early->text_output;
- func = (u64 *)output_string;
-
- efi_early->call(*func, out, str);
- } else {
- struct efi_simple_text_output_protocol_32 *out;
- u32 *func;
-
- offset = offsetof(typeof(*out), output_string);
- output_string = efi_early->text_output + offset;
- out = (typeof(out))(unsigned long)efi_early->text_output;
- func = (u32 *)output_string;
-
- efi_early->call(*func, out, str);
- }
+ efi_call_proto(efi_simple_text_output_protocol, output_string,
+ efi_early->text_output, str);
}
static efi_status_t
@@ -1157,6 +988,13 @@
else
setup_boot_services32(efi_early);
+ /*
+ * If the boot loader gave us a value for secure_boot then we use that,
+ * otherwise we ask the BIOS.
+ */
+ if (boot_params->secure_boot == efi_secureboot_mode_unset)
+ boot_params->secure_boot = efi_get_secureboot(sys_table);
+
setup_graphics(boot_params);
setup_efi_pci(boot_params);
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index fd0b6a2..d85b962 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -82,7 +82,7 @@
/* Relocate efi_config->call() */
leal efi32_config(%esi), %eax
- add %esi, 32(%eax)
+ add %esi, 40(%eax)
pushl %eax
call make_boot_params
@@ -108,7 +108,7 @@
/* Relocate efi_config->call() */
leal efi32_config(%esi), %eax
- add %esi, 32(%eax)
+ add %esi, 40(%eax)
pushl %eax
2:
call efi_main
@@ -264,7 +264,7 @@
#ifdef CONFIG_EFI_STUB
.data
efi32_config:
- .fill 4,8,0
+ .fill 5,8,0
.long efi_call_phys
.long 0
.byte 0
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 4d85e60..d2ae1f8 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -264,7 +264,7 @@
/*
* Relocate efi_config->call().
*/
- addq %rbp, efi64_config+32(%rip)
+ addq %rbp, efi64_config+40(%rip)
movq %rax, %rdi
call make_boot_params
@@ -284,7 +284,7 @@
* Relocate efi_config->call().
*/
movq efi_config(%rip), %rax
- addq %rbp, 32(%rax)
+ addq %rbp, 40(%rax)
2:
movq efi_config(%rip), %rdi
call efi_main
@@ -456,14 +456,14 @@
#ifdef CONFIG_EFI_MIXED
.global efi32_config
efi32_config:
- .fill 4,8,0
+ .fill 5,8,0
.quad efi64_thunk
.byte 0
#endif
.global efi64_config
efi64_config:
- .fill 4,8,0
+ .fill 5,8,0
.quad efi_call
.byte 1
#endif /* CONFIG_EFI_STUB */
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index cc3bd58..9e240fc 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -14,6 +14,7 @@
#include <linux/types.h>
#include "ctype.h"
+#include "string.h"
int memcmp(const void *s1, const void *s2, size_t len)
{
diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h
index 725e820..113588d 100644
--- a/arch/x86/boot/string.h
+++ b/arch/x86/boot/string.h
@@ -18,4 +18,13 @@
#define memset(d,c,l) __builtin_memset(d,c,l)
#define memcmp __builtin_memcmp
+extern int strcmp(const char *str1, const char *str2);
+extern int strncmp(const char *cs, const char *ct, size_t count);
+extern size_t strlen(const char *s);
+extern char *strstr(const char *s1, const char *s2);
+extern size_t strnlen(const char *s, size_t maxlen);
+extern unsigned int atou(const char *s);
+extern unsigned long long simple_strtoull(const char *cp, char **endp,
+ unsigned int base);
+
#endif /* BOOT_STRING_H */
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 6ef688a..7ff1b0c 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1085,9 +1085,9 @@
aesni_simd_skciphers[i]; i++)
simd_skcipher_free(aesni_simd_skciphers[i]);
- for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2) &&
- aesni_simd_skciphers2[i].simd; i++)
- simd_skcipher_free(aesni_simd_skciphers2[i].simd);
+ for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++)
+ if (aesni_simd_skciphers2[i].simd)
+ simd_skcipher_free(aesni_simd_skciphers2[i].simd);
}
static int __init aesni_init(void)
@@ -1168,7 +1168,7 @@
simd = simd_skcipher_create_compat(algname, drvname, basename);
err = PTR_ERR(simd);
if (IS_ERR(simd))
- goto unregister_simds;
+ continue;
aesni_simd_skciphers2[i].simd = simd;
}
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 701d29f..57f7ec3 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -255,23 +255,6 @@
END(__switch_to_asm)
/*
- * The unwinder expects the last frame on the stack to always be at the same
- * offset from the end of the page, which allows it to validate the stack.
- * Calling schedule_tail() directly would break that convention because its an
- * asmlinkage function so its argument has to be pushed on the stack. This
- * wrapper creates a proper "end of stack" frame header before the call.
- */
-ENTRY(schedule_tail_wrapper)
- FRAME_BEGIN
-
- pushl %eax
- call schedule_tail
- popl %eax
-
- FRAME_END
- ret
-ENDPROC(schedule_tail_wrapper)
-/*
* A newly forked process directly context switches into this address.
*
* eax: prev task we switched from
@@ -279,15 +262,24 @@
* edi: kernel thread arg
*/
ENTRY(ret_from_fork)
- call schedule_tail_wrapper
+ FRAME_BEGIN /* help unwinder find end of stack */
+
+ /*
+ * schedule_tail() is asmlinkage so we have to put its 'prev' argument
+ * on the stack.
+ */
+ pushl %eax
+ call schedule_tail
+ popl %eax
testl %ebx, %ebx
jnz 1f /* kernel threads are uncommon */
2:
/* When we fork, we trace the syscall return in the child, too. */
- movl %esp, %eax
+ leal FRAME_OFFSET(%esp), %eax
call syscall_return_slowpath
+ FRAME_END
jmp restore_all
/* kernel thread */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 5b21970..044d18e 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -36,6 +36,7 @@
#include <asm/smap.h>
#include <asm/pgtable_types.h>
#include <asm/export.h>
+#include <asm/frame.h>
#include <linux/err.h>
.code64
@@ -408,17 +409,19 @@
* r12: kernel thread arg
*/
ENTRY(ret_from_fork)
+ FRAME_BEGIN /* help unwinder find end of stack */
movq %rax, %rdi
- call schedule_tail /* rdi: 'prev' task parameter */
+ call schedule_tail /* rdi: 'prev' task parameter */
- testq %rbx, %rbx /* from kernel_thread? */
- jnz 1f /* kernel threads are uncommon */
+ testq %rbx, %rbx /* from kernel_thread? */
+ jnz 1f /* kernel threads are uncommon */
2:
- movq %rsp, %rdi
+ leaq FRAME_OFFSET(%rsp),%rdi /* pt_regs pointer */
call syscall_return_slowpath /* returns with IRQs disabled */
TRACE_IRQS_ON /* user mode is traced as IRQS on */
SWAPGS
+ FRAME_END
jmp restore_regs_and_iret
1:
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 1d392c3..b8ccdb5 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,11 +1,4 @@
-obj-y += core.o
-
-obj-$(CONFIG_CPU_SUP_AMD) += amd/core.o amd/uncore.o
-obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += amd/power.o
-obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o
-ifdef CONFIG_AMD_IOMMU
-obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o
-endif
-
-obj-$(CONFIG_CPU_SUP_INTEL) += msr.o
+obj-y += core.o
+obj-y += amd/
+obj-$(CONFIG_X86_LOCAL_APIC) += msr.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel/
diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile
new file mode 100644
index 0000000..b1da46f
--- /dev/null
+++ b/arch/x86/events/amd/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o
+obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o
+obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o
+ifdef CONFIG_AMD_IOMMU
+obj-$(CONFIG_CPU_SUP_AMD) += iommu.o
+endif
+
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 05612a2..496e603 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1010,7 +1010,7 @@
* all online cpus.
*/
cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
- "perf/x86/amd/ibs:STARTING",
+ "perf/x86/amd/ibs:starting",
x86_pmu_amd_ibs_starting_cpu,
x86_pmu_amd_ibs_dying_cpu);
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index a0b1bdb..4d1f7f2d 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -22,13 +22,17 @@
#define NUM_COUNTERS_NB 4
#define NUM_COUNTERS_L2 4
-#define MAX_COUNTERS NUM_COUNTERS_NB
+#define NUM_COUNTERS_L3 6
+#define MAX_COUNTERS 6
#define RDPMC_BASE_NB 6
-#define RDPMC_BASE_L2 10
+#define RDPMC_BASE_LLC 10
#define COUNTER_SHIFT 16
+static int num_counters_llc;
+static int num_counters_nb;
+
static HLIST_HEAD(uncore_unused_list);
struct amd_uncore {
@@ -45,30 +49,30 @@
};
static struct amd_uncore * __percpu *amd_uncore_nb;
-static struct amd_uncore * __percpu *amd_uncore_l2;
+static struct amd_uncore * __percpu *amd_uncore_llc;
static struct pmu amd_nb_pmu;
-static struct pmu amd_l2_pmu;
+static struct pmu amd_llc_pmu;
static cpumask_t amd_nb_active_mask;
-static cpumask_t amd_l2_active_mask;
+static cpumask_t amd_llc_active_mask;
static bool is_nb_event(struct perf_event *event)
{
return event->pmu->type == amd_nb_pmu.type;
}
-static bool is_l2_event(struct perf_event *event)
+static bool is_llc_event(struct perf_event *event)
{
- return event->pmu->type == amd_l2_pmu.type;
+ return event->pmu->type == amd_llc_pmu.type;
}
static struct amd_uncore *event_to_amd_uncore(struct perf_event *event)
{
if (is_nb_event(event) && amd_uncore_nb)
return *per_cpu_ptr(amd_uncore_nb, event->cpu);
- else if (is_l2_event(event) && amd_uncore_l2)
- return *per_cpu_ptr(amd_uncore_l2, event->cpu);
+ else if (is_llc_event(event) && amd_uncore_llc)
+ return *per_cpu_ptr(amd_uncore_llc, event->cpu);
return NULL;
}
@@ -183,16 +187,16 @@
return -ENOENT;
/*
- * NB and L2 counters (MSRs) are shared across all cores that share the
- * same NB / L2 cache. Interrupts can be directed to a single target
- * core, however, event counts generated by processes running on other
- * cores cannot be masked out. So we do not support sampling and
- * per-thread events.
+ * NB and Last level cache counters (MSRs) are shared across all cores
+ * that share the same NB / Last level cache. Interrupts can be directed
+ * to a single target core, however, event counts generated by processes
+ * running on other cores cannot be masked out. So we do not support
+ * sampling and per-thread events.
*/
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EINVAL;
- /* NB and L2 counters do not have usr/os/guest/host bits */
+ /* NB and Last level cache counters do not have usr/os/guest/host bits */
if (event->attr.exclude_user || event->attr.exclude_kernel ||
event->attr.exclude_host || event->attr.exclude_guest)
return -EINVAL;
@@ -226,8 +230,8 @@
if (pmu->type == amd_nb_pmu.type)
active_mask = &amd_nb_active_mask;
- else if (pmu->type == amd_l2_pmu.type)
- active_mask = &amd_l2_active_mask;
+ else if (pmu->type == amd_llc_pmu.type)
+ active_mask = &amd_llc_active_mask;
else
return 0;
@@ -244,30 +248,47 @@
.attrs = amd_uncore_attrs,
};
-PMU_FORMAT_ATTR(event, "config:0-7,32-35");
-PMU_FORMAT_ATTR(umask, "config:8-15");
+/*
+ * Similar to PMU_FORMAT_ATTR but allowing for format_attr to be assigned based
+ * on family
+ */
+#define AMD_FORMAT_ATTR(_dev, _name, _format) \
+static ssize_t \
+_dev##_show##_name(struct device *dev, \
+ struct device_attribute *attr, \
+ char *page) \
+{ \
+ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
+ return sprintf(page, _format "\n"); \
+} \
+static struct device_attribute format_attr_##_dev##_name = __ATTR_RO(_dev);
-static struct attribute *amd_uncore_format_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- NULL,
+/* Used for each uncore counter type */
+#define AMD_ATTRIBUTE(_name) \
+static struct attribute *amd_uncore_format_attr_##_name[] = { \
+ &format_attr_event_##_name.attr, \
+ &format_attr_umask.attr, \
+ NULL, \
+}; \
+static struct attribute_group amd_uncore_format_group_##_name = { \
+ .name = "format", \
+ .attrs = amd_uncore_format_attr_##_name, \
+}; \
+static const struct attribute_group *amd_uncore_attr_groups_##_name[] = { \
+ &amd_uncore_attr_group, \
+ &amd_uncore_format_group_##_name, \
+ NULL, \
};
-static struct attribute_group amd_uncore_format_group = {
- .name = "format",
- .attrs = amd_uncore_format_attr,
-};
-
-static const struct attribute_group *amd_uncore_attr_groups[] = {
- &amd_uncore_attr_group,
- &amd_uncore_format_group,
- NULL,
-};
+AMD_FORMAT_ATTR(event, , "config:0-7,32-35");
+AMD_FORMAT_ATTR(umask, , "config:8-15");
+AMD_FORMAT_ATTR(event, _df, "config:0-7,32-35,59-60");
+AMD_FORMAT_ATTR(event, _l3, "config:0-7");
+AMD_ATTRIBUTE(df);
+AMD_ATTRIBUTE(l3);
static struct pmu amd_nb_pmu = {
.task_ctx_nr = perf_invalid_context,
- .attr_groups = amd_uncore_attr_groups,
- .name = "amd_nb",
.event_init = amd_uncore_event_init,
.add = amd_uncore_add,
.del = amd_uncore_del,
@@ -276,10 +297,8 @@
.read = amd_uncore_read,
};
-static struct pmu amd_l2_pmu = {
+static struct pmu amd_llc_pmu = {
.task_ctx_nr = perf_invalid_context,
- .attr_groups = amd_uncore_attr_groups,
- .name = "amd_l2",
.event_init = amd_uncore_event_init,
.add = amd_uncore_add,
.del = amd_uncore_del,
@@ -296,14 +315,14 @@
static int amd_uncore_cpu_up_prepare(unsigned int cpu)
{
- struct amd_uncore *uncore_nb = NULL, *uncore_l2;
+ struct amd_uncore *uncore_nb = NULL, *uncore_llc;
if (amd_uncore_nb) {
uncore_nb = amd_uncore_alloc(cpu);
if (!uncore_nb)
goto fail;
uncore_nb->cpu = cpu;
- uncore_nb->num_counters = NUM_COUNTERS_NB;
+ uncore_nb->num_counters = num_counters_nb;
uncore_nb->rdpmc_base = RDPMC_BASE_NB;
uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
uncore_nb->active_mask = &amd_nb_active_mask;
@@ -312,18 +331,18 @@
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
}
- if (amd_uncore_l2) {
- uncore_l2 = amd_uncore_alloc(cpu);
- if (!uncore_l2)
+ if (amd_uncore_llc) {
+ uncore_llc = amd_uncore_alloc(cpu);
+ if (!uncore_llc)
goto fail;
- uncore_l2->cpu = cpu;
- uncore_l2->num_counters = NUM_COUNTERS_L2;
- uncore_l2->rdpmc_base = RDPMC_BASE_L2;
- uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
- uncore_l2->active_mask = &amd_l2_active_mask;
- uncore_l2->pmu = &amd_l2_pmu;
- uncore_l2->id = -1;
- *per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
+ uncore_llc->cpu = cpu;
+ uncore_llc->num_counters = num_counters_llc;
+ uncore_llc->rdpmc_base = RDPMC_BASE_LLC;
+ uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL;
+ uncore_llc->active_mask = &amd_llc_active_mask;
+ uncore_llc->pmu = &amd_llc_pmu;
+ uncore_llc->id = -1;
+ *per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc;
}
return 0;
@@ -376,17 +395,17 @@
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
}
- if (amd_uncore_l2) {
+ if (amd_uncore_llc) {
unsigned int apicid = cpu_data(cpu).apicid;
unsigned int nshared;
- uncore = *per_cpu_ptr(amd_uncore_l2, cpu);
+ uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx);
nshared = ((eax >> 14) & 0xfff) + 1;
uncore->id = apicid - (apicid % nshared);
- uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2);
- *per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+ uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
+ *per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
}
return 0;
@@ -419,8 +438,8 @@
if (amd_uncore_nb)
uncore_online(cpu, amd_uncore_nb);
- if (amd_uncore_l2)
- uncore_online(cpu, amd_uncore_l2);
+ if (amd_uncore_llc)
+ uncore_online(cpu, amd_uncore_llc);
return 0;
}
@@ -456,8 +475,8 @@
if (amd_uncore_nb)
uncore_down_prepare(cpu, amd_uncore_nb);
- if (amd_uncore_l2)
- uncore_down_prepare(cpu, amd_uncore_l2);
+ if (amd_uncore_llc)
+ uncore_down_prepare(cpu, amd_uncore_llc);
return 0;
}
@@ -479,8 +498,8 @@
if (amd_uncore_nb)
uncore_dead(cpu, amd_uncore_nb);
- if (amd_uncore_l2)
- uncore_dead(cpu, amd_uncore_l2);
+ if (amd_uncore_llc)
+ uncore_dead(cpu, amd_uncore_llc);
return 0;
}
@@ -492,6 +511,47 @@
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
goto fail_nodev;
+ switch(boot_cpu_data.x86) {
+ case 23:
+ /* Family 17h: */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L3;
+ /*
+ * For Family17h, the NorthBridge counters are
+ * re-purposed as Data Fabric counters. Also, support is
+ * added for L3 counters. The pmus are exported based on
+ * family as either L2 or L3 and NB or DF.
+ */
+ amd_nb_pmu.name = "amd_df";
+ amd_llc_pmu.name = "amd_l3";
+ format_attr_event_df.show = &event_show_df;
+ format_attr_event_l3.show = &event_show_l3;
+ break;
+ case 22:
+ /* Family 16h - may change: */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L2;
+ amd_nb_pmu.name = "amd_nb";
+ amd_llc_pmu.name = "amd_l2";
+ format_attr_event_df = format_attr_event;
+ format_attr_event_l3 = format_attr_event;
+ break;
+ default:
+ /*
+ * All prior families have the same number of
+ * NorthBridge and Last Level Cache counters
+ */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L2;
+ amd_nb_pmu.name = "amd_nb";
+ amd_llc_pmu.name = "amd_l2";
+ format_attr_event_df = format_attr_event;
+ format_attr_event_l3 = format_attr_event;
+ break;
+ }
+ amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
+ amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3;
+
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
goto fail_nodev;
@@ -510,16 +570,16 @@
}
if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) {
- amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
- if (!amd_uncore_l2) {
+ amd_uncore_llc = alloc_percpu(struct amd_uncore *);
+ if (!amd_uncore_llc) {
ret = -ENOMEM;
- goto fail_l2;
+ goto fail_llc;
}
- ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+ ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1);
if (ret)
- goto fail_l2;
+ goto fail_llc;
- pr_info("perf: AMD L2I counters detected\n");
+ pr_info("perf: AMD LLC counters detected\n");
ret = 0;
}
@@ -529,7 +589,7 @@
if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
"perf/x86/amd/uncore:prepare",
amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
- goto fail_l2;
+ goto fail_llc;
if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
"perf/x86/amd/uncore:starting",
@@ -546,11 +606,11 @@
cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
fail_prep:
cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
-fail_l2:
+fail_llc:
if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
perf_pmu_unregister(&amd_nb_pmu);
- if (amd_uncore_l2)
- free_percpu(amd_uncore_l2);
+ if (amd_uncore_llc)
+ free_percpu(amd_uncore_llc);
fail_nb:
if (amd_uncore_nb)
free_percpu(amd_uncore_nb);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 019c588..1635c0c 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -505,6 +505,10 @@
if (event->attr.precise_ip > precise)
return -EOPNOTSUPP;
+
+ /* There's no sense in having PEBS for non sampling events: */
+ if (!is_sampling_event(event))
+ return -EINVAL;
}
/*
* check that PEBS LBR correction does not conflict with
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8613826..eb1484c 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3176,13 +3176,16 @@
if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
for_each_cpu(i, topology_sibling_cpumask(cpu)) {
+ struct cpu_hw_events *sibling;
struct intel_excl_cntrs *c;
- c = per_cpu(cpu_hw_events, i).excl_cntrs;
+ sibling = &per_cpu(cpu_hw_events, i);
+ c = sibling->excl_cntrs;
if (c && c->core_id == core_id) {
cpuc->kfree_on_online[1] = cpuc->excl_cntrs;
cpuc->excl_cntrs = c;
- cpuc->excl_thread_id = 1;
+ if (!sibling->excl_thread_id)
+ cpuc->excl_thread_id = 1;
break;
}
}
@@ -3987,7 +3990,7 @@
x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC;
}
- x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+ x86_pmu.intel_ctrl = (1ULL << x86_pmu.num_counters) - 1;
if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) {
WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index fec8a461..aff4b5b 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -434,6 +434,7 @@
.stop = cstate_pmu_event_stop,
.read = cstate_pmu_event_update,
.capabilities = PERF_PMU_CAP_NO_INTERRUPT,
+ .module = THIS_MODULE,
};
static struct pmu cstate_pkg_pmu = {
@@ -447,6 +448,7 @@
.stop = cstate_pmu_event_stop,
.read = cstate_pmu_event_update,
.capabilities = PERF_PMU_CAP_NO_INTERRUPT,
+ .module = THIS_MODULE,
};
static const struct cstate_model nhm_cstates __initconst = {
@@ -539,6 +541,9 @@
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
{ },
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index be20239..9dfeeec 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1389,9 +1389,13 @@
continue;
/* log dropped samples number */
- if (error[bit])
+ if (error[bit]) {
perf_log_lost_samples(event, error[bit]);
+ if (perf_event_account_interrupt(event))
+ x86_pmu_stop(event, 0);
+ }
+
if (counts[bit]) {
__intel_pmu_pebs_event(event, iregs, base,
top, bit, counts[bit]);
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 1c1b9fe..5900471 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -99,18 +99,24 @@
};
PMU_FORMAT_ATTR(cyc, "config:1" );
+PMU_FORMAT_ATTR(pwr_evt, "config:4" );
+PMU_FORMAT_ATTR(fup_on_ptw, "config:5" );
PMU_FORMAT_ATTR(mtc, "config:9" );
PMU_FORMAT_ATTR(tsc, "config:10" );
PMU_FORMAT_ATTR(noretcomp, "config:11" );
+PMU_FORMAT_ATTR(ptw, "config:12" );
PMU_FORMAT_ATTR(mtc_period, "config:14-17" );
PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" );
PMU_FORMAT_ATTR(psb_period, "config:24-27" );
static struct attribute *pt_formats_attr[] = {
&format_attr_cyc.attr,
+ &format_attr_pwr_evt.attr,
+ &format_attr_fup_on_ptw.attr,
&format_attr_mtc.attr,
&format_attr_tsc.attr,
&format_attr_noretcomp.attr,
+ &format_attr_ptw.attr,
&format_attr_mtc_period.attr,
&format_attr_cyc_thresh.attr,
&format_attr_psb_period.attr,
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index bd34124..22054ca 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -161,7 +161,13 @@
static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
{
- return rapl_pmus->pmus[topology_logical_package_id(cpu)];
+ unsigned int pkgid = topology_logical_package_id(cpu);
+
+ /*
+ * The unsigned check also catches the '-1' return value for non
+ * existent mappings in the topology map.
+ */
+ return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
}
static inline u64 rapl_read_counter(struct perf_event *event)
@@ -402,6 +408,8 @@
/* must be done before validate_group */
pmu = cpu_to_rapl_pmu(event->cpu);
+ if (!pmu)
+ return -EINVAL;
event->cpu = pmu->cpu;
event->pmu_private = pmu;
event->hw.event_base = msr;
@@ -585,6 +593,20 @@
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
int target;
+ if (!pmu) {
+ pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+ if (!pmu)
+ return -ENOMEM;
+
+ raw_spin_lock_init(&pmu->lock);
+ INIT_LIST_HEAD(&pmu->active_list);
+ pmu->pmu = &rapl_pmus->pmu;
+ pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+ rapl_hrtimer_init(pmu);
+
+ rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+ }
+
/*
* Check if there is an online cpu in the package which collects rapl
* events already.
@@ -598,27 +620,6 @@
return 0;
}
-static int rapl_cpu_prepare(unsigned int cpu)
-{
- struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-
- if (pmu)
- return 0;
-
- pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
- if (!pmu)
- return -ENOMEM;
-
- raw_spin_lock_init(&pmu->lock);
- INIT_LIST_HEAD(&pmu->active_list);
- pmu->pmu = &rapl_pmus->pmu;
- pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
- pmu->cpu = -1;
- rapl_hrtimer_init(pmu);
- rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
- return 0;
-}
-
static int rapl_check_hw_unit(bool apply_quirk)
{
u64 msr_rapl_power_unit_bits;
@@ -697,6 +698,7 @@
rapl_pmus->pmu.start = rapl_pmu_event_start;
rapl_pmus->pmu.stop = rapl_pmu_event_stop;
rapl_pmus->pmu.read = rapl_pmu_event_read;
+ rapl_pmus->pmu.module = THIS_MODULE;
return 0;
}
@@ -769,6 +771,9 @@
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
+
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
{},
};
@@ -802,29 +807,21 @@
/*
* Install callbacks. Core will call them for each online cpu.
*/
-
- ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
- rapl_cpu_prepare, NULL);
- if (ret)
- goto out;
-
ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
"perf/x86/rapl:online",
rapl_cpu_online, rapl_cpu_offline);
if (ret)
- goto out1;
+ goto out;
ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
if (ret)
- goto out2;
+ goto out1;
rapl_advertise();
return 0;
-out2:
- cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
out1:
- cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
out:
pr_warn("Initialization failed (%d), disabled\n", ret);
cleanup_rapl_pmus();
@@ -835,7 +832,6 @@
static void __exit intel_rapl_exit(void)
{
cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
- cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
perf_pmu_unregister(&rapl_pmus->pmu);
cleanup_rapl_pmus();
}
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 97c246f..758c1aa 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -100,7 +100,13 @@
struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
{
- return pmu->boxes[topology_logical_package_id(cpu)];
+ unsigned int pkgid = topology_logical_package_id(cpu);
+
+ /*
+ * The unsigned check also catches the '-1' return value for non
+ * existent mappings in the topology map.
+ */
+ return pkgid < max_packages ? pmu->boxes[pkgid] : NULL;
}
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -733,6 +739,7 @@
.start = uncore_pmu_event_start,
.stop = uncore_pmu_event_stop,
.read = uncore_pmu_event_read,
+ .module = THIS_MODULE,
};
} else {
pmu->pmu = *pmu->type->pmu;
@@ -763,30 +770,6 @@
pmu->registered = false;
}
-static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu)
-{
- struct intel_uncore_pmu *pmu = type->pmus;
- struct intel_uncore_box *box;
- int i, pkg;
-
- if (pmu) {
- pkg = topology_physical_package_id(cpu);
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
- if (box)
- uncore_box_exit(box);
- }
- }
-}
-
-static void uncore_exit_boxes(void *dummy)
-{
- struct intel_uncore_type **types;
-
- for (types = uncore_msr_uncores; *types; types++)
- __uncore_exit_boxes(*types++, smp_processor_id());
-}
-
static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
{
int pkg;
@@ -1057,86 +1040,6 @@
}
}
-static int uncore_cpu_dying(unsigned int cpu)
-{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
- struct intel_uncore_pmu *pmu;
- struct intel_uncore_box *box;
- int i, pkg;
-
- pkg = topology_logical_package_id(cpu);
- for (; *types; types++) {
- type = *types;
- pmu = type->pmus;
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
- if (box && atomic_dec_return(&box->refcnt) == 0)
- uncore_box_exit(box);
- }
- }
- return 0;
-}
-
-static int first_init;
-
-static int uncore_cpu_starting(unsigned int cpu)
-{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
- struct intel_uncore_pmu *pmu;
- struct intel_uncore_box *box;
- int i, pkg, ncpus = 1;
-
- if (first_init) {
- /*
- * On init we get the number of online cpus in the package
- * and set refcount for all of them.
- */
- ncpus = cpumask_weight(topology_core_cpumask(cpu));
- }
-
- pkg = topology_logical_package_id(cpu);
- for (; *types; types++) {
- type = *types;
- pmu = type->pmus;
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
- if (!box)
- continue;
- /* The first cpu on a package activates the box */
- if (atomic_add_return(ncpus, &box->refcnt) == ncpus)
- uncore_box_init(box);
- }
- }
-
- return 0;
-}
-
-static int uncore_cpu_prepare(unsigned int cpu)
-{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
- struct intel_uncore_pmu *pmu;
- struct intel_uncore_box *box;
- int i, pkg;
-
- pkg = topology_logical_package_id(cpu);
- for (; *types; types++) {
- type = *types;
- pmu = type->pmus;
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- if (pmu->boxes[pkg])
- continue;
- /* First cpu of a package allocates the box */
- box = uncore_alloc_box(type, cpu_to_node(cpu));
- if (!box)
- return -ENOMEM;
- box->pmu = pmu;
- box->pkgid = pkg;
- pmu->boxes[pkg] = box;
- }
- }
- return 0;
-}
-
static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
int new_cpu)
{
@@ -1176,12 +1079,14 @@
static int uncore_event_cpu_offline(unsigned int cpu)
{
- int target;
+ struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, pkg, target;
/* Check if exiting cpu is used for collecting uncore events */
if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
- return 0;
-
+ goto unref;
/* Find a new cpu to collect uncore events */
target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
@@ -1193,12 +1098,82 @@
uncore_change_context(uncore_msr_uncores, cpu, target);
uncore_change_context(uncore_pci_uncores, cpu, target);
+
+unref:
+ /* Clear the references */
+ pkg = topology_logical_package_id(cpu);
+ for (; *types; types++) {
+ type = *types;
+ pmu = type->pmus;
+ for (i = 0; i < type->num_boxes; i++, pmu++) {
+ box = pmu->boxes[pkg];
+ if (box && atomic_dec_return(&box->refcnt) == 0)
+ uncore_box_exit(box);
+ }
+ }
return 0;
}
+static int allocate_boxes(struct intel_uncore_type **types,
+ unsigned int pkg, unsigned int cpu)
+{
+ struct intel_uncore_box *box, *tmp;
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ LIST_HEAD(allocated);
+ int i;
+
+ /* Try to allocate all required boxes */
+ for (; *types; types++) {
+ type = *types;
+ pmu = type->pmus;
+ for (i = 0; i < type->num_boxes; i++, pmu++) {
+ if (pmu->boxes[pkg])
+ continue;
+ box = uncore_alloc_box(type, cpu_to_node(cpu));
+ if (!box)
+ goto cleanup;
+ box->pmu = pmu;
+ box->pkgid = pkg;
+ list_add(&box->active_list, &allocated);
+ }
+ }
+ /* Install them in the pmus */
+ list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+ list_del_init(&box->active_list);
+ box->pmu->boxes[pkg] = box;
+ }
+ return 0;
+
+cleanup:
+ list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+ list_del_init(&box->active_list);
+ kfree(box);
+ }
+ return -ENOMEM;
+}
+
static int uncore_event_cpu_online(unsigned int cpu)
{
- int target;
+ struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, ret, pkg, target;
+
+ pkg = topology_logical_package_id(cpu);
+ ret = allocate_boxes(types, pkg, cpu);
+ if (ret)
+ return ret;
+
+ for (; *types; types++) {
+ type = *types;
+ pmu = type->pmus;
+ for (i = 0; i < type->num_boxes; i++, pmu++) {
+ box = pmu->boxes[pkg];
+ if (!box && atomic_inc_return(&box->refcnt) == 1)
+ uncore_box_init(box);
+ }
+ }
/*
* Check if there is an online cpu in the package
@@ -1353,6 +1328,8 @@
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
{},
};
@@ -1388,38 +1365,16 @@
if (cret && pret)
return -ENODEV;
- /*
- * Install callbacks. Core will call them for each online cpu.
- *
- * The first online cpu of each package allocates and takes
- * the refcounts for all other online cpus in that package.
- * If msrs are not enabled no allocation is required and
- * uncore_cpu_prepare() is not called for each online cpu.
- */
- if (!cret) {
- ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
- "perf/x86/intel/uncore:prepare",
- uncore_cpu_prepare, NULL);
- if (ret)
- goto err;
- } else {
- cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
- "perf/x86/intel/uncore:prepare",
- uncore_cpu_prepare, NULL);
- }
- first_init = 1;
- cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
- "perf/x86/uncore:starting",
- uncore_cpu_starting, uncore_cpu_dying);
- first_init = 0;
- cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
- "perf/x86/uncore:online",
- uncore_event_cpu_online, uncore_event_cpu_offline);
+ /* Install hotplug callbacks to setup the targets for each package */
+ ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
+ "perf/x86/intel/uncore:online",
+ uncore_event_cpu_online,
+ uncore_event_cpu_offline);
+ if (ret)
+ goto err;
return 0;
err:
- /* Undo box->init_box() */
- on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1);
uncore_types_exit(uncore_msr_uncores);
uncore_pci_exit();
return ret;
@@ -1428,9 +1383,7 @@
static void __exit intel_uncore_exit(void)
{
- cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
- cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING);
- cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP);
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
uncore_types_exit(uncore_msr_uncores);
uncore_pci_exit();
}
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index e6832be..dae2fed 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2686,7 +2686,7 @@
void hswep_uncore_cpu_init(void)
{
- int pkg = topology_phys_to_logical_pkg(0);
+ int pkg = boot_cpu_data.logical_proc_id;
if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 2b892e2..5d6a53f 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -7,7 +7,6 @@
generated-y += xen-hypercalls.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += dma-contiguous.h
generic-y += early_ioremap.h
generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index ced283a..af95c47 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -59,6 +59,17 @@
}
#define div_u64_rem div_u64_rem
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+ u32 high, low;
+
+ asm ("mull %[b]" : "=a" (low), "=d" (high)
+ : [a] "a" (a), [b] "rm" (b) );
+
+ return low | ((u64)high) << 32;
+}
+#define mul_u32_u32 mul_u32_u32
+
#else
# include <asm-generic/div64.h>
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index e99675b..2f77bce 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -191,6 +191,7 @@
struct efi_config {
u64 image_handle;
u64 table;
+ u64 runtime_services;
u64 boot_services;
u64 text_output;
efi_status_t (*call)(unsigned long, ...);
@@ -226,6 +227,10 @@
#define __efi_call_early(f, ...) \
__efi_early()->call((unsigned long)f, __VA_ARGS__);
+#define efi_call_runtime(f, ...) \
+ __efi_early()->call(efi_table_attr(efi_runtime_services, f, \
+ __efi_early()->runtime_services), __VA_ARGS__)
+
extern bool efi_reboot_required(void);
#else
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 34a46dc..8167fdb 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -57,7 +57,7 @@
#define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */
#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */
#define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */
+#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */
#define INTEL_FAM6_ATOM_GOLDMONT 0x5C
#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 5132f2a..e638736 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -97,10 +97,6 @@
#define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */
-/* Software defined banks */
-#define MCE_EXTENDED_BANK 128
-#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0)
-
#define MCE_LOG_LEN 32
#define MCE_LOG_SIGNATURE "MACHINECHECK"
@@ -193,6 +189,15 @@
extern struct mca_config mca_cfg;
extern struct mca_msr_regs msr_ops;
+
+enum mce_notifier_prios {
+ MCE_PRIO_SRAO = INT_MAX,
+ MCE_PRIO_EXTLOG = INT_MAX - 1,
+ MCE_PRIO_NFIT = INT_MAX - 2,
+ MCE_PRIO_EDAC = INT_MAX - 3,
+ MCE_PRIO_LOWEST = 0,
+};
+
extern void mce_register_decode_chain(struct notifier_block *nb);
extern void mce_unregister_decode_chain(struct notifier_block *nb);
@@ -306,8 +311,6 @@
void intel_init_thermal(struct cpuinfo_x86 *c);
-void mce_log_therm_throt_event(__u64 status);
-
/* Interrupt Handler for core thermal thresholds */
extern int (*platform_thermal_notify)(__u64 msr_val);
@@ -362,12 +365,13 @@
unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */
u32 hwid_mcatype; /* (hwid,mcatype) tuple */
u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */
+ u8 count; /* Number of instances. */
};
struct smca_bank {
struct smca_hwid *hwid;
- /* Instance ID */
- u32 id;
+ u32 id; /* Value of MCA_IPID[InstanceId]. */
+ u8 sysfs_id; /* Value used for sysfs name. */
};
extern struct smca_bank smca_banks[MAX_NR_BANKS];
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 38711df..2266f86 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -140,6 +140,7 @@
extern void load_ucode_ap(void);
void reload_early_microcode(void);
extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
+extern bool initrd_gone;
#else
static inline int __init microcode_init(void) { return 0; };
static inline void __init load_ucode_bsp(void) { }
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 195becc..e793fc9 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -52,6 +52,21 @@
#define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
+static inline u32 intel_get_microcode_revision(void)
+{
+ u32 rev, dummy;
+
+ native_wrmsrl(MSR_IA32_UCODE_REV, 0);
+
+ /* As documented in the SDM: Do a CPUID 1 here */
+ native_cpuid_eax(1);
+
+ /* get the current revision from MSR 0x8B */
+ native_rdmsr(MSR_IA32_UCODE_REV, dummy, rev);
+
+ return rev;
+}
+
#ifdef CONFIG_MICROCODE_INTEL
extern void __init load_ucode_intel_bsp(void);
extern void load_ucode_intel_ap(void);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index eaf1005..e6cfe7b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -104,6 +104,7 @@
__u8 x86_phys_bits;
/* CPUID returned core id bits: */
__u8 x86_coreid_bits;
+ __u8 cu_id;
/* Max extended CPUID function supported: */
__u32 extended_cpuid_level;
/* Maximum supported CPUID level, -1=no CPUID: */
@@ -219,6 +220,24 @@
: "memory");
}
+#define native_cpuid_reg(reg) \
+static inline unsigned int native_cpuid_##reg(unsigned int op) \
+{ \
+ unsigned int eax = op, ebx, ecx = 0, edx; \
+ \
+ native_cpuid(&eax, &ebx, &ecx, &edx); \
+ \
+ return reg; \
+}
+
+/*
+ * Native CPUID functions returning a single datum.
+ */
+native_cpuid_reg(eax)
+native_cpuid_reg(ebx)
+native_cpuid_reg(ecx)
+native_cpuid_reg(edx)
+
static inline void load_cr3(pgd_t *pgdir)
{
write_cr3(__pa(pgdir));
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index a3269c8..2e41c50 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -58,7 +58,7 @@
if (task == current)
return __builtin_frame_address(0);
- return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp;
+ return &((struct inactive_task_frame *)task->thread.sp)->bp;
}
#else
static inline unsigned long *
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 5cb436a..fcc5cd3 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -36,7 +36,10 @@
asmlinkage void ret_from_fork(void);
-/* data that is pointed to by thread.sp */
+/*
+ * This is the structure pointed to by thread.sp for an inactive task. The
+ * order of the fields must match the code in __switch_to_asm().
+ */
struct inactive_task_frame {
#ifdef CONFIG_X86_64
unsigned long r15;
@@ -48,6 +51,11 @@
unsigned long di;
#endif
unsigned long bx;
+
+ /*
+ * These two fields must be together. They form a stack frame header,
+ * needed by get_frame_pointer().
+ */
unsigned long bp;
unsigned long ret_addr;
};
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index b10bf31..5138dac 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -135,7 +135,8 @@
__u8 eddbuf_entries; /* 0x1e9 */
__u8 edd_mbr_sig_buf_entries; /* 0x1ea */
__u8 kbd_status; /* 0x1eb */
- __u8 _pad5[3]; /* 0x1ec */
+ __u8 secure_boot; /* 0x1ec */
+ __u8 _pad5[2]; /* 0x1ed */
/*
* The sentinel is set to a nonzero value (0xff) in header.S.
*
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 64422f8..7ff007e 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -35,6 +35,7 @@
#include <linux/bootmem.h>
#include <linux/ioport.h>
#include <linux/pci.h>
+#include <linux/efi-bgrt.h>
#include <asm/irqdomain.h>
#include <asm/pci_x86.h>
@@ -1557,6 +1558,12 @@
return 0;
}
+static int __init acpi_parse_bgrt(struct acpi_table_header *table)
+{
+ efi_bgrt_init(table);
+ return 0;
+}
+
int __init acpi_boot_init(void)
{
/* those are executed after early-quirks are executed */
@@ -1581,6 +1588,8 @@
acpi_process_madt();
acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet);
+ if (IS_ENABLED(CONFIG_ACPI_BGRT))
+ acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
if (!acpi_noirq)
x86_init.pci.init = pci_acpi_init;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 945e512..bd6b8c2 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2115,6 +2115,7 @@
if (idx != -1 && irq_trigger(idx))
unmask_ioapic_irq(irq_get_chip_data(0));
}
+ irq_domain_deactivate_irq(irq_data);
irq_domain_activate_irq(irq_data);
if (timer_irq_works()) {
if (disable_timer_pin_1 > 0)
@@ -2136,6 +2137,7 @@
* legacy devices should be connected to IO APIC #0
*/
replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+ irq_domain_deactivate_irq(irq_data);
irq_domain_activate_irq(irq_data);
legacy_pic->unmask(0);
if (timer_irq_works()) {
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 45d44c173c..4a7080c 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -905,8 +905,8 @@
{
static int use_apm_idle; /* = 0 */
static unsigned int last_jiffies; /* = 0 */
- static unsigned int last_stime; /* = 0 */
- cputime_t stime, utime;
+ static u64 last_stime; /* = 0 */
+ u64 stime, utime;
int apm_idle_done = 0;
unsigned int jiffies_since_last_check = jiffies - last_jiffies;
@@ -919,7 +919,7 @@
} else if (jiffies_since_last_check > idle_period) {
unsigned int idle_percentage;
- idle_percentage = cputime_to_jiffies(stime - last_stime);
+ idle_percentage = nsecs_to_jiffies(stime - last_stime);
idle_percentage *= 100;
idle_percentage /= jiffies_since_last_check;
use_apm_idle = (idle_percentage > idle_threshold);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index c62e015..de827d6 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -81,6 +81,7 @@
BLANK();
OFFSET(BP_scratch, boot_params, scratch);
+ OFFSET(BP_secure_boot, boot_params, secure_boot);
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 71cae73..4e95b2e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -312,12 +312,19 @@
u32 eax, ebx, ecx, edx;
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
- node_id = ecx & 7;
- /* get compute unit information */
- smp_num_siblings = ((ebx >> 8) & 3) + 1;
- c->x86_max_cores /= smp_num_siblings;
- c->cpu_core_id = ebx & 0xff;
+ node_id = ecx & 0xff;
+ smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+
+ if (c->x86 == 0x15)
+ c->cu_id = ebx & 0xff;
+
+ if (c->x86 >= 0x17) {
+ c->cpu_core_id = ebx & 0xff;
+
+ if (smp_num_siblings > 1)
+ c->x86_max_cores /= smp_num_siblings;
+ }
/*
* We may have multiple LLCs if L3 caches exist, so check if we
@@ -548,8 +555,10 @@
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (!check_tsc_unstable())
- set_sched_clock_stable();
+ if (check_tsc_unstable())
+ clear_sched_clock_stable();
+ } else {
+ clear_sched_clock_stable();
}
/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 1661d8e..2c234a6 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -1,5 +1,5 @@
-#include <linux/bitops.h>
-#include <linux/kernel.h>
+
+#include <linux/sched.h>
#include <asm/cpufeature.h>
#include <asm/e820.h>
@@ -104,6 +104,8 @@
#ifdef CONFIG_X86_64
set_cpu_cap(c, X86_FEATURE_SYSENTER32);
#endif
+
+ clear_sched_clock_stable();
}
static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index dc1697c..3bcf6d8 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -83,6 +83,7 @@
strcpy(c->x86_model_id, "386");
}
#endif
+ clear_sched_clock_stable();
}
static const struct cpu_dev default_cpu = {
@@ -1015,6 +1016,7 @@
c->x86_model_id[0] = '\0'; /* Unset */
c->x86_max_cores = 1;
c->x86_coreid_bits = 0;
+ c->cu_id = 0xff;
#ifdef CONFIG_X86_64
c->x86_clflush_size = 64;
c->x86_phys_bits = 36;
@@ -1055,6 +1057,8 @@
*/
if (this_cpu->c_init)
this_cpu->c_init(c);
+ else
+ clear_sched_clock_stable();
/* Disable the PN if appropriate */
squash_the_stupid_serial_number(c);
@@ -1221,7 +1225,7 @@
{
int bit;
- if (get_option(&arg, &bit) && bit < NCAPINTS*32)
+ if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32)
setup_clear_cpu_cap(bit);
else
return 0;
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index bd9dcd6..47416f9 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -9,6 +9,7 @@
#include <asm/pci-direct.h>
#include <asm/tsc.h>
#include <asm/cpufeature.h>
+#include <linux/sched.h>
#include "cpu.h"
@@ -183,6 +184,7 @@
set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
break;
}
+ clear_sched_clock_stable();
}
static void init_cyrix(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fcd484d..026c728 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -14,6 +14,7 @@
#include <asm/bugs.h>
#include <asm/cpu.h>
#include <asm/intel-family.h>
+#include <asm/microcode_intel.h>
#ifdef CONFIG_X86_64
#include <linux/topology.h>
@@ -78,14 +79,8 @@
(c->x86 == 0x6 && c->x86_model >= 0x0e))
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
- if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) {
- unsigned lower_word;
-
- wrmsr(MSR_IA32_UCODE_REV, 0, 0);
- /* Required by the SDM */
- sync_core();
- rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode);
- }
+ if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64))
+ c->microcode = intel_get_microcode_revision();
/*
* Atom erratum AAE44/AAF40/AAG38/AAH41:
@@ -124,8 +119,10 @@
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (!check_tsc_unstable())
- set_sched_clock_stable();
+ if (check_tsc_unstable())
+ clear_sched_clock_stable();
+ } else {
+ clear_sched_clock_stable();
}
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 83f1a98..2eee853 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -52,8 +52,11 @@
if (severity >= GHES_SEV_RECOVERABLE)
m.status |= MCI_STATUS_UC;
- if (severity >= GHES_SEV_PANIC)
+
+ if (severity >= GHES_SEV_PANIC) {
m.status |= MCI_STATUS_PCC;
+ m.tsc = rdtsc();
+ }
m.addr = mem_err->physical_addr;
mce_log(&m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 93d824e..1e5a50c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -72,7 +72,7 @@
return new_head.first;
}
-void mce_gen_pool_process(void)
+void mce_gen_pool_process(struct work_struct *__unused)
{
struct llist_node *head;
struct mce_evt_llist *node, *tmp;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 517619e..99165b2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -152,7 +152,6 @@
if (context == MCJ_CTX_RANDOM)
return;
-#ifdef CONFIG_X86_LOCAL_APIC
if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) {
unsigned long start;
int cpu;
@@ -192,9 +191,7 @@
raise_local();
put_cpu();
put_online_cpus();
- } else
-#endif
- {
+ } else {
preempt_disable();
raise_local();
preempt_enable();
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index cd74a3f..903043e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -31,7 +31,7 @@
struct mce mce;
};
-void mce_gen_pool_process(void);
+void mce_gen_pool_process(struct work_struct *__unused);
bool mce_gen_pool_empty(void);
int mce_gen_pool_add(struct mce *mce);
int mce_gen_pool_init(void);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 00ef432..8e9725c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -128,7 +128,6 @@
{
memset(m, 0, sizeof(struct mce));
m->cpu = m->extcpu = smp_processor_id();
- m->tsc = rdtsc();
/* We hope get_seconds stays lockless */
m->time = get_seconds();
m->cpuvendor = boot_cpu_data.x86_vendor;
@@ -217,9 +216,7 @@
{
atomic_inc(&num_notifiers);
- /* Ensure SRAO notifier has the highest priority in the decode chain. */
- if (nb != &mce_srao_nb && nb->priority == INT_MAX)
- nb->priority -= 1;
+ WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
}
@@ -583,7 +580,7 @@
}
static struct notifier_block mce_srao_nb = {
.notifier_call = srao_decode_notifier,
- .priority = INT_MAX,
+ .priority = MCE_PRIO_SRAO,
};
static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
@@ -609,7 +606,7 @@
static struct notifier_block mce_default_nb = {
.notifier_call = mce_default_notifier,
/* lowest prio, we want it to run last. */
- .priority = 0,
+ .priority = MCE_PRIO_LOWEST,
};
/*
@@ -710,14 +707,8 @@
mce_gather_info(&m, NULL);
- /*
- * m.tsc was set in mce_setup(). Clear it if not requested.
- *
- * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid
- * that dance.
- */
- if (!(flags & MCP_TIMESTAMP))
- m.tsc = 0;
+ if (flags & MCP_TIMESTAMP)
+ m.tsc = rdtsc();
for (i = 0; i < mca_cfg.banks; i++) {
if (!mce_banks[i].ctl || !test_bit(i, *b))
@@ -1156,6 +1147,7 @@
goto out;
mce_gather_info(&m, regs);
+ m.tsc = rdtsc();
final = this_cpu_ptr(&mces_seen);
*final = m;
@@ -1322,41 +1314,6 @@
#endif
/*
- * Action optional processing happens here (picking up
- * from the list of faulting pages that do_machine_check()
- * placed into the genpool).
- */
-static void mce_process_work(struct work_struct *dummy)
-{
- mce_gen_pool_process();
-}
-
-#ifdef CONFIG_X86_MCE_INTEL
-/***
- * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog
- * @cpu: The CPU on which the event occurred.
- * @status: Event status information
- *
- * This function should be called by the thermal interrupt after the
- * event has been processed and the decision was made to log the event
- * further.
- *
- * The status parameter will be saved to the 'status' field of 'struct mce'
- * and historically has been the register value of the
- * MSR_IA32_THERMAL_STATUS (Intel) msr.
- */
-void mce_log_therm_throt_event(__u64 status)
-{
- struct mce m;
-
- mce_setup(&m);
- m.bank = MCE_THERMAL_BANK;
- m.status = status;
- mce_log(&m);
-}
-#endif /* CONFIG_X86_MCE_INTEL */
-
-/*
* Periodic polling timer for "silent" machine check errors. If the
* poller finds an MCE, poll 2x faster. When the poller finds no more
* errors, poll 2x slower (up to check_interval seconds).
@@ -1373,20 +1330,15 @@
static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
-static void __restart_timer(struct timer_list *t, unsigned long interval)
+static void __start_timer(struct timer_list *t, unsigned long interval)
{
unsigned long when = jiffies + interval;
unsigned long flags;
local_irq_save(flags);
- if (timer_pending(t)) {
- if (time_before(when, t->expires))
- mod_timer(t, when);
- } else {
- t->expires = round_jiffies(when);
- add_timer_on(t, smp_processor_id());
- }
+ if (!timer_pending(t) || time_before(when, t->expires))
+ mod_timer(t, round_jiffies(when));
local_irq_restore(flags);
}
@@ -1421,7 +1373,7 @@
done:
__this_cpu_write(mce_next_interval, iv);
- __restart_timer(t, iv);
+ __start_timer(t, iv);
}
/*
@@ -1432,7 +1384,7 @@
struct timer_list *t = this_cpu_ptr(&mce_timer);
unsigned long iv = __this_cpu_read(mce_next_interval);
- __restart_timer(t, interval);
+ __start_timer(t, interval);
if (interval < iv)
__this_cpu_write(mce_next_interval, interval);
@@ -1779,17 +1731,15 @@
}
}
-static void mce_start_timer(unsigned int cpu, struct timer_list *t)
+static void mce_start_timer(struct timer_list *t)
{
unsigned long iv = check_interval * HZ;
if (mca_cfg.ignore_ce || !iv)
return;
- per_cpu(mce_next_interval, cpu) = iv;
-
- t->expires = round_jiffies(jiffies + iv);
- add_timer_on(t, cpu);
+ this_cpu_write(mce_next_interval, iv);
+ __start_timer(t, iv);
}
static void __mcheck_cpu_setup_timer(void)
@@ -1806,7 +1756,7 @@
unsigned int cpu = smp_processor_id();
setup_pinned_timer(t, mce_timer_fn, cpu);
- mce_start_timer(cpu, t);
+ mce_start_timer(t);
}
/* Handle unconfigured int18 (should never happen) */
@@ -2196,7 +2146,7 @@
mce_register_decode_chain(&mce_default_nb);
mcheck_vendor_init_severity();
- INIT_WORK(&mce_work, mce_process_work);
+ INIT_WORK(&mce_work, mce_gen_pool_process);
init_irq_work(&mce_irq_work, mce_irq_work_cb);
return 0;
@@ -2566,7 +2516,7 @@
static int mce_cpu_online(unsigned int cpu)
{
- struct timer_list *t = &per_cpu(mce_timer, cpu);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
int ret;
mce_device_create(cpu);
@@ -2577,13 +2527,13 @@
return ret;
}
mce_reenable_cpu();
- mce_start_timer(cpu, t);
+ mce_start_timer(t);
return 0;
}
static int mce_cpu_pre_down(unsigned int cpu)
{
- struct timer_list *t = &per_cpu(mce_timer, cpu);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
mce_disable_cpu();
del_timer_sync(t);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index a5fd137..9e5427d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -192,6 +192,7 @@
smca_banks[bank].hwid = s_hwid;
smca_banks[bank].id = instance_id;
+ smca_banks[bank].sysfs_id = s_hwid->count++;
break;
}
}
@@ -777,7 +778,8 @@
mce_setup(&m);
m.status = status;
- m.bank = bank;
+ m.bank = bank;
+ m.tsc = rdtsc();
if (threshold_err)
m.misc = misc;
@@ -1064,9 +1066,12 @@
return NULL;
}
+ if (smca_banks[bank].hwid->count == 1)
+ return smca_get_name(bank_type);
+
snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN,
"%s_%x", smca_get_name(bank_type),
- smca_banks[bank].id);
+ smca_banks[bank].sysfs_id);
return buf_mcatype;
}
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 465aca8..85469f8 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -6,7 +6,7 @@
*
* Maintains a counter in /sys that keeps track of the number of thermal
* events, such that the user knows how bad the thermal problem might be
- * (since the logging to syslog and mcelog is rate limited).
+ * (since the logging to syslog is rate limited).
*
* Author: Dmitriy Zavin (dmitriyz@google.com)
*
@@ -141,13 +141,8 @@
* IRQ has been acknowledged.
*
* It will take care of rate limiting and printing messages to the syslog.
- *
- * Returns: 0 : Event should NOT be further logged, i.e. still in
- * "timeout" from previous log message.
- * 1 : Event should be logged further, and a message has been
- * printed to the syslog.
*/
-static int therm_throt_process(bool new_event, int event, int level)
+static void therm_throt_process(bool new_event, int event, int level)
{
struct _thermal_state *state;
unsigned int this_cpu = smp_processor_id();
@@ -162,16 +157,16 @@
else if (event == POWER_LIMIT_EVENT)
state = &pstate->core_power_limit;
else
- return 0;
+ return;
} else if (level == PACKAGE_LEVEL) {
if (event == THERMAL_THROTTLING_EVENT)
state = &pstate->package_throttle;
else if (event == POWER_LIMIT_EVENT)
state = &pstate->package_power_limit;
else
- return 0;
+ return;
} else
- return 0;
+ return;
old_event = state->new_event;
state->new_event = new_event;
@@ -181,7 +176,7 @@
if (time_before64(now, state->next_check) &&
state->count != state->last_count)
- return 0;
+ return;
state->next_check = now + CHECK_INTERVAL;
state->last_count = state->count;
@@ -193,16 +188,14 @@
this_cpu,
level == CORE_LEVEL ? "Core" : "Package",
state->count);
- return 1;
+ return;
}
if (old_event) {
if (event == THERMAL_THROTTLING_EVENT)
pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
level == CORE_LEVEL ? "Core" : "Package");
- return 1;
+ return;
}
-
- return 0;
}
static int thresh_event_valid(int level, int event)
@@ -365,10 +358,9 @@
/* Check for violation of core thermal thresholds*/
notify_thresholds(msr_val);
- if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
- THERMAL_THROTTLING_EVENT,
- CORE_LEVEL) != 0)
- mce_log_therm_throt_event(msr_val);
+ therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
+ THERMAL_THROTTLING_EVENT,
+ CORE_LEVEL);
if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable)
therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 6a31e26..079e817 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -384,8 +384,9 @@
reget:
if (!get_builtin_microcode(&cp, family)) {
#ifdef CONFIG_BLK_DEV_INITRD
- cp = find_cpio_data(ucode_path, (void *)initrd_start,
- initrd_end - initrd_start, NULL);
+ if (!initrd_gone)
+ cp = find_cpio_data(ucode_path, (void *)initrd_start,
+ initrd_end - initrd_start, NULL);
#endif
if (!(cp.data && cp.size)) {
/*
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 2af69d2..73102d9 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -46,6 +46,8 @@
static struct microcode_ops *microcode_ops;
static bool dis_ucode_ldr = true;
+bool initrd_gone;
+
LIST_HEAD(microcode_cache);
/*
@@ -190,21 +192,24 @@
static int __init save_microcode_in_initrd(void)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
+ int ret = -EINVAL;
switch (c->x86_vendor) {
case X86_VENDOR_INTEL:
if (c->x86 >= 6)
- return save_microcode_in_initrd_intel();
+ ret = save_microcode_in_initrd_intel();
break;
case X86_VENDOR_AMD:
if (c->x86 >= 0x10)
- return save_microcode_in_initrd_amd(c->x86);
+ ret = save_microcode_in_initrd_amd(c->x86);
break;
default:
break;
}
- return -EINVAL;
+ initrd_gone = true;
+
+ return ret;
}
struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
@@ -247,9 +252,16 @@
* has the virtual address of the beginning of the initrd. It also
* possibly relocates the ramdisk. In either case, initrd_start contains
* the updated address so use that instead.
+ *
+ * initrd_gone is for the hotplug case where we've thrown out initrd
+ * already.
*/
- if (!use_pa && initrd_start)
- start = initrd_start;
+ if (!use_pa) {
+ if (initrd_gone)
+ return (struct cpio_data){ NULL, 0, "" };
+ if (initrd_start)
+ start = initrd_start;
+ }
return find_cpio_data(path, (void *)start, size, NULL);
#else /* !CONFIG_BLK_DEV_INITRD */
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index b624b54..8325d8a 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -41,7 +41,7 @@
static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
-/* Current microcode patch used in early patching */
+/* Current microcode patch used in early patching on the APs. */
struct microcode_intel *intel_ucode_patch;
static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
@@ -150,7 +150,7 @@
{
struct ucode_patch *p;
- p = kzalloc(size, GFP_KERNEL);
+ p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL);
if (!p)
return ERR_PTR(-ENOMEM);
@@ -368,26 +368,6 @@
return patch;
}
-static void cpuid_1(void)
-{
- /*
- * According to the Intel SDM, Volume 3, 9.11.7:
- *
- * CPUID returns a value in a model specific register in
- * addition to its usual register return values. The
- * semantics of CPUID cause it to deposit an update ID value
- * in the 64-bit model-specific register at address 08BH
- * (IA32_BIOS_SIGN_ID). If no update is present in the
- * processor, the value in the MSR remains unmodified.
- *
- * Use native_cpuid -- this code runs very early and we don't
- * want to mess with paravirt.
- */
- unsigned int eax = 1, ebx, ecx = 0, edx;
-
- native_cpuid(&eax, &ebx, &ecx, &edx);
-}
-
static int collect_cpu_info_early(struct ucode_cpu_info *uci)
{
unsigned int val[2];
@@ -410,15 +390,8 @@
native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
csig.pf = 1 << ((val[1] >> 18) & 7);
}
- native_wrmsrl(MSR_IA32_UCODE_REV, 0);
- /* As documented in the SDM: Do a CPUID 1 here */
- cpuid_1();
-
- /* get the current revision from MSR 0x8B */
- native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
-
- csig.rev = val[1];
+ csig.rev = intel_get_microcode_revision();
uci->cpu_sig = csig;
uci->valid = 1;
@@ -602,7 +575,7 @@
static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
{
struct microcode_intel *mc;
- unsigned int val[2];
+ u32 rev;
mc = uci->mc;
if (!mc)
@@ -610,21 +583,16 @@
/* write microcode via MSR 0x79 */
native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
- native_wrmsrl(MSR_IA32_UCODE_REV, 0);
- /* As documented in the SDM: Do a CPUID 1 here */
- cpuid_1();
-
- /* get the current revision from MSR 0x8B */
- native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
- if (val[1] != mc->hdr.rev)
+ rev = intel_get_microcode_revision();
+ if (rev != mc->hdr.rev)
return -1;
#ifdef CONFIG_X86_64
/* Flush global tlb. This is precaution. */
flush_tlb_early();
#endif
- uci->cpu_sig.rev = val[1];
+ uci->cpu_sig.rev = rev;
if (early)
print_ucode(uci);
@@ -639,12 +607,6 @@
struct ucode_cpu_info uci;
struct cpio_data cp;
- /*
- * AP loading didn't find any microcode patch, no need to save anything.
- */
- if (!intel_ucode_patch || IS_ERR(intel_ucode_patch))
- return 0;
-
if (!load_builtin_intel_microcode(&cp))
cp = find_microcode_in_initrd(ucode_path, false);
@@ -660,7 +622,6 @@
return 0;
}
-
/*
* @res_patch, output: a pointer to the patch we found.
*/
@@ -804,8 +765,8 @@
struct microcode_intel *mc;
struct ucode_cpu_info *uci;
struct cpuinfo_x86 *c;
- unsigned int val[2];
static int prev_rev;
+ u32 rev;
/* We should bind the task to the CPU */
if (WARN_ON(raw_smp_processor_id() != cpu))
@@ -822,33 +783,28 @@
/* write microcode via MSR 0x79 */
wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
- wrmsrl(MSR_IA32_UCODE_REV, 0);
- /* As documented in the SDM: Do a CPUID 1 here */
- cpuid_1();
+ rev = intel_get_microcode_revision();
- /* get the current revision from MSR 0x8B */
- rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
-
- if (val[1] != mc->hdr.rev) {
+ if (rev != mc->hdr.rev) {
pr_err("CPU%d update to revision 0x%x failed\n",
cpu, mc->hdr.rev);
return -1;
}
- if (val[1] != prev_rev) {
+ if (rev != prev_rev) {
pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
- val[1],
+ rev,
mc->hdr.date & 0xffff,
mc->hdr.date >> 24,
(mc->hdr.date >> 16) & 0xff);
- prev_rev = val[1];
+ prev_rev = rev;
}
c = &cpu_data(cpu);
- uci->cpu_sig.rev = val[1];
- c->microcode = val[1];
+ uci->cpu_sig.rev = rev;
+ c->microcode = rev;
return 0;
}
@@ -860,7 +816,7 @@
u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
int new_rev = uci->cpu_sig.rev;
unsigned int leftover = size;
- unsigned int curr_mc_size = 0;
+ unsigned int curr_mc_size = 0, new_mc_size = 0;
unsigned int csig, cpf;
while (leftover) {
@@ -901,6 +857,7 @@
vfree(new_mc);
new_rev = mc_header.rev;
new_mc = mc;
+ new_mc_size = mc_size;
mc = NULL; /* trigger new vmalloc */
}
@@ -926,7 +883,7 @@
* permanent memory. So it will be loaded early when a CPU is hot added
* or resumes.
*/
- save_mc_for_early(new_mc, curr_mc_size);
+ save_mc_for_early(new_mc, new_mc_size);
pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
cpu, new_rev, uci->cpu_sig.rev);
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 3417856..c1ea5b9 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -1,4 +1,5 @@
#include <linux/kernel.h>
+#include <linux/sched.h>
#include <linux/mm.h>
#include <asm/cpufeature.h>
#include <asm/msr.h>
@@ -14,6 +15,8 @@
if (xlvl >= 0x80860001)
c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
}
+
+ clear_sched_clock_stable();
}
static void init_transmeta(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index e4e97a5..de72344 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -9,6 +9,7 @@
#include <asm/fpu/regset.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/types.h>
+#include <asm/fpu/xstate.h>
#include <asm/traps.h>
#include <linux/hardirq.h>
@@ -183,7 +184,8 @@
* it will #GP. Make sure it is replaced after the memset().
*/
if (static_cpu_has(X86_FEATURE_XSAVES))
- state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT;
+ state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT |
+ xfeatures_mask;
if (static_cpu_has(X86_FEATURE_FXSR))
fpstate_init_fxstate(&state->fxsave);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 85e87b4..dc6ba5b 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -352,6 +352,7 @@
} else {
struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+ irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
disable_irq(hdev->irq);
irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index cb9c1ed..f73f475 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -132,10 +132,8 @@
sysctl_sched_itmt_enabled = 1;
- if (sysctl_sched_itmt_enabled) {
- x86_topology_update = true;
- rebuild_sched_domains();
- }
+ x86_topology_update = true;
+ rebuild_sched_domains();
mutex_unlock(&itmt_update_mutex);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index eb35093..520b8df 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -745,7 +745,7 @@
* will be the real return address, and all the rest will
* point to kretprobe_trampoline.
*/
- hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+ hlist_for_each_entry(ri, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2a5cafd..542710b 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -107,12 +107,12 @@
{
if (!stable) {
pv_time_ops.sched_clock = kvm_clock_read;
+ clear_sched_clock_stable();
return;
}
kvm_sched_clock_offset = kvm_clock_read();
pv_time_ops.sched_clock = kvm_sched_clock_read;
- set_sched_clock_stable();
printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
kvm_sched_clock_offset);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4cfba94..69780ed 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1176,6 +1176,20 @@
/* Allocate bigger log buffer */
setup_log_buf(1);
+ if (efi_enabled(EFI_BOOT)) {
+ switch (boot_params.secure_boot) {
+ case efi_secureboot_mode_disabled:
+ pr_info("Secure boot disabled\n");
+ break;
+ case efi_secureboot_mode_enabled:
+ pr_info("Secure boot enabled\n");
+ break;
+ default:
+ pr_info("Secure boot could not be determined\n");
+ break;
+ }
+ }
+
reserve_initrd();
acpi_table_upgrade();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 46732dc..99b920d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -433,9 +433,15 @@
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
if (c->phys_proc_id == o->phys_proc_id &&
- per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
- c->cpu_core_id == o->cpu_core_id)
- return topology_sane(c, o, "smt");
+ per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
+ if (c->cpu_core_id == o->cpu_core_id)
+ return topology_sane(c, o, "smt");
+
+ if ((c->cu_id != 0xff) &&
+ (o->cu_id != 0xff) &&
+ (c->cu_id == o->cu_id))
+ return topology_sane(c, o, "smt");
+ }
} else if (c->phys_proc_id == o->phys_proc_id &&
c->cpu_core_id == o->cpu_core_id) {
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index be3a49e..2724dc8 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -694,6 +694,7 @@
crystal_khz = 24000; /* 24.0 MHz */
break;
case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_FAM6_ATOM_DENVERTON:
crystal_khz = 25000; /* 25.0 MHz */
break;
case INTEL_FAM6_ATOM_GOLDMONT:
@@ -1106,6 +1107,16 @@
return (u64)rdtsc_ordered();
}
+static void tsc_cs_mark_unstable(struct clocksource *cs)
+{
+ if (tsc_unstable)
+ return;
+ tsc_unstable = 1;
+ clear_sched_clock_stable();
+ disable_sched_clock_irqtime();
+ pr_info("Marking TSC unstable due to clocksource watchdog\n");
+}
+
/*
* .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
*/
@@ -1118,6 +1129,7 @@
CLOCK_SOURCE_MUST_VERIFY,
.archdata = { .vclock_mode = VCLOCK_TSC },
.resume = tsc_resume,
+ .mark_unstable = tsc_cs_mark_unstable,
};
void mark_tsc_unstable(char *reason)
@@ -1355,6 +1367,9 @@
(unsigned long)cpu_khz / 1000,
(unsigned long)cpu_khz % 1000);
+ /* Sanitize TSC ADJUST before cyc2ns gets initialized */
+ tsc_store_and_check_tsc_adjust(true);
+
/*
* Secondary CPUs do not run through tsc_init(), so set up
* all the scale factors for all CPUs, assuming the same
@@ -1385,8 +1400,6 @@
if (unsynchronized_tsc())
mark_tsc_unstable("TSCs unsynchronized");
- else
- tsc_store_and_check_tsc_adjust(true);
check_system_tsc_reliable();
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index d0db011..728f753 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -286,13 +286,6 @@
if (unsynchronized_tsc())
return;
- if (tsc_clocksource_reliable) {
- if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING)
- pr_info(
- "Skipped synchronization checks as TSC is reliable.\n");
- return;
- }
-
/*
* Set the maximum number of test runs to
* 1 if the CPU does not provide the TSC_ADJUST MSR
@@ -380,14 +373,19 @@
int cpus = 2;
/* Also aborts if there is no TSC. */
- if (unsynchronized_tsc() || tsc_clocksource_reliable)
+ if (unsynchronized_tsc())
return;
/*
* Store, verify and sanitize the TSC adjust register. If
* successful skip the test.
+ *
+ * The test is also skipped when the TSC is marked reliable. This
+ * is true for SoCs which have no fallback clocksource. On these
+ * SoCs the TSC is frequency synchronized, but still the TSC ADJUST
+ * register might have been wreckaged by the BIOS..
*/
- if (tsc_store_and_check_tsc_adjust(false)) {
+ if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) {
atomic_inc(&skip_test);
return;
}
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 4443e499..23d1556 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -6,6 +6,21 @@
#define FRAME_HEADER_SIZE (sizeof(long) * 2)
+/*
+ * This disables KASAN checking when reading a value from another task's stack,
+ * since the other task could be running on another CPU and could have poisoned
+ * the stack in the meantime.
+ */
+#define READ_ONCE_TASK_STACK(task, x) \
+({ \
+ unsigned long val; \
+ if (task == current) \
+ val = READ_ONCE(x); \
+ else \
+ val = READ_ONCE_NOCHECK(x); \
+ val; \
+})
+
static void unwind_dump(struct unwind_state *state, unsigned long *sp)
{
static bool dumped_before = false;
@@ -48,7 +63,8 @@
if (state->regs && user_mode(state->regs))
return 0;
- addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
+ addr = READ_ONCE_TASK_STACK(state->task, *addr_p);
+ addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr,
addr_p);
return __kernel_text_address(addr) ? addr : 0;
@@ -162,7 +178,7 @@
if (state->regs)
next_bp = (unsigned long *)state->regs->bp;
else
- next_bp = (unsigned long *)*state->bp;
+ next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp);
/* is the next frame pointer an encoded pointer to pt_regs? */
regs = decode_frame_pointer(next_bp);
@@ -207,6 +223,16 @@
return true;
bad_address:
+ /*
+ * When unwinding a non-current task, the task might actually be
+ * running on another CPU, in which case it could be modifying its
+ * stack while we're reading it. This is generally not a problem and
+ * can be ignored as long as the caller understands that unwinding
+ * another task will not always succeed.
+ */
+ if (state->task != current)
+ goto the_end;
+
if (state->regs) {
printk_deferred_once(KERN_WARNING
"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index ec5d754..0442d98 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -160,11 +160,12 @@
static void mark_screen_rdonly(struct mm_struct *mm)
{
+ struct vm_area_struct *vma;
+ spinlock_t *ptl;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
- spinlock_t *ptl;
int i;
down_write(&mm->mmap_sem);
@@ -177,7 +178,7 @@
pmd = pmd_offset(pud, 0xA0000);
if (pmd_trans_huge(*pmd)) {
- struct vm_area_struct *vma = find_vma(mm, 0xA0000);
+ vma = find_vma(mm, 0xA0000);
split_huge_pmd(vma, pmd, 0xA0000);
}
if (pmd_none_or_clear_bad(pmd))
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 56628a4..cedbba0 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -818,6 +818,20 @@
return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception);
}
+static int segmented_write_std(struct x86_emulate_ctxt *ctxt,
+ struct segmented_address addr,
+ void *data,
+ unsigned int size)
+{
+ int rc;
+ ulong linear;
+
+ rc = linearize(ctxt, addr, size, true, &linear);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception);
+}
+
/*
* Prefetch the remaining bytes of the instruction without crossing page
* boundary if they are not in fetch_cache yet.
@@ -1571,7 +1585,6 @@
&ctxt->exception);
}
-/* Does not support long mode */
static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
u16 selector, int seg, u8 cpl,
enum x86_transfer_type transfer,
@@ -1608,20 +1621,34 @@
rpl = selector & 3;
- /* NULL selector is not valid for TR, CS and SS (except for long mode) */
- if ((seg == VCPU_SREG_CS
- || (seg == VCPU_SREG_SS
- && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl))
- || seg == VCPU_SREG_TR)
- && null_selector)
- goto exception;
-
/* TR should be in GDT only */
if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
goto exception;
- if (null_selector) /* for NULL selector skip all following checks */
+ /* NULL selector is not valid for TR, CS and (except for long mode) SS */
+ if (null_selector) {
+ if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR)
+ goto exception;
+
+ if (seg == VCPU_SREG_SS) {
+ if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)
+ goto exception;
+
+ /*
+ * ctxt->ops->set_segment expects the CPL to be in
+ * SS.DPL, so fake an expand-up 32-bit data segment.
+ */
+ seg_desc.type = 3;
+ seg_desc.p = 1;
+ seg_desc.s = 1;
+ seg_desc.dpl = cpl;
+ seg_desc.d = 1;
+ seg_desc.g = 1;
+ }
+
+ /* Skip all following checks */
goto load;
+ }
ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr);
if (ret != X86EMUL_CONTINUE)
@@ -1737,6 +1764,21 @@
u16 selector, int seg)
{
u8 cpl = ctxt->ops->cpl(ctxt);
+
+ /*
+ * None of MOV, POP and LSS can load a NULL selector in CPL=3, but
+ * they can load it at CPL<3 (Intel's manual says only LSS can,
+ * but it's wrong).
+ *
+ * However, the Intel manual says that putting IST=1/DPL=3 in
+ * an interrupt gate will result in SS=3 (the AMD manual instead
+ * says it doesn't), so allow SS=3 in __load_segment_descriptor
+ * and only forbid it here.
+ */
+ if (seg == VCPU_SREG_SS && selector == 3 &&
+ ctxt->mode == X86EMUL_MODE_PROT64)
+ return emulate_exception(ctxt, GP_VECTOR, 0, true);
+
return __load_segment_descriptor(ctxt, selector, seg, cpl,
X86_TRANSFER_NONE, NULL);
}
@@ -3685,8 +3727,8 @@
}
/* Disable writeback. */
ctxt->dst.type = OP_NONE;
- return segmented_write(ctxt, ctxt->dst.addr.mem,
- &desc_ptr, 2 + ctxt->op_bytes);
+ return segmented_write_std(ctxt, ctxt->dst.addr.mem,
+ &desc_ptr, 2 + ctxt->op_bytes);
}
static int em_sgdt(struct x86_emulate_ctxt *ctxt)
@@ -3932,7 +3974,7 @@
else
size = offsetof(struct fxregs_state, xmm_space[0]);
- return segmented_write(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+ return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
}
static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt,
@@ -3974,7 +4016,7 @@
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = segmented_read(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
+ rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
if (rc != X86EMUL_CONTINUE)
return rc;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 1572c35..2ecd7da 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -964,10 +964,11 @@
/* Calculate cpu time spent by current task in 100ns units */
static u64 current_task_runtime_100ns(void)
{
- cputime_t utime, stime;
+ u64 utime, stime;
task_cputime_adjusted(current, &utime, &stime);
- return div_u64(cputime_to_nsecs(utime + stime), 100);
+
+ return div_u64(utime + stime, 100);
}
static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 5fe290c..2f6ef51 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2426,3 +2426,9 @@
jump_label_rate_limit(&apic_hw_disabled, HZ);
jump_label_rate_limit(&apic_sw_disabled, HZ);
}
+
+void kvm_lapic_exit(void)
+{
+ static_key_deferred_flush(&apic_hw_disabled);
+ static_key_deferred_flush(&apic_sw_disabled);
+}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index e0c8023..ff8039d 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -110,6 +110,7 @@
int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
void kvm_lapic_init(void);
+void kvm_lapic_exit(void);
#define VEC_POS(v) ((v) & (32 - 1))
#define REG_POS(v) (((v) >> 5) << 4)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2f22810..e52c908 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3182,6 +3182,7 @@
memcpy(dest, xsave, XSAVE_HDR_OFFSET);
/* Set XSTATE_BV */
+ xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
/*
@@ -3342,6 +3343,8 @@
switch (cap->cap) {
case KVM_CAP_HYPERV_SYNIC:
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return -EINVAL;
return kvm_hv_activate_synic(vcpu);
default:
return -EINVAL;
@@ -6045,6 +6048,7 @@
void kvm_arch_exit(void)
{
+ kvm_lapic_exit();
perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
@@ -6168,7 +6172,8 @@
kvm_x86_ops->patch_hypercall(vcpu, instruction);
- return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
+ return emulator_write_emulated(ctxt, rip, instruction, 3,
+ &ctxt->exception);
}
static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 073d1f1..a8e91ae 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -156,13 +156,13 @@
inline void __const_udelay(unsigned long xloops)
{
+ unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy;
int d0;
xloops *= 4;
asm("mull %%edx"
:"=d" (xloops), "=&a" (d0)
- :"1" (xloops), "0"
- (this_cpu_read(cpu_info.loops_per_jiffy) * (HZ/4)));
+ :"1" (xloops), "0" (lpj * (HZ / 4)));
__delay(++xloops);
}
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ea9c49a..8aa6bea 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -15,6 +15,7 @@
#include <linux/debugfs.h>
#include <linux/mm.h>
#include <linux/init.h>
+#include <linux/sched.h>
#include <linux/seq_file.h>
#include <asm/pgtable.h>
@@ -406,6 +407,7 @@
} else
note_page(m, &st, __pgprot(0), 1);
+ cond_resched();
start++;
}
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 324e571..af59f80 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -293,7 +293,7 @@
* We were not able to extract an address from the instruction,
* probably because there was something invalid in it.
*/
- if (info->si_addr == (void *)-1) {
+ if (info->si_addr == (void __user *)-1) {
err = -EINVAL;
goto err_out;
}
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 3cd6983..3961103 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -114,6 +114,16 @@
DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
},
},
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=42606 */
+ {
+ .callback = set_nouse_crs,
+ .ident = "Supermicro X8DTH",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X8DTH-i/6/iF/6F"),
+ DMI_MATCH(DMI_BIOS_VERSION, "2.0a"),
+ },
+ },
/* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */
{
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 6aad870..04ca876 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -19,8 +19,7 @@
#include <linux/efi.h>
#include <linux/efi-bgrt.h>
-struct acpi_table_bgrt *bgrt_tab;
-void *__initdata bgrt_image;
+struct acpi_table_bgrt bgrt_tab;
size_t __initdata bgrt_image_size;
struct bmp_header {
@@ -28,66 +27,58 @@
u32 size;
} __packed;
-void __init efi_bgrt_init(void)
+void __init efi_bgrt_init(struct acpi_table_header *table)
{
- acpi_status status;
void *image;
struct bmp_header bmp_header;
+ struct acpi_table_bgrt *bgrt = &bgrt_tab;
if (acpi_disabled)
return;
- status = acpi_get_table("BGRT", 0,
- (struct acpi_table_header **)&bgrt_tab);
- if (ACPI_FAILURE(status))
- return;
-
- if (bgrt_tab->header.length < sizeof(*bgrt_tab)) {
+ if (table->length < sizeof(bgrt_tab)) {
pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n",
- bgrt_tab->header.length, sizeof(*bgrt_tab));
+ table->length, sizeof(bgrt_tab));
return;
}
- if (bgrt_tab->version != 1) {
+ *bgrt = *(struct acpi_table_bgrt *)table;
+ if (bgrt->version != 1) {
pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n",
- bgrt_tab->version);
- return;
+ bgrt->version);
+ goto out;
}
- if (bgrt_tab->status & 0xfe) {
+ if (bgrt->status & 0xfe) {
pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n",
- bgrt_tab->status);
- return;
+ bgrt->status);
+ goto out;
}
- if (bgrt_tab->image_type != 0) {
+ if (bgrt->image_type != 0) {
pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n",
- bgrt_tab->image_type);
- return;
+ bgrt->image_type);
+ goto out;
}
- if (!bgrt_tab->image_address) {
+ if (!bgrt->image_address) {
pr_notice("Ignoring BGRT: null image address\n");
- return;
+ goto out;
}
- image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB);
+ image = early_memremap(bgrt->image_address, sizeof(bmp_header));
if (!image) {
pr_notice("Ignoring BGRT: failed to map image header memory\n");
- return;
+ goto out;
}
memcpy(&bmp_header, image, sizeof(bmp_header));
- memunmap(image);
+ early_memunmap(image, sizeof(bmp_header));
if (bmp_header.id != 0x4d42) {
pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n",
bmp_header.id);
- return;
+ goto out;
}
bgrt_image_size = bmp_header.size;
+ efi_mem_reserve(bgrt->image_address, bgrt_image_size);
- bgrt_image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
- if (!bgrt_image) {
- pr_notice("Ignoring BGRT: failed to map image memory\n");
- bgrt_image = NULL;
- return;
- }
-
- efi_mem_reserve(bgrt_tab->image_address, bgrt_image_size);
+ return;
+out:
+ memset(bgrt, 0, sizeof(bgrt_tab));
}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 936a488..565dff3 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -210,6 +210,70 @@
return 0;
}
+#define OVERFLOW_ADDR_SHIFT (64 - EFI_PAGE_SHIFT)
+#define OVERFLOW_ADDR_MASK (U64_MAX << OVERFLOW_ADDR_SHIFT)
+#define U64_HIGH_BIT (~(U64_MAX >> 1))
+
+static bool __init efi_memmap_entry_valid(const efi_memory_desc_t *md, int i)
+{
+ u64 end = (md->num_pages << EFI_PAGE_SHIFT) + md->phys_addr - 1;
+ u64 end_hi = 0;
+ char buf[64];
+
+ if (md->num_pages == 0) {
+ end = 0;
+ } else if (md->num_pages > EFI_PAGES_MAX ||
+ EFI_PAGES_MAX - md->num_pages <
+ (md->phys_addr >> EFI_PAGE_SHIFT)) {
+ end_hi = (md->num_pages & OVERFLOW_ADDR_MASK)
+ >> OVERFLOW_ADDR_SHIFT;
+
+ if ((md->phys_addr & U64_HIGH_BIT) && !(end & U64_HIGH_BIT))
+ end_hi += 1;
+ } else {
+ return true;
+ }
+
+ pr_warn_once(FW_BUG "Invalid EFI memory map entries:\n");
+
+ if (end_hi) {
+ pr_warn("mem%02u: %s range=[0x%016llx-0x%llx%016llx] (invalid)\n",
+ i, efi_md_typeattr_format(buf, sizeof(buf), md),
+ md->phys_addr, end_hi, end);
+ } else {
+ pr_warn("mem%02u: %s range=[0x%016llx-0x%016llx] (invalid)\n",
+ i, efi_md_typeattr_format(buf, sizeof(buf), md),
+ md->phys_addr, end);
+ }
+ return false;
+}
+
+static void __init efi_clean_memmap(void)
+{
+ efi_memory_desc_t *out = efi.memmap.map;
+ const efi_memory_desc_t *in = out;
+ const efi_memory_desc_t *end = efi.memmap.map_end;
+ int i, n_removal;
+
+ for (i = n_removal = 0; in < end; i++) {
+ if (efi_memmap_entry_valid(in, i)) {
+ if (out != in)
+ memcpy(out, in, efi.memmap.desc_size);
+ out = (void *)out + efi.memmap.desc_size;
+ } else {
+ n_removal++;
+ }
+ in = (void *)in + efi.memmap.desc_size;
+ }
+
+ if (n_removal > 0) {
+ u64 size = efi.memmap.nr_map - n_removal;
+
+ pr_warn("Removing %d invalid memory map entries.\n", n_removal);
+ efi_memmap_install(efi.memmap.phys_map, size);
+ }
+}
+
void __init efi_print_memmap(void)
{
efi_memory_desc_t *md;
@@ -472,15 +536,12 @@
}
}
+ efi_clean_memmap();
+
if (efi_enabled(EFI_DBG))
efi_print_memmap();
}
-void __init efi_late_init(void)
-{
- efi_bgrt_init();
-}
-
void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
{
u64 addr, npages;
@@ -894,6 +955,11 @@
return;
}
+ if (efi_enabled(EFI_DBG)) {
+ pr_info("EFI runtime memory map:\n");
+ efi_print_memmap();
+ }
+
BUG_ON(!efi.systab);
if (efi_setup_page_tables(pa, 1 << pg_shift)) {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 319148b..a4695da 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -269,6 +269,22 @@
efi_scratch.use_pgd = true;
/*
+ * Certain firmware versions are way too sentimential and still believe
+ * they are exclusive and unquestionable owners of the first physical page,
+ * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY
+ * (but then write-access it later during SetVirtualAddressMap()).
+ *
+ * Create a 1:1 mapping for this page, to avoid triple faults during early
+ * boot with such firmware. We are free to hand this page to the BIOS,
+ * as trim_bios_range() will reserve the first page and isolate it away
+ * from memory allocators anyway.
+ */
+ if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) {
+ pr_err("Failed to create 1:1 mapping for the first page!\n");
+ return 1;
+ }
+
+ /*
* When making calls to the firmware everything needs to be 1:1
* mapped and addressable with 32-bit pointers. Map the kernel
* text and allocate a new stack because we can't rely on the
@@ -398,10 +414,44 @@
efi_setup = phys_addr + sizeof(struct setup_data);
}
-void __init efi_runtime_update_mappings(void)
+static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf)
{
unsigned long pfn;
pgd_t *pgd = efi_pgd;
+ int err1, err2;
+
+ /* Update the 1:1 mapping */
+ pfn = md->phys_addr >> PAGE_SHIFT;
+ err1 = kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf);
+ if (err1) {
+ pr_err("Error while updating 1:1 mapping PA 0x%llx -> VA 0x%llx!\n",
+ md->phys_addr, md->virt_addr);
+ }
+
+ err2 = kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf);
+ if (err2) {
+ pr_err("Error while updating VA mapping PA 0x%llx -> VA 0x%llx!\n",
+ md->phys_addr, md->virt_addr);
+ }
+
+ return err1 || err2;
+}
+
+static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md)
+{
+ unsigned long pf = 0;
+
+ if (md->attribute & EFI_MEMORY_XP)
+ pf |= _PAGE_NX;
+
+ if (!(md->attribute & EFI_MEMORY_RO))
+ pf |= _PAGE_RW;
+
+ return efi_update_mappings(md, pf);
+}
+
+void __init efi_runtime_update_mappings(void)
+{
efi_memory_desc_t *md;
if (efi_enabled(EFI_OLD_MEMMAP)) {
@@ -410,6 +460,24 @@
return;
}
+ /*
+ * Use the EFI Memory Attribute Table for mapping permissions if it
+ * exists, since it is intended to supersede EFI_PROPERTIES_TABLE.
+ */
+ if (efi_enabled(EFI_MEM_ATTR)) {
+ efi_memattr_apply_permissions(NULL, efi_update_mem_attr);
+ return;
+ }
+
+ /*
+ * EFI_MEMORY_ATTRIBUTES_TABLE is intended to replace
+ * EFI_PROPERTIES_TABLE. So, use EFI_PROPERTIES_TABLE to update
+ * permissions only if EFI_MEMORY_ATTRIBUTES_TABLE is not
+ * published by the firmware. Even if we find a buggy implementation of
+ * EFI_MEMORY_ATTRIBUTES_TABLE, don't fall back to
+ * EFI_PROPERTIES_TABLE, because of the same reason.
+ */
+
if (!efi_enabled(EFI_NX_PE_DATA))
return;
@@ -430,15 +498,7 @@
(md->type != EFI_RUNTIME_SERVICES_CODE))
pf |= _PAGE_RW;
- /* Update the 1:1 mapping */
- pfn = md->phys_addr >> PAGE_SHIFT;
- if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf))
- pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
- md->phys_addr, md->virt_addr);
-
- if (kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf))
- pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
- md->phys_addr, md->virt_addr);
+ efi_update_mappings(md, pf);
}
}
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 10aca63..30031d5 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -214,7 +214,7 @@
new_size = efi.memmap.desc_size * num_entries;
- new_phys = memblock_alloc(new_size, 0);
+ new_phys = efi_memmap_alloc(num_entries);
if (!new_phys) {
pr_err("Could not allocate boot services memmap\n");
return;
@@ -355,7 +355,7 @@
}
new_size = efi.memmap.desc_size * num_entries;
- new_phys = memblock_alloc(new_size, 0);
+ new_phys = efi_memmap_alloc(num_entries);
if (!new_phys) {
pr_err("Failed to allocate new EFI memmap\n");
return;
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index 61b5ed2..90e4f2a 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -15,7 +15,7 @@
obj-$(subst m,y,$(CONFIG_GPIO_INTEL_PMIC)) += platform_pmic_gpio.o
obj-$(subst m,y,$(CONFIG_INTEL_MFLD_THERMAL)) += platform_msic_thermal.o
# SPI Devices
-obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_spidev.o
+obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_mrfld_spidev.o
# I2C Devices
obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o
obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_spidev.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c
similarity index 91%
rename from arch/x86/platform/intel-mid/device_libs/platform_spidev.c
rename to arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c
index 30c601b..27186ad 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_spidev.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c
@@ -11,6 +11,7 @@
* of the License.
*/
+#include <linux/err.h>
#include <linux/init.h>
#include <linux/sfi.h>
#include <linux/spi/pxa2xx_spi.h>
@@ -34,6 +35,9 @@
{
struct spi_board_info *spi_info = info;
+ if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+ return ERR_PTR(-ENODEV);
+
spi_info->mode = SPI_MODE_0;
spi_info->controller_data = &spidev_spi_chip;
diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig
index d957d5f..0bc60a3 100644
--- a/arch/x86/ras/Kconfig
+++ b/arch/x86/ras/Kconfig
@@ -1,6 +1,6 @@
config MCE_AMD_INJ
tristate "Simple MCE injection interface for AMD processors"
- depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB
+ depends on RAS && X86_MCE && DEBUG_FS && AMD_NB
default n
help
This is a simple debugfs interface to inject MCEs and test different
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index b7fbaa5..9e9760b 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -1,7 +1,6 @@
generic-y += bitsperlong.h
generic-y += bug.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += div64.h
generic-y += dma-contiguous.h
generic-y += emergency-restart.h
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 848e856..8fd4be6 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -419,7 +419,7 @@
void cpu_reset(void)
{
-#if XCHAL_HAVE_PTP_MMU
+#if XCHAL_HAVE_PTP_MMU && IS_ENABLED(CONFIG_MMU)
local_irq_disable();
/*
* We have full MMU: all autoload ways, ways 7, 8 and 9 of DTLB must
diff --git a/block/blk-lib.c b/block/blk-lib.c
index ed89c8f..ed1e78e 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -301,23 +301,11 @@
if ((sector | nr_sects) & bs_mask)
return -EINVAL;
- if (discard) {
- ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
- BLKDEV_DISCARD_ZERO, biop);
- if (ret == 0 || (ret && ret != -EOPNOTSUPP))
- goto out;
- }
-
ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
biop);
if (ret == 0 || (ret && ret != -EOPNOTSUPP))
goto out;
- ret = __blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
- ZERO_PAGE(0), biop);
- if (ret == 0 || (ret && ret != -EOPNOTSUPP))
- goto out;
-
ret = 0;
while (nr_sects != 0) {
bio = next_bio(bio, min(nr_sects, (sector_t)BIO_MAX_PAGES),
@@ -370,6 +358,16 @@
struct bio *bio = NULL;
struct blk_plug plug;
+ if (discard) {
+ if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
+ BLKDEV_DISCARD_ZERO))
+ return 0;
+ }
+
+ if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
+ ZERO_PAGE(0)))
+ return 0;
+
blk_start_plug(&plug);
ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
&bio, discard);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a8e67a1..c3400b5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -912,7 +912,6 @@
static void blk_mq_process_rq_list(struct blk_mq_hw_ctx *hctx)
{
LIST_HEAD(rq_list);
- LIST_HEAD(driver_list);
if (unlikely(blk_mq_hctx_stopped(hctx)))
return;
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 472211f..3bd15d8 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -16,7 +16,7 @@
static inline sector_t blk_zone_start(struct request_queue *q,
sector_t sector)
{
- sector_t zone_mask = blk_queue_zone_size(q) - 1;
+ sector_t zone_mask = blk_queue_zone_sectors(q) - 1;
return sector & ~zone_mask;
}
@@ -222,7 +222,7 @@
return -EINVAL;
/* Check alignment (handle eventual smaller last zone) */
- zone_sectors = blk_queue_zone_size(q);
+ zone_sectors = blk_queue_zone_sectors(q);
if (sector & (zone_sectors - 1))
return -EINVAL;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index c73a6fc..838f07e 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3758,7 +3758,7 @@
}
#ifdef CONFIG_CFQ_GROUP_IOSCHED
-static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
{
struct cfq_data *cfqd = cic_to_cfqd(cic);
struct cfq_queue *cfqq;
@@ -3775,15 +3775,7 @@
* spuriously on a newly created cic but there's no harm.
*/
if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr))
- return;
-
- /*
- * If we have a non-root cgroup, we can depend on that to
- * do proper throttling of writes. Turn off wbt for that
- * case, if it was enabled by default.
- */
- if (nonroot_cg)
- wbt_disable_default(cfqd->queue);
+ return nonroot_cg;
/*
* Drop reference to queues. New queues will be assigned in new
@@ -3804,9 +3796,13 @@
}
cic->blkcg_serial_nr = serial_nr;
+ return nonroot_cg;
}
#else
-static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { }
+static inline bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+{
+ return false;
+}
#endif /* CONFIG_CFQ_GROUP_IOSCHED */
static struct cfq_queue **
@@ -4448,11 +4444,12 @@
const int rw = rq_data_dir(rq);
const bool is_sync = rq_is_sync(rq);
struct cfq_queue *cfqq;
+ bool disable_wbt;
spin_lock_irq(q->queue_lock);
check_ioprio_changed(cic, bio);
- check_blkcg_changed(cic, bio);
+ disable_wbt = check_blkcg_changed(cic, bio);
new_queue:
cfqq = cic_to_cfqq(cic, is_sync);
if (!cfqq || cfqq == &cfqd->oom_cfqq) {
@@ -4488,6 +4485,10 @@
rq->elv.priv[0] = cfqq;
rq->elv.priv[1] = cfqq->cfqg;
spin_unlock_irq(q->queue_lock);
+
+ if (disable_wbt)
+ wbt_disable_default(q);
+
return 0;
}
diff --git a/block/partition-generic.c b/block/partition-generic.c
index d7beb6b..7afb990 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -434,7 +434,7 @@
struct block_device *bdev,
sector_t from, sector_t size)
{
- unsigned int zone_size = bdev_zone_size(bdev);
+ unsigned int zone_sectors = bdev_zone_sectors(bdev);
/*
* If this function is called, then the disk is a zoned block device
@@ -446,7 +446,7 @@
* regular block devices (no zone operation) and their zone size will
* be reported as 0. Allow this case.
*/
- if (!zone_size)
+ if (!zone_sectors)
return true;
/*
@@ -455,24 +455,24 @@
* use it. Check the zone size too: it should be a power of 2 number
* of sectors.
*/
- if (WARN_ON_ONCE(!is_power_of_2(zone_size))) {
+ if (WARN_ON_ONCE(!is_power_of_2(zone_sectors))) {
u32 rem;
- div_u64_rem(from, zone_size, &rem);
+ div_u64_rem(from, zone_sectors, &rem);
if (rem)
return false;
if ((from + size) < get_capacity(disk)) {
- div_u64_rem(size, zone_size, &rem);
+ div_u64_rem(size, zone_sectors, &rem);
if (rem)
return false;
}
} else {
- if (from & (zone_size - 1))
+ if (from & (zone_sectors - 1))
return false;
if ((from + size) < get_capacity(disk) &&
- (size & (zone_size - 1)))
+ (size & (zone_sectors - 1)))
return false;
}
diff --git a/crypto/algapi.c b/crypto/algapi.c
index df939b5..1fad2a6 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -356,6 +356,7 @@
struct crypto_larval *larval;
int err;
+ alg->cra_flags &= ~CRYPTO_ALG_DEAD;
err = crypto_check_alg(alg);
if (err)
return err;
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index f849311..533265f 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -661,9 +661,9 @@
unlock:
list_for_each_entry_safe(rsgl, tmp, &ctx->list, list) {
af_alg_free_sg(&rsgl->sgl);
+ list_del(&rsgl->list);
if (rsgl != &ctx->first_rsgl)
sock_kfree_s(sk, rsgl, sizeof(*rsgl));
- list_del(&rsgl->list);
}
INIT_LIST_HEAD(&ctx->list);
aead_wmem_wakeup(sk);
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 9ed0878..a391bbc 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -55,7 +55,7 @@
acpi-$(CONFIG_ACPI_NUMA) += numa.o
acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
acpi-y += acpi_lpat.o
-acpi-$(CONFIG_ACPI_GENERIC_GSI) += gsi.o
+acpi-$(CONFIG_ACPI_GENERIC_GSI) += irq.o
acpi-$(CONFIG_ACPI_WATCHDOG) += acpi_watchdog.o
# These are (potentially) separate modules
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index b3842ff..a15270a 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -212,6 +212,7 @@
}
static struct notifier_block extlog_mce_dec = {
.notifier_call = extlog_print,
+ .priority = MCE_PRIO_EXTLOG,
};
static int __init extlog_init(void)
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index 82b0b57..b0399e8 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -852,23 +852,18 @@
ACPI_FUNCTION_TRACE(tb_install_and_load_table);
- (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
-
/* Install the table and load it into the namespace */
status = acpi_tb_install_standard_table(address, flags, TRUE,
override, &i);
if (ACPI_FAILURE(status)) {
- goto unlock_and_exit;
+ goto exit;
}
- (void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
status = acpi_tb_load_table(i, acpi_gbl_root_node);
- (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
-unlock_and_exit:
+exit:
*table_index = i;
- (void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
return_ACPI_STATUS(status);
}
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index 5fdf251..01e1b3d 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -217,6 +217,10 @@
goto release_and_exit;
}
+ /* Acquire the table lock */
+
+ (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
+
if (reload) {
/*
* Validate the incoming table signature.
@@ -244,7 +248,7 @@
new_table_desc.signature.integer));
status = AE_BAD_SIGNATURE;
- goto release_and_exit;
+ goto unlock_and_exit;
}
/* Check if table is already registered */
@@ -279,7 +283,7 @@
/* Table is still loaded, this is an error */
status = AE_ALREADY_EXISTS;
- goto release_and_exit;
+ goto unlock_and_exit;
} else {
/*
* Table was unloaded, allow it to be reloaded.
@@ -290,6 +294,7 @@
* indicate the re-installation.
*/
acpi_tb_uninstall_table(&new_table_desc);
+ (void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
*table_index = i;
return_ACPI_STATUS(AE_OK);
}
@@ -303,11 +308,19 @@
/* Invoke table handler if present */
+ (void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
if (acpi_gbl_table_handler) {
(void)acpi_gbl_table_handler(ACPI_TABLE_EVENT_INSTALL,
new_table_desc.pointer,
acpi_gbl_table_handler_context);
}
+ (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
+
+unlock_and_exit:
+
+ /* Release the table lock */
+
+ (void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
release_and_exit:
diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
index 75f128e..ca28aa57 100644
--- a/drivers/acpi/bgrt.c
+++ b/drivers/acpi/bgrt.c
@@ -15,40 +15,41 @@
#include <linux/sysfs.h>
#include <linux/efi-bgrt.h>
+static void *bgrt_image;
static struct kobject *bgrt_kobj;
static ssize_t show_version(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->version);
+ return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.version);
}
static DEVICE_ATTR(version, S_IRUGO, show_version, NULL);
static ssize_t show_status(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->status);
+ return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.status);
}
static DEVICE_ATTR(status, S_IRUGO, show_status, NULL);
static ssize_t show_type(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_type);
+ return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_type);
}
static DEVICE_ATTR(type, S_IRUGO, show_type, NULL);
static ssize_t show_xoffset(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_offset_x);
+ return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_x);
}
static DEVICE_ATTR(xoffset, S_IRUGO, show_xoffset, NULL);
static ssize_t show_yoffset(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_offset_y);
+ return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_y);
}
static DEVICE_ATTR(yoffset, S_IRUGO, show_yoffset, NULL);
@@ -84,15 +85,24 @@
{
int ret;
- if (!bgrt_image)
+ if (!bgrt_tab.image_address)
return -ENODEV;
+ bgrt_image = memremap(bgrt_tab.image_address, bgrt_image_size,
+ MEMREMAP_WB);
+ if (!bgrt_image) {
+ pr_notice("Ignoring BGRT: failed to map image memory\n");
+ return -ENOMEM;
+ }
+
bin_attr_image.private = bgrt_image;
bin_attr_image.size = bgrt_image_size;
bgrt_kobj = kobject_create_and_add("bgrt", acpi_kobj);
- if (!bgrt_kobj)
- return -EINVAL;
+ if (!bgrt_kobj) {
+ ret = -EINVAL;
+ goto out_memmap;
+ }
ret = sysfs_create_group(bgrt_kobj, &bgrt_attribute_group);
if (ret)
@@ -102,6 +112,8 @@
out_kobject:
kobject_put(bgrt_kobj);
+out_memmap:
+ memunmap(bgrt_image);
return ret;
}
device_initcall(bgrt_init);
diff --git a/drivers/acpi/gsi.c b/drivers/acpi/gsi.c
deleted file mode 100644
index ee9e0f2..0000000
--- a/drivers/acpi/gsi.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * ACPI GSI IRQ layer
- *
- * Copyright (C) 2015 ARM Ltd.
- * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/acpi.h>
-#include <linux/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/of.h>
-
-enum acpi_irq_model_id acpi_irq_model;
-
-static struct fwnode_handle *acpi_gsi_domain_id;
-
-/**
- * acpi_gsi_to_irq() - Retrieve the linux irq number for a given GSI
- * @gsi: GSI IRQ number to map
- * @irq: pointer where linux IRQ number is stored
- *
- * irq location updated with irq value [>0 on success, 0 on failure]
- *
- * Returns: linux IRQ number on success (>0)
- * -EINVAL on failure
- */
-int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
-{
- struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id,
- DOMAIN_BUS_ANY);
-
- *irq = irq_find_mapping(d, gsi);
- /*
- * *irq == 0 means no mapping, that should
- * be reported as a failure
- */
- return (*irq > 0) ? *irq : -EINVAL;
-}
-EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
-
-/**
- * acpi_register_gsi() - Map a GSI to a linux IRQ number
- * @dev: device for which IRQ has to be mapped
- * @gsi: GSI IRQ number
- * @trigger: trigger type of the GSI number to be mapped
- * @polarity: polarity of the GSI to be mapped
- *
- * Returns: a valid linux IRQ number on success
- * -EINVAL on failure
- */
-int acpi_register_gsi(struct device *dev, u32 gsi, int trigger,
- int polarity)
-{
- struct irq_fwspec fwspec;
-
- if (WARN_ON(!acpi_gsi_domain_id)) {
- pr_warn("GSI: No registered irqchip, giving up\n");
- return -EINVAL;
- }
-
- fwspec.fwnode = acpi_gsi_domain_id;
- fwspec.param[0] = gsi;
- fwspec.param[1] = acpi_dev_get_irq_type(trigger, polarity);
- fwspec.param_count = 2;
-
- return irq_create_fwspec_mapping(&fwspec);
-}
-EXPORT_SYMBOL_GPL(acpi_register_gsi);
-
-/**
- * acpi_unregister_gsi() - Free a GSI<->linux IRQ number mapping
- * @gsi: GSI IRQ number
- */
-void acpi_unregister_gsi(u32 gsi)
-{
- struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id,
- DOMAIN_BUS_ANY);
- int irq = irq_find_mapping(d, gsi);
-
- irq_dispose_mapping(irq);
-}
-EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
-
-/**
- * acpi_set_irq_model - Setup the GSI irqdomain information
- * @model: the value assigned to acpi_irq_model
- * @fwnode: the irq_domain identifier for mapping and looking up
- * GSI interrupts
- */
-void __init acpi_set_irq_model(enum acpi_irq_model_id model,
- struct fwnode_handle *fwnode)
-{
- acpi_irq_model = model;
- acpi_gsi_domain_id = fwnode;
-}
diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c
new file mode 100644
index 0000000..830299a
--- /dev/null
+++ b/drivers/acpi/irq.c
@@ -0,0 +1,297 @@
+/*
+ * ACPI GSI IRQ layer
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/acpi.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+
+enum acpi_irq_model_id acpi_irq_model;
+
+static struct fwnode_handle *acpi_gsi_domain_id;
+
+/**
+ * acpi_gsi_to_irq() - Retrieve the linux irq number for a given GSI
+ * @gsi: GSI IRQ number to map
+ * @irq: pointer where linux IRQ number is stored
+ *
+ * irq location updated with irq value [>0 on success, 0 on failure]
+ *
+ * Returns: linux IRQ number on success (>0)
+ * -EINVAL on failure
+ */
+int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
+{
+ struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id,
+ DOMAIN_BUS_ANY);
+
+ *irq = irq_find_mapping(d, gsi);
+ /*
+ * *irq == 0 means no mapping, that should
+ * be reported as a failure
+ */
+ return (*irq > 0) ? *irq : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
+
+/**
+ * acpi_register_gsi() - Map a GSI to a linux IRQ number
+ * @dev: device for which IRQ has to be mapped
+ * @gsi: GSI IRQ number
+ * @trigger: trigger type of the GSI number to be mapped
+ * @polarity: polarity of the GSI to be mapped
+ *
+ * Returns: a valid linux IRQ number on success
+ * -EINVAL on failure
+ */
+int acpi_register_gsi(struct device *dev, u32 gsi, int trigger,
+ int polarity)
+{
+ struct irq_fwspec fwspec;
+
+ if (WARN_ON(!acpi_gsi_domain_id)) {
+ pr_warn("GSI: No registered irqchip, giving up\n");
+ return -EINVAL;
+ }
+
+ fwspec.fwnode = acpi_gsi_domain_id;
+ fwspec.param[0] = gsi;
+ fwspec.param[1] = acpi_dev_get_irq_type(trigger, polarity);
+ fwspec.param_count = 2;
+
+ return irq_create_fwspec_mapping(&fwspec);
+}
+EXPORT_SYMBOL_GPL(acpi_register_gsi);
+
+/**
+ * acpi_unregister_gsi() - Free a GSI<->linux IRQ number mapping
+ * @gsi: GSI IRQ number
+ */
+void acpi_unregister_gsi(u32 gsi)
+{
+ struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id,
+ DOMAIN_BUS_ANY);
+ int irq = irq_find_mapping(d, gsi);
+
+ irq_dispose_mapping(irq);
+}
+EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
+
+/**
+ * acpi_get_irq_source_fwhandle() - Retrieve fwhandle from IRQ resource source.
+ * @source: acpi_resource_source to use for the lookup.
+ *
+ * Description:
+ * Retrieve the fwhandle of the device referenced by the given IRQ resource
+ * source.
+ *
+ * Return:
+ * The referenced device fwhandle or NULL on failure
+ */
+static struct fwnode_handle *
+acpi_get_irq_source_fwhandle(const struct acpi_resource_source *source)
+{
+ struct fwnode_handle *result;
+ struct acpi_device *device;
+ acpi_handle handle;
+ acpi_status status;
+
+ if (!source->string_length)
+ return acpi_gsi_domain_id;
+
+ status = acpi_get_handle(NULL, source->string_ptr, &handle);
+ if (WARN_ON(ACPI_FAILURE(status)))
+ return NULL;
+
+ device = acpi_bus_get_acpi_device(handle);
+ if (WARN_ON(!device))
+ return NULL;
+
+ result = &device->fwnode;
+ acpi_bus_put_acpi_device(device);
+ return result;
+}
+
+/*
+ * Context for the resource walk used to lookup IRQ resources.
+ * Contains a return code, the lookup index, and references to the flags
+ * and fwspec where the result is returned.
+ */
+struct acpi_irq_parse_one_ctx {
+ int rc;
+ unsigned int index;
+ unsigned long *res_flags;
+ struct irq_fwspec *fwspec;
+};
+
+/**
+ * acpi_irq_parse_one_match - Handle a matching IRQ resource.
+ * @fwnode: matching fwnode
+ * @hwirq: hardware IRQ number
+ * @triggering: triggering attributes of hwirq
+ * @polarity: polarity attributes of hwirq
+ * @polarity: polarity attributes of hwirq
+ * @shareable: shareable attributes of hwirq
+ * @ctx: acpi_irq_parse_one_ctx updated by this function
+ *
+ * Description:
+ * Handle a matching IRQ resource by populating the given ctx with
+ * the information passed.
+ */
+static inline void acpi_irq_parse_one_match(struct fwnode_handle *fwnode,
+ u32 hwirq, u8 triggering,
+ u8 polarity, u8 shareable,
+ struct acpi_irq_parse_one_ctx *ctx)
+{
+ if (!fwnode)
+ return;
+ ctx->rc = 0;
+ *ctx->res_flags = acpi_dev_irq_flags(triggering, polarity, shareable);
+ ctx->fwspec->fwnode = fwnode;
+ ctx->fwspec->param[0] = hwirq;
+ ctx->fwspec->param[1] = acpi_dev_get_irq_type(triggering, polarity);
+ ctx->fwspec->param_count = 2;
+}
+
+/**
+ * acpi_irq_parse_one_cb - Handle the given resource.
+ * @ares: resource to handle
+ * @context: context for the walk
+ *
+ * Description:
+ * This is called by acpi_walk_resources passing each resource returned by
+ * the _CRS method. We only inspect IRQ resources. Since IRQ resources
+ * might contain multiple interrupts we check if the index is within this
+ * one's interrupt array, otherwise we subtract the current resource IRQ
+ * count from the lookup index to prepare for the next resource.
+ * Once a match is found we call acpi_irq_parse_one_match to populate
+ * the result and end the walk by returning AE_CTRL_TERMINATE.
+ *
+ * Return:
+ * AE_OK if the walk should continue, AE_CTRL_TERMINATE if a matching
+ * IRQ resource was found.
+ */
+static acpi_status acpi_irq_parse_one_cb(struct acpi_resource *ares,
+ void *context)
+{
+ struct acpi_irq_parse_one_ctx *ctx = context;
+ struct acpi_resource_irq *irq;
+ struct acpi_resource_extended_irq *eirq;
+ struct fwnode_handle *fwnode;
+
+ switch (ares->type) {
+ case ACPI_RESOURCE_TYPE_IRQ:
+ irq = &ares->data.irq;
+ if (ctx->index >= irq->interrupt_count) {
+ ctx->index -= irq->interrupt_count;
+ return AE_OK;
+ }
+ fwnode = acpi_gsi_domain_id;
+ acpi_irq_parse_one_match(fwnode, irq->interrupts[ctx->index],
+ irq->triggering, irq->polarity,
+ irq->sharable, ctx);
+ return AE_CTRL_TERMINATE;
+ case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
+ eirq = &ares->data.extended_irq;
+ if (eirq->producer_consumer == ACPI_PRODUCER)
+ return AE_OK;
+ if (ctx->index >= eirq->interrupt_count) {
+ ctx->index -= eirq->interrupt_count;
+ return AE_OK;
+ }
+ fwnode = acpi_get_irq_source_fwhandle(&eirq->resource_source);
+ acpi_irq_parse_one_match(fwnode, eirq->interrupts[ctx->index],
+ eirq->triggering, eirq->polarity,
+ eirq->sharable, ctx);
+ return AE_CTRL_TERMINATE;
+ }
+
+ return AE_OK;
+}
+
+/**
+ * acpi_irq_parse_one - Resolve an interrupt for a device
+ * @handle: the device whose interrupt is to be resolved
+ * @index: index of the interrupt to resolve
+ * @fwspec: structure irq_fwspec filled by this function
+ * @flags: resource flags filled by this function
+ *
+ * Description:
+ * Resolves an interrupt for a device by walking its CRS resources to find
+ * the appropriate ACPI IRQ resource and populating the given struct irq_fwspec
+ * and flags.
+ *
+ * Return:
+ * The result stored in ctx.rc by the callback, or the default -EINVAL value
+ * if an error occurs.
+ */
+static int acpi_irq_parse_one(acpi_handle handle, unsigned int index,
+ struct irq_fwspec *fwspec, unsigned long *flags)
+{
+ struct acpi_irq_parse_one_ctx ctx = { -EINVAL, index, flags, fwspec };
+
+ acpi_walk_resources(handle, METHOD_NAME__CRS, acpi_irq_parse_one_cb, &ctx);
+ return ctx.rc;
+}
+
+/**
+ * acpi_irq_get - Lookup an ACPI IRQ resource and use it to initialize resource.
+ * @handle: ACPI device handle
+ * @index: ACPI IRQ resource index to lookup
+ * @res: Linux IRQ resource to initialize
+ *
+ * Description:
+ * Look for the ACPI IRQ resource with the given index and use it to initialize
+ * the given Linux IRQ resource.
+ *
+ * Return:
+ * 0 on success
+ * -EINVAL if an error occurs
+ * -EPROBE_DEFER if the IRQ lookup/conversion failed
+ */
+int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res)
+{
+ struct irq_fwspec fwspec;
+ struct irq_domain *domain;
+ unsigned long flags;
+ int rc;
+
+ rc = acpi_irq_parse_one(handle, index, &fwspec, &flags);
+ if (rc)
+ return rc;
+
+ domain = irq_find_matching_fwnode(fwspec.fwnode, DOMAIN_BUS_ANY);
+ if (!domain)
+ return -EPROBE_DEFER;
+
+ rc = irq_create_fwspec_mapping(&fwspec);
+ if (rc <= 0)
+ return -EINVAL;
+
+ res->start = rc;
+ res->end = rc;
+ res->flags = flags;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_irq_get);
+
+/**
+ * acpi_set_irq_model - Setup the GSI irqdomain information
+ * @model: the value assigned to acpi_irq_model
+ * @fwnode: the irq_domain identifier for mapping and looking up
+ * GSI interrupts
+ */
+void __init acpi_set_irq_model(enum acpi_irq_model_id model,
+ struct fwnode_handle *fwnode)
+{
+ acpi_irq_model = model;
+ acpi_gsi_domain_id = fwnode;
+}
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 2f82b8e..7361d00 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -2704,6 +2704,7 @@
struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
struct device *dev = acpi_desc->dev;
struct acpi_nfit_flush_work flush;
+ int rc;
/* bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */
device_lock(dev);
@@ -2716,7 +2717,10 @@
INIT_WORK_ONSTACK(&flush.work, flush_probe);
COMPLETION_INITIALIZER_ONSTACK(flush.cmp);
queue_work(nfit_wq, &flush.work);
- return wait_for_completion_interruptible(&flush.cmp);
+
+ rc = wait_for_completion_interruptible(&flush.cmp);
+ cancel_work_sync(&flush.work);
+ return rc;
}
static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index e5ce81c..3ba1c34 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -90,6 +90,7 @@
static struct notifier_block nfit_mce_dec = {
.notifier_call = nfit_handle_mce,
+ .priority = MCE_PRIO_NFIT,
};
void nfit_mce_register(void)
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index cb57962..8b11d6d 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -43,6 +43,19 @@
acpi_iospace_resource_valid(struct resource *res) { return true; }
#endif
+#if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI)
+static inline bool is_gsi(struct acpi_resource_extended_irq *ext_irq)
+{
+ return ext_irq->resource_source.string_length == 0 &&
+ ext_irq->producer_consumer == ACPI_CONSUMER;
+}
+#else
+static inline bool is_gsi(struct acpi_resource_extended_irq *ext_irq)
+{
+ return true;
+}
+#endif
+
static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io)
{
u64 reslen = end - start + 1;
@@ -470,9 +483,12 @@
acpi_dev_irqresource_disabled(res, 0);
return false;
}
- acpi_dev_get_irqresource(res, ext_irq->interrupts[index],
+ if (is_gsi(ext_irq))
+ acpi_dev_get_irqresource(res, ext_irq->interrupts[index],
ext_irq->triggering, ext_irq->polarity,
ext_irq->sharable, false);
+ else
+ acpi_dev_irqresource_disabled(res, 0);
break;
default:
res->flags = 0;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 9b6cebe..54abb26 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -674,14 +674,6 @@
if (acpi_sleep_state_supported(i))
sleep_states[i] = 1;
- /*
- * Use suspend-to-idle by default if ACPI_FADT_LOW_POWER_S0 is set and
- * the default suspend mode was not selected from the command line.
- */
- if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0 &&
- mem_sleep_default > PM_SUSPEND_MEM)
- mem_sleep_default = PM_SUSPEND_FREEZE;
-
suspend_set_ops(old_suspend_ordering ?
&acpi_suspend_ops_old : &acpi_suspend_ops);
freeze_set_ops(&acpi_freeze_ops);
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 02ded25..7f48156 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -305,17 +305,6 @@
DMI_MATCH(DMI_PRODUCT_NAME, "Dell System XPS L702X"),
},
},
- {
- /* https://bugzilla.redhat.com/show_bug.cgi?id=1204476 */
- /* https://bugs.launchpad.net/ubuntu/+source/linux-lts-trusty/+bug/1416940 */
- .callback = video_detect_force_native,
- .ident = "HP Pavilion dv6",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv6 Notebook PC"),
- },
- },
-
{ },
};
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 9cd0a2d..c2d3785 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -1702,6 +1702,8 @@
if (qc->err_mask & ~AC_ERR_OTHER)
qc->err_mask &= ~AC_ERR_OTHER;
+ } else if (qc->tf.command == ATA_CMD_REQ_SENSE_DATA) {
+ qc->result_tf.command |= ATA_SENSE;
}
/* finish up */
@@ -4356,10 +4358,10 @@
{ "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 },
/*
- * Device times out with higher max sects.
+ * These devices time out with higher max sects.
* https://bugzilla.kernel.org/show_bug.cgi?id=121671
*/
- { "LITEON CX1-JB256-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 },
+ { "LITEON CX1-JB*-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 },
/* Devices we expect to fail diagnostics */
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 823e938..2f32782 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -4132,6 +4132,9 @@
host->iomap = NULL;
hpriv->base = devm_ioremap(&pdev->dev, res->start,
resource_size(res));
+ if (!hpriv->base)
+ return -ENOMEM;
+
hpriv->base -= SATAHC0_REG_BASE;
hpriv->clk = clk_get(&pdev->dev, NULL);
diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig
index 4ef4c5c..8a8e403 100644
--- a/drivers/auxdisplay/Kconfig
+++ b/drivers/auxdisplay/Kconfig
@@ -132,9 +132,9 @@
tristate "Holtek Ht16K33 LED controller with keyscan"
depends on FB && OF && I2C && INPUT
select FB_SYS_FOPS
- select FB_CFB_FILLRECT
- select FB_CFB_COPYAREA
- select FB_CFB_IMAGEBLIT
+ select FB_SYS_FILLRECT
+ select FB_SYS_COPYAREA
+ select FB_SYS_IMAGEBLIT
select INPUT_MATRIXKMAP
select FB_BACKLIGHT
help
diff --git a/drivers/base/base.h b/drivers/base/base.h
index ada9dce..e19b100 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -141,8 +141,6 @@
extern struct kset *devices_kset;
extern void devices_kset_move_last(struct device *dev);
-extern struct device_attribute dev_attr_deferred_probe;
-
#if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS)
extern void module_add_driver(struct module *mod, struct device_driver *drv);
extern void module_remove_driver(struct device_driver *drv);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 020ea7f..8c25e68 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1060,14 +1060,8 @@
goto err_remove_dev_groups;
}
- error = device_create_file(dev, &dev_attr_deferred_probe);
- if (error)
- goto err_remove_online;
-
return 0;
- err_remove_online:
- device_remove_file(dev, &dev_attr_online);
err_remove_dev_groups:
device_remove_groups(dev, dev->groups);
err_remove_type_groups:
@@ -1085,7 +1079,6 @@
struct class *class = dev->class;
const struct device_type *type = dev->type;
- device_remove_file(dev, &dev_attr_deferred_probe);
device_remove_file(dev, &dev_attr_online);
device_remove_groups(dev, dev->groups);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index a8b258e..a1fbf55 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -53,19 +53,6 @@
static LIST_HEAD(deferred_probe_active_list);
static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
-static ssize_t deferred_probe_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- bool value;
-
- mutex_lock(&deferred_probe_mutex);
- value = !list_empty(&dev->p->deferred_probe);
- mutex_unlock(&deferred_probe_mutex);
-
- return sprintf(buf, "%d\n", value);
-}
-DEVICE_ATTR_RO(deferred_probe);
-
/*
* In some cases, like suspend to RAM or hibernation, It might be reasonable
* to prohibit probing of devices as it could be unsafe.
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 4497d26..ac350c5 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -558,9 +558,6 @@
struct firmware_buf *buf = fw_priv->buf;
__fw_load_abort(buf);
-
- /* avoid user action after loading abort */
- fw_priv->buf = NULL;
}
static LIST_HEAD(pending_fw_head);
@@ -713,7 +710,7 @@
mutex_lock(&fw_lock);
fw_buf = fw_priv->buf;
- if (!fw_buf)
+ if (fw_state_is_aborted(&fw_buf->fw_st))
goto out;
switch (loading) {
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 8ab8ea1..fa26ffd 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -389,33 +389,33 @@
{
struct memory_block *mem = to_memory_block(dev);
unsigned long start_pfn, end_pfn;
+ unsigned long valid_start, valid_end, valid_pages;
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
- struct page *first_page;
struct zone *zone;
int zone_shift = 0;
start_pfn = section_nr_to_pfn(mem->start_section_nr);
end_pfn = start_pfn + nr_pages;
- first_page = pfn_to_page(start_pfn);
/* The block contains more than one zone can not be offlined. */
- if (!test_pages_in_a_zone(start_pfn, end_pfn))
+ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
return sprintf(buf, "none\n");
- zone = page_zone(first_page);
+ zone = page_zone(pfn_to_page(valid_start));
+ valid_pages = valid_end - valid_start;
/* MMOP_ONLINE_KEEP */
sprintf(buf, "%s", zone->name);
/* MMOP_ONLINE_KERNEL */
- zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL);
+ zone_can_shift(valid_start, valid_pages, ZONE_NORMAL, &zone_shift);
if (zone_shift) {
strcat(buf, " ");
strcat(buf, (zone + zone_shift)->name);
}
/* MMOP_ONLINE_MOVABLE */
- zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE);
+ zone_can_shift(valid_start, valid_pages, ZONE_MOVABLE, &zone_shift);
if (zone_shift) {
strcat(buf, " ");
strcat(buf, (zone + zone_shift)->name);
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index be6a599..0fc7c4d 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -206,7 +206,7 @@
{
struct platform_msi_priv_data *datap;
/*
- * Limit the number of interrupts to 256 per device. Should we
+ * Limit the number of interrupts to 2048 per device. Should we
* need to bump this up, DEV_ID_SHIFT should be adjusted
* accordingly (which would impact the max number of MSI
* capable devices).
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index c4af003..647e476 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -102,6 +102,16 @@
}
r = platform_get_resource(dev, IORESOURCE_IRQ, num);
+ if (has_acpi_companion(&dev->dev)) {
+ if (r && r->flags & IORESOURCE_DISABLED) {
+ int ret;
+
+ ret = acpi_irq_get(ACPI_HANDLE(&dev->dev), num, r);
+ if (ret)
+ return ret;
+ }
+ }
+
/*
* The resources may pass trigger flags to the irqs that need
* to be set up. It so happens that the trigger flags for
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 872eac4..a14fac6 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -966,13 +966,13 @@
unsigned long flags;
int retval;
- might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
-
if (rpmflags & RPM_GET_PUT) {
if (!atomic_dec_and_test(&dev->power.usage_count))
return 0;
}
+ might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
spin_lock_irqsave(&dev->power.lock, flags);
retval = rpm_idle(dev, rpmflags);
spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -998,13 +998,13 @@
unsigned long flags;
int retval;
- might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
-
if (rpmflags & RPM_GET_PUT) {
if (!atomic_dec_and_test(&dev->power.usage_count))
return 0;
}
+ might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
spin_lock_irqsave(&dev->power.lock, flags);
retval = rpm_suspend(dev, rpmflags);
spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -1029,7 +1029,8 @@
unsigned long flags;
int retval;
- might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+ might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe &&
+ dev->power.runtime_status != RPM_ACTIVE);
if (rpmflags & RPM_GET_PUT)
atomic_inc(&dev->power.usage_count);
diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index f642c42..168fa17 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -45,6 +45,9 @@
void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc);
void bcma_core_chipcommon_init(struct bcma_drv_cc *cc);
void bcma_chipco_bcm4331_ext_pa_lines_ctl(struct bcma_drv_cc *cc, bool enable);
+#ifdef CONFIG_BCMA_DRIVER_MIPS
+void bcma_chipco_serial_init(struct bcma_drv_cc *cc);
+#endif /* CONFIG_BCMA_DRIVER_MIPS */
/* driver_chipcommon_b.c */
int bcma_core_chipcommon_b_init(struct bcma_drv_cc_b *ccb);
diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c
index b4f6520..62f5bfa 100644
--- a/drivers/bcma/driver_chipcommon.c
+++ b/drivers/bcma/driver_chipcommon.c
@@ -15,8 +15,6 @@
#include <linux/platform_device.h>
#include <linux/bcma/bcma.h>
-static void bcma_chipco_serial_init(struct bcma_drv_cc *cc);
-
static inline u32 bcma_cc_write32_masked(struct bcma_drv_cc *cc, u16 offset,
u32 mask, u32 value)
{
@@ -186,9 +184,6 @@
if (cc->capabilities & BCMA_CC_CAP_PMU)
bcma_pmu_early_init(cc);
- if (IS_BUILTIN(CONFIG_BCM47XX) && bus->hosttype == BCMA_HOSTTYPE_SOC)
- bcma_chipco_serial_init(cc);
-
if (bus->hosttype == BCMA_HOSTTYPE_SOC)
bcma_core_chipcommon_flash_detect(cc);
@@ -378,9 +373,9 @@
return res;
}
-static void bcma_chipco_serial_init(struct bcma_drv_cc *cc)
+#ifdef CONFIG_BCMA_DRIVER_MIPS
+void bcma_chipco_serial_init(struct bcma_drv_cc *cc)
{
-#if IS_BUILTIN(CONFIG_BCM47XX)
unsigned int irq;
u32 baud_base;
u32 i;
@@ -422,5 +417,5 @@
ports[i].baud_base = baud_base;
ports[i].reg_shift = 0;
}
-#endif /* CONFIG_BCM47XX */
}
+#endif /* CONFIG_BCMA_DRIVER_MIPS */
diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index 96f1713..89af807 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -278,9 +278,12 @@
void bcma_core_mips_early_init(struct bcma_drv_mips *mcore)
{
+ struct bcma_bus *bus = mcore->core->bus;
+
if (mcore->early_setup_done)
return;
+ bcma_chipco_serial_init(&bus->drv_cc);
bcma_core_mips_nvram_init(mcore);
mcore->early_setup_done = true;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 38c576f..9fd06ee 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -271,7 +271,7 @@
static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
{
struct request *req = blk_mq_rq_from_pdu(cmd);
- int result, flags;
+ int result;
struct nbd_request request;
unsigned long size = blk_rq_bytes(req);
struct bio *bio;
@@ -310,7 +310,6 @@
if (type != NBD_CMD_WRITE)
return 0;
- flags = 0;
bio = req->bio;
while (bio) {
struct bio *next = bio->bi_next;
@@ -319,9 +318,8 @@
bio_for_each_segment(bvec, bio, iter) {
bool is_last = !next && bio_iter_last(bvec, iter);
+ int flags = is_last ? 0 : MSG_MORE;
- if (is_last)
- flags = MSG_MORE;
dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n",
cmd, bvec.bv_len);
result = sock_send_bvec(nbd, index, &bvec, flags);
@@ -1042,6 +1040,7 @@
return -ENOMEM;
for (i = 0; i < nbds_max; i++) {
+ struct request_queue *q;
struct gendisk *disk = alloc_disk(1 << part_shift);
if (!disk)
goto out;
@@ -1067,12 +1066,13 @@
* every gendisk to have its very own request_queue struct.
* These structs are big so we dynamically allocate them.
*/
- disk->queue = blk_mq_init_queue(&nbd_dev[i].tag_set);
- if (!disk->queue) {
+ q = blk_mq_init_queue(&nbd_dev[i].tag_set);
+ if (IS_ERR(q)) {
blk_mq_free_tag_set(&nbd_dev[i].tag_set);
put_disk(disk);
goto out;
}
+ disk->queue = q;
/*
* Tell the block layer that we are not a rotational device
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 79a346c..264c5ea 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -56,6 +56,7 @@
struct virtio_blk_outhdr out_hdr;
struct virtio_scsi_inhdr in_hdr;
u8 status;
+ u8 sense[SCSI_SENSE_BUFFERSIZE];
struct scatterlist sg[];
};
@@ -102,7 +103,8 @@
}
if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
- sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
+ memcpy(vbr->sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
+ sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
sgs[num_out + num_in++] = &sense;
sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
sgs[num_out + num_in++] = &inhdr;
@@ -628,11 +630,12 @@
if (err)
goto out_put_disk;
- q = vblk->disk->queue = blk_mq_init_queue(&vblk->tag_set);
+ q = blk_mq_init_queue(&vblk->tag_set);
if (IS_ERR(q)) {
err = -ENOMEM;
goto out_free_tags;
}
+ vblk->disk->queue = q;
q->queuedata = vblk;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index b2bdfa8..265f1a7 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -197,13 +197,13 @@
/* Number of pages per ring buffer. */
unsigned int nr_ring_pages;
struct request_queue *rq;
- unsigned int feature_flush;
- unsigned int feature_fua;
+ unsigned int feature_flush:1;
+ unsigned int feature_fua:1;
unsigned int feature_discard:1;
unsigned int feature_secdiscard:1;
+ unsigned int feature_persistent:1;
unsigned int discard_granularity;
unsigned int discard_alignment;
- unsigned int feature_persistent:1;
/* Number of 4KB segments handled */
unsigned int max_indirect_segments;
int is_ready;
@@ -2223,7 +2223,7 @@
}
else
grants = info->max_indirect_segments;
- psegs = grants / GRANTS_PER_PSEG;
+ psegs = DIV_ROUND_UP(grants, GRANTS_PER_PSEG);
err = fill_grant_buffer(rinfo,
(grants + INDIRECT_GREFS(grants)) * BLK_RING_SIZE(info));
@@ -2323,13 +2323,16 @@
blkfront_setup_discard(info);
info->feature_persistent =
- xenbus_read_unsigned(info->xbdev->otherend,
- "feature-persistent", 0);
+ !!xenbus_read_unsigned(info->xbdev->otherend,
+ "feature-persistent", 0);
indirect_segments = xenbus_read_unsigned(info->xbdev->otherend,
"feature-max-indirect-segments", 0);
- info->max_indirect_segments = min(indirect_segments,
- xen_blkif_max_segments);
+ if (indirect_segments > xen_blkif_max_segments)
+ indirect_segments = xen_blkif_max_segments;
+ if (indirect_segments <= BLKIF_MAX_SEGMENTS_PER_REQUEST)
+ indirect_segments = 0;
+ info->max_indirect_segments = indirect_segments;
}
/*
@@ -2652,6 +2655,9 @@
if (!xen_domain())
return -ENODEV;
+ if (xen_blkif_max_segments < BLKIF_MAX_SEGMENTS_PER_REQUEST)
+ xen_blkif_max_segments = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) {
pr_info("Invalid max_ring_order (%d), will use default max: %d.\n",
xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER);
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 6ce5ce8..87fba42 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -92,7 +92,6 @@
mutex_unlock(&reading_mutex);
if (bytes_read > 0)
add_device_randomness(rng_buffer, bytes_read);
- memset(rng_buffer, 0, size);
}
static inline void cleanup_rng(struct kref *kref)
@@ -288,7 +287,6 @@
}
}
out:
- memset(rng_buffer, 0, rng_buffer_size());
return ret ? : err;
out_unlock_reading:
@@ -427,7 +425,6 @@
/* Outside lock, sure, but y'know: randomness. */
add_hwgenerator_randomness((void *)rng_fillbuf, rc,
rc * current_quality * 8 >> 10);
- memset(rng_fillbuf, 0, rng_buffer_size());
}
hwrng_fill = NULL;
return 0;
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 5bb1985..6d9cc2d 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -381,9 +381,6 @@
char *kbuf; /* k-addr because vread() takes vmlist_lock rwlock */
int err = 0;
- if (!pfn_valid(PFN_DOWN(p)))
- return -EIO;
-
read = 0;
if (p < (unsigned long) high_memory) {
low_count = count;
@@ -412,6 +409,8 @@
* by the kernel or data corruption may occur
*/
kbuf = xlate_dev_kmem_ptr((void *)p);
+ if (!virt_addr_valid(kbuf))
+ return -ENXIO;
if (copy_to_user(buf, kbuf, sz))
return -EFAULT;
@@ -482,6 +481,8 @@
* corruption may occur.
*/
ptr = xlate_dev_kmem_ptr((void *)p);
+ if (!virt_addr_valid(ptr))
+ return -ENXIO;
copied = copy_from_user(ptr, buf, sz);
if (copied) {
@@ -512,9 +513,6 @@
char *kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */
int err = 0;
- if (!pfn_valid(PFN_DOWN(p)))
- return -EIO;
-
if (p < (unsigned long) high_memory) {
unsigned long to_write = min_t(unsigned long, count,
(unsigned long)high_memory - p);
diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index 02819e0..87885d1 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -290,6 +290,7 @@
struct pardevice *pdev = NULL;
char *name;
struct pardev_cb ppdev_cb;
+ int rc = 0;
name = kasprintf(GFP_KERNEL, CHRDEV "%x", minor);
if (name == NULL)
@@ -298,8 +299,8 @@
port = parport_find_number(minor);
if (!port) {
pr_warn("%s: no associated port!\n", name);
- kfree(name);
- return -ENXIO;
+ rc = -ENXIO;
+ goto err;
}
memset(&ppdev_cb, 0, sizeof(ppdev_cb));
@@ -308,16 +309,18 @@
ppdev_cb.private = pp;
pdev = parport_register_dev_model(port, name, &ppdev_cb, minor);
parport_put_port(port);
- kfree(name);
if (!pdev) {
pr_warn("%s: failed to register device!\n", name);
- return -ENXIO;
+ rc = -ENXIO;
+ goto err;
}
pp->pdev = pdev;
dev_dbg(&pdev->dev, "registered pardevice\n");
- return 0;
+err:
+ kfree(name);
+ return rc;
}
static enum ieee1284_phase init_phase(int mode)
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 8b00e79..17857be 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1862,7 +1862,7 @@
{
struct ports_device *portdev;
- portdev = container_of(work, struct ports_device, control_work);
+ portdev = container_of(work, struct ports_device, config_work);
if (!use_multiport(portdev)) {
struct virtio_device *vdev;
struct port *port;
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index 8c8b495..cdc092a 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -586,7 +586,7 @@
GATE(CLK_ACLK550_CAM, "aclk550_cam", "mout_user_aclk550_cam",
GATE_BUS_TOP, 24, 0, 0),
GATE(CLK_ACLK432_SCALER, "aclk432_scaler", "mout_user_aclk432_scaler",
- GATE_BUS_TOP, 27, 0, 0),
+ GATE_BUS_TOP, 27, CLK_IS_CRITICAL, 0),
};
static const struct samsung_mux_clock exynos5420_mux_clks[] __initconst = {
@@ -956,20 +956,20 @@
GATE(CLK_SMMU_G2D, "smmu_g2d", "aclk333_g2d", GATE_IP_G2D, 7, 0, 0),
GATE(0, "aclk200_fsys", "mout_user_aclk200_fsys",
- GATE_BUS_FSYS0, 9, CLK_IGNORE_UNUSED, 0),
+ GATE_BUS_FSYS0, 9, CLK_IS_CRITICAL, 0),
GATE(0, "aclk200_fsys2", "mout_user_aclk200_fsys2",
GATE_BUS_FSYS0, 10, CLK_IGNORE_UNUSED, 0),
GATE(0, "aclk333_g2d", "mout_user_aclk333_g2d",
GATE_BUS_TOP, 0, CLK_IGNORE_UNUSED, 0),
GATE(0, "aclk266_g2d", "mout_user_aclk266_g2d",
- GATE_BUS_TOP, 1, CLK_IGNORE_UNUSED, 0),
+ GATE_BUS_TOP, 1, CLK_IS_CRITICAL, 0),
GATE(0, "aclk300_jpeg", "mout_user_aclk300_jpeg",
GATE_BUS_TOP, 4, CLK_IGNORE_UNUSED, 0),
GATE(0, "aclk333_432_isp0", "mout_user_aclk333_432_isp0",
GATE_BUS_TOP, 5, 0, 0),
GATE(0, "aclk300_gscl", "mout_user_aclk300_gscl",
- GATE_BUS_TOP, 6, CLK_IGNORE_UNUSED, 0),
+ GATE_BUS_TOP, 6, CLK_IS_CRITICAL, 0),
GATE(0, "aclk333_432_gscl", "mout_user_aclk333_432_gscl",
GATE_BUS_TOP, 7, CLK_IGNORE_UNUSED, 0),
GATE(0, "aclk333_432_isp", "mout_user_aclk333_432_isp",
@@ -983,20 +983,20 @@
GATE(0, "aclk166", "mout_user_aclk166",
GATE_BUS_TOP, 14, CLK_IGNORE_UNUSED, 0),
GATE(CLK_ACLK333, "aclk333", "mout_user_aclk333",
- GATE_BUS_TOP, 15, CLK_IGNORE_UNUSED, 0),
+ GATE_BUS_TOP, 15, CLK_IS_CRITICAL, 0),
GATE(0, "aclk400_isp", "mout_user_aclk400_isp",
GATE_BUS_TOP, 16, 0, 0),
GATE(0, "aclk400_mscl", "mout_user_aclk400_mscl",
GATE_BUS_TOP, 17, 0, 0),
GATE(0, "aclk200_disp1", "mout_user_aclk200_disp1",
- GATE_BUS_TOP, 18, 0, 0),
+ GATE_BUS_TOP, 18, CLK_IS_CRITICAL, 0),
GATE(CLK_SCLK_MPHY_IXTAL24, "sclk_mphy_ixtal24", "mphy_refclk_ixtal24",
GATE_BUS_TOP, 28, 0, 0),
GATE(CLK_SCLK_HSIC_12M, "sclk_hsic_12m", "ff_hsic_12m",
GATE_BUS_TOP, 29, 0, 0),
GATE(0, "aclk300_disp1", "mout_user_aclk300_disp1",
- SRC_MASK_TOP2, 24, 0, 0),
+ SRC_MASK_TOP2, 24, CLK_IS_CRITICAL, 0),
GATE(CLK_MAU_EPLL, "mau_epll", "mout_mau_epll_clk",
SRC_MASK_TOP7, 20, 0, 0),
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 4866f7a..3356ab8 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -5,6 +5,10 @@
bool
select CLKSRC_PROBE
+config CLKEVT_OF
+ bool
+ select CLKEVT_PROBE
+
config CLKSRC_ACPI
bool
select CLKSRC_PROBE
@@ -12,6 +16,9 @@
config CLKSRC_PROBE
bool
+config CLKEVT_PROBE
+ bool
+
config CLKSRC_I8253
bool
@@ -60,6 +67,16 @@
select DW_APB_TIMER
select CLKSRC_OF
+config GEMINI_TIMER
+ bool "Cortina Gemini timer driver" if COMPILE_TEST
+ depends on GENERIC_CLOCKEVENTS
+ depends on HAS_IOMEM
+ select CLKSRC_MMIO
+ select CLKSRC_OF
+ select MFD_SYSCON
+ help
+ Enables support for the Gemini timer
+
config ROCKCHIP_TIMER
bool "Rockchip timer driver" if COMPILE_TEST
depends on ARM || ARM64
@@ -325,16 +342,30 @@
This must be disabled for hardware validation purposes to detect any
hardware anomalies of missing events.
+config ARM_ARCH_TIMER_OOL_WORKAROUND
+ bool
+
config FSL_ERRATUM_A008585
bool "Workaround for Freescale/NXP Erratum A-008585"
default y
depends on ARM_ARCH_TIMER && ARM64
+ select ARM_ARCH_TIMER_OOL_WORKAROUND
help
This option enables a workaround for Freescale/NXP Erratum
A-008585 ("ARM generic timer may contain an erroneous
value"). The workaround will only be active if the
fsl,erratum-a008585 property is found in the timer node.
+config HISILICON_ERRATUM_161010101
+ bool "Workaround for Hisilicon Erratum 161010101"
+ default y
+ select ARM_ARCH_TIMER_OOL_WORKAROUND
+ depends on ARM_ARCH_TIMER && ARM64
+ help
+ This option enables a workaround for Hisilicon Erratum
+ 161010101. The workaround will be active if the hisilicon,erratum-161010101
+ property is found in the timer node.
+
config ARM_GLOBAL_TIMER
bool "Support for the ARM global timer" if COMPILE_TEST
select CLKSRC_OF if OF
@@ -467,6 +498,13 @@
Timer Pulse Unit 2 (MTU2) hardware available on SoCs from Renesas.
This hardware comes with 16 bit-timer registers.
+config RENESAS_OSTM
+ bool "Renesas OSTM timer driver" if COMPILE_TEST
+ depends on GENERIC_CLOCKEVENTS
+ select CLKSRC_MMIO
+ help
+ Enables the support for the Renesas OSTM.
+
config SH_TIMER_TMU
bool "Renesas TMU timer driver" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index a14111e..d227d13 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -1,4 +1,5 @@
obj-$(CONFIG_CLKSRC_PROBE) += clksrc-probe.o
+obj-$(CONFIG_CLKEVT_PROBE) += clkevt-probe.o
obj-$(CONFIG_ATMEL_PIT) += timer-atmel-pit.o
obj-$(CONFIG_ATMEL_ST) += timer-atmel-st.o
obj-$(CONFIG_ATMEL_TCB_CLKSRC) += tcb_clksrc.o
@@ -8,6 +9,7 @@
obj-$(CONFIG_CLKSRC_JCORE_PIT) += jcore-pit.o
obj-$(CONFIG_SH_TIMER_CMT) += sh_cmt.o
obj-$(CONFIG_SH_TIMER_MTU2) += sh_mtu2.o
+obj-$(CONFIG_RENESAS_OSTM) += renesas-ostm.o
obj-$(CONFIG_SH_TIMER_TMU) += sh_tmu.o
obj-$(CONFIG_EM_TIMER_STI) += em_sti.o
obj-$(CONFIG_CLKBLD_I8253) += i8253.o
@@ -15,6 +17,7 @@
obj-$(CONFIG_DIGICOLOR_TIMER) += timer-digicolor.o
obj-$(CONFIG_DW_APB_TIMER) += dw_apb_timer.o
obj-$(CONFIG_DW_APB_TIMER_OF) += dw_apb_timer_of.o
+obj-$(CONFIG_GEMINI_TIMER) += timer-gemini.o
obj-$(CONFIG_ROCKCHIP_TIMER) += rockchip_timer.o
obj-$(CONFIG_CLKSRC_NOMADIK_MTU) += nomadik-mtu.o
obj-$(CONFIG_CLKSRC_DBX500_PRCMU) += clksrc-dbx500-prcmu.o
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 4c8c3fb..93aa136 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -96,41 +96,107 @@
*/
#ifdef CONFIG_FSL_ERRATUM_A008585
-DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
-EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+/*
+ * The number of retries is an arbitrary value well beyond the highest number
+ * of iterations the loop has been observed to take.
+ */
+#define __fsl_a008585_read_reg(reg) ({ \
+ u64 _old, _new; \
+ int _retries = 200; \
+ \
+ do { \
+ _old = read_sysreg(reg); \
+ _new = read_sysreg(reg); \
+ _retries--; \
+ } while (unlikely(_old != _new) && _retries); \
+ \
+ WARN_ON_ONCE(!_retries); \
+ _new; \
+})
-static int fsl_a008585_enable = -1;
-
-static int __init early_fsl_a008585_cfg(char *buf)
-{
- int ret;
- bool val;
-
- ret = strtobool(buf, &val);
- if (ret)
- return ret;
-
- fsl_a008585_enable = val;
- return 0;
-}
-early_param("clocksource.arm_arch_timer.fsl-a008585", early_fsl_a008585_cfg);
-
-u32 __fsl_a008585_read_cntp_tval_el0(void)
+static u32 notrace fsl_a008585_read_cntp_tval_el0(void)
{
return __fsl_a008585_read_reg(cntp_tval_el0);
}
-u32 __fsl_a008585_read_cntv_tval_el0(void)
+static u32 notrace fsl_a008585_read_cntv_tval_el0(void)
{
return __fsl_a008585_read_reg(cntv_tval_el0);
}
-u64 __fsl_a008585_read_cntvct_el0(void)
+static u64 notrace fsl_a008585_read_cntvct_el0(void)
{
return __fsl_a008585_read_reg(cntvct_el0);
}
-EXPORT_SYMBOL(__fsl_a008585_read_cntvct_el0);
-#endif /* CONFIG_FSL_ERRATUM_A008585 */
+#endif
+
+#ifdef CONFIG_HISILICON_ERRATUM_161010101
+/*
+ * Verify whether the value of the second read is larger than the first by
+ * less than 32 is the only way to confirm the value is correct, so clear the
+ * lower 5 bits to check whether the difference is greater than 32 or not.
+ * Theoretically the erratum should not occur more than twice in succession
+ * when reading the system counter, but it is possible that some interrupts
+ * may lead to more than twice read errors, triggering the warning, so setting
+ * the number of retries far beyond the number of iterations the loop has been
+ * observed to take.
+ */
+#define __hisi_161010101_read_reg(reg) ({ \
+ u64 _old, _new; \
+ int _retries = 50; \
+ \
+ do { \
+ _old = read_sysreg(reg); \
+ _new = read_sysreg(reg); \
+ _retries--; \
+ } while (unlikely((_new - _old) >> 5) && _retries); \
+ \
+ WARN_ON_ONCE(!_retries); \
+ _new; \
+})
+
+static u32 notrace hisi_161010101_read_cntp_tval_el0(void)
+{
+ return __hisi_161010101_read_reg(cntp_tval_el0);
+}
+
+static u32 notrace hisi_161010101_read_cntv_tval_el0(void)
+{
+ return __hisi_161010101_read_reg(cntv_tval_el0);
+}
+
+static u64 notrace hisi_161010101_read_cntvct_el0(void)
+{
+ return __hisi_161010101_read_reg(cntvct_el0);
+}
+#endif
+
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
+const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround = NULL;
+EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
+
+DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
+EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+
+static const struct arch_timer_erratum_workaround ool_workarounds[] = {
+#ifdef CONFIG_FSL_ERRATUM_A008585
+ {
+ .id = "fsl,erratum-a008585",
+ .read_cntp_tval_el0 = fsl_a008585_read_cntp_tval_el0,
+ .read_cntv_tval_el0 = fsl_a008585_read_cntv_tval_el0,
+ .read_cntvct_el0 = fsl_a008585_read_cntvct_el0,
+ },
+#endif
+#ifdef CONFIG_HISILICON_ERRATUM_161010101
+ {
+ .id = "hisilicon,erratum-161010101",
+ .read_cntp_tval_el0 = hisi_161010101_read_cntp_tval_el0,
+ .read_cntv_tval_el0 = hisi_161010101_read_cntv_tval_el0,
+ .read_cntvct_el0 = hisi_161010101_read_cntvct_el0,
+ },
+#endif
+};
+#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
static __always_inline
void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
@@ -281,8 +347,8 @@
arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
}
-#ifdef CONFIG_FSL_ERRATUM_A008585
-static __always_inline void fsl_a008585_set_next_event(const int access,
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
+static __always_inline void erratum_set_next_event_generic(const int access,
unsigned long evt, struct clock_event_device *clk)
{
unsigned long ctrl;
@@ -300,20 +366,20 @@
arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
}
-static int fsl_a008585_set_next_event_virt(unsigned long evt,
+static int erratum_set_next_event_virt(unsigned long evt,
struct clock_event_device *clk)
{
- fsl_a008585_set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
+ erratum_set_next_event_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk);
return 0;
}
-static int fsl_a008585_set_next_event_phys(unsigned long evt,
+static int erratum_set_next_event_phys(unsigned long evt,
struct clock_event_device *clk)
{
- fsl_a008585_set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
+ erratum_set_next_event_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk);
return 0;
}
-#endif /* CONFIG_FSL_ERRATUM_A008585 */
+#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
static int arch_timer_set_next_event_virt(unsigned long evt,
struct clock_event_device *clk)
@@ -343,16 +409,16 @@
return 0;
}
-static void fsl_a008585_set_sne(struct clock_event_device *clk)
+static void erratum_workaround_set_sne(struct clock_event_device *clk)
{
-#ifdef CONFIG_FSL_ERRATUM_A008585
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
if (!static_branch_unlikely(&arch_timer_read_ool_enabled))
return;
if (arch_timer_uses_ppi == VIRT_PPI)
- clk->set_next_event = fsl_a008585_set_next_event_virt;
+ clk->set_next_event = erratum_set_next_event_virt;
else
- clk->set_next_event = fsl_a008585_set_next_event_phys;
+ clk->set_next_event = erratum_set_next_event_phys;
#endif
}
@@ -385,7 +451,7 @@
BUG();
}
- fsl_a008585_set_sne(clk);
+ erratum_workaround_set_sne(clk);
} else {
clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
clk->name = "arch_mem_timer";
@@ -580,7 +646,7 @@
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
-static struct cyclecounter cyclecounter = {
+static struct cyclecounter cyclecounter __ro_after_init = {
.read = arch_counter_read_cc,
.mask = CLOCKSOURCE_MASK(56),
};
@@ -605,7 +671,7 @@
clocksource_counter.archdata.vdso_direct = true;
-#ifdef CONFIG_FSL_ERRATUM_A008585
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
/*
* Don't use the vdso fastpath if errata require using
* the out-of-line counter accessor.
@@ -893,12 +959,15 @@
arch_timer_c3stop = !of_property_read_bool(np, "always-on");
-#ifdef CONFIG_FSL_ERRATUM_A008585
- if (fsl_a008585_enable < 0)
- fsl_a008585_enable = of_property_read_bool(np, "fsl,erratum-a008585");
- if (fsl_a008585_enable) {
- static_branch_enable(&arch_timer_read_ool_enabled);
- pr_info("Enabling workaround for FSL erratum A-008585\n");
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
+ for (i = 0; i < ARRAY_SIZE(ool_workarounds); i++) {
+ if (of_property_read_bool(np, ool_workarounds[i].id)) {
+ timer_unstable_counter_workaround = &ool_workarounds[i];
+ static_branch_enable(&arch_timer_read_ool_enabled);
+ pr_info("arch_timer: Enabling workaround for %s\n",
+ timer_unstable_counter_workaround->id);
+ break;
+ }
}
#endif
diff --git a/drivers/clocksource/clkevt-probe.c b/drivers/clocksource/clkevt-probe.c
new file mode 100644
index 0000000..8c30fec
--- /dev/null
+++ b/drivers/clocksource/clkevt-probe.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2016, Linaro Ltd. All rights reserved.
+ * Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/clockchip.h>
+
+extern struct of_device_id __clkevt_of_table[];
+
+static const struct of_device_id __clkevt_of_table_sentinel
+ __used __section(__clkevt_of_table_end);
+
+int __init clockevent_probe(void)
+{
+ struct device_node *np;
+ const struct of_device_id *match;
+ of_init_fn_1_ret init_func;
+ int ret, clockevents = 0;
+
+ for_each_matching_node_and_match(np, __clkevt_of_table, &match) {
+ if (!of_device_is_available(np))
+ continue;
+
+ init_func = match->data;
+
+ ret = init_func(np);
+ if (ret) {
+ pr_warn("Failed to initialize '%s' (%d)\n",
+ np->name, ret);
+ continue;
+ }
+
+ clockevents++;
+ }
+
+ if (!clockevents) {
+ pr_crit("%s: no matching clockevent found\n", __func__);
+ return -ENODEV;
+ }
+
+ return 0;
+}
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 4da1dc2..670ff0f 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -495,6 +495,7 @@
if (mct_int_type == MCT_INT_SPI) {
if (evt->irq != -1)
disable_irq_nosync(evt->irq);
+ exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
} else {
disable_percpu_irq(mct_irqs[MCT_L0_IRQ]);
}
diff --git a/drivers/clocksource/renesas-ostm.c b/drivers/clocksource/renesas-ostm.c
new file mode 100644
index 0000000..c76f576
--- /dev/null
+++ b/drivers/clocksource/renesas-ostm.c
@@ -0,0 +1,265 @@
+/*
+ * Renesas Timer Support - OSTM
+ *
+ * Copyright (C) 2017 Renesas Electronics America, Inc.
+ * Copyright (C) 2017 Chris Brandt
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+
+/*
+ * The OSTM contains independent channels.
+ * The first OSTM channel probed will be set up as a free running
+ * clocksource. Additionally we will use this clocksource for the system
+ * schedule timer sched_clock().
+ *
+ * The second (or more) channel probed will be set up as an interrupt
+ * driven clock event.
+ */
+
+struct ostm_device {
+ void __iomem *base;
+ unsigned long ticks_per_jiffy;
+ struct clock_event_device ced;
+};
+
+static void __iomem *system_clock; /* For sched_clock() */
+
+/* OSTM REGISTERS */
+#define OSTM_CMP 0x000 /* RW,32 */
+#define OSTM_CNT 0x004 /* R,32 */
+#define OSTM_TE 0x010 /* R,8 */
+#define OSTM_TS 0x014 /* W,8 */
+#define OSTM_TT 0x018 /* W,8 */
+#define OSTM_CTL 0x020 /* RW,8 */
+
+#define TE 0x01
+#define TS 0x01
+#define TT 0x01
+#define CTL_PERIODIC 0x00
+#define CTL_ONESHOT 0x02
+#define CTL_FREERUN 0x02
+
+static struct ostm_device *ced_to_ostm(struct clock_event_device *ced)
+{
+ return container_of(ced, struct ostm_device, ced);
+}
+
+static void ostm_timer_stop(struct ostm_device *ostm)
+{
+ if (readb(ostm->base + OSTM_TE) & TE) {
+ writeb(TT, ostm->base + OSTM_TT);
+
+ /*
+ * Read back the register simply to confirm the write operation
+ * has completed since I/O writes can sometimes get queued by
+ * the bus architecture.
+ */
+ while (readb(ostm->base + OSTM_TE) & TE)
+ ;
+ }
+}
+
+static int __init ostm_init_clksrc(struct ostm_device *ostm, unsigned long rate)
+{
+ /*
+ * irq not used (clock sources don't use interrupts)
+ */
+
+ ostm_timer_stop(ostm);
+
+ writel(0, ostm->base + OSTM_CMP);
+ writeb(CTL_FREERUN, ostm->base + OSTM_CTL);
+ writeb(TS, ostm->base + OSTM_TS);
+
+ return clocksource_mmio_init(ostm->base + OSTM_CNT,
+ "ostm", rate,
+ 300, 32, clocksource_mmio_readl_up);
+}
+
+static u64 notrace ostm_read_sched_clock(void)
+{
+ return readl(system_clock);
+}
+
+static void __init ostm_init_sched_clock(struct ostm_device *ostm,
+ unsigned long rate)
+{
+ system_clock = ostm->base + OSTM_CNT;
+ sched_clock_register(ostm_read_sched_clock, 32, rate);
+}
+
+static int ostm_clock_event_next(unsigned long delta,
+ struct clock_event_device *ced)
+{
+ struct ostm_device *ostm = ced_to_ostm(ced);
+
+ ostm_timer_stop(ostm);
+
+ writel(delta, ostm->base + OSTM_CMP);
+ writeb(CTL_ONESHOT, ostm->base + OSTM_CTL);
+ writeb(TS, ostm->base + OSTM_TS);
+
+ return 0;
+}
+
+static int ostm_shutdown(struct clock_event_device *ced)
+{
+ struct ostm_device *ostm = ced_to_ostm(ced);
+
+ ostm_timer_stop(ostm);
+
+ return 0;
+}
+static int ostm_set_periodic(struct clock_event_device *ced)
+{
+ struct ostm_device *ostm = ced_to_ostm(ced);
+
+ if (clockevent_state_oneshot(ced) || clockevent_state_periodic(ced))
+ ostm_timer_stop(ostm);
+
+ writel(ostm->ticks_per_jiffy - 1, ostm->base + OSTM_CMP);
+ writeb(CTL_PERIODIC, ostm->base + OSTM_CTL);
+ writeb(TS, ostm->base + OSTM_TS);
+
+ return 0;
+}
+
+static int ostm_set_oneshot(struct clock_event_device *ced)
+{
+ struct ostm_device *ostm = ced_to_ostm(ced);
+
+ ostm_timer_stop(ostm);
+
+ return 0;
+}
+
+static irqreturn_t ostm_timer_interrupt(int irq, void *dev_id)
+{
+ struct ostm_device *ostm = dev_id;
+
+ if (clockevent_state_oneshot(&ostm->ced))
+ ostm_timer_stop(ostm);
+
+ /* notify clockevent layer */
+ if (ostm->ced.event_handler)
+ ostm->ced.event_handler(&ostm->ced);
+
+ return IRQ_HANDLED;
+}
+
+static int __init ostm_init_clkevt(struct ostm_device *ostm, int irq,
+ unsigned long rate)
+{
+ struct clock_event_device *ced = &ostm->ced;
+ int ret = -ENXIO;
+
+ ret = request_irq(irq, ostm_timer_interrupt,
+ IRQF_TIMER | IRQF_IRQPOLL,
+ "ostm", ostm);
+ if (ret) {
+ pr_err("ostm: failed to request irq\n");
+ return ret;
+ }
+
+ ced->name = "ostm";
+ ced->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC;
+ ced->set_state_shutdown = ostm_shutdown;
+ ced->set_state_periodic = ostm_set_periodic;
+ ced->set_state_oneshot = ostm_set_oneshot;
+ ced->set_next_event = ostm_clock_event_next;
+ ced->shift = 32;
+ ced->rating = 300;
+ ced->cpumask = cpumask_of(0);
+ clockevents_config_and_register(ced, rate, 0xf, 0xffffffff);
+
+ return 0;
+}
+
+static int __init ostm_init(struct device_node *np)
+{
+ struct ostm_device *ostm;
+ int ret = -EFAULT;
+ struct clk *ostm_clk = NULL;
+ int irq;
+ unsigned long rate;
+
+ ostm = kzalloc(sizeof(*ostm), GFP_KERNEL);
+ if (!ostm)
+ return -ENOMEM;
+
+ ostm->base = of_iomap(np, 0);
+ if (!ostm->base) {
+ pr_err("ostm: failed to remap I/O memory\n");
+ goto err;
+ }
+
+ irq = irq_of_parse_and_map(np, 0);
+ if (irq < 0) {
+ pr_err("ostm: Failed to get irq\n");
+ goto err;
+ }
+
+ ostm_clk = of_clk_get(np, 0);
+ if (IS_ERR(ostm_clk)) {
+ pr_err("ostm: Failed to get clock\n");
+ ostm_clk = NULL;
+ goto err;
+ }
+
+ ret = clk_prepare_enable(ostm_clk);
+ if (ret) {
+ pr_err("ostm: Failed to enable clock\n");
+ goto err;
+ }
+
+ rate = clk_get_rate(ostm_clk);
+ ostm->ticks_per_jiffy = (rate + HZ / 2) / HZ;
+
+ /*
+ * First probed device will be used as system clocksource. Any
+ * additional devices will be used as clock events.
+ */
+ if (!system_clock) {
+ ret = ostm_init_clksrc(ostm, rate);
+
+ if (!ret) {
+ ostm_init_sched_clock(ostm, rate);
+ pr_info("ostm: used for clocksource\n");
+ }
+
+ } else {
+ ret = ostm_init_clkevt(ostm, irq, rate);
+
+ if (!ret)
+ pr_info("ostm: used for clock events\n");
+ }
+
+err:
+ if (ret) {
+ clk_disable_unprepare(ostm_clk);
+ iounmap(ostm->base);
+ kfree(ostm);
+ return ret;
+ }
+
+ return 0;
+}
+
+CLOCKSOURCE_OF_DECLARE(ostm, "renesas,ostm", ostm_init);
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index d4ca996..745844e 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -10,6 +10,7 @@
#include <linux/io.h>
#include <linux/platform_device.h>
#include <linux/atmel_tc.h>
+#include <linux/sched_clock.h>
/*
@@ -56,11 +57,16 @@
return (upper << 16) | lower;
}
-static u64 tc_get_cycles32(struct clocksource *cs)
+static u32 tc_get_cv32(void)
{
return __raw_readl(tcaddr + ATMEL_TC_REG(0, CV));
}
+static u64 tc_get_cycles32(struct clocksource *cs)
+{
+ return tc_get_cv32();
+}
+
static struct clocksource clksrc = {
.name = "tcb_clksrc",
.rating = 200,
@@ -69,6 +75,11 @@
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
+static u64 notrace tc_read_sched_clock(void)
+{
+ return tc_get_cv32();
+}
+
#ifdef CONFIG_GENERIC_CLOCKEVENTS
struct tc_clkevt_device {
@@ -339,6 +350,9 @@
clksrc.read = tc_get_cycles32;
/* setup ony channel 0 */
tcb_setup_single_chan(tc, best_divisor_idx);
+
+ /* register sched_clock on chips with single 32 bit counter */
+ sched_clock_register(tc_read_sched_clock, 32, divided_rate);
} else {
/* tclib will give us three clocks no matter what the
* underlying platform supports.
diff --git a/drivers/clocksource/timer-gemini.c b/drivers/clocksource/timer-gemini.c
new file mode 100644
index 0000000..dda27b7
--- /dev/null
+++ b/drivers/clocksource/timer-gemini.c
@@ -0,0 +1,277 @@
+/*
+ * Gemini timer driver
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * Based on a rewrite of arch/arm/mach-gemini/timer.c:
+ * Copyright (C) 2001-2006 Storlink, Corp.
+ * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
+ */
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/sched_clock.h>
+
+/*
+ * Relevant registers in the global syscon
+ */
+#define GLOBAL_STATUS 0x04
+#define CPU_AHB_RATIO_MASK (0x3 << 18)
+#define CPU_AHB_1_1 (0x0 << 18)
+#define CPU_AHB_3_2 (0x1 << 18)
+#define CPU_AHB_24_13 (0x2 << 18)
+#define CPU_AHB_2_1 (0x3 << 18)
+#define REG_TO_AHB_SPEED(reg) ((((reg) >> 15) & 0x7) * 10 + 130)
+
+/*
+ * Register definitions for the timers
+ */
+#define TIMER1_COUNT (0x00)
+#define TIMER1_LOAD (0x04)
+#define TIMER1_MATCH1 (0x08)
+#define TIMER1_MATCH2 (0x0c)
+#define TIMER2_COUNT (0x10)
+#define TIMER2_LOAD (0x14)
+#define TIMER2_MATCH1 (0x18)
+#define TIMER2_MATCH2 (0x1c)
+#define TIMER3_COUNT (0x20)
+#define TIMER3_LOAD (0x24)
+#define TIMER3_MATCH1 (0x28)
+#define TIMER3_MATCH2 (0x2c)
+#define TIMER_CR (0x30)
+#define TIMER_INTR_STATE (0x34)
+#define TIMER_INTR_MASK (0x38)
+
+#define TIMER_1_CR_ENABLE (1 << 0)
+#define TIMER_1_CR_CLOCK (1 << 1)
+#define TIMER_1_CR_INT (1 << 2)
+#define TIMER_2_CR_ENABLE (1 << 3)
+#define TIMER_2_CR_CLOCK (1 << 4)
+#define TIMER_2_CR_INT (1 << 5)
+#define TIMER_3_CR_ENABLE (1 << 6)
+#define TIMER_3_CR_CLOCK (1 << 7)
+#define TIMER_3_CR_INT (1 << 8)
+#define TIMER_1_CR_UPDOWN (1 << 9)
+#define TIMER_2_CR_UPDOWN (1 << 10)
+#define TIMER_3_CR_UPDOWN (1 << 11)
+#define TIMER_DEFAULT_FLAGS (TIMER_1_CR_UPDOWN | \
+ TIMER_3_CR_ENABLE | \
+ TIMER_3_CR_UPDOWN)
+
+#define TIMER_1_INT_MATCH1 (1 << 0)
+#define TIMER_1_INT_MATCH2 (1 << 1)
+#define TIMER_1_INT_OVERFLOW (1 << 2)
+#define TIMER_2_INT_MATCH1 (1 << 3)
+#define TIMER_2_INT_MATCH2 (1 << 4)
+#define TIMER_2_INT_OVERFLOW (1 << 5)
+#define TIMER_3_INT_MATCH1 (1 << 6)
+#define TIMER_3_INT_MATCH2 (1 << 7)
+#define TIMER_3_INT_OVERFLOW (1 << 8)
+#define TIMER_INT_ALL_MASK 0x1ff
+
+static unsigned int tick_rate;
+static void __iomem *base;
+
+static u64 notrace gemini_read_sched_clock(void)
+{
+ return readl(base + TIMER3_COUNT);
+}
+
+static int gemini_timer_set_next_event(unsigned long cycles,
+ struct clock_event_device *evt)
+{
+ u32 cr;
+
+ /* Setup the match register */
+ cr = readl(base + TIMER1_COUNT);
+ writel(cr + cycles, base + TIMER1_MATCH1);
+ if (readl(base + TIMER1_COUNT) - cr > cycles)
+ return -ETIME;
+
+ return 0;
+}
+
+static int gemini_timer_shutdown(struct clock_event_device *evt)
+{
+ u32 cr;
+
+ /*
+ * Disable also for oneshot: the set_next() call will arm the timer
+ * instead.
+ */
+ /* Stop timer and interrupt. */
+ cr = readl(base + TIMER_CR);
+ cr &= ~(TIMER_1_CR_ENABLE | TIMER_1_CR_INT);
+ writel(cr, base + TIMER_CR);
+
+ /* Setup counter start from 0 */
+ writel(0, base + TIMER1_COUNT);
+ writel(0, base + TIMER1_LOAD);
+
+ /* enable interrupt */
+ cr = readl(base + TIMER_INTR_MASK);
+ cr &= ~(TIMER_1_INT_OVERFLOW | TIMER_1_INT_MATCH2);
+ cr |= TIMER_1_INT_MATCH1;
+ writel(cr, base + TIMER_INTR_MASK);
+
+ /* start the timer */
+ cr = readl(base + TIMER_CR);
+ cr |= TIMER_1_CR_ENABLE;
+ writel(cr, base + TIMER_CR);
+
+ return 0;
+}
+
+static int gemini_timer_set_periodic(struct clock_event_device *evt)
+{
+ u32 period = DIV_ROUND_CLOSEST(tick_rate, HZ);
+ u32 cr;
+
+ /* Stop timer and interrupt */
+ cr = readl(base + TIMER_CR);
+ cr &= ~(TIMER_1_CR_ENABLE | TIMER_1_CR_INT);
+ writel(cr, base + TIMER_CR);
+
+ /* Setup timer to fire at 1/HT intervals. */
+ cr = 0xffffffff - (period - 1);
+ writel(cr, base + TIMER1_COUNT);
+ writel(cr, base + TIMER1_LOAD);
+
+ /* enable interrupt on overflow */
+ cr = readl(base + TIMER_INTR_MASK);
+ cr &= ~(TIMER_1_INT_MATCH1 | TIMER_1_INT_MATCH2);
+ cr |= TIMER_1_INT_OVERFLOW;
+ writel(cr, base + TIMER_INTR_MASK);
+
+ /* Start the timer */
+ cr = readl(base + TIMER_CR);
+ cr |= TIMER_1_CR_ENABLE;
+ cr |= TIMER_1_CR_INT;
+ writel(cr, base + TIMER_CR);
+
+ return 0;
+}
+
+/* Use TIMER1 as clock event */
+static struct clock_event_device gemini_clockevent = {
+ .name = "TIMER1",
+ /* Reasonably fast and accurate clock event */
+ .rating = 300,
+ .shift = 32,
+ .features = CLOCK_EVT_FEAT_PERIODIC |
+ CLOCK_EVT_FEAT_ONESHOT,
+ .set_next_event = gemini_timer_set_next_event,
+ .set_state_shutdown = gemini_timer_shutdown,
+ .set_state_periodic = gemini_timer_set_periodic,
+ .set_state_oneshot = gemini_timer_shutdown,
+ .tick_resume = gemini_timer_shutdown,
+};
+
+/*
+ * IRQ handler for the timer
+ */
+static irqreturn_t gemini_timer_interrupt(int irq, void *dev_id)
+{
+ struct clock_event_device *evt = &gemini_clockevent;
+
+ evt->event_handler(evt);
+ return IRQ_HANDLED;
+}
+
+static struct irqaction gemini_timer_irq = {
+ .name = "Gemini Timer Tick",
+ .flags = IRQF_TIMER,
+ .handler = gemini_timer_interrupt,
+};
+
+static int __init gemini_timer_of_init(struct device_node *np)
+{
+ static struct regmap *map;
+ int irq;
+ int ret;
+ u32 val;
+
+ map = syscon_regmap_lookup_by_phandle(np, "syscon");
+ if (IS_ERR(map)) {
+ pr_err("Can't get regmap for syscon handle");
+ return -ENODEV;
+ }
+ ret = regmap_read(map, GLOBAL_STATUS, &val);
+ if (ret) {
+ pr_err("Can't read syscon status register");
+ return -ENXIO;
+ }
+
+ base = of_iomap(np, 0);
+ if (!base) {
+ pr_err("Can't remap registers");
+ return -ENXIO;
+ }
+ /* IRQ for timer 1 */
+ irq = irq_of_parse_and_map(np, 0);
+ if (irq <= 0) {
+ pr_err("Can't parse IRQ");
+ return -EINVAL;
+ }
+
+ tick_rate = REG_TO_AHB_SPEED(val) * 1000000;
+ printk(KERN_INFO "Bus: %dMHz", tick_rate / 1000000);
+
+ tick_rate /= 6; /* APB bus run AHB*(1/6) */
+
+ switch (val & CPU_AHB_RATIO_MASK) {
+ case CPU_AHB_1_1:
+ printk(KERN_CONT "(1/1)\n");
+ break;
+ case CPU_AHB_3_2:
+ printk(KERN_CONT "(3/2)\n");
+ break;
+ case CPU_AHB_24_13:
+ printk(KERN_CONT "(24/13)\n");
+ break;
+ case CPU_AHB_2_1:
+ printk(KERN_CONT "(2/1)\n");
+ break;
+ }
+
+ /*
+ * Reset the interrupt mask and status
+ */
+ writel(TIMER_INT_ALL_MASK, base + TIMER_INTR_MASK);
+ writel(0, base + TIMER_INTR_STATE);
+ writel(TIMER_DEFAULT_FLAGS, base + TIMER_CR);
+
+ /*
+ * Setup free-running clocksource timer (interrupts
+ * disabled.)
+ */
+ writel(0, base + TIMER3_COUNT);
+ writel(0, base + TIMER3_LOAD);
+ writel(0, base + TIMER3_MATCH1);
+ writel(0, base + TIMER3_MATCH2);
+ clocksource_mmio_init(base + TIMER3_COUNT,
+ "gemini_clocksource", tick_rate,
+ 300, 32, clocksource_mmio_readl_up);
+ sched_clock_register(gemini_read_sched_clock, 32, tick_rate);
+
+ /*
+ * Setup clockevent timer (interrupt-driven.)
+ */
+ writel(0, base + TIMER1_COUNT);
+ writel(0, base + TIMER1_LOAD);
+ writel(0, base + TIMER1_MATCH1);
+ writel(0, base + TIMER1_MATCH2);
+ setup_irq(irq, &gemini_timer_irq);
+ gemini_clockevent.cpumask = cpumask_of(0);
+ clockevents_config_and_register(&gemini_clockevent, tick_rate,
+ 1, 0xffffffff);
+
+ return 0;
+}
+CLOCKSOURCE_OF_DECLARE(nomadik_mtu, "cortina,gemini-timer",
+ gemini_timer_of_init);
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index 4fda623..c943606 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -784,8 +784,19 @@
static int brcm_avs_suspend(struct cpufreq_policy *policy)
{
struct private_data *priv = policy->driver_data;
+ int ret;
- return brcm_avs_get_pmap(priv, &priv->pmap);
+ ret = brcm_avs_get_pmap(priv, &priv->pmap);
+ if (ret)
+ return ret;
+
+ /*
+ * We can't use the P-state returned by brcm_avs_get_pmap(), since
+ * that's the initial P-state from when the P-map was downloaded to the
+ * AVS co-processor, not necessarily the P-state we are running at now.
+ * So, we get the current P-state explicitly.
+ */
+ return brcm_avs_get_pstate(priv, &priv->pmap.state);
}
static int brcm_avs_resume(struct cpufreq_policy *policy)
@@ -954,9 +965,9 @@
brcm_avs_parse_p1(pmap.p1, &mdiv_p0, &pdiv, &ndiv);
brcm_avs_parse_p2(pmap.p2, &mdiv_p1, &mdiv_p2, &mdiv_p3, &mdiv_p4);
- return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u\n",
+ return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u %u %u\n",
pmap.p1, pmap.p2, ndiv, pdiv, mdiv_p0, mdiv_p1, mdiv_p2,
- mdiv_p3, mdiv_p4);
+ mdiv_p3, mdiv_p4, pmap.mode, pmap.state);
}
static ssize_t show_brcm_avs_voltage(struct cpufreq_policy *policy, char *buf)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index cc475ef..3e9b319 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -132,7 +132,7 @@
u64 cur_wall_time;
u64 busy_time;
- cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
+ cur_wall_time = jiffies64_to_nsecs(get_jiffies_64());
busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
@@ -143,9 +143,9 @@
idle_time = cur_wall_time - busy_time;
if (wall)
- *wall = cputime_to_usecs(cur_wall_time);
+ *wall = div_u64(cur_wall_time, NSEC_PER_USEC);
- return cputime_to_usecs(idle_time);
+ return div_u64(idle_time, NSEC_PER_USEC);
}
u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 0196467..631bd2c 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -152,7 +152,7 @@
if (ignore_nice) {
u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
- idle_time += cputime_to_usecs(cur_nice - j_cdbs->prev_cpu_nice);
+ idle_time += div_u64(cur_nice - j_cdbs->prev_cpu_nice, NSEC_PER_USEC);
j_cdbs->prev_cpu_nice = cur_nice;
}
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index ac284e6..17048bb 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -13,7 +13,6 @@
#include <linux/cpufreq.h>
#include <linux/module.h>
#include <linux/slab.h>
-#include <linux/cputime.h>
static DEFINE_SPINLOCK(cpufreq_stats_lock);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f91c257..50bd6d9 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1235,6 +1235,25 @@
cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
}
+#define MSR_IA32_POWER_CTL_BIT_EE 19
+
+/* Disable energy efficiency optimization */
+static void intel_pstate_disable_ee(int cpu)
+{
+ u64 power_ctl;
+ int ret;
+
+ ret = rdmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, &power_ctl);
+ if (ret)
+ return;
+
+ if (!(power_ctl & BIT(MSR_IA32_POWER_CTL_BIT_EE))) {
+ pr_info("Disabling energy efficiency optimization\n");
+ power_ctl |= BIT(MSR_IA32_POWER_CTL_BIT_EE);
+ wrmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, power_ctl);
+ }
+}
+
static int atom_get_min_pstate(void)
{
u64 value;
@@ -1845,6 +1864,11 @@
{}
};
+static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
+ ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_params),
+ {}
+};
+
static int intel_pstate_init_cpu(unsigned int cpunum)
{
struct cpudata *cpu;
@@ -1875,6 +1899,12 @@
cpu->cpu = cpunum;
if (hwp_active) {
+ const struct x86_cpu_id *id;
+
+ id = x86_match_cpu(intel_pstate_cpu_ee_disable_ids);
+ if (id)
+ intel_pstate_disable_ee(cpunum);
+
intel_pstate_hwp_enable(cpu);
pid_params.sample_rate_ms = 50;
pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
@@ -2005,7 +2035,8 @@
limits = &performance_limits;
perf_limits = limits;
}
- if (policy->max >= policy->cpuinfo.max_freq) {
+ if (policy->max >= policy->cpuinfo.max_freq &&
+ !limits->no_turbo) {
pr_debug("set performance\n");
intel_pstate_set_performance_limits(perf_limits);
goto out;
@@ -2047,6 +2078,17 @@
policy->policy != CPUFREQ_POLICY_PERFORMANCE)
return -EINVAL;
+ /* When per-CPU limits are used, sysfs limits are not used */
+ if (!per_cpu_limits) {
+ unsigned int max_freq, min_freq;
+
+ max_freq = policy->cpuinfo.max_freq *
+ limits->max_sysfs_pct / 100;
+ min_freq = policy->cpuinfo.max_freq *
+ limits->min_sysfs_pct / 100;
+ cpufreq_verify_within_limits(policy, min_freq, max_freq);
+ }
+
return 0;
}
diff --git a/drivers/crypto/ccp/ccp-dev-v5.c b/drivers/crypto/ccp/ccp-dev-v5.c
index e2ce819..612898b 100644
--- a/drivers/crypto/ccp/ccp-dev-v5.c
+++ b/drivers/crypto/ccp/ccp-dev-v5.c
@@ -959,7 +959,7 @@
static void ccp5_config(struct ccp_device *ccp)
{
/* Public side */
- iowrite32(0x00001249, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET);
+ iowrite32(0x0, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET);
}
static void ccp5other_config(struct ccp_device *ccp)
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 830f35e..649e561 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -238,6 +238,7 @@
struct ccp_device *ccp;
spinlock_t lock;
+ struct list_head created;
struct list_head pending;
struct list_head active;
struct list_head complete;
diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c
index 6553912..e5d9278 100644
--- a/drivers/crypto/ccp/ccp-dmaengine.c
+++ b/drivers/crypto/ccp/ccp-dmaengine.c
@@ -63,6 +63,7 @@
ccp_free_desc_resources(chan->ccp, &chan->complete);
ccp_free_desc_resources(chan->ccp, &chan->active);
ccp_free_desc_resources(chan->ccp, &chan->pending);
+ ccp_free_desc_resources(chan->ccp, &chan->created);
spin_unlock_irqrestore(&chan->lock, flags);
}
@@ -273,6 +274,7 @@
spin_lock_irqsave(&chan->lock, flags);
cookie = dma_cookie_assign(tx_desc);
+ list_del(&desc->entry);
list_add_tail(&desc->entry, &chan->pending);
spin_unlock_irqrestore(&chan->lock, flags);
@@ -426,7 +428,7 @@
spin_lock_irqsave(&chan->lock, sflags);
- list_add_tail(&desc->entry, &chan->pending);
+ list_add_tail(&desc->entry, &chan->created);
spin_unlock_irqrestore(&chan->lock, sflags);
@@ -610,6 +612,7 @@
/*TODO: Purge the complete list? */
ccp_free_desc_resources(chan->ccp, &chan->active);
ccp_free_desc_resources(chan->ccp, &chan->pending);
+ ccp_free_desc_resources(chan->ccp, &chan->created);
spin_unlock_irqrestore(&chan->lock, flags);
@@ -679,6 +682,7 @@
chan->ccp = ccp;
spin_lock_init(&chan->lock);
+ INIT_LIST_HEAD(&chan->created);
INIT_LIST_HEAD(&chan->pending);
INIT_LIST_HEAD(&chan->active);
INIT_LIST_HEAD(&chan->complete);
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 2ed1e24..b4b78b3 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -158,7 +158,7 @@
case CRYPTO_ALG_TYPE_AEAD:
ctx_req.req.aead_req = (struct aead_request *)req;
ctx_req.ctx.reqctx = aead_request_ctx(ctx_req.req.aead_req);
- dma_unmap_sg(&u_ctx->lldi.pdev->dev, ctx_req.req.aead_req->dst,
+ dma_unmap_sg(&u_ctx->lldi.pdev->dev, ctx_req.ctx.reqctx->dst,
ctx_req.ctx.reqctx->dst_nents, DMA_FROM_DEVICE);
if (ctx_req.ctx.reqctx->skb) {
kfree_skb(ctx_req.ctx.reqctx->skb);
@@ -1362,8 +1362,7 @@
struct chcr_wr *chcr_req;
struct cpl_rx_phys_dsgl *phys_cpl;
struct phys_sge_parm sg_param;
- struct scatterlist *src, *dst;
- struct scatterlist src_sg[2], dst_sg[2];
+ struct scatterlist *src;
unsigned int frags = 0, transhdr_len;
unsigned int ivsize = crypto_aead_ivsize(tfm), dst_size = 0;
unsigned int kctx_len = 0;
@@ -1383,19 +1382,21 @@
if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0)
goto err;
- src = scatterwalk_ffwd(src_sg, req->src, req->assoclen);
- dst = src;
+ src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen);
+ reqctx->dst = src;
+
if (req->src != req->dst) {
err = chcr_copy_assoc(req, aeadctx);
if (err)
return ERR_PTR(err);
- dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen);
+ reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst,
+ req->assoclen);
}
if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_NULL) {
null = 1;
assoclen = 0;
}
- reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen +
+ reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen +
(op_type ? -authsize : authsize));
if (reqctx->dst_nents <= 0) {
pr_err("AUTHENC:Invalid Destination sg entries\n");
@@ -1460,7 +1461,7 @@
sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize);
sg_param.qid = qid;
sg_param.align = 0;
- if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst,
+ if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst,
&sg_param))
goto dstmap_fail;
@@ -1711,8 +1712,7 @@
struct chcr_wr *chcr_req;
struct cpl_rx_phys_dsgl *phys_cpl;
struct phys_sge_parm sg_param;
- struct scatterlist *src, *dst;
- struct scatterlist src_sg[2], dst_sg[2];
+ struct scatterlist *src;
unsigned int frags = 0, transhdr_len, ivsize = AES_BLOCK_SIZE;
unsigned int dst_size = 0, kctx_len;
unsigned int sub_type;
@@ -1728,17 +1728,19 @@
if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0)
goto err;
sub_type = get_aead_subtype(tfm);
- src = scatterwalk_ffwd(src_sg, req->src, req->assoclen);
- dst = src;
+ src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen);
+ reqctx->dst = src;
+
if (req->src != req->dst) {
err = chcr_copy_assoc(req, aeadctx);
if (err) {
pr_err("AAD copy to destination buffer fails\n");
return ERR_PTR(err);
}
- dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen);
+ reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst,
+ req->assoclen);
}
- reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen +
+ reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen +
(op_type ? -authsize : authsize));
if (reqctx->dst_nents <= 0) {
pr_err("CCM:Invalid Destination sg entries\n");
@@ -1777,7 +1779,7 @@
sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize);
sg_param.qid = qid;
sg_param.align = 0;
- if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst,
+ if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst,
&sg_param))
goto dstmap_fail;
@@ -1809,8 +1811,7 @@
struct chcr_wr *chcr_req;
struct cpl_rx_phys_dsgl *phys_cpl;
struct phys_sge_parm sg_param;
- struct scatterlist *src, *dst;
- struct scatterlist src_sg[2], dst_sg[2];
+ struct scatterlist *src;
unsigned int frags = 0, transhdr_len;
unsigned int ivsize = AES_BLOCK_SIZE;
unsigned int dst_size = 0, kctx_len;
@@ -1832,13 +1833,14 @@
if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0)
goto err;
- src = scatterwalk_ffwd(src_sg, req->src, req->assoclen);
- dst = src;
+ src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen);
+ reqctx->dst = src;
if (req->src != req->dst) {
err = chcr_copy_assoc(req, aeadctx);
if (err)
return ERR_PTR(err);
- dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen);
+ reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst,
+ req->assoclen);
}
if (!req->cryptlen)
@@ -1848,7 +1850,7 @@
crypt_len = AES_BLOCK_SIZE;
else
crypt_len = req->cryptlen;
- reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen +
+ reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen +
(op_type ? -authsize : authsize));
if (reqctx->dst_nents <= 0) {
pr_err("GCM:Invalid Destination sg entries\n");
@@ -1923,7 +1925,7 @@
sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize);
sg_param.qid = qid;
sg_param.align = 0;
- if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst,
+ if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst,
&sg_param))
goto dstmap_fail;
@@ -1937,7 +1939,8 @@
write_sg_to_skb(skb, &frags, src, req->cryptlen);
} else {
aes_gcm_empty_pld_pad(req->dst, authsize - 1);
- write_sg_to_skb(skb, &frags, dst, crypt_len);
+ write_sg_to_skb(skb, &frags, reqctx->dst, crypt_len);
+
}
create_wreq(ctx, chcr_req, req, skb, kctx_len, size, 1,
@@ -2189,8 +2192,8 @@
unsigned int ck_size;
int ret = 0, key_ctx_size = 0;
- if (get_aead_subtype(aead) ==
- CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106) {
+ if (get_aead_subtype(aead) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106 &&
+ keylen > 3) {
keylen -= 4; /* nonce/salt is present in the last 4 bytes */
memcpy(aeadctx->salt, key + keylen, 4);
}
diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c
index 918da8e..1c65f07 100644
--- a/drivers/crypto/chelsio/chcr_core.c
+++ b/drivers/crypto/chelsio/chcr_core.c
@@ -52,6 +52,7 @@
int assign_chcr_device(struct chcr_dev **dev)
{
struct uld_ctx *u_ctx;
+ int ret = -ENXIO;
/*
* Which device to use if multiple devices are available TODO
@@ -59,15 +60,14 @@
* must go to the same device to maintain the ordering.
*/
mutex_lock(&dev_mutex); /* TODO ? */
- u_ctx = list_first_entry(&uld_ctx_list, struct uld_ctx, entry);
- if (!u_ctx) {
- mutex_unlock(&dev_mutex);
- return -ENXIO;
+ list_for_each_entry(u_ctx, &uld_ctx_list, entry)
+ if (u_ctx && u_ctx->dev) {
+ *dev = u_ctx->dev;
+ ret = 0;
+ break;
}
-
- *dev = u_ctx->dev;
mutex_unlock(&dev_mutex);
- return 0;
+ return ret;
}
static int chcr_dev_add(struct uld_ctx *u_ctx)
@@ -202,10 +202,8 @@
static int __init chcr_crypto_init(void)
{
- if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info)) {
+ if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info))
pr_err("ULD register fail: No chcr crypto support in cxgb4");
- return -1;
- }
return 0;
}
diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h
index d5af7d6..7ec0a8f 100644
--- a/drivers/crypto/chelsio/chcr_crypto.h
+++ b/drivers/crypto/chelsio/chcr_crypto.h
@@ -158,6 +158,9 @@
};
struct chcr_aead_reqctx {
struct sk_buff *skb;
+ struct scatterlist *dst;
+ struct scatterlist srcffwd[2];
+ struct scatterlist dstffwd[2];
short int dst_nents;
u16 verify;
u8 iv[CHCR_MAX_CRYPTO_IV_LEN];
diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c
index bc5cbc1..5b2d78a 100644
--- a/drivers/crypto/qat/qat_c62x/adf_drv.c
+++ b/drivers/crypto/qat/qat_c62x/adf_drv.c
@@ -233,7 +233,7 @@
&hw_data->accel_capabilities_mask);
/* Find and map all the device's BARS */
- i = 0;
+ i = (hw_data->fuses & ADF_DEVICE_FUSECTL_MASK) ? 1 : 0;
bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
ADF_PCI_MAX_BARS * 2) {
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index e882253..33f0a62 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -69,6 +69,7 @@
#define ADF_ERRSOU5 (0x3A000 + 0xD8)
#define ADF_DEVICE_FUSECTL_OFFSET 0x40
#define ADF_DEVICE_LEGFUSE_OFFSET 0x4C
+#define ADF_DEVICE_FUSECTL_MASK 0x80000000
#define ADF_PCI_MAX_BARS 3
#define ADF_DEVICE_NAME_LENGTH 32
#define ADF_ETR_MAX_RINGS_PER_BANK 16
diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c
index 1e480f1..8c4fd25 100644
--- a/drivers/crypto/qat/qat_common/qat_hal.c
+++ b/drivers/crypto/qat/qat_common/qat_hal.c
@@ -456,7 +456,7 @@
unsigned int csr_val;
int times = 30;
- if (handle->pci_dev->device == ADF_C3XXX_PCI_DEVICE_ID)
+ if (handle->pci_dev->device != ADF_DH895XCC_PCI_DEVICE_ID)
return 0;
csr_val = ADF_CSR_RD(csr_addr, 0);
@@ -716,7 +716,7 @@
(void __iomem *)((uintptr_t)handle->hal_cap_ae_xfer_csr_addr_v +
LOCAL_TO_XFER_REG_OFFSET);
handle->pci_dev = pci_info->pci_dev;
- if (handle->pci_dev->device != ADF_C3XXX_PCI_DEVICE_ID) {
+ if (handle->pci_dev->device == ADF_DH895XCC_PCI_DEVICE_ID) {
sram_bar =
&pci_info->pci_bars[hw_data->get_sram_bar_id(hw_data)];
handle->hal_sram_addr_v = sram_bar->virt_addr;
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index d5ba43a..200828c 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -153,6 +153,8 @@
/* context for suspend/resume */
unsigned int dma_tdfdq;
+
+ bool is_suspended;
};
#define FIST_COMPLETION_QUEUE 93
@@ -257,6 +259,10 @@
BUG_ON(desc_num >= ALLOC_DECS_NUM);
c = cdd->chan_busy[desc_num];
cdd->chan_busy[desc_num] = NULL;
+
+ /* Usecount for chan_busy[], paired with push_desc_queue() */
+ pm_runtime_put(cdd->ddev.dev);
+
return c;
}
@@ -317,12 +323,12 @@
while (val) {
u32 desc, len;
- int error;
- error = pm_runtime_get(cdd->ddev.dev);
- if (error < 0)
- dev_err(cdd->ddev.dev, "%s pm runtime get: %i\n",
- __func__, error);
+ /*
+ * This should never trigger, see the comments in
+ * push_desc_queue()
+ */
+ WARN_ON(cdd->is_suspended);
q_num = __fls(val);
val &= ~(1 << q_num);
@@ -343,9 +349,6 @@
c->residue = pd_trans_len(c->desc->pd6) - len;
dma_cookie_complete(&c->txd);
dmaengine_desc_get_callback_invoke(&c->txd, NULL);
-
- pm_runtime_mark_last_busy(cdd->ddev.dev);
- pm_runtime_put_autosuspend(cdd->ddev.dev);
}
}
return IRQ_HANDLED;
@@ -447,6 +450,15 @@
*/
__iowmb();
+ /*
+ * DMA transfers can take at least 200ms to complete with USB mass
+ * storage connected. To prevent autosuspend timeouts, we must use
+ * pm_runtime_get/put() when chan_busy[] is modified. This will get
+ * cleared in desc_to_chan() or cppi41_stop_chan() depending on the
+ * outcome of the transfer.
+ */
+ pm_runtime_get(cdd->ddev.dev);
+
desc_phys = lower_32_bits(c->desc_phys);
desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
WARN_ON(cdd->chan_busy[desc_num]);
@@ -457,20 +469,26 @@
cppi_writel(reg, cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
}
-static void pending_desc(struct cppi41_channel *c)
+/*
+ * Caller must hold cdd->lock to prevent push_desc_queue()
+ * getting called out of order. We have both cppi41_dma_issue_pending()
+ * and cppi41_runtime_resume() call this function.
+ */
+static void cppi41_run_queue(struct cppi41_dd *cdd)
{
- struct cppi41_dd *cdd = c->cdd;
- unsigned long flags;
+ struct cppi41_channel *c, *_c;
- spin_lock_irqsave(&cdd->lock, flags);
- list_add_tail(&c->node, &cdd->pending);
- spin_unlock_irqrestore(&cdd->lock, flags);
+ list_for_each_entry_safe(c, _c, &cdd->pending, node) {
+ push_desc_queue(c);
+ list_del(&c->node);
+ }
}
static void cppi41_dma_issue_pending(struct dma_chan *chan)
{
struct cppi41_channel *c = to_cpp41_chan(chan);
struct cppi41_dd *cdd = c->cdd;
+ unsigned long flags;
int error;
error = pm_runtime_get(cdd->ddev.dev);
@@ -482,10 +500,11 @@
return;
}
- if (likely(pm_runtime_active(cdd->ddev.dev)))
- push_desc_queue(c);
- else
- pending_desc(c);
+ spin_lock_irqsave(&cdd->lock, flags);
+ list_add_tail(&c->node, &cdd->pending);
+ if (!cdd->is_suspended)
+ cppi41_run_queue(cdd);
+ spin_unlock_irqrestore(&cdd->lock, flags);
pm_runtime_mark_last_busy(cdd->ddev.dev);
pm_runtime_put_autosuspend(cdd->ddev.dev);
@@ -705,6 +724,9 @@
WARN_ON(!cdd->chan_busy[desc_num]);
cdd->chan_busy[desc_num] = NULL;
+ /* Usecount for chan_busy[], paired with push_desc_queue() */
+ pm_runtime_put(cdd->ddev.dev);
+
return 0;
}
@@ -1150,8 +1172,12 @@
static int __maybe_unused cppi41_runtime_suspend(struct device *dev)
{
struct cppi41_dd *cdd = dev_get_drvdata(dev);
+ unsigned long flags;
+ spin_lock_irqsave(&cdd->lock, flags);
+ cdd->is_suspended = true;
WARN_ON(!list_empty(&cdd->pending));
+ spin_unlock_irqrestore(&cdd->lock, flags);
return 0;
}
@@ -1159,14 +1185,11 @@
static int __maybe_unused cppi41_runtime_resume(struct device *dev)
{
struct cppi41_dd *cdd = dev_get_drvdata(dev);
- struct cppi41_channel *c, *_c;
unsigned long flags;
spin_lock_irqsave(&cdd->lock, flags);
- list_for_each_entry_safe(c, _c, &cdd->pending, node) {
- push_desc_queue(c);
- list_del(&c->node);
- }
+ cdd->is_suspended = false;
+ cppi41_run_queue(cdd);
spin_unlock_irqrestore(&cdd->lock, flags);
return 0;
diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig
index e00c9b0..5a37b9f 100644
--- a/drivers/dma/dw/Kconfig
+++ b/drivers/dma/dw/Kconfig
@@ -24,5 +24,5 @@
select DW_DMAC_CORE
help
Support the Synopsys DesignWare AHB DMA controller on the
- platfroms that enumerate it as a PCI device. For example,
+ platforms that enumerate it as a PCI device. For example,
Intel Medfield has integrated this GPDMA controller.
diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h
index 8e67895..abcc51b 100644
--- a/drivers/dma/ioat/hw.h
+++ b/drivers/dma/ioat/hw.h
@@ -64,6 +64,8 @@
#define PCI_DEVICE_ID_INTEL_IOAT_BDX8 0x6f2e
#define PCI_DEVICE_ID_INTEL_IOAT_BDX9 0x6f2f
+#define PCI_DEVICE_ID_INTEL_IOAT_SKX 0x2021
+
#define IOAT_VER_1_2 0x12 /* Version 1.2 */
#define IOAT_VER_2_0 0x20 /* Version 2.0 */
#define IOAT_VER_3_0 0x30 /* Version 3.0 */
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 90eddd9..cc5259b 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -106,6 +106,8 @@
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX8) },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX9) },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SKX) },
+
/* I/OAT v3.3 platforms */
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD0) },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD1) },
@@ -243,10 +245,15 @@
}
}
+static inline bool is_skx_ioat(struct pci_dev *pdev)
+{
+ return (pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SKX) ? true : false;
+}
+
static bool is_xeon_cb32(struct pci_dev *pdev)
{
return is_jf_ioat(pdev) || is_snb_ioat(pdev) || is_ivb_ioat(pdev) ||
- is_hsw_ioat(pdev) || is_bdx_ioat(pdev);
+ is_hsw_ioat(pdev) || is_bdx_ioat(pdev) || is_skx_ioat(pdev);
}
bool is_bwd_ioat(struct pci_dev *pdev)
@@ -693,7 +700,7 @@
/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
ioat_chan->completion =
dma_pool_zalloc(ioat_chan->ioat_dma->completion_pool,
- GFP_KERNEL, &ioat_chan->completion_dma);
+ GFP_NOWAIT, &ioat_chan->completion_dma);
if (!ioat_chan->completion)
return -ENOMEM;
@@ -703,7 +710,7 @@
ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
order = IOAT_MAX_ORDER;
- ring = ioat_alloc_ring(c, order, GFP_KERNEL);
+ ring = ioat_alloc_ring(c, order, GFP_NOWAIT);
if (!ring)
return -ENOMEM;
@@ -1357,6 +1364,8 @@
device->version = readb(device->reg_base + IOAT_VER_OFFSET);
if (device->version >= IOAT_VER_3_0) {
+ if (is_skx_ioat(pdev))
+ device->version = IOAT_VER_3_2;
err = ioat3_dma_probe(device, ioat_dca_enabled);
if (device->version >= IOAT_VER_3_3)
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index ac68666..daf479c 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -938,6 +938,23 @@
d->ccr |= CCR_DST_AMODE_POSTINC;
if (port_window) {
d->ccr |= CCR_SRC_AMODE_DBLIDX;
+
+ if (port_window_bytes >= 64)
+ d->csdp |= CSDP_SRC_BURST_64;
+ else if (port_window_bytes >= 32)
+ d->csdp |= CSDP_SRC_BURST_32;
+ else if (port_window_bytes >= 16)
+ d->csdp |= CSDP_SRC_BURST_16;
+
+ } else {
+ d->ccr |= CCR_SRC_AMODE_CONSTANT;
+ }
+ } else {
+ d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED;
+
+ d->ccr |= CCR_SRC_AMODE_POSTINC;
+ if (port_window) {
+ d->ccr |= CCR_DST_AMODE_DBLIDX;
d->ei = 1;
/*
* One frame covers the port_window and by configure
@@ -948,27 +965,11 @@
d->fi = -(port_window_bytes - 1);
if (port_window_bytes >= 64)
- d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED;
+ d->csdp |= CSDP_DST_BURST_64;
else if (port_window_bytes >= 32)
- d->csdp = CSDP_SRC_BURST_32 | CSDP_SRC_PACKED;
+ d->csdp |= CSDP_DST_BURST_32;
else if (port_window_bytes >= 16)
- d->csdp = CSDP_SRC_BURST_16 | CSDP_SRC_PACKED;
- } else {
- d->ccr |= CCR_SRC_AMODE_CONSTANT;
- }
- } else {
- d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED;
-
- d->ccr |= CCR_SRC_AMODE_POSTINC;
- if (port_window) {
- d->ccr |= CCR_DST_AMODE_DBLIDX;
-
- if (port_window_bytes >= 64)
- d->csdp = CSDP_DST_BURST_64 | CSDP_DST_PACKED;
- else if (port_window_bytes >= 32)
- d->csdp = CSDP_DST_BURST_32 | CSDP_DST_PACKED;
- else if (port_window_bytes >= 16)
- d->csdp = CSDP_DST_BURST_16 | CSDP_DST_PACKED;
+ d->csdp |= CSDP_DST_BURST_16;
} else {
d->ccr |= CCR_DST_AMODE_CONSTANT;
}
@@ -1017,7 +1018,7 @@
osg->addr = sg_dma_address(sgent);
osg->en = en;
osg->fn = sg_dma_len(sgent) / frame_bytes;
- if (port_window && dir == DMA_MEM_TO_DEV) {
+ if (port_window && dir == DMA_DEV_TO_MEM) {
osg->ei = 1;
/*
* One frame covers the port_window and by configure
@@ -1452,6 +1453,7 @@
struct omap_dmadev *od;
struct resource *res;
int rc, i, irq;
+ u32 lch_count;
od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL);
if (!od)
@@ -1494,20 +1496,31 @@
spin_lock_init(&od->lock);
spin_lock_init(&od->irq_lock);
- if (!pdev->dev.of_node) {
- od->dma_requests = od->plat->dma_attr->lch_count;
- if (unlikely(!od->dma_requests))
- od->dma_requests = OMAP_SDMA_REQUESTS;
- } else if (of_property_read_u32(pdev->dev.of_node, "dma-requests",
- &od->dma_requests)) {
+ /* Number of DMA requests */
+ od->dma_requests = OMAP_SDMA_REQUESTS;
+ if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
+ "dma-requests",
+ &od->dma_requests)) {
dev_info(&pdev->dev,
"Missing dma-requests property, using %u.\n",
OMAP_SDMA_REQUESTS);
- od->dma_requests = OMAP_SDMA_REQUESTS;
}
- od->lch_map = devm_kcalloc(&pdev->dev, od->dma_requests,
- sizeof(*od->lch_map), GFP_KERNEL);
+ /* Number of available logical channels */
+ if (!pdev->dev.of_node) {
+ lch_count = od->plat->dma_attr->lch_count;
+ if (unlikely(!lch_count))
+ lch_count = OMAP_SDMA_CHANNELS;
+ } else if (of_property_read_u32(pdev->dev.of_node, "dma-channels",
+ &lch_count)) {
+ dev_info(&pdev->dev,
+ "Missing dma-channels property, using %u.\n",
+ OMAP_SDMA_CHANNELS);
+ lch_count = OMAP_SDMA_CHANNELS;
+ }
+
+ od->lch_map = devm_kcalloc(&pdev->dev, lch_count, sizeof(*od->lch_map),
+ GFP_KERNEL);
if (!od->lch_map)
return -ENOMEM;
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 87fd015..7539f73 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -448,6 +448,9 @@
/* for cyclic capability */
bool cyclic;
+
+ /* for runtime pm tracking */
+ bool active;
};
struct pl330_dmac {
@@ -1696,7 +1699,6 @@
static struct pl330_thread *pl330_request_channel(struct pl330_dmac *pl330)
{
struct pl330_thread *thrd = NULL;
- unsigned long flags;
int chans, i;
if (pl330->state == DYING)
@@ -1704,8 +1706,6 @@
chans = pl330->pcfg.num_chan;
- spin_lock_irqsave(&pl330->lock, flags);
-
for (i = 0; i < chans; i++) {
thrd = &pl330->channels[i];
if ((thrd->free) && (!_manager_ns(thrd) ||
@@ -1723,8 +1723,6 @@
thrd = NULL;
}
- spin_unlock_irqrestore(&pl330->lock, flags);
-
return thrd;
}
@@ -1742,7 +1740,6 @@
static void pl330_release_channel(struct pl330_thread *thrd)
{
struct pl330_dmac *pl330;
- unsigned long flags;
if (!thrd || thrd->free)
return;
@@ -1754,10 +1751,8 @@
pl330 = thrd->dmac;
- spin_lock_irqsave(&pl330->lock, flags);
_free_event(thrd, thrd->ev);
thrd->free = true;
- spin_unlock_irqrestore(&pl330->lock, flags);
}
/* Initialize the structure for PL330 configuration, that can be used
@@ -2033,6 +2028,7 @@
_stop(pch->thread);
spin_unlock(&pch->thread->dmac->lock);
power_down = true;
+ pch->active = false;
} else {
/* Make sure the PL330 Channel thread is active */
spin_lock(&pch->thread->dmac->lock);
@@ -2052,6 +2048,7 @@
desc->status = PREP;
list_move_tail(&desc->node, &pch->work_list);
if (power_down) {
+ pch->active = true;
spin_lock(&pch->thread->dmac->lock);
_start(pch->thread);
spin_unlock(&pch->thread->dmac->lock);
@@ -2117,20 +2114,20 @@
struct pl330_dmac *pl330 = pch->dmac;
unsigned long flags;
- spin_lock_irqsave(&pch->lock, flags);
+ spin_lock_irqsave(&pl330->lock, flags);
dma_cookie_init(chan);
pch->cyclic = false;
pch->thread = pl330_request_channel(pl330);
if (!pch->thread) {
- spin_unlock_irqrestore(&pch->lock, flags);
+ spin_unlock_irqrestore(&pl330->lock, flags);
return -ENOMEM;
}
tasklet_init(&pch->task, pl330_tasklet, (unsigned long) pch);
- spin_unlock_irqrestore(&pch->lock, flags);
+ spin_unlock_irqrestore(&pl330->lock, flags);
return 1;
}
@@ -2166,6 +2163,7 @@
unsigned long flags;
struct pl330_dmac *pl330 = pch->dmac;
LIST_HEAD(list);
+ bool power_down = false;
pm_runtime_get_sync(pl330->ddma.dev);
spin_lock_irqsave(&pch->lock, flags);
@@ -2176,6 +2174,8 @@
pch->thread->req[0].desc = NULL;
pch->thread->req[1].desc = NULL;
pch->thread->req_running = -1;
+ power_down = pch->active;
+ pch->active = false;
/* Mark all desc done */
list_for_each_entry(desc, &pch->submitted_list, node) {
@@ -2193,6 +2193,8 @@
list_splice_tail_init(&pch->completed_list, &pl330->desc_pool);
spin_unlock_irqrestore(&pch->lock, flags);
pm_runtime_mark_last_busy(pl330->ddma.dev);
+ if (power_down)
+ pm_runtime_put_autosuspend(pl330->ddma.dev);
pm_runtime_put_autosuspend(pl330->ddma.dev);
return 0;
@@ -2228,12 +2230,13 @@
static void pl330_free_chan_resources(struct dma_chan *chan)
{
struct dma_pl330_chan *pch = to_pchan(chan);
+ struct pl330_dmac *pl330 = pch->dmac;
unsigned long flags;
tasklet_kill(&pch->task);
pm_runtime_get_sync(pch->dmac->ddma.dev);
- spin_lock_irqsave(&pch->lock, flags);
+ spin_lock_irqsave(&pl330->lock, flags);
pl330_release_channel(pch->thread);
pch->thread = NULL;
@@ -2241,7 +2244,7 @@
if (pch->cyclic)
list_splice_tail_init(&pch->work_list, &pch->dmac->desc_pool);
- spin_unlock_irqrestore(&pch->lock, flags);
+ spin_unlock_irqrestore(&pl330->lock, flags);
pm_runtime_mark_last_busy(pch->dmac->ddma.dev);
pm_runtime_put_autosuspend(pch->dmac->ddma.dev);
}
@@ -2357,6 +2360,7 @@
* updated on work_list emptiness status.
*/
WARN_ON(list_empty(&pch->submitted_list));
+ pch->active = true;
pm_runtime_get_sync(pch->dmac->ddma.dev);
}
list_splice_tail_init(&pch->submitted_list, &pch->work_list);
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 2e441d0..4c357d4 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -986,6 +986,7 @@
{
struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
struct rcar_dmac *dmac = to_rcar_dmac(chan->device);
+ struct rcar_dmac_chan_map *map = &rchan->map;
struct rcar_dmac_desc_page *page, *_page;
struct rcar_dmac_desc *desc;
LIST_HEAD(list);
@@ -1019,6 +1020,13 @@
free_page((unsigned long)page);
}
+ /* Remove slave mapping if present. */
+ if (map->slave.xfer_size) {
+ dma_unmap_resource(chan->device->dev, map->addr,
+ map->slave.xfer_size, map->dir, 0);
+ map->slave.xfer_size = 0;
+ }
+
pm_runtime_put(chan->device->dev);
}
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 3688d08..3056ce7 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -880,7 +880,7 @@
struct virt_dma_desc *vdesc;
enum dma_status status;
unsigned long flags;
- u32 residue;
+ u32 residue = 0;
status = dma_cookie_status(c, cookie, state);
if ((status == DMA_COMPLETE) || (!state))
@@ -888,16 +888,12 @@
spin_lock_irqsave(&chan->vchan.lock, flags);
vdesc = vchan_find_desc(&chan->vchan, cookie);
- if (cookie == chan->desc->vdesc.tx.cookie) {
+ if (chan->desc && cookie == chan->desc->vdesc.tx.cookie)
residue = stm32_dma_desc_residue(chan, chan->desc,
chan->next_sg);
- } else if (vdesc) {
+ else if (vdesc)
residue = stm32_dma_desc_residue(chan,
to_stm32_dma_desc(vdesc), 0);
- } else {
- residue = 0;
- }
-
dma_set_residue(state, residue);
spin_unlock_irqrestore(&chan->vchan.lock, flags);
@@ -972,21 +968,18 @@
struct stm32_dma_chan *chan;
struct dma_chan *c;
- if (dma_spec->args_count < 3)
+ if (dma_spec->args_count < 4)
return NULL;
cfg.channel_id = dma_spec->args[0];
cfg.request_line = dma_spec->args[1];
cfg.stream_config = dma_spec->args[2];
- cfg.threshold = 0;
+ cfg.threshold = dma_spec->args[3];
if ((cfg.channel_id >= STM32_DMA_MAX_CHANNELS) || (cfg.request_line >=
STM32_DMA_MAX_REQUEST_ID))
return NULL;
- if (dma_spec->args_count > 3)
- cfg.threshold = dma_spec->args[3];
-
chan = &dmadev->chan[cfg.channel_id];
c = dma_get_slave_channel(&chan->vchan.chan);
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index 3f24aeb..2403475 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -149,6 +149,7 @@
match = of_match_node(ti_am335x_master_match, dma_node);
if (!match) {
dev_err(&pdev->dev, "DMA master is not supported\n");
+ of_node_put(dma_node);
return -EINVAL;
}
@@ -339,6 +340,7 @@
match = of_match_node(ti_dra7_master_match, dma_node);
if (!match) {
dev_err(&pdev->dev, "DMA master is not supported\n");
+ of_node_put(dma_node);
return -EINVAL;
}
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 2602511..82dab16 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -3065,6 +3065,8 @@
/* Check whether at least one UMC is enabled: */
if (umc_en_mask)
ecc_en = umc_en_mask == ecc_en_mask;
+ else
+ edac_dbg(0, "Node %d: No enabled UMCs.\n", nid);
/* Assume UMC MCA banks are enabled. */
nb_mce_en = true;
@@ -3075,14 +3077,15 @@
nb_mce_en = nb_mce_bank_enabled_on_node(nid);
if (!nb_mce_en)
- amd64_notice("NB MCE bank disabled, set MSR 0x%08x[4] on node %d to enable.\n",
+ edac_dbg(0, "NB MCE bank disabled, set MSR 0x%08x[4] on node %d to enable.\n",
MSR_IA32_MCG_CTL, nid);
}
- amd64_info("DRAM ECC %s.\n", (ecc_en ? "enabled" : "disabled"));
+ amd64_info("Node %d: DRAM ECC %s.\n",
+ nid, (ecc_en ? "enabled" : "disabled"));
if (!ecc_en || !nb_mce_en) {
- amd64_notice("%s", ecc_msg);
+ amd64_info("%s", ecc_msg);
return false;
}
return true;
@@ -3300,15 +3303,6 @@
goto err_add_mc;
}
- /* register stuff with EDAC MCE */
- if (report_gart_errors)
- amd_report_gart_errors(true);
-
- if (pvt->umc)
- amd_register_ecc_decoder(decode_umc_error);
- else
- amd_register_ecc_decoder(decode_bus_error);
-
return 0;
err_add_mc:
@@ -3342,7 +3336,7 @@
ecc_stngs[nid] = s;
if (!ecc_enabled(F3, nid)) {
- ret = -ENODEV;
+ ret = 0;
if (!ecc_enable_override)
goto err_enable;
@@ -3363,6 +3357,8 @@
if (boot_cpu_data.x86 < 0x17)
restore_ecc_error_reporting(s, nid, F3);
+
+ goto err_enable;
}
return ret;
@@ -3396,14 +3392,6 @@
free_mc_sibling_devs(pvt);
- /* unregister from EDAC MCE */
- amd_report_gart_errors(false);
-
- if (pvt->umc)
- amd_unregister_ecc_decoder(decode_umc_error);
- else
- amd_unregister_ecc_decoder(decode_bus_error);
-
kfree(ecc_stngs[nid]);
ecc_stngs[nid] = NULL;
@@ -3452,8 +3440,11 @@
int err = -ENODEV;
int i;
+ if (!x86_match_cpu(amd64_cpuids))
+ return -ENODEV;
+
if (amd_cache_northbridges() < 0)
- goto err_ret;
+ return -ENODEV;
opstate_init();
@@ -3466,14 +3457,30 @@
if (!msrs)
goto err_free;
- for (i = 0; i < amd_nb_num(); i++)
- if (probe_one_instance(i)) {
+ for (i = 0; i < amd_nb_num(); i++) {
+ err = probe_one_instance(i);
+ if (err) {
/* unwind properly */
while (--i >= 0)
remove_one_instance(i);
goto err_pci;
}
+ }
+
+ if (!edac_has_mcs()) {
+ err = -ENODEV;
+ goto err_pci;
+ }
+
+ /* register stuff with EDAC MCE */
+ if (report_gart_errors)
+ amd_report_gart_errors(true);
+
+ if (boot_cpu_data.x86 >= 0x17)
+ amd_register_ecc_decoder(decode_umc_error);
+ else
+ amd_register_ecc_decoder(decode_bus_error);
setup_pci_device();
@@ -3493,7 +3500,6 @@
kfree(ecc_stngs);
ecc_stngs = NULL;
-err_ret:
return err;
}
@@ -3504,6 +3510,14 @@
if (pci_ctl)
edac_pci_release_generic_ctl(pci_ctl);
+ /* unregister from EDAC MCE */
+ amd_report_gart_errors(false);
+
+ if (boot_cpu_data.x86 >= 0x17)
+ amd_unregister_ecc_decoder(decode_umc_error);
+ else
+ amd_unregister_ecc_decoder(decode_bus_error);
+
for (i = 0; i < amd_nb_num(); i++)
remove_one_instance(i);
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 496603d..1d4b74e 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -16,19 +16,14 @@
#include <linux/slab.h>
#include <linux/mmzone.h>
#include <linux/edac.h>
+#include <asm/cpu_device_id.h>
#include <asm/msr.h>
#include "edac_module.h"
#include "mce_amd.h"
-#define amd64_debug(fmt, arg...) \
- edac_printk(KERN_DEBUG, "amd64", fmt, ##arg)
-
#define amd64_info(fmt, arg...) \
edac_printk(KERN_INFO, "amd64", fmt, ##arg)
-#define amd64_notice(fmt, arg...) \
- edac_printk(KERN_NOTICE, "amd64", fmt, ##arg)
-
#define amd64_warn(fmt, arg...) \
edac_printk(KERN_WARNING, "amd64", "Warning: " fmt, ##arg)
@@ -90,7 +85,7 @@
* sections 3.5.4 and 3.5.5 for more information.
*/
-#define EDAC_AMD64_VERSION "3.4.0"
+#define EDAC_AMD64_VERSION "3.5.0"
#define EDAC_MOD_STR "amd64_edac"
/* Extended Model from CPUID, for CPU Revision numbers */
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 750891e..e5573c5 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -453,6 +453,20 @@
}
EXPORT_SYMBOL_GPL(edac_mc_free);
+bool edac_has_mcs(void)
+{
+ bool ret;
+
+ mutex_lock(&mem_ctls_mutex);
+
+ ret = list_empty(&mc_devices);
+
+ mutex_unlock(&mem_ctls_mutex);
+
+ return !ret;
+}
+EXPORT_SYMBOL_GPL(edac_has_mcs);
+
/* Caller must hold mem_ctls_mutex */
static struct mem_ctl_info *__find_mci_by_dev(struct device *dev)
{
diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h
index 50fc1dc..5357800 100644
--- a/drivers/edac/edac_mc.h
+++ b/drivers/edac/edac_mc.h
@@ -149,6 +149,15 @@
extern void edac_mc_free(struct mem_ctl_info *mci);
/**
+ * edac_has_mcs() - Check if any MCs have been allocated.
+ *
+ * Returns:
+ * True if MC instances have been registered successfully.
+ * False otherwise.
+ */
+extern bool edac_has_mcs(void);
+
+/**
* edac_mc_find() - Search for a mem_ctl_info structure whose index is @idx.
*
* @idx: index to be seek
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 39dbab7..445862d 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -569,6 +569,40 @@
return sprintf(data, "%s\n", edac_caps[dimm->edac_mode]);
}
+static ssize_t dimmdev_ce_count_show(struct device *dev,
+ struct device_attribute *mattr,
+ char *data)
+{
+ struct dimm_info *dimm = to_dimm(dev);
+ u32 count;
+ int off;
+
+ off = EDAC_DIMM_OFF(dimm->mci->layers,
+ dimm->mci->n_layers,
+ dimm->location[0],
+ dimm->location[1],
+ dimm->location[2]);
+ count = dimm->mci->ce_per_layer[dimm->mci->n_layers-1][off];
+ return sprintf(data, "%u\n", count);
+}
+
+static ssize_t dimmdev_ue_count_show(struct device *dev,
+ struct device_attribute *mattr,
+ char *data)
+{
+ struct dimm_info *dimm = to_dimm(dev);
+ u32 count;
+ int off;
+
+ off = EDAC_DIMM_OFF(dimm->mci->layers,
+ dimm->mci->n_layers,
+ dimm->location[0],
+ dimm->location[1],
+ dimm->location[2]);
+ count = dimm->mci->ue_per_layer[dimm->mci->n_layers-1][off];
+ return sprintf(data, "%u\n", count);
+}
+
/* dimm/rank attribute files */
static DEVICE_ATTR(dimm_label, S_IRUGO | S_IWUSR,
dimmdev_label_show, dimmdev_label_store);
@@ -577,6 +611,8 @@
static DEVICE_ATTR(dimm_mem_type, S_IRUGO, dimmdev_mem_type_show, NULL);
static DEVICE_ATTR(dimm_dev_type, S_IRUGO, dimmdev_dev_type_show, NULL);
static DEVICE_ATTR(dimm_edac_mode, S_IRUGO, dimmdev_edac_mode_show, NULL);
+static DEVICE_ATTR(dimm_ce_count, S_IRUGO, dimmdev_ce_count_show, NULL);
+static DEVICE_ATTR(dimm_ue_count, S_IRUGO, dimmdev_ue_count_show, NULL);
/* attributes of the dimm<id>/rank<id> object */
static struct attribute *dimm_attrs[] = {
@@ -586,6 +622,8 @@
&dev_attr_dimm_mem_type.attr,
&dev_attr_dimm_dev_type.attr,
&dev_attr_dimm_edac_mode.attr,
+ &dev_attr_dimm_ce_count.attr,
+ &dev_attr_dimm_ue_count.attr,
NULL,
};
@@ -831,7 +869,7 @@
static DEVICE_ATTR(max_location, S_IRUGO, mci_max_location_show, NULL);
/* memory scrubber attribute file */
-DEVICE_ATTR(sdram_scrub_rate, 0, mci_sdram_scrub_rate_show,
+static DEVICE_ATTR(sdram_scrub_rate, 0, mci_sdram_scrub_rate_show,
mci_sdram_scrub_rate_store); /* umode set later in is_visible */
static struct attribute *mci_attrs[] = {
diff --git a/drivers/edac/fsl_ddr_edac.c b/drivers/edac/fsl_ddr_edac.c
index 4e9608a..efc8276 100644
--- a/drivers/edac/fsl_ddr_edac.c
+++ b/drivers/edac/fsl_ddr_edac.c
@@ -145,12 +145,12 @@
return 0;
}
-DEVICE_ATTR(inject_data_hi, S_IRUGO | S_IWUSR,
- fsl_mc_inject_data_hi_show, fsl_mc_inject_data_hi_store);
-DEVICE_ATTR(inject_data_lo, S_IRUGO | S_IWUSR,
- fsl_mc_inject_data_lo_show, fsl_mc_inject_data_lo_store);
-DEVICE_ATTR(inject_ctrl, S_IRUGO | S_IWUSR,
- fsl_mc_inject_ctrl_show, fsl_mc_inject_ctrl_store);
+static DEVICE_ATTR(inject_data_hi, S_IRUGO | S_IWUSR,
+ fsl_mc_inject_data_hi_show, fsl_mc_inject_data_hi_store);
+static DEVICE_ATTR(inject_data_lo, S_IRUGO | S_IWUSR,
+ fsl_mc_inject_data_lo_show, fsl_mc_inject_data_lo_store);
+static DEVICE_ATTR(inject_ctrl, S_IRUGO | S_IWUSR,
+ fsl_mc_inject_ctrl_show, fsl_mc_inject_ctrl_store);
static struct attribute *fsl_ddr_dev_attrs[] = {
&dev_attr_inject_data_hi.attr,
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index 0a912bf..e391f5a 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -304,7 +304,6 @@
#define REDMEMA 0xdc
#define REDMEMB 0x7c
- #define IS_SECOND_CH(v) ((v) * (1 << 17))
#define RECMEMA 0xe0
#define RECMEMA_BANK(v) (((v) >> 12) & 7)
@@ -483,8 +482,9 @@
pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
REDMEMB, &value);
channel = (branch << 1);
- if (IS_SECOND_CH(value))
- channel++;
+
+ /* Second channel ? */
+ channel += !!(value & BIT(17));
/* Clear the error bit */
pci_write_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 69b5ade..75ad847 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1835,6 +1835,7 @@
static struct notifier_block i7_mce_dec = {
.notifier_call = i7core_mce_check_error,
+ .priority = MCE_PRIO_EDAC,
};
struct memdev_dmi_entry {
diff --git a/drivers/edac/i82975x_edac.c b/drivers/edac/i82975x_edac.c
index 7baa8ac..9dcdab2 100644
--- a/drivers/edac/i82975x_edac.c
+++ b/drivers/edac/i82975x_edac.c
@@ -494,6 +494,10 @@
}
mchbar &= 0xffffc000; /* bits 31:14 used for 16K window */
mch_window = ioremap_nocache(mchbar, 0x1000);
+ if (!mch_window) {
+ edac_dbg(3, "error ioremapping MCHBAR!\n");
+ goto fail0;
+ }
#ifdef i82975x_DEBUG_IOMEM
i82975x_printk(KERN_INFO, "MCHBAR real = %0x, remapped = %p\n",
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 34208f3..ba35b7e 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -937,12 +937,13 @@
}
if (m->status & MCI_STATUS_DEFERRED)
- return "Deferred error.";
+ return "Deferred error, no action required.";
return "Corrected error, no action required.";
}
-int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
+static int
+amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
{
struct mce *m = (struct mce *)data;
struct cpuinfo_x86 *c = &cpu_data(m->extcpu);
@@ -991,20 +992,22 @@
pr_cont("]: 0x%016llx\n", m->status);
if (m->status & MCI_STATUS_ADDRV)
- pr_emerg(HW_ERR "Error Addr: 0x%016llx", m->addr);
+ pr_emerg(HW_ERR "Error Addr: 0x%016llx\n", m->addr);
if (boot_cpu_has(X86_FEATURE_SMCA)) {
+ pr_emerg(HW_ERR "IPID: 0x%016llx", m->ipid);
+
if (m->status & MCI_STATUS_SYNDV)
pr_cont(", Syndrome: 0x%016llx", m->synd);
- pr_cont(", IPID: 0x%016llx", m->ipid);
-
pr_cont("\n");
decode_smca_errors(m);
goto err_code;
- } else
- pr_cont("\n");
+ }
+
+ if (m->tsc)
+ pr_emerg(HW_ERR "TSC: %llu\n", m->tsc);
if (!fam_ops)
goto err_code;
@@ -1047,10 +1050,10 @@
return NOTIFY_STOP;
}
-EXPORT_SYMBOL_GPL(amd_decode_mce);
static struct notifier_block amd_mce_dec_nb = {
.notifier_call = amd_decode_mce,
+ .priority = MCE_PRIO_EDAC,
};
static int __init mce_amd_init(void)
diff --git a/drivers/edac/mce_amd.h b/drivers/edac/mce_amd.h
index c2359a1..0b6a686 100644
--- a/drivers/edac/mce_amd.h
+++ b/drivers/edac/mce_amd.h
@@ -79,6 +79,5 @@
void amd_report_gart_errors(bool);
void amd_register_ecc_decoder(void (*f)(int, struct mce *));
void amd_unregister_ecc_decoder(void (*f)(int, struct mce *));
-int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data);
#endif /* _EDAC_MCE_AMD_H */
diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c
index 8f66cbe..67f7bc3 100644
--- a/drivers/edac/mpc85xx_edac.c
+++ b/drivers/edac/mpc85xx_edac.c
@@ -629,6 +629,7 @@
{ .compatible = "fsl,p1020-l2-cache-controller", },
{ .compatible = "fsl,p1021-l2-cache-controller", },
{ .compatible = "fsl,p2020-l2-cache-controller", },
+ { .compatible = "fsl,t2080-l2-cache-controller", },
{},
};
MODULE_DEVICE_TABLE(of, mpc85xx_l2_err_of_match);
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 54ae6dc..a65ea44 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -304,7 +304,6 @@
u64 (*rir_limit)(u32 reg);
u64 (*sad_limit)(u32 reg);
u32 (*interleave_mode)(u32 reg);
- char* (*show_interleave_mode)(u32 reg);
u32 (*dram_attr)(u32 reg);
const u32 *dram_rule;
const u32 *interleave_list;
@@ -811,11 +810,6 @@
return GET_BITFIELD(reg, 1, 1);
}
-char *show_interleave_mode(u32 reg)
-{
- return interleave_mode(reg) ? "8:6" : "[8:6]XOR[18:16]";
-}
-
static u32 dram_attr(u32 reg)
{
return GET_BITFIELD(reg, 2, 3);
@@ -831,29 +825,16 @@
return GET_BITFIELD(reg, 1, 2);
}
-static char *knl_show_interleave_mode(u32 reg)
+static const char * const knl_intlv_mode[] = {
+ "[8:6]", "[10:8]", "[14:12]", "[32:30]"
+};
+
+static const char *get_intlv_mode_str(u32 reg, enum type t)
{
- char *s;
-
- switch (knl_interleave_mode(reg)) {
- case 0:
- s = "use address bits [8:6]";
- break;
- case 1:
- s = "use address bits [10:8]";
- break;
- case 2:
- s = "use address bits [14:12]";
- break;
- case 3:
- s = "use address bits [32:30]";
- break;
- default:
- WARN_ON(1);
- break;
- }
-
- return s;
+ if (t == KNIGHTS_LANDING)
+ return knl_intlv_mode[knl_interleave_mode(reg)];
+ else
+ return interleave_mode(reg) ? "[8:6]" : "[8:6]XOR[18:16]";
}
static u32 dram_attr_knl(u32 reg)
@@ -1810,7 +1791,7 @@
show_dram_attr(pvt->info.dram_attr(reg)),
gb, (mb*1000)/1024,
((u64)tmp_mb) << 20L,
- pvt->info.show_interleave_mode(reg),
+ get_intlv_mode_str(reg, pvt->info.type),
reg);
prv = limit;
@@ -3136,7 +3117,8 @@
}
static struct notifier_block sbridge_mce_dec = {
- .notifier_call = sbridge_mce_check_error,
+ .notifier_call = sbridge_mce_check_error,
+ .priority = MCE_PRIO_EDAC,
};
/****************************************************************************
@@ -3227,7 +3209,6 @@
pvt->info.rir_limit = rir_limit;
pvt->info.sad_limit = sad_limit;
pvt->info.interleave_mode = interleave_mode;
- pvt->info.show_interleave_mode = show_interleave_mode;
pvt->info.dram_attr = dram_attr;
pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule);
pvt->info.interleave_list = ibridge_interleave_list;
@@ -3251,7 +3232,6 @@
pvt->info.rir_limit = rir_limit;
pvt->info.sad_limit = sad_limit;
pvt->info.interleave_mode = interleave_mode;
- pvt->info.show_interleave_mode = show_interleave_mode;
pvt->info.dram_attr = dram_attr;
pvt->info.max_sad = ARRAY_SIZE(sbridge_dram_rule);
pvt->info.interleave_list = sbridge_interleave_list;
@@ -3275,7 +3255,6 @@
pvt->info.rir_limit = haswell_rir_limit;
pvt->info.sad_limit = sad_limit;
pvt->info.interleave_mode = interleave_mode;
- pvt->info.show_interleave_mode = show_interleave_mode;
pvt->info.dram_attr = dram_attr;
pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule);
pvt->info.interleave_list = ibridge_interleave_list;
@@ -3299,7 +3278,6 @@
pvt->info.rir_limit = haswell_rir_limit;
pvt->info.sad_limit = sad_limit;
pvt->info.interleave_mode = interleave_mode;
- pvt->info.show_interleave_mode = show_interleave_mode;
pvt->info.dram_attr = dram_attr;
pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule);
pvt->info.interleave_list = ibridge_interleave_list;
@@ -3323,7 +3301,6 @@
pvt->info.rir_limit = NULL;
pvt->info.sad_limit = knl_sad_limit;
pvt->info.interleave_mode = knl_interleave_mode;
- pvt->info.show_interleave_mode = knl_show_interleave_mode;
pvt->info.dram_attr = dram_attr_knl;
pvt->info.max_sad = ARRAY_SIZE(knl_dram_rule);
pvt->info.interleave_list = knl_interleave_list;
diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c
index 79ef675..1159dba 100644
--- a/drivers/edac/skx_edac.c
+++ b/drivers/edac/skx_edac.c
@@ -1007,7 +1007,8 @@
}
static struct notifier_block skx_mce_dec = {
- .notifier_call = skx_mce_check_error,
+ .notifier_call = skx_mce_check_error,
+ .priority = MCE_PRIO_EDAC,
};
static void skx_remove(void)
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index 7829846..7c1e3a7 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -453,7 +453,7 @@
dev_err(&edev->dev, "out of memory in extcon_set_state\n");
kobject_uevent(&edev->dev.kobj, KOBJ_CHANGE);
- return 0;
+ return -ENOMEM;
}
length = name_show(&edev->dev, NULL, prop_buf);
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index f853ad2..1027d7b4 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -250,7 +250,6 @@
}
reserve_regions();
- efi_memattr_init();
efi_esrt_init();
efi_memmap_unmap();
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 9291480..e7d4040 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -529,6 +529,8 @@
}
}
+ efi_memattr_init();
+
/* Parse the EFI Properties table if it exists */
if (efi.properties_table != EFI_INVALID_TABLE_ADDR) {
efi_properties_table_t *tbl;
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 1491407..08b0268 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -269,7 +269,7 @@
max -= efi.esrt;
if (max < size) {
- pr_err("ESRT header doen't fit on single memory map entry. (size: %zu max: %zu)\n",
+ pr_err("ESRT header doesn't fit on single memory map entry. (size: %zu max: %zu)\n",
size, max);
return;
}
diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c
index 520a40e..6c7d60c 100644
--- a/drivers/firmware/efi/fake_mem.c
+++ b/drivers/firmware/efi/fake_mem.c
@@ -71,8 +71,7 @@
}
/* allocate memory for new EFI memmap */
- new_memmap_phy = memblock_alloc(efi.memmap.desc_size * new_nr_map,
- PAGE_SIZE);
+ new_memmap_phy = efi_memmap_alloc(new_nr_map);
if (!new_memmap_phy)
return;
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index d564d25..f742596 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -11,7 +11,7 @@
-mno-mmx -mno-sse
cflags-$(CONFIG_ARM64) := $(subst -pg,,$(KBUILD_CFLAGS))
-cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) -g0 \
+cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \
-fno-builtin -fpic -mno-single-pic-base
cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt
@@ -28,7 +28,7 @@
# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
KCOV_INSTRUMENT := n
-lib-y := efi-stub-helper.o gop.o
+lib-y := efi-stub-helper.o gop.o secureboot.o
# include the stub's generic dependencies from lib/ when building for ARM/arm64
arm-deps := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c sort.c
@@ -60,7 +60,7 @@
extra-$(CONFIG_EFI_ARMSTUB) := $(lib-y)
lib-$(CONFIG_EFI_ARMSTUB) := $(patsubst %.o,%.stub.o,$(lib-y))
-STUBCOPY_FLAGS-y := -R .debug* -R *ksymtab* -R *kcrctab*
+STUBCOPY_RM-y := -R *ksymtab* -R *kcrctab*
STUBCOPY_FLAGS-$(CONFIG_ARM64) += --prefix-alloc-sections=.init \
--prefix-symbols=__efistub_
STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS
@@ -68,17 +68,25 @@
$(obj)/%.stub.o: $(obj)/%.o FORCE
$(call if_changed,stubcopy)
+#
+# Strip debug sections and some other sections that may legally contain
+# absolute relocations, so that we can inspect the remaining sections for
+# such relocations. If none are found, regenerate the output object, but
+# this time, use objcopy and leave all sections in place.
+#
quiet_cmd_stubcopy = STUBCPY $@
- cmd_stubcopy = if $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; then \
- $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y) \
- && (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \
- rm -f $@; /bin/false); else /bin/false; fi
+ cmd_stubcopy = if $(STRIP) --strip-debug $(STUBCOPY_RM-y) -o $@ $<; \
+ then if $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y); \
+ then (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \
+ rm -f $@; /bin/false); \
+ else $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; fi \
+ else /bin/false; fi
#
# ARM discards the .data section because it disallows r/w data in the
# decompressor. So move our .data to .data.efistub, which is preserved
# explicitly by the decompressor linker script.
#
-STUBCOPY_FLAGS-$(CONFIG_ARM) += --rename-section .data=.data.efistub \
- -R ___ksymtab+sort -R ___kcrctab+sort
+STUBCOPY_FLAGS-$(CONFIG_ARM) += --rename-section .data=.data.efistub
+STUBCOPY_RM-$(CONFIG_ARM) += -R ___ksymtab+sort -R ___kcrctab+sort
STUBCOPY_RELOC-$(CONFIG_ARM) := R_ARM_ABS
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index b4f7d78..d4056c6 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -20,52 +20,6 @@
bool __nokaslr;
-static int efi_get_secureboot(efi_system_table_t *sys_table_arg)
-{
- static efi_char16_t const sb_var_name[] = {
- 'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0 };
- static efi_char16_t const sm_var_name[] = {
- 'S', 'e', 't', 'u', 'p', 'M', 'o', 'd', 'e', 0 };
-
- efi_guid_t var_guid = EFI_GLOBAL_VARIABLE_GUID;
- efi_get_variable_t *f_getvar = sys_table_arg->runtime->get_variable;
- u8 val;
- unsigned long size = sizeof(val);
- efi_status_t status;
-
- status = f_getvar((efi_char16_t *)sb_var_name, (efi_guid_t *)&var_guid,
- NULL, &size, &val);
-
- if (status != EFI_SUCCESS)
- goto out_efi_err;
-
- if (val == 0)
- return 0;
-
- status = f_getvar((efi_char16_t *)sm_var_name, (efi_guid_t *)&var_guid,
- NULL, &size, &val);
-
- if (status != EFI_SUCCESS)
- goto out_efi_err;
-
- if (val == 1)
- return 0;
-
- return 1;
-
-out_efi_err:
- switch (status) {
- case EFI_NOT_FOUND:
- return 0;
- case EFI_DEVICE_ERROR:
- return -EIO;
- case EFI_SECURITY_VIOLATION:
- return -EACCES;
- default:
- return -EINVAL;
- }
-}
-
efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
void *__image, void **__fh)
{
@@ -91,75 +45,6 @@
return status;
}
-efi_status_t efi_file_close(void *handle)
-{
- efi_file_handle_t *fh = handle;
-
- return fh->close(handle);
-}
-
-efi_status_t
-efi_file_read(void *handle, unsigned long *size, void *addr)
-{
- efi_file_handle_t *fh = handle;
-
- return fh->read(handle, size, addr);
-}
-
-
-efi_status_t
-efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
- efi_char16_t *filename_16, void **handle, u64 *file_sz)
-{
- efi_file_handle_t *h, *fh = __fh;
- efi_file_info_t *info;
- efi_status_t status;
- efi_guid_t info_guid = EFI_FILE_INFO_ID;
- unsigned long info_sz;
-
- status = fh->open(fh, &h, filename_16, EFI_FILE_MODE_READ, (u64)0);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table_arg, "Failed to open file: ");
- efi_char16_printk(sys_table_arg, filename_16);
- efi_printk(sys_table_arg, "\n");
- return status;
- }
-
- *handle = h;
-
- info_sz = 0;
- status = h->get_info(h, &info_guid, &info_sz, NULL);
- if (status != EFI_BUFFER_TOO_SMALL) {
- efi_printk(sys_table_arg, "Failed to get file info size\n");
- return status;
- }
-
-grow:
- status = sys_table_arg->boottime->allocate_pool(EFI_LOADER_DATA,
- info_sz, (void **)&info);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table_arg, "Failed to alloc mem for file info\n");
- return status;
- }
-
- status = h->get_info(h, &info_guid, &info_sz,
- info);
- if (status == EFI_BUFFER_TOO_SMALL) {
- sys_table_arg->boottime->free_pool(info);
- goto grow;
- }
-
- *file_sz = info->file_size;
- sys_table_arg->boottime->free_pool(info);
-
- if (status != EFI_SUCCESS)
- efi_printk(sys_table_arg, "Failed to get initrd info\n");
-
- return status;
-}
-
-
-
void efi_char16_printk(efi_system_table_t *sys_table_arg,
efi_char16_t *str)
{
@@ -226,7 +111,7 @@
efi_guid_t loaded_image_proto = LOADED_IMAGE_PROTOCOL_GUID;
unsigned long reserve_addr = 0;
unsigned long reserve_size = 0;
- int secure_boot = 0;
+ enum efi_secureboot_mode secure_boot;
struct screen_info *si;
/* Check if we were booted by the EFI firmware */
@@ -296,19 +181,14 @@
pr_efi_err(sys_table, "Failed to parse EFI cmdline options\n");
secure_boot = efi_get_secureboot(sys_table);
- if (secure_boot > 0)
- pr_efi(sys_table, "UEFI Secure Boot is enabled.\n");
-
- if (secure_boot < 0) {
- pr_efi_err(sys_table,
- "could not determine UEFI Secure Boot status.\n");
- }
/*
- * Unauthenticated device tree data is a security hazard, so
- * ignore 'dtb=' unless UEFI Secure Boot is disabled.
+ * Unauthenticated device tree data is a security hazard, so ignore
+ * 'dtb=' unless UEFI Secure Boot is disabled. We assume that secure
+ * boot is enabled if we can't determine its state.
*/
- if (secure_boot != 0 && strstr(cmdline_ptr, "dtb=")) {
+ if (secure_boot != efi_secureboot_mode_disabled &&
+ strstr(cmdline_ptr, "dtb=")) {
pr_efi(sys_table, "Ignoring DTB from command line.\n");
} else {
status = handle_cmdline_files(sys_table, image, cmdline_ptr,
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 757badc..919822b 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -338,6 +338,69 @@
efi_call_early(free_pages, addr, nr_pages);
}
+static efi_status_t efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
+ efi_char16_t *filename_16, void **handle,
+ u64 *file_sz)
+{
+ efi_file_handle_t *h, *fh = __fh;
+ efi_file_info_t *info;
+ efi_status_t status;
+ efi_guid_t info_guid = EFI_FILE_INFO_ID;
+ unsigned long info_sz;
+
+ status = efi_call_proto(efi_file_handle, open, fh, &h, filename_16,
+ EFI_FILE_MODE_READ, (u64)0);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table_arg, "Failed to open file: ");
+ efi_char16_printk(sys_table_arg, filename_16);
+ efi_printk(sys_table_arg, "\n");
+ return status;
+ }
+
+ *handle = h;
+
+ info_sz = 0;
+ status = efi_call_proto(efi_file_handle, get_info, h, &info_guid,
+ &info_sz, NULL);
+ if (status != EFI_BUFFER_TOO_SMALL) {
+ efi_printk(sys_table_arg, "Failed to get file info size\n");
+ return status;
+ }
+
+grow:
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ info_sz, (void **)&info);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table_arg, "Failed to alloc mem for file info\n");
+ return status;
+ }
+
+ status = efi_call_proto(efi_file_handle, get_info, h, &info_guid,
+ &info_sz, info);
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ efi_call_early(free_pool, info);
+ goto grow;
+ }
+
+ *file_sz = info->file_size;
+ efi_call_early(free_pool, info);
+
+ if (status != EFI_SUCCESS)
+ efi_printk(sys_table_arg, "Failed to get initrd info\n");
+
+ return status;
+}
+
+static efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr)
+{
+ return efi_call_proto(efi_file_handle, read, handle, size, addr);
+}
+
+static efi_status_t efi_file_close(void *handle)
+{
+ return efi_call_proto(efi_file_handle, close, handle);
+}
+
/*
* Parse the ASCII string 'cmdline' for EFI options, denoted by the efi=
* option, e.g. efi=nochunk.
@@ -351,6 +414,14 @@
char *str;
/*
+ * Currently, the only efi= option we look for is 'nochunk', which
+ * is intended to work around known issues on certain x86 UEFI
+ * versions. So ignore for now on other architectures.
+ */
+ if (!IS_ENABLED(CONFIG_X86))
+ return EFI_SUCCESS;
+
+ /*
* If no EFI parameters were specified on the cmdline we've got
* nothing to do.
*/
@@ -523,7 +594,8 @@
size = files[j].size;
while (size) {
unsigned long chunksize;
- if (size > __chunk_size)
+
+ if (IS_ENABLED(CONFIG_X86) && size > __chunk_size)
chunksize = __chunk_size;
else
chunksize = size;
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index b98824e..71c4d0e 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -29,24 +29,8 @@
efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
void **__fh);
-efi_status_t efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
- efi_char16_t *filename_16, void **handle,
- u64 *file_sz);
-
-efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr);
-
-efi_status_t efi_file_close(void *handle);
-
unsigned long get_dram_base(efi_system_table_t *sys_table_arg);
-efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
- unsigned long orig_fdt_size,
- void *fdt, int new_fdt_size, char *cmdline_ptr,
- u64 initrd_addr, u64 initrd_size,
- efi_memory_desc_t *memory_map,
- unsigned long map_size, unsigned long desc_size,
- u32 desc_ver);
-
efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
void *handle,
unsigned long *new_fdt_addr,
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index a6a9311..260c4b4 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -16,13 +16,10 @@
#include "efistub.h"
-efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
- unsigned long orig_fdt_size,
- void *fdt, int new_fdt_size, char *cmdline_ptr,
- u64 initrd_addr, u64 initrd_size,
- efi_memory_desc_t *memory_map,
- unsigned long map_size, unsigned long desc_size,
- u32 desc_ver)
+static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
+ unsigned long orig_fdt_size,
+ void *fdt, int new_fdt_size, char *cmdline_ptr,
+ u64 initrd_addr, u64 initrd_size)
{
int node, num_rsv;
int status;
@@ -101,25 +98,23 @@
if (status)
goto fdt_set_fail;
- fdt_val64 = cpu_to_fdt64((u64)(unsigned long)memory_map);
+ fdt_val64 = U64_MAX; /* placeholder */
status = fdt_setprop(fdt, node, "linux,uefi-mmap-start",
&fdt_val64, sizeof(fdt_val64));
if (status)
goto fdt_set_fail;
- fdt_val32 = cpu_to_fdt32(map_size);
+ fdt_val32 = U32_MAX; /* placeholder */
status = fdt_setprop(fdt, node, "linux,uefi-mmap-size",
&fdt_val32, sizeof(fdt_val32));
if (status)
goto fdt_set_fail;
- fdt_val32 = cpu_to_fdt32(desc_size);
status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-size",
&fdt_val32, sizeof(fdt_val32));
if (status)
goto fdt_set_fail;
- fdt_val32 = cpu_to_fdt32(desc_ver);
status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-ver",
&fdt_val32, sizeof(fdt_val32));
if (status)
@@ -148,6 +143,43 @@
return EFI_LOAD_ERROR;
}
+static efi_status_t update_fdt_memmap(void *fdt, struct efi_boot_memmap *map)
+{
+ int node = fdt_path_offset(fdt, "/chosen");
+ u64 fdt_val64;
+ u32 fdt_val32;
+ int err;
+
+ if (node < 0)
+ return EFI_LOAD_ERROR;
+
+ fdt_val64 = cpu_to_fdt64((unsigned long)*map->map);
+ err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-start",
+ &fdt_val64, sizeof(fdt_val64));
+ if (err)
+ return EFI_LOAD_ERROR;
+
+ fdt_val32 = cpu_to_fdt32(*map->map_size);
+ err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-size",
+ &fdt_val32, sizeof(fdt_val32));
+ if (err)
+ return EFI_LOAD_ERROR;
+
+ fdt_val32 = cpu_to_fdt32(*map->desc_size);
+ err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-desc-size",
+ &fdt_val32, sizeof(fdt_val32));
+ if (err)
+ return EFI_LOAD_ERROR;
+
+ fdt_val32 = cpu_to_fdt32(*map->desc_ver);
+ err = fdt_setprop_inplace(fdt, node, "linux,uefi-mmap-desc-ver",
+ &fdt_val32, sizeof(fdt_val32));
+ if (err)
+ return EFI_LOAD_ERROR;
+
+ return EFI_SUCCESS;
+}
+
#ifndef EFI_FDT_ALIGN
#define EFI_FDT_ALIGN EFI_PAGE_SIZE
#endif
@@ -155,6 +187,7 @@
struct exit_boot_struct {
efi_memory_desc_t *runtime_map;
int *runtime_entry_count;
+ void *new_fdt_addr;
};
static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
@@ -170,7 +203,7 @@
efi_get_virtmap(*map->map, *map->map_size, *map->desc_size,
p->runtime_map, p->runtime_entry_count);
- return EFI_SUCCESS;
+ return update_fdt_memmap(p->new_fdt_addr, map);
}
/*
@@ -243,20 +276,10 @@
goto fail;
}
- /*
- * Now that we have done our final memory allocation (and free)
- * we can get the memory map key needed for
- * exit_boot_services().
- */
- status = efi_get_memory_map(sys_table, &map);
- if (status != EFI_SUCCESS)
- goto fail_free_new_fdt;
-
status = update_fdt(sys_table,
(void *)fdt_addr, fdt_size,
(void *)*new_fdt_addr, new_fdt_size,
- cmdline_ptr, initrd_addr, initrd_size,
- memory_map, map_size, desc_size, desc_ver);
+ cmdline_ptr, initrd_addr, initrd_size);
/* Succeeding the first time is the expected case. */
if (status == EFI_SUCCESS)
@@ -266,22 +289,19 @@
/*
* We need to allocate more space for the new
* device tree, so free existing buffer that is
- * too small. Also free memory map, as we will need
- * to get new one that reflects the free/alloc we do
- * on the device tree buffer.
+ * too small.
*/
efi_free(sys_table, new_fdt_size, *new_fdt_addr);
- sys_table->boottime->free_pool(memory_map);
new_fdt_size += EFI_PAGE_SIZE;
} else {
pr_efi_err(sys_table, "Unable to construct new device tree.\n");
- goto fail_free_mmap;
+ goto fail_free_new_fdt;
}
}
- sys_table->boottime->free_pool(memory_map);
priv.runtime_map = runtime_map;
priv.runtime_entry_count = &runtime_entry_count;
+ priv.new_fdt_addr = (void *)*new_fdt_addr;
status = efi_exit_boot_services(sys_table, handle, &map, &priv,
exit_boot_func);
@@ -319,9 +339,6 @@
pr_efi_err(sys_table, "Exit boot services failed.\n");
-fail_free_mmap:
- sys_table->boottime->free_pool(memory_map);
-
fail_free_new_fdt:
efi_free(sys_table, new_fdt_size, *new_fdt_addr);
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
new file mode 100644
index 0000000..6def402
--- /dev/null
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -0,0 +1,84 @@
+/*
+ * Secure boot handling.
+ *
+ * Copyright (C) 2013,2014 Linaro Limited
+ * Roy Franz <roy.franz@linaro.org
+ * Copyright (C) 2013 Red Hat, Inc.
+ * Mark Salter <msalter@redhat.com>
+ *
+ * This file is part of the Linux kernel, and is made available under the
+ * terms of the GNU General Public License version 2.
+ */
+#include <linux/efi.h>
+#include <asm/efi.h>
+
+/* BIOS variables */
+static const efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
+static const efi_char16_t const efi_SecureBoot_name[] = {
+ 'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0
+};
+static const efi_char16_t const efi_SetupMode_name[] = {
+ 'S', 'e', 't', 'u', 'p', 'M', 'o', 'd', 'e', 0
+};
+
+/* SHIM variables */
+static const efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID;
+static efi_char16_t const shim_MokSBState_name[] = {
+ 'M', 'o', 'k', 'S', 'B', 'S', 't', 'a', 't', 'e', 0
+};
+
+#define get_efi_var(name, vendor, ...) \
+ efi_call_runtime(get_variable, \
+ (efi_char16_t *)(name), (efi_guid_t *)(vendor), \
+ __VA_ARGS__);
+
+/*
+ * Determine whether we're in secure boot mode.
+ */
+enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg)
+{
+ u32 attr;
+ u8 secboot, setupmode, moksbstate;
+ unsigned long size;
+ efi_status_t status;
+
+ size = sizeof(secboot);
+ status = get_efi_var(efi_SecureBoot_name, &efi_variable_guid,
+ NULL, &size, &secboot);
+ if (status != EFI_SUCCESS)
+ goto out_efi_err;
+
+ size = sizeof(setupmode);
+ status = get_efi_var(efi_SetupMode_name, &efi_variable_guid,
+ NULL, &size, &setupmode);
+ if (status != EFI_SUCCESS)
+ goto out_efi_err;
+
+ if (secboot == 0 || setupmode == 1)
+ return efi_secureboot_mode_disabled;
+
+ /*
+ * See if a user has put the shim into insecure mode. If so, and if the
+ * variable doesn't have the runtime attribute set, we might as well
+ * honor that.
+ */
+ size = sizeof(moksbstate);
+ status = get_efi_var(shim_MokSBState_name, &shim_guid,
+ &attr, &size, &moksbstate);
+
+ /* If it fails, we don't care why. Default to secure */
+ if (status != EFI_SUCCESS)
+ goto secure_boot_enabled;
+ if (!(attr & EFI_VARIABLE_RUNTIME_ACCESS) && moksbstate == 1)
+ return efi_secureboot_mode_disabled;
+
+secure_boot_enabled:
+ pr_efi(sys_table_arg, "UEFI Secure Boot is enabled.\n");
+ return efi_secureboot_mode_enabled;
+
+out_efi_err:
+ pr_efi_err(sys_table_arg, "Could not determine UEFI Secure Boot status.\n");
+ if (status == EFI_NOT_FOUND)
+ return efi_secureboot_mode_disabled;
+ return efi_secureboot_mode_unknown;
+}
diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c
index 236004b..8986757 100644
--- a/drivers/firmware/efi/memattr.c
+++ b/drivers/firmware/efi/memattr.c
@@ -43,6 +43,7 @@
tbl_size = sizeof(*tbl) + tbl->num_entries * tbl->desc_size;
memblock_reserve(efi.mem_attr_table, tbl_size);
+ set_bit(EFI_MEM_ATTR, &efi.flags);
unmap:
early_memunmap(tbl, sizeof(*tbl));
@@ -174,8 +175,11 @@
md.phys_addr + size - 1,
efi_md_typeattr_format(buf, sizeof(buf), &md));
- if (valid)
+ if (valid) {
ret = fn(mm, &md);
+ if (ret)
+ pr_err("Error updating mappings, skipping subsequent md's\n");
+ }
}
memunmap(tbl);
return ret;
diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c
index f03ddec..7868644 100644
--- a/drivers/firmware/efi/memmap.c
+++ b/drivers/firmware/efi/memmap.c
@@ -9,6 +9,44 @@
#include <linux/efi.h>
#include <linux/io.h>
#include <asm/early_ioremap.h>
+#include <linux/memblock.h>
+#include <linux/slab.h>
+
+static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size)
+{
+ return memblock_alloc(size, 0);
+}
+
+static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size)
+{
+ unsigned int order = get_order(size);
+ struct page *p = alloc_pages(GFP_KERNEL, order);
+
+ if (!p)
+ return 0;
+
+ return PFN_PHYS(page_to_pfn(p));
+}
+
+/**
+ * efi_memmap_alloc - Allocate memory for the EFI memory map
+ * @num_entries: Number of entries in the allocated map.
+ *
+ * Depending on whether mm_init() has already been invoked or not,
+ * either memblock or "normal" page allocation is used.
+ *
+ * Returns the physical address of the allocated memory map on
+ * success, zero on failure.
+ */
+phys_addr_t __init efi_memmap_alloc(unsigned int num_entries)
+{
+ unsigned long size = num_entries * efi.memmap.desc_size;
+
+ if (slab_is_available())
+ return __efi_memmap_alloc_late(size);
+
+ return __efi_memmap_alloc_early(size);
+}
/**
* __efi_memmap_init - Common code for mapping the EFI memory map
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 86bf3b8..a07ae9e 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1723,7 +1723,7 @@
}
/**
- * _gpiochip_irqchip_add() - adds an irqchip to a gpiochip
+ * gpiochip_irqchip_add_key() - adds an irqchip to a gpiochip
* @gpiochip: the gpiochip to add the irqchip to
* @irqchip: the irqchip to add to the gpiochip
* @first_irq: if not dynamically assigned, the base (first) IRQ to
@@ -1749,13 +1749,13 @@
* the pins on the gpiochip can generate a unique IRQ. Everything else
* need to be open coded.
*/
-int _gpiochip_irqchip_add(struct gpio_chip *gpiochip,
- struct irq_chip *irqchip,
- unsigned int first_irq,
- irq_flow_handler_t handler,
- unsigned int type,
- bool nested,
- struct lock_class_key *lock_key)
+int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip,
+ struct irq_chip *irqchip,
+ unsigned int first_irq,
+ irq_flow_handler_t handler,
+ unsigned int type,
+ bool nested,
+ struct lock_class_key *lock_key)
{
struct device_node *of_node;
bool irq_base_set = false;
@@ -1840,7 +1840,7 @@
return 0;
}
-EXPORT_SYMBOL_GPL(_gpiochip_irqchip_add);
+EXPORT_SYMBOL_GPL(gpiochip_irqchip_add_key);
#else /* CONFIG_GPIOLIB_IRQCHIP */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 29d6d84..41e41f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -83,6 +83,13 @@
}
break;
}
+
+ if (!(*out_ring && (*out_ring)->adev)) {
+ DRM_ERROR("Ring %d is not initialized on IP %d\n",
+ ring, ip_type);
+ return -EINVAL;
+ }
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 9999dc7..ccb5e02 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2512,6 +2512,8 @@
WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+ WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+ ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
return 0;
}
@@ -2537,7 +2539,6 @@
int32_t hot_y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
struct drm_gem_object *obj;
struct amdgpu_bo *aobj;
int ret;
@@ -2578,7 +2579,9 @@
dce_v10_0_lock_cursor(crtc, true);
- if (hot_x != amdgpu_crtc->cursor_hot_x ||
+ if (width != amdgpu_crtc->cursor_width ||
+ height != amdgpu_crtc->cursor_height ||
+ hot_x != amdgpu_crtc->cursor_hot_x ||
hot_y != amdgpu_crtc->cursor_hot_y) {
int x, y;
@@ -2587,16 +2590,10 @@
dce_v10_0_cursor_move_locked(crtc, x, y);
- amdgpu_crtc->cursor_hot_x = hot_x;
- amdgpu_crtc->cursor_hot_y = hot_y;
- }
-
- if (width != amdgpu_crtc->cursor_width ||
- height != amdgpu_crtc->cursor_height) {
- WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
- (width - 1) << 16 | (height - 1));
amdgpu_crtc->cursor_width = width;
amdgpu_crtc->cursor_height = height;
+ amdgpu_crtc->cursor_hot_x = hot_x;
+ amdgpu_crtc->cursor_hot_y = hot_y;
}
dce_v10_0_show_cursor(crtc);
@@ -2620,7 +2617,6 @@
static void dce_v10_0_cursor_reset(struct drm_crtc *crtc)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
if (amdgpu_crtc->cursor_bo) {
dce_v10_0_lock_cursor(crtc, true);
@@ -2628,10 +2624,6 @@
dce_v10_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
amdgpu_crtc->cursor_y);
- WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
- (amdgpu_crtc->cursor_width - 1) << 16 |
- (amdgpu_crtc->cursor_height - 1));
-
dce_v10_0_show_cursor(crtc);
dce_v10_0_lock_cursor(crtc, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 2006abb..a7af5b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -2532,6 +2532,8 @@
WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+ WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+ ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
return 0;
}
@@ -2557,7 +2559,6 @@
int32_t hot_y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
struct drm_gem_object *obj;
struct amdgpu_bo *aobj;
int ret;
@@ -2598,7 +2599,9 @@
dce_v11_0_lock_cursor(crtc, true);
- if (hot_x != amdgpu_crtc->cursor_hot_x ||
+ if (width != amdgpu_crtc->cursor_width ||
+ height != amdgpu_crtc->cursor_height ||
+ hot_x != amdgpu_crtc->cursor_hot_x ||
hot_y != amdgpu_crtc->cursor_hot_y) {
int x, y;
@@ -2607,16 +2610,10 @@
dce_v11_0_cursor_move_locked(crtc, x, y);
- amdgpu_crtc->cursor_hot_x = hot_x;
- amdgpu_crtc->cursor_hot_y = hot_y;
- }
-
- if (width != amdgpu_crtc->cursor_width ||
- height != amdgpu_crtc->cursor_height) {
- WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
- (width - 1) << 16 | (height - 1));
amdgpu_crtc->cursor_width = width;
amdgpu_crtc->cursor_height = height;
+ amdgpu_crtc->cursor_hot_x = hot_x;
+ amdgpu_crtc->cursor_hot_y = hot_y;
}
dce_v11_0_show_cursor(crtc);
@@ -2640,7 +2637,6 @@
static void dce_v11_0_cursor_reset(struct drm_crtc *crtc)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
if (amdgpu_crtc->cursor_bo) {
dce_v11_0_lock_cursor(crtc, true);
@@ -2648,10 +2644,6 @@
dce_v11_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
amdgpu_crtc->cursor_y);
- WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
- (amdgpu_crtc->cursor_width - 1) << 16 |
- (amdgpu_crtc->cursor_height - 1));
-
dce_v11_0_show_cursor(crtc);
dce_v11_0_lock_cursor(crtc, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index b4e4ec6..39df6a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1859,6 +1859,8 @@
struct amdgpu_device *adev = crtc->dev->dev_private;
int xorigin = 0, yorigin = 0;
+ int w = amdgpu_crtc->cursor_width;
+
amdgpu_crtc->cursor_x = x;
amdgpu_crtc->cursor_y = y;
@@ -1878,6 +1880,8 @@
WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+ WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+ ((w - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
return 0;
}
@@ -1903,7 +1907,6 @@
int32_t hot_y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
struct drm_gem_object *obj;
struct amdgpu_bo *aobj;
int ret;
@@ -1944,7 +1947,9 @@
dce_v6_0_lock_cursor(crtc, true);
- if (hot_x != amdgpu_crtc->cursor_hot_x ||
+ if (width != amdgpu_crtc->cursor_width ||
+ height != amdgpu_crtc->cursor_height ||
+ hot_x != amdgpu_crtc->cursor_hot_x ||
hot_y != amdgpu_crtc->cursor_hot_y) {
int x, y;
@@ -1953,16 +1958,10 @@
dce_v6_0_cursor_move_locked(crtc, x, y);
- amdgpu_crtc->cursor_hot_x = hot_x;
- amdgpu_crtc->cursor_hot_y = hot_y;
- }
-
- if (width != amdgpu_crtc->cursor_width ||
- height != amdgpu_crtc->cursor_height) {
- WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
- (width - 1) << 16 | (height - 1));
amdgpu_crtc->cursor_width = width;
amdgpu_crtc->cursor_height = height;
+ amdgpu_crtc->cursor_hot_x = hot_x;
+ amdgpu_crtc->cursor_hot_y = hot_y;
}
dce_v6_0_show_cursor(crtc);
@@ -1986,7 +1985,6 @@
static void dce_v6_0_cursor_reset(struct drm_crtc *crtc)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
if (amdgpu_crtc->cursor_bo) {
dce_v6_0_lock_cursor(crtc, true);
@@ -1994,10 +1992,6 @@
dce_v6_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
amdgpu_crtc->cursor_y);
- WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
- (amdgpu_crtc->cursor_width - 1) << 16 |
- (amdgpu_crtc->cursor_height - 1));
-
dce_v6_0_show_cursor(crtc);
dce_v6_0_lock_cursor(crtc, false);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 584abe8..28102bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2363,6 +2363,8 @@
WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+ WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+ ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
return 0;
}
@@ -2388,7 +2390,6 @@
int32_t hot_y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
struct drm_gem_object *obj;
struct amdgpu_bo *aobj;
int ret;
@@ -2429,7 +2430,9 @@
dce_v8_0_lock_cursor(crtc, true);
- if (hot_x != amdgpu_crtc->cursor_hot_x ||
+ if (width != amdgpu_crtc->cursor_width ||
+ height != amdgpu_crtc->cursor_height ||
+ hot_x != amdgpu_crtc->cursor_hot_x ||
hot_y != amdgpu_crtc->cursor_hot_y) {
int x, y;
@@ -2438,16 +2441,10 @@
dce_v8_0_cursor_move_locked(crtc, x, y);
- amdgpu_crtc->cursor_hot_x = hot_x;
- amdgpu_crtc->cursor_hot_y = hot_y;
- }
-
- if (width != amdgpu_crtc->cursor_width ||
- height != amdgpu_crtc->cursor_height) {
- WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
- (width - 1) << 16 | (height - 1));
amdgpu_crtc->cursor_width = width;
amdgpu_crtc->cursor_height = height;
+ amdgpu_crtc->cursor_hot_x = hot_x;
+ amdgpu_crtc->cursor_hot_y = hot_y;
}
dce_v8_0_show_cursor(crtc);
@@ -2471,7 +2468,6 @@
static void dce_v8_0_cursor_reset(struct drm_crtc *crtc)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
if (amdgpu_crtc->cursor_bo) {
dce_v8_0_lock_cursor(crtc, true);
@@ -2479,10 +2475,6 @@
dce_v8_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
amdgpu_crtc->cursor_y);
- WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
- (amdgpu_crtc->cursor_width - 1) << 16 |
- (amdgpu_crtc->cursor_height - 1));
-
dce_v8_0_show_cursor(crtc);
dce_v8_0_lock_cursor(crtc, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index 762f8e8..e9a1768 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -627,11 +627,8 @@
static void dce_virtual_encoder_destroy(struct drm_encoder *encoder)
{
- struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
-
- kfree(amdgpu_encoder->enc_priv);
drm_encoder_cleanup(encoder);
- kfree(amdgpu_encoder);
+ kfree(encoder);
}
static const struct drm_encoder_funcs dce_virtual_encoder_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 45a573e..0635829 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -44,6 +44,7 @@
MODULE_FIRMWARE("radeon/pitcairn_mc.bin");
MODULE_FIRMWARE("radeon/verde_mc.bin");
MODULE_FIRMWARE("radeon/oland_mc.bin");
+MODULE_FIRMWARE("radeon/si58_mc.bin");
#define MC_SEQ_MISC0__MT__MASK 0xf0000000
#define MC_SEQ_MISC0__MT__GDDR1 0x10000000
@@ -113,6 +114,7 @@
const char *chip_name;
char fw_name[30];
int err;
+ bool is_58_fw = false;
DRM_DEBUG("\n");
@@ -135,7 +137,14 @@
default: BUG();
}
- snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+ /* this memory configuration requires special firmware */
+ if (((RREG32(mmMC_SEQ_MISC0) & 0xff000000) >> 24) == 0x58)
+ is_58_fw = true;
+
+ if (is_58_fw)
+ snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+ else
+ snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
err = request_firmware(&adev->mc.fw, fw_name, adev->dev);
if (err)
goto out;
@@ -245,6 +254,9 @@
}
WREG32(mmHDP_REG_COHERENCY_FLUSH_CNTL, 0);
+ if (adev->mode_info.num_crtc)
+ amdgpu_display_set_vga_render_state(adev, false);
+
gmc_v6_0_mc_stop(adev, &save);
if (gmc_v6_0_wait_for_idle((void *)adev)) {
@@ -274,7 +286,6 @@
dev_warn(adev->dev, "Wait for MC idle timedout !\n");
}
gmc_v6_0_mc_resume(adev, &save);
- amdgpu_display_set_vga_render_state(adev, false);
}
static int gmc_v6_0_mc_init(struct amdgpu_device *adev)
@@ -463,19 +474,11 @@
WREG32(mmVM_CONTEXT1_CNTL,
VM_CONTEXT1_CNTL__ENABLE_CONTEXT_MASK |
(1UL << VM_CONTEXT1_CNTL__PAGE_TABLE_DEPTH__SHIFT) |
- ((amdgpu_vm_block_size - 9) << VM_CONTEXT1_CNTL__PAGE_TABLE_BLOCK_SIZE__SHIFT) |
- VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
- VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
- VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
- VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
- VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
- VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
- VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
- VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
- VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
- VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
- VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
- VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK);
+ ((amdgpu_vm_block_size - 9) << VM_CONTEXT1_CNTL__PAGE_TABLE_BLOCK_SIZE__SHIFT));
+ if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
+ gmc_v6_0_set_fault_enable_default(adev, false);
+ else
+ gmc_v6_0_set_fault_enable_default(adev, true);
gmc_v6_0_gart_flush_gpu_tlb(adev, 0);
dev_info(adev->dev, "PCIE GART of %uM enabled (table at 0x%016llX).\n",
@@ -754,7 +757,10 @@
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+ if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
+ return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+ else
+ return 0;
}
static int gmc_v6_0_sw_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 10bedfa..6e150db 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -64,6 +64,7 @@
MODULE_FIRMWARE("radeon/oland_k_smc.bin");
MODULE_FIRMWARE("radeon/hainan_smc.bin");
MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
+MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
union power_info {
struct _ATOM_POWERPLAY_INFO info;
@@ -3487,17 +3488,6 @@
(adev->pdev->device == 0x6817) ||
(adev->pdev->device == 0x6806))
max_mclk = 120000;
- } else if (adev->asic_type == CHIP_OLAND) {
- if ((adev->pdev->revision == 0xC7) ||
- (adev->pdev->revision == 0x80) ||
- (adev->pdev->revision == 0x81) ||
- (adev->pdev->revision == 0x83) ||
- (adev->pdev->revision == 0x87) ||
- (adev->pdev->device == 0x6604) ||
- (adev->pdev->device == 0x6605)) {
- max_sclk = 75000;
- max_mclk = 80000;
- }
} else if (adev->asic_type == CHIP_HAINAN) {
if ((adev->pdev->revision == 0x81) ||
(adev->pdev->revision == 0x83) ||
@@ -3506,7 +3496,6 @@
(adev->pdev->device == 0x6665) ||
(adev->pdev->device == 0x6667)) {
max_sclk = 75000;
- max_mclk = 80000;
}
}
/* Apply dpm quirks */
@@ -7713,10 +7702,11 @@
((adev->pdev->device == 0x6660) ||
(adev->pdev->device == 0x6663) ||
(adev->pdev->device == 0x6665) ||
- (adev->pdev->device == 0x6667))) ||
- ((adev->pdev->revision == 0xc3) &&
- (adev->pdev->device == 0x6665)))
+ (adev->pdev->device == 0x6667))))
chip_name = "hainan_k";
+ else if ((adev->pdev->revision == 0xc3) &&
+ (adev->pdev->device == 0x6665))
+ chip_name = "banks_k_2";
else
chip_name = "hainan";
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 96444e4..7fb9137 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -40,13 +40,14 @@
#include "smu/smu_7_0_1_sh_mask.h"
static void uvd_v4_2_mc_resume(struct amdgpu_device *adev);
-static void uvd_v4_2_init_cg(struct amdgpu_device *adev);
static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev);
static void uvd_v4_2_set_irq_funcs(struct amdgpu_device *adev);
static int uvd_v4_2_start(struct amdgpu_device *adev);
static void uvd_v4_2_stop(struct amdgpu_device *adev);
static int uvd_v4_2_set_clockgating_state(void *handle,
enum amd_clockgating_state state);
+static void uvd_v4_2_set_dcm(struct amdgpu_device *adev,
+ bool sw_mode);
/**
* uvd_v4_2_ring_get_rptr - get read pointer
*
@@ -140,7 +141,8 @@
return r;
}
-
+static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev,
+ bool enable);
/**
* uvd_v4_2_hw_init - start and test UVD block
*
@@ -155,8 +157,7 @@
uint32_t tmp;
int r;
- uvd_v4_2_init_cg(adev);
- uvd_v4_2_set_clockgating_state(adev, AMD_CG_STATE_GATE);
+ uvd_v4_2_enable_mgcg(adev, true);
amdgpu_asic_set_uvd_clocks(adev, 10000, 10000);
r = uvd_v4_2_start(adev);
if (r)
@@ -266,11 +267,13 @@
struct amdgpu_ring *ring = &adev->uvd.ring;
uint32_t rb_bufsz;
int i, j, r;
-
/* disable byte swapping */
u32 lmi_swap_cntl = 0;
u32 mp_swap_cntl = 0;
+ WREG32(mmUVD_CGC_GATE, 0);
+ uvd_v4_2_set_dcm(adev, true);
+
uvd_v4_2_mc_resume(adev);
/* disable interupt */
@@ -406,6 +409,8 @@
/* Unstall UMC and register bus */
WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8));
+
+ uvd_v4_2_set_dcm(adev, false);
}
/**
@@ -619,19 +624,6 @@
WREG32_UVD_CTX(ixUVD_CGC_CTRL2, tmp2);
}
-static void uvd_v4_2_init_cg(struct amdgpu_device *adev)
-{
- bool hw_mode = true;
-
- if (hw_mode) {
- uvd_v4_2_set_dcm(adev, false);
- } else {
- u32 tmp = RREG32(mmUVD_CGC_CTRL);
- tmp &= ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
- WREG32(mmUVD_CGC_CTRL, tmp);
- }
-}
-
static bool uvd_v4_2_is_idle(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -685,17 +677,6 @@
static int uvd_v4_2_set_clockgating_state(void *handle,
enum amd_clockgating_state state)
{
- bool gate = false;
- struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
- if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
- return 0;
-
- if (state == AMD_CG_STATE_GATE)
- gate = true;
-
- uvd_v4_2_enable_mgcg(adev, gate);
-
return 0;
}
@@ -711,9 +692,6 @@
*/
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
- return 0;
-
if (state == AMD_PG_STATE_GATE) {
uvd_v4_2_stop(adev);
return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 5fb0b7f..37ca685 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -43,9 +43,13 @@
#define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT 0x04
#define GRBM_GFX_INDEX__VCE_INSTANCE_MASK 0x10
+#define GRBM_GFX_INDEX__VCE_ALL_PIPE 0x07
+
#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0 0x8616
#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1 0x8617
#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2 0x8618
+#define mmGRBM_GFX_INDEX_DEFAULT 0xE0000000
+
#define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK 0x02
#define VCE_V3_0_FW_SIZE (384 * 1024)
@@ -54,6 +58,9 @@
#define FW_52_8_3 ((52 << 24) | (8 << 16) | (3 << 8))
+#define GET_VCE_INSTANCE(i) ((i) << GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT \
+ | GRBM_GFX_INDEX__VCE_ALL_PIPE)
+
static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx);
static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev);
static void vce_v3_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -175,7 +182,7 @@
WREG32(mmVCE_UENC_CLOCK_GATING_2, data);
data = RREG32(mmVCE_UENC_REG_CLOCK_GATING);
- data &= ~0xffc00000;
+ data &= ~0x3ff;
WREG32(mmVCE_UENC_REG_CLOCK_GATING, data);
data = RREG32(mmVCE_UENC_DMA_DCLK_CTRL);
@@ -249,7 +256,7 @@
if (adev->vce.harvest_config & (1 << idx))
continue;
- WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx);
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
vce_v3_0_mc_resume(adev, idx);
WREG32_FIELD(VCE_STATUS, JOB_BUSY, 1);
@@ -273,7 +280,7 @@
}
}
- WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
mutex_unlock(&adev->grbm_idx_mutex);
return 0;
@@ -288,7 +295,7 @@
if (adev->vce.harvest_config & (1 << idx))
continue;
- WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx);
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
if (adev->asic_type >= CHIP_STONEY)
WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x200001);
@@ -306,7 +313,7 @@
vce_v3_0_set_vce_sw_clock_gating(adev, false);
}
- WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
mutex_unlock(&adev->grbm_idx_mutex);
return 0;
@@ -586,17 +593,17 @@
* VCE team suggest use bit 3--bit 6 for busy status check
*/
mutex_lock(&adev->grbm_idx_mutex);
- WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0);
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) {
srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1);
srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1);
}
- WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0x10);
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) {
srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1);
srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1);
}
- WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0);
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
mutex_unlock(&adev->grbm_idx_mutex);
if (srbm_soft_reset) {
@@ -734,7 +741,7 @@
if (adev->vce.harvest_config & (1 << i))
continue;
- WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, i);
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(i));
if (enable) {
/* initialize VCE_CLOCK_GATING_A: Clock ON/OFF delay */
@@ -753,7 +760,7 @@
vce_v3_0_set_vce_sw_clock_gating(adev, enable);
}
- WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
mutex_unlock(&adev->grbm_idx_mutex);
return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
index b0c63c5..6bb79c9 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
@@ -200,7 +200,7 @@
cgs_set_clockgating_state(
hwmgr->device,
AMD_IP_BLOCK_TYPE_VCE,
- AMD_CG_STATE_UNGATE);
+ AMD_CG_STATE_GATE);
cgs_set_powergating_state(
hwmgr->device,
AMD_IP_BLOCK_TYPE_VCE,
@@ -218,7 +218,7 @@
cgs_set_clockgating_state(
hwmgr->device,
AMD_IP_BLOCK_TYPE_VCE,
- AMD_PG_STATE_GATE);
+ AMD_PG_STATE_UNGATE);
cz_dpm_update_vce_dpm(hwmgr);
cz_enable_disable_vce_dpm(hwmgr, true);
return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
index 4b14f25..0fb4e8c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
@@ -1402,14 +1402,22 @@
cz_hwmgr->vce_dpm.hard_min_clk,
PPSMC_MSG_SetEclkHardMin));
} else {
- /*EPR# 419220 -HW limitation to to */
- cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk;
- smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
- PPSMC_MSG_SetEclkHardMin,
- cz_get_eclk_level(hwmgr,
- cz_hwmgr->vce_dpm.hard_min_clk,
- PPSMC_MSG_SetEclkHardMin));
-
+ /*Program HardMin based on the vce_arbiter.ecclk */
+ if (hwmgr->vce_arbiter.ecclk == 0) {
+ smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+ PPSMC_MSG_SetEclkHardMin, 0);
+ /* disable ECLK DPM 0. Otherwise VCE could hang if
+ * switching SCLK from DPM 0 to 6/7 */
+ smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+ PPSMC_MSG_SetEclkSoftMin, 1);
+ } else {
+ cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk;
+ smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+ PPSMC_MSG_SetEclkHardMin,
+ cz_get_eclk_level(hwmgr,
+ cz_hwmgr->vce_dpm.hard_min_clk,
+ PPSMC_MSG_SetEclkHardMin));
+ }
}
return 0;
}
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 908011d..7abda94 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -113,6 +113,7 @@
struct ttm_bo_kmap_obj cache_kmap;
int next_cursor;
bool support_wide_screen;
+ bool DisableP2A;
enum ast_tx_chip tx_chip_type;
u8 dp501_maxclk;
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index f75c642..533e762 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -124,6 +124,12 @@
} else
*need_post = false;
+ /* Check P2A Access */
+ ast->DisableP2A = true;
+ data = ast_read32(ast, 0xf004);
+ if (data != 0xFFFFFFFF)
+ ast->DisableP2A = false;
+
/* Check if we support wide screen */
switch (ast->chip) {
case AST1180:
@@ -140,15 +146,17 @@
ast->support_wide_screen = true;
else {
ast->support_wide_screen = false;
- /* Read SCU7c (silicon revision register) */
- ast_write32(ast, 0xf004, 0x1e6e0000);
- ast_write32(ast, 0xf000, 0x1);
- data = ast_read32(ast, 0x1207c);
- data &= 0x300;
- if (ast->chip == AST2300 && data == 0x0) /* ast1300 */
- ast->support_wide_screen = true;
- if (ast->chip == AST2400 && data == 0x100) /* ast1400 */
- ast->support_wide_screen = true;
+ if (ast->DisableP2A == false) {
+ /* Read SCU7c (silicon revision register) */
+ ast_write32(ast, 0xf004, 0x1e6e0000);
+ ast_write32(ast, 0xf000, 0x1);
+ data = ast_read32(ast, 0x1207c);
+ data &= 0x300;
+ if (ast->chip == AST2300 && data == 0x0) /* ast1300 */
+ ast->support_wide_screen = true;
+ if (ast->chip == AST2400 && data == 0x100) /* ast1400 */
+ ast->support_wide_screen = true;
+ }
}
break;
}
@@ -216,80 +224,81 @@
uint32_t data, data2;
uint32_t denum, num, div, ref_pll;
- ast_write32(ast, 0xf004, 0x1e6e0000);
- ast_write32(ast, 0xf000, 0x1);
-
-
- ast_write32(ast, 0x10000, 0xfc600309);
-
- do {
- if (pci_channel_offline(dev->pdev))
- return -EIO;
- } while (ast_read32(ast, 0x10000) != 0x01);
- data = ast_read32(ast, 0x10004);
-
- if (data & 0x40)
+ if (ast->DisableP2A)
+ {
ast->dram_bus_width = 16;
+ ast->dram_type = AST_DRAM_1Gx16;
+ ast->mclk = 396;
+ }
else
- ast->dram_bus_width = 32;
+ {
+ ast_write32(ast, 0xf004, 0x1e6e0000);
+ ast_write32(ast, 0xf000, 0x1);
+ data = ast_read32(ast, 0x10004);
- if (ast->chip == AST2300 || ast->chip == AST2400) {
- switch (data & 0x03) {
- case 0:
- ast->dram_type = AST_DRAM_512Mx16;
- break;
- default:
- case 1:
- ast->dram_type = AST_DRAM_1Gx16;
+ if (data & 0x40)
+ ast->dram_bus_width = 16;
+ else
+ ast->dram_bus_width = 32;
+
+ if (ast->chip == AST2300 || ast->chip == AST2400) {
+ switch (data & 0x03) {
+ case 0:
+ ast->dram_type = AST_DRAM_512Mx16;
+ break;
+ default:
+ case 1:
+ ast->dram_type = AST_DRAM_1Gx16;
+ break;
+ case 2:
+ ast->dram_type = AST_DRAM_2Gx16;
+ break;
+ case 3:
+ ast->dram_type = AST_DRAM_4Gx16;
+ break;
+ }
+ } else {
+ switch (data & 0x0c) {
+ case 0:
+ case 4:
+ ast->dram_type = AST_DRAM_512Mx16;
+ break;
+ case 8:
+ if (data & 0x40)
+ ast->dram_type = AST_DRAM_1Gx16;
+ else
+ ast->dram_type = AST_DRAM_512Mx32;
+ break;
+ case 0xc:
+ ast->dram_type = AST_DRAM_1Gx32;
+ break;
+ }
+ }
+
+ data = ast_read32(ast, 0x10120);
+ data2 = ast_read32(ast, 0x10170);
+ if (data2 & 0x2000)
+ ref_pll = 14318;
+ else
+ ref_pll = 12000;
+
+ denum = data & 0x1f;
+ num = (data & 0x3fe0) >> 5;
+ data = (data & 0xc000) >> 14;
+ switch (data) {
+ case 3:
+ div = 0x4;
break;
case 2:
- ast->dram_type = AST_DRAM_2Gx16;
+ case 1:
+ div = 0x2;
break;
- case 3:
- ast->dram_type = AST_DRAM_4Gx16;
+ default:
+ div = 0x1;
break;
}
- } else {
- switch (data & 0x0c) {
- case 0:
- case 4:
- ast->dram_type = AST_DRAM_512Mx16;
- break;
- case 8:
- if (data & 0x40)
- ast->dram_type = AST_DRAM_1Gx16;
- else
- ast->dram_type = AST_DRAM_512Mx32;
- break;
- case 0xc:
- ast->dram_type = AST_DRAM_1Gx32;
- break;
- }
+ ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000);
}
-
- data = ast_read32(ast, 0x10120);
- data2 = ast_read32(ast, 0x10170);
- if (data2 & 0x2000)
- ref_pll = 14318;
- else
- ref_pll = 12000;
-
- denum = data & 0x1f;
- num = (data & 0x3fe0) >> 5;
- data = (data & 0xc000) >> 14;
- switch (data) {
- case 3:
- div = 0x4;
- break;
- case 2:
- case 1:
- div = 0x2;
- break;
- default:
- div = 0x1;
- break;
- }
- ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000);
return 0;
}
diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c
index 810c51d..5331ee1 100644
--- a/drivers/gpu/drm/ast/ast_post.c
+++ b/drivers/gpu/drm/ast/ast_post.c
@@ -379,12 +379,20 @@
ast_open_key(ast);
ast_set_def_ext_reg(dev);
- if (ast->chip == AST2300 || ast->chip == AST2400)
- ast_init_dram_2300(dev);
- else
- ast_init_dram_reg(dev);
+ if (ast->DisableP2A == false)
+ {
+ if (ast->chip == AST2300 || ast->chip == AST2400)
+ ast_init_dram_2300(dev);
+ else
+ ast_init_dram_reg(dev);
- ast_init_3rdtx(dev);
+ ast_init_3rdtx(dev);
+ }
+ else
+ {
+ if (ast->tx_chip_type != AST_TX_NONE)
+ ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80); /* Enable DVO */
+ }
}
/* AST 2300 DRAM settings */
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index eb9bf87..18eefdc 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1382,6 +1382,7 @@
pm_runtime_enable(dev);
+ pm_runtime_get_sync(dev);
phy_power_on(dp->phy);
analogix_dp_init_dp(dp);
@@ -1414,9 +1415,15 @@
goto err_disable_pm_runtime;
}
+ phy_power_off(dp->phy);
+ pm_runtime_put(dev);
+
return 0;
err_disable_pm_runtime:
+
+ phy_power_off(dp->phy);
+ pm_runtime_put(dev);
pm_runtime_disable(dev);
return ret;
diff --git a/drivers/gpu/drm/cirrus/Kconfig b/drivers/gpu/drm/cirrus/Kconfig
index 04b3c16..7f4cc6e 100644
--- a/drivers/gpu/drm/cirrus/Kconfig
+++ b/drivers/gpu/drm/cirrus/Kconfig
@@ -7,3 +7,12 @@
This is a KMS driver for emulated cirrus device in qemu.
It is *NOT* intended for real cirrus devices. This requires
the modesetting userspace X.org driver.
+
+ Cirrus is obsolete, the hardware was designed in the 90ies
+ and can't keep up with todays needs. More background:
+ https://www.kraxel.org/blog/2014/10/qemu-using-cirrus-considered-harmful/
+
+ Better alternatives are:
+ - stdvga (DRM_BOCHS, qemu -vga std, default in qemu 2.2+)
+ - qxl (DRM_QXL, qemu -vga qxl, works best with spice)
+ - virtio (DRM_VIRTIO_GPU), qemu -vga virtio)
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 6069748..fdfb1ec 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -291,15 +291,15 @@
EXPORT_SYMBOL(drm_atomic_get_crtc_state);
static void set_out_fence_for_crtc(struct drm_atomic_state *state,
- struct drm_crtc *crtc, s64 __user *fence_ptr)
+ struct drm_crtc *crtc, s32 __user *fence_ptr)
{
state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = fence_ptr;
}
-static s64 __user *get_out_fence_for_crtc(struct drm_atomic_state *state,
+static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state,
struct drm_crtc *crtc)
{
- s64 __user *fence_ptr;
+ s32 __user *fence_ptr;
fence_ptr = state->crtcs[drm_crtc_index(crtc)].out_fence_ptr;
state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = NULL;
@@ -512,7 +512,7 @@
state->color_mgmt_changed |= replaced;
return ret;
} else if (property == config->prop_out_fence_ptr) {
- s64 __user *fence_ptr = u64_to_user_ptr(val);
+ s32 __user *fence_ptr = u64_to_user_ptr(val);
if (!fence_ptr)
return 0;
@@ -1915,7 +1915,7 @@
*/
struct drm_out_fence_state {
- s64 __user *out_fence_ptr;
+ s32 __user *out_fence_ptr;
struct sync_file *sync_file;
int fd;
};
@@ -1952,7 +1952,7 @@
return 0;
for_each_crtc_in_state(state, crtc, crtc_state, i) {
- u64 __user *fence_ptr;
+ s32 __user *fence_ptr;
fence_ptr = get_out_fence_for_crtc(crtc_state->state, crtc);
@@ -2032,13 +2032,16 @@
}
for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ struct drm_pending_vblank_event *event = crtc_state->event;
/*
- * TEST_ONLY and PAGE_FLIP_EVENT are mutually
- * exclusive, if they weren't, this code should be
- * called on success for TEST_ONLY too.
+ * Free the allocated event. drm_atomic_helper_setup_commit
+ * can allocate an event too, so only free it if it's ours
+ * to prevent a double free in drm_atomic_state_clear.
*/
- if (crtc_state->event)
- drm_event_cancel_free(dev, &crtc_state->event->base);
+ if (event && (event->base.fence || event->base.file_priv)) {
+ drm_event_cancel_free(dev, &event->base);
+ crtc_state->event = NULL;
+ }
}
if (!fence_state)
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 34f757b..4594477 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1666,9 +1666,6 @@
funcs = plane->helper_private;
- if (!drm_atomic_helper_framebuffer_changed(dev, state, plane_state->crtc))
- continue;
-
if (funcs->prepare_fb) {
ret = funcs->prepare_fb(plane, plane_state);
if (ret)
@@ -1685,9 +1682,6 @@
if (j >= i)
continue;
- if (!drm_atomic_helper_framebuffer_changed(dev, state, plane_state->crtc))
- continue;
-
funcs = plane->helper_private;
if (funcs->cleanup_fb)
@@ -1954,9 +1948,6 @@
for_each_plane_in_state(old_state, plane, plane_state, i) {
const struct drm_plane_helper_funcs *funcs;
- if (!drm_atomic_helper_framebuffer_changed(dev, old_state, plane_state->crtc))
- continue;
-
funcs = plane->helper_private;
if (funcs->cleanup_fb)
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 5a45262..7a7019a 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -225,6 +225,7 @@
INIT_LIST_HEAD(&connector->probed_modes);
INIT_LIST_HEAD(&connector->modes);
+ mutex_init(&connector->mutex);
connector->edid_blob_ptr = NULL;
connector->status = connector_status_unknown;
@@ -359,6 +360,8 @@
connector->funcs->atomic_destroy_state(connector,
connector->state);
+ mutex_destroy(&connector->mutex);
+
memset(connector, 0, sizeof(*connector));
}
EXPORT_SYMBOL(drm_connector_cleanup);
@@ -374,14 +377,18 @@
*/
int drm_connector_register(struct drm_connector *connector)
{
- int ret;
+ int ret = 0;
- if (connector->registered)
+ if (!connector->dev->registered)
return 0;
+ mutex_lock(&connector->mutex);
+ if (connector->registered)
+ goto unlock;
+
ret = drm_sysfs_connector_add(connector);
if (ret)
- return ret;
+ goto unlock;
ret = drm_debugfs_connector_add(connector);
if (ret) {
@@ -397,12 +404,14 @@
drm_mode_object_register(connector->dev, &connector->base);
connector->registered = true;
- return 0;
+ goto unlock;
err_debugfs:
drm_debugfs_connector_remove(connector);
err_sysfs:
drm_sysfs_connector_remove(connector);
+unlock:
+ mutex_unlock(&connector->mutex);
return ret;
}
EXPORT_SYMBOL(drm_connector_register);
@@ -415,8 +424,11 @@
*/
void drm_connector_unregister(struct drm_connector *connector)
{
- if (!connector->registered)
+ mutex_lock(&connector->mutex);
+ if (!connector->registered) {
+ mutex_unlock(&connector->mutex);
return;
+ }
if (connector->funcs->early_unregister)
connector->funcs->early_unregister(connector);
@@ -425,6 +437,7 @@
drm_debugfs_connector_remove(connector);
connector->registered = false;
+ mutex_unlock(&connector->mutex);
}
EXPORT_SYMBOL(drm_connector_unregister);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index aa64448..f59771d 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1817,7 +1817,7 @@
mgr->payloads[i].vcpi = req_payload.vcpi;
} else if (mgr->payloads[i].num_slots) {
mgr->payloads[i].num_slots = 0;
- drm_dp_destroy_payload_step1(mgr, port, port->vcpi.vcpi, &mgr->payloads[i]);
+ drm_dp_destroy_payload_step1(mgr, port, mgr->payloads[i].vcpi, &mgr->payloads[i]);
req_payload.payload_state = mgr->payloads[i].payload_state;
mgr->payloads[i].start_slot = 0;
}
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index a525751..6594b40 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -745,6 +745,8 @@
if (ret)
goto err_minors;
+ dev->registered = true;
+
if (dev->driver->load) {
ret = dev->driver->load(dev, flags);
if (ret)
@@ -785,6 +787,8 @@
drm_lastclose(dev);
+ dev->registered = false;
+
if (drm_core_check_feature(dev, DRIVER_MODESET))
drm_modeset_unregister_all(dev);
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index ac6a352..e6b19bc 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1460,6 +1460,13 @@
return NULL;
mode->type |= DRM_MODE_TYPE_USERDEF;
+ /* fix up 1368x768: GFT/CVT can't express 1366 width due to alignment */
+ if (cmd->xres == 1366 && mode->hdisplay == 1368) {
+ mode->hdisplay = 1366;
+ mode->hsync_start--;
+ mode->hsync_end--;
+ drm_mode_set_name(mode);
+ }
drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
return mode;
}
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index ac953f0..cf8f012 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -143,8 +143,18 @@
}
if (dev->mode_config.delayed_event) {
+ /*
+ * FIXME:
+ *
+ * Use short (1s) delay to handle the initial delayed event.
+ * This delay should not be needed, but Optimus/nouveau will
+ * fail in a mysterious way if the delayed event is handled as
+ * soon as possible like it is done in
+ * drm_helper_probe_single_connector_modes() in case the poll
+ * was enabled before.
+ */
poll = true;
- delay = 0;
+ delay = HZ;
}
if (poll)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index 169ac96..fe0e85b 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -116,9 +116,14 @@
struct list_head list;
bool found;
+ /*
+ * XXX: The DRM_MM_SEARCH_BELOW is really a hack to trick
+ * drm_mm into giving out a low IOVA after address space
+ * rollover. This needs a proper fix.
+ */
ret = drm_mm_insert_node_in_range(&mmu->mm, node,
size, 0, mmu->last_iova, ~0UL,
- DRM_MM_SEARCH_DEFAULT);
+ mmu->last_iova ? DRM_MM_SEARCH_DEFAULT : DRM_MM_SEARCH_BELOW);
if (ret != -ENOSPC)
break;
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 6ca1f31..75eeb83 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -46,7 +46,8 @@
BIT_CLKS_ENABLED,
BIT_IRQS_ENABLED,
BIT_WIN_UPDATED,
- BIT_SUSPENDED
+ BIT_SUSPENDED,
+ BIT_REQUEST_UPDATE
};
struct decon_context {
@@ -141,12 +142,6 @@
m->crtc_vsync_end = m->crtc_vsync_start + 1;
}
- decon_set_bits(ctx, DECON_VIDCON0, VIDCON0_ENVID, 0);
-
- /* enable clock gate */
- val = CMU_CLKGAGE_MODE_SFR_F | CMU_CLKGAGE_MODE_MEM_F;
- writel(val, ctx->addr + DECON_CMU);
-
if (ctx->out_type & (IFTYPE_I80 | I80_HW_TRG))
decon_setup_trigger(ctx);
@@ -315,6 +310,7 @@
/* window enable */
decon_set_bits(ctx, DECON_WINCONx(win), WINCONx_ENWIN_F, ~0);
+ set_bit(BIT_REQUEST_UPDATE, &ctx->flags);
}
static void decon_disable_plane(struct exynos_drm_crtc *crtc,
@@ -327,6 +323,7 @@
return;
decon_set_bits(ctx, DECON_WINCONx(win), WINCONx_ENWIN_F, 0);
+ set_bit(BIT_REQUEST_UPDATE, &ctx->flags);
}
static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
@@ -340,8 +337,8 @@
for (i = ctx->first_win; i < WINDOWS_NR; i++)
decon_shadow_protect_win(ctx, i, false);
- /* standalone update */
- decon_set_bits(ctx, DECON_UPDATE, STANDALONE_UPDATE_F, ~0);
+ if (test_and_clear_bit(BIT_REQUEST_UPDATE, &ctx->flags))
+ decon_set_bits(ctx, DECON_UPDATE, STANDALONE_UPDATE_F, ~0);
if (ctx->out_type & IFTYPE_I80)
set_bit(BIT_WIN_UPDATED, &ctx->flags);
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 0d41ebc..f7bce86 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -37,13 +37,6 @@
#include "i915_drv.h"
#include "gvt.h"
-#define MB_TO_BYTES(mb) ((mb) << 20ULL)
-#define BYTES_TO_MB(b) ((b) >> 20ULL)
-
-#define HOST_LOW_GM_SIZE MB_TO_BYTES(128)
-#define HOST_HIGH_GM_SIZE MB_TO_BYTES(384)
-#define HOST_FENCE 4
-
static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm)
{
struct intel_gvt *gvt = vgpu->gvt;
@@ -165,6 +158,14 @@
POSTING_READ(fence_reg_lo);
}
+static void _clear_vgpu_fence(struct intel_vgpu *vgpu)
+{
+ int i;
+
+ for (i = 0; i < vgpu_fence_sz(vgpu); i++)
+ intel_vgpu_write_fence(vgpu, i, 0);
+}
+
static void free_vgpu_fence(struct intel_vgpu *vgpu)
{
struct intel_gvt *gvt = vgpu->gvt;
@@ -178,9 +179,9 @@
intel_runtime_pm_get(dev_priv);
mutex_lock(&dev_priv->drm.struct_mutex);
+ _clear_vgpu_fence(vgpu);
for (i = 0; i < vgpu_fence_sz(vgpu); i++) {
reg = vgpu->fence.regs[i];
- intel_vgpu_write_fence(vgpu, i, 0);
list_add_tail(®->link,
&dev_priv->mm.fence_list);
}
@@ -208,13 +209,14 @@
continue;
list_del(pos);
vgpu->fence.regs[i] = reg;
- intel_vgpu_write_fence(vgpu, i, 0);
if (++i == vgpu_fence_sz(vgpu))
break;
}
if (i != vgpu_fence_sz(vgpu))
goto out_free_fence;
+ _clear_vgpu_fence(vgpu);
+
mutex_unlock(&dev_priv->drm.struct_mutex);
intel_runtime_pm_put(dev_priv);
return 0;
@@ -314,6 +316,22 @@
}
/**
+ * intel_vgpu_reset_resource - reset resource state owned by a vGPU
+ * @vgpu: a vGPU
+ *
+ * This function is used to reset resource state owned by a vGPU.
+ *
+ */
+void intel_vgpu_reset_resource(struct intel_vgpu *vgpu)
+{
+ struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+
+ intel_runtime_pm_get(dev_priv);
+ _clear_vgpu_fence(vgpu);
+ intel_runtime_pm_put(dev_priv);
+}
+
+/**
* intel_alloc_vgpu_resource - allocate HW resource for a vGPU
* @vgpu: vGPU
* @param: vGPU creation params
diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index 711c31c..4a6a2ed 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -282,3 +282,77 @@
}
return 0;
}
+
+/**
+ * intel_vgpu_init_cfg_space - init vGPU configuration space when create vGPU
+ *
+ * @vgpu: a vGPU
+ * @primary: is the vGPU presented as primary
+ *
+ */
+void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu,
+ bool primary)
+{
+ struct intel_gvt *gvt = vgpu->gvt;
+ const struct intel_gvt_device_info *info = &gvt->device_info;
+ u16 *gmch_ctl;
+ int i;
+
+ memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space,
+ info->cfg_space_size);
+
+ if (!primary) {
+ vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] =
+ INTEL_GVT_PCI_CLASS_VGA_OTHER;
+ vgpu_cfg_space(vgpu)[PCI_CLASS_PROG] =
+ INTEL_GVT_PCI_CLASS_VGA_OTHER;
+ }
+
+ /* Show guest that there isn't any stolen memory.*/
+ gmch_ctl = (u16 *)(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_GMCH_CONTROL);
+ *gmch_ctl &= ~(BDW_GMCH_GMS_MASK << BDW_GMCH_GMS_SHIFT);
+
+ intel_vgpu_write_pci_bar(vgpu, PCI_BASE_ADDRESS_2,
+ gvt_aperture_pa_base(gvt), true);
+
+ vgpu_cfg_space(vgpu)[PCI_COMMAND] &= ~(PCI_COMMAND_IO
+ | PCI_COMMAND_MEMORY
+ | PCI_COMMAND_MASTER);
+ /*
+ * Clear the bar upper 32bit and let guest to assign the new value
+ */
+ memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4);
+ memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4);
+ memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4);
+
+ for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) {
+ vgpu->cfg_space.bar[i].size = pci_resource_len(
+ gvt->dev_priv->drm.pdev, i * 2);
+ vgpu->cfg_space.bar[i].tracked = false;
+ }
+}
+
+/**
+ * intel_vgpu_reset_cfg_space - reset vGPU configuration space
+ *
+ * @vgpu: a vGPU
+ *
+ */
+void intel_vgpu_reset_cfg_space(struct intel_vgpu *vgpu)
+{
+ u8 cmd = vgpu_cfg_space(vgpu)[PCI_COMMAND];
+ bool primary = vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] !=
+ INTEL_GVT_PCI_CLASS_VGA_OTHER;
+
+ if (cmd & PCI_COMMAND_MEMORY) {
+ trap_gttmmio(vgpu, false);
+ map_aperture(vgpu, false);
+ }
+
+ /**
+ * Currently we only do such reset when vGPU is not
+ * owned by any VM, so we simply restore entire cfg
+ * space to default value.
+ */
+ intel_vgpu_init_cfg_space(vgpu, primary);
+}
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index d26a092..e456398 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -481,7 +481,6 @@
(s->vgpu->gvt->device_info.gmadr_bytes_in_cmd >> 2)
static unsigned long bypass_scan_mask = 0;
-static bool bypass_batch_buffer_scan = true;
/* ring ALL, type = 0 */
static struct sub_op_bits sub_op_mi[] = {
@@ -1525,9 +1524,6 @@
{
struct intel_gvt *gvt = s->vgpu->gvt;
- if (bypass_batch_buffer_scan)
- return 0;
-
if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)) {
/* BDW decides privilege based on address space */
if (cmd_val(s, 0) & (1 << 8))
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index f32bb6f..3408373 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -364,58 +364,30 @@
#define get_desc_from_elsp_dwords(ed, i) \
((struct execlist_ctx_descriptor_format *)&((ed)->data[i * 2]))
-
-#define BATCH_BUFFER_ADDR_MASK ((1UL << 32) - (1U << 2))
-#define BATCH_BUFFER_ADDR_HIGH_MASK ((1UL << 16) - (1U))
-static int set_gma_to_bb_cmd(struct intel_shadow_bb_entry *entry_obj,
- unsigned long add, int gmadr_bytes)
-{
- if (WARN_ON(gmadr_bytes != 4 && gmadr_bytes != 8))
- return -1;
-
- *((u32 *)(entry_obj->bb_start_cmd_va + (1 << 2))) = add &
- BATCH_BUFFER_ADDR_MASK;
- if (gmadr_bytes == 8) {
- *((u32 *)(entry_obj->bb_start_cmd_va + (2 << 2))) =
- add & BATCH_BUFFER_ADDR_HIGH_MASK;
- }
-
- return 0;
-}
-
static void prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
{
- int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd;
+ const int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd;
+ struct intel_shadow_bb_entry *entry_obj;
/* pin the gem object to ggtt */
- if (!list_empty(&workload->shadow_bb)) {
- struct intel_shadow_bb_entry *entry_obj =
- list_first_entry(&workload->shadow_bb,
- struct intel_shadow_bb_entry,
- list);
- struct intel_shadow_bb_entry *temp;
+ list_for_each_entry(entry_obj, &workload->shadow_bb, list) {
+ struct i915_vma *vma;
- list_for_each_entry_safe(entry_obj, temp, &workload->shadow_bb,
- list) {
- struct i915_vma *vma;
-
- vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0,
- 4, 0);
- if (IS_ERR(vma)) {
- gvt_err("Cannot pin\n");
- return;
- }
-
- /* FIXME: we are not tracking our pinned VMA leaving it
- * up to the core to fix up the stray pin_count upon
- * free.
- */
-
- /* update the relocate gma with shadow batch buffer*/
- set_gma_to_bb_cmd(entry_obj,
- i915_ggtt_offset(vma),
- gmadr_bytes);
+ vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0, 4, 0);
+ if (IS_ERR(vma)) {
+ gvt_err("Cannot pin\n");
+ return;
}
+
+ /* FIXME: we are not tracking our pinned VMA leaving it
+ * up to the core to fix up the stray pin_count upon
+ * free.
+ */
+
+ /* update the relocate gma with shadow batch buffer*/
+ entry_obj->bb_start_cmd_va[1] = i915_ggtt_offset(vma);
+ if (gmadr_bytes == 8)
+ entry_obj->bb_start_cmd_va[2] = 0;
}
}
@@ -826,7 +798,7 @@
INIT_LIST_HEAD(&vgpu->workload_q_head[i]);
}
- vgpu->workloads = kmem_cache_create("gvt-g vgpu workload",
+ vgpu->workloads = kmem_cache_create("gvt-g_vgpu_workload",
sizeof(struct intel_vgpu_workload), 0,
SLAB_HWCACHE_ALIGN,
NULL);
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 6c5fdf5..47dec4a 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -240,15 +240,8 @@
static u64 read_pte64(struct drm_i915_private *dev_priv, unsigned long index)
{
void __iomem *addr = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + index;
- u64 pte;
-#ifdef readq
- pte = readq(addr);
-#else
- pte = ioread32(addr);
- pte |= (u64)ioread32(addr + 4) << 32;
-#endif
- return pte;
+ return readq(addr);
}
static void write_pte64(struct drm_i915_private *dev_priv,
@@ -256,12 +249,8 @@
{
void __iomem *addr = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + index;
-#ifdef writeq
writeq(pte, addr);
-#else
- iowrite32((u32)pte, addr);
- iowrite32(pte >> 32, addr + 4);
-#endif
+
I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
POSTING_READ(GFX_FLSH_CNTL_GEN6);
}
@@ -1380,8 +1369,7 @@
info->gtt_entry_size;
mem = kzalloc(mm->has_shadow_page_table ?
mm->page_table_entry_size * 2
- : mm->page_table_entry_size,
- GFP_ATOMIC);
+ : mm->page_table_entry_size, GFP_KERNEL);
if (!mem)
return -ENOMEM;
mm->virtual_page_table = mem;
@@ -1532,7 +1520,7 @@
struct intel_vgpu_mm *mm;
int ret;
- mm = kzalloc(sizeof(*mm), GFP_ATOMIC);
+ mm = kzalloc(sizeof(*mm), GFP_KERNEL);
if (!mm) {
ret = -ENOMEM;
goto fail;
@@ -1886,30 +1874,27 @@
struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
int page_entry_num = GTT_PAGE_SIZE >>
vgpu->gvt->device_info.gtt_entry_size_shift;
- struct page *scratch_pt;
+ void *scratch_pt;
unsigned long mfn;
int i;
- void *p;
if (WARN_ON(type < GTT_TYPE_PPGTT_PTE_PT || type >= GTT_TYPE_MAX))
return -EINVAL;
- scratch_pt = alloc_page(GFP_KERNEL | GFP_ATOMIC | __GFP_ZERO);
+ scratch_pt = (void *)get_zeroed_page(GFP_KERNEL);
if (!scratch_pt) {
gvt_err("fail to allocate scratch page\n");
return -ENOMEM;
}
- p = kmap_atomic(scratch_pt);
- mfn = intel_gvt_hypervisor_virt_to_mfn(p);
+ mfn = intel_gvt_hypervisor_virt_to_mfn(scratch_pt);
if (mfn == INTEL_GVT_INVALID_ADDR) {
- gvt_err("fail to translate vaddr:0x%llx\n", (u64)p);
- kunmap_atomic(p);
- __free_page(scratch_pt);
+ gvt_err("fail to translate vaddr:0x%lx\n", (unsigned long)scratch_pt);
+ free_page((unsigned long)scratch_pt);
return -EFAULT;
}
gtt->scratch_pt[type].page_mfn = mfn;
- gtt->scratch_pt[type].page = scratch_pt;
+ gtt->scratch_pt[type].page = virt_to_page(scratch_pt);
gvt_dbg_mm("vgpu%d create scratch_pt: type %d mfn=0x%lx\n",
vgpu->id, type, mfn);
@@ -1918,7 +1903,7 @@
* scratch_pt[type] indicate the scratch pt/scratch page used by the
* 'type' pt.
* e.g. scratch_pt[GTT_TYPE_PPGTT_PDE_PT] is used by
- * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scatch_pt it self
+ * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scratch_pt it self
* is GTT_TYPE_PPGTT_PTE_PT, and full filled by scratch page mfn.
*/
if (type > GTT_TYPE_PPGTT_PTE_PT && type < GTT_TYPE_MAX) {
@@ -1936,11 +1921,9 @@
se.val64 |= PPAT_CACHED_INDEX;
for (i = 0; i < page_entry_num; i++)
- ops->set_entry(p, &se, i, false, 0, vgpu);
+ ops->set_entry(scratch_pt, &se, i, false, 0, vgpu);
}
- kunmap_atomic(p);
-
return 0;
}
@@ -2208,7 +2191,7 @@
int intel_gvt_init_gtt(struct intel_gvt *gvt)
{
int ret;
- void *page_addr;
+ void *page;
gvt_dbg_core("init gtt\n");
@@ -2221,17 +2204,14 @@
return -ENODEV;
}
- gvt->gtt.scratch_ggtt_page =
- alloc_page(GFP_KERNEL | GFP_ATOMIC | __GFP_ZERO);
- if (!gvt->gtt.scratch_ggtt_page) {
+ page = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!page) {
gvt_err("fail to allocate scratch ggtt page\n");
return -ENOMEM;
}
+ gvt->gtt.scratch_ggtt_page = virt_to_page(page);
- page_addr = page_address(gvt->gtt.scratch_ggtt_page);
-
- gvt->gtt.scratch_ggtt_mfn =
- intel_gvt_hypervisor_virt_to_mfn(page_addr);
+ gvt->gtt.scratch_ggtt_mfn = intel_gvt_hypervisor_virt_to_mfn(page);
if (gvt->gtt.scratch_ggtt_mfn == INTEL_GVT_INVALID_ADDR) {
gvt_err("fail to translate scratch ggtt page\n");
__free_page(gvt->gtt.scratch_ggtt_page);
@@ -2297,3 +2277,30 @@
for (offset = 0; offset < num_entries; offset++)
ops->set_entry(NULL, &e, index + offset, false, 0, vgpu);
}
+
+/**
+ * intel_vgpu_reset_gtt - reset the all GTT related status
+ * @vgpu: a vGPU
+ * @dmlr: true for vGPU Device Model Level Reset, false for GT Reset
+ *
+ * This function is called from vfio core to reset reset all
+ * GTT related status, including GGTT, PPGTT, scratch page.
+ *
+ */
+void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr)
+{
+ int i;
+
+ ppgtt_free_all_shadow_page(vgpu);
+ if (!dmlr)
+ return;
+
+ intel_vgpu_reset_ggtt(vgpu);
+
+ /* clear scratch page for security */
+ for (i = GTT_TYPE_PPGTT_PTE_PT; i < GTT_TYPE_MAX; i++) {
+ if (vgpu->gtt.scratch_pt[i].page != NULL)
+ memset(page_address(vgpu->gtt.scratch_pt[i].page),
+ 0, PAGE_SIZE);
+ }
+}
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index b315ab3..f88eb5e 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -208,6 +208,7 @@
void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu);
extern int intel_gvt_init_gtt(struct intel_gvt *gvt);
+extern void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr);
extern void intel_gvt_clean_gtt(struct intel_gvt *gvt);
extern struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu,
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 398877c..e6bf5c5 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -201,6 +201,8 @@
intel_gvt_hypervisor_host_exit(&dev_priv->drm.pdev->dev, gvt);
intel_gvt_clean_vgpu_types(gvt);
+ idr_destroy(&gvt->vgpu_idr);
+
kfree(dev_priv->gvt);
dev_priv->gvt = NULL;
}
@@ -237,6 +239,8 @@
gvt_dbg_core("init gvt device\n");
+ idr_init(&gvt->vgpu_idr);
+
mutex_init(&gvt->lock);
gvt->dev_priv = dev_priv;
@@ -244,7 +248,7 @@
ret = intel_gvt_setup_mmio_info(gvt);
if (ret)
- return ret;
+ goto out_clean_idr;
ret = intel_gvt_load_firmware(gvt);
if (ret)
@@ -313,6 +317,8 @@
intel_gvt_free_firmware(gvt);
out_clean_mmio_info:
intel_gvt_clean_mmio_info(gvt);
+out_clean_idr:
+ idr_destroy(&gvt->vgpu_idr);
kfree(gvt);
return ret;
}
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 0af1701..e227caf 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -323,6 +323,7 @@
int intel_vgpu_alloc_resource(struct intel_vgpu *vgpu,
struct intel_vgpu_creation_params *param);
+void intel_vgpu_reset_resource(struct intel_vgpu *vgpu);
void intel_vgpu_free_resource(struct intel_vgpu *vgpu);
void intel_vgpu_write_fence(struct intel_vgpu *vgpu,
u32 fence, u64 value);
@@ -375,6 +376,8 @@
struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
struct intel_vgpu_type *type);
void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu);
+void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
+ unsigned int engine_mask);
void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu);
@@ -411,6 +414,10 @@
int intel_gvt_ggtt_h2g_index(struct intel_vgpu *vgpu, unsigned long h_index,
unsigned long *g_index);
+void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu,
+ bool primary);
+void intel_vgpu_reset_cfg_space(struct intel_vgpu *vgpu);
+
int intel_vgpu_emulate_cfg_read(struct intel_vgpu *vgpu, unsigned int offset,
void *p_data, unsigned int bytes);
@@ -424,7 +431,6 @@
int intel_vgpu_init_opregion(struct intel_vgpu *vgpu, u32 gpa);
int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci);
-int setup_vgpu_mmio(struct intel_vgpu *vgpu);
void populate_pvinfo_page(struct intel_vgpu *vgpu);
struct intel_gvt_ops {
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 5228097..ab2ea15 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -93,7 +93,8 @@
static int new_mmio_info(struct intel_gvt *gvt,
u32 offset, u32 flags, u32 size,
u32 addr_mask, u32 ro_mask, u32 device,
- void *read, void *write)
+ int (*read)(struct intel_vgpu *, unsigned int, void *, unsigned int),
+ int (*write)(struct intel_vgpu *, unsigned int, void *, unsigned int))
{
struct intel_gvt_mmio_info *info, *p;
u32 start, end, i;
@@ -219,7 +220,7 @@
default:
/*should not hit here*/
gvt_err("invalid forcewake offset 0x%x\n", offset);
- return 1;
+ return -EINVAL;
}
} else {
ack_reg_offset = FORCEWAKE_ACK_HSW_REG;
@@ -230,77 +231,45 @@
return 0;
}
-static int handle_device_reset(struct intel_vgpu *vgpu, unsigned int offset,
- void *p_data, unsigned int bytes, unsigned long bitmap)
-{
- struct intel_gvt_workload_scheduler *scheduler =
- &vgpu->gvt->scheduler;
-
- vgpu->resetting = true;
-
- intel_vgpu_stop_schedule(vgpu);
- /*
- * The current_vgpu will set to NULL after stopping the
- * scheduler when the reset is triggered by current vgpu.
- */
- if (scheduler->current_vgpu == NULL) {
- mutex_unlock(&vgpu->gvt->lock);
- intel_gvt_wait_vgpu_idle(vgpu);
- mutex_lock(&vgpu->gvt->lock);
- }
-
- intel_vgpu_reset_execlist(vgpu, bitmap);
-
- /* full GPU reset */
- if (bitmap == 0xff) {
- mutex_unlock(&vgpu->gvt->lock);
- intel_vgpu_clean_gtt(vgpu);
- mutex_lock(&vgpu->gvt->lock);
- setup_vgpu_mmio(vgpu);
- populate_pvinfo_page(vgpu);
- intel_vgpu_init_gtt(vgpu);
- }
-
- vgpu->resetting = false;
-
- return 0;
-}
-
static int gdrst_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
- void *p_data, unsigned int bytes)
+ void *p_data, unsigned int bytes)
{
+ unsigned int engine_mask = 0;
u32 data;
- u64 bitmap = 0;
write_vreg(vgpu, offset, p_data, bytes);
data = vgpu_vreg(vgpu, offset);
if (data & GEN6_GRDOM_FULL) {
gvt_dbg_mmio("vgpu%d: request full GPU reset\n", vgpu->id);
- bitmap = 0xff;
+ engine_mask = ALL_ENGINES;
+ } else {
+ if (data & GEN6_GRDOM_RENDER) {
+ gvt_dbg_mmio("vgpu%d: request RCS reset\n", vgpu->id);
+ engine_mask |= (1 << RCS);
+ }
+ if (data & GEN6_GRDOM_MEDIA) {
+ gvt_dbg_mmio("vgpu%d: request VCS reset\n", vgpu->id);
+ engine_mask |= (1 << VCS);
+ }
+ if (data & GEN6_GRDOM_BLT) {
+ gvt_dbg_mmio("vgpu%d: request BCS Reset\n", vgpu->id);
+ engine_mask |= (1 << BCS);
+ }
+ if (data & GEN6_GRDOM_VECS) {
+ gvt_dbg_mmio("vgpu%d: request VECS Reset\n", vgpu->id);
+ engine_mask |= (1 << VECS);
+ }
+ if (data & GEN8_GRDOM_MEDIA2) {
+ gvt_dbg_mmio("vgpu%d: request VCS2 Reset\n", vgpu->id);
+ if (HAS_BSD2(vgpu->gvt->dev_priv))
+ engine_mask |= (1 << VCS2);
+ }
}
- if (data & GEN6_GRDOM_RENDER) {
- gvt_dbg_mmio("vgpu%d: request RCS reset\n", vgpu->id);
- bitmap |= (1 << RCS);
- }
- if (data & GEN6_GRDOM_MEDIA) {
- gvt_dbg_mmio("vgpu%d: request VCS reset\n", vgpu->id);
- bitmap |= (1 << VCS);
- }
- if (data & GEN6_GRDOM_BLT) {
- gvt_dbg_mmio("vgpu%d: request BCS Reset\n", vgpu->id);
- bitmap |= (1 << BCS);
- }
- if (data & GEN6_GRDOM_VECS) {
- gvt_dbg_mmio("vgpu%d: request VECS Reset\n", vgpu->id);
- bitmap |= (1 << VECS);
- }
- if (data & GEN8_GRDOM_MEDIA2) {
- gvt_dbg_mmio("vgpu%d: request VCS2 Reset\n", vgpu->id);
- if (HAS_BSD2(vgpu->gvt->dev_priv))
- bitmap |= (1 << VCS2);
- }
- return handle_device_reset(vgpu, offset, p_data, bytes, bitmap);
+
+ intel_gvt_reset_vgpu_locked(vgpu, false, engine_mask);
+
+ return 0;
}
static int gmbus_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
@@ -974,7 +943,7 @@
return 0;
}
-static bool sbi_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+static int sbi_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
void *p_data, unsigned int bytes)
{
u32 data;
@@ -1366,7 +1335,6 @@
static int gvt_reg_tlb_control_handler(struct intel_vgpu *vgpu,
unsigned int offset, void *p_data, unsigned int bytes)
{
- int rc = 0;
unsigned int id = 0;
write_vreg(vgpu, offset, p_data, bytes);
@@ -1389,12 +1357,11 @@
id = VECS;
break;
default:
- rc = -EINVAL;
- break;
+ return -EINVAL;
}
set_bit(id, (void *)vgpu->tlb_handle_pending);
- return rc;
+ return 0;
}
static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index faaae07..3f656e3 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -230,8 +230,8 @@
return NULL;
}
-static ssize_t available_instance_show(struct kobject *kobj, struct device *dev,
- char *buf)
+static ssize_t available_instances_show(struct kobject *kobj,
+ struct device *dev, char *buf)
{
struct intel_vgpu_type *type;
unsigned int num = 0;
@@ -269,12 +269,12 @@
type->fence);
}
-static MDEV_TYPE_ATTR_RO(available_instance);
+static MDEV_TYPE_ATTR_RO(available_instances);
static MDEV_TYPE_ATTR_RO(device_api);
static MDEV_TYPE_ATTR_RO(description);
static struct attribute *type_attrs[] = {
- &mdev_type_attr_available_instance.attr,
+ &mdev_type_attr_available_instances.attr,
&mdev_type_attr_device_api.attr,
&mdev_type_attr_description.attr,
NULL,
@@ -398,6 +398,7 @@
struct intel_vgpu_type *type;
struct device *pdev;
void *gvt;
+ int ret;
pdev = mdev_parent_dev(mdev);
gvt = kdev_to_i915(pdev)->gvt;
@@ -406,13 +407,15 @@
if (!type) {
gvt_err("failed to find type %s to create\n",
kobject_name(kobj));
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
vgpu = intel_gvt_ops->vgpu_create(gvt, type);
if (IS_ERR_OR_NULL(vgpu)) {
- gvt_err("create intel vgpu failed\n");
- return -EINVAL;
+ ret = vgpu == NULL ? -EFAULT : PTR_ERR(vgpu);
+ gvt_err("failed to create intel vgpu: %d\n", ret);
+ goto out;
}
INIT_WORK(&vgpu->vdev.release_work, intel_vgpu_release_work);
@@ -422,7 +425,10 @@
gvt_dbg_core("intel_vgpu_create succeeded for mdev: %s\n",
dev_name(mdev_dev(mdev)));
- return 0;
+ ret = 0;
+
+out:
+ return ret;
}
static int intel_vgpu_remove(struct mdev_device *mdev)
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index 09c9450..4df078b 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -125,25 +125,12 @@
if (WARN_ON(!reg_is_mmio(gvt, offset + bytes - 1)))
goto err;
- mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4));
- if (!mmio && !vgpu->mmio.disable_warn_untrack) {
- gvt_err("vgpu%d: read untracked MMIO %x len %d val %x\n",
- vgpu->id, offset, bytes, *(u32 *)p_data);
-
- if (offset == 0x206c) {
- gvt_err("------------------------------------------\n");
- gvt_err("vgpu%d: likely triggers a gfx reset\n",
- vgpu->id);
- gvt_err("------------------------------------------\n");
- vgpu->mmio.disable_warn_untrack = true;
- }
- }
-
if (!intel_gvt_mmio_is_unalign(gvt, offset)) {
if (WARN_ON(!IS_ALIGNED(offset, bytes)))
goto err;
}
+ mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4));
if (mmio) {
if (!intel_gvt_mmio_is_unalign(gvt, mmio->offset)) {
if (WARN_ON(offset + bytes > mmio->offset + mmio->size))
@@ -152,9 +139,23 @@
goto err;
}
ret = mmio->read(vgpu, offset, p_data, bytes);
- } else
+ } else {
ret = intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes);
+ if (!vgpu->mmio.disable_warn_untrack) {
+ gvt_err("vgpu%d: read untracked MMIO %x(%dB) val %x\n",
+ vgpu->id, offset, bytes, *(u32 *)p_data);
+
+ if (offset == 0x206c) {
+ gvt_err("------------------------------------------\n");
+ gvt_err("vgpu%d: likely triggers a gfx reset\n",
+ vgpu->id);
+ gvt_err("------------------------------------------\n");
+ vgpu->mmio.disable_warn_untrack = true;
+ }
+ }
+ }
+
if (ret)
goto err;
@@ -302,3 +303,56 @@
mutex_unlock(&gvt->lock);
return ret;
}
+
+
+/**
+ * intel_vgpu_reset_mmio - reset virtual MMIO space
+ * @vgpu: a vGPU
+ *
+ */
+void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu)
+{
+ struct intel_gvt *gvt = vgpu->gvt;
+ const struct intel_gvt_device_info *info = &gvt->device_info;
+
+ memcpy(vgpu->mmio.vreg, gvt->firmware.mmio, info->mmio_size);
+ memcpy(vgpu->mmio.sreg, gvt->firmware.mmio, info->mmio_size);
+
+ vgpu_vreg(vgpu, GEN6_GT_THREAD_STATUS_REG) = 0;
+
+ /* set the bit 0:2(Core C-State ) to C0 */
+ vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0;
+}
+
+/**
+ * intel_vgpu_init_mmio - init MMIO space
+ * @vgpu: a vGPU
+ *
+ * Returns:
+ * Zero on success, negative error code if failed
+ */
+int intel_vgpu_init_mmio(struct intel_vgpu *vgpu)
+{
+ const struct intel_gvt_device_info *info = &vgpu->gvt->device_info;
+
+ vgpu->mmio.vreg = vzalloc(info->mmio_size * 2);
+ if (!vgpu->mmio.vreg)
+ return -ENOMEM;
+
+ vgpu->mmio.sreg = vgpu->mmio.vreg + info->mmio_size;
+
+ intel_vgpu_reset_mmio(vgpu);
+
+ return 0;
+}
+
+/**
+ * intel_vgpu_clean_mmio - clean MMIO space
+ * @vgpu: a vGPU
+ *
+ */
+void intel_vgpu_clean_mmio(struct intel_vgpu *vgpu)
+{
+ vfree(vgpu->mmio.vreg);
+ vgpu->mmio.vreg = vgpu->mmio.sreg = NULL;
+}
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 87d5b5e..3bc620f 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -86,6 +86,10 @@
*offset; \
})
+int intel_vgpu_init_mmio(struct intel_vgpu *vgpu);
+void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu);
+void intel_vgpu_clean_mmio(struct intel_vgpu *vgpu);
+
int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa);
int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, u64 pa,
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index 81cd921..d9fb41a 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -36,9 +36,9 @@
vgpu->id))
return -EINVAL;
- vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_ATOMIC |
- GFP_DMA32 | __GFP_ZERO,
- INTEL_GVT_OPREGION_PORDER);
+ vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_KERNEL |
+ __GFP_ZERO,
+ get_order(INTEL_GVT_OPREGION_SIZE));
if (!vgpu_opregion(vgpu)->va)
return -ENOMEM;
@@ -97,7 +97,7 @@
if (intel_gvt_host.hypervisor_type == INTEL_GVT_HYPERVISOR_XEN) {
map_vgpu_opregion(vgpu, false);
free_pages((unsigned long)vgpu_opregion(vgpu)->va,
- INTEL_GVT_OPREGION_PORDER);
+ get_order(INTEL_GVT_OPREGION_SIZE));
vgpu_opregion(vgpu)->va = NULL;
}
diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h
index 0dfe789..fbd023a 100644
--- a/drivers/gpu/drm/i915/gvt/reg.h
+++ b/drivers/gpu/drm/i915/gvt/reg.h
@@ -50,8 +50,7 @@
#define INTEL_GVT_OPREGION_PARM 0x204
#define INTEL_GVT_OPREGION_PAGES 2
-#define INTEL_GVT_OPREGION_PORDER 1
-#define INTEL_GVT_OPREGION_SIZE (2 * 4096)
+#define INTEL_GVT_OPREGION_SIZE (INTEL_GVT_OPREGION_PAGES * PAGE_SIZE)
#define VGT_SPRSTRIDE(pipe) _PIPE(pipe, _SPRA_STRIDE, _PLANE_STRIDE_2_B)
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 4db2422..e91885d 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -350,13 +350,15 @@
{
struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
struct intel_vgpu_workload *workload;
+ struct intel_vgpu *vgpu;
int event;
mutex_lock(&gvt->lock);
workload = scheduler->current_workload[ring_id];
+ vgpu = workload->vgpu;
- if (!workload->status && !workload->vgpu->resetting) {
+ if (!workload->status && !vgpu->resetting) {
wait_event(workload->shadow_ctx_status_wq,
!atomic_read(&workload->shadow_ctx_active));
@@ -364,8 +366,7 @@
for_each_set_bit(event, workload->pending_events,
INTEL_GVT_EVENT_MAX)
- intel_vgpu_trigger_virtual_event(workload->vgpu,
- event);
+ intel_vgpu_trigger_virtual_event(vgpu, event);
}
gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -373,11 +374,10 @@
scheduler->current_workload[ring_id] = NULL;
- atomic_dec(&workload->vgpu->running_workload_num);
-
list_del_init(&workload->list);
workload->complete(workload);
+ atomic_dec(&vgpu->running_workload_num);
wake_up(&scheduler->workload_complete_wq);
mutex_unlock(&gvt->lock);
}
@@ -459,11 +459,11 @@
gvt_dbg_sched("will complete workload %p\n, status: %d\n",
workload, workload->status);
- complete_current_workload(gvt, ring_id);
-
if (workload->req)
i915_gem_request_put(fetch_and_zero(&workload->req));
+ complete_current_workload(gvt, ring_id);
+
if (need_force_wake)
intel_uncore_forcewake_put(gvt->dev_priv,
FORCEWAKE_ALL);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 3b30c28..2833dfa 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -113,7 +113,7 @@
struct drm_i915_gem_object *obj;
void *va;
unsigned long len;
- void *bb_start_cmd_va;
+ u32 *bb_start_cmd_va;
};
#define workload_q_head(vgpu, ring_id) \
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 536d2b9..7295bc8 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -35,79 +35,6 @@
#include "gvt.h"
#include "i915_pvinfo.h"
-static void clean_vgpu_mmio(struct intel_vgpu *vgpu)
-{
- vfree(vgpu->mmio.vreg);
- vgpu->mmio.vreg = vgpu->mmio.sreg = NULL;
-}
-
-int setup_vgpu_mmio(struct intel_vgpu *vgpu)
-{
- struct intel_gvt *gvt = vgpu->gvt;
- const struct intel_gvt_device_info *info = &gvt->device_info;
-
- if (vgpu->mmio.vreg)
- memset(vgpu->mmio.vreg, 0, info->mmio_size * 2);
- else {
- vgpu->mmio.vreg = vzalloc(info->mmio_size * 2);
- if (!vgpu->mmio.vreg)
- return -ENOMEM;
- }
-
- vgpu->mmio.sreg = vgpu->mmio.vreg + info->mmio_size;
-
- memcpy(vgpu->mmio.vreg, gvt->firmware.mmio, info->mmio_size);
- memcpy(vgpu->mmio.sreg, gvt->firmware.mmio, info->mmio_size);
-
- vgpu_vreg(vgpu, GEN6_GT_THREAD_STATUS_REG) = 0;
-
- /* set the bit 0:2(Core C-State ) to C0 */
- vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0;
- return 0;
-}
-
-static void setup_vgpu_cfg_space(struct intel_vgpu *vgpu,
- struct intel_vgpu_creation_params *param)
-{
- struct intel_gvt *gvt = vgpu->gvt;
- const struct intel_gvt_device_info *info = &gvt->device_info;
- u16 *gmch_ctl;
- int i;
-
- memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space,
- info->cfg_space_size);
-
- if (!param->primary) {
- vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] =
- INTEL_GVT_PCI_CLASS_VGA_OTHER;
- vgpu_cfg_space(vgpu)[PCI_CLASS_PROG] =
- INTEL_GVT_PCI_CLASS_VGA_OTHER;
- }
-
- /* Show guest that there isn't any stolen memory.*/
- gmch_ctl = (u16 *)(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_GMCH_CONTROL);
- *gmch_ctl &= ~(BDW_GMCH_GMS_MASK << BDW_GMCH_GMS_SHIFT);
-
- intel_vgpu_write_pci_bar(vgpu, PCI_BASE_ADDRESS_2,
- gvt_aperture_pa_base(gvt), true);
-
- vgpu_cfg_space(vgpu)[PCI_COMMAND] &= ~(PCI_COMMAND_IO
- | PCI_COMMAND_MEMORY
- | PCI_COMMAND_MASTER);
- /*
- * Clear the bar upper 32bit and let guest to assign the new value
- */
- memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4);
- memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4);
- memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4);
-
- for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) {
- vgpu->cfg_space.bar[i].size = pci_resource_len(
- gvt->dev_priv->drm.pdev, i * 2);
- vgpu->cfg_space.bar[i].tracked = false;
- }
-}
-
void populate_pvinfo_page(struct intel_vgpu *vgpu)
{
/* setup the ballooning information */
@@ -177,7 +104,7 @@
if (low_avail / min_low == 0)
break;
gvt->types[i].low_gm_size = min_low;
- gvt->types[i].high_gm_size = 3 * gvt->types[i].low_gm_size;
+ gvt->types[i].high_gm_size = max((min_low<<3), MB_TO_BYTES(384U));
gvt->types[i].fence = 4;
gvt->types[i].max_instance = low_avail / min_low;
gvt->types[i].avail_instance = gvt->types[i].max_instance;
@@ -217,7 +144,7 @@
*/
low_gm_avail = MB_TO_BYTES(256) - HOST_LOW_GM_SIZE -
gvt->gm.vgpu_allocated_low_gm_size;
- high_gm_avail = MB_TO_BYTES(256) * 3 - HOST_HIGH_GM_SIZE -
+ high_gm_avail = MB_TO_BYTES(256) * 8UL - HOST_HIGH_GM_SIZE -
gvt->gm.vgpu_allocated_high_gm_size;
fence_avail = gvt_fence_sz(gvt) - HOST_FENCE -
gvt->fence.vgpu_allocated_fence_num;
@@ -268,7 +195,7 @@
intel_vgpu_clean_gtt(vgpu);
intel_gvt_hypervisor_detach_vgpu(vgpu);
intel_vgpu_free_resource(vgpu);
- clean_vgpu_mmio(vgpu);
+ intel_vgpu_clean_mmio(vgpu);
vfree(vgpu);
intel_gvt_update_vgpu_types(gvt);
@@ -300,11 +227,11 @@
vgpu->gvt = gvt;
bitmap_zero(vgpu->tlb_handle_pending, I915_NUM_ENGINES);
- setup_vgpu_cfg_space(vgpu, param);
+ intel_vgpu_init_cfg_space(vgpu, param->primary);
- ret = setup_vgpu_mmio(vgpu);
+ ret = intel_vgpu_init_mmio(vgpu);
if (ret)
- goto out_free_vgpu;
+ goto out_clean_idr;
ret = intel_vgpu_alloc_resource(vgpu, param);
if (ret)
@@ -354,7 +281,9 @@
out_clean_vgpu_resource:
intel_vgpu_free_resource(vgpu);
out_clean_vgpu_mmio:
- clean_vgpu_mmio(vgpu);
+ intel_vgpu_clean_mmio(vgpu);
+out_clean_idr:
+ idr_remove(&gvt->vgpu_idr, vgpu->id);
out_free_vgpu:
vfree(vgpu);
mutex_unlock(&gvt->lock);
@@ -398,7 +327,75 @@
}
/**
- * intel_gvt_reset_vgpu - reset a virtual GPU
+ * intel_gvt_reset_vgpu_locked - reset a virtual GPU by DMLR or GT reset
+ * @vgpu: virtual GPU
+ * @dmlr: vGPU Device Model Level Reset or GT Reset
+ * @engine_mask: engines to reset for GT reset
+ *
+ * This function is called when user wants to reset a virtual GPU through
+ * device model reset or GT reset. The caller should hold the gvt lock.
+ *
+ * vGPU Device Model Level Reset (DMLR) simulates the PCI level reset to reset
+ * the whole vGPU to default state as when it is created. This vGPU function
+ * is required both for functionary and security concerns.The ultimate goal
+ * of vGPU FLR is that reuse a vGPU instance by virtual machines. When we
+ * assign a vGPU to a virtual machine we must isse such reset first.
+ *
+ * Full GT Reset and Per-Engine GT Reset are soft reset flow for GPU engines
+ * (Render, Blitter, Video, Video Enhancement). It is defined by GPU Spec.
+ * Unlike the FLR, GT reset only reset particular resource of a vGPU per
+ * the reset request. Guest driver can issue a GT reset by programming the
+ * virtual GDRST register to reset specific virtual GPU engine or all
+ * engines.
+ *
+ * The parameter dev_level is to identify if we will do DMLR or GT reset.
+ * The parameter engine_mask is to specific the engines that need to be
+ * resetted. If value ALL_ENGINES is given for engine_mask, it means
+ * the caller requests a full GT reset that we will reset all virtual
+ * GPU engines. For FLR, engine_mask is ignored.
+ */
+void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
+ unsigned int engine_mask)
+{
+ struct intel_gvt *gvt = vgpu->gvt;
+ struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
+
+ gvt_dbg_core("------------------------------------------\n");
+ gvt_dbg_core("resseting vgpu%d, dmlr %d, engine_mask %08x\n",
+ vgpu->id, dmlr, engine_mask);
+ vgpu->resetting = true;
+
+ intel_vgpu_stop_schedule(vgpu);
+ /*
+ * The current_vgpu will set to NULL after stopping the
+ * scheduler when the reset is triggered by current vgpu.
+ */
+ if (scheduler->current_vgpu == NULL) {
+ mutex_unlock(&gvt->lock);
+ intel_gvt_wait_vgpu_idle(vgpu);
+ mutex_lock(&gvt->lock);
+ }
+
+ intel_vgpu_reset_execlist(vgpu, dmlr ? ALL_ENGINES : engine_mask);
+
+ /* full GPU reset or device model level reset */
+ if (engine_mask == ALL_ENGINES || dmlr) {
+ intel_vgpu_reset_gtt(vgpu, dmlr);
+ intel_vgpu_reset_resource(vgpu);
+ intel_vgpu_reset_mmio(vgpu);
+ populate_pvinfo_page(vgpu);
+
+ if (dmlr)
+ intel_vgpu_reset_cfg_space(vgpu);
+ }
+
+ vgpu->resetting = false;
+ gvt_dbg_core("reset vgpu%d done\n", vgpu->id);
+ gvt_dbg_core("------------------------------------------\n");
+}
+
+/**
+ * intel_gvt_reset_vgpu - reset a virtual GPU (Function Level)
* @vgpu: virtual GPU
*
* This function is called when user wants to reset a virtual GPU.
@@ -406,4 +403,7 @@
*/
void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu)
{
+ mutex_lock(&vgpu->gvt->lock);
+ intel_gvt_reset_vgpu_locked(vgpu, true, 0);
+ mutex_unlock(&vgpu->gvt->lock);
}
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 445fec9c..728ca3e 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -213,7 +213,8 @@
} else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) {
dev_priv->pch_type = PCH_KBP;
DRM_DEBUG_KMS("Found KabyPoint PCH\n");
- WARN_ON(!IS_KABYLAKE(dev_priv));
+ WARN_ON(!IS_SKYLAKE(dev_priv) &&
+ !IS_KABYLAKE(dev_priv));
} else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) ||
(id == INTEL_PCH_P3X_DEVICE_ID_TYPE) ||
((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) &&
@@ -2378,7 +2379,7 @@
assert_forcewakes_inactive(dev_priv);
- if (!IS_VALLEYVIEW(dev_priv) || !IS_CHERRYVIEW(dev_priv))
+ if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
intel_hpd_poll_init(dev_priv);
DRM_DEBUG_KMS("Device suspended\n");
@@ -2427,6 +2428,7 @@
* we can do is to hope that things will still work (and disable RPM).
*/
i915_gem_init_swizzling(dev_priv);
+ i915_gem_restore_fences(dev_priv);
intel_runtime_pm_enable_interrupts(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 243224a..8493e19 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1012,6 +1012,8 @@
struct work_struct underrun_work;
struct intel_fbc_state_cache {
+ struct i915_vma *vma;
+
struct {
unsigned int mode_flags;
uint32_t hsw_bdw_pixel_rate;
@@ -1025,15 +1027,14 @@
} plane;
struct {
- u64 ilk_ggtt_offset;
uint32_t pixel_format;
unsigned int stride;
- int fence_reg;
- unsigned int tiling_mode;
} fb;
} state_cache;
struct intel_fbc_reg_params {
+ struct i915_vma *vma;
+
struct {
enum pipe pipe;
enum plane plane;
@@ -1041,10 +1042,8 @@
} crtc;
struct {
- u64 ggtt_offset;
uint32_t pixel_format;
unsigned int stride;
- int fence_reg;
} fb;
int cfb_size;
@@ -1977,6 +1976,11 @@
struct i915_frontbuffer_tracking fb_tracking;
+ struct intel_atomic_helper {
+ struct llist_head free_list;
+ struct work_struct free_work;
+ } atomic_helper;
+
u16 orig_clock;
bool mchbar_need_disable;
@@ -3163,13 +3167,6 @@
return i915_gem_obj_to_vma(obj, &to_i915(obj->base.dev)->ggtt.base, view);
}
-static inline unsigned long
-i915_gem_object_ggtt_offset(struct drm_i915_gem_object *o,
- const struct i915_ggtt_view *view)
-{
- return i915_ggtt_offset(i915_gem_object_to_ggtt(o, view));
-}
-
/* i915_gem_fence_reg.c */
int __must_check i915_vma_get_fence(struct i915_vma *vma);
int __must_check i915_vma_put_fence(struct i915_vma *vma);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 3dd7fc6..24b5b04 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -595,47 +595,21 @@
struct drm_i915_gem_pwrite *args,
struct drm_file *file)
{
- struct drm_device *dev = obj->base.dev;
void *vaddr = obj->phys_handle->vaddr + args->offset;
char __user *user_data = u64_to_user_ptr(args->data_ptr);
- int ret;
/* We manually control the domain here and pretend that it
* remains coherent i.e. in the GTT domain, like shmem_pwrite.
*/
- lockdep_assert_held(&obj->base.dev->struct_mutex);
- ret = i915_gem_object_wait(obj,
- I915_WAIT_INTERRUPTIBLE |
- I915_WAIT_LOCKED |
- I915_WAIT_ALL,
- MAX_SCHEDULE_TIMEOUT,
- to_rps_client(file));
- if (ret)
- return ret;
-
intel_fb_obj_invalidate(obj, ORIGIN_CPU);
- if (__copy_from_user_inatomic_nocache(vaddr, user_data, args->size)) {
- unsigned long unwritten;
-
- /* The physical object once assigned is fixed for the lifetime
- * of the obj, so we can safely drop the lock and continue
- * to access vaddr.
- */
- mutex_unlock(&dev->struct_mutex);
- unwritten = copy_from_user(vaddr, user_data, args->size);
- mutex_lock(&dev->struct_mutex);
- if (unwritten) {
- ret = -EFAULT;
- goto out;
- }
- }
+ if (copy_from_user(vaddr, user_data, args->size))
+ return -EFAULT;
drm_clflush_virt_range(vaddr, args->size);
- i915_gem_chipset_flush(to_i915(dev));
+ i915_gem_chipset_flush(to_i915(obj->base.dev));
-out:
intel_fb_obj_flush(obj, false, ORIGIN_CPU);
- return ret;
+ return 0;
}
void *i915_gem_object_alloc(struct drm_device *dev)
@@ -2036,8 +2010,16 @@
for (i = 0; i < dev_priv->num_fence_regs; i++) {
struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
- if (WARN_ON(reg->pin_count))
- continue;
+ /* Ideally we want to assert that the fence register is not
+ * live at this point (i.e. that no piece of code will be
+ * trying to write through fence + GTT, as that both violates
+ * our tracking of activity and associated locking/barriers,
+ * but also is illegal given that the hw is powered down).
+ *
+ * Previously we used reg->pin_count as a "liveness" indicator.
+ * That is not sufficient, and we need a more fine-grained
+ * tool if we want to have a sanity check here.
+ */
if (!reg->vma)
continue;
@@ -3504,7 +3486,7 @@
vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
/* Treat this as an end-of-frame, like intel_user_framebuffer_dirty() */
- if (obj->cache_dirty) {
+ if (obj->cache_dirty || obj->base.write_domain == I915_GEM_DOMAIN_CPU) {
i915_gem_clflush_object(obj, true);
intel_fb_obj_flush(obj, false, ORIGIN_DIRTYFB);
}
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index bd08814..d534a31 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -199,6 +199,7 @@
}
/* Unbinding will emit any required flushes */
+ ret = 0;
while (!list_empty(&eviction_list)) {
vma = list_first_entry(&eviction_list,
struct i915_vma,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 097d9d8..b8b877c 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1181,14 +1181,14 @@
if (exec[i].offset !=
gen8_canonical_addr(exec[i].offset & PAGE_MASK))
return -EINVAL;
-
- /* From drm_mm perspective address space is continuous,
- * so from this point we're always using non-canonical
- * form internally.
- */
- exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
}
+ /* From drm_mm perspective address space is continuous,
+ * so from this point we're always using non-canonical
+ * form internally.
+ */
+ exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
+
if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_gem_internal.c b/drivers/gpu/drm/i915/i915_gem_internal.c
index 4b3ff3e..d09c749 100644
--- a/drivers/gpu/drm/i915/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/i915_gem_internal.c
@@ -66,8 +66,16 @@
max_order = MAX_ORDER;
#ifdef CONFIG_SWIOTLB
- if (swiotlb_nr_tbl()) /* minimum max swiotlb size is IO_TLB_SEGSIZE */
- max_order = min(max_order, ilog2(IO_TLB_SEGPAGES));
+ if (swiotlb_nr_tbl()) {
+ unsigned int max_segment;
+
+ max_segment = swiotlb_max_segment();
+ if (max_segment) {
+ max_segment = max_t(unsigned int, max_segment,
+ PAGE_SIZE) >> PAGE_SHIFT;
+ max_order = min(max_order, ilog2(max_segment));
+ }
+ }
#endif
gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE;
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index a792dcb..e924a95 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -185,6 +185,7 @@
return ret;
}
+ trace_i915_vma_bind(vma, bind_flags);
ret = vma->vm->bind_vma(vma, cache_level, bind_flags);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index dbe9fb4..8d3e515 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -85,6 +85,8 @@
__drm_atomic_helper_plane_duplicate_state(plane, state);
+ intel_state->vma = NULL;
+
return state;
}
@@ -100,6 +102,24 @@
intel_plane_destroy_state(struct drm_plane *plane,
struct drm_plane_state *state)
{
+ struct i915_vma *vma;
+
+ vma = fetch_and_zero(&to_intel_plane_state(state)->vma);
+
+ /*
+ * FIXME: Normally intel_cleanup_plane_fb handles destruction of vma.
+ * We currently don't clear all planes during driver unload, so we have
+ * to be able to unpin vma here for now.
+ *
+ * Normally this can only happen during unload when kmscon is disabled
+ * and userspace doesn't attempt to set a framebuffer at all.
+ */
+ if (vma) {
+ mutex_lock(&plane->dev->struct_mutex);
+ intel_unpin_fb_vma(vma);
+ mutex_unlock(&plane->dev->struct_mutex);
+ }
+
drm_atomic_helper_plane_destroy_state(plane, state);
}
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 86ecec5..588470e 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -499,6 +499,7 @@
struct drm_i915_private *dev_priv = to_i915(crt->base.base.dev);
struct edid *edid;
struct i2c_adapter *i2c;
+ bool ret = false;
BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG);
@@ -515,17 +516,17 @@
*/
if (!is_digital) {
DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n");
- return true;
+ ret = true;
+ } else {
+ DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
}
-
- DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
} else {
DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [no valid EDID found]\n");
}
kfree(edid);
- return false;
+ return ret;
}
static enum drm_connector_status
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3dc8724..891c86a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2235,24 +2235,22 @@
i915_vma_pin_fence(vma);
}
+ i915_vma_get(vma);
err:
intel_runtime_pm_put(dev_priv);
return vma;
}
-void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
+void intel_unpin_fb_vma(struct i915_vma *vma)
{
- struct drm_i915_gem_object *obj = intel_fb_obj(fb);
- struct i915_ggtt_view view;
- struct i915_vma *vma;
+ lockdep_assert_held(&vma->vm->dev->struct_mutex);
- WARN_ON(!mutex_is_locked(&obj->base.dev->struct_mutex));
-
- intel_fill_fb_ggtt_view(&view, fb, rotation);
- vma = i915_gem_object_to_ggtt(obj, &view);
+ if (WARN_ON_ONCE(!vma))
+ return;
i915_vma_unpin_fence(vma);
i915_gem_object_unpin_from_display_plane(vma);
+ i915_vma_put(vma);
}
static int intel_fb_pitch(const struct drm_framebuffer *fb, int plane,
@@ -2585,8 +2583,9 @@
* We only keep the x/y offsets, so push all of the
* gtt offset into the x/y offsets.
*/
- _intel_adjust_tile_offset(&x, &y, tile_size,
- tile_width, tile_height, pitch_tiles,
+ _intel_adjust_tile_offset(&x, &y,
+ tile_width, tile_height,
+ tile_size, pitch_tiles,
gtt_offset_rotated * tile_size, 0);
gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height;
@@ -2746,7 +2745,6 @@
struct drm_device *dev = intel_crtc->base.dev;
struct drm_i915_private *dev_priv = to_i915(dev);
struct drm_crtc *c;
- struct intel_crtc *i;
struct drm_i915_gem_object *obj;
struct drm_plane *primary = intel_crtc->base.primary;
struct drm_plane_state *plane_state = primary->state;
@@ -2771,20 +2769,20 @@
* an fb with another CRTC instead
*/
for_each_crtc(dev, c) {
- i = to_intel_crtc(c);
+ struct intel_plane_state *state;
if (c == &intel_crtc->base)
continue;
- if (!i->active)
+ if (!to_intel_crtc(c)->active)
continue;
- fb = c->primary->fb;
- if (!fb)
+ state = to_intel_plane_state(c->primary->state);
+ if (!state->vma)
continue;
- obj = intel_fb_obj(fb);
- if (i915_gem_object_ggtt_offset(obj, NULL) == plane_config->base) {
+ if (intel_plane_ggtt_offset(state) == plane_config->base) {
+ fb = c->primary->fb;
drm_framebuffer_reference(fb);
goto valid_fb;
}
@@ -2805,6 +2803,19 @@
return;
valid_fb:
+ mutex_lock(&dev->struct_mutex);
+ intel_state->vma =
+ intel_pin_and_fence_fb_obj(fb, primary->state->rotation);
+ mutex_unlock(&dev->struct_mutex);
+ if (IS_ERR(intel_state->vma)) {
+ DRM_ERROR("failed to pin boot fb on pipe %d: %li\n",
+ intel_crtc->pipe, PTR_ERR(intel_state->vma));
+
+ intel_state->vma = NULL;
+ drm_framebuffer_unreference(fb);
+ return;
+ }
+
plane_state->src_x = 0;
plane_state->src_y = 0;
plane_state->src_w = fb->width << 16;
@@ -2967,6 +2978,9 @@
unsigned int rotation = plane_state->base.rotation;
int ret;
+ if (!plane_state->base.visible)
+ return 0;
+
/* Rotate src coordinates to match rotated GTT view */
if (drm_rotation_90_or_270(rotation))
drm_rect_rotate(&plane_state->base.src,
@@ -3097,13 +3111,13 @@
I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
if (INTEL_GEN(dev_priv) >= 4) {
I915_WRITE(DSPSURF(plane),
- intel_fb_gtt_offset(fb, rotation) +
+ intel_plane_ggtt_offset(plane_state) +
intel_crtc->dspaddr_offset);
I915_WRITE(DSPTILEOFF(plane), (y << 16) | x);
I915_WRITE(DSPLINOFF(plane), linear_offset);
} else {
I915_WRITE(DSPADDR(plane),
- intel_fb_gtt_offset(fb, rotation) +
+ intel_plane_ggtt_offset(plane_state) +
intel_crtc->dspaddr_offset);
}
POSTING_READ(reg);
@@ -3200,7 +3214,7 @@
I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
I915_WRITE(DSPSURF(plane),
- intel_fb_gtt_offset(fb, rotation) +
+ intel_plane_ggtt_offset(plane_state) +
intel_crtc->dspaddr_offset);
if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
I915_WRITE(DSPOFFSET(plane), (y << 16) | x);
@@ -3223,23 +3237,6 @@
}
}
-u32 intel_fb_gtt_offset(struct drm_framebuffer *fb,
- unsigned int rotation)
-{
- struct drm_i915_gem_object *obj = intel_fb_obj(fb);
- struct i915_ggtt_view view;
- struct i915_vma *vma;
-
- intel_fill_fb_ggtt_view(&view, fb, rotation);
-
- vma = i915_gem_object_to_ggtt(obj, &view);
- if (WARN(!vma, "ggtt vma for display object not found! (view=%u)\n",
- view.type))
- return -1;
-
- return i915_ggtt_offset(vma);
-}
-
static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
{
struct drm_device *dev = intel_crtc->base.dev;
@@ -3434,7 +3431,7 @@
}
I915_WRITE(PLANE_SURF(pipe, 0),
- intel_fb_gtt_offset(fb, rotation) + surf_addr);
+ intel_plane_ggtt_offset(plane_state) + surf_addr);
POSTING_READ(PLANE_SURF(pipe, 0));
}
@@ -4265,10 +4262,10 @@
drm_crtc_vblank_put(&intel_crtc->base);
wake_up_all(&dev_priv->pending_flip_queue);
- queue_work(dev_priv->wq, &work->unpin_work);
-
trace_i915_flip_complete(intel_crtc->plane,
work->pending_flip_obj);
+
+ queue_work(dev_priv->wq, &work->unpin_work);
}
static int intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
@@ -6846,6 +6843,12 @@
}
state = drm_atomic_state_alloc(crtc->dev);
+ if (!state) {
+ DRM_DEBUG_KMS("failed to disable [CRTC:%d:%s], out of memory",
+ crtc->base.id, crtc->name);
+ return;
+ }
+
state->acquire_ctx = crtc->dev->mode_config.acquire_ctx;
/* Everything's already locked, -EDEADLK can't happen. */
@@ -11243,6 +11246,7 @@
}
old->restore_state = restore_state;
+ drm_atomic_state_put(state);
/* let the connector get through one full cycle before testing */
intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
@@ -11522,7 +11526,7 @@
flush_work(&work->mmio_work);
mutex_lock(&dev->struct_mutex);
- intel_unpin_fb_obj(work->old_fb, primary->state->rotation);
+ intel_unpin_fb_vma(work->old_vma);
i915_gem_object_put(work->pending_flip_obj);
mutex_unlock(&dev->struct_mutex);
@@ -12232,8 +12236,10 @@
goto cleanup_pending;
}
- work->gtt_offset = intel_fb_gtt_offset(fb, primary->state->rotation);
- work->gtt_offset += intel_crtc->dspaddr_offset;
+ work->old_vma = to_intel_plane_state(primary->state)->vma;
+ to_intel_plane_state(primary->state)->vma = vma;
+
+ work->gtt_offset = i915_ggtt_offset(vma) + intel_crtc->dspaddr_offset;
work->rotation = crtc->primary->state->rotation;
/*
@@ -12287,7 +12293,8 @@
cleanup_request:
i915_add_request_no_flush(request);
cleanup_unpin:
- intel_unpin_fb_obj(fb, crtc->primary->state->rotation);
+ to_intel_plane_state(primary->state)->vma = work->old_vma;
+ intel_unpin_fb_vma(vma);
cleanup_pending:
atomic_dec(&intel_crtc->unpin_work_count);
unlock:
@@ -14512,8 +14519,14 @@
break;
case FENCE_FREE:
- drm_atomic_state_put(&state->base);
- break;
+ {
+ struct intel_atomic_helper *helper =
+ &to_i915(state->base.dev)->atomic_helper;
+
+ if (llist_add(&state->freed, &helper->free_list))
+ schedule_work(&helper->free_work);
+ break;
+ }
}
return NOTIFY_DONE;
@@ -14774,6 +14787,8 @@
DRM_DEBUG_KMS("failed to pin object\n");
return PTR_ERR(vma);
}
+
+ to_intel_plane_state(new_state)->vma = vma;
}
return 0;
@@ -14792,19 +14807,12 @@
intel_cleanup_plane_fb(struct drm_plane *plane,
struct drm_plane_state *old_state)
{
- struct drm_i915_private *dev_priv = to_i915(plane->dev);
- struct intel_plane_state *old_intel_state;
- struct drm_i915_gem_object *old_obj = intel_fb_obj(old_state->fb);
- struct drm_i915_gem_object *obj = intel_fb_obj(plane->state->fb);
+ struct i915_vma *vma;
- old_intel_state = to_intel_plane_state(old_state);
-
- if (!obj && !old_obj)
- return;
-
- if (old_obj && (plane->type != DRM_PLANE_TYPE_CURSOR ||
- !INTEL_INFO(dev_priv)->cursor_needs_physical))
- intel_unpin_fb_obj(old_state->fb, old_state->rotation);
+ /* Should only be called after a successful intel_prepare_plane_fb()! */
+ vma = fetch_and_zero(&to_intel_plane_state(old_state)->vma);
+ if (vma)
+ intel_unpin_fb_vma(vma);
}
int
@@ -15146,7 +15154,7 @@
if (!obj)
addr = 0;
else if (!INTEL_INFO(dev_priv)->cursor_needs_physical)
- addr = i915_gem_object_ggtt_offset(obj, NULL);
+ addr = intel_plane_ggtt_offset(state);
else
addr = obj->phys_handle->busaddr;
@@ -16392,6 +16400,18 @@
drm_modeset_acquire_fini(&ctx);
}
+static void intel_atomic_helper_free_state(struct work_struct *work)
+{
+ struct drm_i915_private *dev_priv =
+ container_of(work, typeof(*dev_priv), atomic_helper.free_work);
+ struct intel_atomic_state *state, *next;
+ struct llist_node *freed;
+
+ freed = llist_del_all(&dev_priv->atomic_helper.free_list);
+ llist_for_each_entry_safe(state, next, freed, freed)
+ drm_atomic_state_put(&state->base);
+}
+
int intel_modeset_init(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = to_i915(dev);
@@ -16411,6 +16431,9 @@
dev->mode_config.funcs = &intel_mode_funcs;
+ INIT_WORK(&dev_priv->atomic_helper.free_work,
+ intel_atomic_helper_free_state);
+
intel_init_quirks(dev);
intel_init_pm(dev_priv);
@@ -17024,47 +17047,19 @@
if (ret)
DRM_ERROR("Restoring old state failed with %i\n", ret);
- drm_atomic_state_put(state);
+ if (state)
+ drm_atomic_state_put(state);
}
void intel_modeset_gem_init(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = to_i915(dev);
- struct drm_crtc *c;
- struct drm_i915_gem_object *obj;
intel_init_gt_powersave(dev_priv);
intel_modeset_init_hw(dev);
intel_setup_overlay(dev_priv);
-
- /*
- * Make sure any fbs we allocated at startup are properly
- * pinned & fenced. When we do the allocation it's too early
- * for this.
- */
- for_each_crtc(dev, c) {
- struct i915_vma *vma;
-
- obj = intel_fb_obj(c->primary->fb);
- if (obj == NULL)
- continue;
-
- mutex_lock(&dev->struct_mutex);
- vma = intel_pin_and_fence_fb_obj(c->primary->fb,
- c->primary->state->rotation);
- mutex_unlock(&dev->struct_mutex);
- if (IS_ERR(vma)) {
- DRM_ERROR("failed to pin boot fb on pipe %d\n",
- to_intel_crtc(c)->pipe);
- drm_framebuffer_unreference(c->primary->fb);
- c->primary->fb = NULL;
- c->primary->crtc = c->primary->state->crtc = NULL;
- update_state_fb(c->primary);
- c->state->plane_mask &= ~(1 << drm_plane_index(c->primary));
- }
- }
}
int intel_connector_register(struct drm_connector *connector)
@@ -17094,6 +17089,9 @@
{
struct drm_i915_private *dev_priv = to_i915(dev);
+ flush_work(&dev_priv->atomic_helper.free_work);
+ WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list));
+
intel_disable_gt_powersave(dev_priv);
/*
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 58a756f..a2f0e07 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -1730,7 +1730,8 @@
return NULL;
if ((encoder->type == INTEL_OUTPUT_DP ||
- encoder->type == INTEL_OUTPUT_EDP) &&
+ encoder->type == INTEL_OUTPUT_EDP ||
+ encoder->type == INTEL_OUTPUT_DP_MST) &&
!bxt_ddi_dp_set_dpll_hw_state(clock, &dpll_hw_state))
return NULL;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index cd132c2..03a2112 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -370,11 +370,14 @@
struct skl_wm_values wm_results;
struct i915_sw_fence commit_ready;
+
+ struct llist_node freed;
};
struct intel_plane_state {
struct drm_plane_state base;
struct drm_rect clip;
+ struct i915_vma *vma;
struct {
u32 offset;
@@ -1044,6 +1047,7 @@
struct work_struct mmio_work;
struct drm_crtc *crtc;
+ struct i915_vma *old_vma;
struct drm_framebuffer *old_fb;
struct drm_i915_gem_object *pending_flip_obj;
struct drm_pending_vblank_event *event;
@@ -1271,7 +1275,7 @@
struct drm_modeset_acquire_ctx *ctx);
struct i915_vma *
intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, unsigned int rotation);
-void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation);
+void intel_unpin_fb_vma(struct i915_vma *vma);
struct drm_framebuffer *
__intel_framebuffer_create(struct drm_device *dev,
struct drm_mode_fb_cmd2 *mode_cmd,
@@ -1360,7 +1364,10 @@
int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state);
-u32 intel_fb_gtt_offset(struct drm_framebuffer *fb, unsigned int rotation);
+static inline u32 intel_plane_ggtt_offset(const struct intel_plane_state *state)
+{
+ return i915_ggtt_offset(state->vma);
+}
u32 skl_plane_ctl_format(uint32_t pixel_format);
u32 skl_plane_ctl_tiling(uint64_t fb_modifier);
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 62f215b..f3a1d6a 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -173,7 +173,7 @@
if (IS_I945GM(dev_priv))
fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */
fbc_ctl |= (cfb_pitch & 0xff) << FBC_CTL_STRIDE_SHIFT;
- fbc_ctl |= params->fb.fence_reg;
+ fbc_ctl |= params->vma->fence->id;
I915_WRITE(FBC_CONTROL, fbc_ctl);
}
@@ -193,8 +193,8 @@
else
dpfc_ctl |= DPFC_CTL_LIMIT_1X;
- if (params->fb.fence_reg != I915_FENCE_REG_NONE) {
- dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fb.fence_reg;
+ if (params->vma->fence) {
+ dpfc_ctl |= DPFC_CTL_FENCE_EN | params->vma->fence->id;
I915_WRITE(DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
} else {
I915_WRITE(DPFC_FENCE_YOFF, 0);
@@ -251,13 +251,14 @@
break;
}
- if (params->fb.fence_reg != I915_FENCE_REG_NONE) {
+ if (params->vma->fence) {
dpfc_ctl |= DPFC_CTL_FENCE_EN;
if (IS_GEN5(dev_priv))
- dpfc_ctl |= params->fb.fence_reg;
+ dpfc_ctl |= params->vma->fence->id;
if (IS_GEN6(dev_priv)) {
I915_WRITE(SNB_DPFC_CTL_SA,
- SNB_CPU_FENCE_ENABLE | params->fb.fence_reg);
+ SNB_CPU_FENCE_ENABLE |
+ params->vma->fence->id);
I915_WRITE(DPFC_CPU_FENCE_OFFSET,
params->crtc.fence_y_offset);
}
@@ -269,7 +270,8 @@
}
I915_WRITE(ILK_DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
- I915_WRITE(ILK_FBC_RT_BASE, params->fb.ggtt_offset | ILK_FBC_RT_VALID);
+ I915_WRITE(ILK_FBC_RT_BASE,
+ i915_ggtt_offset(params->vma) | ILK_FBC_RT_VALID);
/* enable it... */
I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
@@ -319,10 +321,11 @@
break;
}
- if (params->fb.fence_reg != I915_FENCE_REG_NONE) {
+ if (params->vma->fence) {
dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN;
I915_WRITE(SNB_DPFC_CTL_SA,
- SNB_CPU_FENCE_ENABLE | params->fb.fence_reg);
+ SNB_CPU_FENCE_ENABLE |
+ params->vma->fence->id);
I915_WRITE(DPFC_CPU_FENCE_OFFSET, params->crtc.fence_y_offset);
} else {
I915_WRITE(SNB_DPFC_CTL_SA,0);
@@ -727,14 +730,6 @@
return effective_w <= max_w && effective_h <= max_h;
}
-/* XXX replace me when we have VMA tracking for intel_plane_state */
-static int get_fence_id(struct drm_framebuffer *fb)
-{
- struct i915_vma *vma = i915_gem_object_to_ggtt(intel_fb_obj(fb), NULL);
-
- return vma && vma->fence ? vma->fence->id : I915_FENCE_REG_NONE;
-}
-
static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
struct intel_crtc_state *crtc_state,
struct intel_plane_state *plane_state)
@@ -743,7 +738,8 @@
struct intel_fbc *fbc = &dev_priv->fbc;
struct intel_fbc_state_cache *cache = &fbc->state_cache;
struct drm_framebuffer *fb = plane_state->base.fb;
- struct drm_i915_gem_object *obj;
+
+ cache->vma = NULL;
cache->crtc.mode_flags = crtc_state->base.adjusted_mode.flags;
if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
@@ -758,16 +754,10 @@
if (!cache->plane.visible)
return;
- obj = intel_fb_obj(fb);
-
- /* FIXME: We lack the proper locking here, so only run this on the
- * platforms that need. */
- if (IS_GEN(dev_priv, 5, 6))
- cache->fb.ilk_ggtt_offset = i915_gem_object_ggtt_offset(obj, NULL);
cache->fb.pixel_format = fb->pixel_format;
cache->fb.stride = fb->pitches[0];
- cache->fb.fence_reg = get_fence_id(fb);
- cache->fb.tiling_mode = i915_gem_object_get_tiling(obj);
+
+ cache->vma = plane_state->vma;
}
static bool intel_fbc_can_activate(struct intel_crtc *crtc)
@@ -784,7 +774,7 @@
return false;
}
- if (!cache->plane.visible) {
+ if (!cache->vma) {
fbc->no_fbc_reason = "primary plane not visible";
return false;
}
@@ -807,8 +797,7 @@
* so have no fence associated with it) due to aperture constaints
* at the time of pinning.
*/
- if (cache->fb.tiling_mode != I915_TILING_X ||
- cache->fb.fence_reg == I915_FENCE_REG_NONE) {
+ if (!cache->vma->fence) {
fbc->no_fbc_reason = "framebuffer not tiled or fenced";
return false;
}
@@ -888,17 +877,16 @@
* zero. */
memset(params, 0, sizeof(*params));
+ params->vma = cache->vma;
+
params->crtc.pipe = crtc->pipe;
params->crtc.plane = crtc->plane;
params->crtc.fence_y_offset = get_crtc_fence_y_offset(crtc);
params->fb.pixel_format = cache->fb.pixel_format;
params->fb.stride = cache->fb.stride;
- params->fb.fence_reg = cache->fb.fence_reg;
params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache);
-
- params->fb.ggtt_offset = cache->fb.ilk_ggtt_offset;
}
static bool intel_fbc_reg_params_equal(struct intel_fbc_reg_params *params1,
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index beb0898..f4a8c4f 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -284,7 +284,7 @@
out_destroy_fbi:
drm_fb_helper_release_fbi(helper);
out_unpin:
- intel_unpin_fb_obj(&ifbdev->fb->base, DRM_ROTATE_0);
+ intel_unpin_fb_vma(vma);
out_unlock:
mutex_unlock(&dev->struct_mutex);
return ret;
@@ -549,7 +549,7 @@
if (ifbdev->fb) {
mutex_lock(&ifbdev->helper.dev->struct_mutex);
- intel_unpin_fb_obj(&ifbdev->fb->base, DRM_ROTATE_0);
+ intel_unpin_fb_vma(ifbdev->vma);
mutex_unlock(&ifbdev->helper.dev->struct_mutex);
drm_framebuffer_remove(&ifbdev->fb->base);
@@ -742,6 +742,9 @@
{
struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
+ if (!ifbdev)
+ return;
+
ifbdev->cookie = async_schedule(intel_fbdev_initial_config, ifbdev);
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d4961fa..beabc17 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -979,18 +979,8 @@
uint32_t *batch,
uint32_t index)
{
- struct drm_i915_private *dev_priv = engine->i915;
uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES);
- /*
- * WaDisableLSQCROPERFforOCL:kbl
- * This WA is implemented in skl_init_clock_gating() but since
- * this batch updates GEN8_L3SQCREG4 with default value we need to
- * set this bit here to retain the WA during flush.
- */
- if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
- l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS;
-
wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
MI_SRM_LRM_GLOBAL_GTT));
wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index aeb637d..91cb4c4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1095,14 +1095,6 @@
WA_SET_BIT_MASKED(HDC_CHICKEN0,
HDC_FENCE_DEST_SLM_DISABLE);
- /* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes
- * involving this register should also be added to WA batch as required.
- */
- if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
- /* WaDisableLSQCROPERFforOCL:kbl */
- I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
- GEN8_LQSC_RO_PERF_DIS);
-
/* WaToEnableHwFixForPushConstHWBug:kbl */
if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER))
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 8f131a0..242a73e 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -273,7 +273,7 @@
I915_WRITE(PLANE_CTL(pipe, plane), plane_ctl);
I915_WRITE(PLANE_SURF(pipe, plane),
- intel_fb_gtt_offset(fb, rotation) + surf_addr);
+ intel_plane_ggtt_offset(plane_state) + surf_addr);
POSTING_READ(PLANE_SURF(pipe, plane));
}
@@ -458,7 +458,7 @@
I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w);
I915_WRITE(SPCNTR(pipe, plane), sprctl);
I915_WRITE(SPSURF(pipe, plane),
- intel_fb_gtt_offset(fb, rotation) + sprsurf_offset);
+ intel_plane_ggtt_offset(plane_state) + sprsurf_offset);
POSTING_READ(SPSURF(pipe, plane));
}
@@ -594,7 +594,7 @@
I915_WRITE(SPRSCALE(pipe), sprscale);
I915_WRITE(SPRCTL(pipe), sprctl);
I915_WRITE(SPRSURF(pipe),
- intel_fb_gtt_offset(fb, rotation) + sprsurf_offset);
+ intel_plane_ggtt_offset(plane_state) + sprsurf_offset);
POSTING_READ(SPRSURF(pipe));
}
@@ -721,7 +721,7 @@
I915_WRITE(DVSSCALE(pipe), dvsscale);
I915_WRITE(DVSCNTR(pipe), dvscntr);
I915_WRITE(DVSSURF(pipe),
- intel_fb_gtt_offset(fb, rotation) + dvssurf_offset);
+ intel_plane_ggtt_offset(plane_state) + dvssurf_offset);
POSTING_READ(DVSSURF(pipe));
}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 14ff876..686a580 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -345,7 +345,6 @@
{
struct adreno_platform_config *config = pdev->dev.platform_data;
struct msm_gpu *gpu = &adreno_gpu->base;
- struct msm_mmu *mmu;
int ret;
adreno_gpu->funcs = funcs;
@@ -385,8 +384,8 @@
return ret;
}
- mmu = gpu->aspace->mmu;
- if (mmu) {
+ if (gpu->aspace && gpu->aspace->mmu) {
+ struct msm_mmu *mmu = gpu->aspace->mmu;
ret = mmu->funcs->attach(mmu, iommu_ports,
ARRAY_SIZE(iommu_ports));
if (ret)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index 5f6cd87..c396d45 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -119,13 +119,7 @@
static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state)
{
- int i;
struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
- struct drm_plane *plane;
- struct drm_plane_state *plane_state;
-
- for_each_plane_in_state(state, plane, plane_state, i)
- mdp5_plane_complete_commit(plane, plane_state);
if (mdp5_kms->smp)
mdp5_smp_complete_commit(mdp5_kms->smp, &mdp5_kms->state->smp);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
index 17b0cc1..cdfc63d 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
@@ -104,8 +104,6 @@
/* assigned by crtc blender */
enum mdp_mixer_stage_id stage;
-
- bool pending : 1;
};
#define to_mdp5_plane_state(x) \
container_of(x, struct mdp5_plane_state, base)
@@ -232,8 +230,6 @@
void mdp5_irq_domain_fini(struct mdp5_kms *mdp5_kms);
uint32_t mdp5_plane_get_flush(struct drm_plane *plane);
-void mdp5_plane_complete_commit(struct drm_plane *plane,
- struct drm_plane_state *state);
enum mdp5_pipe mdp5_plane_pipe(struct drm_plane *plane);
struct drm_plane *mdp5_plane_init(struct drm_device *dev, bool primary);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index c099da7..25d9d0a 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -179,7 +179,6 @@
drm_printf(p, "\tzpos=%u\n", pstate->zpos);
drm_printf(p, "\talpha=%u\n", pstate->alpha);
drm_printf(p, "\tstage=%s\n", stage2name(pstate->stage));
- drm_printf(p, "\tpending=%u\n", pstate->pending);
}
static void mdp5_plane_reset(struct drm_plane *plane)
@@ -220,8 +219,6 @@
if (mdp5_state && mdp5_state->base.fb)
drm_framebuffer_reference(mdp5_state->base.fb);
- mdp5_state->pending = false;
-
return &mdp5_state->base;
}
@@ -288,13 +285,6 @@
DBG("%s: check (%d -> %d)", plane->name,
plane_enabled(old_state), plane_enabled(state));
- /* We don't allow faster-than-vblank updates.. if we did add this
- * some day, we would need to disallow in cases where hwpipe
- * changes
- */
- if (WARN_ON(to_mdp5_plane_state(old_state)->pending))
- return -EBUSY;
-
max_width = config->hw->lm.max_width << 16;
max_height = config->hw->lm.max_height << 16;
@@ -370,12 +360,9 @@
struct drm_plane_state *old_state)
{
struct drm_plane_state *state = plane->state;
- struct mdp5_plane_state *mdp5_state = to_mdp5_plane_state(state);
DBG("%s: update", plane->name);
- mdp5_state->pending = true;
-
if (plane_enabled(state)) {
int ret;
@@ -851,15 +838,6 @@
return pstate->hwpipe->flush_mask;
}
-/* called after vsync in thread context */
-void mdp5_plane_complete_commit(struct drm_plane *plane,
- struct drm_plane_state *state)
-{
- struct mdp5_plane_state *pstate = to_mdp5_plane_state(plane->state);
-
- pstate->pending = false;
-}
-
/* initialize plane */
struct drm_plane *mdp5_plane_init(struct drm_device *dev, bool primary)
{
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 4d24d93..1974ccb 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -294,6 +294,8 @@
WARN_ON(!mutex_is_locked(&dev->struct_mutex));
for (id = 0; id < ARRAY_SIZE(msm_obj->domain); id++) {
+ if (!priv->aspace[id])
+ continue;
msm_gem_unmap_vma(priv->aspace[id],
&msm_obj->domain[id], msm_obj->sgt);
}
diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c
index 74856a8..e64f524 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/hw.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c
@@ -222,6 +222,7 @@
uint32_t mpllP;
pci_read_config_dword(pci_get_bus_and_slot(0, 3), 0x6c, &mpllP);
+ mpllP = (mpllP >> 8) & 0xf;
if (!mpllP)
mpllP = 4;
@@ -232,7 +233,7 @@
uint32_t clock;
pci_read_config_dword(pci_get_bus_and_slot(0, 5), 0x4c, &clock);
- return clock;
+ return clock / 1000;
}
ret = nouveau_hw_get_pllvals(dev, plltype, &pllvals);
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index cef08da..6a15776 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -411,7 +411,8 @@
return ret;
/* enable polling for external displays */
- drm_kms_helper_poll_enable(dev);
+ if (!dev->mode_config.poll_enabled)
+ drm_kms_helper_poll_enable(dev);
/* enable hotplug interrupts */
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 59348fc..bc85a45 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -773,7 +773,10 @@
pci_set_master(pdev);
ret = nouveau_do_resume(drm_dev, true);
- drm_kms_helper_poll_enable(drm_dev);
+
+ if (!drm_dev->mode_config.poll_enabled)
+ drm_kms_helper_poll_enable(drm_dev);
+
/* do magic */
nvif_mask(&device->object, 0x088488, (1 << 25), (1 << 25));
vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 8d5ed5b..42c1fa5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -165,6 +165,8 @@
struct backlight_device *backlight;
struct list_head bl_connectors;
struct work_struct hpd_work;
+ struct work_struct fbcon_work;
+ int fbcon_new_state;
#ifdef CONFIG_ACPI
struct notifier_block acpi_nb;
#endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 2f2a3dc..fa2d0a9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -470,19 +470,43 @@
.fb_probe = nouveau_fbcon_create,
};
+static void
+nouveau_fbcon_set_suspend_work(struct work_struct *work)
+{
+ struct nouveau_drm *drm = container_of(work, typeof(*drm), fbcon_work);
+ int state = READ_ONCE(drm->fbcon_new_state);
+
+ if (state == FBINFO_STATE_RUNNING)
+ pm_runtime_get_sync(drm->dev->dev);
+
+ console_lock();
+ if (state == FBINFO_STATE_RUNNING)
+ nouveau_fbcon_accel_restore(drm->dev);
+ drm_fb_helper_set_suspend(&drm->fbcon->helper, state);
+ if (state != FBINFO_STATE_RUNNING)
+ nouveau_fbcon_accel_save_disable(drm->dev);
+ console_unlock();
+
+ if (state == FBINFO_STATE_RUNNING) {
+ pm_runtime_mark_last_busy(drm->dev->dev);
+ pm_runtime_put_sync(drm->dev->dev);
+ }
+}
+
void
nouveau_fbcon_set_suspend(struct drm_device *dev, int state)
{
struct nouveau_drm *drm = nouveau_drm(dev);
- if (drm->fbcon) {
- console_lock();
- if (state == FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_restore(dev);
- drm_fb_helper_set_suspend(&drm->fbcon->helper, state);
- if (state != FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_save_disable(dev);
- console_unlock();
- }
+
+ if (!drm->fbcon)
+ return;
+
+ drm->fbcon_new_state = state;
+ /* Since runtime resume can happen as a result of a sysfs operation,
+ * it's possible we already have the console locked. So handle fbcon
+ * init/deinit from a seperate work thread
+ */
+ schedule_work(&drm->fbcon_work);
}
int
@@ -502,6 +526,7 @@
return -ENOMEM;
drm->fbcon = fbcon;
+ INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work);
drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index ccdce1b..d5e58a3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -99,6 +99,7 @@
struct nouveau_bo *bo;
struct nouveau_bo *bo_gart;
u32 *suspend;
+ struct mutex mutex;
};
int nv84_fence_context_new(struct nouveau_channel *);
diff --git a/drivers/gpu/drm/nouveau/nouveau_led.h b/drivers/gpu/drm/nouveau/nouveau_led.h
index 187ecdb..21a5775 100644
--- a/drivers/gpu/drm/nouveau/nouveau_led.h
+++ b/drivers/gpu/drm/nouveau/nouveau_led.h
@@ -42,7 +42,7 @@
}
/* nouveau_led.c */
-#if IS_ENABLED(CONFIG_LEDS_CLASS)
+#if IS_REACHABLE(CONFIG_LEDS_CLASS)
int nouveau_led_init(struct drm_device *dev);
void nouveau_led_suspend(struct drm_device *dev);
void nouveau_led_resume(struct drm_device *dev);
diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c
index 08f9c6f..1fba386 100644
--- a/drivers/gpu/drm/nouveau/nouveau_usif.c
+++ b/drivers/gpu/drm/nouveau/nouveau_usif.c
@@ -313,7 +313,8 @@
if (!(ret = nvif_unpack(-ENOSYS, &data, &size, argv->v0, 0, 0, true))) {
/* block access to objects not created via this interface */
owner = argv->v0.owner;
- if (argv->v0.object == 0ULL)
+ if (argv->v0.object == 0ULL &&
+ argv->v0.type != NVIF_IOCTL_V0_DEL)
argv->v0.owner = NVDRM_OBJECT_ANY; /* except client */
else
argv->v0.owner = NVDRM_OBJECT_USIF;
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 2c2c645..32097fd 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -4052,6 +4052,11 @@
}
}
+ for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ if (crtc->state->event)
+ drm_crtc_vblank_get(crtc);
+ }
+
/* Update plane(s). */
for_each_plane_in_state(state, plane, plane_state, i) {
struct nv50_wndw_atom *asyw = nv50_wndw_atom(plane->state);
@@ -4101,6 +4106,7 @@
drm_crtc_send_vblank_event(crtc, crtc->state->event);
spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
crtc->state->event = NULL;
+ drm_crtc_vblank_put(crtc);
}
}
diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c
index 52b87ae..f0b322b 100644
--- a/drivers/gpu/drm/nouveau/nv84_fence.c
+++ b/drivers/gpu/drm/nouveau/nv84_fence.c
@@ -107,8 +107,10 @@
struct nv84_fence_chan *fctx = chan->fence;
nouveau_bo_wr32(priv->bo, chan->chid * 16 / 4, fctx->base.sequence);
+ mutex_lock(&priv->mutex);
nouveau_bo_vma_del(priv->bo, &fctx->vma_gart);
nouveau_bo_vma_del(priv->bo, &fctx->vma);
+ mutex_unlock(&priv->mutex);
nouveau_fence_context_del(&fctx->base);
chan->fence = NULL;
nouveau_fence_context_free(&fctx->base);
@@ -134,11 +136,13 @@
fctx->base.sync32 = nv84_fence_sync32;
fctx->base.sequence = nv84_fence_read(chan);
+ mutex_lock(&priv->mutex);
ret = nouveau_bo_vma_add(priv->bo, cli->vm, &fctx->vma);
if (ret == 0) {
ret = nouveau_bo_vma_add(priv->bo_gart, cli->vm,
&fctx->vma_gart);
}
+ mutex_unlock(&priv->mutex);
if (ret)
nv84_fence_context_del(chan);
@@ -212,6 +216,8 @@
priv->base.context_base = dma_fence_context_alloc(priv->base.contexts);
priv->base.uevent = true;
+ mutex_init(&priv->mutex);
+
/* Use VRAM if there is any ; otherwise fallback to system memory */
domain = drm->device.info.ram_size != 0 ? TTM_PL_FLAG_VRAM :
/*
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c
index 6f0436d..f8f2f16 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c
@@ -59,7 +59,7 @@
);
}
for (i = 0; i < size; i++)
- nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[0]);
+ nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[i]);
for (; i < 0x60; i++)
nvkm_wr32(device, 0x61c440 + soff, (i << 8));
nvkm_mask(device, 0x61c448 + soff, 0x80000003, 0x80000003);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
index 567466f..0db8efb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
@@ -433,8 +433,6 @@
case 0x94:
case 0x96:
case 0x98:
- case 0xaa:
- case 0xac:
return true;
default:
break;
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index fb16070..4a4f953 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -205,8 +205,8 @@
}
if (x <= (crtc->x - w) || y <= (crtc->y - radeon_crtc->cursor_height) ||
- x >= (crtc->x + crtc->mode.crtc_hdisplay) ||
- y >= (crtc->y + crtc->mode.crtc_vdisplay))
+ x >= (crtc->x + crtc->mode.hdisplay) ||
+ y >= (crtc->y + crtc->mode.vdisplay))
goto out_of_bounds;
x += xorigin;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 00ea000..30bd4a6 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -97,9 +97,10 @@
* 2.46.0 - Add PFP_SYNC_ME support on evergreen
* 2.47.0 - Add UVD_NO_OP register support
* 2.48.0 - TA_CS_BC_BASE_ADDR allowed on SI
+ * 2.49.0 - DRM_RADEON_GEM_INFO ioctl returns correct vram_size/visible values
*/
#define KMS_DRIVER_MAJOR 2
-#define KMS_DRIVER_MINOR 48
+#define KMS_DRIVER_MINOR 49
#define KMS_DRIVER_PATCHLEVEL 0
int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
int radeon_driver_unload_kms(struct drm_device *dev);
@@ -366,11 +367,10 @@
radeon_pci_shutdown(struct pci_dev *pdev)
{
/* if we are running in a VM, make sure the device
- * torn down properly on reboot/shutdown.
- * unfortunately we can't detect certain
- * hypervisors so just do this all the time.
+ * torn down properly on reboot/shutdown
*/
- radeon_pci_remove(pdev);
+ if (radeon_device_is_virtual())
+ radeon_pci_remove(pdev);
}
static int radeon_pmops_suspend(struct device *dev)
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 0bcffd8..96683f5 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -220,8 +220,8 @@
man = &rdev->mman.bdev.man[TTM_PL_VRAM];
- args->vram_size = rdev->mc.real_vram_size;
- args->vram_visible = (u64)man->size << PAGE_SHIFT;
+ args->vram_size = (u64)man->size << PAGE_SHIFT;
+ args->vram_visible = rdev->mc.visible_vram_size;
args->vram_visible -= rdev->vram_pin_size;
args->gart_size = rdev->mc.gtt_size;
args->gart_size -= rdev->gart_pin_size;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index e8a38d2..4147768 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -114,6 +114,9 @@
MODULE_FIRMWARE("radeon/hainan_rlc.bin");
MODULE_FIRMWARE("radeon/hainan_smc.bin");
MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
+MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
+
+MODULE_FIRMWARE("radeon/si58_mc.bin");
static u32 si_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh);
static void si_pcie_gen3_enable(struct radeon_device *rdev);
@@ -1650,6 +1653,8 @@
int err;
int new_fw = 0;
bool new_smc = false;
+ bool si58_fw = false;
+ bool banks2_fw = false;
DRM_DEBUG("\n");
@@ -1727,10 +1732,11 @@
((rdev->pdev->device == 0x6660) ||
(rdev->pdev->device == 0x6663) ||
(rdev->pdev->device == 0x6665) ||
- (rdev->pdev->device == 0x6667))) ||
- ((rdev->pdev->revision == 0xc3) &&
- (rdev->pdev->device == 0x6665)))
+ (rdev->pdev->device == 0x6667))))
new_smc = true;
+ else if ((rdev->pdev->revision == 0xc3) &&
+ (rdev->pdev->device == 0x6665))
+ banks2_fw = true;
new_chip_name = "hainan";
pfp_req_size = SI_PFP_UCODE_SIZE * 4;
me_req_size = SI_PM4_UCODE_SIZE * 4;
@@ -1742,6 +1748,10 @@
default: BUG();
}
+ /* this memory configuration requires special firmware */
+ if (((RREG32(MC_SEQ_MISC0) & 0xff000000) >> 24) == 0x58)
+ si58_fw = true;
+
DRM_INFO("Loading %s Microcode\n", new_chip_name);
snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", new_chip_name);
@@ -1845,7 +1855,10 @@
}
}
- snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name);
+ if (si58_fw)
+ snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+ else
+ snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name);
err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
if (err) {
snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name);
@@ -1876,7 +1889,9 @@
}
}
- if (new_smc)
+ if (banks2_fw)
+ snprintf(fw_name, sizeof(fw_name), "radeon/banks_k_2_smc.bin");
+ else if (new_smc)
snprintf(fw_name, sizeof(fw_name), "radeon/%s_k_smc.bin", new_chip_name);
else
snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", new_chip_name);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 13ba73f..2944916 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -3008,17 +3008,6 @@
(rdev->pdev->device == 0x6817) ||
(rdev->pdev->device == 0x6806))
max_mclk = 120000;
- } else if (rdev->family == CHIP_OLAND) {
- if ((rdev->pdev->revision == 0xC7) ||
- (rdev->pdev->revision == 0x80) ||
- (rdev->pdev->revision == 0x81) ||
- (rdev->pdev->revision == 0x83) ||
- (rdev->pdev->revision == 0x87) ||
- (rdev->pdev->device == 0x6604) ||
- (rdev->pdev->device == 0x6605)) {
- max_sclk = 75000;
- max_mclk = 80000;
- }
} else if (rdev->family == CHIP_HAINAN) {
if ((rdev->pdev->revision == 0x81) ||
(rdev->pdev->revision == 0x83) ||
@@ -3027,7 +3016,6 @@
(rdev->pdev->device == 0x6665) ||
(rdev->pdev->device == 0x6667)) {
max_sclk = 75000;
- max_mclk = 80000;
}
}
/* Apply dpm quirks */
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index a0fd3e6..7aadce1 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -839,7 +839,7 @@
}
- __drm_atomic_helper_crtc_destroy_state(state);
+ drm_atomic_helper_crtc_destroy_state(crtc, state);
}
static const struct drm_crtc_funcs vc4_crtc_funcs = {
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index db92077..ab30169 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -594,12 +594,14 @@
args->shader_rec_count);
struct vc4_bo *bo;
- if (uniforms_offset < shader_rec_offset ||
+ if (shader_rec_offset < args->bin_cl_size ||
+ uniforms_offset < shader_rec_offset ||
exec_size < uniforms_offset ||
args->shader_rec_count >= (UINT_MAX /
sizeof(struct vc4_shader_state)) ||
temp_size < exec_size) {
DRM_ERROR("overflow in exec arguments\n");
+ ret = -EINVAL;
goto fail;
}
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 881bf48..686cdd3 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -858,7 +858,7 @@
}
}
plane = &vc4_plane->base;
- ret = drm_universal_plane_init(dev, plane, 0xff,
+ ret = drm_universal_plane_init(dev, plane, 0,
&vc4_plane_funcs,
formats, num_formats,
type, NULL);
diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c
index 08886a3..5cdd003 100644
--- a/drivers/gpu/drm/vc4/vc4_render_cl.c
+++ b/drivers/gpu/drm/vc4/vc4_render_cl.c
@@ -461,7 +461,7 @@
}
ret = vc4_full_res_bounds_check(exec, *obj, surf);
- if (!ret)
+ if (ret)
return ret;
return 0;
diff --git a/drivers/gpu/drm/virtio/virtgpu_fb.c b/drivers/gpu/drm/virtio/virtgpu_fb.c
index dd21f95..cde9f37 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fb.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fb.c
@@ -331,7 +331,7 @@
info->fbops = &virtio_gpufb_ops;
info->pixmap.flags = FB_PIXMAP_SYSTEM;
- info->screen_base = obj->vmap;
+ info->screen_buffer = obj->vmap;
info->screen_size = obj->gem_base.size;
drm_fb_helper_fill_fix(info, fb->pitches[0], fb->depth);
drm_fb_helper_fill_var(info, &vfbdev->helper,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 723fd76..7a96798 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -481,8 +481,7 @@
mode_cmd.height = var->yres;
mode_cmd.pitches[0] = ((var->bits_per_pixel + 7) / 8) * mode_cmd.width;
mode_cmd.pixel_format =
- drm_mode_legacy_fb_format(var->bits_per_pixel,
- ((var->bits_per_pixel + 7) / 8) * mode_cmd.width);
+ drm_mode_legacy_fb_format(var->bits_per_pixel, depth);
cur_fb = par->set_fb;
if (cur_fb && cur_fb->width == mode_cmd.width &&
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index cff060b..ea36b55 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2496,6 +2496,7 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0002) },
{ HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0003) },
{ HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0004) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_PETZL, USB_DEVICE_ID_PETZL_HEADLAMP) },
{ HID_USB_DEVICE(USB_VENDOR_ID_PHILIPS, USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_POWERCOM, USB_DEVICE_ID_POWERCOM_UPS) },
#if IS_ENABLED(CONFIG_MOUSE_SYNAPTICS_USB)
diff --git a/drivers/hid/hid-corsair.c b/drivers/hid/hid-corsair.c
index 717704e..c0303f6 100644
--- a/drivers/hid/hid-corsair.c
+++ b/drivers/hid/hid-corsair.c
@@ -148,26 +148,36 @@
struct usb_interface *usbif = to_usb_interface(dev->parent);
struct usb_device *usbdev = interface_to_usbdev(usbif);
int brightness;
- char data[8];
+ char *data;
+
+ data = kmalloc(8, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
K90_REQUEST_STATUS,
USB_DIR_IN | USB_TYPE_VENDOR |
USB_RECIP_DEVICE, 0, 0, data, 8,
USB_CTRL_SET_TIMEOUT);
- if (ret < 0) {
+ if (ret < 5) {
dev_warn(dev, "Failed to get K90 initial state (error %d).\n",
ret);
- return -EIO;
+ ret = -EIO;
+ goto out;
}
brightness = data[4];
if (brightness < 0 || brightness > 3) {
dev_warn(dev,
"Read invalid backlight brightness: %02hhx.\n",
data[4]);
- return -EIO;
+ ret = -EIO;
+ goto out;
}
- return brightness;
+ ret = brightness;
+out:
+ kfree(data);
+
+ return ret;
}
static enum led_brightness k90_record_led_get(struct led_classdev *led_cdev)
@@ -253,17 +263,22 @@
struct usb_interface *usbif = to_usb_interface(dev->parent);
struct usb_device *usbdev = interface_to_usbdev(usbif);
const char *macro_mode;
- char data[8];
+ char *data;
+
+ data = kmalloc(2, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
K90_REQUEST_GET_MODE,
USB_DIR_IN | USB_TYPE_VENDOR |
USB_RECIP_DEVICE, 0, 0, data, 2,
USB_CTRL_SET_TIMEOUT);
- if (ret < 0) {
+ if (ret < 1) {
dev_warn(dev, "Failed to get K90 initial mode (error %d).\n",
ret);
- return -EIO;
+ ret = -EIO;
+ goto out;
}
switch (data[0]) {
@@ -277,10 +292,15 @@
default:
dev_warn(dev, "K90 in unknown mode: %02hhx.\n",
data[0]);
- return -EIO;
+ ret = -EIO;
+ goto out;
}
- return snprintf(buf, PAGE_SIZE, "%s\n", macro_mode);
+ ret = snprintf(buf, PAGE_SIZE, "%s\n", macro_mode);
+out:
+ kfree(data);
+
+ return ret;
}
static ssize_t k90_store_macro_mode(struct device *dev,
@@ -320,26 +340,36 @@
struct usb_interface *usbif = to_usb_interface(dev->parent);
struct usb_device *usbdev = interface_to_usbdev(usbif);
int current_profile;
- char data[8];
+ char *data;
+
+ data = kmalloc(8, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
K90_REQUEST_STATUS,
USB_DIR_IN | USB_TYPE_VENDOR |
USB_RECIP_DEVICE, 0, 0, data, 8,
USB_CTRL_SET_TIMEOUT);
- if (ret < 0) {
+ if (ret < 8) {
dev_warn(dev, "Failed to get K90 initial state (error %d).\n",
ret);
- return -EIO;
+ ret = -EIO;
+ goto out;
}
current_profile = data[7];
if (current_profile < 1 || current_profile > 3) {
dev_warn(dev, "Read invalid current profile: %02hhx.\n",
data[7]);
- return -EIO;
+ ret = -EIO;
+ goto out;
}
- return snprintf(buf, PAGE_SIZE, "%d\n", current_profile);
+ ret = snprintf(buf, PAGE_SIZE, "%d\n", current_profile);
+out:
+ kfree(data);
+
+ return ret;
}
static ssize_t k90_store_current_profile(struct device *dev,
diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c
index f31a778..b22d0f8 100644
--- a/drivers/hid/hid-cp2112.c
+++ b/drivers/hid/hid-cp2112.c
@@ -168,7 +168,7 @@
atomic_t xfer_avail;
struct gpio_chip gc;
u8 *in_out_buffer;
- spinlock_t lock;
+ struct mutex lock;
struct gpio_desc *desc[8];
bool gpio_poll;
@@ -186,10 +186,9 @@
struct cp2112_device *dev = gpiochip_get_data(chip);
struct hid_device *hdev = dev->hdev;
u8 *buf = dev->in_out_buffer;
- unsigned long flags;
int ret;
- spin_lock_irqsave(&dev->lock, flags);
+ mutex_lock(&dev->lock);
ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf,
CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT,
@@ -213,8 +212,8 @@
ret = 0;
exit:
- spin_unlock_irqrestore(&dev->lock, flags);
- return ret <= 0 ? ret : -EIO;
+ mutex_unlock(&dev->lock);
+ return ret < 0 ? ret : -EIO;
}
static void cp2112_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
@@ -222,10 +221,9 @@
struct cp2112_device *dev = gpiochip_get_data(chip);
struct hid_device *hdev = dev->hdev;
u8 *buf = dev->in_out_buffer;
- unsigned long flags;
int ret;
- spin_lock_irqsave(&dev->lock, flags);
+ mutex_lock(&dev->lock);
buf[0] = CP2112_GPIO_SET;
buf[1] = value ? 0xff : 0;
@@ -237,7 +235,7 @@
if (ret < 0)
hid_err(hdev, "error setting GPIO values: %d\n", ret);
- spin_unlock_irqrestore(&dev->lock, flags);
+ mutex_unlock(&dev->lock);
}
static int cp2112_gpio_get_all(struct gpio_chip *chip)
@@ -245,10 +243,9 @@
struct cp2112_device *dev = gpiochip_get_data(chip);
struct hid_device *hdev = dev->hdev;
u8 *buf = dev->in_out_buffer;
- unsigned long flags;
int ret;
- spin_lock_irqsave(&dev->lock, flags);
+ mutex_lock(&dev->lock);
ret = hid_hw_raw_request(hdev, CP2112_GPIO_GET, buf,
CP2112_GPIO_GET_LENGTH, HID_FEATURE_REPORT,
@@ -262,7 +259,7 @@
ret = buf[1];
exit:
- spin_unlock_irqrestore(&dev->lock, flags);
+ mutex_unlock(&dev->lock);
return ret;
}
@@ -284,10 +281,9 @@
struct cp2112_device *dev = gpiochip_get_data(chip);
struct hid_device *hdev = dev->hdev;
u8 *buf = dev->in_out_buffer;
- unsigned long flags;
int ret;
- spin_lock_irqsave(&dev->lock, flags);
+ mutex_lock(&dev->lock);
ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf,
CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT,
@@ -308,7 +304,7 @@
goto fail;
}
- spin_unlock_irqrestore(&dev->lock, flags);
+ mutex_unlock(&dev->lock);
/*
* Set gpio value when output direction is already set,
@@ -319,7 +315,7 @@
return 0;
fail:
- spin_unlock_irqrestore(&dev->lock, flags);
+ mutex_unlock(&dev->lock);
return ret < 0 ? ret : -EIO;
}
@@ -1235,7 +1231,7 @@
if (!dev->in_out_buffer)
return -ENOMEM;
- spin_lock_init(&dev->lock);
+ mutex_init(&dev->lock);
ret = hid_parse(hdev);
if (ret) {
diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c
index 1b764d1..1689568 100644
--- a/drivers/hid/hid-cypress.c
+++ b/drivers/hid/hid-cypress.c
@@ -39,6 +39,9 @@
if (!(quirks & CP_RDESC_SWAPPED_MIN_MAX))
return rdesc;
+ if (*rsize < 4)
+ return rdesc;
+
for (i = 0; i < *rsize - 4; i++)
if (rdesc[i] == 0x29 && rdesc[i + 2] == 0x19) {
rdesc[i] = 0x19;
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 54bd22d..350accf 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -76,6 +76,9 @@
#define USB_VENDOR_ID_ALPS_JP 0x044E
#define HID_DEVICE_ID_ALPS_U1_DUAL 0x120B
+#define USB_VENDOR_ID_AMI 0x046b
+#define USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE 0xff10
+
#define USB_VENDOR_ID_ANTON 0x1130
#define USB_DEVICE_ID_ANTON_TOUCH_PAD 0x3101
@@ -816,6 +819,9 @@
#define USB_VENDOR_ID_PETALYNX 0x18b1
#define USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE 0x0037
+#define USB_VENDOR_ID_PETZL 0x2122
+#define USB_DEVICE_ID_PETZL_HEADLAMP 0x1234
+
#define USB_VENDOR_ID_PHILIPS 0x0471
#define USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE 0x0617
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index c5c5fbe..52026dc 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -872,7 +872,7 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_WINGMAN_FFG),
.driver_data = LG_NOGET | LG_FF4 },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD2),
- .driver_data = LG_FF2 },
+ .driver_data = LG_NOGET | LG_FF2 },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_FLIGHT_SYSTEM_G940),
.driver_data = LG_FF3 },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_SPACENAVIGATOR),
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 78fb32a..ea3c354 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -426,6 +426,15 @@
if (ret)
goto out_unlock;
+ /*
+ * The HID over I2C specification states that if a DEVICE needs time
+ * after the PWR_ON request, it should utilise CLOCK stretching.
+ * However, it has been observered that the Windows driver provides a
+ * 1ms sleep between the PWR_ON and RESET requests and that some devices
+ * rely on this.
+ */
+ usleep_range(1000, 5000);
+
i2c_hid_dbg(ihid, "resetting...\n");
ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0);
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index e9d6cc7..30a2977 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -57,6 +57,7 @@
{ USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_AKAI, USB_DEVICE_ID_AKAI_MPKMINI2, HID_QUIRK_NO_INIT_REPORTS },
{ USB_VENDOR_ID_AKAI_09E8, USB_DEVICE_ID_AKAI_09E8_MIDIMIX, HID_QUIRK_NO_INIT_REPORTS },
+ { USB_VENDOR_ID_AMI, USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE, HID_QUIRK_ALWAYS_POLL },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_UC100KM, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS124U, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_2PORTKVM, HID_QUIRK_NOGET },
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index b9779bc..8aeca03 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -740,6 +740,11 @@
return retval;
}
+ if (wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH)
+ wacom_wac->shared->touch = hdev;
+ else if (wacom_wac->features.device_type & WACOM_DEVICETYPE_PEN)
+ wacom_wac->shared->pen = hdev;
+
out:
mutex_unlock(&wacom_udev_list_lock);
return retval;
@@ -2036,10 +2041,6 @@
if (error)
goto fail;
- error = wacom_add_shared_data(hdev);
- if (error)
- goto fail;
-
/*
* Bamboo Pad has a generic hid handling for the Pen, and we switch it
* into debug mode for the touch part.
@@ -2080,10 +2081,9 @@
wacom_update_name(wacom, wireless ? " (WL)" : "");
- if (wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH)
- wacom_wac->shared->touch = hdev;
- else if (wacom_wac->features.device_type & WACOM_DEVICETYPE_PEN)
- wacom_wac->shared->pen = hdev;
+ error = wacom_add_shared_data(hdev);
+ if (error)
+ goto fail;
if (!(features->device_type & WACOM_DEVICETYPE_WL_MONITOR) &&
(features->quirks & WACOM_QUIRK_BATTERY)) {
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index b1a9a3c..672145b 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -166,19 +166,21 @@
wacom->id[0] = STYLUS_DEVICE_ID;
}
- pressure = (signed char)((data[7] << 1) | ((data[4] >> 2) & 1));
- if (features->pressure_max > 255)
- pressure = (pressure << 1) | ((data[4] >> 6) & 1);
- pressure += (features->pressure_max + 1) / 2;
+ if (prox) {
+ pressure = (signed char)((data[7] << 1) | ((data[4] >> 2) & 1));
+ if (features->pressure_max > 255)
+ pressure = (pressure << 1) | ((data[4] >> 6) & 1);
+ pressure += (features->pressure_max + 1) / 2;
- input_report_abs(input, ABS_X, data[3] | (data[2] << 7) | ((data[1] & 0x03) << 14));
- input_report_abs(input, ABS_Y, data[6] | (data[5] << 7) | ((data[4] & 0x03) << 14));
- input_report_abs(input, ABS_PRESSURE, pressure);
+ input_report_abs(input, ABS_X, data[3] | (data[2] << 7) | ((data[1] & 0x03) << 14));
+ input_report_abs(input, ABS_Y, data[6] | (data[5] << 7) | ((data[4] & 0x03) << 14));
+ input_report_abs(input, ABS_PRESSURE, pressure);
- input_report_key(input, BTN_TOUCH, data[4] & 0x08);
- input_report_key(input, BTN_STYLUS, data[4] & 0x10);
- /* Only allow the stylus2 button to be reported for the pen tool. */
- input_report_key(input, BTN_STYLUS2, (wacom->tool[0] == BTN_TOOL_PEN) && (data[4] & 0x20));
+ input_report_key(input, BTN_TOUCH, data[4] & 0x08);
+ input_report_key(input, BTN_STYLUS, data[4] & 0x10);
+ /* Only allow the stylus2 button to be reported for the pen tool. */
+ input_report_key(input, BTN_STYLUS2, (wacom->tool[0] == BTN_TOOL_PEN) && (data[4] & 0x20));
+ }
if (!prox)
wacom->id[0] = 0;
@@ -2187,6 +2189,16 @@
wacom_report_events(hdev, report);
+ /*
+ * Non-input reports may be sent prior to the device being
+ * completely initialized. Since only their events need
+ * to be processed, exit after 'wacom_report_events' has
+ * been called to prevent potential crashes in the report-
+ * processing functions.
+ */
+ if (report->type != HID_INPUT_REPORT)
+ return;
+
if (WACOM_PAD_FIELD(field)) {
wacom_wac_pad_battery_report(hdev, report);
if (wacom->wacom_wac.pad_input)
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index cd49cb1..308dbda 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -383,6 +383,7 @@
return ret;
}
+ init_cached_read_index(channel);
next_read_location = hv_get_next_read_location(inring_info);
next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc,
sizeof(desc),
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 190d270..0649d53f3 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1459,6 +1459,16 @@
This driver can also be built as a module. If so, the module
will be called sch5636.
+config SENSORS_STTS751
+ tristate "ST Microelectronics STTS751"
+ depends on I2C
+ help
+ If you say yes here you get support for STTS751
+ temperature sensor chips.
+
+ This driver can also be built as a module. If so, the module
+ will be called stts751.
+
config SENSORS_SMM665
tristate "Summit Microelectronics SMM665"
depends on I2C
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index d2cb7e8..5509edf 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -148,6 +148,7 @@
obj-$(CONFIG_SENSORS_SMSC47B397)+= smsc47b397.o
obj-$(CONFIG_SENSORS_SMSC47M1) += smsc47m1.o
obj-$(CONFIG_SENSORS_SMSC47M192)+= smsc47m192.o
+obj-$(CONFIG_SENSORS_STTS751) += stts751.o
obj-$(CONFIG_SENSORS_AMC6821) += amc6821.o
obj-$(CONFIG_SENSORS_TC74) += tc74.o
obj-$(CONFIG_SENSORS_THMC50) += thmc50.o
diff --git a/drivers/hwmon/adc128d818.c b/drivers/hwmon/adc128d818.c
index ad2b47e..bbe3a5c 100644
--- a/drivers/hwmon/adc128d818.c
+++ b/drivers/hwmon/adc128d818.c
@@ -28,6 +28,7 @@
#include <linux/regulator/consumer.h>
#include <linux/mutex.h>
#include <linux/bitops.h>
+#include <linux/of.h>
/* Addresses to scan
* The chip also supports addresses 0x35..0x37. Don't scan those addresses
@@ -58,15 +59,22 @@
#define ADC128_REG_MAN_ID 0x3e
#define ADC128_REG_DEV_ID 0x3f
+/* No. of voltage entries in adc128_attrs */
+#define ADC128_ATTR_NUM_VOLT (8 * 4)
+
+/* Voltage inputs visible per operation mode */
+static const u8 num_inputs[] = { 7, 8, 4, 6 };
+
struct adc128_data {
struct i2c_client *client;
struct regulator *regulator;
int vref; /* Reference voltage in mV */
struct mutex update_lock;
+ u8 mode; /* Operation mode */
bool valid; /* true if following fields are valid */
unsigned long last_updated; /* In jiffies */
- u16 in[3][7]; /* Register value, normalized to 12 bit
+ u16 in[3][8]; /* Register value, normalized to 12 bit
* 0: input voltage
* 1: min limit
* 2: max limit
@@ -87,7 +95,7 @@
mutex_lock(&data->update_lock);
if (time_after(jiffies, data->last_updated + HZ) || !data->valid) {
- for (i = 0; i < 7; i++) {
+ for (i = 0; i < num_inputs[data->mode]; i++) {
rv = i2c_smbus_read_word_swapped(client,
ADC128_REG_IN(i));
if (rv < 0)
@@ -107,20 +115,25 @@
data->in[2][i] = rv << 4;
}
- rv = i2c_smbus_read_word_swapped(client, ADC128_REG_TEMP);
- if (rv < 0)
- goto abort;
- data->temp[0] = rv >> 7;
+ if (data->mode != 1) {
+ rv = i2c_smbus_read_word_swapped(client,
+ ADC128_REG_TEMP);
+ if (rv < 0)
+ goto abort;
+ data->temp[0] = rv >> 7;
- rv = i2c_smbus_read_byte_data(client, ADC128_REG_TEMP_MAX);
- if (rv < 0)
- goto abort;
- data->temp[1] = rv << 1;
+ rv = i2c_smbus_read_byte_data(client,
+ ADC128_REG_TEMP_MAX);
+ if (rv < 0)
+ goto abort;
+ data->temp[1] = rv << 1;
- rv = i2c_smbus_read_byte_data(client, ADC128_REG_TEMP_HYST);
- if (rv < 0)
- goto abort;
- data->temp[2] = rv << 1;
+ rv = i2c_smbus_read_byte_data(client,
+ ADC128_REG_TEMP_HYST);
+ if (rv < 0)
+ goto abort;
+ data->temp[2] = rv << 1;
+ }
rv = i2c_smbus_read_byte_data(client, ADC128_REG_ALARM);
if (rv < 0)
@@ -240,6 +253,25 @@
return sprintf(buf, "%u\n", !!(alarms & mask));
}
+static umode_t adc128_is_visible(struct kobject *kobj,
+ struct attribute *attr, int index)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct adc128_data *data = dev_get_drvdata(dev);
+
+ if (index < ADC128_ATTR_NUM_VOLT) {
+ /* Voltage, visible according to num_inputs[] */
+ if (index >= num_inputs[data->mode] * 4)
+ return 0;
+ } else {
+ /* Temperature, visible if not in mode 1 */
+ if (data->mode == 1)
+ return 0;
+ }
+
+ return attr->mode;
+}
+
static SENSOR_DEVICE_ATTR_2(in0_input, S_IRUGO,
adc128_show_in, NULL, 0, 0);
static SENSOR_DEVICE_ATTR_2(in0_min, S_IWUSR | S_IRUGO,
@@ -289,6 +321,13 @@
static SENSOR_DEVICE_ATTR_2(in6_max, S_IWUSR | S_IRUGO,
adc128_show_in, adc128_set_in, 6, 2);
+static SENSOR_DEVICE_ATTR_2(in7_input, S_IRUGO,
+ adc128_show_in, NULL, 7, 0);
+static SENSOR_DEVICE_ATTR_2(in7_min, S_IWUSR | S_IRUGO,
+ adc128_show_in, adc128_set_in, 7, 1);
+static SENSOR_DEVICE_ATTR_2(in7_max, S_IWUSR | S_IRUGO,
+ adc128_show_in, adc128_set_in, 7, 2);
+
static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, adc128_show_temp, NULL, 0);
static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO,
adc128_show_temp, adc128_set_temp, 1);
@@ -302,44 +341,54 @@
static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, adc128_show_alarm, NULL, 4);
static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, adc128_show_alarm, NULL, 5);
static SENSOR_DEVICE_ATTR(in6_alarm, S_IRUGO, adc128_show_alarm, NULL, 6);
+static SENSOR_DEVICE_ATTR(in7_alarm, S_IRUGO, adc128_show_alarm, NULL, 7);
static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, adc128_show_alarm, NULL, 7);
static struct attribute *adc128_attrs[] = {
- &sensor_dev_attr_in0_min.dev_attr.attr,
- &sensor_dev_attr_in1_min.dev_attr.attr,
- &sensor_dev_attr_in2_min.dev_attr.attr,
- &sensor_dev_attr_in3_min.dev_attr.attr,
- &sensor_dev_attr_in4_min.dev_attr.attr,
- &sensor_dev_attr_in5_min.dev_attr.attr,
- &sensor_dev_attr_in6_min.dev_attr.attr,
- &sensor_dev_attr_in0_max.dev_attr.attr,
- &sensor_dev_attr_in1_max.dev_attr.attr,
- &sensor_dev_attr_in2_max.dev_attr.attr,
- &sensor_dev_attr_in3_max.dev_attr.attr,
- &sensor_dev_attr_in4_max.dev_attr.attr,
- &sensor_dev_attr_in5_max.dev_attr.attr,
- &sensor_dev_attr_in6_max.dev_attr.attr,
+ &sensor_dev_attr_in0_alarm.dev_attr.attr,
&sensor_dev_attr_in0_input.dev_attr.attr,
+ &sensor_dev_attr_in0_max.dev_attr.attr,
+ &sensor_dev_attr_in0_min.dev_attr.attr,
+ &sensor_dev_attr_in1_alarm.dev_attr.attr,
&sensor_dev_attr_in1_input.dev_attr.attr,
+ &sensor_dev_attr_in1_max.dev_attr.attr,
+ &sensor_dev_attr_in1_min.dev_attr.attr,
+ &sensor_dev_attr_in2_alarm.dev_attr.attr,
&sensor_dev_attr_in2_input.dev_attr.attr,
+ &sensor_dev_attr_in2_max.dev_attr.attr,
+ &sensor_dev_attr_in2_min.dev_attr.attr,
+ &sensor_dev_attr_in3_alarm.dev_attr.attr,
&sensor_dev_attr_in3_input.dev_attr.attr,
+ &sensor_dev_attr_in3_max.dev_attr.attr,
+ &sensor_dev_attr_in3_min.dev_attr.attr,
+ &sensor_dev_attr_in4_alarm.dev_attr.attr,
&sensor_dev_attr_in4_input.dev_attr.attr,
+ &sensor_dev_attr_in4_max.dev_attr.attr,
+ &sensor_dev_attr_in4_min.dev_attr.attr,
+ &sensor_dev_attr_in5_alarm.dev_attr.attr,
&sensor_dev_attr_in5_input.dev_attr.attr,
+ &sensor_dev_attr_in5_max.dev_attr.attr,
+ &sensor_dev_attr_in5_min.dev_attr.attr,
+ &sensor_dev_attr_in6_alarm.dev_attr.attr,
&sensor_dev_attr_in6_input.dev_attr.attr,
+ &sensor_dev_attr_in6_max.dev_attr.attr,
+ &sensor_dev_attr_in6_min.dev_attr.attr,
+ &sensor_dev_attr_in7_alarm.dev_attr.attr,
+ &sensor_dev_attr_in7_input.dev_attr.attr,
+ &sensor_dev_attr_in7_max.dev_attr.attr,
+ &sensor_dev_attr_in7_min.dev_attr.attr,
&sensor_dev_attr_temp1_input.dev_attr.attr,
&sensor_dev_attr_temp1_max.dev_attr.attr,
- &sensor_dev_attr_temp1_max_hyst.dev_attr.attr,
- &sensor_dev_attr_in0_alarm.dev_attr.attr,
- &sensor_dev_attr_in1_alarm.dev_attr.attr,
- &sensor_dev_attr_in2_alarm.dev_attr.attr,
- &sensor_dev_attr_in3_alarm.dev_attr.attr,
- &sensor_dev_attr_in4_alarm.dev_attr.attr,
- &sensor_dev_attr_in5_alarm.dev_attr.attr,
- &sensor_dev_attr_in6_alarm.dev_attr.attr,
&sensor_dev_attr_temp1_max_alarm.dev_attr.attr,
+ &sensor_dev_attr_temp1_max_hyst.dev_attr.attr,
NULL
};
-ATTRIBUTE_GROUPS(adc128);
+
+static struct attribute_group adc128_group = {
+ .attrs = adc128_attrs,
+ .is_visible = adc128_is_visible,
+};
+__ATTRIBUTE_GROUPS(adc128);
static int adc128_detect(struct i2c_client *client, struct i2c_board_info *info)
{
@@ -387,6 +436,15 @@
if (err)
return err;
+ /* Set operation mode, if non-default */
+ if (data->mode != 0) {
+ err = i2c_smbus_write_byte_data(client,
+ ADC128_REG_CONFIG_ADV,
+ data->mode << 1);
+ if (err)
+ return err;
+ }
+
/* Start monitoring */
err = i2c_smbus_write_byte_data(client, ADC128_REG_CONFIG, 0x01);
if (err)
@@ -433,6 +491,21 @@
data->vref = 2560; /* 2.56V, in mV */
}
+ /* Operation mode is optional. If unspecified, keep current mode */
+ if (of_property_read_u8(dev->of_node, "ti,mode", &data->mode) == 0) {
+ if (data->mode > 3) {
+ dev_err(dev, "invalid operation mode %d\n",
+ data->mode);
+ err = -EINVAL;
+ goto error;
+ }
+ } else {
+ err = i2c_smbus_read_byte_data(client, ADC128_REG_CONFIG_ADV);
+ if (err < 0)
+ goto error;
+ data->mode = (err >> 1) & ADC128_REG_MASK;
+ }
+
data->client = client;
i2c_set_clientdata(client, data);
mutex_init(&data->update_lock);
diff --git a/drivers/hwmon/adm1021.c b/drivers/hwmon/adm1021.c
index 1fdcc3e..eacf10f 100644
--- a/drivers/hwmon/adm1021.c
+++ b/drivers/hwmon/adm1021.c
@@ -191,7 +191,7 @@
return sprintf(buf, "%u\n", (data->alarms >> index) & 1);
}
-static ssize_t show_alarms(struct device *dev,
+static ssize_t alarms_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
@@ -251,16 +251,16 @@
return count;
}
-static ssize_t show_low_power(struct device *dev,
+static ssize_t low_power_show(struct device *dev,
struct device_attribute *devattr, char *buf)
{
struct adm1021_data *data = adm1021_update_device(dev);
return sprintf(buf, "%d\n", data->low_power);
}
-static ssize_t set_low_power(struct device *dev,
- struct device_attribute *devattr,
- const char *buf, size_t count)
+static ssize_t low_power_store(struct device *dev,
+ struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct adm1021_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -303,8 +303,8 @@
static SENSOR_DEVICE_ATTR(temp2_min_alarm, S_IRUGO, show_alarm, NULL, 3);
static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2);
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
-static DEVICE_ATTR(low_power, S_IWUSR | S_IRUGO, show_low_power, set_low_power);
+static DEVICE_ATTR_RO(alarms);
+static DEVICE_ATTR_RW(low_power);
static struct attribute *adm1021_attributes[] = {
&sensor_dev_attr_temp1_max.dev_attr.attr,
diff --git a/drivers/hwmon/adm1025.c b/drivers/hwmon/adm1025.c
index 1abb460..1e4dad3 100644
--- a/drivers/hwmon/adm1025.c
+++ b/drivers/hwmon/adm1025.c
@@ -333,12 +333,12 @@
set_temp(2);
static ssize_t
-show_alarms(struct device *dev, struct device_attribute *attr, char *buf)
+alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct adm1025_data *data = adm1025_update_device(dev);
return sprintf(buf, "%u\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t
show_alarm(struct device *dev, struct device_attribute *attr, char *buf)
@@ -358,21 +358,21 @@
static SENSOR_DEVICE_ATTR(temp1_fault, S_IRUGO, show_alarm, NULL, 14);
static ssize_t
-show_vid(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct adm1025_data *data = adm1025_update_device(dev);
return sprintf(buf, "%u\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
static ssize_t
-show_vrm(struct device *dev, struct device_attribute *attr, char *buf)
+vrm_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct adm1025_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%u\n", data->vrm);
}
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm1025_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -388,7 +388,7 @@
data->vrm = val;
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
/*
* Real code
diff --git a/drivers/hwmon/adm1026.c b/drivers/hwmon/adm1026.c
index b2a5d9e..e43f09a 100644
--- a/drivers/hwmon/adm1026.c
+++ b/drivers/hwmon/adm1026.c
@@ -1034,15 +1034,15 @@
temp_crit_reg(2);
temp_crit_reg(3);
-static ssize_t show_analog_out_reg(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t analog_out_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct adm1026_data *data = adm1026_update_device(dev);
return sprintf(buf, "%d\n", DAC_FROM_REG(data->analog_out));
}
-static ssize_t set_analog_out_reg(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t analog_out_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm1026_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -1060,11 +1060,10 @@
return count;
}
-static DEVICE_ATTR(analog_out, S_IRUGO | S_IWUSR, show_analog_out_reg,
- set_analog_out_reg);
+static DEVICE_ATTR_RW(analog_out);
-static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct adm1026_data *data = adm1026_update_device(dev);
int vid = (data->gpio >> 11) & 0x1f;
@@ -1073,17 +1072,17 @@
return sprintf(buf, "%d\n", vid_from_reg(vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
-static ssize_t show_vrm_reg(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct adm1026_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", data->vrm);
}
-static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm1026_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -1100,16 +1099,16 @@
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
-static ssize_t show_alarms_reg(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct adm1026_data *data = adm1026_update_device(dev);
return sprintf(buf, "%ld\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -1148,14 +1147,15 @@
static SENSOR_DEVICE_ATTR(in10_alarm, S_IRUGO, show_alarm, NULL, 25);
static SENSOR_DEVICE_ATTR(in8_alarm, S_IRUGO, show_alarm, NULL, 26);
-static ssize_t show_alarm_mask(struct device *dev,
+static ssize_t alarm_mask_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct adm1026_data *data = adm1026_update_device(dev);
return sprintf(buf, "%ld\n", data->alarm_mask);
}
-static ssize_t set_alarm_mask(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t alarm_mask_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm1026_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -1186,18 +1186,17 @@
return count;
}
-static DEVICE_ATTR(alarm_mask, S_IRUGO | S_IWUSR, show_alarm_mask,
- set_alarm_mask);
+static DEVICE_ATTR_RW(alarm_mask);
-static ssize_t show_gpio(struct device *dev, struct device_attribute *attr,
+static ssize_t gpio_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct adm1026_data *data = adm1026_update_device(dev);
return sprintf(buf, "%ld\n", data->gpio);
}
-static ssize_t set_gpio(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t gpio_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm1026_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -1221,16 +1220,18 @@
return count;
}
-static DEVICE_ATTR(gpio, S_IRUGO | S_IWUSR, show_gpio, set_gpio);
+static DEVICE_ATTR_RW(gpio);
-static ssize_t show_gpio_mask(struct device *dev, struct device_attribute *attr,
+static ssize_t gpio_mask_show(struct device *dev,
+ struct device_attribute *attr,
char *buf)
{
struct adm1026_data *data = adm1026_update_device(dev);
return sprintf(buf, "%ld\n", data->gpio_mask);
}
-static ssize_t set_gpio_mask(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t gpio_mask_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct adm1026_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -1254,17 +1255,17 @@
return count;
}
-static DEVICE_ATTR(gpio_mask, S_IRUGO | S_IWUSR, show_gpio_mask, set_gpio_mask);
+static DEVICE_ATTR_RW(gpio_mask);
-static ssize_t show_pwm_reg(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct adm1026_data *data = adm1026_update_device(dev);
return sprintf(buf, "%d\n", PWM_FROM_REG(data->pwm1.pwm));
}
-static ssize_t set_pwm_reg(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm1026_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -1285,16 +1286,17 @@
return count;
}
-static ssize_t show_auto_pwm_min(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t temp1_auto_point1_pwm_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
{
struct adm1026_data *data = adm1026_update_device(dev);
return sprintf(buf, "%d\n", data->pwm1.auto_pwm_min);
}
-static ssize_t set_auto_pwm_min(struct device *dev,
- struct device_attribute *attr, const char *buf,
- size_t count)
+static ssize_t temp1_auto_point1_pwm_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm1026_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -1316,21 +1318,23 @@
return count;
}
-static ssize_t show_auto_pwm_max(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t temp1_auto_point2_pwm_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
{
return sprintf(buf, "%d\n", ADM1026_PWM_MAX);
}
-static ssize_t show_pwm_enable(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t pwm1_enable_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct adm1026_data *data = adm1026_update_device(dev);
return sprintf(buf, "%d\n", data->pwm1.enable);
}
-static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm1026_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -1366,25 +1370,25 @@
}
/* enable PWM fan control */
-static DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm_reg, set_pwm_reg);
-static DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, show_pwm_reg, set_pwm_reg);
-static DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, show_pwm_reg, set_pwm_reg);
-static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, show_pwm_enable,
- set_pwm_enable);
-static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR, show_pwm_enable,
- set_pwm_enable);
-static DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR, show_pwm_enable,
- set_pwm_enable);
-static DEVICE_ATTR(temp1_auto_point1_pwm, S_IRUGO | S_IWUSR,
- show_auto_pwm_min, set_auto_pwm_min);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, pwm1_show, pwm1_store);
+static DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, pwm1_show, pwm1_store);
+static DEVICE_ATTR_RW(pwm1_enable);
+static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR, pwm1_enable_show,
+ pwm1_enable_store);
+static DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR, pwm1_enable_show,
+ pwm1_enable_store);
+static DEVICE_ATTR_RW(temp1_auto_point1_pwm);
static DEVICE_ATTR(temp2_auto_point1_pwm, S_IRUGO | S_IWUSR,
- show_auto_pwm_min, set_auto_pwm_min);
+ temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store);
static DEVICE_ATTR(temp3_auto_point1_pwm, S_IRUGO | S_IWUSR,
- show_auto_pwm_min, set_auto_pwm_min);
+ temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store);
-static DEVICE_ATTR(temp1_auto_point2_pwm, S_IRUGO, show_auto_pwm_max, NULL);
-static DEVICE_ATTR(temp2_auto_point2_pwm, S_IRUGO, show_auto_pwm_max, NULL);
-static DEVICE_ATTR(temp3_auto_point2_pwm, S_IRUGO, show_auto_pwm_max, NULL);
+static DEVICE_ATTR_RO(temp1_auto_point2_pwm);
+static DEVICE_ATTR(temp2_auto_point2_pwm, S_IRUGO, temp1_auto_point2_pwm_show,
+ NULL);
+static DEVICE_ATTR(temp3_auto_point2_pwm, S_IRUGO, temp1_auto_point2_pwm_show,
+ NULL);
static struct attribute *adm1026_attributes[] = {
&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c
index a581898..bcf5082 100644
--- a/drivers/hwmon/adm1031.c
+++ b/drivers/hwmon/adm1031.c
@@ -829,14 +829,14 @@
temp_reg(3);
/* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct adm1031_data *data = adm1031_update_device(dev);
return sprintf(buf, "%d\n", data->alarm);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -867,7 +867,7 @@
16000, 8000, 4000, 2000, 1000, 500, 250, 125,
};
-static ssize_t show_update_interval(struct device *dev,
+static ssize_t update_interval_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct adm1031_data *data = dev_get_drvdata(dev);
@@ -875,9 +875,9 @@
return sprintf(buf, "%u\n", data->update_interval);
}
-static ssize_t set_update_interval(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm1031_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -912,8 +912,7 @@
return count;
}
-static DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, show_update_interval,
- set_update_interval);
+static DEVICE_ATTR_RW(update_interval);
static struct attribute *adm1031_attributes[] = {
&sensor_dev_attr_fan1_input.dev_attr.attr,
diff --git a/drivers/hwmon/adm9240.c b/drivers/hwmon/adm9240.c
index 72bf248..255413f 100644
--- a/drivers/hwmon/adm9240.c
+++ b/drivers/hwmon/adm9240.c
@@ -262,8 +262,8 @@
/*** sysfs accessors ***/
/* temperature */
-static ssize_t show_temp(struct device *dev, struct device_attribute *dummy,
- char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+ struct device_attribute *dummy, char *buf)
{
struct adm9240_data *data = adm9240_update_device(dev);
return sprintf(buf, "%d\n", data->temp / 128 * 500); /* 9-bit value */
@@ -298,7 +298,7 @@
return count;
}
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
+static DEVICE_ATTR_RO(temp1_input);
static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO,
show_max, set_max, 0);
static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IWUSR | S_IRUGO,
@@ -501,13 +501,13 @@
fan(2);
/* alarms */
-static ssize_t show_alarms(struct device *dev,
+static ssize_t alarms_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct adm9240_data *data = adm9240_update_device(dev);
return sprintf(buf, "%u\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -527,25 +527,25 @@
static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
/* vid */
-static ssize_t show_vid(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct adm9240_data *data = adm9240_update_device(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
/* analog output */
-static ssize_t show_aout(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t aout_output_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct adm9240_data *data = adm9240_update_device(dev);
return sprintf(buf, "%d\n", AOUT_FROM_REG(data->aout));
}
-static ssize_t set_aout(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t aout_output_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct adm9240_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -562,7 +562,7 @@
mutex_unlock(&data->update_lock);
return count;
}
-static DEVICE_ATTR(aout_output, S_IRUGO | S_IWUSR, show_aout, set_aout);
+static DEVICE_ATTR_RW(aout_output);
static ssize_t chassis_clear(struct device *dev,
struct device_attribute *attr,
diff --git a/drivers/hwmon/adt7411.c b/drivers/hwmon/adt7411.c
index bdeaece..b939f8a 100644
--- a/drivers/hwmon/adt7411.c
+++ b/drivers/hwmon/adt7411.c
@@ -21,6 +21,21 @@
#include <linux/hwmon-sysfs.h>
#include <linux/slab.h>
+#define ADT7411_REG_STAT_1 0x00
+#define ADT7411_STAT_1_INT_TEMP_HIGH BIT(0)
+#define ADT7411_STAT_1_INT_TEMP_LOW BIT(1)
+#define ADT7411_STAT_1_EXT_TEMP_HIGH_AIN1 BIT(2)
+#define ADT7411_STAT_1_EXT_TEMP_LOW BIT(3)
+#define ADT7411_STAT_1_EXT_TEMP_FAULT BIT(4)
+#define ADT7411_STAT_1_AIN2 BIT(5)
+#define ADT7411_STAT_1_AIN3 BIT(6)
+#define ADT7411_STAT_1_AIN4 BIT(7)
+#define ADT7411_REG_STAT_2 0x01
+#define ADT7411_STAT_2_AIN5 BIT(0)
+#define ADT7411_STAT_2_AIN6 BIT(1)
+#define ADT7411_STAT_2_AIN7 BIT(2)
+#define ADT7411_STAT_2_AIN8 BIT(3)
+#define ADT7411_STAT_2_VDD BIT(4)
#define ADT7411_REG_INT_TEMP_VDD_LSB 0x03
#define ADT7411_REG_EXT_TEMP_AIN14_LSB 0x04
#define ADT7411_REG_VDD_MSB 0x06
@@ -28,20 +43,31 @@
#define ADT7411_REG_EXT_TEMP_AIN1_MSB 0x08
#define ADT7411_REG_CFG1 0x18
-#define ADT7411_CFG1_START_MONITOR (1 << 0)
-#define ADT7411_CFG1_RESERVED_BIT1 (1 << 1)
-#define ADT7411_CFG1_EXT_TDM (1 << 2)
-#define ADT7411_CFG1_RESERVED_BIT3 (1 << 3)
+#define ADT7411_CFG1_START_MONITOR BIT(0)
+#define ADT7411_CFG1_RESERVED_BIT1 BIT(1)
+#define ADT7411_CFG1_EXT_TDM BIT(2)
+#define ADT7411_CFG1_RESERVED_BIT3 BIT(3)
#define ADT7411_REG_CFG2 0x19
-#define ADT7411_CFG2_DISABLE_AVG (1 << 5)
+#define ADT7411_CFG2_DISABLE_AVG BIT(5)
#define ADT7411_REG_CFG3 0x1a
-#define ADT7411_CFG3_ADC_CLK_225 (1 << 0)
-#define ADT7411_CFG3_RESERVED_BIT1 (1 << 1)
-#define ADT7411_CFG3_RESERVED_BIT2 (1 << 2)
-#define ADT7411_CFG3_RESERVED_BIT3 (1 << 3)
-#define ADT7411_CFG3_REF_VDD (1 << 4)
+#define ADT7411_CFG3_ADC_CLK_225 BIT(0)
+#define ADT7411_CFG3_RESERVED_BIT1 BIT(1)
+#define ADT7411_CFG3_RESERVED_BIT2 BIT(2)
+#define ADT7411_CFG3_RESERVED_BIT3 BIT(3)
+#define ADT7411_CFG3_REF_VDD BIT(4)
+
+#define ADT7411_REG_VDD_HIGH 0x23
+#define ADT7411_REG_VDD_LOW 0x24
+#define ADT7411_REG_TEMP_HIGH(nr) (0x25 + 2 * (nr))
+#define ADT7411_REG_TEMP_LOW(nr) (0x26 + 2 * (nr))
+#define ADT7411_REG_IN_HIGH(nr) ((nr) > 1 \
+ ? 0x2b + 2 * ((nr)-2) \
+ : 0x27)
+#define ADT7411_REG_IN_LOW(nr) ((nr) > 1 \
+ ? 0x2c + 2 * ((nr)-2) \
+ : 0x28)
#define ADT7411_REG_DEVICE_ID 0x4d
#define ADT7411_REG_MANUFACTURER_ID 0x4e
@@ -51,6 +77,30 @@
static const unsigned short normal_i2c[] = { 0x48, 0x4a, 0x4b, I2C_CLIENT_END };
+static const u8 adt7411_in_alarm_reg[] = {
+ ADT7411_REG_STAT_2,
+ ADT7411_REG_STAT_1,
+ ADT7411_REG_STAT_1,
+ ADT7411_REG_STAT_1,
+ ADT7411_REG_STAT_1,
+ ADT7411_REG_STAT_2,
+ ADT7411_REG_STAT_2,
+ ADT7411_REG_STAT_2,
+ ADT7411_REG_STAT_2,
+};
+
+static const u8 adt7411_in_alarm_bits[] = {
+ ADT7411_STAT_2_VDD,
+ ADT7411_STAT_1_EXT_TEMP_HIGH_AIN1,
+ ADT7411_STAT_1_AIN2,
+ ADT7411_STAT_1_AIN3,
+ ADT7411_STAT_1_AIN4,
+ ADT7411_STAT_2_AIN5,
+ ADT7411_STAT_2_AIN6,
+ ADT7411_STAT_2_AIN7,
+ ADT7411_STAT_2_AIN8,
+};
+
struct adt7411_data {
struct mutex device_lock; /* for "atomic" device accesses */
struct mutex update_lock;
@@ -165,6 +215,19 @@
};
ATTRIBUTE_GROUPS(adt7411);
+static int adt7411_read_in_alarm(struct device *dev, int channel, long *val)
+{
+ struct adt7411_data *data = dev_get_drvdata(dev);
+ struct i2c_client *client = data->client;
+ int ret;
+
+ ret = i2c_smbus_read_byte_data(client, adt7411_in_alarm_reg[channel]);
+ if (ret < 0)
+ return ret;
+ *val = !!(ret & adt7411_in_alarm_bits[channel]);
+ return 0;
+}
+
static int adt7411_read_in_vdd(struct device *dev, u32 attr, long *val)
{
struct adt7411_data *data = dev_get_drvdata(dev);
@@ -179,11 +242,51 @@
return ret;
*val = ret * 7000 / 1024;
return 0;
+ case hwmon_in_min:
+ ret = i2c_smbus_read_byte_data(client, ADT7411_REG_VDD_LOW);
+ if (ret < 0)
+ return ret;
+ *val = ret * 7000 / 256;
+ return 0;
+ case hwmon_in_max:
+ ret = i2c_smbus_read_byte_data(client, ADT7411_REG_VDD_HIGH);
+ if (ret < 0)
+ return ret;
+ *val = ret * 7000 / 256;
+ return 0;
+ case hwmon_in_alarm:
+ return adt7411_read_in_alarm(dev, 0, val);
default:
return -EOPNOTSUPP;
}
}
+static int adt7411_update_vref(struct device *dev)
+{
+ struct adt7411_data *data = dev_get_drvdata(dev);
+ struct i2c_client *client = data->client;
+ int val;
+
+ if (time_after_eq(jiffies, data->next_update)) {
+ val = i2c_smbus_read_byte_data(client, ADT7411_REG_CFG3);
+ if (val < 0)
+ return val;
+
+ if (val & ADT7411_CFG3_REF_VDD) {
+ val = adt7411_read_in_vdd(dev, hwmon_in_input,
+ &data->vref_cached);
+ if (val < 0)
+ return val;
+ } else {
+ data->vref_cached = 2250;
+ }
+
+ data->next_update = jiffies + HZ;
+ }
+
+ return 0;
+}
+
static int adt7411_read_in_chan(struct device *dev, u32 attr, int channel,
long *val)
{
@@ -191,26 +294,13 @@
struct i2c_client *client = data->client;
int ret;
- int lsb_reg, lsb_shift;
+ int reg, lsb_reg, lsb_shift;
int nr = channel - 1;
mutex_lock(&data->update_lock);
- if (time_after_eq(jiffies, data->next_update)) {
- ret = i2c_smbus_read_byte_data(client, ADT7411_REG_CFG3);
- if (ret < 0)
- goto exit_unlock;
-
- if (ret & ADT7411_CFG3_REF_VDD) {
- ret = adt7411_read_in_vdd(dev, hwmon_in_input,
- &data->vref_cached);
- if (ret < 0)
- goto exit_unlock;
- } else {
- data->vref_cached = 2250;
- }
-
- data->next_update = jiffies + HZ;
- }
+ ret = adt7411_update_vref(dev);
+ if (ret < 0)
+ goto exit_unlock;
switch (attr) {
case hwmon_in_input:
@@ -224,6 +314,20 @@
*val = ret * data->vref_cached / 1024;
ret = 0;
break;
+ case hwmon_in_min:
+ case hwmon_in_max:
+ reg = (attr == hwmon_in_min)
+ ? ADT7411_REG_IN_LOW(channel)
+ : ADT7411_REG_IN_HIGH(channel);
+ ret = i2c_smbus_read_byte_data(client, reg);
+ if (ret < 0)
+ goto exit_unlock;
+ *val = ret * data->vref_cached / 256;
+ ret = 0;
+ break;
+ case hwmon_in_alarm:
+ ret = adt7411_read_in_alarm(dev, channel, val);
+ break;
default:
ret = -EOPNOTSUPP;
break;
@@ -242,12 +346,44 @@
return adt7411_read_in_chan(dev, attr, channel, val);
}
+
+static int adt7411_read_temp_alarm(struct device *dev, u32 attr, int channel,
+ long *val)
+{
+ struct adt7411_data *data = dev_get_drvdata(dev);
+ struct i2c_client *client = data->client;
+ int ret, bit;
+
+ ret = i2c_smbus_read_byte_data(client, ADT7411_REG_STAT_1);
+ if (ret < 0)
+ return ret;
+
+ switch (attr) {
+ case hwmon_temp_min_alarm:
+ bit = channel ? ADT7411_STAT_1_EXT_TEMP_LOW
+ : ADT7411_STAT_1_INT_TEMP_LOW;
+ break;
+ case hwmon_temp_max_alarm:
+ bit = channel ? ADT7411_STAT_1_EXT_TEMP_HIGH_AIN1
+ : ADT7411_STAT_1_INT_TEMP_HIGH;
+ break;
+ case hwmon_temp_fault:
+ bit = ADT7411_STAT_1_EXT_TEMP_FAULT;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ *val = !!(ret & bit);
+ return 0;
+}
+
static int adt7411_read_temp(struct device *dev, u32 attr, int channel,
long *val)
{
struct adt7411_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
- int ret, regl, regh;
+ int ret, reg, regl, regh;
switch (attr) {
case hwmon_temp_input:
@@ -261,6 +397,21 @@
ret = ret & 0x200 ? ret - 0x400 : ret; /* 10 bit signed */
*val = ret * 250;
return 0;
+ case hwmon_temp_min:
+ case hwmon_temp_max:
+ reg = (attr == hwmon_temp_min)
+ ? ADT7411_REG_TEMP_LOW(channel)
+ : ADT7411_REG_TEMP_HIGH(channel);
+ ret = i2c_smbus_read_byte_data(client, reg);
+ if (ret < 0)
+ return ret;
+ ret = ret & 0x80 ? ret - 0x100 : ret; /* 8 bit signed */
+ *val = ret * 1000;
+ return 0;
+ case hwmon_temp_min_alarm:
+ case hwmon_temp_max_alarm:
+ case hwmon_temp_fault:
+ return adt7411_read_temp_alarm(dev, attr, channel, val);
default:
return -EOPNOTSUPP;
}
@@ -279,26 +430,143 @@
}
}
+static int adt7411_write_in_vdd(struct device *dev, u32 attr, long val)
+{
+ struct adt7411_data *data = dev_get_drvdata(dev);
+ struct i2c_client *client = data->client;
+ int reg;
+
+ val = clamp_val(val, 0, 255 * 7000 / 256);
+ val = DIV_ROUND_CLOSEST(val * 256, 7000);
+
+ switch (attr) {
+ case hwmon_in_min:
+ reg = ADT7411_REG_VDD_LOW;
+ break;
+ case hwmon_in_max:
+ reg = ADT7411_REG_VDD_HIGH;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return i2c_smbus_write_byte_data(client, reg, val);
+}
+
+static int adt7411_write_in_chan(struct device *dev, u32 attr, int channel,
+ long val)
+{
+ struct adt7411_data *data = dev_get_drvdata(dev);
+ struct i2c_client *client = data->client;
+ int ret, reg;
+
+ mutex_lock(&data->update_lock);
+ ret = adt7411_update_vref(dev);
+ if (ret < 0)
+ goto exit_unlock;
+ val = clamp_val(val, 0, 255 * data->vref_cached / 256);
+ val = DIV_ROUND_CLOSEST(val * 256, data->vref_cached);
+
+ switch (attr) {
+ case hwmon_in_min:
+ reg = ADT7411_REG_IN_LOW(channel);
+ break;
+ case hwmon_in_max:
+ reg = ADT7411_REG_IN_HIGH(channel);
+ break;
+ default:
+ ret = -EOPNOTSUPP;
+ goto exit_unlock;
+ }
+
+ ret = i2c_smbus_write_byte_data(client, reg, val);
+ exit_unlock:
+ mutex_unlock(&data->update_lock);
+ return ret;
+}
+
+static int adt7411_write_in(struct device *dev, u32 attr, int channel,
+ long val)
+{
+ if (channel == 0)
+ return adt7411_write_in_vdd(dev, attr, val);
+ else
+ return adt7411_write_in_chan(dev, attr, channel, val);
+}
+
+static int adt7411_write_temp(struct device *dev, u32 attr, int channel,
+ long val)
+{
+ struct adt7411_data *data = dev_get_drvdata(dev);
+ struct i2c_client *client = data->client;
+ int reg;
+
+ val = clamp_val(val, -128000, 127000);
+ val = DIV_ROUND_CLOSEST(val, 1000);
+
+ switch (attr) {
+ case hwmon_temp_min:
+ reg = ADT7411_REG_TEMP_LOW(channel);
+ break;
+ case hwmon_temp_max:
+ reg = ADT7411_REG_TEMP_HIGH(channel);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return i2c_smbus_write_byte_data(client, reg, val);
+}
+
+static int adt7411_write(struct device *dev, enum hwmon_sensor_types type,
+ u32 attr, int channel, long val)
+{
+ switch (type) {
+ case hwmon_in:
+ return adt7411_write_in(dev, attr, channel, val);
+ case hwmon_temp:
+ return adt7411_write_temp(dev, attr, channel, val);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static umode_t adt7411_is_visible(const void *_data,
enum hwmon_sensor_types type,
u32 attr, int channel)
{
const struct adt7411_data *data = _data;
+ bool visible;
switch (type) {
case hwmon_in:
- if (channel > 0 && channel < 3)
- return data->use_ext_temp ? 0 : S_IRUGO;
- else
- return S_IRUGO;
+ visible = channel == 0 || channel >= 3 || !data->use_ext_temp;
+ switch (attr) {
+ case hwmon_in_input:
+ case hwmon_in_alarm:
+ return visible ? S_IRUGO : 0;
+ case hwmon_in_min:
+ case hwmon_in_max:
+ return visible ? S_IRUGO | S_IWUSR : 0;
+ }
+ break;
case hwmon_temp:
- if (channel == 1)
- return data->use_ext_temp ? S_IRUGO : 0;
- else
- return S_IRUGO;
+ visible = channel == 0 || data->use_ext_temp;
+ switch (attr) {
+ case hwmon_temp_input:
+ case hwmon_temp_min_alarm:
+ case hwmon_temp_max_alarm:
+ case hwmon_temp_fault:
+ return visible ? S_IRUGO : 0;
+ case hwmon_temp_min:
+ case hwmon_temp_max:
+ return visible ? S_IRUGO | S_IWUSR : 0;
+ }
+ break;
default:
- return 0;
+ break;
}
+ return 0;
}
static int adt7411_detect(struct i2c_client *client,
@@ -372,15 +640,15 @@
}
static const u32 adt7411_in_config[] = {
- HWMON_I_INPUT,
- HWMON_I_INPUT,
- HWMON_I_INPUT,
- HWMON_I_INPUT,
- HWMON_I_INPUT,
- HWMON_I_INPUT,
- HWMON_I_INPUT,
- HWMON_I_INPUT,
- HWMON_I_INPUT,
+ HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+ HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+ HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+ HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+ HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+ HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+ HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+ HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+ HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
0
};
@@ -390,8 +658,10 @@
};
static const u32 adt7411_temp_config[] = {
- HWMON_T_INPUT,
- HWMON_T_INPUT,
+ HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM |
+ HWMON_T_MAX | HWMON_T_MAX_ALARM,
+ HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM |
+ HWMON_T_MAX | HWMON_T_MAX_ALARM | HWMON_T_FAULT,
0
};
@@ -409,6 +679,7 @@
static const struct hwmon_ops adt7411_hwmon_ops = {
.is_visible = adt7411_is_visible,
.read = adt7411_read,
+ .write = adt7411_write,
};
static const struct hwmon_chip_info adt7411_chip_info = {
diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c
index c9a1d9c..2cd9207 100644
--- a/drivers/hwmon/adt7470.c
+++ b/drivers/hwmon/adt7470.c
@@ -403,7 +403,7 @@
return data;
}
-static ssize_t show_auto_update_interval(struct device *dev,
+static ssize_t auto_update_interval_show(struct device *dev,
struct device_attribute *devattr,
char *buf)
{
@@ -411,10 +411,9 @@
return sprintf(buf, "%d\n", data->auto_update_interval);
}
-static ssize_t set_auto_update_interval(struct device *dev,
- struct device_attribute *devattr,
- const char *buf,
- size_t count)
+static ssize_t auto_update_interval_store(struct device *dev,
+ struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct adt7470_data *data = dev_get_drvdata(dev);
long temp;
@@ -431,7 +430,7 @@
return count;
}
-static ssize_t show_num_temp_sensors(struct device *dev,
+static ssize_t num_temp_sensors_show(struct device *dev,
struct device_attribute *devattr,
char *buf)
{
@@ -439,10 +438,9 @@
return sprintf(buf, "%d\n", data->num_temp_sensors);
}
-static ssize_t set_num_temp_sensors(struct device *dev,
- struct device_attribute *devattr,
- const char *buf,
- size_t count)
+static ssize_t num_temp_sensors_store(struct device *dev,
+ struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct adt7470_data *data = dev_get_drvdata(dev);
long temp;
@@ -537,7 +535,7 @@
return sprintf(buf, "%d\n", 1000 * data->temp[attr->index]);
}
-static ssize_t show_alarm_mask(struct device *dev,
+static ssize_t alarm_mask_show(struct device *dev,
struct device_attribute *devattr,
char *buf)
{
@@ -546,10 +544,9 @@
return sprintf(buf, "%x\n", data->alarms_mask);
}
-static ssize_t set_alarm_mask(struct device *dev,
- struct device_attribute *devattr,
- const char *buf,
- size_t count)
+static ssize_t alarm_mask_store(struct device *dev,
+ struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct adt7470_data *data = dev_get_drvdata(dev);
long mask;
@@ -723,8 +720,8 @@
11, 15, 22, 29, 35, 44, 59, 88, 1400, 22500
};
-static ssize_t show_pwm_freq(struct device *dev,
- struct device_attribute *devattr, char *buf)
+static ssize_t pwm1_freq_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
{
struct adt7470_data *data = adt7470_update_device(dev);
unsigned char cfg_reg_1;
@@ -745,9 +742,9 @@
return scnprintf(buf, PAGE_SIZE, "%d\n", adt7470_freq_map[index]);
}
-static ssize_t set_pwm_freq(struct device *dev,
- struct device_attribute *devattr,
- const char *buf, size_t count)
+static ssize_t pwm1_freq_store(struct device *dev,
+ struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct adt7470_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -1012,12 +1009,9 @@
return sprintf(buf, "0\n");
}
-static DEVICE_ATTR(alarm_mask, S_IWUSR | S_IRUGO, show_alarm_mask,
- set_alarm_mask);
-static DEVICE_ATTR(num_temp_sensors, S_IWUSR | S_IRUGO, show_num_temp_sensors,
- set_num_temp_sensors);
-static DEVICE_ATTR(auto_update_interval, S_IWUSR | S_IRUGO,
- show_auto_update_interval, set_auto_update_interval);
+static DEVICE_ATTR_RW(alarm_mask);
+static DEVICE_ATTR_RW(num_temp_sensors);
+static DEVICE_ATTR_RW(auto_update_interval);
static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_temp_max,
set_temp_max, 0);
@@ -1133,7 +1127,7 @@
static SENSOR_DEVICE_ATTR(pwm3, S_IWUSR | S_IRUGO, show_pwm, set_pwm, 2);
static SENSOR_DEVICE_ATTR(pwm4, S_IWUSR | S_IRUGO, show_pwm, set_pwm, 3);
-static DEVICE_ATTR(pwm1_freq, S_IWUSR | S_IRUGO, show_pwm_freq, set_pwm_freq);
+static DEVICE_ATTR_RW(pwm1_freq);
static SENSOR_DEVICE_ATTR(pwm1_auto_point1_pwm, S_IWUSR | S_IRUGO,
show_pwm_min, set_pwm_min, 0);
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index 3cefd1a..c646670 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -856,16 +856,17 @@
return count;
}
-static ssize_t show_pwm_at_crit(struct device *dev,
- struct device_attribute *devattr, char *buf)
+static ssize_t pwm_use_point2_pwm_at_crit_show(struct device *dev,
+ struct device_attribute *devattr,
+ char *buf)
{
struct adt7475_data *data = adt7475_update_device(dev);
return sprintf(buf, "%d\n", !!(data->config4 & CONFIG4_MAXDUTY));
}
-static ssize_t set_pwm_at_crit(struct device *dev,
- struct device_attribute *devattr,
- const char *buf, size_t count)
+static ssize_t pwm_use_point2_pwm_at_crit_store(struct device *dev,
+ struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct i2c_client *client = to_i2c_client(dev);
struct adt7475_data *data = i2c_get_clientdata(client);
@@ -888,15 +889,15 @@
return count;
}
-static ssize_t show_vrm(struct device *dev, struct device_attribute *devattr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *devattr,
char *buf)
{
struct adt7475_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", (int)data->vrm);
}
-static ssize_t set_vrm(struct device *dev, struct device_attribute *devattr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct adt7475_data *data = dev_get_drvdata(dev);
long val;
@@ -910,8 +911,8 @@
return count;
}
-static ssize_t show_vid(struct device *dev, struct device_attribute *devattr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
{
struct adt7475_data *data = adt7475_update_device(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
@@ -1057,11 +1058,10 @@
set_pwm, MAX, 2);
/* Non-standard name, might need revisiting */
-static DEVICE_ATTR(pwm_use_point2_pwm_at_crit, S_IWUSR | S_IRUGO,
- show_pwm_at_crit, set_pwm_at_crit);
+static DEVICE_ATTR_RW(pwm_use_point2_pwm_at_crit);
-static DEVICE_ATTR(vrm, S_IWUSR | S_IRUGO, show_vrm, set_vrm);
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RW(vrm);
+static DEVICE_ATTR_RO(cpu0_vid);
static struct attribute *adt7475_attrs[] = {
&sensor_dev_attr_in1_input.dev_attr.attr,
diff --git a/drivers/hwmon/adt7x10.c b/drivers/hwmon/adt7x10.c
index 98141f4..0f538f8 100644
--- a/drivers/hwmon/adt7x10.c
+++ b/drivers/hwmon/adt7x10.c
@@ -331,9 +331,8 @@
return sprintf(buf, "%d\n", !!(ret & attr->index));
}
-static ssize_t adt7x10_show_name(struct device *dev,
- struct device_attribute *da,
- char *buf)
+static ssize_t name_show(struct device *dev, struct device_attribute *da,
+ char *buf)
{
struct adt7x10_data *data = dev_get_drvdata(dev);
@@ -359,7 +358,7 @@
NULL, ADT7X10_STAT_T_HIGH);
static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, adt7x10_show_alarm,
NULL, ADT7X10_STAT_T_CRIT);
-static DEVICE_ATTR(name, S_IRUGO, adt7x10_show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct attribute *adt7x10_attributes[] = {
&sensor_dev_attr_temp1_input.dev_attr.attr,
diff --git a/drivers/hwmon/asb100.c b/drivers/hwmon/asb100.c
index 272fcc8..62e1913 100644
--- a/drivers/hwmon/asb100.c
+++ b/drivers/hwmon/asb100.c
@@ -483,25 +483,25 @@
sysfs_temp(4);
/* VID */
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct asb100_data *data = asb100_update_device(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
/* VRM */
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct asb100_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", data->vrm);
}
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct asb100_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -519,16 +519,16 @@
}
/* Alarms */
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct asb100_data *data = asb100_update_device(dev);
return sprintf(buf, "%u\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -550,15 +550,15 @@
static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 13);
/* 1 PWM */
-static ssize_t show_pwm1(struct device *dev, struct device_attribute *attr,
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct asb100_data *data = asb100_update_device(dev);
return sprintf(buf, "%d\n", ASB100_PWM_FROM_REG(data->pwm & 0x0f));
}
-static ssize_t set_pwm1(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct i2c_client *client = to_i2c_client(dev);
struct asb100_data *data = i2c_get_clientdata(client);
@@ -577,15 +577,16 @@
return count;
}
-static ssize_t show_pwm_enable1(struct device *dev,
+static ssize_t pwm1_enable_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct asb100_data *data = asb100_update_device(dev);
return sprintf(buf, "%d\n", (data->pwm & 0x80) ? 1 : 0);
}
-static ssize_t set_pwm_enable1(struct device *dev,
- struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct i2c_client *client = to_i2c_client(dev);
struct asb100_data *data = i2c_get_clientdata(client);
@@ -604,9 +605,8 @@
return count;
}
-static DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm1, set_pwm1);
-static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR,
- show_pwm_enable1, set_pwm_enable1);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RW(pwm1_enable);
static struct attribute *asb100_attributes[] = {
&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/atxp1.c b/drivers/hwmon/atxp1.c
index f2f2f2f..b7eadb5 100644
--- a/drivers/hwmon/atxp1.c
+++ b/drivers/hwmon/atxp1.c
@@ -81,8 +81,8 @@
}
/* sys file functions for cpu0_vid */
-static ssize_t atxp1_showvcore(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
int size;
struct atxp1_data *data;
@@ -95,9 +95,9 @@
return size;
}
-static ssize_t atxp1_storevcore(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t cpu0_vid_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct atxp1_data *data = atxp1_update_device(dev);
struct i2c_client *client = data->client;
@@ -154,12 +154,11 @@
* CPU core reference voltage
* unit: millivolt
*/
-static DEVICE_ATTR(cpu0_vid, S_IRUGO | S_IWUSR, atxp1_showvcore,
- atxp1_storevcore);
+static DEVICE_ATTR_RW(cpu0_vid);
/* sys file functions for GPIO1 */
-static ssize_t atxp1_showgpio1(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t gpio1_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
int size;
struct atxp1_data *data;
@@ -171,9 +170,8 @@
return size;
}
-static ssize_t atxp1_storegpio1(struct device *dev,
- struct device_attribute *attr, const char *buf,
- size_t count)
+static ssize_t gpio1_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct atxp1_data *data = atxp1_update_device(dev);
struct i2c_client *client = data->client;
@@ -201,11 +199,11 @@
* GPIO1 data register
* unit: Four bit as hex (e.g. 0x0f)
*/
-static DEVICE_ATTR(gpio1, S_IRUGO | S_IWUSR, atxp1_showgpio1, atxp1_storegpio1);
+static DEVICE_ATTR_RW(gpio1);
/* sys file functions for GPIO2 */
-static ssize_t atxp1_showgpio2(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t gpio2_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
int size;
struct atxp1_data *data;
@@ -217,9 +215,8 @@
return size;
}
-static ssize_t atxp1_storegpio2(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t gpio2_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct atxp1_data *data = atxp1_update_device(dev);
struct i2c_client *client = data->client;
@@ -246,7 +243,7 @@
* GPIO2 data register
* unit: Eight bit as hex (e.g. 0xff)
*/
-static DEVICE_ATTR(gpio2, S_IRUGO | S_IWUSR, atxp1_showgpio2, atxp1_storegpio2);
+static DEVICE_ATTR_RW(gpio2);
static struct attribute *atxp1_attrs[] = {
&dev_attr_gpio1.attr,
diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c
index 8763c4a..aa40a00 100644
--- a/drivers/hwmon/dme1737.c
+++ b/drivers/hwmon/dme1737.c
@@ -279,7 +279,8 @@
static inline int IN_TO_REG(long val, int nominal)
{
- return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255);
+ val = clamp_val(val, 0, 255 * nominal / 192);
+ return DIV_ROUND_CLOSEST(val * 192, nominal);
}
/*
@@ -295,7 +296,8 @@
static inline int TEMP_TO_REG(long val)
{
- return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127);
+ val = clamp_val(val, -128000, 127000);
+ return DIV_ROUND_CLOSEST(val, 1000);
}
/* Temperature range */
@@ -331,9 +333,10 @@
return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000;
}
-static inline int TEMP_HYST_TO_REG(long val, int ix, int reg)
+static inline int TEMP_HYST_TO_REG(int temp, long hyst, int ix, int reg)
{
- int hyst = clamp_val((val + 500) / 1000, 0, 15);
+ hyst = clamp_val(hyst, temp - 15000, temp);
+ hyst = DIV_ROUND_CLOSEST(temp - hyst, 1000);
return (ix == 1) ? (reg & 0xf0) | hyst : (reg & 0x0f) | (hyst << 4);
}
@@ -1022,7 +1025,9 @@
int ix = sensor_attr_2->index;
int fn = sensor_attr_2->nr;
long val;
+ int temp;
int err;
+ u8 reg;
err = kstrtol(buf, 10, &val);
if (err)
@@ -1035,10 +1040,9 @@
data->zone_low[ix] = dme1737_read(data,
DME1737_REG_ZONE_LOW(ix));
/* Modify the temp hyst value */
- data->zone_hyst[ix == 2] = TEMP_HYST_TO_REG(
- TEMP_FROM_REG(data->zone_low[ix], 8) -
- val, ix, dme1737_read(data,
- DME1737_REG_ZONE_HYST(ix == 2)));
+ temp = TEMP_FROM_REG(data->zone_low[ix], 8);
+ reg = dme1737_read(data, DME1737_REG_ZONE_HYST(ix == 2));
+ data->zone_hyst[ix == 2] = TEMP_HYST_TO_REG(temp, val, ix, reg);
dme1737_write(data, DME1737_REG_ZONE_HYST(ix == 2),
data->zone_hyst[ix == 2]);
break;
@@ -1055,10 +1059,10 @@
* Modify the temp range value (which is stored in the upper
* nibble of the pwm_freq register)
*/
- data->pwm_freq[ix] = TEMP_RANGE_TO_REG(val -
- TEMP_FROM_REG(data->zone_low[ix], 8),
- dme1737_read(data,
- DME1737_REG_PWM_FREQ(ix)));
+ temp = TEMP_FROM_REG(data->zone_low[ix], 8);
+ val = clamp_val(val, temp, temp + 80000);
+ reg = dme1737_read(data, DME1737_REG_PWM_FREQ(ix));
+ data->pwm_freq[ix] = TEMP_RANGE_TO_REG(val - temp, reg);
dme1737_write(data, DME1737_REG_PWM_FREQ(ix),
data->pwm_freq[ix]);
break;
@@ -1468,7 +1472,7 @@
* Miscellaneous sysfs attributes
* --------------------------------------------------------------------- */
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct i2c_client *client = to_i2c_client(dev);
@@ -1477,8 +1481,8 @@
return sprintf(buf, "%d\n", data->vrm);
}
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct dme1737_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -1495,15 +1499,15 @@
return count;
}
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct dme1737_data *data = dme1737_update_device(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
}
-static ssize_t show_name(struct device *dev, struct device_attribute *attr,
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct dme1737_data *data = dev_get_drvdata(dev);
@@ -1645,9 +1649,9 @@
/* Misc */
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL); /* for ISA devices */
+static DEVICE_ATTR_RW(vrm);
+static DEVICE_ATTR_RO(cpu0_vid);
+static DEVICE_ATTR_RO(name); /* for ISA devices */
/*
* This struct holds all the attributes that are always present and need to be
diff --git a/drivers/hwmon/ds1621.c b/drivers/hwmon/ds1621.c
index 8890870..5c317fc 100644
--- a/drivers/hwmon/ds1621.c
+++ b/drivers/hwmon/ds1621.c
@@ -263,7 +263,7 @@
return count;
}
-static ssize_t show_alarms(struct device *dev, struct device_attribute *da,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *da,
char *buf)
{
struct ds1621_data *data = ds1621_update_client(dev);
@@ -278,15 +278,16 @@
return sprintf(buf, "%d\n", !!(data->conf & attr->index));
}
-static ssize_t show_convrate(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t update_interval_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct ds1621_data *data = dev_get_drvdata(dev);
return scnprintf(buf, PAGE_SIZE, "%hu\n", data->update_interval);
}
-static ssize_t set_convrate(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+ struct device_attribute *da,
+ const char *buf, size_t count)
{
struct ds1621_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -315,9 +316,8 @@
return count;
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
-static DEVICE_ATTR(update_interval, S_IWUSR | S_IRUGO, show_convrate,
- set_convrate);
+static DEVICE_ATTR_RO(alarms);
+static DEVICE_ATTR_RW(update_interval);
static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL, 0);
static SENSOR_DEVICE_ATTR(temp1_min, S_IWUSR | S_IRUGO, show_temp, set_temp, 1);
diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c
index 4b870ee..1ed9a7a 100644
--- a/drivers/hwmon/emc2103.c
+++ b/drivers/hwmon/emc2103.c
@@ -284,7 +284,7 @@
}
static ssize_t
-show_fan(struct device *dev, struct device_attribute *da, char *buf)
+fan1_input_show(struct device *dev, struct device_attribute *da, char *buf)
{
struct emc2103_data *data = emc2103_update_device(dev);
int rpm = 0;
@@ -294,7 +294,7 @@
}
static ssize_t
-show_fan_div(struct device *dev, struct device_attribute *da, char *buf)
+fan1_div_show(struct device *dev, struct device_attribute *da, char *buf)
{
struct emc2103_data *data = emc2103_update_device(dev);
int fan_div = 8 / data->fan_multiplier;
@@ -307,8 +307,8 @@
* of least surprise; the user doesn't expect the fan target to change just
* because the divider changed.
*/
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t fan1_div_store(struct device *dev, struct device_attribute *da,
+ const char *buf, size_t count)
{
struct emc2103_data *data = emc2103_update_device(dev);
struct i2c_client *client = data->client;
@@ -369,7 +369,7 @@
}
static ssize_t
-show_fan_target(struct device *dev, struct device_attribute *da, char *buf)
+fan1_target_show(struct device *dev, struct device_attribute *da, char *buf)
{
struct emc2103_data *data = emc2103_update_device(dev);
int rpm = 0;
@@ -382,8 +382,9 @@
return sprintf(buf, "%d\n", rpm);
}
-static ssize_t set_fan_target(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t fan1_target_store(struct device *dev,
+ struct device_attribute *da, const char *buf,
+ size_t count)
{
struct emc2103_data *data = emc2103_update_device(dev);
struct i2c_client *client = data->client;
@@ -412,7 +413,7 @@
}
static ssize_t
-show_fan_fault(struct device *dev, struct device_attribute *da, char *buf)
+fan1_fault_show(struct device *dev, struct device_attribute *da, char *buf)
{
struct emc2103_data *data = emc2103_update_device(dev);
bool fault = ((data->fan_tach & 0x1fe0) == 0x1fe0);
@@ -420,14 +421,15 @@
}
static ssize_t
-show_pwm_enable(struct device *dev, struct device_attribute *da, char *buf)
+pwm1_enable_show(struct device *dev, struct device_attribute *da, char *buf)
{
struct emc2103_data *data = emc2103_update_device(dev);
return sprintf(buf, "%d\n", data->fan_rpm_control ? 3 : 0);
}
-static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+ struct device_attribute *da, const char *buf,
+ size_t count)
{
struct emc2103_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -512,14 +514,12 @@
static SENSOR_DEVICE_ATTR(temp4_max_alarm, S_IRUGO, show_temp_max_alarm,
NULL, 3);
-static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL);
-static DEVICE_ATTR(fan1_div, S_IRUGO | S_IWUSR, show_fan_div, set_fan_div);
-static DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, show_fan_target,
- set_fan_target);
-static DEVICE_ATTR(fan1_fault, S_IRUGO, show_fan_fault, NULL);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR_RW(fan1_div);
+static DEVICE_ATTR_RW(fan1_target);
+static DEVICE_ATTR_RO(fan1_fault);
-static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, show_pwm_enable,
- set_pwm_enable);
+static DEVICE_ATTR_RW(pwm1_enable);
/* sensors present on all models */
static struct attribute *emc2103_attributes[] = {
diff --git a/drivers/hwmon/f71805f.c b/drivers/hwmon/f71805f.c
index facd05c..73c6811 100644
--- a/drivers/hwmon/f71805f.c
+++ b/drivers/hwmon/f71805f.c
@@ -946,7 +946,7 @@
return count;
}
-static ssize_t show_alarms_in(struct device *dev, struct device_attribute
+static ssize_t alarms_in_show(struct device *dev, struct device_attribute
*devattr, char *buf)
{
struct f71805f_data *data = f71805f_update_device(dev);
@@ -954,7 +954,7 @@
return sprintf(buf, "%lu\n", data->alarms & 0x7ff);
}
-static ssize_t show_alarms_fan(struct device *dev, struct device_attribute
+static ssize_t alarms_fan_show(struct device *dev, struct device_attribute
*devattr, char *buf)
{
struct f71805f_data *data = f71805f_update_device(dev);
@@ -962,7 +962,7 @@
return sprintf(buf, "%lu\n", (data->alarms >> 16) & 0x07);
}
-static ssize_t show_alarms_temp(struct device *dev, struct device_attribute
+static ssize_t alarms_temp_show(struct device *dev, struct device_attribute
*devattr, char *buf)
{
struct f71805f_data *data = f71805f_update_device(dev);
@@ -980,7 +980,7 @@
return sprintf(buf, "%lu\n", (data->alarms >> bitnr) & 1);
}
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
*devattr, char *buf)
{
struct f71805f_data *data = dev_get_drvdata(dev);
@@ -1176,11 +1176,11 @@
static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 16);
static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 17);
static SENSOR_DEVICE_ATTR(fan3_alarm, S_IRUGO, show_alarm, NULL, 18);
-static DEVICE_ATTR(alarms_in, S_IRUGO, show_alarms_in, NULL);
-static DEVICE_ATTR(alarms_fan, S_IRUGO, show_alarms_fan, NULL);
-static DEVICE_ATTR(alarms_temp, S_IRUGO, show_alarms_temp, NULL);
+static DEVICE_ATTR_RO(alarms_in);
+static DEVICE_ATTR_RO(alarms_fan);
+static DEVICE_ATTR_RO(alarms_temp);
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct attribute *f71805f_attributes[] = {
&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c
index cb28e4b..ca54ce5 100644
--- a/drivers/hwmon/f71882fg.c
+++ b/drivers/hwmon/f71882fg.c
@@ -390,7 +390,7 @@
static ssize_t store_pwm_auto_point_temp(struct device *dev,
struct device_attribute *devattr, const char *buf, size_t count);
/* Sysfs misc */
-static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
char *buf);
static int f71882fg_probe(struct platform_device *pdev);
@@ -404,7 +404,7 @@
.remove = f71882fg_remove,
};
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
/*
* Temp attr for the f71858fg, the f71858fg is special as it has its
@@ -2212,7 +2212,7 @@
return count;
}
-static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
char *buf)
{
struct f71882fg_data *data = dev_get_drvdata(dev);
diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
index 15aa49d..9545a34 100644
--- a/drivers/hwmon/fam15h_power.c
+++ b/drivers/hwmon/fam15h_power.c
@@ -83,8 +83,8 @@
return boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model >= 0x60;
}
-static ssize_t show_power(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t power1_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
u32 val, tdp_limit, running_avg_range;
s32 running_avg_capture;
@@ -136,16 +136,16 @@
curr_pwr_watts = (curr_pwr_watts * 15625) >> (10 + running_avg_range);
return sprintf(buf, "%u\n", (unsigned int) curr_pwr_watts);
}
-static DEVICE_ATTR(power1_input, S_IRUGO, show_power, NULL);
+static DEVICE_ATTR_RO(power1_input);
-static ssize_t show_power_crit(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t power1_crit_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct fam15h_power_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%u\n", data->processor_pwr_watts);
}
-static DEVICE_ATTR(power1_crit, S_IRUGO, show_power_crit, NULL);
+static DEVICE_ATTR_RO(power1_crit);
static void do_read_registers_on_cu(void *_data)
{
@@ -212,9 +212,8 @@
return 0;
}
-static ssize_t acc_show_power(struct device *dev,
- struct device_attribute *attr,
- char *buf)
+static ssize_t power1_average_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct fam15h_power_data *data = dev_get_drvdata(dev);
u64 prev_cu_acc_power[MAX_CUS], prev_ptsc[MAX_CUS],
@@ -267,20 +266,20 @@
return sprintf(buf, "%llu\n", (unsigned long long)avg_acc);
}
-static DEVICE_ATTR(power1_average, S_IRUGO, acc_show_power, NULL);
+static DEVICE_ATTR_RO(power1_average);
-static ssize_t acc_show_power_period(struct device *dev,
- struct device_attribute *attr,
- char *buf)
+static ssize_t power1_average_interval_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
{
struct fam15h_power_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%lu\n", data->power_period);
}
-static ssize_t acc_set_power_period(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t power1_average_interval_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct fam15h_power_data *data = dev_get_drvdata(dev);
unsigned long temp;
@@ -301,8 +300,7 @@
return count;
}
-static DEVICE_ATTR(power1_average_interval, S_IRUGO | S_IWUSR,
- acc_show_power_period, acc_set_power_period);
+static DEVICE_ATTR_RW(power1_average_interval);
static int fam15h_power_init_attrs(struct pci_dev *pdev,
struct fam15h_power_data *data)
diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c
index d58abdc..5e78229 100644
--- a/drivers/hwmon/fschmd.c
+++ b/drivers/hwmon/fschmd.c
@@ -561,7 +561,7 @@
* The FSC hwmon family has the ability to force an attached alert led to flash
* from software, we export this as an alert_led sysfs attr
*/
-static ssize_t show_alert_led(struct device *dev,
+static ssize_t alert_led_show(struct device *dev,
struct device_attribute *devattr, char *buf)
{
struct fschmd_data *data = fschmd_update_device(dev);
@@ -572,7 +572,7 @@
return sprintf(buf, "0\n");
}
-static ssize_t store_alert_led(struct device *dev,
+static ssize_t alert_led_store(struct device *dev,
struct device_attribute *devattr, const char *buf, size_t count)
{
u8 reg;
@@ -602,7 +602,7 @@
return count;
}
-static DEVICE_ATTR(alert_led, 0644, show_alert_led, store_alert_led);
+static DEVICE_ATTR_RW(alert_led);
static struct sensor_device_attribute fschmd_attr[] = {
SENSOR_ATTR(in0_input, 0444, show_in_value, NULL, 0),
diff --git a/drivers/hwmon/g760a.c b/drivers/hwmon/g760a.c
index ec6a77d..7be1371 100644
--- a/drivers/hwmon/g760a.c
+++ b/drivers/hwmon/g760a.c
@@ -107,8 +107,8 @@
return data;
}
-static ssize_t show_fan(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t fan1_input_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct g760a_data *data = g760a_update_client(dev);
unsigned int rpm = 0;
@@ -121,8 +121,8 @@
return sprintf(buf, "%d\n", rpm);
}
-static ssize_t show_fan_alarm(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t fan1_alarm_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct g760a_data *data = g760a_update_client(dev);
@@ -131,16 +131,16 @@
return sprintf(buf, "%d\n", fan_alarm);
}
-static ssize_t get_pwm(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *da,
+ char *buf)
{
struct g760a_data *data = g760a_update_client(dev);
return sprintf(buf, "%d\n", PWM_FROM_CNT(data->set_cnt));
}
-static ssize_t set_pwm(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *da,
+ const char *buf, size_t count)
{
struct g760a_data *data = g760a_update_client(dev);
struct i2c_client *client = data->client;
@@ -157,9 +157,9 @@
return count;
}
-static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, get_pwm, set_pwm);
-static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL);
-static DEVICE_ATTR(fan1_alarm, S_IRUGO, show_fan_alarm, NULL);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR_RO(fan1_alarm);
static struct attribute *g760a_attrs[] = {
&dev_attr_pwm1.attr,
diff --git a/drivers/hwmon/g762.c b/drivers/hwmon/g762.c
index 628be9c..6dca2fd 100644
--- a/drivers/hwmon/g762.c
+++ b/drivers/hwmon/g762.c
@@ -738,8 +738,8 @@
* Read function for fan1_input sysfs file. Return current fan RPM value, or
* 0 if fan is out of control.
*/
-static ssize_t get_fan_rpm(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t fan1_input_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct g762_data *data = g762_update_client(dev);
unsigned int rpm = 0;
@@ -764,8 +764,8 @@
* Read and write functions for pwm1_mode sysfs file. Get and set fan speed
* control mode i.e. PWM (1) or DC (0).
*/
-static ssize_t get_pwm_mode(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t pwm1_mode_show(struct device *dev, struct device_attribute *da,
+ char *buf)
{
struct g762_data *data = g762_update_client(dev);
@@ -776,8 +776,9 @@
!!(data->fan_cmd1 & G762_REG_FAN_CMD1_OUT_MODE));
}
-static ssize_t set_pwm_mode(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t pwm1_mode_store(struct device *dev,
+ struct device_attribute *da, const char *buf,
+ size_t count)
{
unsigned long val;
int ret;
@@ -796,8 +797,8 @@
* Read and write functions for fan1_div sysfs file. Get and set fan
* controller prescaler value
*/
-static ssize_t get_fan_div(struct device *dev,
- struct device_attribute *da, char *buf)
+static ssize_t fan1_div_show(struct device *dev, struct device_attribute *da,
+ char *buf)
{
struct g762_data *data = g762_update_client(dev);
@@ -807,9 +808,8 @@
return sprintf(buf, "%d\n", G762_CLKDIV_FROM_REG(data->fan_cmd1));
}
-static ssize_t set_fan_div(struct device *dev,
- struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t fan1_div_store(struct device *dev, struct device_attribute *da,
+ const char *buf, size_t count)
{
unsigned long val;
int ret;
@@ -828,8 +828,8 @@
* Read and write functions for fan1_pulses sysfs file. Get and set number
* of tachometer pulses per fan revolution.
*/
-static ssize_t get_fan_pulses(struct device *dev,
- struct device_attribute *da, char *buf)
+static ssize_t fan1_pulses_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct g762_data *data = g762_update_client(dev);
@@ -839,9 +839,9 @@
return sprintf(buf, "%d\n", G762_PULSE_FROM_REG(data->fan_cmd1));
}
-static ssize_t set_fan_pulses(struct device *dev,
- struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t fan1_pulses_store(struct device *dev,
+ struct device_attribute *da, const char *buf,
+ size_t count)
{
unsigned long val;
int ret;
@@ -870,8 +870,8 @@
* but we do not accept 0 as this mode is not natively supported by the chip
* and it is not emulated by g762 driver. -EINVAL is returned in this case.
*/
-static ssize_t get_pwm_enable(struct device *dev,
- struct device_attribute *da, char *buf)
+static ssize_t pwm1_enable_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct g762_data *data = g762_update_client(dev);
@@ -882,9 +882,9 @@
(!!(data->fan_cmd1 & G762_REG_FAN_CMD1_FAN_MODE)) + 1);
}
-static ssize_t set_pwm_enable(struct device *dev,
- struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+ struct device_attribute *da, const char *buf,
+ size_t count)
{
unsigned long val;
int ret;
@@ -904,8 +904,8 @@
* (which affects fan speed) in open-loop mode. 0 stops the fan and 255
* makes it run at full speed.
*/
-static ssize_t get_pwm(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *da,
+ char *buf)
{
struct g762_data *data = g762_update_client(dev);
@@ -915,8 +915,8 @@
return sprintf(buf, "%d\n", data->set_out);
}
-static ssize_t set_pwm(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *da,
+ const char *buf, size_t count)
{
unsigned long val;
int ret;
@@ -942,8 +942,8 @@
* Also note that due to rounding errors it is possible that you don't read
* back exactly the value you have set.
*/
-static ssize_t get_fan_target(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t fan1_target_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct g762_data *data = g762_update_client(dev);
unsigned int rpm;
@@ -961,8 +961,9 @@
return sprintf(buf, "%u\n", rpm);
}
-static ssize_t set_fan_target(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t fan1_target_store(struct device *dev,
+ struct device_attribute *da, const char *buf,
+ size_t count)
{
unsigned long val;
int ret;
@@ -978,7 +979,7 @@
}
/* read function for fan1_fault sysfs file. */
-static ssize_t get_fan_failure(struct device *dev, struct device_attribute *da,
+static ssize_t fan1_fault_show(struct device *dev, struct device_attribute *da,
char *buf)
{
struct g762_data *data = g762_update_client(dev);
@@ -993,8 +994,8 @@
* read function for fan1_alarm sysfs file. Note that OOC condition is
* enabled low
*/
-static ssize_t get_fan_ooc(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t fan1_alarm_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct g762_data *data = g762_update_client(dev);
@@ -1004,18 +1005,15 @@
return sprintf(buf, "%u\n", !(data->fan_sta & G762_REG_FAN_STA_OOC));
}
-static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, get_pwm, set_pwm);
-static DEVICE_ATTR(pwm1_mode, S_IWUSR | S_IRUGO, get_pwm_mode, set_pwm_mode);
-static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO,
- get_pwm_enable, set_pwm_enable);
-static DEVICE_ATTR(fan1_input, S_IRUGO, get_fan_rpm, NULL);
-static DEVICE_ATTR(fan1_alarm, S_IRUGO, get_fan_ooc, NULL);
-static DEVICE_ATTR(fan1_fault, S_IRUGO, get_fan_failure, NULL);
-static DEVICE_ATTR(fan1_target, S_IWUSR | S_IRUGO,
- get_fan_target, set_fan_target);
-static DEVICE_ATTR(fan1_div, S_IWUSR | S_IRUGO, get_fan_div, set_fan_div);
-static DEVICE_ATTR(fan1_pulses, S_IWUSR | S_IRUGO,
- get_fan_pulses, set_fan_pulses);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RW(pwm1_mode);
+static DEVICE_ATTR_RW(pwm1_enable);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR_RO(fan1_alarm);
+static DEVICE_ATTR_RO(fan1_fault);
+static DEVICE_ATTR_RW(fan1_target);
+static DEVICE_ATTR_RW(fan1_div);
+static DEVICE_ATTR_RW(fan1_pulses);
/* Driver data */
static struct attribute *g762_attrs[] = {
diff --git a/drivers/hwmon/gl518sm.c b/drivers/hwmon/gl518sm.c
index 0212c83..b267510 100644
--- a/drivers/hwmon/gl518sm.c
+++ b/drivers/hwmon/gl518sm.c
@@ -86,9 +86,8 @@
#define BOOL_FROM_REG(val) ((val) ? 0 : 1)
#define BOOL_TO_REG(val) ((val) ? 0 : 1)
-#define TEMP_TO_REG(val) clamp_val(((((val) < 0 ? \
- (val) - 500 : \
- (val) + 500) / 1000) + 119), 0, 255)
+#define TEMP_CLAMP(val) clamp_val(val, -119000, 136000)
+#define TEMP_TO_REG(val) (DIV_ROUND_CLOSEST(TEMP_CLAMP(val), 1000) + 119)
#define TEMP_FROM_REG(val) (((val) - 119) * 1000)
static inline u8 FAN_TO_REG(long rpm, int div)
@@ -101,11 +100,13 @@
}
#define FAN_FROM_REG(val, div) ((val) == 0 ? 0 : (480000 / ((val) * (div))))
-#define IN_TO_REG(val) clamp_val((((val) + 9) / 19), 0, 255)
+#define IN_CLAMP(val) clamp_val(val, 0, 255 * 19)
+#define IN_TO_REG(val) DIV_ROUND_CLOSEST(IN_CLAMP(val), 19)
#define IN_FROM_REG(val) ((val) * 19)
-#define VDD_TO_REG(val) clamp_val((((val) * 4 + 47) / 95), 0, 255)
-#define VDD_FROM_REG(val) (((val) * 95 + 2) / 4)
+#define VDD_CLAMP(val) clamp_val(val, 0, 255 * 95 / 4)
+#define VDD_TO_REG(val) DIV_ROUND_CLOSEST(VDD_CLAMP(val) * 4, 95)
+#define VDD_FROM_REG(val) DIV_ROUND_CLOSEST((val) * 95, 4)
#define DIV_FROM_REG(val) (1 << (val))
diff --git a/drivers/hwmon/gl520sm.c b/drivers/hwmon/gl520sm.c
index dee93ec..4ff32ee 100644
--- a/drivers/hwmon/gl520sm.c
+++ b/drivers/hwmon/gl520sm.c
@@ -200,19 +200,21 @@
* Sysfs stuff
*/
-static ssize_t get_cpu_vid(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct gl520_data *data = gl520_update_device(dev);
return sprintf(buf, "%u\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, get_cpu_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
-#define VDD_FROM_REG(val) (((val) * 95 + 2) / 4)
-#define VDD_TO_REG(val) clamp_val((((val) * 4 + 47) / 95), 0, 255)
+#define VDD_FROM_REG(val) DIV_ROUND_CLOSEST((val) * 95, 4)
+#define VDD_CLAMP(val) clamp_val(val, 0, 255 * 95 / 4)
+#define VDD_TO_REG(val) DIV_ROUND_CLOSEST(VDD_CLAMP(val) * 4, 95)
-#define IN_FROM_REG(val) ((val) * 19)
-#define IN_TO_REG(val) clamp_val((((val) + 9) / 19), 0, 255)
+#define IN_FROM_REG(val) ((val) * 19)
+#define IN_CLAMP(val) clamp_val(val, 0, 255 * 19)
+#define IN_TO_REG(val) DIV_ROUND_CLOSEST(IN_CLAMP(val), 19)
static ssize_t get_in_input(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -349,8 +351,13 @@
#define DIV_FROM_REG(val) (1 << (val))
#define FAN_FROM_REG(val, div) ((val) == 0 ? 0 : (480000 / ((val) << (div))))
-#define FAN_TO_REG(val, div) ((val) <= 0 ? 0 : \
- clamp_val((480000 + ((val) << ((div)-1))) / ((val) << (div)), 1, 255))
+
+#define FAN_BASE(div) (480000 >> (div))
+#define FAN_CLAMP(val, div) clamp_val(val, FAN_BASE(div) / 255, \
+ FAN_BASE(div))
+#define FAN_TO_REG(val, div) ((val) == 0 ? 0 : \
+ DIV_ROUND_CLOSEST(480000, \
+ FAN_CLAMP(val, div) << (div)))
static ssize_t get_fan_input(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -381,8 +388,8 @@
return sprintf(buf, "%d\n", DIV_FROM_REG(data->fan_div[n]));
}
-static ssize_t get_fan_off(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t fan1_off_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct gl520_data *data = gl520_update_device(dev);
return sprintf(buf, "%d\n", data->fan_off);
@@ -476,8 +483,9 @@
return count;
}
-static ssize_t set_fan_off(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t fan1_off_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct gl520_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -510,12 +518,11 @@
get_fan_div, set_fan_div, 0);
static SENSOR_DEVICE_ATTR(fan2_div, S_IRUGO | S_IWUSR,
get_fan_div, set_fan_div, 1);
-static DEVICE_ATTR(fan1_off, S_IRUGO | S_IWUSR,
- get_fan_off, set_fan_off);
+static DEVICE_ATTR_RW(fan1_off);
-#define TEMP_FROM_REG(val) (((val) - 130) * 1000)
-#define TEMP_TO_REG(val) clamp_val(((((val) < 0 ? \
- (val) - 500 : (val) + 500) / 1000) + 130), 0, 255)
+#define TEMP_FROM_REG(val) (((val) - 130) * 1000)
+#define TEMP_CLAMP(val) clamp_val(val, -130000, 125000)
+#define TEMP_TO_REG(val) (DIV_ROUND_CLOSEST(TEMP_CLAMP(val), 1000) + 130)
static ssize_t get_temp_input(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -596,29 +603,30 @@
static SENSOR_DEVICE_ATTR(temp2_max_hyst, S_IRUGO | S_IWUSR,
get_temp_max_hyst, set_temp_max_hyst, 1);
-static ssize_t get_alarms(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct gl520_data *data = gl520_update_device(dev);
return sprintf(buf, "%d\n", data->alarms);
}
-static ssize_t get_beep_enable(struct device *dev, struct device_attribute
- *attr, char *buf)
+static ssize_t beep_enable_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct gl520_data *data = gl520_update_device(dev);
return sprintf(buf, "%d\n", data->beep_enable);
}
-static ssize_t get_beep_mask(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t beep_mask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct gl520_data *data = gl520_update_device(dev);
return sprintf(buf, "%d\n", data->beep_mask);
}
-static ssize_t set_beep_enable(struct device *dev, struct device_attribute
- *attr, const char *buf, size_t count)
+static ssize_t beep_enable_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct gl520_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -641,8 +649,9 @@
return count;
}
-static ssize_t set_beep_mask(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t beep_mask_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct gl520_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -661,11 +670,9 @@
return count;
}
-static DEVICE_ATTR(alarms, S_IRUGO, get_alarms, NULL);
-static DEVICE_ATTR(beep_enable, S_IRUGO | S_IWUSR,
- get_beep_enable, set_beep_enable);
-static DEVICE_ATTR(beep_mask, S_IRUGO | S_IWUSR,
- get_beep_mask, set_beep_mask);
+static DEVICE_ATTR_RO(alarms);
+static DEVICE_ATTR_RW(beep_enable);
+static DEVICE_ATTR_RW(beep_mask);
static ssize_t get_alarm(struct device *dev, struct device_attribute *attr,
char *buf)
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 685568b..9c355b9 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -77,8 +77,8 @@
return IRQ_NONE;
}
-static ssize_t show_fan_alarm(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t fan1_alarm_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
struct gpio_fan_alarm *alarm = fan_data->alarm;
@@ -90,7 +90,7 @@
return sprintf(buf, "%d\n", value);
}
-static DEVICE_ATTR(fan1_alarm, S_IRUGO, show_fan_alarm, NULL);
+static DEVICE_ATTR_RO(fan1_alarm);
static int fan_alarm_init(struct gpio_fan_data *fan_data,
struct gpio_fan_alarm *alarm)
@@ -188,8 +188,8 @@
return fan_data->num_speed - 1;
}
-static ssize_t show_pwm(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
u8 pwm = fan_data->speed_index * 255 / (fan_data->num_speed - 1);
@@ -197,8 +197,8 @@
return sprintf(buf, "%d\n", pwm);
}
-static ssize_t set_pwm(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
unsigned long pwm;
@@ -224,16 +224,17 @@
return ret;
}
-static ssize_t show_pwm_enable(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t pwm1_enable_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", fan_data->pwm_enable);
}
-static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
unsigned long val;
@@ -257,22 +258,22 @@
return count;
}
-static ssize_t show_pwm_mode(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t pwm1_mode_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
return sprintf(buf, "0\n");
}
-static ssize_t show_rpm_min(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t fan1_min_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", fan_data->speed[0].rpm);
}
-static ssize_t show_rpm_max(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t fan1_max_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
@@ -280,8 +281,8 @@
fan_data->speed[fan_data->num_speed - 1].rpm);
}
-static ssize_t show_rpm(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t fan1_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
@@ -313,14 +314,13 @@
return ret;
}
-static DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm, set_pwm);
-static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR,
- show_pwm_enable, set_pwm_enable);
-static DEVICE_ATTR(pwm1_mode, S_IRUGO, show_pwm_mode, NULL);
-static DEVICE_ATTR(fan1_min, S_IRUGO, show_rpm_min, NULL);
-static DEVICE_ATTR(fan1_max, S_IRUGO, show_rpm_max, NULL);
-static DEVICE_ATTR(fan1_input, S_IRUGO, show_rpm, NULL);
-static DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, show_rpm, set_rpm);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RW(pwm1_enable);
+static DEVICE_ATTR_RO(pwm1_mode);
+static DEVICE_ATTR_RO(fan1_min);
+static DEVICE_ATTR_RO(fan1_max);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, fan1_input_show, set_rpm);
static umode_t gpio_fan_is_visible(struct kobject *kobj,
struct attribute *attr, int index)
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 3932f92..28375d5 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -63,11 +63,11 @@
};
static ssize_t
-show_name(struct device *dev, struct device_attribute *attr, char *buf)
+name_show(struct device *dev, struct device_attribute *attr, char *buf)
{
return sprintf(buf, "%s\n", to_hwmon_device(dev)->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct attribute *hwmon_dev_attrs[] = {
&dev_attr_name.attr,
@@ -544,9 +544,11 @@
struct device *hdev;
int i, j, err, id;
- /* Do not accept invalid characters in hwmon name attribute */
+ /* Complain about invalid characters in hwmon name attribute */
if (name && (!strlen(name) || strpbrk(name, "-* \t\n")))
- return ERR_PTR(-EINVAL);
+ dev_warn(dev,
+ "hwmon: '%s' is not a valid name attribute, please fix\n",
+ name);
id = ida_simple_get(&hwmon_ida, 0, 0, GFP_KERNEL);
if (id < 0)
@@ -606,7 +608,7 @@
if (err)
goto free_hwmon;
- if (chip && chip->ops->read &&
+ if (dev && chip && chip->ops->read &&
chip->info[0]->type == hwmon_chip &&
(chip->info[0]->config[0] & HWMON_C_REGISTER_TZ)) {
const struct hwmon_channel_info **info = chip->info;
@@ -651,6 +653,9 @@
void *drvdata,
const struct attribute_group **groups)
{
+ if (!name)
+ return ERR_PTR(-EINVAL);
+
return __hwmon_device_register(dev, name, drvdata, NULL, groups);
}
EXPORT_SYMBOL_GPL(hwmon_device_register_with_groups);
@@ -674,6 +679,9 @@
const struct hwmon_chip_info *chip,
const struct attribute_group **extra_groups)
{
+ if (!name)
+ return ERR_PTR(-EINVAL);
+
if (chip && (!chip->ops || !chip->ops->is_visible || !chip->info))
return ERR_PTR(-EINVAL);
@@ -695,7 +703,7 @@
dev_warn(dev,
"hwmon_device_register() is deprecated. Please convert the driver to use hwmon_device_register_with_info().\n");
- return hwmon_device_register_with_groups(dev, NULL, NULL, NULL);
+ return __hwmon_device_register(dev, NULL, NULL, NULL, NULL);
}
EXPORT_SYMBOL_GPL(hwmon_device_register);
diff --git a/drivers/hwmon/i5500_temp.c b/drivers/hwmon/i5500_temp.c
index 3e3ccbf..400e067 100644
--- a/drivers/hwmon/i5500_temp.c
+++ b/drivers/hwmon/i5500_temp.c
@@ -43,8 +43,8 @@
*/
/* Sensor resolution : 0.5 degree C */
-static ssize_t show_temp(struct device *dev,
- struct device_attribute *devattr, char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
{
struct pci_dev *pdev = to_pci_dev(dev->parent);
long temp;
@@ -83,7 +83,7 @@
return sprintf(buf, "%u\n", (unsigned int)ctsts & (1 << nr));
}
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
+static DEVICE_ATTR_RO(temp1_input);
static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_thresh, NULL, 0xE2);
static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IRUGO, show_thresh, NULL, 0xEC);
static SENSOR_DEVICE_ATTR(temp1_max, S_IRUGO, show_thresh, NULL, 0xEE);
diff --git a/drivers/hwmon/i5k_amb.c b/drivers/hwmon/i5k_amb.c
index 6b3d197..a5a9f45 100644
--- a/drivers/hwmon/i5k_amb.c
+++ b/drivers/hwmon/i5k_amb.c
@@ -114,14 +114,14 @@
unsigned int num_attrs;
};
-static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
char *buf)
{
return sprintf(buf, "%s\n", DRVNAME);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct platform_device *amb_pdev;
diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index ad82cb2..efb01c2 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -12,6 +12,7 @@
*
* Supports: IT8603E Super I/O chip w/LPC interface
* IT8620E Super I/O chip w/LPC interface
+ * IT8622E Super I/O chip w/LPC interface
* IT8623E Super I/O chip w/LPC interface
* IT8628E Super I/O chip w/LPC interface
* IT8705F Super I/O chip w/LPC interface
@@ -31,6 +32,7 @@
* IT8783E/F Super I/O chip w/LPC interface
* IT8786E Super I/O chip w/LPC interface
* IT8790E Super I/O chip w/LPC interface
+ * IT8792E Super I/O chip w/LPC interface
* Sis950 A clone of the IT8705F
*
* Copyright (C) 2001 Chris Gauthron
@@ -69,8 +71,8 @@
#define DRVNAME "it87"
enum chips { it87, it8712, it8716, it8718, it8720, it8721, it8728, it8732,
- it8771, it8772, it8781, it8782, it8783, it8786, it8790, it8603,
- it8620, it8628 };
+ it8771, it8772, it8781, it8782, it8783, it8786, it8790,
+ it8792, it8603, it8620, it8622, it8628 };
static unsigned short force_id;
module_param(force_id, ushort, 0);
@@ -151,6 +153,7 @@
#define IT8726F_DEVID 0x8726
#define IT8728F_DEVID 0x8728
#define IT8732F_DEVID 0x8732
+#define IT8792E_DEVID 0x8733
#define IT8771E_DEVID 0x8771
#define IT8772E_DEVID 0x8772
#define IT8781F_DEVID 0x8781
@@ -160,6 +163,7 @@
#define IT8790E_DEVID 0x8790
#define IT8603E_DEVID 0x8603
#define IT8620E_DEVID 0x8620
+#define IT8622E_DEVID 0x8622
#define IT8623E_DEVID 0x8623
#define IT8628E_DEVID 0x8628
#define IT87_ACT_REG 0x30
@@ -293,9 +297,11 @@
#define FEAT_SIX_FANS BIT(11) /* Supports six fans */
#define FEAT_10_9MV_ADC BIT(12)
#define FEAT_AVCC3 BIT(13) /* Chip supports in9/AVCC3 */
-#define FEAT_SIX_PWM BIT(14) /* Chip supports 6 pwm chn */
-#define FEAT_PWM_FREQ2 BIT(15) /* Separate pwm freq 2 */
-#define FEAT_SIX_TEMP BIT(16) /* Up to 6 temp sensors */
+#define FEAT_FIVE_PWM BIT(14) /* Chip supports 5 pwm chn */
+#define FEAT_SIX_PWM BIT(15) /* Chip supports 6 pwm chn */
+#define FEAT_PWM_FREQ2 BIT(16) /* Separate pwm freq 2 */
+#define FEAT_SIX_TEMP BIT(17) /* Up to 6 temp sensors */
+#define FEAT_VIN3_5V BIT(18) /* VIN3 connected to +5V */
static const struct it87_devices it87_devices[] = {
[it87] = {
@@ -419,6 +425,15 @@
| FEAT_PWM_FREQ2,
.peci_mask = 0x07,
},
+ [it8792] = {
+ .name = "it8792",
+ .suffix = "E",
+ .features = FEAT_NEWER_AUTOPWM | FEAT_16BIT_FANS
+ | FEAT_TEMP_OFFSET | FEAT_TEMP_OLD_PECI | FEAT_TEMP_PECI
+ | FEAT_10_9MV_ADC | FEAT_IN7_INTERNAL,
+ .peci_mask = 0x07,
+ .old_peci_mask = 0x02, /* Actually reports PCH */
+ },
[it8603] = {
.name = "it8603",
.suffix = "E",
@@ -433,7 +448,16 @@
.features = FEAT_NEWER_AUTOPWM | FEAT_12MV_ADC | FEAT_16BIT_FANS
| FEAT_TEMP_OFFSET | FEAT_TEMP_PECI | FEAT_SIX_FANS
| FEAT_IN7_INTERNAL | FEAT_SIX_PWM | FEAT_PWM_FREQ2
- | FEAT_SIX_TEMP,
+ | FEAT_SIX_TEMP | FEAT_VIN3_5V,
+ .peci_mask = 0x07,
+ },
+ [it8622] = {
+ .name = "it8622",
+ .suffix = "E",
+ .features = FEAT_NEWER_AUTOPWM | FEAT_12MV_ADC | FEAT_16BIT_FANS
+ | FEAT_TEMP_OFFSET | FEAT_TEMP_PECI | FEAT_FIVE_FANS
+ | FEAT_FIVE_PWM | FEAT_IN7_INTERNAL | FEAT_PWM_FREQ2
+ | FEAT_AVCC3 | FEAT_VIN3_5V,
.peci_mask = 0x07,
},
[it8628] = {
@@ -442,7 +466,7 @@
.features = FEAT_NEWER_AUTOPWM | FEAT_12MV_ADC | FEAT_16BIT_FANS
| FEAT_TEMP_OFFSET | FEAT_TEMP_PECI | FEAT_SIX_FANS
| FEAT_IN7_INTERNAL | FEAT_SIX_PWM | FEAT_PWM_FREQ2
- | FEAT_SIX_TEMP,
+ | FEAT_SIX_TEMP | FEAT_VIN3_5V,
.peci_mask = 0x07,
},
};
@@ -465,9 +489,12 @@
#define has_in7_internal(data) ((data)->features & FEAT_IN7_INTERNAL)
#define has_six_fans(data) ((data)->features & FEAT_SIX_FANS)
#define has_avcc3(data) ((data)->features & FEAT_AVCC3)
+#define has_five_pwm(data) ((data)->features & (FEAT_FIVE_PWM \
+ | FEAT_SIX_PWM))
#define has_six_pwm(data) ((data)->features & FEAT_SIX_PWM)
#define has_pwm_freq2(data) ((data)->features & FEAT_PWM_FREQ2)
#define has_six_temp(data) ((data)->features & FEAT_SIX_TEMP)
+#define has_vin3_5v(data) ((data)->features & FEAT_VIN3_5V)
struct it87_sio_data {
enum chips type;
@@ -1300,25 +1327,35 @@
it87_write_value(data, IT87_REG_FAN_MAIN_CTRL,
data->fan_main_ctrl);
} else {
+ u8 ctrl;
+
/* No on/off mode, set maximum pwm value */
data->pwm_duty[nr] = pwm_to_reg(data, 0xff);
it87_write_value(data, IT87_REG_PWM_DUTY[nr],
data->pwm_duty[nr]);
/* and set manual mode */
- data->pwm_ctrl[nr] = has_newer_autopwm(data) ?
- data->pwm_temp_map[nr] :
- data->pwm_duty[nr];
- it87_write_value(data, IT87_REG_PWM[nr],
- data->pwm_ctrl[nr]);
+ if (has_newer_autopwm(data)) {
+ ctrl = (data->pwm_ctrl[nr] & 0x7c) |
+ data->pwm_temp_map[nr];
+ } else {
+ ctrl = data->pwm_duty[nr];
+ }
+ data->pwm_ctrl[nr] = ctrl;
+ it87_write_value(data, IT87_REG_PWM[nr], ctrl);
}
} else {
- if (val == 1) /* Manual mode */
- data->pwm_ctrl[nr] = has_newer_autopwm(data) ?
- data->pwm_temp_map[nr] :
- data->pwm_duty[nr];
- else /* Automatic mode */
- data->pwm_ctrl[nr] = 0x80 | data->pwm_temp_map[nr];
- it87_write_value(data, IT87_REG_PWM[nr], data->pwm_ctrl[nr]);
+ u8 ctrl;
+
+ if (has_newer_autopwm(data)) {
+ ctrl = (data->pwm_ctrl[nr] & 0x7c) |
+ data->pwm_temp_map[nr];
+ if (val != 1)
+ ctrl |= 0x80;
+ } else {
+ ctrl = (val == 1 ? data->pwm_duty[nr] : 0x80);
+ }
+ data->pwm_ctrl[nr] = ctrl;
+ it87_write_value(data, IT87_REG_PWM[nr], ctrl);
if (data->type != it8603 && nr < 3) {
/* set SmartGuardian mode */
@@ -1344,6 +1381,7 @@
return -EINVAL;
mutex_lock(&data->update_lock);
+ it87_update_pwm_ctrl(data, nr);
if (has_newer_autopwm(data)) {
/*
* If we are in automatic mode, the PWM duty cycle register
@@ -1456,13 +1494,15 @@
}
mutex_lock(&data->update_lock);
+ it87_update_pwm_ctrl(data, nr);
data->pwm_temp_map[nr] = reg;
/*
* If we are in automatic mode, write the temp mapping immediately;
* otherwise, just store it for later use.
*/
if (data->pwm_ctrl[nr] & 0x80) {
- data->pwm_ctrl[nr] = 0x80 | data->pwm_temp_map[nr];
+ data->pwm_ctrl[nr] = (data->pwm_ctrl[nr] & 0xfc) |
+ data->pwm_temp_map[nr];
it87_write_value(data, IT87_REG_PWM[nr], data->pwm_ctrl[nr]);
}
mutex_unlock(&data->update_lock);
@@ -1762,14 +1802,14 @@
show_auto_pwm_slope, set_auto_pwm_slope, 5);
/* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct it87_data *data = it87_update_device(dev);
return sprintf(buf, "%u\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -1877,16 +1917,16 @@
static SENSOR_DEVICE_ATTR(temp2_beep, S_IRUGO, show_beep, NULL, 2);
static SENSOR_DEVICE_ATTR(temp3_beep, S_IRUGO, show_beep, NULL, 2);
-static ssize_t show_vrm_reg(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct it87_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%u\n", data->vrm);
}
-static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct it87_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -1898,16 +1938,16 @@
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
-static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct it87_data *data = it87_update_device(dev);
return sprintf(buf, "%ld\n", (long)vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
static ssize_t show_label(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -1916,17 +1956,21 @@
"+5V",
"5VSB",
"Vbat",
+ "AVCC",
};
static const char * const labels_it8721[] = {
"+3.3V",
"3VSB",
"Vbat",
+ "+3.3V",
};
struct it87_data *data = dev_get_drvdata(dev);
int nr = to_sensor_dev_attr(attr)->index;
const char *label;
- if (has_12mv_adc(data) || has_10_9mv_adc(data))
+ if (has_vin3_5v(data) && nr == 0)
+ label = labels[0];
+ else if (has_12mv_adc(data) || has_10_9mv_adc(data))
label = labels_it8721[nr];
else
label = labels[nr];
@@ -1937,7 +1981,7 @@
static SENSOR_DEVICE_ATTR(in7_label, S_IRUGO, show_label, NULL, 1);
static SENSOR_DEVICE_ATTR(in8_label, S_IRUGO, show_label, NULL, 2);
/* AVCC3 */
-static SENSOR_DEVICE_ATTR(in9_label, S_IRUGO, show_label, NULL, 0);
+static SENSOR_DEVICE_ATTR(in9_label, S_IRUGO, show_label, NULL, 3);
static umode_t it87_in_is_visible(struct kobject *kobj,
struct attribute *attr, int index)
@@ -2386,6 +2430,9 @@
case IT8732F_DEVID:
sio_data->type = it8732;
break;
+ case IT8792E_DEVID:
+ sio_data->type = it8792;
+ break;
case IT8771E_DEVID:
sio_data->type = it8771;
break;
@@ -2414,6 +2461,9 @@
case IT8620E_DEVID:
sio_data->type = it8620;
break;
+ case IT8622E_DEVID:
+ sio_data->type = it8622;
+ break;
case IT8628E_DEVID:
sio_data->type = it8628;
break;
@@ -2457,8 +2507,10 @@
else
sio_data->skip_in |= BIT(9);
- if (!has_six_pwm(config))
+ if (!has_five_pwm(config))
sio_data->skip_pwm |= BIT(3) | BIT(4) | BIT(5);
+ else if (!has_six_pwm(config))
+ sio_data->skip_pwm |= BIT(5);
if (!has_vid(config))
sio_data->skip_vid = 1;
@@ -2587,7 +2639,7 @@
/* Check for pwm4 */
reg = superio_inb(sioaddr, IT87_SIO_GPIO4_REG);
- if (!(reg & BIT(2)))
+ if (reg & BIT(2))
sio_data->skip_pwm |= BIT(3);
/* Check for pwm2, fan2 */
@@ -2602,6 +2654,50 @@
sio_data->skip_fan |= BIT(5);
}
+ /* Check if AVCC is on VIN3 */
+ reg = superio_inb(sioaddr, IT87_SIO_PINX2_REG);
+ if (reg & BIT(0))
+ sio_data->internal |= BIT(0);
+ else
+ sio_data->skip_in |= BIT(9);
+
+ sio_data->beep_pin = superio_inb(sioaddr,
+ IT87_SIO_BEEP_PIN_REG) & 0x3f;
+ } else if (sio_data->type == it8622) {
+ int reg;
+
+ superio_select(sioaddr, GPIO);
+
+ /* Check for pwm4, fan4 */
+ reg = superio_inb(sioaddr, IT87_SIO_GPIO1_REG);
+ if (reg & BIT(6))
+ sio_data->skip_fan |= BIT(3);
+ if (reg & BIT(5))
+ sio_data->skip_pwm |= BIT(3);
+
+ /* Check for pwm3, fan3, pwm5, fan5 */
+ reg = superio_inb(sioaddr, IT87_SIO_GPIO3_REG);
+ if (reg & BIT(6))
+ sio_data->skip_pwm |= BIT(2);
+ if (reg & BIT(7))
+ sio_data->skip_fan |= BIT(2);
+ if (reg & BIT(3))
+ sio_data->skip_pwm |= BIT(4);
+ if (reg & BIT(1))
+ sio_data->skip_fan |= BIT(4);
+
+ /* Check for pwm2, fan2 */
+ reg = superio_inb(sioaddr, IT87_SIO_GPIO5_REG);
+ if (reg & BIT(1))
+ sio_data->skip_pwm |= BIT(1);
+ if (reg & BIT(2))
+ sio_data->skip_fan |= BIT(1);
+
+ /* Check for AVCC */
+ reg = superio_inb(sioaddr, IT87_SIO_PINX2_REG);
+ if (!(reg & BIT(0)))
+ sio_data->skip_in |= BIT(9);
+
sio_data->beep_pin = superio_inb(sioaddr,
IT87_SIO_BEEP_PIN_REG) & 0x3f;
} else {
diff --git a/drivers/hwmon/jz4740-hwmon.c b/drivers/hwmon/jz4740-hwmon.c
index 0621ee1..2d40a2e 100644
--- a/drivers/hwmon/jz4740-hwmon.c
+++ b/drivers/hwmon/jz4740-hwmon.c
@@ -44,8 +44,8 @@
return IRQ_HANDLED;
}
-static ssize_t jz4740_hwmon_read_adcin(struct device *dev,
- struct device_attribute *dev_attr, char *buf)
+static ssize_t in0_input_show(struct device *dev,
+ struct device_attribute *dev_attr, char *buf)
{
struct jz4740_hwmon *hwmon = dev_get_drvdata(dev);
struct platform_device *pdev = hwmon->pdev;
@@ -79,7 +79,7 @@
return ret;
}
-static DEVICE_ATTR(in0_input, S_IRUGO, jz4740_hwmon_read_adcin, NULL);
+static DEVICE_ATTR_RO(in0_input);
static struct attribute *jz4740_attrs[] = {
&dev_attr_in0_input.attr,
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 9cdfde6..ce3b91f 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -72,8 +72,8 @@
mutex_unlock(&nb_smu_ind_mutex);
}
-static ssize_t show_temp(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
u32 regval;
struct pci_dev *pdev = dev_get_drvdata(dev);
@@ -88,8 +88,8 @@
return sprintf(buf, "%u\n", (regval >> 21) * 125);
}
-static ssize_t show_temp_max(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t temp1_max_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
return sprintf(buf, "%d\n", 70 * 1000);
}
@@ -110,8 +110,8 @@
return sprintf(buf, "%d\n", value);
}
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
-static DEVICE_ATTR(temp1_max, S_IRUGO, show_temp_max, NULL);
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RO(temp1_max);
static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit, NULL, 0);
static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, show_temp_crit, NULL, 1);
diff --git a/drivers/hwmon/k8temp.c b/drivers/hwmon/k8temp.c
index 734d55d..5a632bc 100644
--- a/drivers/hwmon/k8temp.c
+++ b/drivers/hwmon/k8temp.c
@@ -100,7 +100,7 @@
* Sysfs stuff
*/
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
*devattr, char *buf)
{
struct k8temp_data *data = dev_get_drvdata(dev);
@@ -133,7 +133,7 @@
static SENSOR_DEVICE_ATTR_2(temp2_input, S_IRUGO, show_temp, NULL, 0, 1);
static SENSOR_DEVICE_ATTR_2(temp3_input, S_IRUGO, show_temp, NULL, 1, 0);
static SENSOR_DEVICE_ATTR_2(temp4_input, S_IRUGO, show_temp, NULL, 1, 1);
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static const struct pci_device_id k8temp_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
diff --git a/drivers/hwmon/lm63.c b/drivers/hwmon/lm63.c
index 33bfdb4..2e19486 100644
--- a/drivers/hwmon/lm63.c
+++ b/drivers/hwmon/lm63.c
@@ -417,16 +417,16 @@
return count;
}
-static ssize_t show_pwm1_enable(struct device *dev,
+static ssize_t pwm1_enable_show(struct device *dev,
struct device_attribute *dummy, char *buf)
{
struct lm63_data *data = lm63_update_device(dev);
return sprintf(buf, "%d\n", data->config_fan & 0x20 ? 1 : 2);
}
-static ssize_t set_pwm1_enable(struct device *dev,
- struct device_attribute *dummy,
- const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+ struct device_attribute *dummy,
+ const char *buf, size_t count)
{
struct lm63_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -600,7 +600,7 @@
* Hysteresis register holds a relative value, while we want to present
* an absolute to user-space
*/
-static ssize_t show_temp2_crit_hyst(struct device *dev,
+static ssize_t temp2_crit_hyst_show(struct device *dev,
struct device_attribute *dummy, char *buf)
{
struct lm63_data *data = lm63_update_device(dev);
@@ -624,9 +624,9 @@
* And now the other way around, user-space provides an absolute
* hysteresis value and we have to store a relative one
*/
-static ssize_t set_temp2_crit_hyst(struct device *dev,
- struct device_attribute *dummy,
- const char *buf, size_t count)
+static ssize_t temp2_crit_hyst_store(struct device *dev,
+ struct device_attribute *dummy,
+ const char *buf, size_t count)
{
struct lm63_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -670,7 +670,7 @@
data->update_interval = UPDATE_INTERVAL(data->max_convrate_hz, i);
}
-static ssize_t show_update_interval(struct device *dev,
+static ssize_t update_interval_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct lm63_data *data = dev_get_drvdata(dev);
@@ -678,9 +678,9 @@
return sprintf(buf, "%u\n", data->update_interval);
}
-static ssize_t set_update_interval(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct lm63_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -697,16 +697,17 @@
return count;
}
-static ssize_t show_type(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t temp2_type_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct lm63_data *data = dev_get_drvdata(dev);
return sprintf(buf, data->trutherm ? "1\n" : "2\n");
}
-static ssize_t set_type(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t temp2_type_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct lm63_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -731,7 +732,7 @@
return count;
}
-static ssize_t show_alarms(struct device *dev, struct device_attribute *dummy,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *dummy,
char *buf)
{
struct lm63_data *data = lm63_update_device(dev);
@@ -753,8 +754,7 @@
set_fan, 1);
static SENSOR_DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm1, set_pwm1, 0);
-static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO,
- show_pwm1_enable, set_pwm1_enable);
+static DEVICE_ATTR_RW(pwm1_enable);
static SENSOR_DEVICE_ATTR(pwm1_auto_point1_pwm, S_IWUSR | S_IRUGO,
show_pwm1, set_pwm1, 1);
static SENSOR_DEVICE_ATTR(pwm1_auto_point1_temp, S_IWUSR | S_IRUGO,
@@ -841,10 +841,9 @@
set_temp11, 3);
static SENSOR_DEVICE_ATTR(temp2_crit, S_IRUGO, show_remote_temp8,
set_temp8, 2);
-static DEVICE_ATTR(temp2_crit_hyst, S_IWUSR | S_IRUGO, show_temp2_crit_hyst,
- set_temp2_crit_hyst);
+static DEVICE_ATTR_RW(temp2_crit_hyst);
-static DEVICE_ATTR(temp2_type, S_IWUSR | S_IRUGO, show_type, set_type);
+static DEVICE_ATTR_RW(temp2_type);
/* Individual alarm files */
static SENSOR_DEVICE_ATTR(fan1_min_alarm, S_IRUGO, show_alarm, NULL, 0);
@@ -854,10 +853,9 @@
static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 4);
static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 6);
/* Raw alarm file for compatibility */
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
-static DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, show_update_interval,
- set_update_interval);
+static DEVICE_ATTR_RW(update_interval);
static struct attribute *lm63_attributes[] = {
&sensor_dev_attr_pwm1.dev_attr.attr,
diff --git a/drivers/hwmon/lm70.c b/drivers/hwmon/lm70.c
index 583f883..543556d 100644
--- a/drivers/hwmon/lm70.c
+++ b/drivers/hwmon/lm70.c
@@ -46,6 +46,7 @@
#define LM70_CHIP_TMP121 1 /* TI TMP121/TMP123 */
#define LM70_CHIP_LM71 2 /* NS LM71 */
#define LM70_CHIP_LM74 3 /* NS LM74 */
+#define LM70_CHIP_TMP122 4 /* TI TMP122/TMP124 */
struct lm70 {
struct spi_device *spi;
@@ -54,8 +55,8 @@
};
/* sysfs hook function */
-static ssize_t lm70_sense_temp(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct lm70 *p_lm70 = dev_get_drvdata(dev);
struct spi_device *spi = p_lm70->spi;
@@ -72,7 +73,8 @@
*/
status = spi_write_then_read(spi, NULL, 0, &rxbuf[0], 2);
if (status < 0) {
- pr_warn("spi_write_then_read failed with status %d\n", status);
+ dev_warn(dev, "spi_write_then_read failed with status %d\n",
+ status);
goto out;
}
raw = (rxbuf[0] << 8) + rxbuf[1];
@@ -91,7 +93,7 @@
* Celsius.
* So it's equivalent to multiplying by 0.25 * 1000 = 250.
*
- * LM74 and TMP121/TMP123:
+ * LM74 and TMP121/TMP122/TMP123/TMP124:
* 13 bits of 2's complement data, discard LSB 3 bits,
* resolution 0.0625 degrees celsius.
*
@@ -105,6 +107,7 @@
break;
case LM70_CHIP_TMP121:
+ case LM70_CHIP_TMP122:
case LM70_CHIP_LM74:
val = ((int)raw / 8) * 625 / 10;
break;
@@ -120,7 +123,7 @@
return status;
}
-static DEVICE_ATTR(temp1_input, S_IRUGO, lm70_sense_temp, NULL);
+static DEVICE_ATTR_RO(temp1_input);
static struct attribute *lm70_attrs[] = {
&dev_attr_temp1_input.attr,
@@ -142,6 +145,10 @@
.data = (void *) LM70_CHIP_TMP121,
},
{
+ .compatible = "ti,tmp122",
+ .data = (void *) LM70_CHIP_TMP122,
+ },
+ {
.compatible = "ti,lm71",
.data = (void *) LM70_CHIP_LM71,
},
@@ -190,6 +197,7 @@
static const struct spi_device_id lm70_ids[] = {
{ "lm70", LM70_CHIP_LM70 },
{ "tmp121", LM70_CHIP_TMP121 },
+ { "tmp122", LM70_CHIP_TMP122 },
{ "lm71", LM70_CHIP_LM71 },
{ "lm74", LM70_CHIP_LM74 },
{ },
diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c
index 539efe4..0cb7ff6 100644
--- a/drivers/hwmon/lm78.c
+++ b/drivers/hwmon/lm78.c
@@ -236,22 +236,23 @@
show_in_offset(6);
/* Temperature */
-static ssize_t show_temp(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct lm78_data *data = lm78_update_device(dev);
return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp));
}
-static ssize_t show_temp_over(struct device *dev, struct device_attribute *da,
+static ssize_t temp1_max_show(struct device *dev, struct device_attribute *da,
char *buf)
{
struct lm78_data *data = lm78_update_device(dev);
return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_over));
}
-static ssize_t set_temp_over(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t temp1_max_store(struct device *dev,
+ struct device_attribute *da, const char *buf,
+ size_t count)
{
struct lm78_data *data = dev_get_drvdata(dev);
long val;
@@ -268,15 +269,16 @@
return count;
}
-static ssize_t show_temp_hyst(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t temp1_max_hyst_show(struct device *dev,
+ struct device_attribute *da, char *buf)
{
struct lm78_data *data = lm78_update_device(dev);
return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_hyst));
}
-static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *da,
- const char *buf, size_t count)
+static ssize_t temp1_max_hyst_store(struct device *dev,
+ struct device_attribute *da,
+ const char *buf, size_t count)
{
struct lm78_data *data = dev_get_drvdata(dev);
long val;
@@ -293,11 +295,9 @@
return count;
}
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
-static DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR,
- show_temp_over, set_temp_over);
-static DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR,
- show_temp_hyst, set_temp_hyst);
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RW(temp1_max);
+static DEVICE_ATTR_RW(temp1_max_hyst);
/* 3 Fans */
static ssize_t show_fan(struct device *dev, struct device_attribute *da,
@@ -431,22 +431,22 @@
static SENSOR_DEVICE_ATTR(fan3_div, S_IRUGO, show_fan_div, NULL, 2);
/* VID */
-static ssize_t show_vid(struct device *dev, struct device_attribute *da,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev, struct device_attribute *da,
+ char *buf)
{
struct lm78_data *data = lm78_update_device(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, 82));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
/* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *da,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *da,
char *buf)
{
struct lm78_data *data = lm78_update_device(dev);
return sprintf(buf, "%u\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev, struct device_attribute *da,
char *buf)
diff --git a/drivers/hwmon/lm80.c b/drivers/hwmon/lm80.c
index 4bcd9b8..08e3945 100644
--- a/drivers/hwmon/lm80.c
+++ b/drivers/hwmon/lm80.c
@@ -432,7 +432,7 @@
return count;
}
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct lm80_data *data = lm80_update_device(dev);
@@ -505,7 +505,7 @@
set_temp, t_os_max);
static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IWUSR | S_IRUGO, show_temp,
set_temp, t_os_hyst);
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
diff --git a/drivers/hwmon/lm83.c b/drivers/hwmon/lm83.c
index 9e4d0e1..cbfd0bb 100644
--- a/drivers/hwmon/lm83.c
+++ b/drivers/hwmon/lm83.c
@@ -188,7 +188,7 @@
return count;
}
-static ssize_t show_alarms(struct device *dev, struct device_attribute *dummy,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *dummy,
char *buf)
{
struct lm83_data *data = lm83_update_device(dev);
@@ -236,7 +236,7 @@
static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 13);
static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 15);
/* Raw alarm file for compatibility */
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static struct attribute *lm83_attributes[] = {
&sensor_dev_attr_temp1_input.dev_attr.attr,
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index 29c8136..691469f 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -604,8 +604,8 @@
/* vid, vrm, alarms */
-static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct lm85_data *data = lm85_update_device(dev);
int vid;
@@ -621,17 +621,17 @@
return sprintf(buf, "%d\n", vid);
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
-static ssize_t show_vrm_reg(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct lm85_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%ld\n", (long) data->vrm);
}
-static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct lm85_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -648,16 +648,16 @@
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
-static ssize_t show_alarms_reg(struct device *dev, struct device_attribute
- *attr, char *buf)
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct lm85_data *data = lm85_update_device(dev);
return sprintf(buf, "%u\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
char *buf)
diff --git a/drivers/hwmon/lm87.c b/drivers/hwmon/lm87.c
index 13cca36..e06faf9 100644
--- a/drivers/hwmon/lm87.c
+++ b/drivers/hwmon/lm87.c
@@ -445,23 +445,23 @@
set_temp(2);
set_temp(3);
-static ssize_t show_temp_crit_int(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t temp1_crit_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct lm87_data *data = lm87_update_device(dev);
return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_crit_int));
}
-static ssize_t show_temp_crit_ext(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t temp2_crit_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct lm87_data *data = lm87_update_device(dev);
return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_crit_ext));
}
-static DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit_int, NULL);
-static DEVICE_ATTR(temp2_crit, S_IRUGO, show_temp_crit_ext, NULL);
-static DEVICE_ATTR(temp3_crit, S_IRUGO, show_temp_crit_ext, NULL);
+static DEVICE_ATTR_RO(temp1_crit);
+static DEVICE_ATTR_RO(temp2_crit);
+static DEVICE_ATTR(temp3_crit, S_IRUGO, temp2_crit_show, NULL);
static ssize_t show_fan_input(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -586,30 +586,30 @@
set_fan(1);
set_fan(2);
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct lm87_data *data = lm87_update_device(dev);
return sprintf(buf, "%d\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct lm87_data *data = lm87_update_device(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct lm87_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", data->vrm);
}
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct lm87_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -625,16 +625,17 @@
data->vrm = val;
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
-static ssize_t show_aout(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t aout_output_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct lm87_data *data = lm87_update_device(dev);
return sprintf(buf, "%d\n", AOUT_FROM_REG(data->aout));
}
-static ssize_t set_aout(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t aout_output_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct i2c_client *client = dev_get_drvdata(dev);
struct lm87_data *data = i2c_get_clientdata(client);
@@ -651,7 +652,7 @@
mutex_unlock(&data->update_lock);
return count;
}
-static DEVICE_ATTR(aout_output, S_IRUGO | S_IWUSR, show_aout, set_aout);
+static DEVICE_ATTR_RW(aout_output);
static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
char *buf)
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 841f242..aff5297 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -830,7 +830,7 @@
}
/* pec used for ADM1032 only */
-static ssize_t show_pec(struct device *dev, struct device_attribute *dummy,
+static ssize_t pec_show(struct device *dev, struct device_attribute *dummy,
char *buf)
{
struct i2c_client *client = to_i2c_client(dev);
@@ -838,8 +838,8 @@
return sprintf(buf, "%d\n", !!(client->flags & I2C_CLIENT_PEC));
}
-static ssize_t set_pec(struct device *dev, struct device_attribute *dummy,
- const char *buf, size_t count)
+static ssize_t pec_store(struct device *dev, struct device_attribute *dummy,
+ const char *buf, size_t count)
{
struct i2c_client *client = to_i2c_client(dev);
long val;
@@ -863,7 +863,7 @@
return count;
}
-static DEVICE_ATTR(pec, S_IWUSR | S_IRUGO, show_pec, set_pec);
+static DEVICE_ATTR_RW(pec);
static int lm90_get_temp11(struct lm90_data *data, int index)
{
diff --git a/drivers/hwmon/lm92.c b/drivers/hwmon/lm92.c
index cfaf70b..2a91974 100644
--- a/drivers/hwmon/lm92.c
+++ b/drivers/hwmon/lm92.c
@@ -181,8 +181,8 @@
- TEMP_FROM_REG(data->temp[t_hyst]));
}
-static ssize_t show_temp_min_hyst(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t temp1_min_hyst_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct lm92_data *data = lm92_update_device(dev);
return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp[t_min])
@@ -213,7 +213,7 @@
return count;
}
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct lm92_data *data = lm92_update_device(dev);
@@ -235,11 +235,11 @@
set_temp_hyst, t_crit);
static SENSOR_DEVICE_ATTR(temp1_min, S_IWUSR | S_IRUGO, show_temp, set_temp,
t_min);
-static DEVICE_ATTR(temp1_min_hyst, S_IRUGO, show_temp_min_hyst, NULL);
+static DEVICE_ATTR_RO(temp1_min_hyst);
static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_temp, set_temp,
t_max);
static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IRUGO, show_temp_hyst, NULL, t_max);
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, show_alarm, NULL, 2);
static SENSOR_DEVICE_ATTR(temp1_min_alarm, S_IRUGO, show_alarm, NULL, 0);
static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 1);
diff --git a/drivers/hwmon/lm93.c b/drivers/hwmon/lm93.c
index 90bb048..77a0a83 100644
--- a/drivers/hwmon/lm93.c
+++ b/drivers/hwmon/lm93.c
@@ -2156,7 +2156,7 @@
show_pwm_auto_spinup_time,
store_pwm_auto_spinup_time, 1);
-static ssize_t show_pwm_auto_prochot_ramp(struct device *dev,
+static ssize_t pwm_auto_prochot_ramp_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct lm93_data *data = lm93_update_device(dev);
@@ -2164,7 +2164,7 @@
LM93_RAMP_FROM_REG(data->pwm_ramp_ctl >> 4 & 0x0f));
}
-static ssize_t store_pwm_auto_prochot_ramp(struct device *dev,
+static ssize_t pwm_auto_prochot_ramp_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
@@ -2186,11 +2186,9 @@
return count;
}
-static DEVICE_ATTR(pwm_auto_prochot_ramp, S_IRUGO | S_IWUSR,
- show_pwm_auto_prochot_ramp,
- store_pwm_auto_prochot_ramp);
+static DEVICE_ATTR_RW(pwm_auto_prochot_ramp);
-static ssize_t show_pwm_auto_vrdhot_ramp(struct device *dev,
+static ssize_t pwm_auto_vrdhot_ramp_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct lm93_data *data = lm93_update_device(dev);
@@ -2198,7 +2196,7 @@
LM93_RAMP_FROM_REG(data->pwm_ramp_ctl & 0x0f));
}
-static ssize_t store_pwm_auto_vrdhot_ramp(struct device *dev,
+static ssize_t pwm_auto_vrdhot_ramp_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
@@ -2220,9 +2218,7 @@
return 0;
}
-static DEVICE_ATTR(pwm_auto_vrdhot_ramp, S_IRUGO | S_IWUSR,
- show_pwm_auto_vrdhot_ramp,
- store_pwm_auto_vrdhot_ramp);
+static DEVICE_ATTR_RW(pwm_auto_vrdhot_ramp);
static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -2378,7 +2374,7 @@
static SENSOR_DEVICE_ATTR(prochot2_interval, S_IWUSR | S_IRUGO,
show_prochot_interval, store_prochot_interval, 1);
-static ssize_t show_prochot_override_duty_cycle(struct device *dev,
+static ssize_t prochot_override_duty_cycle_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
@@ -2386,7 +2382,7 @@
return sprintf(buf, "%d\n", data->prochot_override & 0x0f);
}
-static ssize_t store_prochot_override_duty_cycle(struct device *dev,
+static ssize_t prochot_override_duty_cycle_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
@@ -2408,18 +2404,16 @@
return count;
}
-static DEVICE_ATTR(prochot_override_duty_cycle, S_IRUGO | S_IWUSR,
- show_prochot_override_duty_cycle,
- store_prochot_override_duty_cycle);
+static DEVICE_ATTR_RW(prochot_override_duty_cycle);
-static ssize_t show_prochot_short(struct device *dev,
+static ssize_t prochot_short_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct lm93_data *data = lm93_update_device(dev);
return sprintf(buf, "%d\n", (data->config & 0x10) ? 1 : 0);
}
-static ssize_t store_prochot_short(struct device *dev,
+static ssize_t prochot_short_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
@@ -2442,8 +2436,7 @@
return count;
}
-static DEVICE_ATTR(prochot_short, S_IRUGO | S_IWUSR,
- show_prochot_short, store_prochot_short);
+static DEVICE_ATTR_RW(prochot_short);
static ssize_t show_vrdhot(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -2457,23 +2450,23 @@
static SENSOR_DEVICE_ATTR(vrdhot1, S_IRUGO, show_vrdhot, NULL, 0);
static SENSOR_DEVICE_ATTR(vrdhot2, S_IRUGO, show_vrdhot, NULL, 1);
-static ssize_t show_gpio(struct device *dev, struct device_attribute *attr,
+static ssize_t gpio_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct lm93_data *data = lm93_update_device(dev);
return sprintf(buf, "%d\n", LM93_GPI_FROM_REG(data->gpi));
}
-static DEVICE_ATTR(gpio, S_IRUGO, show_gpio, NULL);
+static DEVICE_ATTR_RO(gpio);
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct lm93_data *data = lm93_update_device(dev);
return sprintf(buf, "%d\n", LM93_ALARMS_FROM_REG(data->block1));
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static struct attribute *lm93_attrs[] = {
&sensor_dev_attr_in1_input.dev_attr.attr,
diff --git a/drivers/hwmon/lm95234.c b/drivers/hwmon/lm95234.c
index 8796de3..c7fcc9e 100644
--- a/drivers/hwmon/lm95234.c
+++ b/drivers/hwmon/lm95234.c
@@ -450,8 +450,8 @@
return count;
}
-static ssize_t show_interval(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t update_interval_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct lm95234_data *data = dev_get_drvdata(dev);
int ret = lm95234_update_device(data);
@@ -463,8 +463,9 @@
DIV_ROUND_CLOSEST(data->interval * 1000, HZ));
}
-static ssize_t set_interval(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct lm95234_data *data = dev_get_drvdata(dev);
int ret = lm95234_update_device(data);
@@ -566,8 +567,7 @@
static SENSOR_DEVICE_ATTR(temp5_offset, S_IWUSR | S_IRUGO, show_offset,
set_offset, 3);
-static DEVICE_ATTR(update_interval, S_IWUSR | S_IRUGO, show_interval,
- set_interval);
+static DEVICE_ATTR_RW(update_interval);
static struct attribute *lm95234_common_attrs[] = {
&sensor_dev_attr_temp1_input.dev_attr.attr,
diff --git a/drivers/hwmon/ltc4151.c b/drivers/hwmon/ltc4151.c
index 8445c9f..b904cb5 100644
--- a/drivers/hwmon/ltc4151.c
+++ b/drivers/hwmon/ltc4151.c
@@ -215,6 +215,7 @@
{ .compatible = "lltc,ltc4151" },
{},
};
+MODULE_DEVICE_TABLE(of, ltc4151_match);
/* This is the driver that will be inserted */
static struct i2c_driver ltc4151_driver = {
diff --git a/drivers/hwmon/max1111.c b/drivers/hwmon/max1111.c
index 303d0c9..8ddd4d6 100644
--- a/drivers/hwmon/max1111.c
+++ b/drivers/hwmon/max1111.c
@@ -98,7 +98,7 @@
* likely to be used by hwmon applications to distinguish between
* different devices, explicitly add a name attribute here.
*/
-static ssize_t show_name(struct device *dev,
+static ssize_t name_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return sprintf(buf, "%s\n", to_spi_device(dev)->modalias);
@@ -125,7 +125,7 @@
#define MAX1111_ADC_ATTR(_id) \
SENSOR_DEVICE_ATTR(in##_id##_input, S_IRUGO, show_adc, NULL, _id)
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static MAX1111_ADC_ATTR(0);
static MAX1111_ADC_ATTR(1);
static MAX1111_ADC_ATTR(2);
diff --git a/drivers/hwmon/max1619.c b/drivers/hwmon/max1619.c
index eda9cf5..a182789 100644
--- a/drivers/hwmon/max1619.c
+++ b/drivers/hwmon/max1619.c
@@ -173,7 +173,7 @@
return count;
}
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct max1619_data *data = max1619_update_device(dev);
@@ -199,7 +199,7 @@
static SENSOR_DEVICE_ATTR(temp2_crit_hyst, S_IWUSR | S_IRUGO, show_temp,
set_temp, t_hyst2);
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static SENSOR_DEVICE_ATTR(temp2_crit_alarm, S_IRUGO, show_alarm, NULL, 1);
static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2);
static SENSOR_DEVICE_ATTR(temp2_min_alarm, S_IRUGO, show_alarm, NULL, 3);
diff --git a/drivers/hwmon/max197.c b/drivers/hwmon/max197.c
index 0762856..638567f 100644
--- a/drivers/hwmon/max197.c
+++ b/drivers/hwmon/max197.c
@@ -207,8 +207,8 @@
return ret;
}
-static ssize_t max197_show_name(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct platform_device *pdev = to_platform_device(dev);
return sprintf(buf, "%s\n", pdev->name);
@@ -231,7 +231,7 @@
&sensor_dev_attr_in##chan##_max.dev_attr.attr, \
&sensor_dev_attr_in##chan##_min.dev_attr.attr
-static DEVICE_ATTR(name, S_IRUGO, max197_show_name, NULL);
+static DEVICE_ATTR_RO(name);
MAX197_SENSOR_DEVICE_ATTR_CH(0);
MAX197_SENSOR_DEVICE_ATTR_CH(1);
diff --git a/drivers/hwmon/max6650.c b/drivers/hwmon/max6650.c
index a993b44..65be4b1 100644
--- a/drivers/hwmon/max6650.c
+++ b/drivers/hwmon/max6650.c
@@ -270,8 +270,8 @@
* controlled.
*/
-static ssize_t get_target(struct device *dev, struct device_attribute *devattr,
- char *buf)
+static ssize_t fan1_target_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
{
struct max6650_data *data = max6650_update_device(dev);
int kscale, ktach, rpm;
@@ -318,8 +318,9 @@
data->speed);
}
-static ssize_t set_target(struct device *dev, struct device_attribute *devattr,
- const char *buf, size_t count)
+static ssize_t fan1_target_store(struct device *dev,
+ struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct max6650_data *data = dev_get_drvdata(dev);
unsigned long rpm;
@@ -350,8 +351,8 @@
* back exactly the value you have set.
*/
-static ssize_t get_pwm(struct device *dev, struct device_attribute *devattr,
- char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *devattr,
+ char *buf)
{
int pwm;
struct max6650_data *data = max6650_update_device(dev);
@@ -371,8 +372,9 @@
return sprintf(buf, "%d\n", pwm);
}
-static ssize_t set_pwm(struct device *dev, struct device_attribute *devattr,
- const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev,
+ struct device_attribute *devattr, const char *buf,
+ size_t count)
{
struct max6650_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -406,8 +408,8 @@
* 2 = Closed loop, RPM for all fans regulated by fan1 tachometer
* 3 = Fan off
*/
-static ssize_t get_enable(struct device *dev, struct device_attribute *devattr,
- char *buf)
+static ssize_t pwm1_enable_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
{
struct max6650_data *data = max6650_update_device(dev);
int mode = (data->config & MAX6650_CFG_MODE_MASK) >> 4;
@@ -416,8 +418,9 @@
return sprintf(buf, "%d\n", sysfs_modes[mode]);
}
-static ssize_t set_enable(struct device *dev, struct device_attribute *devattr,
- const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+ struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct max6650_data *data = dev_get_drvdata(dev);
unsigned long mode;
@@ -458,16 +461,17 @@
* defined for that. See the data sheet for details.
*/
-static ssize_t get_div(struct device *dev, struct device_attribute *devattr,
- char *buf)
+static ssize_t fan1_div_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
{
struct max6650_data *data = max6650_update_device(dev);
return sprintf(buf, "%d\n", DIV_FROM_REG(data->count));
}
-static ssize_t set_div(struct device *dev, struct device_attribute *devattr,
- const char *buf, size_t count)
+static ssize_t fan1_div_store(struct device *dev,
+ struct device_attribute *devattr,
+ const char *buf, size_t count)
{
struct max6650_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -534,10 +538,10 @@
static SENSOR_DEVICE_ATTR(fan2_input, S_IRUGO, get_fan, NULL, 1);
static SENSOR_DEVICE_ATTR(fan3_input, S_IRUGO, get_fan, NULL, 2);
static SENSOR_DEVICE_ATTR(fan4_input, S_IRUGO, get_fan, NULL, 3);
-static DEVICE_ATTR(fan1_target, S_IWUSR | S_IRUGO, get_target, set_target);
-static DEVICE_ATTR(fan1_div, S_IWUSR | S_IRUGO, get_div, set_div);
-static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO, get_enable, set_enable);
-static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, get_pwm, set_pwm);
+static DEVICE_ATTR_RW(fan1_target);
+static DEVICE_ATTR_RW(fan1_div);
+static DEVICE_ATTR_RW(pwm1_enable);
+static DEVICE_ATTR_RW(pwm1);
static SENSOR_DEVICE_ATTR(fan1_max_alarm, S_IRUGO, get_alarm, NULL,
MAX6650_ALRM_MAX);
static SENSOR_DEVICE_ATTR(fan1_min_alarm, S_IRUGO, get_alarm, NULL,
diff --git a/drivers/hwmon/mc13783-adc.c b/drivers/hwmon/mc13783-adc.c
index 0c02f40..960a1db 100644
--- a/drivers/hwmon/mc13783-adc.c
+++ b/drivers/hwmon/mc13783-adc.c
@@ -40,8 +40,8 @@
char name[PLATFORM_NAME_SIZE];
};
-static ssize_t mc13783_adc_show_name(struct device *dev, struct device_attribute
- *devattr, char *buf)
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
+ char *buf)
{
struct mc13783_adc_priv *priv = dev_get_drvdata(dev);
@@ -111,7 +111,7 @@
return sprintf(buf, "%u\n", val);
}
-static DEVICE_ATTR(name, S_IRUGO, mc13783_adc_show_name, NULL);
+static DEVICE_ATTR_RO(name);
static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, mc13783_adc_read_bp, NULL, 2);
static SENSOR_DEVICE_ATTR(in5_input, S_IRUGO, mc13783_adc_read_gp, NULL, 5);
static SENSOR_DEVICE_ATTR(in6_input, S_IRUGO, mc13783_adc_read_gp, NULL, 6);
diff --git a/drivers/hwmon/mcp3021.c b/drivers/hwmon/mcp3021.c
index 1929734..de886f8 100644
--- a/drivers/hwmon/mcp3021.c
+++ b/drivers/hwmon/mcp3021.c
@@ -86,8 +86,8 @@
return DIV_ROUND_CLOSEST(data->vdd * val, 1 << data->output_res);
}
-static ssize_t show_in_input(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t in0_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct i2c_client *client = to_i2c_client(dev);
struct mcp3021_data *data = i2c_get_clientdata(client);
@@ -102,7 +102,7 @@
return sprintf(buf, "%d\n", in_input);
}
-static DEVICE_ATTR(in0_input, 0444, show_in_input, NULL);
+static DEVICE_ATTR_RO(in0_input);
static int mcp3021_probe(struct i2c_client *client,
const struct i2c_device_id *id)
diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c
index 559c596..8b0bc4f 100644
--- a/drivers/hwmon/nct6683.c
+++ b/drivers/hwmon/nct6683.c
@@ -979,7 +979,7 @@
};
static ssize_t
-show_global_beep(struct device *dev, struct device_attribute *attr, char *buf)
+beep_enable_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct nct6683_data *data = dev_get_drvdata(dev);
int ret;
@@ -1004,7 +1004,7 @@
}
static ssize_t
-store_global_beep(struct device *dev, struct device_attribute *attr,
+beep_enable_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct nct6683_data *data = dev_get_drvdata(dev);
@@ -1039,7 +1039,8 @@
/* Case open detection */
static ssize_t
-show_caseopen(struct device *dev, struct device_attribute *attr, char *buf)
+intrusion0_alarm_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct nct6683_data *data = dev_get_drvdata(dev);
int ret;
@@ -1064,8 +1065,8 @@
}
static ssize_t
-clear_caseopen(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+intrusion0_alarm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct nct6683_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -1102,10 +1103,8 @@
return count;
}
-static DEVICE_ATTR(intrusion0_alarm, S_IWUSR | S_IRUGO, show_caseopen,
- clear_caseopen);
-static DEVICE_ATTR(beep_enable, S_IWUSR | S_IRUGO, show_global_beep,
- store_global_beep);
+static DEVICE_ATTR_RW(intrusion0_alarm);
+static DEVICE_ATTR_RW(beep_enable);
static struct attribute *nct6683_attributes_other[] = {
&dev_attr_intrusion0_alarm.attr,
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index ce75dd4..2458b40 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -3127,14 +3127,14 @@
};
static ssize_t
-show_vid(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct nct6775_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
/* Case open detection */
diff --git a/drivers/hwmon/nsa320-hwmon.c b/drivers/hwmon/nsa320-hwmon.c
index 0517a2657..5a16109 100644
--- a/drivers/hwmon/nsa320-hwmon.c
+++ b/drivers/hwmon/nsa320-hwmon.c
@@ -122,8 +122,8 @@
return sprintf(buf, "%s\n", nsa320_input_names[channel]);
}
-static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
s32 mcu_data = nsa320_hwmon_update(dev);
@@ -133,8 +133,8 @@
return sprintf(buf, "%d\n", (mcu_data & 0xffff) * 100);
}
-static ssize_t show_fan(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t fan1_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
s32 mcu_data = nsa320_hwmon_update(dev);
@@ -145,9 +145,9 @@
}
static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, show_label, NULL, NSA320_TEMP);
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
+static DEVICE_ATTR_RO(temp1_input);
static SENSOR_DEVICE_ATTR(fan1_label, S_IRUGO, show_label, NULL, NSA320_FAN);
-static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL);
+static DEVICE_ATTR_RO(fan1_input);
static struct attribute *nsa320_attrs[] = {
&sensor_dev_attr_temp1_label.dev_attr.attr,
diff --git a/drivers/hwmon/pc87360.c b/drivers/hwmon/pc87360.c
index d50fbf9..7e36977 100644
--- a/drivers/hwmon/pc87360.c
+++ b/drivers/hwmon/pc87360.c
@@ -589,22 +589,22 @@
&in_min_alarm[X].dev_attr.attr, \
&in_max_alarm[X].dev_attr.attr
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct pc87360_data *data = pc87360_update_device(dev);
return sprintf(buf, "%u\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct pc87360_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%u\n", data->vrm);
}
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct pc87360_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -620,15 +620,15 @@
data->vrm = val;
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
-static ssize_t show_in_alarms(struct device *dev,
+static ssize_t alarms_in_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct pc87360_data *data = pc87360_update_device(dev);
return sprintf(buf, "%u\n", data->in_alarms);
}
-static DEVICE_ATTR(alarms_in, S_IRUGO, show_in_alarms, NULL);
+static DEVICE_ATTR_RO(alarms_in);
static struct attribute *pc8736x_vin_attr_array[] = {
VIN_UNIT_ATTRS(0),
@@ -1006,14 +1006,14 @@
show_temp_crit, set_temp_crit, 2),
};
-static ssize_t show_temp_alarms(struct device *dev,
+static ssize_t alarms_temp_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct pc87360_data *data = pc87360_update_device(dev);
return sprintf(buf, "%u\n", data->temp_alarms);
}
-static DEVICE_ATTR(alarms_temp, S_IRUGO, show_temp_alarms, NULL);
+static DEVICE_ATTR_RO(alarms_temp);
/*
* show_temp_min/max_alarm() reads data from the per-channel status
@@ -1106,14 +1106,14 @@
{ .attrs = pc8736x_temp_attr[2] }
};
-static ssize_t show_name(struct device *dev,
+static ssize_t name_show(struct device *dev,
struct device_attribute *devattr, char *buf)
{
struct pc87360_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%s\n", data->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
/*
* Device detection, registration and update
diff --git a/drivers/hwmon/pc87427.c b/drivers/hwmon/pc87427.c
index cb9fdd3..dc5a9d5 100644
--- a/drivers/hwmon/pc87427.c
+++ b/drivers/hwmon/pc87427.c
@@ -943,14 +943,14 @@
{ .attrs = pc87427_attributes_temp[5] },
};
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
*devattr, char *buf)
{
struct pc87427_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%s\n", data->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
/*
diff --git a/drivers/hwmon/pcf8591.c b/drivers/hwmon/pcf8591.c
index 5740888..60e25c8 100644
--- a/drivers/hwmon/pcf8591.c
+++ b/drivers/hwmon/pcf8591.c
@@ -103,16 +103,16 @@
show_in_channel(2);
show_in_channel(3);
-static ssize_t show_out0_ouput(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t out0_output_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct pcf8591_data *data = i2c_get_clientdata(to_i2c_client(dev));
return sprintf(buf, "%d\n", data->aout * 10);
}
-static ssize_t set_out0_output(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t out0_output_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
unsigned long val;
struct i2c_client *client = to_i2c_client(dev);
@@ -132,19 +132,18 @@
return count;
}
-static DEVICE_ATTR(out0_output, S_IWUSR | S_IRUGO,
- show_out0_ouput, set_out0_output);
+static DEVICE_ATTR_RW(out0_output);
-static ssize_t show_out0_enable(struct device *dev,
+static ssize_t out0_enable_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct pcf8591_data *data = i2c_get_clientdata(to_i2c_client(dev));
return sprintf(buf, "%u\n", !(!(data->control & PCF8591_CONTROL_AOEF)));
}
-static ssize_t set_out0_enable(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t out0_enable_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct i2c_client *client = to_i2c_client(dev);
struct pcf8591_data *data = i2c_get_clientdata(client);
@@ -165,8 +164,7 @@
return count;
}
-static DEVICE_ATTR(out0_enable, S_IWUSR | S_IRUGO,
- show_out0_enable, set_out0_enable);
+static DEVICE_ATTR_RW(out0_enable);
static struct attribute *pcf8591_attributes[] = {
&dev_attr_out0_enable.attr,
diff --git a/drivers/hwmon/sch5627.c b/drivers/hwmon/sch5627.c
index 19f85c0..91544f2 100644
--- a/drivers/hwmon/sch5627.c
+++ b/drivers/hwmon/sch5627.c
@@ -205,7 +205,7 @@
return 5400540 / reg;
}
-static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
char *buf)
{
return snprintf(buf, PAGE_SIZE, "%s\n", DEVNAME);
@@ -326,7 +326,7 @@
SCH5627_IN_LABELS[attr->index]);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL, 0);
static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, show_temp, NULL, 1);
static SENSOR_DEVICE_ATTR(temp3_input, S_IRUGO, show_temp, NULL, 2);
diff --git a/drivers/hwmon/sch56xx-common.c b/drivers/hwmon/sch56xx-common.c
index 68c350c..bda3d52 100644
--- a/drivers/hwmon/sch56xx-common.c
+++ b/drivers/hwmon/sch56xx-common.c
@@ -28,7 +28,6 @@
#include <linux/delay.h>
#include <linux/fs.h>
#include <linux/watchdog.h>
-#include <linux/miscdevice.h>
#include <linux/uaccess.h>
#include <linux/slab.h>
#include "sch56xx-common.h"
diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c
index a2fdbb7..e4d642b 100644
--- a/drivers/hwmon/sht15.c
+++ b/drivers/hwmon/sht15.c
@@ -34,6 +34,7 @@
#include <linux/slab.h>
#include <linux/atomic.h>
#include <linux/bitrev.h>
+#include <linux/of_gpio.h>
/* Commands */
#define SHT15_MEASURE_TEMP 0x03
@@ -769,7 +770,7 @@
return ret ? ret : sprintf(buf, "%d\n", sht15_calc_humid(data));
}
-static ssize_t show_name(struct device *dev,
+static ssize_t name_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
@@ -787,7 +788,7 @@
SHT15_STATUS_LOW_BATTERY);
static SENSOR_DEVICE_ATTR(heater_enable, S_IRUGO | S_IWUSR, sht15_show_status,
sht15_store_heater, SHT15_STATUS_HEATER);
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct attribute *sht15_attrs[] = {
&sensor_dev_attr_temp1_input.dev_attr.attr,
&sensor_dev_attr_humidity1_input.dev_attr.attr,
@@ -911,6 +912,54 @@
return NOTIFY_OK;
}
+#ifdef CONFIG_OF
+static const struct of_device_id sht15_dt_match[] = {
+ { .compatible = "sensirion,sht15" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, sht15_dt_match);
+
+/*
+ * This function returns NULL if pdev isn't a device instatiated by dt,
+ * a pointer to pdata if it could successfully get all information
+ * from dt or a negative ERR_PTR() on error.
+ */
+static struct sht15_platform_data *sht15_probe_dt(struct device *dev)
+{
+ struct device_node *np = dev->of_node;
+ struct sht15_platform_data *pdata;
+
+ /* no device tree device */
+ if (!np)
+ return NULL;
+
+ pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+ if (!pdata)
+ return ERR_PTR(-ENOMEM);
+
+ pdata->gpio_data = of_get_named_gpio(np, "data-gpios", 0);
+ if (pdata->gpio_data < 0) {
+ if (pdata->gpio_data != -EPROBE_DEFER)
+ dev_err(dev, "data-gpios not found\n");
+ return ERR_PTR(pdata->gpio_data);
+ }
+
+ pdata->gpio_sck = of_get_named_gpio(np, "clk-gpios", 0);
+ if (pdata->gpio_sck < 0) {
+ if (pdata->gpio_sck != -EPROBE_DEFER)
+ dev_err(dev, "clk-gpios not found\n");
+ return ERR_PTR(pdata->gpio_sck);
+ }
+
+ return pdata;
+}
+#else
+static inline struct sht15_platform_data *sht15_probe_dt(struct device *dev)
+{
+ return NULL;
+}
+#endif
+
static int sht15_probe(struct platform_device *pdev)
{
int ret;
@@ -928,11 +977,17 @@
data->dev = &pdev->dev;
init_waitqueue_head(&data->wait_queue);
- if (dev_get_platdata(&pdev->dev) == NULL) {
- dev_err(&pdev->dev, "no platform data supplied\n");
- return -EINVAL;
+ data->pdata = sht15_probe_dt(&pdev->dev);
+ if (IS_ERR(data->pdata))
+ return PTR_ERR(data->pdata);
+ if (data->pdata == NULL) {
+ data->pdata = dev_get_platdata(&pdev->dev);
+ if (data->pdata == NULL) {
+ dev_err(&pdev->dev, "no platform data supplied\n");
+ return -EINVAL;
+ }
}
- data->pdata = dev_get_platdata(&pdev->dev);
+
data->supply_uv = data->pdata->supply_mv * 1000;
if (data->pdata->checksum)
data->checksumming = true;
@@ -1075,6 +1130,7 @@
static struct platform_driver sht15_driver = {
.driver = {
.name = "sht15",
+ .of_match_table = of_match_ptr(sht15_dt_match),
},
.probe = sht15_probe,
.remove = sht15_remove,
diff --git a/drivers/hwmon/sht21.c b/drivers/hwmon/sht21.c
index 84cdb1c..06706d2 100644
--- a/drivers/hwmon/sht21.c
+++ b/drivers/hwmon/sht21.c
@@ -34,23 +34,29 @@
/* I2C command bytes */
#define SHT21_TRIG_T_MEASUREMENT_HM 0xe3
#define SHT21_TRIG_RH_MEASUREMENT_HM 0xe5
+#define SHT21_READ_SNB_CMD1 0xFA
+#define SHT21_READ_SNB_CMD2 0x0F
+#define SHT21_READ_SNAC_CMD1 0xFC
+#define SHT21_READ_SNAC_CMD2 0xC9
/**
* struct sht21 - SHT21 device specific data
* @hwmon_dev: device registered with hwmon
* @lock: mutex to protect measurement values
- * @valid: only 0 before first measurement is taken
* @last_update: time of last update (jiffies)
* @temperature: cached temperature measurement value
* @humidity: cached humidity measurement value
+ * @valid: only 0 before first measurement is taken
+ * @eic: cached electronic identification code text
*/
struct sht21 {
struct i2c_client *client;
struct mutex lock;
- char valid;
unsigned long last_update;
int temperature;
int humidity;
+ char valid;
+ char eic[18];
};
/**
@@ -165,15 +171,97 @@
return sprintf(buf, "%d\n", sht21->humidity);
}
+static ssize_t eic_read(struct sht21 *sht21)
+{
+ struct i2c_client *client = sht21->client;
+ u8 tx[2];
+ u8 rx[8];
+ u8 eic[8];
+ struct i2c_msg msgs[2] = {
+ {
+ .addr = client->addr,
+ .flags = 0,
+ .len = 2,
+ .buf = tx,
+ },
+ {
+ .addr = client->addr,
+ .flags = I2C_M_RD,
+ .len = 8,
+ .buf = rx,
+ },
+ };
+ int ret;
+
+ tx[0] = SHT21_READ_SNB_CMD1;
+ tx[1] = SHT21_READ_SNB_CMD2;
+ ret = i2c_transfer(client->adapter, msgs, 2);
+ if (ret < 0)
+ goto out;
+ eic[2] = rx[0];
+ eic[3] = rx[2];
+ eic[4] = rx[4];
+ eic[5] = rx[6];
+
+ tx[0] = SHT21_READ_SNAC_CMD1;
+ tx[1] = SHT21_READ_SNAC_CMD2;
+ msgs[1].len = 6;
+ ret = i2c_transfer(client->adapter, msgs, 2);
+ if (ret < 0)
+ goto out;
+ eic[0] = rx[3];
+ eic[1] = rx[4];
+ eic[6] = rx[0];
+ eic[7] = rx[1];
+
+ ret = snprintf(sht21->eic, sizeof(sht21->eic),
+ "%02x%02x%02x%02x%02x%02x%02x%02x\n",
+ eic[0], eic[1], eic[2], eic[3],
+ eic[4], eic[5], eic[6], eic[7]);
+out:
+ if (ret < 0)
+ sht21->eic[0] = 0;
+
+ return ret;
+}
+
+/**
+ * eic_show() - show Electronic Identification Code in sysfs
+ * @dev: device
+ * @attr: device attribute
+ * @buf: sysfs buffer (PAGE_SIZE) where EIC is written
+ *
+ * Will be called on read access to eic sysfs attribute.
+ * Returns number of bytes written into buffer, negative errno on error.
+ */
+static ssize_t eic_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct sht21 *sht21 = dev_get_drvdata(dev);
+ int ret;
+
+ ret = sizeof(sht21->eic) - 1;
+ mutex_lock(&sht21->lock);
+ if (!sht21->eic[0])
+ ret = eic_read(sht21);
+ if (ret > 0)
+ memcpy(buf, sht21->eic, ret);
+ mutex_unlock(&sht21->lock);
+ return ret;
+}
+
/* sysfs attributes */
static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, sht21_show_temperature,
NULL, 0);
static SENSOR_DEVICE_ATTR(humidity1_input, S_IRUGO, sht21_show_humidity,
NULL, 0);
+static DEVICE_ATTR_RO(eic);
static struct attribute *sht21_attrs[] = {
&sensor_dev_attr_temp1_input.dev_attr.attr,
&sensor_dev_attr_humidity1_input.dev_attr.attr,
+ &dev_attr_eic.attr,
NULL
};
diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c
index 45a028f..6d789aa 100644
--- a/drivers/hwmon/sis5595.c
+++ b/drivers/hwmon/sis5595.c
@@ -304,22 +304,23 @@
show_in_offset(4);
/* Temperature */
-static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct sis5595_data *data = sis5595_update_device(dev);
return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp));
}
-static ssize_t show_temp_over(struct device *dev, struct device_attribute *attr,
+static ssize_t temp1_max_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct sis5595_data *data = sis5595_update_device(dev);
return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_over));
}
-static ssize_t set_temp_over(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t temp1_max_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct sis5595_data *data = dev_get_drvdata(dev);
long val;
@@ -336,15 +337,16 @@
return count;
}
-static ssize_t show_temp_hyst(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t temp1_max_hyst_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct sis5595_data *data = sis5595_update_device(dev);
return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_hyst));
}
-static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t temp1_max_hyst_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct sis5595_data *data = dev_get_drvdata(dev);
long val;
@@ -361,11 +363,9 @@
return count;
}
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
-static DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR,
- show_temp_over, set_temp_over);
-static DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR,
- show_temp_hyst, set_temp_hyst);
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RW(temp1_max);
+static DEVICE_ATTR_RW(temp1_max_hyst);
/* 2 Fans */
static ssize_t show_fan(struct device *dev, struct device_attribute *da,
@@ -492,13 +492,13 @@
show_fan_offset(2);
/* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct sis5595_data *data = sis5595_update_device(dev);
return sprintf(buf, "%d\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev, struct device_attribute *da,
char *buf)
@@ -516,13 +516,13 @@
static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 15);
-static ssize_t show_name(struct device *dev, struct device_attribute *attr,
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct sis5595_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%s\n", data->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct attribute *sis5595_attributes[] = {
&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/smsc47m1.c b/drivers/hwmon/smsc47m1.c
index 5d32318..c7b6a42 100644
--- a/drivers/hwmon/smsc47m1.c
+++ b/drivers/hwmon/smsc47m1.c
@@ -264,8 +264,8 @@
return sprintf(buf, "%d\n", PWM_EN_FROM_REG(data->pwm[attr->index]));
}
-static ssize_t get_alarms(struct device *dev, struct device_attribute
- *devattr, char *buf)
+static ssize_t alarms_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
{
struct smsc47m1_data *data = smsc47m1_update_device(dev, 0);
return sprintf(buf, "%d\n", data->alarms);
@@ -440,16 +440,16 @@
fan_present(2);
fan_present(3);
-static DEVICE_ATTR(alarms, S_IRUGO, get_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
*devattr, char *buf)
{
struct smsc47m1_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%s\n", data->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct attribute *smsc47m1_attributes_fan1[] = {
&sensor_dev_attr_fan1_input.dev_attr.attr,
diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c
index 15650f2..6989408 100644
--- a/drivers/hwmon/smsc47m192.c
+++ b/drivers/hwmon/smsc47m192.c
@@ -400,23 +400,23 @@
show_temp_index(3)
/* VID */
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct smsc47m192_data *data = smsc47m192_update_device(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct smsc47m192_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", data->vrm);
}
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct smsc47m192_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -431,7 +431,7 @@
data->vrm = val;
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
/* Alarms */
static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/hwmon/stts751.c b/drivers/hwmon/stts751.c
new file mode 100644
index 0000000..5545068
--- /dev/null
+++ b/drivers/hwmon/stts751.c
@@ -0,0 +1,834 @@
+/*
+ * STTS751 sensor driver
+ *
+ * Copyright (C) 2016-2017 Istituto Italiano di Tecnologia - RBCS - EDL
+ * Robotics, Brain and Cognitive Sciences department
+ * Electronic Design Laboratory
+ *
+ * Written by Andrea Merello <andrea.merello@gmail.com>
+ *
+ * Based on LM95241 driver and LM90 driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/property.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/util_macros.h>
+
+#define DEVNAME "stts751"
+
+static const unsigned short normal_i2c[] = {
+ 0x48, 0x49, 0x38, 0x39, /* STTS751-0 */
+ 0x4A, 0x4B, 0x3A, 0x3B, /* STTS751-1 */
+ I2C_CLIENT_END };
+
+#define STTS751_REG_TEMP_H 0x00
+#define STTS751_REG_STATUS 0x01
+#define STTS751_STATUS_TRIPT BIT(0)
+#define STTS751_STATUS_TRIPL BIT(5)
+#define STTS751_STATUS_TRIPH BIT(6)
+#define STTS751_REG_TEMP_L 0x02
+#define STTS751_REG_CONF 0x03
+#define STTS751_CONF_RES_MASK 0x0C
+#define STTS751_CONF_RES_SHIFT 2
+#define STTS751_CONF_EVENT_DIS BIT(7)
+#define STTS751_CONF_STOP BIT(6)
+#define STTS751_REG_RATE 0x04
+#define STTS751_REG_HLIM_H 0x05
+#define STTS751_REG_HLIM_L 0x06
+#define STTS751_REG_LLIM_H 0x07
+#define STTS751_REG_LLIM_L 0x08
+#define STTS751_REG_TLIM 0x20
+#define STTS751_REG_HYST 0x21
+#define STTS751_REG_SMBUS_TO 0x22
+
+#define STTS751_REG_PROD_ID 0xFD
+#define STTS751_REG_MAN_ID 0xFE
+#define STTS751_REG_REV_ID 0xFF
+
+#define STTS751_0_PROD_ID 0x00
+#define STTS751_1_PROD_ID 0x01
+#define ST_MAN_ID 0x53
+
+/*
+ * Possible update intervals are (in mS):
+ * 16000, 8000, 4000, 2000, 1000, 500, 250, 125, 62.5, 31.25
+ * However we are not going to complicate things too much and we stick to the
+ * approx value in mS.
+ */
+static const int stts751_intervals[] = {
+ 16000, 8000, 4000, 2000, 1000, 500, 250, 125, 63, 31
+};
+
+static const struct i2c_device_id stts751_id[] = {
+ { "stts751", 0 },
+ { }
+};
+
+struct stts751_priv {
+ struct device *dev;
+ struct i2c_client *client;
+ struct mutex access_lock;
+ u8 interval;
+ int res;
+ int event_max, event_min;
+ int therm;
+ int hyst;
+ bool smbus_timeout;
+ int temp;
+ unsigned long last_update, last_alert_update;
+ u8 config;
+ bool min_alert, max_alert, therm_trip;
+ bool data_valid, alert_valid;
+ bool notify_max, notify_min;
+};
+
+/*
+ * These functions converts temperature from HW format to integer format and
+ * vice-vers. They are (mostly) taken from lm90 driver. Unit is in mC.
+ */
+static int stts751_to_deg(s16 hw_val)
+{
+ return hw_val * 125 / 32;
+}
+
+static s32 stts751_to_hw(int val)
+{
+ return DIV_ROUND_CLOSEST(val, 125) * 32;
+}
+
+static int stts751_adjust_resolution(struct stts751_priv *priv)
+{
+ u8 res;
+
+ switch (priv->interval) {
+ case 9:
+ /* 10 bits */
+ res = 0;
+ break;
+ case 8:
+ /* 11 bits */
+ res = 1;
+ break;
+ default:
+ /* 12 bits */
+ res = 3;
+ break;
+ }
+
+ if (priv->res == res)
+ return 0;
+
+ priv->config &= ~STTS751_CONF_RES_MASK;
+ priv->config |= res << STTS751_CONF_RES_SHIFT;
+ dev_dbg(&priv->client->dev, "setting res %d. config %x",
+ res, priv->config);
+ priv->res = res;
+
+ return i2c_smbus_write_byte_data(priv->client,
+ STTS751_REG_CONF, priv->config);
+}
+
+static int stts751_update_temp(struct stts751_priv *priv)
+{
+ s32 integer1, integer2, frac;
+
+ /*
+ * There is a trick here, like in the lm90 driver. We have to read two
+ * registers to get the sensor temperature, but we have to beware a
+ * conversion could occur between the readings. We could use the
+ * one-shot conversion register, but we don't want to do this (disables
+ * hardware monitoring). So the solution used here is to read the high
+ * byte once, then the low byte, then the high byte again. If the new
+ * high byte matches the old one, then we have a valid reading. Else we
+ * have to read the low byte again, and now we believe we have a correct
+ * reading.
+ */
+ integer1 = i2c_smbus_read_byte_data(priv->client, STTS751_REG_TEMP_H);
+ if (integer1 < 0) {
+ dev_dbg(&priv->client->dev,
+ "I2C read failed (temp H). ret: %x\n", integer1);
+ return integer1;
+ }
+
+ frac = i2c_smbus_read_byte_data(priv->client, STTS751_REG_TEMP_L);
+ if (frac < 0) {
+ dev_dbg(&priv->client->dev,
+ "I2C read failed (temp L). ret: %x\n", frac);
+ return frac;
+ }
+
+ integer2 = i2c_smbus_read_byte_data(priv->client, STTS751_REG_TEMP_H);
+ if (integer2 < 0) {
+ dev_dbg(&priv->client->dev,
+ "I2C 2nd read failed (temp H). ret: %x\n", integer2);
+ return integer2;
+ }
+
+ if (integer1 != integer2) {
+ frac = i2c_smbus_read_byte_data(priv->client,
+ STTS751_REG_TEMP_L);
+ if (frac < 0) {
+ dev_dbg(&priv->client->dev,
+ "I2C 2nd read failed (temp L). ret: %x\n",
+ frac);
+ return frac;
+ }
+ }
+
+ priv->temp = stts751_to_deg((integer1 << 8) | frac);
+ return 0;
+}
+
+static int stts751_set_temp_reg16(struct stts751_priv *priv, int temp,
+ u8 hreg, u8 lreg)
+{
+ s32 hwval;
+ int ret;
+
+ hwval = stts751_to_hw(temp);
+
+ ret = i2c_smbus_write_byte_data(priv->client, hreg, hwval >> 8);
+ if (ret)
+ return ret;
+
+ return i2c_smbus_write_byte_data(priv->client, lreg, hwval & 0xff);
+}
+
+static int stts751_set_temp_reg8(struct stts751_priv *priv, int temp, u8 reg)
+{
+ s32 hwval;
+
+ hwval = stts751_to_hw(temp);
+ return i2c_smbus_write_byte_data(priv->client, reg, hwval >> 8);
+}
+
+static int stts751_read_reg16(struct stts751_priv *priv, int *temp,
+ u8 hreg, u8 lreg)
+{
+ int integer, frac;
+
+ integer = i2c_smbus_read_byte_data(priv->client, hreg);
+ if (integer < 0)
+ return integer;
+
+ frac = i2c_smbus_read_byte_data(priv->client, lreg);
+ if (frac < 0)
+ return frac;
+
+ *temp = stts751_to_deg((integer << 8) | frac);
+
+ return 0;
+}
+
+static int stts751_read_reg8(struct stts751_priv *priv, int *temp, u8 reg)
+{
+ int integer;
+
+ integer = i2c_smbus_read_byte_data(priv->client, reg);
+ if (integer < 0)
+ return integer;
+
+ *temp = stts751_to_deg(integer << 8);
+
+ return 0;
+}
+
+/*
+ * Update alert flags without waiting for cache to expire. We detects alerts
+ * immediately for the sake of the alert handler; we still need to deal with
+ * caching to workaround the fact that alarm flags int the status register,
+ * despite what the datasheet claims, gets always cleared on read.
+ */
+static int stts751_update_alert(struct stts751_priv *priv)
+{
+ int ret;
+ bool conv_done;
+ int cache_time = msecs_to_jiffies(stts751_intervals[priv->interval]);
+
+ /*
+ * Add another 10% because if we run faster than the HW conversion
+ * rate we will end up in reporting incorrectly alarms.
+ */
+ cache_time += cache_time / 10;
+
+ ret = i2c_smbus_read_byte_data(priv->client, STTS751_REG_STATUS);
+ if (ret < 0)
+ return ret;
+
+ dev_dbg(&priv->client->dev, "status reg %x\n", ret);
+ conv_done = ret & (STTS751_STATUS_TRIPH | STTS751_STATUS_TRIPL);
+ /*
+ * Reset the cache if the cache time expired, or if we are sure
+ * we have valid data from a device conversion, or if we know
+ * our cache has been never written.
+ *
+ * Note that when the cache has been never written the point is
+ * to correctly initialize the timestamp, rather than clearing
+ * the cache values.
+ *
+ * Note that updating the cache timestamp when we get an alarm flag
+ * is required, otherwise we could incorrectly report alarms to be zero.
+ */
+ if (time_after(jiffies, priv->last_alert_update + cache_time) ||
+ conv_done || !priv->alert_valid) {
+ priv->max_alert = false;
+ priv->min_alert = false;
+ priv->alert_valid = true;
+ priv->last_alert_update = jiffies;
+ dev_dbg(&priv->client->dev, "invalidating alert cache\n");
+ }
+
+ priv->max_alert |= !!(ret & STTS751_STATUS_TRIPH);
+ priv->min_alert |= !!(ret & STTS751_STATUS_TRIPL);
+ priv->therm_trip = !!(ret & STTS751_STATUS_TRIPT);
+
+ dev_dbg(&priv->client->dev, "max_alert: %d, min_alert: %d, therm_trip: %d\n",
+ priv->max_alert, priv->min_alert, priv->therm_trip);
+
+ return 0;
+}
+
+static void stts751_alert(struct i2c_client *client,
+ enum i2c_alert_protocol type, unsigned int data)
+{
+ int ret;
+ struct stts751_priv *priv = i2c_get_clientdata(client);
+
+ if (type != I2C_PROTOCOL_SMBUS_ALERT)
+ return;
+
+ dev_dbg(&client->dev, "alert!");
+
+ mutex_lock(&priv->access_lock);
+ ret = stts751_update_alert(priv);
+ if (ret < 0) {
+ /* default to worst case */
+ priv->max_alert = true;
+ priv->min_alert = true;
+
+ dev_warn(priv->dev,
+ "Alert received, but can't communicate to the device. Triggering all alarms!");
+ }
+
+ if (priv->max_alert) {
+ if (priv->notify_max)
+ dev_notice(priv->dev, "got alert for HIGH temperature");
+ priv->notify_max = false;
+
+ /* unblock alert poll */
+ sysfs_notify(&priv->dev->kobj, NULL, "temp1_max_alarm");
+ }
+
+ if (priv->min_alert) {
+ if (priv->notify_min)
+ dev_notice(priv->dev, "got alert for LOW temperature");
+ priv->notify_min = false;
+
+ /* unblock alert poll */
+ sysfs_notify(&priv->dev->kobj, NULL, "temp1_min_alarm");
+ }
+
+ if (priv->min_alert || priv->max_alert)
+ kobject_uevent(&priv->dev->kobj, KOBJ_CHANGE);
+
+ mutex_unlock(&priv->access_lock);
+}
+
+static int stts751_update(struct stts751_priv *priv)
+{
+ int ret;
+ int cache_time = msecs_to_jiffies(stts751_intervals[priv->interval]);
+
+ if (time_after(jiffies, priv->last_update + cache_time) ||
+ !priv->data_valid) {
+ ret = stts751_update_temp(priv);
+ if (ret)
+ return ret;
+
+ ret = stts751_update_alert(priv);
+ if (ret)
+ return ret;
+ priv->data_valid = true;
+ priv->last_update = jiffies;
+ }
+
+ return 0;
+}
+
+static ssize_t show_max_alarm(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ int ret;
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ mutex_lock(&priv->access_lock);
+ ret = stts751_update(priv);
+ if (!ret)
+ priv->notify_max = true;
+ mutex_unlock(&priv->access_lock);
+ if (ret < 0)
+ return ret;
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->max_alert);
+}
+
+static ssize_t show_min_alarm(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ int ret;
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ mutex_lock(&priv->access_lock);
+ ret = stts751_update(priv);
+ if (!ret)
+ priv->notify_min = true;
+ mutex_unlock(&priv->access_lock);
+ if (ret < 0)
+ return ret;
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->min_alert);
+}
+
+static ssize_t show_input(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ int ret;
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ mutex_lock(&priv->access_lock);
+ ret = stts751_update(priv);
+ mutex_unlock(&priv->access_lock);
+ if (ret < 0)
+ return ret;
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->temp);
+}
+
+static ssize_t show_therm(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->therm);
+}
+
+static ssize_t set_therm(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret;
+ long temp;
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ if (kstrtol(buf, 10, &temp) < 0)
+ return -EINVAL;
+
+ /* HW works in range -64C to +127.937C */
+ temp = clamp_val(temp, -64000, 127937);
+ mutex_lock(&priv->access_lock);
+ ret = stts751_set_temp_reg8(priv, temp, STTS751_REG_TLIM);
+ if (ret)
+ goto exit;
+
+ dev_dbg(&priv->client->dev, "setting therm %ld", temp);
+
+ /*
+ * hysteresis reg is relative to therm, so the HW does not need to be
+ * adjusted, we need to update our local copy only.
+ */
+ priv->hyst = temp - (priv->therm - priv->hyst);
+ priv->therm = temp;
+
+exit:
+ mutex_unlock(&priv->access_lock);
+ if (ret)
+ return ret;
+
+ return count;
+}
+
+static ssize_t show_hyst(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->hyst);
+}
+
+static ssize_t set_hyst(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret;
+ long temp;
+
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ if (kstrtol(buf, 10, &temp) < 0)
+ return -EINVAL;
+
+ mutex_lock(&priv->access_lock);
+ /* HW works in range -64C to +127.937C */
+ temp = clamp_val(temp, -64000, priv->therm);
+ priv->hyst = temp;
+ dev_dbg(&priv->client->dev, "setting hyst %ld", temp);
+ temp = priv->therm - temp;
+ ret = stts751_set_temp_reg8(priv, temp, STTS751_REG_HYST);
+ mutex_unlock(&priv->access_lock);
+ if (ret)
+ return ret;
+
+ return count;
+}
+
+static ssize_t show_therm_trip(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int ret;
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ mutex_lock(&priv->access_lock);
+ ret = stts751_update(priv);
+ mutex_unlock(&priv->access_lock);
+ if (ret < 0)
+ return ret;
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->therm_trip);
+}
+
+static ssize_t show_max(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->event_max);
+}
+
+static ssize_t set_max(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret;
+ long temp;
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ if (kstrtol(buf, 10, &temp) < 0)
+ return -EINVAL;
+
+ mutex_lock(&priv->access_lock);
+ /* HW works in range -64C to +127.937C */
+ temp = clamp_val(temp, priv->event_min, 127937);
+ ret = stts751_set_temp_reg16(priv, temp,
+ STTS751_REG_HLIM_H, STTS751_REG_HLIM_L);
+ if (ret)
+ goto exit;
+
+ dev_dbg(&priv->client->dev, "setting event max %ld", temp);
+ priv->event_max = temp;
+ ret = count;
+exit:
+ mutex_unlock(&priv->access_lock);
+ return ret;
+}
+
+static ssize_t show_min(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->event_min);
+}
+
+static ssize_t set_min(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret;
+ long temp;
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ if (kstrtol(buf, 10, &temp) < 0)
+ return -EINVAL;
+
+ mutex_lock(&priv->access_lock);
+ /* HW works in range -64C to +127.937C */
+ temp = clamp_val(temp, -64000, priv->event_max);
+ ret = stts751_set_temp_reg16(priv, temp,
+ STTS751_REG_LLIM_H, STTS751_REG_LLIM_L);
+ if (ret)
+ goto exit;
+
+ dev_dbg(&priv->client->dev, "setting event min %ld", temp);
+ priv->event_min = temp;
+ ret = count;
+exit:
+ mutex_unlock(&priv->access_lock);
+ return ret;
+}
+
+static ssize_t show_interval(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n",
+ stts751_intervals[priv->interval]);
+}
+
+static ssize_t set_interval(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned long val;
+ int idx;
+ int ret = count;
+ struct stts751_priv *priv = dev_get_drvdata(dev);
+
+ if (kstrtoul(buf, 10, &val) < 0)
+ return -EINVAL;
+
+ idx = find_closest_descending(val, stts751_intervals,
+ ARRAY_SIZE(stts751_intervals));
+
+ dev_dbg(&priv->client->dev, "setting interval. req:%lu, idx: %d, val: %d",
+ val, idx, stts751_intervals[idx]);
+
+ mutex_lock(&priv->access_lock);
+ if (priv->interval == idx)
+ goto exit;
+
+ /*
+ * In early development stages I've become suspicious about the chip
+ * starting to misbehave if I ever set, even briefly, an invalid
+ * configuration. While I'm not sure this is really needed, be
+ * conservative and set rate/resolution in such an order that avoids
+ * passing through an invalid configuration.
+ */
+
+ /* speed up: lower the resolution, then modify convrate */
+ if (priv->interval < idx) {
+ dev_dbg(&priv->client->dev, "lower resolution, then modify convrate");
+ priv->interval = idx;
+ ret = stts751_adjust_resolution(priv);
+ if (ret)
+ goto exit;
+ }
+
+ ret = i2c_smbus_write_byte_data(priv->client, STTS751_REG_RATE, idx);
+ if (ret)
+ goto exit;
+ /* slow down: modify convrate, then raise resolution */
+ if (priv->interval != idx) {
+ dev_dbg(&priv->client->dev, "modify convrate, then raise resolution");
+ priv->interval = idx;
+ ret = stts751_adjust_resolution(priv);
+ if (ret)
+ goto exit;
+ }
+ ret = count;
+exit:
+ mutex_unlock(&priv->access_lock);
+
+ return ret;
+}
+
+static int stts751_detect(struct i2c_client *new_client,
+ struct i2c_board_info *info)
+{
+ struct i2c_adapter *adapter = new_client->adapter;
+ const char *name;
+ int tmp;
+
+ if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
+ return -ENODEV;
+
+ tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_MAN_ID);
+ if (tmp != ST_MAN_ID)
+ return -ENODEV;
+
+ /* lower temperaure registers always have bits 0-3 set to zero */
+ tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_TEMP_L);
+ if (tmp & 0xf)
+ return -ENODEV;
+
+ tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_HLIM_L);
+ if (tmp & 0xf)
+ return -ENODEV;
+
+ tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_LLIM_L);
+ if (tmp & 0xf)
+ return -ENODEV;
+
+ /* smbus timeout register always have bits 0-7 set to zero */
+ tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_SMBUS_TO);
+ if (tmp & 0x7f)
+ return -ENODEV;
+
+ tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_PROD_ID);
+
+ switch (tmp) {
+ case STTS751_0_PROD_ID:
+ name = "STTS751-0";
+ break;
+ case STTS751_1_PROD_ID:
+ name = "STTS751-1";
+ break;
+ default:
+ return -ENODEV;
+ }
+ dev_dbg(&new_client->dev, "Chip %s detected", name);
+
+ strlcpy(info->type, stts751_id[0].name, I2C_NAME_SIZE);
+ return 0;
+}
+
+static int stts751_read_chip_config(struct stts751_priv *priv)
+{
+ int ret;
+ int tmp;
+
+ ret = i2c_smbus_read_byte_data(priv->client, STTS751_REG_CONF);
+ if (ret < 0)
+ return ret;
+ priv->config = ret;
+ priv->res = (ret & STTS751_CONF_RES_MASK) >> STTS751_CONF_RES_SHIFT;
+
+ ret = i2c_smbus_read_byte_data(priv->client, STTS751_REG_RATE);
+ if (ret < 0)
+ return ret;
+ priv->interval = ret;
+
+ ret = stts751_read_reg16(priv, &priv->event_max,
+ STTS751_REG_HLIM_H, STTS751_REG_HLIM_L);
+ if (ret)
+ return ret;
+
+ ret = stts751_read_reg16(priv, &priv->event_min,
+ STTS751_REG_LLIM_H, STTS751_REG_LLIM_L);
+ if (ret)
+ return ret;
+
+ ret = stts751_read_reg8(priv, &priv->therm, STTS751_REG_TLIM);
+ if (ret)
+ return ret;
+
+ ret = stts751_read_reg8(priv, &tmp, STTS751_REG_HYST);
+ if (ret)
+ return ret;
+ priv->hyst = priv->therm - tmp;
+
+ return 0;
+}
+
+static SENSOR_DEVICE_ATTR(temp1_input, 0444, show_input, NULL, 0);
+static SENSOR_DEVICE_ATTR(temp1_min, 0644, show_min, set_min, 0);
+static SENSOR_DEVICE_ATTR(temp1_max, 0644, show_max, set_max, 0);
+static SENSOR_DEVICE_ATTR(temp1_min_alarm, 0444, show_min_alarm, NULL, 0);
+static SENSOR_DEVICE_ATTR(temp1_max_alarm, 0444, show_max_alarm, NULL, 0);
+static SENSOR_DEVICE_ATTR(temp1_crit, 0644, show_therm, set_therm, 0);
+static SENSOR_DEVICE_ATTR(temp1_crit_hyst, 0644, show_hyst, set_hyst, 0);
+static SENSOR_DEVICE_ATTR(temp1_crit_alarm, 0444, show_therm_trip, NULL, 0);
+static SENSOR_DEVICE_ATTR(update_interval, 0644,
+ show_interval, set_interval, 0);
+
+static struct attribute *stts751_attrs[] = {
+ &sensor_dev_attr_temp1_input.dev_attr.attr,
+ &sensor_dev_attr_temp1_min.dev_attr.attr,
+ &sensor_dev_attr_temp1_max.dev_attr.attr,
+ &sensor_dev_attr_temp1_min_alarm.dev_attr.attr,
+ &sensor_dev_attr_temp1_max_alarm.dev_attr.attr,
+ &sensor_dev_attr_temp1_crit.dev_attr.attr,
+ &sensor_dev_attr_temp1_crit_hyst.dev_attr.attr,
+ &sensor_dev_attr_temp1_crit_alarm.dev_attr.attr,
+ &sensor_dev_attr_update_interval.dev_attr.attr,
+ NULL
+};
+ATTRIBUTE_GROUPS(stts751);
+
+static int stts751_probe(struct i2c_client *client,
+ const struct i2c_device_id *id)
+{
+ struct stts751_priv *priv;
+ int ret;
+ bool smbus_nto;
+ int rev_id;
+
+ priv = devm_kzalloc(&client->dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ priv->client = client;
+ priv->notify_max = true;
+ priv->notify_min = true;
+ i2c_set_clientdata(client, priv);
+ mutex_init(&priv->access_lock);
+
+ if (device_property_present(&client->dev,
+ "smbus-timeout-disable")) {
+ smbus_nto = device_property_read_bool(&client->dev,
+ "smbus-timeout-disable");
+
+ ret = i2c_smbus_write_byte_data(client, STTS751_REG_SMBUS_TO,
+ smbus_nto ? 0 : 0x80);
+ if (ret)
+ return ret;
+ }
+
+ rev_id = i2c_smbus_read_byte_data(client, STTS751_REG_REV_ID);
+ if (rev_id < 0)
+ return -ENODEV;
+ if (rev_id != 0x1) {
+ dev_dbg(&client->dev, "Chip revision 0x%x is untested\n",
+ rev_id);
+ }
+
+ ret = stts751_read_chip_config(priv);
+ if (ret)
+ return ret;
+
+ priv->config &= ~(STTS751_CONF_STOP | STTS751_CONF_EVENT_DIS);
+ ret = i2c_smbus_write_byte_data(client, STTS751_REG_CONF, priv->config);
+ if (ret)
+ return ret;
+
+ priv->dev = devm_hwmon_device_register_with_groups(&client->dev,
+ client->name, priv,
+ stts751_groups);
+ return PTR_ERR_OR_ZERO(priv->dev);
+}
+
+MODULE_DEVICE_TABLE(i2c, stts751_id);
+
+static struct i2c_driver stts751_driver = {
+ .class = I2C_CLASS_HWMON,
+ .driver = {
+ .name = DEVNAME,
+ },
+ .probe = stts751_probe,
+ .id_table = stts751_id,
+ .detect = stts751_detect,
+ .alert = stts751_alert,
+ .address_list = normal_i2c,
+};
+
+module_i2c_driver(stts751_driver);
+
+MODULE_AUTHOR("Andrea Merello <andrea.merello@gmail.com>");
+MODULE_DESCRIPTION("STTS751 sensor driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c
index eeeed2c..1f2d13d 100644
--- a/drivers/hwmon/tmp401.c
+++ b/drivers/hwmon/tmp401.c
@@ -82,16 +82,6 @@
{ 0, 0x11 }, /* offset */
};
-static const u8 TMP401_TEMP_LSB[7][2] = {
- { 0x15, 0x10 }, /* temp */
- { 0x17, 0x14 }, /* low limit */
- { 0x16, 0x13 }, /* high limit */
- { 0, 0 }, /* therm (crit) limit (unused) */
- { 0x31, 0x35 }, /* lowest */
- { 0x33, 0x37 }, /* highest */
- { 0, 0x12 }, /* offset */
-};
-
static const u8 TMP432_TEMP_MSB_READ[4][3] = {
{ 0x00, 0x01, 0x23 }, /* temp */
{ 0x06, 0x08, 0x16 }, /* low limit */
@@ -106,12 +96,6 @@
{ 0x20, 0x19, 0x1A }, /* therm (crit) limit */
};
-static const u8 TMP432_TEMP_LSB[3][3] = {
- { 0x29, 0x10, 0x24 }, /* temp */
- { 0x3E, 0x14, 0x18 }, /* low limit */
- { 0x3D, 0x13, 0x17 }, /* high limit */
-};
-
/* [0] = fault, [1] = low, [2] = high, [3] = therm/crit */
static const u8 TMP432_STATUS_REG[] = {
0x1b, 0x36, 0x35, 0x37 };
@@ -213,25 +197,20 @@
for (i = 0; i < num_sensors; i++) { /* local / r1 / r2 */
for (j = 0; j < num_regs; j++) { /* temp / low / ... */
u8 regaddr;
- /*
- * High byte must be read first immediately followed
- * by the low byte
- */
+
regaddr = data->kind == tmp432 ?
TMP432_TEMP_MSB_READ[j][i] :
TMP401_TEMP_MSB_READ[j][i];
- val = i2c_smbus_read_byte_data(client, regaddr);
+ if (j == 3) { /* crit is msb only */
+ val = i2c_smbus_read_byte_data(client, regaddr);
+ } else {
+ val = i2c_smbus_read_word_swapped(client,
+ regaddr);
+ }
if (val < 0)
return val;
- data->temp[j][i] = val << 8;
- if (j == 3) /* crit is msb only */
- continue;
- regaddr = data->kind == tmp432 ? TMP432_TEMP_LSB[j][i]
- : TMP401_TEMP_LSB[j][i];
- val = i2c_smbus_read_byte_data(client, regaddr);
- if (val < 0)
- return val;
- data->temp[j][i] |= val;
+
+ data->temp[j][i] = j == 3 ? val << 8 : val;
}
}
return 0;
@@ -373,11 +352,11 @@
regaddr = data->kind == tmp432 ? TMP432_TEMP_MSB_WRITE[nr][index]
: TMP401_TEMP_MSB_WRITE[nr][index];
- i2c_smbus_write_byte_data(client, regaddr, reg >> 8);
- if (nr != 3) {
- regaddr = data->kind == tmp432 ? TMP432_TEMP_LSB[nr][index]
- : TMP401_TEMP_LSB[nr][index];
- i2c_smbus_write_byte_data(client, regaddr, reg & 0xFF);
+ if (nr == 3) { /* crit is msb only */
+ i2c_smbus_write_byte_data(client, regaddr, reg >> 8);
+ } else {
+ /* Hardware expects big endian data --> use _swapped */
+ i2c_smbus_write_word_swapped(client, regaddr, reg);
}
data->temp[nr][index] = reg;
@@ -449,7 +428,7 @@
return count;
}
-static ssize_t show_update_interval(struct device *dev,
+static ssize_t update_interval_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct tmp401_data *data = dev_get_drvdata(dev);
@@ -457,9 +436,9 @@
return sprintf(buf, "%u\n", data->update_interval);
}
-static ssize_t set_update_interval(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct tmp401_data *data = dev_get_drvdata(dev);
struct i2c_client *client = data->client;
@@ -521,8 +500,7 @@
static SENSOR_DEVICE_ATTR_2(temp2_crit_alarm, S_IRUGO, show_status, NULL,
3, TMP432_STATUS_REMOTE1);
-static DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, show_update_interval,
- set_update_interval);
+static DEVICE_ATTR_RW(update_interval);
static struct attribute *tmp401_attributes[] = {
&sensor_dev_attr_temp1_input.dev_attr.attr,
diff --git a/drivers/hwmon/via-cputemp.c b/drivers/hwmon/via-cputemp.c
index d1f209a..07a0cb0 100644
--- a/drivers/hwmon/via-cputemp.c
+++ b/drivers/hwmon/via-cputemp.c
@@ -88,8 +88,8 @@
return sprintf(buf, "%lu\n", ((unsigned long)eax & 0xffffff) * 1000);
}
-static ssize_t show_cpu_vid(struct device *dev,
- struct device_attribute *devattr, char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
{
struct via_cputemp_data *data = dev_get_drvdata(dev);
u32 eax, edx;
@@ -119,7 +119,7 @@
};
/* Optional attributes */
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_cpu_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
static int via_cputemp_probe(struct platform_device *pdev)
{
diff --git a/drivers/hwmon/via686a.c b/drivers/hwmon/via686a.c
index 40dd93c..81f35e3 100644
--- a/drivers/hwmon/via686a.c
+++ b/drivers/hwmon/via686a.c
@@ -580,14 +580,14 @@
show_fan_offset(2);
/* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct via686a_data *data = via686a_update_device(dev);
return sprintf(buf, "%u\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -607,13 +607,13 @@
static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
*devattr, char *buf)
{
struct via686a_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%s\n", data->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct attribute *via686a_attributes[] = {
&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/vt8231.c b/drivers/hwmon/vt8231.c
index cb69a8c..367b5eb5 100644
--- a/drivers/hwmon/vt8231.c
+++ b/drivers/hwmon/vt8231.c
@@ -263,8 +263,8 @@
}
/* Special case for input 5 as this has 3.3V scaling built into the chip */
-static ssize_t show_in5(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t in5_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct vt8231_data *data = vt8231_update_device(dev);
@@ -272,7 +272,7 @@
(((data->in[5] - 3) * 10000 * 54) / (958 * 34)));
}
-static ssize_t show_in5_min(struct device *dev, struct device_attribute *attr,
+static ssize_t in5_min_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct vt8231_data *data = vt8231_update_device(dev);
@@ -281,7 +281,7 @@
(((data->in_min[5] - 3) * 10000 * 54) / (958 * 34)));
}
-static ssize_t show_in5_max(struct device *dev, struct device_attribute *attr,
+static ssize_t in5_max_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct vt8231_data *data = vt8231_update_device(dev);
@@ -290,8 +290,9 @@
(((data->in_max[5] - 3) * 10000 * 54) / (958 * 34)));
}
-static ssize_t set_in5_min(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t in5_min_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct vt8231_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -309,8 +310,9 @@
return count;
}
-static ssize_t set_in5_max(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t in5_max_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct vt8231_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -342,34 +344,35 @@
define_voltage_sysfs(3);
define_voltage_sysfs(4);
-static DEVICE_ATTR(in5_input, S_IRUGO, show_in5, NULL);
-static DEVICE_ATTR(in5_min, S_IRUGO | S_IWUSR, show_in5_min, set_in5_min);
-static DEVICE_ATTR(in5_max, S_IRUGO | S_IWUSR, show_in5_max, set_in5_max);
+static DEVICE_ATTR_RO(in5_input);
+static DEVICE_ATTR_RW(in5_min);
+static DEVICE_ATTR_RW(in5_max);
/* Temperatures */
-static ssize_t show_temp0(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct vt8231_data *data = vt8231_update_device(dev);
return sprintf(buf, "%d\n", data->temp[0] * 250);
}
-static ssize_t show_temp0_max(struct device *dev, struct device_attribute *attr,
+static ssize_t temp1_max_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct vt8231_data *data = vt8231_update_device(dev);
return sprintf(buf, "%d\n", data->temp_max[0] * 1000);
}
-static ssize_t show_temp0_min(struct device *dev, struct device_attribute *attr,
- char *buf)
+static ssize_t temp1_max_hyst_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct vt8231_data *data = vt8231_update_device(dev);
return sprintf(buf, "%d\n", data->temp_min[0] * 1000);
}
-static ssize_t set_temp0_max(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t temp1_max_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct vt8231_data *data = dev_get_drvdata(dev);
long val;
@@ -385,8 +388,9 @@
mutex_unlock(&data->update_lock);
return count;
}
-static ssize_t set_temp0_min(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t temp1_max_hyst_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct vt8231_data *data = dev_get_drvdata(dev);
long val;
@@ -481,10 +485,9 @@
static SENSOR_DEVICE_ATTR(temp##offset##_max_hyst, S_IRUGO | S_IWUSR, \
show_temp_min, set_temp_min, offset - 1)
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp0, NULL);
-static DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR, show_temp0_max, set_temp0_max);
-static DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR, show_temp0_min,
- set_temp0_min);
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RW(temp1_max);
+static DEVICE_ATTR_RW(temp1_max_hyst);
define_temperature_sysfs(2);
define_temperature_sysfs(3);
@@ -603,13 +606,13 @@
define_fan_sysfs(2);
/* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct vt8231_data *data = vt8231_update_device(dev);
return sprintf(buf, "%d\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -633,13 +636,13 @@
static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
*devattr, char *buf)
{
struct vt8231_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%s\n", data->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct attribute *vt8231_attributes_temps[6][5] = {
{
diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c
index 697007a..ab346ed 100644
--- a/drivers/hwmon/w83627ehf.c
+++ b/drivers/hwmon/w83627ehf.c
@@ -1687,14 +1687,14 @@
fan_time_functions(fan_stop_time, FAN_STOP_TIME)
-static ssize_t show_name(struct device *dev, struct device_attribute *attr,
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct w83627ehf_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%s\n", data->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct sensor_device_attribute sda_sf3_arrays_fan4[] = {
SENSOR_ATTR(pwm4_stop_time, S_IWUSR | S_IRUGO, show_fan_stop_time,
@@ -1754,12 +1754,12 @@
};
static ssize_t
-show_vid(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83627ehf_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
/* Case open detection */
diff --git a/drivers/hwmon/w83627hf.c b/drivers/hwmon/w83627hf.c
index 721295b..8ac89d0 100644
--- a/drivers/hwmon/w83627hf.c
+++ b/drivers/hwmon/w83627hf.c
@@ -575,26 +575,30 @@
return sprintf(buf,"%ld\n", in0);
}
-static ssize_t show_regs_in_0(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t in0_input_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct w83627hf_data *data = w83627hf_update_device(dev);
return show_in_0(data, buf, data->in[0]);
}
-static ssize_t show_regs_in_min0(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t in0_min_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct w83627hf_data *data = w83627hf_update_device(dev);
return show_in_0(data, buf, data->in_min[0]);
}
-static ssize_t show_regs_in_max0(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t in0_max_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct w83627hf_data *data = w83627hf_update_device(dev);
return show_in_0(data, buf, data->in_max[0]);
}
-static ssize_t store_regs_in_min0(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t in0_min_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct w83627hf_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -622,8 +626,9 @@
return count;
}
-static ssize_t store_regs_in_max0(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t in0_max_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct w83627hf_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -651,11 +656,9 @@
return count;
}
-static DEVICE_ATTR(in0_input, S_IRUGO, show_regs_in_0, NULL);
-static DEVICE_ATTR(in0_min, S_IRUGO | S_IWUSR,
- show_regs_in_min0, store_regs_in_min0);
-static DEVICE_ATTR(in0_max, S_IRUGO | S_IWUSR,
- show_regs_in_max0, store_regs_in_max0);
+static DEVICE_ATTR_RO(in0_input);
+static DEVICE_ATTR_RW(in0_min);
+static DEVICE_ATTR_RW(in0_max);
static ssize_t
show_fan_input(struct device *dev, struct device_attribute *devattr, char *buf)
@@ -796,21 +799,22 @@
sysfs_temp_decl(3);
static ssize_t
-show_vid_reg(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83627hf_data *data = w83627hf_update_device(dev);
return sprintf(buf, "%ld\n", (long) vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
static ssize_t
-show_vrm_reg(struct device *dev, struct device_attribute *attr, char *buf)
+vrm_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83627hf_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%ld\n", (long) data->vrm);
}
static ssize_t
-store_vrm_reg(struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
+vrm_store(struct device *dev, struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct w83627hf_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -826,15 +830,15 @@
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
static ssize_t
-show_alarms_reg(struct device *dev, struct device_attribute *attr, char *buf)
+alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83627hf_data *data = w83627hf_update_device(dev);
return sprintf(buf, "%ld\n", (long) data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t
show_alarm(struct device *dev, struct device_attribute *attr, char *buf)
@@ -860,7 +864,7 @@
static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 13);
static ssize_t
-show_beep_mask(struct device *dev, struct device_attribute *attr, char *buf)
+beep_mask_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83627hf_data *data = w83627hf_update_device(dev);
return sprintf(buf, "%ld\n",
@@ -868,7 +872,7 @@
}
static ssize_t
-store_beep_mask(struct device *dev, struct device_attribute *attr,
+beep_mask_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct w83627hf_data *data = dev_get_drvdata(dev);
@@ -895,8 +899,7 @@
return count;
}
-static DEVICE_ATTR(beep_mask, S_IRUGO | S_IWUSR,
- show_beep_mask, store_beep_mask);
+static DEVICE_ATTR_RW(beep_mask);
static ssize_t
show_beep(struct device *dev, struct device_attribute *attr, char *buf)
@@ -1264,13 +1267,13 @@
sysfs_temp_type(3);
static ssize_t
-show_name(struct device *dev, struct device_attribute *devattr, char *buf)
+name_show(struct device *dev, struct device_attribute *devattr, char *buf)
{
struct w83627hf_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%s\n", data->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static int __init w83627hf_find(int sioaddr, unsigned short *addr,
struct w83627hf_sio_data *sio_data)
diff --git a/drivers/hwmon/w83781d.c b/drivers/hwmon/w83781d.c
index 54848fd..246fb23 100644
--- a/drivers/hwmon/w83781d.c
+++ b/drivers/hwmon/w83781d.c
@@ -416,24 +416,24 @@
sysfs_temp_offsets(3);
static ssize_t
-show_vid_reg(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83781d_data *data = w83781d_update_device(dev);
return sprintf(buf, "%ld\n", (long) vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
static ssize_t
-show_vrm_reg(struct device *dev, struct device_attribute *attr, char *buf)
+vrm_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83781d_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%ld\n", (long) data->vrm);
}
static ssize_t
-store_vrm_reg(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+vrm_store(struct device *dev, struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct w83781d_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -447,16 +447,16 @@
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
static ssize_t
-show_alarms_reg(struct device *dev, struct device_attribute *attr, char *buf)
+alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83781d_data *data = w83781d_update_device(dev);
return sprintf(buf, "%u\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -491,7 +491,7 @@
static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5);
static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_temp3_alarm, NULL, 0);
-static ssize_t show_beep_mask(struct device *dev,
+static ssize_t beep_mask_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct w83781d_data *data = w83781d_update_device(dev);
@@ -500,7 +500,7 @@
}
static ssize_t
-store_beep_mask(struct device *dev, struct device_attribute *attr,
+beep_mask_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct w83781d_data *data = dev_get_drvdata(dev);
@@ -527,8 +527,7 @@
return count;
}
-static DEVICE_ATTR(beep_mask, S_IRUGO | S_IWUSR,
- show_beep_mask, store_beep_mask);
+static DEVICE_ATTR_RW(beep_mask);
static ssize_t show_beep(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -708,7 +707,7 @@
}
static ssize_t
-show_pwm2_enable(struct device *dev, struct device_attribute *da, char *buf)
+pwm2_enable_show(struct device *dev, struct device_attribute *da, char *buf)
{
struct w83781d_data *data = w83781d_update_device(dev);
return sprintf(buf, "%d\n", (int)data->pwm2_enable);
@@ -736,7 +735,7 @@
}
static ssize_t
-store_pwm2_enable(struct device *dev, struct device_attribute *da,
+pwm2_enable_store(struct device *dev, struct device_attribute *da,
const char *buf, size_t count)
{
struct w83781d_data *data = dev_get_drvdata(dev);
@@ -778,8 +777,7 @@
static SENSOR_DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 2);
static SENSOR_DEVICE_ATTR(pwm4, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 3);
/* only PWM2 can be enabled/disabled */
-static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR,
- show_pwm2_enable, store_pwm2_enable);
+static DEVICE_ATTR_RW(pwm2_enable);
static ssize_t
show_sensor(struct device *dev, struct device_attribute *da, char *buf)
@@ -1616,12 +1614,12 @@
* we must create it by ourselves.
*/
static ssize_t
-show_name(struct device *dev, struct device_attribute *devattr, char *buf)
+name_show(struct device *dev, struct device_attribute *devattr, char *buf)
{
struct w83781d_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%s\n", data->name);
}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
static struct w83781d_data *w83781d_data_if_isa(void)
{
diff --git a/drivers/hwmon/w83791d.c b/drivers/hwmon/w83791d.c
index 001df85..8af6081 100644
--- a/drivers/hwmon/w83791d.c
+++ b/drivers/hwmon/w83791d.c
@@ -1041,14 +1041,14 @@
};
/* get realtime status of all sensors items: voltage, temp, fan */
-static ssize_t show_alarms_reg(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct w83791d_data *data = w83791d_update_device(dev);
return sprintf(buf, "%u\n", data->alarms);
}
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
/* Beep control */
@@ -1147,25 +1147,24 @@
};
/* cpu voltage regulation information */
-static ssize_t show_vid_reg(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct w83791d_data *data = w83791d_update_device(dev);
return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
}
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
-static ssize_t show_vrm_reg(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct w83791d_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", data->vrm);
}
-static ssize_t store_vrm_reg(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct w83791d_data *data = dev_get_drvdata(dev);
unsigned long val;
@@ -1188,7 +1187,7 @@
return count;
}
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
#define IN_UNIT_ATTRS(X) \
&sda_in_input[X].dev_attr.attr, \
diff --git a/drivers/hwmon/w83792d.c b/drivers/hwmon/w83792d.c
index 0a8bce7..d764602 100644
--- a/drivers/hwmon/w83792d.c
+++ b/drivers/hwmon/w83792d.c
@@ -578,7 +578,7 @@
/* get realtime status of all sensors items: voltage, temp, fan */
static ssize_t
-show_alarms_reg(struct device *dev, struct device_attribute *attr, char *buf)
+alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83792d_data *data = w83792d_update_device(dev);
return sprintf(buf, "%d\n", data->alarms);
@@ -735,16 +735,16 @@
}
static ssize_t
-show_chassis_clear(struct device *dev, struct device_attribute *attr,
- char *buf)
+intrusion0_alarm_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct w83792d_data *data = w83792d_update_device(dev);
return sprintf(buf, "%d\n", data->chassis);
}
static ssize_t
-store_chassis_clear(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+intrusion0_alarm_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct i2c_client *client = to_i2c_client(dev);
struct w83792d_data *data = i2c_get_clientdata(client);
@@ -1047,7 +1047,7 @@
show_temp23, store_temp23, 0, 4);
static SENSOR_DEVICE_ATTR_2(temp3_max_hyst, S_IRUGO | S_IWUSR,
show_temp23, store_temp23, 1, 4);
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 2);
@@ -1067,8 +1067,7 @@
static SENSOR_DEVICE_ATTR(fan4_alarm, S_IRUGO, show_alarm, NULL, 21);
static SENSOR_DEVICE_ATTR(fan5_alarm, S_IRUGO, show_alarm, NULL, 22);
static SENSOR_DEVICE_ATTR(fan6_alarm, S_IRUGO, show_alarm, NULL, 23);
-static DEVICE_ATTR(intrusion0_alarm, S_IRUGO | S_IWUSR,
- show_chassis_clear, store_chassis_clear);
+static DEVICE_ATTR_RW(intrusion0_alarm);
static SENSOR_DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 0);
static SENSOR_DEVICE_ATTR(pwm2, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 1);
static SENSOR_DEVICE_ATTR(pwm3, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 2);
diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c
index 816aa6c..dab5c51 100644
--- a/drivers/hwmon/w83793.c
+++ b/drivers/hwmon/w83793.c
@@ -324,7 +324,7 @@
};
static ssize_t
-show_vrm(struct device *dev, struct device_attribute *attr, char *buf)
+vrm_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct w83793_data *data = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", data->vrm);
@@ -342,7 +342,7 @@
}
static ssize_t
-store_vrm(struct device *dev, struct device_attribute *attr,
+vrm_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct w83793_data *data = dev_get_drvdata(dev);
@@ -1169,7 +1169,7 @@
SENSOR_ATTR_2(cpu0_vid, S_IRUGO, show_vid, NULL, NOT_USED, 0),
SENSOR_ATTR_2(cpu1_vid, S_IRUGO, show_vid, NULL, NOT_USED, 1),
};
-static DEVICE_ATTR(vrm, S_IWUSR | S_IRUGO, show_vrm, store_vrm);
+static DEVICE_ATTR_RW(vrm);
static struct sensor_device_attribute_2 sda_single_files[] = {
SENSOR_ATTR_2(intrusion0_alarm, S_IWUSR | S_IRUGO, show_alarm_beep,
diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c
index 6869712..45d6771 100644
--- a/drivers/i2c/busses/i2c-cadence.c
+++ b/drivers/i2c/busses/i2c-cadence.c
@@ -962,10 +962,6 @@
goto err_clk_dis;
}
- ret = i2c_add_adapter(&id->adap);
- if (ret < 0)
- goto err_clk_dis;
-
/*
* Cadence I2C controller has a bug wherein it generates
* invalid read transaction after HW timeout in master receiver mode.
@@ -975,6 +971,10 @@
*/
cdns_i2c_writereg(CDNS_I2C_TIMEOUT_MAX, CDNS_I2C_TIME_OUT_OFFSET);
+ ret = i2c_add_adapter(&id->adap);
+ if (ret < 0)
+ goto err_clk_dis;
+
dev_info(&pdev->dev, "%u kHz mmio %08lx irq %d\n",
id->i2c_clk / 1000, (unsigned long)r_mem->start, id->irq);
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index 6d81c56..e9db857 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -475,30 +475,28 @@
static void i2c_dw_xfer_init(struct dw_i2c_dev *dev)
{
struct i2c_msg *msgs = dev->msgs;
- u32 ic_tar = 0;
+ u32 ic_con, ic_tar = 0;
/* Disable the adapter */
__i2c_dw_enable_and_wait(dev, false);
/* if the slave address is ten bit address, enable 10BITADDR */
- if (dev->dynamic_tar_update_enabled) {
+ ic_con = dw_readl(dev, DW_IC_CON);
+ if (msgs[dev->msg_write_idx].flags & I2C_M_TEN) {
+ ic_con |= DW_IC_CON_10BITADDR_MASTER;
/*
* If I2C_DYNAMIC_TAR_UPDATE is set, the 10-bit addressing
- * mode has to be enabled via bit 12 of IC_TAR register,
- * otherwise bit 4 of IC_CON is used.
+ * mode has to be enabled via bit 12 of IC_TAR register.
+ * We set it always as I2C_DYNAMIC_TAR_UPDATE can't be
+ * detected from registers.
*/
- if (msgs[dev->msg_write_idx].flags & I2C_M_TEN)
- ic_tar = DW_IC_TAR_10BITADDR_MASTER;
+ ic_tar = DW_IC_TAR_10BITADDR_MASTER;
} else {
- u32 ic_con = dw_readl(dev, DW_IC_CON);
-
- if (msgs[dev->msg_write_idx].flags & I2C_M_TEN)
- ic_con |= DW_IC_CON_10BITADDR_MASTER;
- else
- ic_con &= ~DW_IC_CON_10BITADDR_MASTER;
- dw_writel(dev, ic_con, DW_IC_CON);
+ ic_con &= ~DW_IC_CON_10BITADDR_MASTER;
}
+ dw_writel(dev, ic_con, DW_IC_CON);
+
/*
* Set the slave (target) address and enable 10-bit addressing mode
* if applicable.
@@ -963,7 +961,6 @@
{
struct i2c_adapter *adap = &dev->adapter;
int r;
- u32 reg;
init_completion(&dev->cmd_complete);
@@ -971,26 +968,6 @@
if (r)
return r;
- r = i2c_dw_acquire_lock(dev);
- if (r)
- return r;
-
- /*
- * Test if dynamic TAR update is enabled in this controller by writing
- * to IC_10BITADDR_MASTER field in IC_CON: when it is enabled this
- * field is read-only so it should not succeed
- */
- reg = dw_readl(dev, DW_IC_CON);
- dw_writel(dev, reg ^ DW_IC_CON_10BITADDR_MASTER, DW_IC_CON);
-
- if ((dw_readl(dev, DW_IC_CON) & DW_IC_CON_10BITADDR_MASTER) ==
- (reg & DW_IC_CON_10BITADDR_MASTER)) {
- dev->dynamic_tar_update_enabled = true;
- dev_dbg(dev->dev, "Dynamic TAR update enabled");
- }
-
- i2c_dw_release_lock(dev);
-
snprintf(adap->name, sizeof(adap->name),
"Synopsys DesignWare I2C adapter");
adap->retries = 3;
diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h
index 26250b4..c1db3a5 100644
--- a/drivers/i2c/busses/i2c-designware-core.h
+++ b/drivers/i2c/busses/i2c-designware-core.h
@@ -125,7 +125,6 @@
int (*acquire_lock)(struct dw_i2c_dev *dev);
void (*release_lock)(struct dw_i2c_dev *dev);
bool pm_runtime_disabled;
- bool dynamic_tar_update_enabled;
};
#define ACCESS_SWAP 0x00000001
diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c
index c62b7cd..3310f2e 100644
--- a/drivers/i2c/busses/i2c-imx-lpi2c.c
+++ b/drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -28,6 +28,7 @@
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_device.h>
+#include <linux/pinctrl/consumer.h>
#include <linux/platform_device.h>
#include <linux/sched.h>
#include <linux/slab.h>
@@ -636,12 +637,31 @@
return 0;
}
+#ifdef CONFIG_PM_SLEEP
+static int lpi2c_imx_suspend(struct device *dev)
+{
+ pinctrl_pm_select_sleep_state(dev);
+
+ return 0;
+}
+
+static int lpi2c_imx_resume(struct device *dev)
+{
+ pinctrl_pm_select_default_state(dev);
+
+ return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(imx_lpi2c_pm, lpi2c_imx_suspend, lpi2c_imx_resume);
+
static struct platform_driver lpi2c_imx_driver = {
.probe = lpi2c_imx_probe,
.remove = lpi2c_imx_remove,
.driver = {
.name = DRIVER_NAME,
.of_match_table = lpi2c_imx_of_match,
+ .pm = &imx_lpi2c_pm,
},
};
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index c2268cd..c21ca7b 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -58,7 +58,7 @@
#define SMBSLVDAT (0xC + piix4_smba)
/* count for request_region */
-#define SMBIOSIZE 8
+#define SMBIOSIZE 9
/* PCI Address Constants */
#define SMBBA 0x090
@@ -585,12 +585,33 @@
u8 command, int size, union i2c_smbus_data *data)
{
struct i2c_piix4_adapdata *adapdata = i2c_get_adapdata(adap);
+ unsigned short piix4_smba = adapdata->smba;
+ int retries = MAX_TIMEOUT;
+ int smbslvcnt;
u8 smba_en_lo;
u8 port;
int retval;
mutex_lock(&piix4_mutex_sb800);
+ /* Request the SMBUS semaphore, avoid conflicts with the IMC */
+ smbslvcnt = inb_p(SMBSLVCNT);
+ do {
+ outb_p(smbslvcnt | 0x10, SMBSLVCNT);
+
+ /* Check the semaphore status */
+ smbslvcnt = inb_p(SMBSLVCNT);
+ if (smbslvcnt & 0x10)
+ break;
+
+ usleep_range(1000, 2000);
+ } while (--retries);
+ /* SMBus is still owned by the IMC, we give up */
+ if (!retries) {
+ mutex_unlock(&piix4_mutex_sb800);
+ return -EBUSY;
+ }
+
outb_p(piix4_port_sel_sb800, SB800_PIIX4_SMB_IDX);
smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1);
@@ -604,6 +625,9 @@
outb_p(smba_en_lo, SB800_PIIX4_SMB_IDX + 1);
+ /* Release the semaphore */
+ outb_p(smbslvcnt | 0x20, SMBSLVCNT);
+
mutex_unlock(&piix4_mutex_sb800);
return retval;
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index cf9e396..583e950 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -931,7 +931,10 @@
if (!client->irq) {
int irq = -ENOENT;
- if (dev->of_node) {
+ if (client->flags & I2C_CLIENT_HOST_NOTIFY) {
+ dev_dbg(dev, "Using Host Notify IRQ\n");
+ irq = i2c_smbus_host_notify_to_irq(client);
+ } else if (dev->of_node) {
irq = of_irq_get_byname(dev->of_node, "irq");
if (irq == -EINVAL || irq == -ENODATA)
irq = of_irq_get(dev->of_node, 0);
@@ -940,14 +943,7 @@
}
if (irq == -EPROBE_DEFER)
return irq;
- /*
- * ACPI and OF did not find any useful IRQ, try to see
- * if Host Notify can be used.
- */
- if (irq < 0) {
- dev_dbg(dev, "Using Host Notify IRQ\n");
- irq = i2c_smbus_host_notify_to_irq(client);
- }
+
if (irq < 0)
irq = 0;
@@ -1708,7 +1704,7 @@
if (i2c_check_addr_validity(addr, info.flags)) {
dev_err(&adap->dev, "of_i2c: invalid addr=%x on %s\n",
- info.addr, node->full_name);
+ addr, node->full_name);
return ERR_PTR(-EINVAL);
}
@@ -1716,6 +1712,9 @@
info.of_node = of_node_get(node);
info.archdata = &dev_ad;
+ if (of_property_read_bool(node, "host-notify"))
+ info.flags |= I2C_CLIENT_HOST_NOTIFY;
+
if (of_get_property(node, "wakeup-source", NULL))
info.flags |= I2C_CLIENT_WAKE;
@@ -3633,7 +3632,7 @@
int ret;
if (!client || !slave_cb) {
- WARN(1, "insufficent data\n");
+ WARN(1, "insufficient data\n");
return -EINVAL;
}
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index 66f323f..6f638bb 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -331,7 +331,7 @@
unsigned long arg)
{
struct i2c_smbus_ioctl_data data_arg;
- union i2c_smbus_data temp;
+ union i2c_smbus_data temp = {};
int datasize, res;
if (copy_from_user(&data_arg,
diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c
index 2bbf0c5..7d61b56 100644
--- a/drivers/iio/adc/palmas_gpadc.c
+++ b/drivers/iio/adc/palmas_gpadc.c
@@ -775,7 +775,7 @@
static int palmas_gpadc_suspend(struct device *dev)
{
- struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+ struct iio_dev *indio_dev = dev_get_drvdata(dev);
struct palmas_gpadc *adc = iio_priv(indio_dev);
int wakeup = adc->wakeup1_enable || adc->wakeup2_enable;
int ret;
@@ -798,7 +798,7 @@
static int palmas_gpadc_resume(struct device *dev)
{
- struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+ struct iio_dev *indio_dev = dev_get_drvdata(dev);
struct palmas_gpadc *adc = iio_priv(indio_dev);
int wakeup = adc->wakeup1_enable || adc->wakeup2_enable;
int ret;
diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c
index 9a08146..6bb23a4 100644
--- a/drivers/iio/health/afe4403.c
+++ b/drivers/iio/health/afe4403.c
@@ -422,7 +422,7 @@
static int __maybe_unused afe4403_suspend(struct device *dev)
{
- struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+ struct iio_dev *indio_dev = spi_get_drvdata(to_spi_device(dev));
struct afe4403_data *afe = iio_priv(indio_dev);
int ret;
@@ -443,7 +443,7 @@
static int __maybe_unused afe4403_resume(struct device *dev)
{
- struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+ struct iio_dev *indio_dev = spi_get_drvdata(to_spi_device(dev));
struct afe4403_data *afe = iio_priv(indio_dev);
int ret;
diff --git a/drivers/iio/health/afe4404.c b/drivers/iio/health/afe4404.c
index 4526640..964f523 100644
--- a/drivers/iio/health/afe4404.c
+++ b/drivers/iio/health/afe4404.c
@@ -428,7 +428,7 @@
static int __maybe_unused afe4404_suspend(struct device *dev)
{
- struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+ struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev));
struct afe4404_data *afe = iio_priv(indio_dev);
int ret;
@@ -449,7 +449,7 @@
static int __maybe_unused afe4404_resume(struct device *dev)
{
- struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+ struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev));
struct afe4404_data *afe = iio_priv(indio_dev);
int ret;
diff --git a/drivers/iio/health/max30100.c b/drivers/iio/health/max30100.c
index 90ab8a2d..183c143 100644
--- a/drivers/iio/health/max30100.c
+++ b/drivers/iio/health/max30100.c
@@ -238,7 +238,7 @@
mutex_lock(&data->lock);
- while (cnt || (cnt = max30100_fifo_count(data) > 0)) {
+ while (cnt || (cnt = max30100_fifo_count(data)) > 0) {
ret = max30100_read_measurement(data);
if (ret)
break;
diff --git a/drivers/iio/humidity/dht11.c b/drivers/iio/humidity/dht11.c
index 9c47bc9..2a22ad9 100644
--- a/drivers/iio/humidity/dht11.c
+++ b/drivers/iio/humidity/dht11.c
@@ -71,7 +71,8 @@
* a) select an implementation using busy loop polling on those systems
* b) use the checksum to do some probabilistic decoding
*/
-#define DHT11_START_TRANSMISSION 18 /* ms */
+#define DHT11_START_TRANSMISSION_MIN 18000 /* us */
+#define DHT11_START_TRANSMISSION_MAX 20000 /* us */
#define DHT11_MIN_TIMERES 34000 /* ns */
#define DHT11_THRESHOLD 49000 /* ns */
#define DHT11_AMBIG_LOW 23000 /* ns */
@@ -228,7 +229,8 @@
ret = gpio_direction_output(dht11->gpio, 0);
if (ret)
goto err;
- msleep(DHT11_START_TRANSMISSION);
+ usleep_range(DHT11_START_TRANSMISSION_MIN,
+ DHT11_START_TRANSMISSION_MAX);
ret = gpio_direction_input(dht11->gpio);
if (ret)
goto err;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index e7dcfac..3e70a9c 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2811,7 +2811,8 @@
if (!src_addr || !src_addr->sa_family) {
src_addr = (struct sockaddr *) &id->route.addr.src_addr;
src_addr->sa_family = dst_addr->sa_family;
- if (dst_addr->sa_family == AF_INET6) {
+ if (IS_ENABLED(CONFIG_IPV6) &&
+ dst_addr->sa_family == AF_INET6) {
struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *) src_addr;
struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *) dst_addr;
src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 1e62a5f..4609b92 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -134,6 +134,7 @@
IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
if (access & IB_ACCESS_ON_DEMAND) {
+ put_pid(umem->pid);
ret = ib_umem_odp_get(context, umem);
if (ret) {
kfree(umem);
@@ -149,6 +150,7 @@
page_list = (struct page **) __get_free_page(GFP_KERNEL);
if (!page_list) {
+ put_pid(umem->pid);
kfree(umem);
return ERR_PTR(-ENOMEM);
}
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 9d5fe18..6262dc0 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -1135,16 +1135,7 @@
memset(props, 0, sizeof(struct ib_port_attr));
props->max_mtu = IB_MTU_4096;
- if (netdev->mtu >= 4096)
- props->active_mtu = IB_MTU_4096;
- else if (netdev->mtu >= 2048)
- props->active_mtu = IB_MTU_2048;
- else if (netdev->mtu >= 1024)
- props->active_mtu = IB_MTU_1024;
- else if (netdev->mtu >= 512)
- props->active_mtu = IB_MTU_512;
- else
- props->active_mtu = IB_MTU_256;
+ props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
if (!netif_carrier_ok(netdev))
props->state = IB_PORT_DOWN;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index f1510cc..9398143 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1804,20 +1804,21 @@
skb_trim(skb, dlen);
mutex_lock(&ep->com.mutex);
- /* update RX credits */
- update_rx_credits(ep, dlen);
-
switch (ep->com.state) {
case MPA_REQ_SENT:
+ update_rx_credits(ep, dlen);
ep->rcv_seq += dlen;
disconnect = process_mpa_reply(ep, skb);
break;
case MPA_REQ_WAIT:
+ update_rx_credits(ep, dlen);
ep->rcv_seq += dlen;
disconnect = process_mpa_request(ep, skb);
break;
case FPDU_MODE: {
struct c4iw_qp_attributes attrs;
+
+ update_rx_credits(ep, dlen);
BUG_ON(!ep->com.qp);
if (status)
pr_err("%s Unexpected streaming data." \
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 19c6477..bec82a6 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -505,6 +505,15 @@
}
/*
+ * Special cqe for drain WR completions...
+ */
+ if (CQE_OPCODE(hw_cqe) == C4IW_DRAIN_OPCODE) {
+ *cookie = CQE_DRAIN_COOKIE(hw_cqe);
+ *cqe = *hw_cqe;
+ goto skip_cqe;
+ }
+
+ /*
* Gotta tweak READ completions:
* 1) the cqe doesn't contain the sq_wptr from the wr.
* 2) opcode not reflected from the wr.
@@ -753,6 +762,9 @@
c4iw_invalidate_mr(qhp->rhp,
CQE_WRID_FR_STAG(&cqe));
break;
+ case C4IW_DRAIN_OPCODE:
+ wc->opcode = IB_WC_SEND;
+ break;
default:
printk(KERN_ERR MOD "Unexpected opcode %d "
"in the CQE received for QPID=0x%0x\n",
@@ -817,15 +829,8 @@
}
}
out:
- if (wq) {
- if (unlikely(qhp->attr.state != C4IW_QP_STATE_RTS)) {
- if (t4_sq_empty(wq))
- complete(&qhp->sq_drained);
- if (t4_rq_empty(wq))
- complete(&qhp->rq_drained);
- }
+ if (wq)
spin_unlock(&qhp->lock);
- }
return ret;
}
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 516b0ae..40c0e7b 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -846,9 +846,17 @@
}
}
+ rdev->free_workq = create_singlethread_workqueue("iw_cxgb4_free");
+ if (!rdev->free_workq) {
+ err = -ENOMEM;
+ goto err_free_status_page;
+ }
+
rdev->status_page->db_off = 0;
return 0;
+err_free_status_page:
+ free_page((unsigned long)rdev->status_page);
destroy_ocqp_pool:
c4iw_ocqp_pool_destroy(rdev);
destroy_rqtpool:
@@ -862,6 +870,7 @@
static void c4iw_rdev_close(struct c4iw_rdev *rdev)
{
+ destroy_workqueue(rdev->free_workq);
kfree(rdev->wr_log);
free_page((unsigned long)rdev->status_page);
c4iw_pblpool_destroy(rdev);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 4dc1415..d19662f 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -45,6 +45,7 @@
#include <linux/kref.h>
#include <linux/timer.h>
#include <linux/io.h>
+#include <linux/workqueue.h>
#include <asm/byteorder.h>
@@ -107,6 +108,7 @@
struct list_head qpids;
struct list_head cqids;
struct mutex lock;
+ struct kref kref;
};
enum c4iw_rdev_flags {
@@ -183,6 +185,7 @@
atomic_t wr_log_idx;
struct wr_log_entry *wr_log;
int wr_log_size;
+ struct workqueue_struct *free_workq;
};
static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
@@ -480,8 +483,8 @@
wait_queue_head_t wait;
struct timer_list timer;
int sq_sig_all;
- struct completion rq_drained;
- struct completion sq_drained;
+ struct work_struct free_work;
+ struct c4iw_ucontext *ucontext;
};
static inline struct c4iw_qp *to_c4iw_qp(struct ib_qp *ibqp)
@@ -495,6 +498,7 @@
u32 key;
spinlock_t mmap_lock;
struct list_head mmaps;
+ struct kref kref;
};
static inline struct c4iw_ucontext *to_c4iw_ucontext(struct ib_ucontext *c)
@@ -502,6 +506,18 @@
return container_of(c, struct c4iw_ucontext, ibucontext);
}
+void _c4iw_free_ucontext(struct kref *kref);
+
+static inline void c4iw_put_ucontext(struct c4iw_ucontext *ucontext)
+{
+ kref_put(&ucontext->kref, _c4iw_free_ucontext);
+}
+
+static inline void c4iw_get_ucontext(struct c4iw_ucontext *ucontext)
+{
+ kref_get(&ucontext->kref);
+}
+
struct c4iw_mm_entry {
struct list_head entry;
u64 addr;
@@ -615,6 +631,8 @@
return IB_QPS_ERR;
}
+#define C4IW_DRAIN_OPCODE FW_RI_SGE_EC_CR_RETURN
+
static inline u32 c4iw_ib_to_tpt_access(int a)
{
return (a & IB_ACCESS_REMOTE_WRITE ? FW_RI_MEM_ACCESS_REM_WRITE : 0) |
@@ -997,8 +1015,6 @@
extern int db_fc_threshold;
extern int db_coalescing_threshold;
extern int use_dsgl;
-void c4iw_drain_rq(struct ib_qp *qp);
-void c4iw_drain_sq(struct ib_qp *qp);
void c4iw_invalidate_mr(struct c4iw_dev *rhp, u32 rkey);
#endif
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 49b51b7..3345e1c 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -93,17 +93,28 @@
return -ENOSYS;
}
-static int c4iw_dealloc_ucontext(struct ib_ucontext *context)
+void _c4iw_free_ucontext(struct kref *kref)
{
- struct c4iw_dev *rhp = to_c4iw_dev(context->device);
- struct c4iw_ucontext *ucontext = to_c4iw_ucontext(context);
+ struct c4iw_ucontext *ucontext;
+ struct c4iw_dev *rhp;
struct c4iw_mm_entry *mm, *tmp;
- PDBG("%s context %p\n", __func__, context);
+ ucontext = container_of(kref, struct c4iw_ucontext, kref);
+ rhp = to_c4iw_dev(ucontext->ibucontext.device);
+
+ PDBG("%s ucontext %p\n", __func__, ucontext);
list_for_each_entry_safe(mm, tmp, &ucontext->mmaps, entry)
kfree(mm);
c4iw_release_dev_ucontext(&rhp->rdev, &ucontext->uctx);
kfree(ucontext);
+}
+
+static int c4iw_dealloc_ucontext(struct ib_ucontext *context)
+{
+ struct c4iw_ucontext *ucontext = to_c4iw_ucontext(context);
+
+ PDBG("%s context %p\n", __func__, context);
+ c4iw_put_ucontext(ucontext);
return 0;
}
@@ -127,6 +138,7 @@
c4iw_init_dev_ucontext(&rhp->rdev, &context->uctx);
INIT_LIST_HEAD(&context->mmaps);
spin_lock_init(&context->mmap_lock);
+ kref_init(&context->kref);
if (udata->outlen < sizeof(uresp) - sizeof(uresp.reserved)) {
if (!warned++)
@@ -361,16 +373,7 @@
memset(props, 0, sizeof(struct ib_port_attr));
props->max_mtu = IB_MTU_4096;
- if (netdev->mtu >= 4096)
- props->active_mtu = IB_MTU_4096;
- else if (netdev->mtu >= 2048)
- props->active_mtu = IB_MTU_2048;
- else if (netdev->mtu >= 1024)
- props->active_mtu = IB_MTU_1024;
- else if (netdev->mtu >= 512)
- props->active_mtu = IB_MTU_512;
- else
- props->active_mtu = IB_MTU_256;
+ props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
if (!netif_carrier_ok(netdev))
props->state = IB_PORT_DOWN;
@@ -607,8 +610,6 @@
dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION;
dev->ibdev.get_port_immutable = c4iw_port_immutable;
dev->ibdev.get_dev_fw_str = get_dev_fw_str;
- dev->ibdev.drain_sq = c4iw_drain_sq;
- dev->ibdev.drain_rq = c4iw_drain_rq;
dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
if (!dev->ibdev.iwcm)
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 347b3c9..d4fd2f5 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -715,13 +715,32 @@
return 0;
}
-static void _free_qp(struct kref *kref)
+static void free_qp_work(struct work_struct *work)
+{
+ struct c4iw_ucontext *ucontext;
+ struct c4iw_qp *qhp;
+ struct c4iw_dev *rhp;
+
+ qhp = container_of(work, struct c4iw_qp, free_work);
+ ucontext = qhp->ucontext;
+ rhp = qhp->rhp;
+
+ PDBG("%s qhp %p ucontext %p\n", __func__, qhp, ucontext);
+ destroy_qp(&rhp->rdev, &qhp->wq,
+ ucontext ? &ucontext->uctx : &rhp->rdev.uctx);
+
+ if (ucontext)
+ c4iw_put_ucontext(ucontext);
+ kfree(qhp);
+}
+
+static void queue_qp_free(struct kref *kref)
{
struct c4iw_qp *qhp;
qhp = container_of(kref, struct c4iw_qp, kref);
PDBG("%s qhp %p\n", __func__, qhp);
- kfree(qhp);
+ queue_work(qhp->rhp->rdev.free_workq, &qhp->free_work);
}
void c4iw_qp_add_ref(struct ib_qp *qp)
@@ -733,7 +752,7 @@
void c4iw_qp_rem_ref(struct ib_qp *qp)
{
PDBG("%s ib_qp %p\n", __func__, qp);
- kref_put(&to_c4iw_qp(qp)->kref, _free_qp);
+ kref_put(&to_c4iw_qp(qp)->kref, queue_qp_free);
}
static void add_to_fc_list(struct list_head *head, struct list_head *entry)
@@ -776,6 +795,64 @@
return 0;
}
+static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
+{
+ struct t4_cqe cqe = {};
+ struct c4iw_cq *schp;
+ unsigned long flag;
+ struct t4_cq *cq;
+
+ schp = to_c4iw_cq(qhp->ibqp.send_cq);
+ cq = &schp->cq;
+
+ cqe.u.drain_cookie = wr->wr_id;
+ cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
+ CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+ CQE_TYPE_V(1) |
+ CQE_SWCQE_V(1) |
+ CQE_QPID_V(qhp->wq.sq.qid));
+
+ spin_lock_irqsave(&schp->lock, flag);
+ cqe.bits_type_ts = cpu_to_be64(CQE_GENBIT_V((u64)cq->gen));
+ cq->sw_queue[cq->sw_pidx] = cqe;
+ t4_swcq_produce(cq);
+ spin_unlock_irqrestore(&schp->lock, flag);
+
+ spin_lock_irqsave(&schp->comp_handler_lock, flag);
+ (*schp->ibcq.comp_handler)(&schp->ibcq,
+ schp->ibcq.cq_context);
+ spin_unlock_irqrestore(&schp->comp_handler_lock, flag);
+}
+
+static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
+{
+ struct t4_cqe cqe = {};
+ struct c4iw_cq *rchp;
+ unsigned long flag;
+ struct t4_cq *cq;
+
+ rchp = to_c4iw_cq(qhp->ibqp.recv_cq);
+ cq = &rchp->cq;
+
+ cqe.u.drain_cookie = wr->wr_id;
+ cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
+ CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+ CQE_TYPE_V(0) |
+ CQE_SWCQE_V(1) |
+ CQE_QPID_V(qhp->wq.sq.qid));
+
+ spin_lock_irqsave(&rchp->lock, flag);
+ cqe.bits_type_ts = cpu_to_be64(CQE_GENBIT_V((u64)cq->gen));
+ cq->sw_queue[cq->sw_pidx] = cqe;
+ t4_swcq_produce(cq);
+ spin_unlock_irqrestore(&rchp->lock, flag);
+
+ spin_lock_irqsave(&rchp->comp_handler_lock, flag);
+ (*rchp->ibcq.comp_handler)(&rchp->ibcq,
+ rchp->ibcq.cq_context);
+ spin_unlock_irqrestore(&rchp->comp_handler_lock, flag);
+}
+
int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
struct ib_send_wr **bad_wr)
{
@@ -794,8 +871,8 @@
spin_lock_irqsave(&qhp->lock, flag);
if (t4_wq_in_error(&qhp->wq)) {
spin_unlock_irqrestore(&qhp->lock, flag);
- *bad_wr = wr;
- return -EINVAL;
+ complete_sq_drain_wr(qhp, wr);
+ return err;
}
num_wrs = t4_sq_avail(&qhp->wq);
if (num_wrs == 0) {
@@ -937,8 +1014,8 @@
spin_lock_irqsave(&qhp->lock, flag);
if (t4_wq_in_error(&qhp->wq)) {
spin_unlock_irqrestore(&qhp->lock, flag);
- *bad_wr = wr;
- return -EINVAL;
+ complete_rq_drain_wr(qhp, wr);
+ return err;
}
num_wrs = t4_rq_avail(&qhp->wq);
if (num_wrs == 0) {
@@ -1550,7 +1627,12 @@
}
break;
case C4IW_QP_STATE_CLOSING:
- if (!internal) {
+
+ /*
+ * Allow kernel users to move to ERROR for qp draining.
+ */
+ if (!internal && (qhp->ibqp.uobject || attrs->next_state !=
+ C4IW_QP_STATE_ERROR)) {
ret = -EINVAL;
goto out;
}
@@ -1643,7 +1725,6 @@
struct c4iw_dev *rhp;
struct c4iw_qp *qhp;
struct c4iw_qp_attributes attrs;
- struct c4iw_ucontext *ucontext;
qhp = to_c4iw_qp(ib_qp);
rhp = qhp->rhp;
@@ -1663,11 +1744,6 @@
spin_unlock_irq(&rhp->lock);
free_ird(rhp, qhp->attr.max_ird);
- ucontext = ib_qp->uobject ?
- to_c4iw_ucontext(ib_qp->uobject->context) : NULL;
- destroy_qp(&rhp->rdev, &qhp->wq,
- ucontext ? &ucontext->uctx : &rhp->rdev.uctx);
-
c4iw_qp_rem_ref(ib_qp);
PDBG("%s ib_qp %p qpid 0x%0x\n", __func__, ib_qp, qhp->wq.sq.qid);
@@ -1763,11 +1839,10 @@
qhp->attr.max_ird = 0;
qhp->sq_sig_all = attrs->sq_sig_type == IB_SIGNAL_ALL_WR;
spin_lock_init(&qhp->lock);
- init_completion(&qhp->sq_drained);
- init_completion(&qhp->rq_drained);
mutex_init(&qhp->mutex);
init_waitqueue_head(&qhp->wait);
kref_init(&qhp->kref);
+ INIT_WORK(&qhp->free_work, free_qp_work);
ret = insert_handle(rhp, &rhp->qpidr, qhp, qhp->wq.sq.qid);
if (ret)
@@ -1854,6 +1929,9 @@
ma_sync_key_mm->len = PAGE_SIZE;
insert_mmap(ucontext, ma_sync_key_mm);
}
+
+ c4iw_get_ucontext(ucontext);
+ qhp->ucontext = ucontext;
}
qhp->ibqp.qp_num = qhp->wq.sq.qid;
init_timer(&(qhp->timer));
@@ -1958,40 +2036,3 @@
init_attr->sq_sig_type = qhp->sq_sig_all ? IB_SIGNAL_ALL_WR : 0;
return 0;
}
-
-static void move_qp_to_err(struct c4iw_qp *qp)
-{
- struct c4iw_qp_attributes attrs = { .next_state = C4IW_QP_STATE_ERROR };
-
- (void)c4iw_modify_qp(qp->rhp, qp, C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
-}
-
-void c4iw_drain_sq(struct ib_qp *ibqp)
-{
- struct c4iw_qp *qp = to_c4iw_qp(ibqp);
- unsigned long flag;
- bool need_to_wait;
-
- move_qp_to_err(qp);
- spin_lock_irqsave(&qp->lock, flag);
- need_to_wait = !t4_sq_empty(&qp->wq);
- spin_unlock_irqrestore(&qp->lock, flag);
-
- if (need_to_wait)
- wait_for_completion(&qp->sq_drained);
-}
-
-void c4iw_drain_rq(struct ib_qp *ibqp)
-{
- struct c4iw_qp *qp = to_c4iw_qp(ibqp);
- unsigned long flag;
- bool need_to_wait;
-
- move_qp_to_err(qp);
- spin_lock_irqsave(&qp->lock, flag);
- need_to_wait = !t4_rq_empty(&qp->wq);
- spin_unlock_irqrestore(&qp->lock, flag);
-
- if (need_to_wait)
- wait_for_completion(&qp->rq_drained);
-}
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index 862381a..640d221 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -179,6 +179,7 @@
__be32 wrid_hi;
__be32 wrid_low;
} gen;
+ u64 drain_cookie;
} u;
__be64 reserved;
__be64 bits_type_ts;
@@ -238,6 +239,7 @@
/* generic accessor macros */
#define CQE_WRID_HI(x) (be32_to_cpu((x)->u.gen.wrid_hi))
#define CQE_WRID_LOW(x) (be32_to_cpu((x)->u.gen.wrid_low))
+#define CQE_DRAIN_COOKIE(x) ((x)->u.drain_cookie)
/* macros for flit 3 of the cqe */
#define CQE_GENBIT_S 63
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 29e97df..4c000d6 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -100,16 +100,7 @@
memset(props, 0, sizeof(*props));
props->max_mtu = IB_MTU_4096;
- if (netdev->mtu >= 4096)
- props->active_mtu = IB_MTU_4096;
- else if (netdev->mtu >= 2048)
- props->active_mtu = IB_MTU_2048;
- else if (netdev->mtu >= 1024)
- props->active_mtu = IB_MTU_1024;
- else if (netdev->mtu >= 512)
- props->active_mtu = IB_MTU_512;
- else
- props->active_mtu = IB_MTU_256;
+ props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
props->lid = 1;
if (netif_carrier_ok(iwdev->netdev))
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index aff9fb1..5a31f3c 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -478,17 +478,7 @@
memset(props, 0, sizeof(*props));
props->max_mtu = IB_MTU_4096;
-
- if (netdev->mtu >= 4096)
- props->active_mtu = IB_MTU_4096;
- else if (netdev->mtu >= 2048)
- props->active_mtu = IB_MTU_2048;
- else if (netdev->mtu >= 1024)
- props->active_mtu = IB_MTU_1024;
- else if (netdev->mtu >= 512)
- props->active_mtu = IB_MTU_512;
- else
- props->active_mtu = IB_MTU_256;
+ props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
props->lid = 1;
props->lmc = 0;
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 7b74d09..3ac8aa5 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -576,8 +576,7 @@
return 0;
}
-void qedr_unaffiliated_event(void *context,
- u8 event_code)
+void qedr_unaffiliated_event(void *context, u8 event_code)
{
pr_err("unaffiliated event not implemented yet\n");
}
@@ -792,6 +791,9 @@
if (device_create_file(&dev->ibdev.dev, qedr_attributes[i]))
goto sysfs_err;
+ if (!test_and_set_bit(QEDR_ENET_STATE_BIT, &dev->enet_state))
+ qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ACTIVE);
+
DP_DEBUG(dev, QEDR_MSG_INIT, "qedr driver loaded successfully\n");
return dev;
@@ -824,11 +826,10 @@
ib_dealloc_device(&dev->ibdev);
}
-static int qedr_close(struct qedr_dev *dev)
+static void qedr_close(struct qedr_dev *dev)
{
- qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ERR);
-
- return 0;
+ if (test_and_clear_bit(QEDR_ENET_STATE_BIT, &dev->enet_state))
+ qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ERR);
}
static void qedr_shutdown(struct qedr_dev *dev)
@@ -837,6 +838,12 @@
qedr_remove(dev);
}
+static void qedr_open(struct qedr_dev *dev)
+{
+ if (!test_and_set_bit(QEDR_ENET_STATE_BIT, &dev->enet_state))
+ qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ACTIVE);
+}
+
static void qedr_mac_address_change(struct qedr_dev *dev)
{
union ib_gid *sgid = &dev->sgid_tbl[0];
@@ -863,7 +870,7 @@
ether_addr_copy(dev->gsi_ll2_mac_address, dev->ndev->dev_addr);
- qedr_ib_dispatch_event(dev, 1, IB_EVENT_GID_CHANGE);
+ qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_GID_CHANGE);
if (rc)
DP_ERR(dev, "Error updating mac filter\n");
@@ -877,7 +884,7 @@
{
switch (event) {
case QEDE_UP:
- qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE);
+ qedr_open(dev);
break;
case QEDE_DOWN:
qedr_close(dev);
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index 620badd..bb32e47 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -113,6 +113,8 @@
struct qed_rdma_events events;
};
+#define QEDR_ENET_STATE_BIT (0)
+
struct qedr_dev {
struct ib_device ibdev;
struct qed_dev *cdev;
@@ -153,6 +155,8 @@
struct qedr_cq *gsi_sqcq;
struct qedr_cq *gsi_rqcq;
struct qedr_qp *gsi_qp;
+
+ unsigned long enet_state;
};
#define QEDR_MAX_SQ_PBL (0x8000)
@@ -188,6 +192,7 @@
#define QEDR_ROCE_MAX_CNQ_SIZE (0x4000)
#define QEDR_MAX_PORT (1)
+#define QEDR_PORT (1)
#define QEDR_UVERBS(CMD_NAME) (1ull << IB_USER_VERBS_CMD_##CMD_NAME)
@@ -251,9 +256,6 @@
u16 icid;
- /* Lock to protect completion handler */
- spinlock_t comp_handler_lock;
-
/* Lock to protect multiplem CQ's */
spinlock_t cq_lock;
u8 arm_flags;
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c
index 63890eb..a9a8d87 100644
--- a/drivers/infiniband/hw/qedr/qedr_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_cm.c
@@ -87,11 +87,8 @@
qedr_inc_sw_gsi_cons(&qp->sq);
spin_unlock_irqrestore(&qp->q_lock, flags);
- if (cq->ibcq.comp_handler) {
- spin_lock_irqsave(&cq->comp_handler_lock, flags);
+ if (cq->ibcq.comp_handler)
(*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context);
- spin_unlock_irqrestore(&cq->comp_handler_lock, flags);
- }
}
void qedr_ll2_rx_cb(void *_dev, struct qed_roce_ll2_packet *pkt,
@@ -113,11 +110,8 @@
spin_unlock_irqrestore(&qp->q_lock, flags);
- if (cq->ibcq.comp_handler) {
- spin_lock_irqsave(&cq->comp_handler_lock, flags);
+ if (cq->ibcq.comp_handler)
(*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context);
- spin_unlock_irqrestore(&cq->comp_handler_lock, flags);
- }
}
static void qedr_destroy_gsi_cq(struct qedr_dev *dev,
@@ -404,9 +398,9 @@
}
if (ether_addr_equal(udh.eth.smac_h, udh.eth.dmac_h))
- packet->tx_dest = QED_ROCE_LL2_TX_DEST_NW;
- else
packet->tx_dest = QED_ROCE_LL2_TX_DEST_LB;
+ else
+ packet->tx_dest = QED_ROCE_LL2_TX_DEST_NW;
packet->roce_mode = roce_mode;
memcpy(packet->header.vaddr, ud_header_buffer, header_size);
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 57c8de2..c7d6c9a 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -471,8 +471,6 @@
struct ib_ucontext *context, struct ib_udata *udata)
{
struct qedr_dev *dev = get_qedr_dev(ibdev);
- struct qedr_ucontext *uctx = NULL;
- struct qedr_alloc_pd_uresp uresp;
struct qedr_pd *pd;
u16 pd_id;
int rc;
@@ -489,21 +487,33 @@
if (!pd)
return ERR_PTR(-ENOMEM);
- dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id);
+ rc = dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id);
+ if (rc)
+ goto err;
- uresp.pd_id = pd_id;
pd->pd_id = pd_id;
if (udata && context) {
+ struct qedr_alloc_pd_uresp uresp;
+
+ uresp.pd_id = pd_id;
+
rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
- if (rc)
+ if (rc) {
DP_ERR(dev, "copy error pd_id=0x%x.\n", pd_id);
- uctx = get_qedr_ucontext(context);
- uctx->pd = pd;
- pd->uctx = uctx;
+ dev->ops->rdma_dealloc_pd(dev->rdma_ctx, pd_id);
+ goto err;
+ }
+
+ pd->uctx = get_qedr_ucontext(context);
+ pd->uctx->pd = pd;
}
return &pd->ibpd;
+
+err:
+ kfree(pd);
+ return ERR_PTR(rc);
}
int qedr_dealloc_pd(struct ib_pd *ibpd)
@@ -1600,7 +1610,7 @@
return ERR_PTR(-EFAULT);
}
-enum ib_qp_state qedr_get_ibqp_state(enum qed_roce_qp_state qp_state)
+static enum ib_qp_state qedr_get_ibqp_state(enum qed_roce_qp_state qp_state)
{
switch (qp_state) {
case QED_ROCE_QP_STATE_RESET:
@@ -1621,7 +1631,8 @@
return IB_QPS_ERR;
}
-enum qed_roce_qp_state qedr_get_state_from_ibqp(enum ib_qp_state qp_state)
+static enum qed_roce_qp_state qedr_get_state_from_ibqp(
+ enum ib_qp_state qp_state)
{
switch (qp_state) {
case IB_QPS_RESET:
@@ -1657,7 +1668,7 @@
int status = 0;
if (new_state == qp->state)
- return 1;
+ return 0;
switch (qp->state) {
case QED_ROCE_QP_STATE_RESET:
@@ -1733,6 +1744,14 @@
/* ERR->XXX */
switch (new_state) {
case QED_ROCE_QP_STATE_RESET:
+ if ((qp->rq.prod != qp->rq.cons) ||
+ (qp->sq.prod != qp->sq.cons)) {
+ DP_NOTICE(dev,
+ "Error->Reset with rq/sq not empty rq.prod=%x rq.cons=%x sq.prod=%x sq.cons=%x\n",
+ qp->rq.prod, qp->rq.cons, qp->sq.prod,
+ qp->sq.cons);
+ status = -EINVAL;
+ }
break;
default:
status = -EINVAL;
@@ -1865,7 +1884,6 @@
qp_params.sgid.dwords[2], qp_params.sgid.dwords[3]);
DP_DEBUG(dev, QEDR_MSG_QP, "remote_mac=[%pM]\n",
qp_params.remote_mac_addr);
-;
qp_params.mtu = qp->mtu;
qp_params.lb_indication = false;
@@ -2016,7 +2034,7 @@
qp_attr->qp_state = qedr_get_ibqp_state(params.state);
qp_attr->cur_qp_state = qedr_get_ibqp_state(params.state);
- qp_attr->path_mtu = iboe_get_mtu(params.mtu);
+ qp_attr->path_mtu = ib_mtu_int_to_enum(params.mtu);
qp_attr->path_mig_state = IB_MIG_MIGRATED;
qp_attr->rq_psn = params.rq_psn;
qp_attr->sq_psn = params.sq_psn;
@@ -2028,7 +2046,7 @@
qp_attr->cap.max_recv_wr = qp->rq.max_wr;
qp_attr->cap.max_send_sge = qp->sq.max_sges;
qp_attr->cap.max_recv_sge = qp->rq.max_sges;
- qp_attr->cap.max_inline_data = qp->max_inline_data;
+ qp_attr->cap.max_inline_data = ROCE_REQ_MAX_INLINE_DATA_SIZE;
qp_init_attr->cap = qp_attr->cap;
memcpy(&qp_attr->ah_attr.grh.dgid.raw[0], ¶ms.dgid.bytes[0],
@@ -2302,7 +2320,8 @@
return rc;
}
-struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd, int max_page_list_len)
+static struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd,
+ int max_page_list_len)
{
struct qedr_pd *pd = get_qedr_pd(ibpd);
struct qedr_dev *dev = get_qedr_dev(ibpd->device);
@@ -2704,7 +2723,7 @@
return 0;
}
-enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode)
+static enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode)
{
switch (opcode) {
case IB_WR_RDMA_WRITE:
@@ -2729,7 +2748,7 @@
}
}
-inline bool qedr_can_post_send(struct qedr_qp *qp, struct ib_send_wr *wr)
+static inline bool qedr_can_post_send(struct qedr_qp *qp, struct ib_send_wr *wr)
{
int wq_is_full, err_wr, pbl_is_full;
struct qedr_dev *dev = qp->dev;
@@ -2766,7 +2785,7 @@
return true;
}
-int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
+static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
struct ib_send_wr **bad_wr)
{
struct qedr_dev *dev = get_qedr_dev(ibqp->device);
@@ -3234,9 +3253,10 @@
IB_WC_SUCCESS, 0);
break;
case RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR:
- DP_ERR(dev,
- "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n",
- cq->icid, qp->icid);
+ if (qp->state != QED_ROCE_QP_STATE_ERR)
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
cnt = process_req(dev, qp, cq, num_entries, wc, req->sq_cons,
IB_WC_WR_FLUSH_ERR, 1);
break;
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 231a1ce..bd8fbd3 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -1029,7 +1029,7 @@
if (ret) {
dev_err(&pdev->dev, "failed to allocate interrupts\n");
ret = -ENOMEM;
- goto err_netdevice;
+ goto err_free_cq_ring;
}
/* Allocate UAR table. */
@@ -1092,8 +1092,6 @@
err_free_intrs:
pvrdma_free_irq(dev);
pvrdma_disable_msi_all(dev);
-err_netdevice:
- unregister_netdevice_notifier(&dev->nb_netdev);
err_free_cq_ring:
pvrdma_page_dir_cleanup(dev, &dev->cq_pdir);
err_free_async_ring:
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
index 5489137..c2aa526 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
@@ -306,7 +306,7 @@
union pvrdma_cmd_resp rsp;
struct pvrdma_cmd_create_uc *cmd = &req.create_uc;
struct pvrdma_cmd_create_uc_resp *resp = &rsp.create_uc_resp;
- struct pvrdma_alloc_ucontext_resp uresp;
+ struct pvrdma_alloc_ucontext_resp uresp = {0};
int ret;
void *ptr;
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index d0faca2..86a6585 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -59,9 +59,11 @@
case RXE_MEM_TYPE_MR:
case RXE_MEM_TYPE_FMR:
- return ((iova < mem->iova) ||
- ((iova + length) > (mem->iova + mem->length))) ?
- -EFAULT : 0;
+ if (iova < mem->iova ||
+ length > mem->length ||
+ iova > mem->iova + mem->length - length)
+ return -EFAULT;
+ return 0;
default:
return -EFAULT;
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 342e781..4abdeb3 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -555,7 +555,7 @@
}
spin_lock_bh(&dev_list_lock);
- list_add_tail(&rxe_dev_list, &rxe->list);
+ list_add_tail(&rxe->list, &rxe_dev_list);
spin_unlock_bh(&dev_list_lock);
return rxe;
}
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 486d576..44b2108 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -813,8 +813,7 @@
del_timer_sync(&qp->rnr_nak_timer);
rxe_cleanup_task(&qp->req.task);
- if (qp_type(qp) == IB_QPT_RC)
- rxe_cleanup_task(&qp->comp.task);
+ rxe_cleanup_task(&qp->comp.task);
/* flush out any receive wr's or pending requests */
__rxe_do_task(&qp->req.task);
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 3435eff..5bcf073 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -479,7 +479,7 @@
goto err2;
}
- resid = mtu;
+ qp->resp.resid = mtu;
} else {
if (pktlen != resid) {
state = RESPST_ERR_LENGTH;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 9104e6b..e71af71 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -651,13 +651,6 @@
SHOST_DIX_GUARD_CRC);
}
- /*
- * Limit the sg_tablesize and max_sectors based on the device
- * max fastreg page list length.
- */
- shost->sg_tablesize = min_t(unsigned short, shost->sg_tablesize,
- ib_conn->device->ib_device->attrs.max_fast_reg_page_list_len);
-
if (iscsi_host_add(shost,
ib_conn->device->ib_device->dma_device)) {
mutex_unlock(&iser_conn->state_mutex);
@@ -679,6 +672,10 @@
max_fr_sectors = ((shost->sg_tablesize - 1) * PAGE_SIZE) >> 9;
shost->max_sectors = min(iser_max_sectors, max_fr_sectors);
+ iser_dbg("iser_conn %p, sg_tablesize %u, max_sectors %u\n",
+ iser_conn, shost->sg_tablesize,
+ shost->max_sectors);
+
if (cmds_max > max_cmds) {
iser_info("cmds_max changed from %u to %u\n",
cmds_max, max_cmds);
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 0be6a7c..9d0b22a 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -496,7 +496,6 @@
* @rx_descs: rx buffers array (cyclic buffer)
* @num_rx_descs: number of rx descriptors
* @scsi_sg_tablesize: scsi host sg_tablesize
- * @scsi_max_sectors: scsi host max sectors
*/
struct iser_conn {
struct ib_conn ib_conn;
@@ -519,7 +518,6 @@
struct iser_rx_desc *rx_descs;
u32 num_rx_descs;
unsigned short scsi_sg_tablesize;
- unsigned int scsi_max_sectors;
bool snd_w_inv;
};
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 8ae7a3b..6a9d1cb 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -707,18 +707,7 @@
sup_sg_tablesize = min_t(unsigned, ISCSI_ISER_MAX_SG_TABLESIZE,
device->ib_device->attrs.max_fast_reg_page_list_len);
- if (sg_tablesize > sup_sg_tablesize) {
- sg_tablesize = sup_sg_tablesize;
- iser_conn->scsi_max_sectors = sg_tablesize * SIZE_4K / 512;
- } else {
- iser_conn->scsi_max_sectors = max_sectors;
- }
-
- iser_conn->scsi_sg_tablesize = sg_tablesize;
-
- iser_dbg("iser_conn %p, sg_tablesize %u, max_sectors %u\n",
- iser_conn, iser_conn->scsi_sg_tablesize,
- iser_conn->scsi_max_sectors);
+ iser_conn->scsi_sg_tablesize = min(sg_tablesize, sup_sg_tablesize);
}
/**
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 8ddc071..79bf484 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -371,6 +371,7 @@
struct srp_fr_desc *d;
struct ib_mr *mr;
int i, ret = -EINVAL;
+ enum ib_mr_type mr_type;
if (pool_size <= 0)
goto err;
@@ -384,9 +385,13 @@
spin_lock_init(&pool->lock);
INIT_LIST_HEAD(&pool->free_list);
+ if (device->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG)
+ mr_type = IB_MR_TYPE_SG_GAPS;
+ else
+ mr_type = IB_MR_TYPE_MEM_REG;
+
for (i = 0, d = &pool->desc[0]; i < pool->size; i++, d++) {
- mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG,
- max_page_list_len);
+ mr = ib_alloc_mr(pd, mr_type, max_page_list_len);
if (IS_ERR(mr)) {
ret = PTR_ERR(mr);
if (ret == -ENOMEM)
@@ -3694,6 +3699,12 @@
indirect_sg_entries = cmd_sg_entries;
}
+ if (indirect_sg_entries > SG_MAX_SEGMENTS) {
+ pr_warn("Clamping indirect_sg_entries to %u\n",
+ SG_MAX_SEGMENTS);
+ indirect_sg_entries = SG_MAX_SEGMENTS;
+ }
+
srp_remove_wq = create_workqueue("srp_remove");
if (!srp_remove_wq) {
ret = -ENOMEM;
diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c
index f3135ae..abd18f3 100644
--- a/drivers/input/joydev.c
+++ b/drivers/input/joydev.c
@@ -22,7 +22,6 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/mm.h>
-#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/poll.h>
#include <linux/init.h>
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 6d94996..c7d5b2b 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1377,6 +1377,12 @@
input_dev->name = xpad->name;
input_dev->phys = xpad->phys;
usb_to_input_id(xpad->udev, &input_dev->id);
+
+ if (xpad->xtype == XTYPE_XBOX360W) {
+ /* x360w controllers and the receiver have different ids */
+ input_dev->id.product = 0x02a1;
+ }
+
input_dev->dev.parent = &xpad->intf->dev;
input_set_drvdata(input_dev, xpad);
diff --git a/drivers/input/misc/adxl34x-i2c.c b/drivers/input/misc/adxl34x-i2c.c
index a8b0a2e..7fed92f 100644
--- a/drivers/input/misc/adxl34x-i2c.c
+++ b/drivers/input/misc/adxl34x-i2c.c
@@ -136,7 +136,6 @@
MODULE_DEVICE_TABLE(i2c, adxl34x_id);
-#ifdef CONFIG_OF
static const struct of_device_id adxl34x_of_id[] = {
/*
* The ADXL346 is backward-compatible with the ADXL345. Differences are
@@ -153,13 +152,12 @@
};
MODULE_DEVICE_TABLE(of, adxl34x_of_id);
-#endif
static struct i2c_driver adxl34x_driver = {
.driver = {
.name = "adxl34x",
.pm = &adxl34x_i2c_pm,
- .of_match_table = of_match_ptr(adxl34x_of_id),
+ .of_match_table = adxl34x_of_id,
},
.probe = adxl34x_i2c_probe,
.remove = adxl34x_i2c_remove,
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 92595b9..022be0e 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -263,13 +263,21 @@
return -EINVAL;
}
- if (test_bit(ABS_MT_SLOT, dev->absbit)) {
- nslot = input_abs_get_max(dev, ABS_MT_SLOT) + 1;
- error = input_mt_init_slots(dev, nslot, 0);
- if (error)
+ if (test_bit(EV_ABS, dev->evbit)) {
+ input_alloc_absinfo(dev);
+ if (!dev->absinfo) {
+ error = -EINVAL;
goto fail1;
- } else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) {
- input_set_events_per_packet(dev, 60);
+ }
+
+ if (test_bit(ABS_MT_SLOT, dev->absbit)) {
+ nslot = input_abs_get_max(dev, ABS_MT_SLOT) + 1;
+ error = input_mt_init_slots(dev, nslot, 0);
+ if (error)
+ goto fail1;
+ } else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) {
+ input_set_events_per_packet(dev, 60);
+ }
}
if (test_bit(EV_FF, dev->evbit) && !udev->ff_effects_max) {
diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h
index cde6f4b..6d279aa 100644
--- a/drivers/input/mouse/alps.h
+++ b/drivers/input/mouse/alps.h
@@ -114,7 +114,7 @@
(_b[1] & 0x7F) \
)
-#define SS4_TS_Y_V2(_b) (s8)( \
+#define SS4_TS_Y_V2(_b) -(s8)( \
((_b[3] & 0x01) << 7) | \
(_b[2] & 0x7F) \
)
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index fa598f7..1e1d0ad 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -1231,6 +1231,7 @@
{ "ELAN0000", 0 },
{ "ELAN0100", 0 },
{ "ELAN0600", 0 },
+ { "ELAN0605", 0 },
{ "ELAN1000", 0 },
{ }
};
diff --git a/drivers/input/mouse/synaptics_i2c.c b/drivers/input/mouse/synaptics_i2c.c
index aa7c5da..cb2bf20 100644
--- a/drivers/input/mouse/synaptics_i2c.c
+++ b/drivers/input/mouse/synaptics_i2c.c
@@ -29,7 +29,7 @@
* after soft reset, we should wait for 1 ms
* before the device becomes operational
*/
-#define SOFT_RESET_DELAY_MS 3
+#define SOFT_RESET_DELAY_US 3000
/* and after hard reset, we should wait for max 500ms */
#define HARD_RESET_DELAY_MS 500
@@ -311,7 +311,7 @@
if (ret) {
dev_err(&client->dev, "Unable to reset device\n");
} else {
- msleep(SOFT_RESET_DELAY_MS);
+ usleep_range(SOFT_RESET_DELAY_US, SOFT_RESET_DELAY_US + 100);
ret = synaptics_i2c_config(client);
if (ret)
dev_err(&client->dev, "Unable to config device\n");
diff --git a/drivers/input/rmi4/Kconfig b/drivers/input/rmi4/Kconfig
index 30cc627..bb7762b 100644
--- a/drivers/input/rmi4/Kconfig
+++ b/drivers/input/rmi4/Kconfig
@@ -41,13 +41,20 @@
config RMI4_F03
bool "RMI4 Function 03 (PS2 Guest)"
- depends on RMI4_CORE && SERIO
+ depends on RMI4_CORE
help
Say Y here if you want to add support for RMI4 function 03.
Function 03 provides PS2 guest support for RMI4 devices. This
includes support for TrackPoints on TouchPads.
+config RMI4_F03_SERIO
+ tristate
+ depends on RMI4_CORE
+ depends on RMI4_F03
+ default RMI4_CORE
+ select SERIO
+
config RMI4_2D_SENSOR
bool
depends on RMI4_CORE
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 11447ab..bf5c36e 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -901,7 +901,7 @@
data->enabled = true;
if (clear_wake && device_may_wakeup(rmi_dev->xport->dev)) {
retval = disable_irq_wake(irq);
- if (!retval)
+ if (retval)
dev_warn(&rmi_dev->dev,
"Failed to disable irq for wake: %d\n",
retval);
@@ -936,7 +936,7 @@
disable_irq(irq);
if (enable_wake && device_may_wakeup(rmi_dev->xport->dev)) {
retval = enable_irq_wake(irq);
- if (!retval)
+ if (retval)
dev_warn(&rmi_dev->dev,
"Failed to enable irq for wake: %d\n",
retval);
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 77551f5..a761877 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -211,6 +211,12 @@
DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"),
},
},
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "C15B"),
+ },
+ },
{ }
};
diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c
index 02aec28..3e6003d 100644
--- a/drivers/input/touchscreen/elants_i2c.c
+++ b/drivers/input/touchscreen/elants_i2c.c
@@ -914,9 +914,9 @@
case QUEUE_HEADER_NORMAL:
report_count = ts->buf[FW_HDR_COUNT];
- if (report_count > 3) {
+ if (report_count == 0 || report_count > 3) {
dev_err(&client->dev,
- "too large report count: %*ph\n",
+ "bad report count: %*ph\n",
HEADER_SIZE, ts->buf);
break;
}
diff --git a/drivers/input/touchscreen/wm97xx-core.c b/drivers/input/touchscreen/wm97xx-core.c
index 83cf113..c9d1c91 100644
--- a/drivers/input/touchscreen/wm97xx-core.c
+++ b/drivers/input/touchscreen/wm97xx-core.c
@@ -682,7 +682,7 @@
}
platform_set_drvdata(wm->battery_dev, wm);
wm->battery_dev->dev.parent = dev;
- wm->battery_dev->dev.platform_data = pdata->batt_pdata;
+ wm->battery_dev->dev.platform_data = pdata ? pdata->batt_pdata : NULL;
ret = platform_device_add(wm->battery_dev);
if (ret < 0)
goto batt_reg_err;
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index ae96731..125528f 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -283,3 +283,12 @@
config STM32_EXTI
bool
select IRQ_DOMAIN
+
+config QCOM_IRQ_COMBINER
+ bool "QCOM IRQ combiner support"
+ depends on ARCH_QCOM && ACPI
+ select IRQ_DOMAIN
+ select IRQ_DOMAIN_HIERARCHY
+ help
+ Say yes here to add support for the IRQ combiner devices embedded
+ in Qualcomm Technologies chips.
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 0e55d94..152bc40 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -6,6 +6,7 @@
obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2835.o
obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2836.o
obj-$(CONFIG_ARCH_EXYNOS) += exynos-combiner.o
+obj-$(CONFIG_ARCH_GEMINI) += irq-gemini.o
obj-$(CONFIG_ARCH_HIP04) += irq-hip04.o
obj-$(CONFIG_ARCH_LPC32XX) += irq-lpc32xx.o
obj-$(CONFIG_ARCH_MMP) += irq-mmp.o
@@ -75,3 +76,4 @@
obj-$(CONFIG_EZNPS_GIC) += irq-eznps.o
obj-$(CONFIG_ARCH_ASPEED) += irq-aspeed-vic.o
obj-$(CONFIG_STM32_EXTI) += irq-stm32-exti.o
+obj-$(CONFIG_QCOM_IRQ_COMBINER) += qcom-irq-combiner.o
diff --git a/drivers/irqchip/irq-gemini.c b/drivers/irqchip/irq-gemini.c
new file mode 100644
index 0000000..495224c
--- /dev/null
+++ b/drivers/irqchip/irq-gemini.c
@@ -0,0 +1,185 @@
+/*
+ * irqchip for the Cortina Systems Gemini Copyright (C) 2017 Linus
+ * Walleij <linus.walleij@linaro.org>
+ *
+ * Based on arch/arm/mach-gemini/irq.c
+ * Copyright (C) 2001-2006 Storlink, Corp.
+ * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
+ */
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/versatile-fpga.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/cpu.h>
+
+#include <asm/exception.h>
+#include <asm/mach/irq.h>
+
+#define GEMINI_NUM_IRQS 32
+
+#define GEMINI_IRQ_SOURCE(base_addr) (base_addr + 0x00)
+#define GEMINI_IRQ_MASK(base_addr) (base_addr + 0x04)
+#define GEMINI_IRQ_CLEAR(base_addr) (base_addr + 0x08)
+#define GEMINI_IRQ_MODE(base_addr) (base_addr + 0x0C)
+#define GEMINI_IRQ_POLARITY(base_addr) (base_addr + 0x10)
+#define GEMINI_IRQ_STATUS(base_addr) (base_addr + 0x14)
+#define GEMINI_FIQ_SOURCE(base_addr) (base_addr + 0x20)
+#define GEMINI_FIQ_MASK(base_addr) (base_addr + 0x24)
+#define GEMINI_FIQ_CLEAR(base_addr) (base_addr + 0x28)
+#define GEMINI_FIQ_MODE(base_addr) (base_addr + 0x2C)
+#define GEMINI_FIQ_POLARITY(base_addr) (base_addr + 0x30)
+#define GEMINI_FIQ_STATUS(base_addr) (base_addr + 0x34)
+
+/**
+ * struct gemini_irq_data - irq data container for the Gemini IRQ controller
+ * @base: memory offset in virtual memory
+ * @chip: chip container for this instance
+ * @domain: IRQ domain for this instance
+ */
+struct gemini_irq_data {
+ void __iomem *base;
+ struct irq_chip chip;
+ struct irq_domain *domain;
+};
+
+static void gemini_irq_mask(struct irq_data *d)
+{
+ struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
+ unsigned int mask;
+
+ mask = readl(GEMINI_IRQ_MASK(g->base));
+ mask &= ~BIT(irqd_to_hwirq(d));
+ writel(mask, GEMINI_IRQ_MASK(g->base));
+}
+
+static void gemini_irq_unmask(struct irq_data *d)
+{
+ struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
+ unsigned int mask;
+
+ mask = readl(GEMINI_IRQ_MASK(g->base));
+ mask |= BIT(irqd_to_hwirq(d));
+ writel(mask, GEMINI_IRQ_MASK(g->base));
+}
+
+static void gemini_irq_ack(struct irq_data *d)
+{
+ struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
+
+ writel(BIT(irqd_to_hwirq(d)), GEMINI_IRQ_CLEAR(g->base));
+}
+
+static int gemini_irq_set_type(struct irq_data *d, unsigned int trigger)
+{
+ struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
+ int offset = irqd_to_hwirq(d);
+ u32 mode, polarity;
+
+ mode = readl(GEMINI_IRQ_MODE(g->base));
+ polarity = readl(GEMINI_IRQ_POLARITY(g->base));
+
+ if (trigger & (IRQ_TYPE_LEVEL_HIGH)) {
+ irq_set_handler_locked(d, handle_level_irq);
+ /* Disable edge detection */
+ mode &= ~BIT(offset);
+ polarity &= ~BIT(offset);
+ } else if (trigger & IRQ_TYPE_EDGE_RISING) {
+ irq_set_handler_locked(d, handle_edge_irq);
+ mode |= BIT(offset);
+ polarity |= BIT(offset);
+ } else if (trigger & IRQ_TYPE_EDGE_FALLING) {
+ irq_set_handler_locked(d, handle_edge_irq);
+ mode |= BIT(offset);
+ polarity &= ~BIT(offset);
+ } else {
+ irq_set_handler_locked(d, handle_bad_irq);
+ pr_warn("GEMINI IRQ: no supported trigger selected for line %d\n",
+ offset);
+ }
+
+ writel(mode, GEMINI_IRQ_MODE(g->base));
+ writel(polarity, GEMINI_IRQ_POLARITY(g->base));
+
+ return 0;
+}
+
+static struct irq_chip gemini_irq_chip = {
+ .name = "GEMINI",
+ .irq_ack = gemini_irq_ack,
+ .irq_mask = gemini_irq_mask,
+ .irq_unmask = gemini_irq_unmask,
+ .irq_set_type = gemini_irq_set_type,
+};
+
+/* Local static for the IRQ entry call */
+static struct gemini_irq_data girq;
+
+asmlinkage void __exception_irq_entry gemini_irqchip_handle_irq(struct pt_regs *regs)
+{
+ struct gemini_irq_data *g = &girq;
+ int irq;
+ u32 status;
+
+ while ((status = readl(GEMINI_IRQ_STATUS(g->base)))) {
+ irq = ffs(status) - 1;
+ handle_domain_irq(g->domain, irq, regs);
+ }
+}
+
+static int gemini_irqdomain_map(struct irq_domain *d, unsigned int irq,
+ irq_hw_number_t hwirq)
+{
+ struct gemini_irq_data *g = d->host_data;
+
+ irq_set_chip_data(irq, g);
+ /* All IRQs should set up their type, flags as bad by default */
+ irq_set_chip_and_handler(irq, &gemini_irq_chip, handle_bad_irq);
+ irq_set_probe(irq);
+
+ return 0;
+}
+
+static void gemini_irqdomain_unmap(struct irq_domain *d, unsigned int irq)
+{
+ irq_set_chip_and_handler(irq, NULL, NULL);
+ irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops gemini_irqdomain_ops = {
+ .map = gemini_irqdomain_map,
+ .unmap = gemini_irqdomain_unmap,
+ .xlate = irq_domain_xlate_onetwocell,
+};
+
+int __init gemini_of_init_irq(struct device_node *node,
+ struct device_node *parent)
+{
+ struct gemini_irq_data *g = &girq;
+
+ /*
+ * Disable the idle handler by default since it is buggy
+ * For more info see arch/arm/mach-gemini/idle.c
+ */
+ cpu_idle_poll_ctrl(true);
+
+ g->base = of_iomap(node, 0);
+ WARN(!g->base, "unable to map gemini irq registers\n");
+
+ /* Disable all interrupts */
+ writel(0, GEMINI_IRQ_MASK(g->base));
+ writel(0, GEMINI_FIQ_MASK(g->base));
+
+ g->domain = irq_domain_add_simple(node, GEMINI_NUM_IRQS, 0,
+ &gemini_irqdomain_ops, g);
+ set_handle_irq(gemini_irqchip_handle_irq);
+
+ return 0;
+}
+IRQCHIP_DECLARE(gemini, "cortina,gemini-interrupt-controller",
+ gemini_of_init_irq);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 69b040f..4a895c6 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -161,7 +161,7 @@
struct its_device *dev;
u32 phys_id;
u32 event_id;
- } its_mapvi_cmd;
+ } its_mapti_cmd;
struct {
struct its_device *dev;
@@ -193,58 +193,56 @@
typedef struct its_collection *(*its_cmd_builder_t)(struct its_cmd_block *,
struct its_cmd_desc *);
+static void its_mask_encode(u64 *raw_cmd, u64 val, int h, int l)
+{
+ u64 mask = GENMASK_ULL(h, l);
+ *raw_cmd &= ~mask;
+ *raw_cmd |= (val << l) & mask;
+}
+
static void its_encode_cmd(struct its_cmd_block *cmd, u8 cmd_nr)
{
- cmd->raw_cmd[0] &= ~0xffULL;
- cmd->raw_cmd[0] |= cmd_nr;
+ its_mask_encode(&cmd->raw_cmd[0], cmd_nr, 7, 0);
}
static void its_encode_devid(struct its_cmd_block *cmd, u32 devid)
{
- cmd->raw_cmd[0] &= BIT_ULL(32) - 1;
- cmd->raw_cmd[0] |= ((u64)devid) << 32;
+ its_mask_encode(&cmd->raw_cmd[0], devid, 63, 32);
}
static void its_encode_event_id(struct its_cmd_block *cmd, u32 id)
{
- cmd->raw_cmd[1] &= ~0xffffffffULL;
- cmd->raw_cmd[1] |= id;
+ its_mask_encode(&cmd->raw_cmd[1], id, 31, 0);
}
static void its_encode_phys_id(struct its_cmd_block *cmd, u32 phys_id)
{
- cmd->raw_cmd[1] &= 0xffffffffULL;
- cmd->raw_cmd[1] |= ((u64)phys_id) << 32;
+ its_mask_encode(&cmd->raw_cmd[1], phys_id, 63, 32);
}
static void its_encode_size(struct its_cmd_block *cmd, u8 size)
{
- cmd->raw_cmd[1] &= ~0x1fULL;
- cmd->raw_cmd[1] |= size & 0x1f;
+ its_mask_encode(&cmd->raw_cmd[1], size, 4, 0);
}
static void its_encode_itt(struct its_cmd_block *cmd, u64 itt_addr)
{
- cmd->raw_cmd[2] &= ~0xffffffffffffULL;
- cmd->raw_cmd[2] |= itt_addr & 0xffffffffff00ULL;
+ its_mask_encode(&cmd->raw_cmd[2], itt_addr >> 8, 50, 8);
}
static void its_encode_valid(struct its_cmd_block *cmd, int valid)
{
- cmd->raw_cmd[2] &= ~(1ULL << 63);
- cmd->raw_cmd[2] |= ((u64)!!valid) << 63;
+ its_mask_encode(&cmd->raw_cmd[2], !!valid, 63, 63);
}
static void its_encode_target(struct its_cmd_block *cmd, u64 target_addr)
{
- cmd->raw_cmd[2] &= ~(0xffffffffULL << 16);
- cmd->raw_cmd[2] |= (target_addr & (0xffffffffULL << 16));
+ its_mask_encode(&cmd->raw_cmd[2], target_addr >> 16, 50, 16);
}
static void its_encode_collection(struct its_cmd_block *cmd, u16 col)
{
- cmd->raw_cmd[2] &= ~0xffffULL;
- cmd->raw_cmd[2] |= col;
+ its_mask_encode(&cmd->raw_cmd[2], col, 15, 0);
}
static inline void its_fixup_cmd(struct its_cmd_block *cmd)
@@ -289,18 +287,18 @@
return desc->its_mapc_cmd.col;
}
-static struct its_collection *its_build_mapvi_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_mapti_cmd(struct its_cmd_block *cmd,
struct its_cmd_desc *desc)
{
struct its_collection *col;
- col = dev_event_to_col(desc->its_mapvi_cmd.dev,
- desc->its_mapvi_cmd.event_id);
+ col = dev_event_to_col(desc->its_mapti_cmd.dev,
+ desc->its_mapti_cmd.event_id);
- its_encode_cmd(cmd, GITS_CMD_MAPVI);
- its_encode_devid(cmd, desc->its_mapvi_cmd.dev->device_id);
- its_encode_event_id(cmd, desc->its_mapvi_cmd.event_id);
- its_encode_phys_id(cmd, desc->its_mapvi_cmd.phys_id);
+ its_encode_cmd(cmd, GITS_CMD_MAPTI);
+ its_encode_devid(cmd, desc->its_mapti_cmd.dev->device_id);
+ its_encode_event_id(cmd, desc->its_mapti_cmd.event_id);
+ its_encode_phys_id(cmd, desc->its_mapti_cmd.phys_id);
its_encode_collection(cmd, col->col_id);
its_fixup_cmd(cmd);
@@ -413,6 +411,12 @@
if (its->cmd_write == (its->cmd_base + ITS_CMD_QUEUE_NR_ENTRIES))
its->cmd_write = its->cmd_base;
+ /* Clear command */
+ cmd->raw_cmd[0] = 0;
+ cmd->raw_cmd[1] = 0;
+ cmd->raw_cmd[2] = 0;
+ cmd->raw_cmd[3] = 0;
+
return cmd;
}
@@ -531,15 +535,15 @@
its_send_single_command(its, its_build_mapc_cmd, &desc);
}
-static void its_send_mapvi(struct its_device *dev, u32 irq_id, u32 id)
+static void its_send_mapti(struct its_device *dev, u32 irq_id, u32 id)
{
struct its_cmd_desc desc;
- desc.its_mapvi_cmd.dev = dev;
- desc.its_mapvi_cmd.phys_id = irq_id;
- desc.its_mapvi_cmd.event_id = id;
+ desc.its_mapti_cmd.dev = dev;
+ desc.its_mapti_cmd.phys_id = irq_id;
+ desc.its_mapti_cmd.event_id = id;
- its_send_single_command(dev->its, its_build_mapvi_cmd, &desc);
+ its_send_single_command(dev->its, its_build_mapti_cmd, &desc);
}
static void its_send_movi(struct its_device *dev,
@@ -824,7 +828,7 @@
static const char *its_base_type_string[] = {
[GITS_BASER_TYPE_DEVICE] = "Devices",
[GITS_BASER_TYPE_VCPU] = "Virtual CPUs",
- [GITS_BASER_TYPE_CPU] = "Physical CPUs",
+ [GITS_BASER_TYPE_RESERVED3] = "Reserved (3)",
[GITS_BASER_TYPE_COLLECTION] = "Interrupt Collections",
[GITS_BASER_TYPE_RESERVED5] = "Reserved (5)",
[GITS_BASER_TYPE_RESERVED6] = "Reserved (6)",
@@ -960,7 +964,7 @@
u32 psz, u32 *order)
{
u64 esz = GITS_BASER_ENTRY_SIZE(its_read_baser(its, baser));
- u64 val = GITS_BASER_InnerShareable | GITS_BASER_WaWb;
+ u64 val = GITS_BASER_InnerShareable | GITS_BASER_RaWaWb;
u32 ids = its->device_ids;
u32 new_order = *order;
bool indirect = false;
@@ -1025,7 +1029,7 @@
u64 typer = gic_read_typer(its->base + GITS_TYPER);
u32 ids = GITS_TYPER_DEVBITS(typer);
u64 shr = GITS_BASER_InnerShareable;
- u64 cache = GITS_BASER_WaWb;
+ u64 cache = GITS_BASER_RaWaWb;
u32 psz = SZ_64K;
int err, i;
@@ -1122,7 +1126,7 @@
/* set PROPBASE */
val = (page_to_phys(gic_rdists->prop_page) |
GICR_PROPBASER_InnerShareable |
- GICR_PROPBASER_WaWb |
+ GICR_PROPBASER_RaWaWb |
((LPI_NRBITS - 1) & GICR_PROPBASER_IDBITS_MASK));
gicr_write_propbaser(val, rbase + GICR_PROPBASER);
@@ -1147,7 +1151,7 @@
/* set PENDBASE */
val = (page_to_phys(pend_page) |
GICR_PENDBASER_InnerShareable |
- GICR_PENDBASER_WaWb);
+ GICR_PENDBASER_RaWaWb);
gicr_write_pendbaser(val, rbase + GICR_PENDBASER);
tmp = gicr_read_pendbaser(rbase + GICR_PENDBASER);
@@ -1498,7 +1502,7 @@
its_dev->event_map.col_map[event] = cpumask_first(cpu_mask);
/* Map the GIC IRQ and event to the device */
- its_send_mapvi(its_dev, d->hwirq, event);
+ its_send_mapti(its_dev, d->hwirq, event);
}
static void its_irq_domain_deactivate(struct irq_domain *domain,
@@ -1693,7 +1697,8 @@
its->ite_size = ((gic_read_typer(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
its->numa_node = numa_node;
- its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
+ its->cmd_base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+ get_order(ITS_CMD_QUEUE_SZ));
if (!its->cmd_base) {
err = -ENOMEM;
goto out_free_its;
@@ -1711,7 +1716,7 @@
goto out_free_tables;
baser = (virt_to_phys(its->cmd_base) |
- GITS_CBASER_WaWb |
+ GITS_CBASER_RaWaWb |
GITS_CBASER_InnerShareable |
(ITS_CMD_QUEUE_SZ / SZ_4K - 1) |
GITS_CBASER_VALID);
@@ -1751,7 +1756,7 @@
out_free_tables:
its_free_tables(its);
out_free_cmd:
- kfree(its->cmd_base);
+ free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
out_free_its:
kfree(its);
out_unmap:
diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c
index 54a5e87..efbcf84 100644
--- a/drivers/irqchip/irq-keystone.c
+++ b/drivers/irqchip/irq-keystone.c
@@ -19,9 +19,9 @@
#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
+#include <linux/interrupt.h>
#include <linux/irqdomain.h>
#include <linux/irqchip.h>
-#include <linux/irqchip/chained_irq.h>
#include <linux/of.h>
#include <linux/of_platform.h>
#include <linux/mfd/syscon.h>
@@ -39,6 +39,7 @@
struct irq_domain *irqd;
struct regmap *devctrl_regs;
u32 devctrl_offset;
+ raw_spinlock_t wa_lock;
};
static inline u32 keystone_irq_readl(struct keystone_irq_device *kirq)
@@ -83,17 +84,15 @@
/* nothing to do here */
}
-static void keystone_irq_handler(struct irq_desc *desc)
+static irqreturn_t keystone_irq_handler(int irq, void *keystone_irq)
{
- unsigned int irq = irq_desc_get_irq(desc);
- struct keystone_irq_device *kirq = irq_desc_get_handler_data(desc);
+ struct keystone_irq_device *kirq = keystone_irq;
+ unsigned long wa_lock_flags;
unsigned long pending;
int src, virq;
dev_dbg(kirq->dev, "start irq %d\n", irq);
- chained_irq_enter(irq_desc_get_chip(desc), desc);
-
pending = keystone_irq_readl(kirq);
keystone_irq_writel(kirq, pending);
@@ -111,13 +110,15 @@
if (!virq)
dev_warn(kirq->dev, "spurious irq detected hwirq %d, virq %d\n",
src, virq);
+ raw_spin_lock_irqsave(&kirq->wa_lock, wa_lock_flags);
generic_handle_irq(virq);
+ raw_spin_unlock_irqrestore(&kirq->wa_lock,
+ wa_lock_flags);
}
}
- chained_irq_exit(irq_desc_get_chip(desc), desc);
-
dev_dbg(kirq->dev, "end irq %d\n", irq);
+ return IRQ_HANDLED;
}
static int keystone_irq_map(struct irq_domain *h, unsigned int virq,
@@ -182,9 +183,16 @@
return -ENODEV;
}
+ raw_spin_lock_init(&kirq->wa_lock);
+
platform_set_drvdata(pdev, kirq);
- irq_set_chained_handler_and_data(kirq->irq, keystone_irq_handler, kirq);
+ ret = request_irq(kirq->irq, keystone_irq_handler,
+ 0, dev_name(dev), kirq);
+ if (ret) {
+ irq_domain_remove(kirq->irqd);
+ return ret;
+ }
/* clear all source bits */
keystone_irq_writel(kirq, ~0x0);
@@ -199,6 +207,8 @@
struct keystone_irq_device *kirq = platform_get_drvdata(pdev);
int hwirq;
+ free_irq(kirq->irq, kirq);
+
for (hwirq = 0; hwirq < KEYSTONE_N_IRQ; hwirq++)
irq_dispose_mapping(irq_find_mapping(kirq->irqd, hwirq));
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index c01c09e..11d12bc 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -968,6 +968,34 @@
.match = gic_ipi_domain_match,
};
+static void __init gic_map_single_int(struct device_node *node,
+ unsigned int irq)
+{
+ unsigned int linux_irq;
+ struct irq_fwspec local_int_fwspec = {
+ .fwnode = &node->fwnode,
+ .param_count = 3,
+ .param = {
+ [0] = GIC_LOCAL,
+ [1] = irq,
+ [2] = IRQ_TYPE_NONE,
+ },
+ };
+
+ if (!gic_local_irq_is_routable(irq))
+ return;
+
+ linux_irq = irq_create_fwspec_mapping(&local_int_fwspec);
+ WARN_ON(!linux_irq);
+}
+
+static void __init gic_map_interrupts(struct device_node *node)
+{
+ gic_map_single_int(node, GIC_LOCAL_INT_TIMER);
+ gic_map_single_int(node, GIC_LOCAL_INT_PERFCTR);
+ gic_map_single_int(node, GIC_LOCAL_INT_FDC);
+}
+
static void __init __gic_init(unsigned long gic_base_addr,
unsigned long gic_addrspace_size,
unsigned int cpu_vec, unsigned int irqbase,
@@ -1067,6 +1095,7 @@
}
gic_basic_init();
+ gic_map_interrupts(node);
}
void __init gic_init(unsigned long gic_base_addr,
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index 1730470..05fa9f7 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -131,12 +131,16 @@
.irq_ack = icoll_ack_irq,
.irq_mask = icoll_mask_irq,
.irq_unmask = icoll_unmask_irq,
+ .flags = IRQCHIP_MASK_ON_SUSPEND |
+ IRQCHIP_SKIP_SET_WAKE,
};
static struct irq_chip asm9260_icoll_chip = {
.irq_ack = icoll_ack_irq,
.irq_mask = asm9260_mask_irq,
.irq_unmask = asm9260_unmask_irq,
+ .flags = IRQCHIP_MASK_ON_SUSPEND |
+ IRQCHIP_SKIP_SET_WAKE,
};
asmlinkage void __exception_irq_entry icoll_handle_irq(struct pt_regs *regs)
diff --git a/drivers/irqchip/qcom-irq-combiner.c b/drivers/irqchip/qcom-irq-combiner.c
new file mode 100644
index 0000000..2265586
--- /dev/null
+++ b/drivers/irqchip/qcom-irq-combiner.c
@@ -0,0 +1,296 @@
+/* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * Driver for interrupt combiners in the Top-level Control and Status
+ * Registers (TCSR) hardware block in Qualcomm Technologies chips.
+ * An interrupt combiner in this block combines a set of interrupts by
+ * OR'ing the individual interrupt signals into a summary interrupt
+ * signal routed to a parent interrupt controller, and provides read-
+ * only, 32-bit registers to query the status of individual interrupts.
+ * The status bit for IRQ n is bit (n % 32) within register (n / 32)
+ * of the given combiner. Thus, each combiner can be described as a set
+ * of register offsets and the number of IRQs managed.
+ */
+
+#define pr_fmt(fmt) "QCOM80B1:" fmt
+
+#include <linux/acpi.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/platform_device.h>
+
+#define REG_SIZE 32
+
+struct combiner_reg {
+ void __iomem *addr;
+ unsigned long enabled;
+};
+
+struct combiner {
+ struct irq_domain *domain;
+ int parent_irq;
+ u32 nirqs;
+ u32 nregs;
+ struct combiner_reg regs[0];
+};
+
+static inline int irq_nr(u32 reg, u32 bit)
+{
+ return reg * REG_SIZE + bit;
+}
+
+/*
+ * Handler for the cascaded IRQ.
+ */
+static void combiner_handle_irq(struct irq_desc *desc)
+{
+ struct combiner *combiner = irq_desc_get_handler_data(desc);
+ struct irq_chip *chip = irq_desc_get_chip(desc);
+ u32 reg;
+
+ chained_irq_enter(chip, desc);
+
+ for (reg = 0; reg < combiner->nregs; reg++) {
+ int virq;
+ int hwirq;
+ u32 bit;
+ u32 status;
+
+ bit = readl_relaxed(combiner->regs[reg].addr);
+ status = bit & combiner->regs[reg].enabled;
+ if (!status)
+ pr_warn_ratelimited("Unexpected IRQ on CPU%d: (%08x %08lx %p)\n",
+ smp_processor_id(), bit,
+ combiner->regs[reg].enabled,
+ combiner->regs[reg].addr);
+
+ while (status) {
+ bit = __ffs(status);
+ status &= ~(1 << bit);
+ hwirq = irq_nr(reg, bit);
+ virq = irq_find_mapping(combiner->domain, hwirq);
+ if (virq > 0)
+ generic_handle_irq(virq);
+
+ }
+ }
+
+ chained_irq_exit(chip, desc);
+}
+
+static void combiner_irq_chip_mask_irq(struct irq_data *data)
+{
+ struct combiner *combiner = irq_data_get_irq_chip_data(data);
+ struct combiner_reg *reg = combiner->regs + data->hwirq / REG_SIZE;
+
+ clear_bit(data->hwirq % REG_SIZE, ®->enabled);
+}
+
+static void combiner_irq_chip_unmask_irq(struct irq_data *data)
+{
+ struct combiner *combiner = irq_data_get_irq_chip_data(data);
+ struct combiner_reg *reg = combiner->regs + data->hwirq / REG_SIZE;
+
+ set_bit(data->hwirq % REG_SIZE, ®->enabled);
+}
+
+static struct irq_chip irq_chip = {
+ .irq_mask = combiner_irq_chip_mask_irq,
+ .irq_unmask = combiner_irq_chip_unmask_irq,
+ .name = "qcom-irq-combiner"
+};
+
+static int combiner_irq_map(struct irq_domain *domain, unsigned int irq,
+ irq_hw_number_t hwirq)
+{
+ irq_set_chip_and_handler(irq, &irq_chip, handle_level_irq);
+ irq_set_chip_data(irq, domain->host_data);
+ irq_set_noprobe(irq);
+ return 0;
+}
+
+static void combiner_irq_unmap(struct irq_domain *domain, unsigned int irq)
+{
+ irq_domain_reset_irq_data(irq_get_irq_data(irq));
+}
+
+static int combiner_irq_translate(struct irq_domain *d, struct irq_fwspec *fws,
+ unsigned long *hwirq, unsigned int *type)
+{
+ struct combiner *combiner = d->host_data;
+
+ if (is_acpi_node(fws->fwnode)) {
+ if (WARN_ON((fws->param_count != 2) ||
+ (fws->param[0] >= combiner->nirqs) ||
+ (fws->param[1] & IORESOURCE_IRQ_LOWEDGE) ||
+ (fws->param[1] & IORESOURCE_IRQ_HIGHEDGE)))
+ return -EINVAL;
+
+ *hwirq = fws->param[0];
+ *type = fws->param[1];
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static const struct irq_domain_ops domain_ops = {
+ .map = combiner_irq_map,
+ .unmap = combiner_irq_unmap,
+ .translate = combiner_irq_translate
+};
+
+static acpi_status count_registers_cb(struct acpi_resource *ares, void *context)
+{
+ int *count = context;
+
+ if (ares->type == ACPI_RESOURCE_TYPE_GENERIC_REGISTER)
+ ++(*count);
+ return AE_OK;
+}
+
+static int count_registers(struct platform_device *pdev)
+{
+ acpi_handle ahandle = ACPI_HANDLE(&pdev->dev);
+ acpi_status status;
+ int count = 0;
+
+ if (!acpi_has_method(ahandle, METHOD_NAME__CRS))
+ return -EINVAL;
+
+ status = acpi_walk_resources(ahandle, METHOD_NAME__CRS,
+ count_registers_cb, &count);
+ if (ACPI_FAILURE(status))
+ return -EINVAL;
+ return count;
+}
+
+struct get_registers_context {
+ struct device *dev;
+ struct combiner *combiner;
+ int err;
+};
+
+static acpi_status get_registers_cb(struct acpi_resource *ares, void *context)
+{
+ struct get_registers_context *ctx = context;
+ struct acpi_resource_generic_register *reg;
+ phys_addr_t paddr;
+ void __iomem *vaddr;
+
+ if (ares->type != ACPI_RESOURCE_TYPE_GENERIC_REGISTER)
+ return AE_OK;
+
+ reg = &ares->data.generic_reg;
+ paddr = reg->address;
+ if ((reg->space_id != ACPI_SPACE_MEM) ||
+ (reg->bit_offset != 0) ||
+ (reg->bit_width > REG_SIZE)) {
+ dev_err(ctx->dev, "Bad register resource @%pa\n", &paddr);
+ ctx->err = -EINVAL;
+ return AE_ERROR;
+ }
+
+ vaddr = devm_ioremap(ctx->dev, reg->address, REG_SIZE);
+ if (!vaddr) {
+ dev_err(ctx->dev, "Can't map register @%pa\n", &paddr);
+ ctx->err = -ENOMEM;
+ return AE_ERROR;
+ }
+
+ ctx->combiner->regs[ctx->combiner->nregs].addr = vaddr;
+ ctx->combiner->nirqs += reg->bit_width;
+ ctx->combiner->nregs++;
+ return AE_OK;
+}
+
+static int get_registers(struct platform_device *pdev, struct combiner *comb)
+{
+ acpi_handle ahandle = ACPI_HANDLE(&pdev->dev);
+ acpi_status status;
+ struct get_registers_context ctx;
+
+ if (!acpi_has_method(ahandle, METHOD_NAME__CRS))
+ return -EINVAL;
+
+ ctx.dev = &pdev->dev;
+ ctx.combiner = comb;
+ ctx.err = 0;
+
+ status = acpi_walk_resources(ahandle, METHOD_NAME__CRS,
+ get_registers_cb, &ctx);
+ if (ACPI_FAILURE(status))
+ return ctx.err;
+ return 0;
+}
+
+static int __init combiner_probe(struct platform_device *pdev)
+{
+ struct combiner *combiner;
+ size_t alloc_sz;
+ u32 nregs;
+ int err;
+
+ nregs = count_registers(pdev);
+ if (nregs <= 0) {
+ dev_err(&pdev->dev, "Error reading register resources\n");
+ return -EINVAL;
+ }
+
+ alloc_sz = sizeof(*combiner) + sizeof(struct combiner_reg) * nregs;
+ combiner = devm_kzalloc(&pdev->dev, alloc_sz, GFP_KERNEL);
+ if (!combiner)
+ return -ENOMEM;
+
+ err = get_registers(pdev, combiner);
+ if (err < 0)
+ return err;
+
+ combiner->parent_irq = platform_get_irq(pdev, 0);
+ if (combiner->parent_irq <= 0) {
+ dev_err(&pdev->dev, "Error getting IRQ resource\n");
+ return -EPROBE_DEFER;
+ }
+
+ combiner->domain = irq_domain_create_linear(pdev->dev.fwnode, combiner->nirqs,
+ &domain_ops, combiner);
+ if (!combiner->domain)
+ /* Errors printed by irq_domain_create_linear */
+ return -ENODEV;
+
+ irq_set_chained_handler_and_data(combiner->parent_irq,
+ combiner_handle_irq, combiner);
+
+ dev_info(&pdev->dev, "Initialized with [p=%d,n=%d,r=%p]\n",
+ combiner->parent_irq, combiner->nirqs, combiner->regs[0].addr);
+ return 0;
+}
+
+static const struct acpi_device_id qcom_irq_combiner_ids[] = {
+ { "QCOM80B1", },
+ { }
+};
+
+static struct platform_driver qcom_irq_combiner_probe = {
+ .driver = {
+ .name = "qcom-irq-combiner",
+ .acpi_match_table = ACPI_PTR(qcom_irq_combiner_ids),
+ },
+ .probe = combiner_probe,
+};
+
+static int __init register_qcom_irq_combiner(void)
+{
+ return platform_driver_register(&qcom_irq_combiner_probe);
+}
+device_initcall(register_qcom_irq_combiner);
diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c
index 1a1d997..296f1411 100644
--- a/drivers/isdn/hardware/eicon/message.c
+++ b/drivers/isdn/hardware/eicon/message.c
@@ -11297,7 +11297,8 @@
((CAPI_MSG *) msg)->header.ncci = 0;
((CAPI_MSG *) msg)->info.facility_req.Selector = SELECTOR_LINE_INTERCONNECT;
((CAPI_MSG *) msg)->info.facility_req.structs[0] = 3;
- PUT_WORD(&(((CAPI_MSG *) msg)->info.facility_req.structs[1]), LI_REQ_SILENT_UPDATE);
+ ((CAPI_MSG *) msg)->info.facility_req.structs[1] = LI_REQ_SILENT_UPDATE & 0xff;
+ ((CAPI_MSG *) msg)->info.facility_req.structs[2] = LI_REQ_SILENT_UPDATE >> 8;
((CAPI_MSG *) msg)->info.facility_req.structs[3] = 0;
w = api_put(notify_plci->appl, (CAPI_MSG *) msg);
if (w != _QUEUE_FULL)
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index 9cb4b62..b324474 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -203,7 +203,7 @@
{
struct mISDNstack *st = data;
#ifdef MISDN_MSG_STATS
- cputime_t utime, stime;
+ u64 utime, stime;
#endif
int err = 0;
@@ -308,7 +308,7 @@
st->stopped_cnt);
task_cputime(st->thread, &utime, &stime);
printk(KERN_DEBUG
- "mISDNStackd daemon for %s utime(%ld) stime(%ld)\n",
+ "mISDNStackd daemon for %s utime(%llu) stime(%llu)\n",
dev_name(&st->dev->dev), utime, stime);
printk(KERN_DEBUG
"mISDNStackd daemon for %s nvcsw(%ld) nivcsw(%ld)\n",
diff --git a/drivers/macintosh/rack-meter.c b/drivers/macintosh/rack-meter.c
index 7755271..e199fd6 100644
--- a/drivers/macintosh/rack-meter.c
+++ b/drivers/macintosh/rack-meter.c
@@ -52,8 +52,8 @@
struct rackmeter_cpu {
struct delayed_work sniffer;
struct rackmeter *rm;
- cputime64_t prev_wall;
- cputime64_t prev_idle;
+ u64 prev_wall;
+ u64 prev_idle;
int zero;
} ____cacheline_aligned;
@@ -81,7 +81,7 @@
/* This is copied from cpufreq_ondemand, maybe we should put it in
* a common header somewhere
*/
-static inline cputime64_t get_cpu_idle_time(unsigned int cpu)
+static inline u64 get_cpu_idle_time(unsigned int cpu)
{
u64 retval;
@@ -217,23 +217,23 @@
container_of(work, struct rackmeter_cpu, sniffer.work);
struct rackmeter *rm = rcpu->rm;
unsigned int cpu = smp_processor_id();
- cputime64_t cur_jiffies, total_idle_ticks;
- unsigned int total_ticks, idle_ticks;
+ u64 cur_nsecs, total_idle_nsecs;
+ u64 total_nsecs, idle_nsecs;
int i, offset, load, cumm, pause;
- cur_jiffies = jiffies64_to_cputime64(get_jiffies_64());
- total_ticks = (unsigned int) (cur_jiffies - rcpu->prev_wall);
- rcpu->prev_wall = cur_jiffies;
+ cur_nsecs = jiffies64_to_nsecs(get_jiffies_64());
+ total_nsecs = cur_nsecs - rcpu->prev_wall;
+ rcpu->prev_wall = cur_nsecs;
- total_idle_ticks = get_cpu_idle_time(cpu);
- idle_ticks = (unsigned int) (total_idle_ticks - rcpu->prev_idle);
- idle_ticks = min(idle_ticks, total_ticks);
- rcpu->prev_idle = total_idle_ticks;
+ total_idle_nsecs = get_cpu_idle_time(cpu);
+ idle_nsecs = total_idle_nsecs - rcpu->prev_idle;
+ idle_nsecs = min(idle_nsecs, total_nsecs);
+ rcpu->prev_idle = total_idle_nsecs;
/* We do a very dumb calculation to update the LEDs for now,
* we'll do better once we have actual PWM implemented
*/
- load = (9 * (total_ticks - idle_ticks)) / total_ticks;
+ load = div64_u64(9 * (total_nsecs - idle_nsecs), total_nsecs);
offset = cpu << 3;
cumm = 0;
@@ -278,7 +278,7 @@
continue;
rcpu = &rm->cpu[cpu];
rcpu->prev_idle = get_cpu_idle_time(cpu);
- rcpu->prev_wall = jiffies64_to_cputime64(get_jiffies_64());
+ rcpu->prev_wall = jiffies64_to_nsecs(get_jiffies_64());
schedule_delayed_work_on(cpu, &rm->cpu[cpu].sniffer,
msecs_to_jiffies(CPU_SAMPLING_RATE));
}
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 96692d1..1cb2ca9 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1534,18 +1534,18 @@
return PTR_ERR(key);
}
- rcu_read_lock();
+ down_read(&key->sem);
ukp = user_key_payload(key);
if (!ukp) {
- rcu_read_unlock();
+ up_read(&key->sem);
key_put(key);
kzfree(new_key_string);
return -EKEYREVOKED;
}
if (cc->key_size != ukp->datalen) {
- rcu_read_unlock();
+ up_read(&key->sem);
key_put(key);
kzfree(new_key_string);
return -EINVAL;
@@ -1553,7 +1553,7 @@
memcpy(cc->key, ukp->data, cc->key_size);
- rcu_read_unlock();
+ up_read(&key->sem);
key_put(key);
/* clear the flag since following operations may invalidate previously valid key */
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 6400cff..3570bcb 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -427,7 +427,7 @@
unsigned long flags;
struct priority_group *pg;
struct pgpath *pgpath;
- bool bypassed = true;
+ unsigned bypassed = 1;
if (!atomic_read(&m->nr_valid_paths)) {
clear_bit(MPATHF_QUEUE_IO, &m->flags);
@@ -466,7 +466,7 @@
*/
do {
list_for_each_entry(pg, &m->priority_groups, list) {
- if (pg->bypassed == bypassed)
+ if (pg->bypassed == !!bypassed)
continue;
pgpath = choose_path_in_pg(m, pg, nr_bytes);
if (!IS_ERR_OR_NULL(pgpath)) {
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 9d7275f..6e702fc 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -779,6 +779,10 @@
int srcu_idx;
struct dm_table *map = dm_get_live_table(md, &srcu_idx);
+ if (unlikely(!map)) {
+ dm_put_live_table(md, srcu_idx);
+ return;
+ }
ti = dm_table_find_target(map, pos);
dm_put_live_table(md, srcu_idx);
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 82821ee..01175da 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5291,6 +5291,11 @@
if (start_readonly && mddev->ro == 0)
mddev->ro = 2; /* read-only, but switch on first write */
+ /*
+ * NOTE: some pers->run(), for example r5l_recovery_log(), wakes
+ * up mddev->thread. It is important to initialize critical
+ * resources for mddev->thread BEFORE calling pers->run().
+ */
err = pers->run(mddev);
if (err)
pr_warn("md: pers->run() failed ...\n");
diff --git a/drivers/md/md.h b/drivers/md/md.h
index e38936d..2a51403 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -212,6 +212,7 @@
int is_new);
struct md_cluster_info;
+/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
enum mddev_flags {
MD_ARRAY_FIRST_USE, /* First use of array, needs initialization */
MD_CLOSING, /* If set, we are closing the array, do not open
@@ -702,4 +703,11 @@
{
return mddev->cluster_info && mddev->bitmap_info.nodes > 1;
}
+
+/* clear unsupported mddev_flags */
+static inline void mddev_clear_unsupported_flags(struct mddev *mddev,
+ unsigned long unsupported_flags)
+{
+ mddev->flags &= ~unsupported_flags;
+}
#endif /* _MD_MD_H */
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index a162fed..848365d 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -26,6 +26,11 @@
#include "raid0.h"
#include "raid5.h"
+#define UNSUPPORTED_MDDEV_FLAGS \
+ ((1L << MD_HAS_JOURNAL) | \
+ (1L << MD_JOURNAL_CLEAN) | \
+ (1L << MD_FAILFAST_SUPPORTED))
+
static int raid0_congested(struct mddev *mddev, int bits)
{
struct r0conf *conf = mddev->private;
@@ -539,8 +544,7 @@
mddev->delta_disks = -1;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
- clear_bit(MD_HAS_JOURNAL, &mddev->flags);
- clear_bit(MD_JOURNAL_CLEAN, &mddev->flags);
+ mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS);
create_strip_zones(mddev, &priv_conf);
@@ -583,7 +587,7 @@
mddev->degraded = 0;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
- clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
+ mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS);
create_strip_zones(mddev, &priv_conf);
return priv_conf;
@@ -626,7 +630,7 @@
mddev->raid_disks = 1;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
- clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
+ mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS);
create_strip_zones(mddev, &priv_conf);
return priv_conf;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index a1f3fbe..7b0f647 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -42,6 +42,10 @@
#include "raid1.h"
#include "bitmap.h"
+#define UNSUPPORTED_MDDEV_FLAGS \
+ ((1L << MD_HAS_JOURNAL) | \
+ (1L << MD_JOURNAL_CLEAN))
+
/*
* Number of guaranteed r1bios in case of extreme VM load:
*/
@@ -1066,17 +1070,107 @@
kfree(plug);
}
-static void raid1_make_request(struct mddev *mddev, struct bio * bio)
+static void raid1_read_request(struct mddev *mddev, struct bio *bio,
+ struct r1bio *r1_bio)
{
struct r1conf *conf = mddev->private;
struct raid1_info *mirror;
- struct r1bio *r1_bio;
struct bio *read_bio;
+ struct bitmap *bitmap = mddev->bitmap;
+ const int op = bio_op(bio);
+ const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
+ int sectors_handled;
+ int max_sectors;
+ int rdisk;
+
+ wait_barrier(conf, bio);
+
+read_again:
+ rdisk = read_balance(conf, r1_bio, &max_sectors);
+
+ if (rdisk < 0) {
+ /* couldn't find anywhere to read from */
+ raid_end_bio_io(r1_bio);
+ return;
+ }
+ mirror = conf->mirrors + rdisk;
+
+ if (test_bit(WriteMostly, &mirror->rdev->flags) &&
+ bitmap) {
+ /*
+ * Reading from a write-mostly device must take care not to
+ * over-take any writes that are 'behind'
+ */
+ raid1_log(mddev, "wait behind writes");
+ wait_event(bitmap->behind_wait,
+ atomic_read(&bitmap->behind_writes) == 0);
+ }
+ r1_bio->read_disk = rdisk;
+ r1_bio->start_next_window = 0;
+
+ read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+ bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector,
+ max_sectors);
+
+ r1_bio->bios[rdisk] = read_bio;
+
+ read_bio->bi_iter.bi_sector = r1_bio->sector +
+ mirror->rdev->data_offset;
+ read_bio->bi_bdev = mirror->rdev->bdev;
+ read_bio->bi_end_io = raid1_end_read_request;
+ bio_set_op_attrs(read_bio, op, do_sync);
+ if (test_bit(FailFast, &mirror->rdev->flags) &&
+ test_bit(R1BIO_FailFast, &r1_bio->state))
+ read_bio->bi_opf |= MD_FAILFAST;
+ read_bio->bi_private = r1_bio;
+
+ if (mddev->gendisk)
+ trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
+ read_bio, disk_devt(mddev->gendisk),
+ r1_bio->sector);
+
+ if (max_sectors < r1_bio->sectors) {
+ /*
+ * could not read all from this device, so we will need another
+ * r1_bio.
+ */
+ sectors_handled = (r1_bio->sector + max_sectors
+ - bio->bi_iter.bi_sector);
+ r1_bio->sectors = max_sectors;
+ spin_lock_irq(&conf->device_lock);
+ if (bio->bi_phys_segments == 0)
+ bio->bi_phys_segments = 2;
+ else
+ bio->bi_phys_segments++;
+ spin_unlock_irq(&conf->device_lock);
+
+ /*
+ * Cannot call generic_make_request directly as that will be
+ * queued in __make_request and subsequent mempool_alloc might
+ * block waiting for it. So hand bio over to raid1d.
+ */
+ reschedule_retry(r1_bio);
+
+ r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+
+ r1_bio->master_bio = bio;
+ r1_bio->sectors = bio_sectors(bio) - sectors_handled;
+ r1_bio->state = 0;
+ r1_bio->mddev = mddev;
+ r1_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
+ goto read_again;
+ } else
+ generic_make_request(read_bio);
+}
+
+static void raid1_write_request(struct mddev *mddev, struct bio *bio,
+ struct r1bio *r1_bio)
+{
+ struct r1conf *conf = mddev->private;
int i, disks;
- struct bitmap *bitmap;
+ struct bitmap *bitmap = mddev->bitmap;
unsigned long flags;
const int op = bio_op(bio);
- const int rw = bio_data_dir(bio);
const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
const unsigned long do_flush_fua = (bio->bi_opf &
(REQ_PREFLUSH | REQ_FUA));
@@ -1096,15 +1190,15 @@
md_write_start(mddev, bio); /* wait on superblock update early */
- if (bio_data_dir(bio) == WRITE &&
- ((bio_end_sector(bio) > mddev->suspend_lo &&
+ if ((bio_end_sector(bio) > mddev->suspend_lo &&
bio->bi_iter.bi_sector < mddev->suspend_hi) ||
(mddev_is_clustered(mddev) &&
md_cluster_ops->area_resyncing(mddev, WRITE,
- bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
- /* As the suspend_* range is controlled by
- * userspace, we want an interruptible
- * wait.
+ bio->bi_iter.bi_sector, bio_end_sector(bio)))) {
+
+ /*
+ * As the suspend_* range is controlled by userspace, we want
+ * an interruptible wait.
*/
DEFINE_WAIT(w);
for (;;) {
@@ -1115,128 +1209,15 @@
bio->bi_iter.bi_sector >= mddev->suspend_hi ||
(mddev_is_clustered(mddev) &&
!md_cluster_ops->area_resyncing(mddev, WRITE,
- bio->bi_iter.bi_sector, bio_end_sector(bio))))
+ bio->bi_iter.bi_sector,
+ bio_end_sector(bio))))
break;
schedule();
}
finish_wait(&conf->wait_barrier, &w);
}
-
start_next_window = wait_barrier(conf, bio);
- bitmap = mddev->bitmap;
-
- /*
- * make_request() can abort the operation when read-ahead is being
- * used and no empty request is available.
- *
- */
- r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
-
- r1_bio->master_bio = bio;
- r1_bio->sectors = bio_sectors(bio);
- r1_bio->state = 0;
- r1_bio->mddev = mddev;
- r1_bio->sector = bio->bi_iter.bi_sector;
-
- /* We might need to issue multiple reads to different
- * devices if there are bad blocks around, so we keep
- * track of the number of reads in bio->bi_phys_segments.
- * If this is 0, there is only one r1_bio and no locking
- * will be needed when requests complete. If it is
- * non-zero, then it is the number of not-completed requests.
- */
- bio->bi_phys_segments = 0;
- bio_clear_flag(bio, BIO_SEG_VALID);
-
- if (rw == READ) {
- /*
- * read balancing logic:
- */
- int rdisk;
-
-read_again:
- rdisk = read_balance(conf, r1_bio, &max_sectors);
-
- if (rdisk < 0) {
- /* couldn't find anywhere to read from */
- raid_end_bio_io(r1_bio);
- return;
- }
- mirror = conf->mirrors + rdisk;
-
- if (test_bit(WriteMostly, &mirror->rdev->flags) &&
- bitmap) {
- /* Reading from a write-mostly device must
- * take care not to over-take any writes
- * that are 'behind'
- */
- raid1_log(mddev, "wait behind writes");
- wait_event(bitmap->behind_wait,
- atomic_read(&bitmap->behind_writes) == 0);
- }
- r1_bio->read_disk = rdisk;
- r1_bio->start_next_window = 0;
-
- read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
- bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector,
- max_sectors);
-
- r1_bio->bios[rdisk] = read_bio;
-
- read_bio->bi_iter.bi_sector = r1_bio->sector +
- mirror->rdev->data_offset;
- read_bio->bi_bdev = mirror->rdev->bdev;
- read_bio->bi_end_io = raid1_end_read_request;
- bio_set_op_attrs(read_bio, op, do_sync);
- if (test_bit(FailFast, &mirror->rdev->flags) &&
- test_bit(R1BIO_FailFast, &r1_bio->state))
- read_bio->bi_opf |= MD_FAILFAST;
- read_bio->bi_private = r1_bio;
-
- if (mddev->gendisk)
- trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
- read_bio, disk_devt(mddev->gendisk),
- r1_bio->sector);
-
- if (max_sectors < r1_bio->sectors) {
- /* could not read all from this device, so we will
- * need another r1_bio.
- */
-
- sectors_handled = (r1_bio->sector + max_sectors
- - bio->bi_iter.bi_sector);
- r1_bio->sectors = max_sectors;
- spin_lock_irq(&conf->device_lock);
- if (bio->bi_phys_segments == 0)
- bio->bi_phys_segments = 2;
- else
- bio->bi_phys_segments++;
- spin_unlock_irq(&conf->device_lock);
- /* Cannot call generic_make_request directly
- * as that will be queued in __make_request
- * and subsequent mempool_alloc might block waiting
- * for it. So hand bio over to raid1d.
- */
- reschedule_retry(r1_bio);
-
- r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
-
- r1_bio->master_bio = bio;
- r1_bio->sectors = bio_sectors(bio) - sectors_handled;
- r1_bio->state = 0;
- r1_bio->mddev = mddev;
- r1_bio->sector = bio->bi_iter.bi_sector +
- sectors_handled;
- goto read_again;
- } else
- generic_make_request(read_bio);
- return;
- }
-
- /*
- * WRITE:
- */
if (conf->pending_count >= max_queued_requests) {
md_wakeup_thread(mddev->thread);
raid1_log(mddev, "wait queued");
@@ -1280,8 +1261,7 @@
int bad_sectors;
int is_bad;
- is_bad = is_badblock(rdev, r1_bio->sector,
- max_sectors,
+ is_bad = is_badblock(rdev, r1_bio->sector, max_sectors,
&first_bad, &bad_sectors);
if (is_bad < 0) {
/* mustn't write here until the bad block is
@@ -1370,7 +1350,8 @@
continue;
mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
- bio_trim(mbio, r1_bio->sector - bio->bi_iter.bi_sector, max_sectors);
+ bio_trim(mbio, r1_bio->sector - bio->bi_iter.bi_sector,
+ max_sectors);
if (first_clone) {
/* do behind I/O ?
@@ -1464,6 +1445,40 @@
wake_up(&conf->wait_barrier);
}
+static void raid1_make_request(struct mddev *mddev, struct bio *bio)
+{
+ struct r1conf *conf = mddev->private;
+ struct r1bio *r1_bio;
+
+ /*
+ * make_request() can abort the operation when read-ahead is being
+ * used and no empty request is available.
+ *
+ */
+ r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+
+ r1_bio->master_bio = bio;
+ r1_bio->sectors = bio_sectors(bio);
+ r1_bio->state = 0;
+ r1_bio->mddev = mddev;
+ r1_bio->sector = bio->bi_iter.bi_sector;
+
+ /*
+ * We might need to issue multiple reads to different devices if there
+ * are bad blocks around, so we keep track of the number of reads in
+ * bio->bi_phys_segments. If this is 0, there is only one r1_bio and
+ * no locking will be needed when requests complete. If it is
+ * non-zero, then it is the number of not-completed requests.
+ */
+ bio->bi_phys_segments = 0;
+ bio_clear_flag(bio, BIO_SEG_VALID);
+
+ if (bio_data_dir(bio) == READ)
+ raid1_read_request(mddev, bio, r1_bio);
+ else
+ raid1_write_request(mddev, bio, r1_bio);
+}
+
static void raid1_status(struct seq_file *seq, struct mddev *mddev)
{
struct r1conf *conf = mddev->private;
@@ -3246,8 +3261,8 @@
if (!IS_ERR(conf)) {
/* Array must appear to be quiesced */
conf->array_frozen = 1;
- clear_bit(MD_HAS_JOURNAL, &mddev->flags);
- clear_bit(MD_JOURNAL_CLEAN, &mddev->flags);
+ mddev_clear_unsupported_flags(mddev,
+ UNSUPPORTED_MDDEV_FLAGS);
}
return conf;
}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index ab5e862..1920756 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1087,23 +1087,122 @@
kfree(plug);
}
-static void __make_request(struct mddev *mddev, struct bio *bio)
+static void raid10_read_request(struct mddev *mddev, struct bio *bio,
+ struct r10bio *r10_bio)
{
struct r10conf *conf = mddev->private;
- struct r10bio *r10_bio;
struct bio *read_bio;
+ const int op = bio_op(bio);
+ const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
+ int sectors_handled;
+ int max_sectors;
+ sector_t sectors;
+ struct md_rdev *rdev;
+ int slot;
+
+ /*
+ * Register the new request and wait if the reconstruction
+ * thread has put up a bar for new requests.
+ * Continue immediately if no resync is active currently.
+ */
+ wait_barrier(conf);
+
+ sectors = bio_sectors(bio);
+ while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+ bio->bi_iter.bi_sector < conf->reshape_progress &&
+ bio->bi_iter.bi_sector + sectors > conf->reshape_progress) {
+ /*
+ * IO spans the reshape position. Need to wait for reshape to
+ * pass
+ */
+ raid10_log(conf->mddev, "wait reshape");
+ allow_barrier(conf);
+ wait_event(conf->wait_barrier,
+ conf->reshape_progress <= bio->bi_iter.bi_sector ||
+ conf->reshape_progress >= bio->bi_iter.bi_sector +
+ sectors);
+ wait_barrier(conf);
+ }
+
+read_again:
+ rdev = read_balance(conf, r10_bio, &max_sectors);
+ if (!rdev) {
+ raid_end_bio_io(r10_bio);
+ return;
+ }
+ slot = r10_bio->read_slot;
+
+ read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+ bio_trim(read_bio, r10_bio->sector - bio->bi_iter.bi_sector,
+ max_sectors);
+
+ r10_bio->devs[slot].bio = read_bio;
+ r10_bio->devs[slot].rdev = rdev;
+
+ read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
+ choose_data_offset(r10_bio, rdev);
+ read_bio->bi_bdev = rdev->bdev;
+ read_bio->bi_end_io = raid10_end_read_request;
+ bio_set_op_attrs(read_bio, op, do_sync);
+ if (test_bit(FailFast, &rdev->flags) &&
+ test_bit(R10BIO_FailFast, &r10_bio->state))
+ read_bio->bi_opf |= MD_FAILFAST;
+ read_bio->bi_private = r10_bio;
+
+ if (mddev->gendisk)
+ trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
+ read_bio, disk_devt(mddev->gendisk),
+ r10_bio->sector);
+ if (max_sectors < r10_bio->sectors) {
+ /*
+ * Could not read all from this device, so we will need another
+ * r10_bio.
+ */
+ sectors_handled = (r10_bio->sector + max_sectors
+ - bio->bi_iter.bi_sector);
+ r10_bio->sectors = max_sectors;
+ spin_lock_irq(&conf->device_lock);
+ if (bio->bi_phys_segments == 0)
+ bio->bi_phys_segments = 2;
+ else
+ bio->bi_phys_segments++;
+ spin_unlock_irq(&conf->device_lock);
+ /*
+ * Cannot call generic_make_request directly as that will be
+ * queued in __generic_make_request and subsequent
+ * mempool_alloc might block waiting for it. so hand bio over
+ * to raid10d.
+ */
+ reschedule_retry(r10_bio);
+
+ r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
+
+ r10_bio->master_bio = bio;
+ r10_bio->sectors = bio_sectors(bio) - sectors_handled;
+ r10_bio->state = 0;
+ r10_bio->mddev = mddev;
+ r10_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
+ goto read_again;
+ } else
+ generic_make_request(read_bio);
+ return;
+}
+
+static void raid10_write_request(struct mddev *mddev, struct bio *bio,
+ struct r10bio *r10_bio)
+{
+ struct r10conf *conf = mddev->private;
int i;
const int op = bio_op(bio);
- const int rw = bio_data_dir(bio);
const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
const unsigned long do_fua = (bio->bi_opf & REQ_FUA);
unsigned long flags;
struct md_rdev *blocked_rdev;
struct blk_plug_cb *cb;
struct raid10_plug_cb *plug = NULL;
+ sector_t sectors;
int sectors_handled;
int max_sectors;
- int sectors;
md_write_start(mddev, bio);
@@ -1118,8 +1217,9 @@
while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
bio->bi_iter.bi_sector < conf->reshape_progress &&
bio->bi_iter.bi_sector + sectors > conf->reshape_progress) {
- /* IO spans the reshape position. Need to wait for
- * reshape to pass
+ /*
+ * IO spans the reshape position. Need to wait for reshape to
+ * pass
*/
raid10_log(conf->mddev, "wait reshape");
allow_barrier(conf);
@@ -1129,8 +1229,8 @@
sectors);
wait_barrier(conf);
}
+
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
- bio_data_dir(bio) == WRITE &&
(mddev->reshape_backwards
? (bio->bi_iter.bi_sector < conf->reshape_safe &&
bio->bi_iter.bi_sector + sectors > conf->reshape_progress)
@@ -1148,98 +1248,6 @@
conf->reshape_safe = mddev->reshape_position;
}
- r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
-
- r10_bio->master_bio = bio;
- r10_bio->sectors = sectors;
-
- r10_bio->mddev = mddev;
- r10_bio->sector = bio->bi_iter.bi_sector;
- r10_bio->state = 0;
-
- /* We might need to issue multiple reads to different
- * devices if there are bad blocks around, so we keep
- * track of the number of reads in bio->bi_phys_segments.
- * If this is 0, there is only one r10_bio and no locking
- * will be needed when the request completes. If it is
- * non-zero, then it is the number of not-completed requests.
- */
- bio->bi_phys_segments = 0;
- bio_clear_flag(bio, BIO_SEG_VALID);
-
- if (rw == READ) {
- /*
- * read balancing logic:
- */
- struct md_rdev *rdev;
- int slot;
-
-read_again:
- rdev = read_balance(conf, r10_bio, &max_sectors);
- if (!rdev) {
- raid_end_bio_io(r10_bio);
- return;
- }
- slot = r10_bio->read_slot;
-
- read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
- bio_trim(read_bio, r10_bio->sector - bio->bi_iter.bi_sector,
- max_sectors);
-
- r10_bio->devs[slot].bio = read_bio;
- r10_bio->devs[slot].rdev = rdev;
-
- read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
- choose_data_offset(r10_bio, rdev);
- read_bio->bi_bdev = rdev->bdev;
- read_bio->bi_end_io = raid10_end_read_request;
- bio_set_op_attrs(read_bio, op, do_sync);
- if (test_bit(FailFast, &rdev->flags) &&
- test_bit(R10BIO_FailFast, &r10_bio->state))
- read_bio->bi_opf |= MD_FAILFAST;
- read_bio->bi_private = r10_bio;
-
- if (mddev->gendisk)
- trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
- read_bio, disk_devt(mddev->gendisk),
- r10_bio->sector);
- if (max_sectors < r10_bio->sectors) {
- /* Could not read all from this device, so we will
- * need another r10_bio.
- */
- sectors_handled = (r10_bio->sector + max_sectors
- - bio->bi_iter.bi_sector);
- r10_bio->sectors = max_sectors;
- spin_lock_irq(&conf->device_lock);
- if (bio->bi_phys_segments == 0)
- bio->bi_phys_segments = 2;
- else
- bio->bi_phys_segments++;
- spin_unlock_irq(&conf->device_lock);
- /* Cannot call generic_make_request directly
- * as that will be queued in __generic_make_request
- * and subsequent mempool_alloc might block
- * waiting for it. so hand bio over to raid10d.
- */
- reschedule_retry(r10_bio);
-
- r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
-
- r10_bio->master_bio = bio;
- r10_bio->sectors = bio_sectors(bio) - sectors_handled;
- r10_bio->state = 0;
- r10_bio->mddev = mddev;
- r10_bio->sector = bio->bi_iter.bi_sector +
- sectors_handled;
- goto read_again;
- } else
- generic_make_request(read_bio);
- return;
- }
-
- /*
- * WRITE:
- */
if (conf->pending_count >= max_queued_requests) {
md_wakeup_thread(mddev->thread);
raid10_log(mddev, "wait queued");
@@ -1300,8 +1308,7 @@
int bad_sectors;
int is_bad;
- is_bad = is_badblock(rdev, dev_sector,
- max_sectors,
+ is_bad = is_badblock(rdev, dev_sector, max_sectors,
&first_bad, &bad_sectors);
if (is_bad < 0) {
/* Mustn't write here until the bad block
@@ -1405,8 +1412,7 @@
r10_bio->devs[i].bio = mbio;
mbio->bi_iter.bi_sector = (r10_bio->devs[i].addr+
- choose_data_offset(r10_bio,
- rdev));
+ choose_data_offset(r10_bio, rdev));
mbio->bi_bdev = rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
bio_set_op_attrs(mbio, op, do_sync | do_fua);
@@ -1457,8 +1463,7 @@
r10_bio->devs[i].repl_bio = mbio;
mbio->bi_iter.bi_sector = (r10_bio->devs[i].addr +
- choose_data_offset(
- r10_bio, rdev));
+ choose_data_offset(r10_bio, rdev));
mbio->bi_bdev = rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
bio_set_op_attrs(mbio, op, do_sync | do_fua);
@@ -1503,6 +1508,36 @@
one_write_done(r10_bio);
}
+static void __make_request(struct mddev *mddev, struct bio *bio)
+{
+ struct r10conf *conf = mddev->private;
+ struct r10bio *r10_bio;
+
+ r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
+
+ r10_bio->master_bio = bio;
+ r10_bio->sectors = bio_sectors(bio);
+
+ r10_bio->mddev = mddev;
+ r10_bio->sector = bio->bi_iter.bi_sector;
+ r10_bio->state = 0;
+
+ /*
+ * We might need to issue multiple reads to different devices if there
+ * are bad blocks around, so we keep track of the number of reads in
+ * bio->bi_phys_segments. If this is 0, there is only one r10_bio and
+ * no locking will be needed when the request completes. If it is
+ * non-zero, then it is the number of not-completed requests.
+ */
+ bio->bi_phys_segments = 0;
+ bio_clear_flag(bio, BIO_SEG_VALID);
+
+ if (bio_data_dir(bio) == READ)
+ raid10_read_request(mddev, bio, r10_bio);
+ else
+ raid10_write_request(mddev, bio, r10_bio);
+}
+
static void raid10_make_request(struct mddev *mddev, struct bio *bio)
{
struct r10conf *conf = mddev->private;
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index d7bfb6f..302dea3 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -162,6 +162,8 @@
/* to submit async io_units, to fulfill ordering of flush */
struct work_struct deferred_io_work;
+ /* to disable write back during in degraded mode */
+ struct work_struct disable_writeback_work;
};
/*
@@ -611,6 +613,21 @@
r5l_do_submit_io(log, io);
}
+static void r5c_disable_writeback_async(struct work_struct *work)
+{
+ struct r5l_log *log = container_of(work, struct r5l_log,
+ disable_writeback_work);
+ struct mddev *mddev = log->rdev->mddev;
+
+ if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH)
+ return;
+ pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n",
+ mdname(mddev));
+ mddev_suspend(mddev);
+ log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
+ mddev_resume(mddev);
+}
+
static void r5l_submit_current_io(struct r5l_log *log)
{
struct r5l_io_unit *io = log->current_io;
@@ -1393,8 +1410,6 @@
next_checkpoint = r5c_calculate_new_cp(conf);
spin_unlock_irq(&log->io_list_lock);
- BUG_ON(reclaimable < 0);
-
if (reclaimable == 0 || !write_super)
return;
@@ -1682,8 +1697,7 @@
static struct stripe_head *
r5c_recovery_alloc_stripe(struct r5conf *conf,
- sector_t stripe_sect,
- sector_t log_start)
+ sector_t stripe_sect)
{
struct stripe_head *sh;
@@ -1692,7 +1706,6 @@
return NULL; /* no more stripe available */
r5l_recovery_reset_stripe(sh);
- sh->log_start = log_start;
return sh;
}
@@ -1862,7 +1875,7 @@
stripe_sect);
if (!sh) {
- sh = r5c_recovery_alloc_stripe(conf, stripe_sect, ctx->pos);
+ sh = r5c_recovery_alloc_stripe(conf, stripe_sect);
/*
* cannot get stripe from raid5_get_active_stripe
* try replay some stripes
@@ -1871,7 +1884,7 @@
r5c_recovery_replay_stripes(
cached_stripe_list, ctx);
sh = r5c_recovery_alloc_stripe(
- conf, stripe_sect, ctx->pos);
+ conf, stripe_sect);
}
if (!sh) {
pr_debug("md/raid:%s: Increasing stripe cache size to %d to recovery data on journal.\n",
@@ -1879,8 +1892,8 @@
conf->min_nr_stripes * 2);
raid5_set_cache_size(mddev,
conf->min_nr_stripes * 2);
- sh = r5c_recovery_alloc_stripe(
- conf, stripe_sect, ctx->pos);
+ sh = r5c_recovery_alloc_stripe(conf,
+ stripe_sect);
}
if (!sh) {
pr_err("md/raid:%s: Cannot get enough stripes due to memory pressure. Recovery failed.\n",
@@ -1894,7 +1907,6 @@
if (!test_bit(STRIPE_R5C_CACHING, &sh->state) &&
test_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags)) {
r5l_recovery_replay_one_stripe(conf, sh, ctx);
- sh->log_start = ctx->pos;
list_move_tail(&sh->lru, cached_stripe_list);
}
r5l_recovery_load_data(log, sh, ctx, payload,
@@ -1933,8 +1945,6 @@
set_bit(R5_UPTODATE, &dev->flags);
}
}
- list_add_tail(&sh->r5c, &log->stripe_in_journal_list);
- atomic_inc(&log->stripe_in_journal_count);
}
/*
@@ -2067,9 +2077,10 @@
r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
struct r5l_recovery_ctx *ctx)
{
- struct stripe_head *sh, *next;
+ struct stripe_head *sh;
struct mddev *mddev = log->rdev->mddev;
struct page *page;
+ sector_t next_checkpoint = MaxSector;
page = alloc_page(GFP_KERNEL);
if (!page) {
@@ -2078,7 +2089,9 @@
return -ENOMEM;
}
- list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
+ WARN_ON(list_empty(&ctx->cached_list));
+
+ list_for_each_entry(sh, &ctx->cached_list, lru) {
struct r5l_meta_block *mb;
int i;
int offset;
@@ -2123,14 +2136,42 @@
sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page,
REQ_OP_WRITE, REQ_FUA, false);
sh->log_start = ctx->pos;
+ list_add_tail(&sh->r5c, &log->stripe_in_journal_list);
+ atomic_inc(&log->stripe_in_journal_count);
ctx->pos = write_pos;
ctx->seq += 1;
+ next_checkpoint = sh->log_start;
+ }
+ log->next_checkpoint = next_checkpoint;
+ __free_page(page);
+ return 0;
+}
+static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log,
+ struct r5l_recovery_ctx *ctx)
+{
+ struct mddev *mddev = log->rdev->mddev;
+ struct r5conf *conf = mddev->private;
+ struct stripe_head *sh, *next;
+
+ if (ctx->data_only_stripes == 0)
+ return;
+
+ log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_BACK;
+
+ list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
+ r5c_make_stripe_write_out(sh);
+ set_bit(STRIPE_HANDLE, &sh->state);
list_del_init(&sh->lru);
raid5_release_stripe(sh);
}
- __free_page(page);
- return 0;
+
+ md_wakeup_thread(conf->mddev->thread);
+ /* reuse conf->wait_for_quiescent in recovery */
+ wait_event(conf->wait_for_quiescent,
+ atomic_read(&conf->active_stripes) == 0);
+
+ log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
}
static int r5l_recovery_log(struct r5l_log *log)
@@ -2139,7 +2180,6 @@
struct r5l_recovery_ctx ctx;
int ret;
sector_t pos;
- struct stripe_head *sh;
ctx.pos = log->last_checkpoint;
ctx.seq = log->last_cp_seq;
@@ -2160,35 +2200,31 @@
pos = ctx.pos;
ctx.seq += 10000;
- if (ctx.data_only_stripes == 0) {
- log->next_checkpoint = ctx.pos;
- r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
- ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
- } else {
- sh = list_last_entry(&ctx.cached_list, struct stripe_head, lru);
- log->next_checkpoint = sh->log_start;
- }
if ((ctx.data_only_stripes == 0) && (ctx.data_parity_stripes == 0))
pr_debug("md/raid:%s: starting from clean shutdown\n",
mdname(mddev));
- else {
- pr_debug("md/raid:%s: recoverying %d data-only stripes and %d data-parity stripes\n",
+ else
+ pr_debug("md/raid:%s: recovering %d data-only stripes and %d data-parity stripes\n",
mdname(mddev), ctx.data_only_stripes,
ctx.data_parity_stripes);
- if (ctx.data_only_stripes > 0)
- if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
- pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
- mdname(mddev));
- return -EIO;
- }
+ if (ctx.data_only_stripes == 0) {
+ log->next_checkpoint = ctx.pos;
+ r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
+ ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
+ } else if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
+ pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
+ mdname(mddev));
+ return -EIO;
}
log->log_start = ctx.pos;
log->seq = ctx.seq;
log->last_checkpoint = pos;
r5l_write_super(log, pos);
+
+ r5c_recovery_flush_data_only_stripes(log, &ctx);
return 0;
}
@@ -2250,6 +2286,10 @@
val > R5C_JOURNAL_MODE_WRITE_BACK)
return -EINVAL;
+ if (raid5_calc_degraded(conf) > 0 &&
+ val == R5C_JOURNAL_MODE_WRITE_BACK)
+ return -EINVAL;
+
mddev_suspend(mddev);
conf->log->r5c_journal_mode = val;
mddev_resume(mddev);
@@ -2304,6 +2344,16 @@
set_bit(STRIPE_R5C_CACHING, &sh->state);
}
+ /*
+ * When run in degraded mode, array is set to write-through mode.
+ * This check helps drain pending write safely in the transition to
+ * write-through mode.
+ */
+ if (s->failed) {
+ r5c_make_stripe_write_out(sh);
+ return -EAGAIN;
+ }
+
for (i = disks; i--; ) {
dev = &sh->dev[i];
/* if non-overwrite, use writing-out phase */
@@ -2354,6 +2404,8 @@
struct page *p = sh->dev[i].orig_page;
sh->dev[i].orig_page = sh->dev[i].page;
+ clear_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
+
if (!using_disk_info_extra_page)
put_page(p);
}
@@ -2418,9 +2470,6 @@
if (do_wakeup)
wake_up(&conf->wait_for_overlap);
- if (conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH)
- return;
-
spin_lock_irq(&conf->log->stripe_in_journal_lock);
list_del_init(&sh->r5c);
spin_unlock_irq(&conf->log->stripe_in_journal_lock);
@@ -2561,6 +2610,19 @@
return ret;
}
+void r5c_update_on_rdev_error(struct mddev *mddev)
+{
+ struct r5conf *conf = mddev->private;
+ struct r5l_log *log = conf->log;
+
+ if (!log)
+ return;
+
+ if (raid5_calc_degraded(conf) > 0 &&
+ conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
+ schedule_work(&log->disable_writeback_work);
+}
+
int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
{
struct request_queue *q = bdev_get_queue(rdev->bdev);
@@ -2633,20 +2695,23 @@
spin_lock_init(&log->no_space_stripes_lock);
INIT_WORK(&log->deferred_io_work, r5l_submit_io_async);
+ INIT_WORK(&log->disable_writeback_work, r5c_disable_writeback_async);
log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
INIT_LIST_HEAD(&log->stripe_in_journal_list);
spin_lock_init(&log->stripe_in_journal_lock);
atomic_set(&log->stripe_in_journal_count, 0);
+ rcu_assign_pointer(conf->log, log);
+
if (r5l_load_log(log))
goto error;
- rcu_assign_pointer(conf->log, log);
set_bit(MD_HAS_JOURNAL, &conf->mddev->flags);
return 0;
error:
+ rcu_assign_pointer(conf->log, NULL);
md_unregister_thread(&log->reclaim_thread);
reclaim_thread:
mempool_destroy(log->meta_pool);
@@ -2663,6 +2728,7 @@
void r5l_exit_log(struct r5l_log *log)
{
+ flush_work(&log->disable_writeback_work);
md_unregister_thread(&log->reclaim_thread);
mempool_destroy(log->meta_pool);
bioset_free(log->bs);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 06d7279..3c7e106 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -62,6 +62,8 @@
#include "raid0.h"
#include "bitmap.h"
+#define UNSUPPORTED_MDDEV_FLAGS (1L << MD_FAILFAST_SUPPORTED)
+
#define cpu_to_group(cpu) cpu_to_node(cpu)
#define ANY_GROUP NUMA_NO_NODE
@@ -554,7 +556,7 @@
* of the two sections, and some non-in_sync devices may
* be insync in the section most affected by failed devices.
*/
-static int calc_degraded(struct r5conf *conf)
+int raid5_calc_degraded(struct r5conf *conf)
{
int degraded, degraded2;
int i;
@@ -617,7 +619,7 @@
if (conf->mddev->reshape_position == MaxSector)
return conf->mddev->degraded > conf->max_degraded;
- degraded = calc_degraded(conf);
+ degraded = raid5_calc_degraded(conf);
if (degraded > conf->max_degraded)
return 1;
return 0;
@@ -1013,7 +1015,17 @@
if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
- sh->dev[i].vec.bv_page = sh->dev[i].page;
+
+ if (!op_is_write(op) &&
+ test_bit(R5_InJournal, &sh->dev[i].flags))
+ /*
+ * issuing read for a page in journal, this
+ * must be preparing for prexor in rmw; read
+ * the data into orig_page
+ */
+ sh->dev[i].vec.bv_page = sh->dev[i].orig_page;
+ else
+ sh->dev[i].vec.bv_page = sh->dev[i].page;
bi->bi_vcnt = 1;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
@@ -2378,6 +2390,13 @@
} else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
+ if (test_bit(R5_InJournal, &sh->dev[i].flags))
+ /*
+ * end read for a page in journal, this
+ * must be preparing for prexor in rmw
+ */
+ set_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
+
if (atomic_read(&rdev->read_errors))
atomic_set(&rdev->read_errors, 0);
} else {
@@ -2536,7 +2555,7 @@
spin_lock_irqsave(&conf->device_lock, flags);
clear_bit(In_sync, &rdev->flags);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
@@ -2550,6 +2569,7 @@
bdevname(rdev->bdev, b),
mdname(mddev),
conf->raid_disks - mddev->degraded);
+ r5c_update_on_rdev_error(mddev);
}
/*
@@ -2878,6 +2898,30 @@
return r_sector;
}
+/*
+ * There are cases where we want handle_stripe_dirtying() and
+ * schedule_reconstruction() to delay towrite to some dev of a stripe.
+ *
+ * This function checks whether we want to delay the towrite. Specifically,
+ * we delay the towrite when:
+ *
+ * 1. degraded stripe has a non-overwrite to the missing dev, AND this
+ * stripe has data in journal (for other devices).
+ *
+ * In this case, when reading data for the non-overwrite dev, it is
+ * necessary to handle complex rmw of write back cache (prexor with
+ * orig_page, and xor with page). To keep read path simple, we would
+ * like to flush data in journal to RAID disks first, so complex rmw
+ * is handled in the write patch (handle_stripe_dirtying).
+ *
+ */
+static inline bool delay_towrite(struct r5dev *dev,
+ struct stripe_head_state *s)
+{
+ return !test_bit(R5_OVERWRITE, &dev->flags) &&
+ !test_bit(R5_Insync, &dev->flags) && s->injournal;
+}
+
static void
schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
int rcw, int expand)
@@ -2898,7 +2942,7 @@
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if (dev->towrite) {
+ if (dev->towrite && !delay_towrite(dev, s)) {
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantdrain, &dev->flags);
if (!expand)
@@ -3293,13 +3337,6 @@
return rv;
}
-/* fetch_block - checks the given member device to see if its data needs
- * to be read or computed to satisfy a request.
- *
- * Returns 1 when no more member devices need to be checked, otherwise returns
- * 0 to tell the loop in handle_stripe_fill to continue
- */
-
static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
int disk_idx, int disks)
{
@@ -3390,6 +3427,12 @@
return 0;
}
+/* fetch_block - checks the given member device to see if its data needs
+ * to be read or computed to satisfy a request.
+ *
+ * Returns 1 when no more member devices need to be checked, otherwise returns
+ * 0 to tell the loop in handle_stripe_fill to continue
+ */
static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
int disk_idx, int disks)
{
@@ -3476,10 +3519,26 @@
* midst of changing due to a write
*/
if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
- !sh->reconstruct_state)
+ !sh->reconstruct_state) {
+
+ /*
+ * For degraded stripe with data in journal, do not handle
+ * read requests yet, instead, flush the stripe to raid
+ * disks first, this avoids handling complex rmw of write
+ * back cache (prexor with orig_page, and then xor with
+ * page) in the read path
+ */
+ if (s->injournal && s->failed) {
+ if (test_bit(STRIPE_R5C_CACHING, &sh->state))
+ r5c_make_stripe_write_out(sh);
+ goto out;
+ }
+
for (i = disks; i--; )
if (fetch_block(sh, s, i, disks))
break;
+ }
+out:
set_bit(STRIPE_HANDLE, &sh->state);
}
@@ -3592,6 +3651,21 @@
break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
}
+/*
+ * For RMW in write back cache, we need extra page in prexor to store the
+ * old data. This page is stored in dev->orig_page.
+ *
+ * This function checks whether we have data for prexor. The exact logic
+ * is:
+ * R5_UPTODATE && (!R5_InJournal || R5_OrigPageUPTDODATE)
+ */
+static inline bool uptodate_for_rmw(struct r5dev *dev)
+{
+ return (test_bit(R5_UPTODATE, &dev->flags)) &&
+ (!test_bit(R5_InJournal, &dev->flags) ||
+ test_bit(R5_OrigPageUPTDODATE, &dev->flags));
+}
+
static int handle_stripe_dirtying(struct r5conf *conf,
struct stripe_head *sh,
struct stripe_head_state *s,
@@ -3620,12 +3694,11 @@
} else for (i = disks; i--; ) {
/* would I have to read this buffer for read_modify_write */
struct r5dev *dev = &sh->dev[i];
- if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx ||
+ if (((dev->towrite && !delay_towrite(dev, s)) ||
+ i == sh->pd_idx || i == sh->qd_idx ||
test_bit(R5_InJournal, &dev->flags)) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !((test_bit(R5_UPTODATE, &dev->flags) &&
- (!test_bit(R5_InJournal, &dev->flags) ||
- dev->page != dev->orig_page)) ||
+ !(uptodate_for_rmw(dev) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rmw++;
@@ -3637,7 +3710,6 @@
i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_InJournal, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rcw++;
@@ -3687,13 +3759,11 @@
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if ((dev->towrite ||
+ if (((dev->towrite && !delay_towrite(dev, s)) ||
i == sh->pd_idx || i == sh->qd_idx ||
test_bit(R5_InJournal, &dev->flags)) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !((test_bit(R5_UPTODATE, &dev->flags) &&
- (!test_bit(R5_InJournal, &dev->flags) ||
- dev->page != dev->orig_page)) ||
+ !(uptodate_for_rmw(dev) ||
test_bit(R5_Wantcompute, &dev->flags)) &&
test_bit(R5_Insync, &dev->flags)) {
if (test_bit(STRIPE_PREREAD_ACTIVE,
@@ -3720,7 +3790,6 @@
i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_InJournal, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
rcw++;
if (test_bit(R5_Insync, &dev->flags) &&
@@ -7023,7 +7092,7 @@
/*
* 0 for a fully functional array, 1 or 2 for a degraded array.
*/
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
if (has_failed(conf)) {
pr_crit("md/raid:%s: not enough operational devices (%d/%d failed)\n",
@@ -7270,7 +7339,7 @@
}
}
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
print_raid5_conf(conf);
return count;
@@ -7630,7 +7699,7 @@
* pre and post number of devices.
*/
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
}
mddev->raid_disks = conf->raid_disks;
@@ -7718,7 +7787,7 @@
} else {
int d;
spin_lock_irq(&conf->device_lock);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irq(&conf->device_lock);
for (d = conf->raid_disks ;
d < conf->raid_disks - mddev->delta_disks;
@@ -7829,8 +7898,9 @@
mddev->new_chunk_sectors = chunksect;
ret = setup_conf(mddev);
- if (!IS_ERR_VALUE(ret))
- clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
+ if (!IS_ERR(ret))
+ mddev_clear_unsupported_flags(mddev,
+ UNSUPPORTED_MDDEV_FLAGS);
return ret;
}
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index ed8e136..1440fa2 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -322,6 +322,11 @@
* data and parity being written are in the journal
* device
*/
+ R5_OrigPageUPTDODATE, /* with write back cache, we read old data into
+ * dev->orig_page for prexor. When this flag is
+ * set, orig_page contains latest data in the
+ * raid disk.
+ */
};
/*
@@ -753,6 +758,7 @@
extern struct stripe_head *
raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
int previous, int noblock, int noquiesce);
+extern int raid5_calc_degraded(struct r5conf *conf);
extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev);
extern void r5l_exit_log(struct r5l_log *log);
extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh);
@@ -781,4 +787,5 @@
extern void r5c_check_stripe_cache_usage(struct r5conf *conf);
extern void r5c_check_cached_full_stripe(struct r5conf *conf);
extern struct md_sysfs_entry r5c_journal_mode;
+extern void r5c_update_on_rdev_error(struct mddev *mddev);
#endif
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index 0ea4efb..ccda41c 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -30,8 +30,9 @@
#include "cec-priv.h"
-static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx);
-static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx);
+static void cec_fill_msg_report_features(struct cec_adapter *adap,
+ struct cec_msg *msg,
+ unsigned int la_idx);
/*
* 400 ms is the time it takes for one 16 byte message to be
@@ -288,10 +289,10 @@
/* Mark it as an error */
data->msg.tx_ts = ktime_get_ns();
- data->msg.tx_status = CEC_TX_STATUS_ERROR |
- CEC_TX_STATUS_MAX_RETRIES;
+ data->msg.tx_status |= CEC_TX_STATUS_ERROR |
+ CEC_TX_STATUS_MAX_RETRIES;
+ data->msg.tx_error_cnt++;
data->attempts = 0;
- data->msg.tx_error_cnt = 1;
/* Queue transmitted message for monitoring purposes */
cec_queue_msg_monitor(data->adap, &data->msg, 1);
@@ -611,8 +612,7 @@
}
memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len);
if (msg->len == 1) {
- if (cec_msg_initiator(msg) != 0xf ||
- cec_msg_destination(msg) == 0xf) {
+ if (cec_msg_destination(msg) == 0xf) {
dprintk(1, "cec_transmit_msg: invalid poll message\n");
return -EINVAL;
}
@@ -637,7 +637,7 @@
dprintk(1, "cec_transmit_msg: destination is the adapter itself\n");
return -EINVAL;
}
- if (cec_msg_initiator(msg) != 0xf &&
+ if (msg->len > 1 && adap->is_configured &&
!cec_has_log_addr(adap, cec_msg_initiator(msg))) {
dprintk(1, "cec_transmit_msg: initiator has unknown logical address %d\n",
cec_msg_initiator(msg));
@@ -851,7 +851,7 @@
[CEC_MSG_REQUEST_ARC_TERMINATION] = 2 | DIRECTED,
[CEC_MSG_TERMINATE_ARC] = 2 | DIRECTED,
[CEC_MSG_REQUEST_CURRENT_LATENCY] = 4 | BCAST,
- [CEC_MSG_REPORT_CURRENT_LATENCY] = 7 | BCAST,
+ [CEC_MSG_REPORT_CURRENT_LATENCY] = 6 | BCAST,
[CEC_MSG_CDC_MESSAGE] = 2 | BCAST,
};
@@ -1071,7 +1071,7 @@
/* Send poll message */
msg.len = 1;
- msg.msg[0] = 0xf0 | log_addr;
+ msg.msg[0] = (log_addr << 4) | log_addr;
err = cec_transmit_msg_fh(adap, &msg, NULL, true);
/*
@@ -1205,7 +1205,7 @@
las->log_addr[i] = CEC_LOG_ADDR_INVALID;
if (last_la == CEC_LOG_ADDR_INVALID ||
last_la == CEC_LOG_ADDR_UNREGISTERED ||
- !(last_la & type2mask[type]))
+ !((1 << last_la) & type2mask[type]))
last_la = la_list[0];
err = cec_config_log_addr(adap, i, last_la);
@@ -1250,30 +1250,49 @@
for (i = 1; i < las->num_log_addrs; i++)
las->log_addr[i] = CEC_LOG_ADDR_INVALID;
}
+ for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++)
+ las->log_addr[i] = CEC_LOG_ADDR_INVALID;
adap->is_configured = true;
adap->is_configuring = false;
cec_post_state_event(adap);
- mutex_unlock(&adap->lock);
+ /*
+ * Now post the Report Features and Report Physical Address broadcast
+ * messages. Note that these are non-blocking transmits, meaning that
+ * they are just queued up and once adap->lock is unlocked the main
+ * thread will kick in and start transmitting these.
+ *
+ * If after this function is done (but before one or more of these
+ * messages are actually transmitted) the CEC adapter is unconfigured,
+ * then any remaining messages will be dropped by the main thread.
+ */
for (i = 0; i < las->num_log_addrs; i++) {
+ struct cec_msg msg = {};
+
if (las->log_addr[i] == CEC_LOG_ADDR_INVALID ||
(las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY))
continue;
- /*
- * Report Features must come first according
- * to CEC 2.0
- */
- if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED)
- cec_report_features(adap, i);
- cec_report_phys_addr(adap, i);
+ msg.msg[0] = (las->log_addr[i] << 4) | 0x0f;
+
+ /* Report Features must come first according to CEC 2.0 */
+ if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED &&
+ adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0) {
+ cec_fill_msg_report_features(adap, &msg, i);
+ cec_transmit_msg_fh(adap, &msg, NULL, false);
+ }
+
+ /* Report Physical Address */
+ cec_msg_report_physical_addr(&msg, adap->phys_addr,
+ las->primary_device_type[i]);
+ dprintk(2, "config: la %d pa %x.%x.%x.%x\n",
+ las->log_addr[i],
+ cec_phys_addr_exp(adap->phys_addr));
+ cec_transmit_msg_fh(adap, &msg, NULL, false);
}
- for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++)
- las->log_addr[i] = CEC_LOG_ADDR_INVALID;
- mutex_lock(&adap->lock);
adap->kthread_config = NULL;
- mutex_unlock(&adap->lock);
complete(&adap->config_completion);
+ mutex_unlock(&adap->lock);
return 0;
unconfigure:
@@ -1526,52 +1545,32 @@
/* High-level core CEC message handling */
-/* Transmit the Report Features message */
-static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx)
+/* Fill in the Report Features message */
+static void cec_fill_msg_report_features(struct cec_adapter *adap,
+ struct cec_msg *msg,
+ unsigned int la_idx)
{
- struct cec_msg msg = { };
const struct cec_log_addrs *las = &adap->log_addrs;
const u8 *features = las->features[la_idx];
bool op_is_dev_features = false;
unsigned int idx;
- /* This is 2.0 and up only */
- if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0)
- return 0;
-
/* Report Features */
- msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f;
- msg.len = 4;
- msg.msg[1] = CEC_MSG_REPORT_FEATURES;
- msg.msg[2] = adap->log_addrs.cec_version;
- msg.msg[3] = las->all_device_types[la_idx];
+ msg->msg[0] = (las->log_addr[la_idx] << 4) | 0x0f;
+ msg->len = 4;
+ msg->msg[1] = CEC_MSG_REPORT_FEATURES;
+ msg->msg[2] = adap->log_addrs.cec_version;
+ msg->msg[3] = las->all_device_types[la_idx];
/* Write RC Profiles first, then Device Features */
for (idx = 0; idx < ARRAY_SIZE(las->features[0]); idx++) {
- msg.msg[msg.len++] = features[idx];
+ msg->msg[msg->len++] = features[idx];
if ((features[idx] & CEC_OP_FEAT_EXT) == 0) {
if (op_is_dev_features)
break;
op_is_dev_features = true;
}
}
- return cec_transmit_msg(adap, &msg, false);
-}
-
-/* Transmit the Report Physical Address message */
-static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx)
-{
- const struct cec_log_addrs *las = &adap->log_addrs;
- struct cec_msg msg = { };
-
- /* Report Physical Address */
- msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f;
- cec_msg_report_physical_addr(&msg, adap->phys_addr,
- las->primary_device_type[la_idx]);
- dprintk(2, "config: la %d pa %x.%x.%x.%x\n",
- las->log_addr[la_idx],
- cec_phys_addr_exp(adap->phys_addr));
- return cec_transmit_msg(adap, &msg, false);
}
/* Transmit the Feature Abort message */
@@ -1777,9 +1776,10 @@
}
case CEC_MSG_GIVE_FEATURES:
- if (adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0)
- return cec_report_features(adap, la_idx);
- return 0;
+ if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0)
+ return cec_feature_abort(adap, msg);
+ cec_fill_msg_report_features(adap, &tx_cec_msg, la_idx);
+ return cec_transmit_msg(adap, &tx_cec_msg, false);
default:
/*
diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c
index bc5e8cf..8f11d7e 100644
--- a/drivers/media/dvb-core/dvb_net.c
+++ b/drivers/media/dvb-core/dvb_net.c
@@ -719,6 +719,9 @@
skb_copy_from_linear_data(h->priv->ule_skb, dest_addr,
ETH_ALEN);
skb_pull(h->priv->ule_skb, ETH_ALEN);
+ } else {
+ /* dest_addr buffer is only valid if h->priv->ule_dbit == 0 */
+ eth_zero_addr(dest_addr);
}
/* Handle ULE Extension Headers. */
@@ -750,16 +753,8 @@
if (!h->priv->ule_bridged) {
skb_push(h->priv->ule_skb, ETH_HLEN);
h->ethh = (struct ethhdr *)h->priv->ule_skb->data;
- if (!h->priv->ule_dbit) {
- /*
- * dest_addr buffer is only valid if
- * h->priv->ule_dbit == 0
- */
- memcpy(h->ethh->h_dest, dest_addr, ETH_ALEN);
- eth_zero_addr(h->ethh->h_source);
- } else /* zeroize source and dest */
- memset(h->ethh, 0, ETH_ALEN * 2);
-
+ memcpy(h->ethh->h_dest, dest_addr, ETH_ALEN);
+ eth_zero_addr(h->ethh->h_source);
h->ethh->h_proto = htons(h->priv->ule_sndu_type);
}
/* else: skb is in correct state; nothing to do. */
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index b31fa6f..b979ea1 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -655,6 +655,7 @@
config VIDEO_S5K4ECGX
tristate "Samsung S5K4ECGX sensor support"
depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+ select CRC32
---help---
This is a V4L2 sensor-level driver for Samsung S5K4ECGX 5M
camera sensor with an embedded SoC image signal processor.
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index 59872b3..f4e92bd 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -2741,9 +2741,7 @@
* I2C Driver
*/
-#ifdef CONFIG_PM
-
-static int smiapp_suspend(struct device *dev)
+static int __maybe_unused smiapp_suspend(struct device *dev)
{
struct i2c_client *client = to_i2c_client(dev);
struct v4l2_subdev *subdev = i2c_get_clientdata(client);
@@ -2768,7 +2766,7 @@
return 0;
}
-static int smiapp_resume(struct device *dev)
+static int __maybe_unused smiapp_resume(struct device *dev)
{
struct i2c_client *client = to_i2c_client(dev);
struct v4l2_subdev *subdev = i2c_get_clientdata(client);
@@ -2783,13 +2781,6 @@
return rval;
}
-#else
-
-#define smiapp_suspend NULL
-#define smiapp_resume NULL
-
-#endif /* CONFIG_PM */
-
static struct smiapp_hwconfig *smiapp_get_hwconfig(struct device *dev)
{
struct smiapp_hwconfig *hwcfg;
@@ -2913,13 +2904,9 @@
if (IS_ERR(sensor->xshutdown))
return PTR_ERR(sensor->xshutdown);
- pm_runtime_enable(&client->dev);
-
- rval = pm_runtime_get_sync(&client->dev);
- if (rval < 0) {
- rval = -ENODEV;
- goto out_power_off;
- }
+ rval = smiapp_power_on(&client->dev);
+ if (rval < 0)
+ return rval;
rval = smiapp_identify_module(sensor);
if (rval) {
@@ -3100,6 +3087,9 @@
if (rval < 0)
goto out_media_entity_cleanup;
+ pm_runtime_set_active(&client->dev);
+ pm_runtime_get_noresume(&client->dev);
+ pm_runtime_enable(&client->dev);
pm_runtime_set_autosuspend_delay(&client->dev, 1000);
pm_runtime_use_autosuspend(&client->dev);
pm_runtime_put_autosuspend(&client->dev);
@@ -3113,8 +3103,7 @@
smiapp_cleanup(sensor);
out_power_off:
- pm_runtime_put(&client->dev);
- pm_runtime_disable(&client->dev);
+ smiapp_power_off(&client->dev);
return rval;
}
@@ -3127,8 +3116,10 @@
v4l2_async_unregister_subdev(subdev);
- pm_runtime_suspend(&client->dev);
pm_runtime_disable(&client->dev);
+ if (!pm_runtime_status_suspended(&client->dev))
+ smiapp_power_off(&client->dev);
+ pm_runtime_set_suspended(&client->dev);
for (i = 0; i < sensor->ssds_used; i++) {
v4l2_device_unregister_subdev(&sensor->ssds[i].sd);
diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c
index 3a0fe8c..48646a7 100644
--- a/drivers/media/i2c/tvp5150.c
+++ b/drivers/media/i2c/tvp5150.c
@@ -291,8 +291,12 @@
tvp5150_write(sd, TVP5150_OP_MODE_CTL, opmode);
tvp5150_write(sd, TVP5150_VD_IN_SRC_SEL_1, input);
- /* Svideo should enable YCrCb output and disable GPCL output
- * For Composite and TV, it should be the reverse
+ /*
+ * Setup the FID/GLCO/VLK/HVLK and INTREQ/GPCL/VBLK output signals. For
+ * S-Video we output the vertical lock (VLK) signal on FID/GLCO/VLK/HVLK
+ * and set INTREQ/GPCL/VBLK to logic 0. For composite we output the
+ * field indicator (FID) signal on FID/GLCO/VLK/HVLK and set
+ * INTREQ/GPCL/VBLK to logic 1.
*/
val = tvp5150_read(sd, TVP5150_MISC_CTL);
if (val < 0) {
@@ -301,9 +305,9 @@
}
if (decoder->input == TVP5150_SVIDEO)
- val = (val & ~0x40) | 0x10;
+ val = (val & ~TVP5150_MISC_CTL_GPCL) | TVP5150_MISC_CTL_HVLK;
else
- val = (val & ~0x10) | 0x40;
+ val = (val & ~TVP5150_MISC_CTL_HVLK) | TVP5150_MISC_CTL_GPCL;
tvp5150_write(sd, TVP5150_MISC_CTL, val);
};
@@ -455,7 +459,12 @@
},{ /* Automatic offset and AGC enabled */
TVP5150_ANAL_CHL_CTL, 0x15
},{ /* Activate YCrCb output 0x9 or 0xd ? */
- TVP5150_MISC_CTL, 0x6f
+ TVP5150_MISC_CTL, TVP5150_MISC_CTL_GPCL |
+ TVP5150_MISC_CTL_INTREQ_OE |
+ TVP5150_MISC_CTL_YCBCR_OE |
+ TVP5150_MISC_CTL_SYNC_OE |
+ TVP5150_MISC_CTL_VBLANK |
+ TVP5150_MISC_CTL_CLOCK_OE,
},{ /* Activates video std autodetection for all standards */
TVP5150_AUTOSW_MSK, 0x0
},{ /* Default format: 0x47. For 4:2:2: 0x40 */
@@ -861,8 +870,6 @@
f = &format->format;
- tvp5150_reset(sd, 0);
-
f->width = decoder->rect.width;
f->height = decoder->rect.height / 2;
@@ -1051,21 +1058,27 @@
static int tvp5150_s_stream(struct v4l2_subdev *sd, int enable)
{
struct tvp5150 *decoder = to_tvp5150(sd);
- /* Output format: 8-bit ITU-R BT.656 with embedded syncs */
- int val = 0x09;
+ int val;
- /* Output format: 8-bit 4:2:2 YUV with discrete sync */
- if (decoder->mbus_type == V4L2_MBUS_PARALLEL)
- val = 0x0d;
+ /* Enable or disable the video output signals. */
+ val = tvp5150_read(sd, TVP5150_MISC_CTL);
+ if (val < 0)
+ return val;
- /* Initializes TVP5150 to its default values */
- /* # set PCLK (27MHz) */
- tvp5150_write(sd, TVP5150_CONF_SHARED_PIN, 0x00);
+ val &= ~(TVP5150_MISC_CTL_YCBCR_OE | TVP5150_MISC_CTL_SYNC_OE |
+ TVP5150_MISC_CTL_CLOCK_OE);
- if (enable)
- tvp5150_write(sd, TVP5150_MISC_CTL, val);
- else
- tvp5150_write(sd, TVP5150_MISC_CTL, 0x00);
+ if (enable) {
+ /*
+ * Enable the YCbCr and clock outputs. In discrete sync mode
+ * (non-BT.656) additionally enable the the sync outputs.
+ */
+ val |= TVP5150_MISC_CTL_YCBCR_OE | TVP5150_MISC_CTL_CLOCK_OE;
+ if (decoder->mbus_type == V4L2_MBUS_PARALLEL)
+ val |= TVP5150_MISC_CTL_SYNC_OE;
+ }
+
+ tvp5150_write(sd, TVP5150_MISC_CTL, val);
return 0;
}
@@ -1524,7 +1537,6 @@
res = core->hdl.error;
goto err;
}
- v4l2_ctrl_handler_setup(&core->hdl);
/* Default is no cropping */
core->rect.top = 0;
@@ -1535,6 +1547,8 @@
core->rect.left = 0;
core->rect.width = TVP5150_H_MAX;
+ tvp5150_reset(sd, 0); /* Calls v4l2_ctrl_handler_setup() */
+
res = v4l2_async_register_subdev(sd);
if (res < 0)
goto err;
diff --git a/drivers/media/i2c/tvp5150_reg.h b/drivers/media/i2c/tvp5150_reg.h
index 25a9949..30a48c2 100644
--- a/drivers/media/i2c/tvp5150_reg.h
+++ b/drivers/media/i2c/tvp5150_reg.h
@@ -9,6 +9,15 @@
#define TVP5150_ANAL_CHL_CTL 0x01 /* Analog channel controls */
#define TVP5150_OP_MODE_CTL 0x02 /* Operation mode controls */
#define TVP5150_MISC_CTL 0x03 /* Miscellaneous controls */
+#define TVP5150_MISC_CTL_VBLK_GPCL BIT(7)
+#define TVP5150_MISC_CTL_GPCL BIT(6)
+#define TVP5150_MISC_CTL_INTREQ_OE BIT(5)
+#define TVP5150_MISC_CTL_HVLK BIT(4)
+#define TVP5150_MISC_CTL_YCBCR_OE BIT(3)
+#define TVP5150_MISC_CTL_SYNC_OE BIT(2)
+#define TVP5150_MISC_CTL_VBLANK BIT(1)
+#define TVP5150_MISC_CTL_CLOCK_OE BIT(0)
+
#define TVP5150_AUTOSW_MSK 0x04 /* Autoswitch mask: TVP5150A / TVP5150AM */
/* Reserved 05h */
diff --git a/drivers/media/pci/cobalt/cobalt-driver.c b/drivers/media/pci/cobalt/cobalt-driver.c
index 9796340..d5c911c 100644
--- a/drivers/media/pci/cobalt/cobalt-driver.c
+++ b/drivers/media/pci/cobalt/cobalt-driver.c
@@ -308,9 +308,7 @@
static void cobalt_free_msi(struct cobalt *cobalt, struct pci_dev *pci_dev)
{
free_irq(pci_dev->irq, (void *)cobalt);
-
- if (cobalt->msi_enabled)
- pci_disable_msi(pci_dev);
+ pci_free_irq_vectors(pci_dev);
}
static int cobalt_setup_pci(struct cobalt *cobalt, struct pci_dev *pci_dev,
@@ -387,14 +385,12 @@
from being generated. */
cobalt_set_interrupt(cobalt, false);
- if (pci_enable_msi_range(pci_dev, 1, 1) < 1) {
+ if (pci_alloc_irq_vectors(pci_dev, 1, 1, PCI_IRQ_MSI) < 1) {
cobalt_err("Could not enable MSI\n");
- cobalt->msi_enabled = false;
ret = -EIO;
goto err_release;
}
msi_config_show(cobalt, pci_dev);
- cobalt->msi_enabled = true;
/* Register IRQ */
if (request_irq(pci_dev->irq, cobalt_irq_handler, IRQF_SHARED,
diff --git a/drivers/media/pci/cobalt/cobalt-driver.h b/drivers/media/pci/cobalt/cobalt-driver.h
index ed00dc9..00f773e 100644
--- a/drivers/media/pci/cobalt/cobalt-driver.h
+++ b/drivers/media/pci/cobalt/cobalt-driver.h
@@ -287,8 +287,6 @@
u32 irq_none;
u32 irq_full_fifo;
- bool msi_enabled;
-
/* omnitek dma */
int dma_channels;
int first_fifo_channel;
diff --git a/drivers/media/usb/dvb-usb/pctv452e.c b/drivers/media/usb/dvb-usb/pctv452e.c
index 07fa08b..d54ebe7 100644
--- a/drivers/media/usb/dvb-usb/pctv452e.c
+++ b/drivers/media/usb/dvb-usb/pctv452e.c
@@ -97,14 +97,13 @@
u8 c; /* transaction counter, wraps around... */
u8 initialized; /* set to 1 if 0x15 has been sent */
u16 last_rc_key;
-
- unsigned char data[80];
};
static int tt3650_ci_msg(struct dvb_usb_device *d, u8 cmd, u8 *data,
unsigned int write_len, unsigned int read_len)
{
struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
+ u8 *buf;
u8 id;
unsigned int rlen;
int ret;
@@ -114,36 +113,39 @@
return -EIO;
}
- mutex_lock(&state->ca_mutex);
+ buf = kmalloc(64, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
id = state->c++;
- state->data[0] = SYNC_BYTE_OUT;
- state->data[1] = id;
- state->data[2] = cmd;
- state->data[3] = write_len;
+ buf[0] = SYNC_BYTE_OUT;
+ buf[1] = id;
+ buf[2] = cmd;
+ buf[3] = write_len;
- memcpy(state->data + 4, data, write_len);
+ memcpy(buf + 4, data, write_len);
rlen = (read_len > 0) ? 64 : 0;
- ret = dvb_usb_generic_rw(d, state->data, 4 + write_len,
- state->data, rlen, /* delay_ms */ 0);
+ ret = dvb_usb_generic_rw(d, buf, 4 + write_len,
+ buf, rlen, /* delay_ms */ 0);
if (0 != ret)
goto failed;
ret = -EIO;
- if (SYNC_BYTE_IN != state->data[0] || id != state->data[1])
+ if (SYNC_BYTE_IN != buf[0] || id != buf[1])
goto failed;
- memcpy(data, state->data + 4, read_len);
+ memcpy(data, buf + 4, read_len);
- mutex_unlock(&state->ca_mutex);
+ kfree(buf);
return 0;
failed:
err("CI error %d; %02X %02X %02X -> %*ph.",
- ret, SYNC_BYTE_OUT, id, cmd, 3, state->data);
+ ret, SYNC_BYTE_OUT, id, cmd, 3, buf);
- mutex_unlock(&state->ca_mutex);
+ kfree(buf);
return ret;
}
@@ -410,53 +412,57 @@
u8 *rcv_buf, u8 rcv_len)
{
struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
+ u8 *buf;
u8 id;
int ret;
- mutex_lock(&state->ca_mutex);
+ buf = kmalloc(64, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
id = state->c++;
ret = -EINVAL;
if (snd_len > 64 - 7 || rcv_len > 64 - 7)
goto failed;
- state->data[0] = SYNC_BYTE_OUT;
- state->data[1] = id;
- state->data[2] = PCTV_CMD_I2C;
- state->data[3] = snd_len + 3;
- state->data[4] = addr << 1;
- state->data[5] = snd_len;
- state->data[6] = rcv_len;
+ buf[0] = SYNC_BYTE_OUT;
+ buf[1] = id;
+ buf[2] = PCTV_CMD_I2C;
+ buf[3] = snd_len + 3;
+ buf[4] = addr << 1;
+ buf[5] = snd_len;
+ buf[6] = rcv_len;
- memcpy(state->data + 7, snd_buf, snd_len);
+ memcpy(buf + 7, snd_buf, snd_len);
- ret = dvb_usb_generic_rw(d, state->data, 7 + snd_len,
- state->data, /* rcv_len */ 64,
+ ret = dvb_usb_generic_rw(d, buf, 7 + snd_len,
+ buf, /* rcv_len */ 64,
/* delay_ms */ 0);
if (ret < 0)
goto failed;
/* TT USB protocol error. */
ret = -EIO;
- if (SYNC_BYTE_IN != state->data[0] || id != state->data[1])
+ if (SYNC_BYTE_IN != buf[0] || id != buf[1])
goto failed;
/* I2C device didn't respond as expected. */
ret = -EREMOTEIO;
- if (state->data[5] < snd_len || state->data[6] < rcv_len)
+ if (buf[5] < snd_len || buf[6] < rcv_len)
goto failed;
- memcpy(rcv_buf, state->data + 7, rcv_len);
- mutex_unlock(&state->ca_mutex);
+ memcpy(rcv_buf, buf + 7, rcv_len);
+ kfree(buf);
return rcv_len;
failed:
err("I2C error %d; %02X %02X %02X %02X %02X -> %*ph",
ret, SYNC_BYTE_OUT, id, addr << 1, snd_len, rcv_len,
- 7, state->data);
+ 7, buf);
- mutex_unlock(&state->ca_mutex);
+ kfree(buf);
return ret;
}
@@ -505,7 +511,7 @@
static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
{
struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
- u8 *rx;
+ u8 *b0, *rx;
int ret;
info("%s: %d\n", __func__, i);
@@ -516,11 +522,12 @@
if (state->initialized)
return 0;
- rx = kmalloc(PCTV_ANSWER_LEN, GFP_KERNEL);
- if (!rx)
+ b0 = kmalloc(5 + PCTV_ANSWER_LEN, GFP_KERNEL);
+ if (!b0)
return -ENOMEM;
- mutex_lock(&state->ca_mutex);
+ rx = b0 + 5;
+
/* hmm where shoud this should go? */
ret = usb_set_interface(d->udev, 0, ISOC_INTERFACE_ALTERNATIVE);
if (ret != 0)
@@ -528,66 +535,70 @@
__func__, ret);
/* this is a one-time initialization, dont know where to put */
- state->data[0] = 0xaa;
- state->data[1] = state->c++;
- state->data[2] = PCTV_CMD_RESET;
- state->data[3] = 1;
- state->data[4] = 0;
+ b0[0] = 0xaa;
+ b0[1] = state->c++;
+ b0[2] = PCTV_CMD_RESET;
+ b0[3] = 1;
+ b0[4] = 0;
/* reset board */
- ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0);
+ ret = dvb_usb_generic_rw(d, b0, 5, rx, PCTV_ANSWER_LEN, 0);
if (ret)
goto ret;
- state->data[1] = state->c++;
- state->data[4] = 1;
+ b0[1] = state->c++;
+ b0[4] = 1;
/* reset board (again?) */
- ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0);
+ ret = dvb_usb_generic_rw(d, b0, 5, rx, PCTV_ANSWER_LEN, 0);
if (ret)
goto ret;
state->initialized = 1;
ret:
- mutex_unlock(&state->ca_mutex);
- kfree(rx);
+ kfree(b0);
return ret;
}
static int pctv452e_rc_query(struct dvb_usb_device *d)
{
struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
+ u8 *b, *rx;
int ret, i;
u8 id;
- mutex_lock(&state->ca_mutex);
+ b = kmalloc(CMD_BUFFER_SIZE + PCTV_ANSWER_LEN, GFP_KERNEL);
+ if (!b)
+ return -ENOMEM;
+
+ rx = b + CMD_BUFFER_SIZE;
+
id = state->c++;
/* prepare command header */
- state->data[0] = SYNC_BYTE_OUT;
- state->data[1] = id;
- state->data[2] = PCTV_CMD_IR;
- state->data[3] = 0;
+ b[0] = SYNC_BYTE_OUT;
+ b[1] = id;
+ b[2] = PCTV_CMD_IR;
+ b[3] = 0;
/* send ir request */
- ret = dvb_usb_generic_rw(d, state->data, 4,
- state->data, PCTV_ANSWER_LEN, 0);
+ ret = dvb_usb_generic_rw(d, b, 4, rx, PCTV_ANSWER_LEN, 0);
if (ret != 0)
goto ret;
if (debug > 3) {
- info("%s: read: %2d: %*ph: ", __func__, ret, 3, state->data);
- for (i = 0; (i < state->data[3]) && ((i + 3) < PCTV_ANSWER_LEN); i++)
- info(" %02x", state->data[i + 3]);
+ info("%s: read: %2d: %*ph: ", __func__, ret, 3, rx);
+ for (i = 0; (i < rx[3]) && ((i+3) < PCTV_ANSWER_LEN); i++)
+ info(" %02x", rx[i+3]);
info("\n");
}
- if ((state->data[3] == 9) && (state->data[12] & 0x01)) {
+ if ((rx[3] == 9) && (rx[12] & 0x01)) {
/* got a "press" event */
- state->last_rc_key = RC_SCANCODE_RC5(state->data[7], state->data[6]);
+ state->last_rc_key = RC_SCANCODE_RC5(rx[7], rx[6]);
if (debug > 2)
info("%s: cmd=0x%02x sys=0x%02x\n",
- __func__, state->data[6], state->data[7]);
+ __func__, rx[6], rx[7]);
rc_keydown(d->rc_dev, RC_TYPE_RC5, state->last_rc_key, 0);
} else if (state->last_rc_key) {
@@ -595,7 +606,7 @@
state->last_rc_key = 0;
}
ret:
- mutex_unlock(&state->ca_mutex);
+ kfree(b);
return ret;
}
diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c
index a4dcaec..8c1f926 100644
--- a/drivers/media/usb/siano/smsusb.c
+++ b/drivers/media/usb/siano/smsusb.c
@@ -218,22 +218,30 @@
static int smsusb_sendrequest(void *context, void *buffer, size_t size)
{
struct smsusb_device_t *dev = (struct smsusb_device_t *) context;
- struct sms_msg_hdr *phdr = (struct sms_msg_hdr *) buffer;
- int dummy;
+ struct sms_msg_hdr *phdr;
+ int dummy, ret;
if (dev->state != SMSUSB_ACTIVE) {
pr_debug("Device not active yet\n");
return -ENOENT;
}
+ phdr = kmalloc(size, GFP_KERNEL);
+ if (!phdr)
+ return -ENOMEM;
+ memcpy(phdr, buffer, size);
+
pr_debug("sending %s(%d) size: %d\n",
smscore_translate_msg(phdr->msg_type), phdr->msg_type,
phdr->msg_length);
smsendian_handle_tx_message((struct sms_msg_data *) phdr);
- smsendian_handle_message_header((struct sms_msg_hdr *)buffer);
- return usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2),
- buffer, size, &dummy, 1000);
+ smsendian_handle_message_header((struct sms_msg_hdr *)phdr);
+ ret = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2),
+ phdr, size, &dummy, 1000);
+
+ kfree(phdr);
+ return ret;
}
static char *smsusb1_fw_lkup[] = {
diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index a0547db..76382c8 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -330,7 +330,7 @@
struct ms_id_register id_reg;
if (!(*mrq)) {
- memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, NULL,
+ memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, &id_reg,
sizeof(struct ms_id_register));
*mrq = &card->current_mrq;
return 0;
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index 1ef7575..be42957 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -56,6 +56,7 @@
* document number TBD : Wildcat Point-LP
* document number TBD : 9 Series
* document number TBD : Lewisburg
+ * document number TBD : Apollo Lake SoC
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -83,6 +84,17 @@
#define ACPIBASE_GCS_OFF 0x3410
#define ACPIBASE_GCS_END 0x3414
+#define SPIBASE_BYT 0x54
+#define SPIBASE_BYT_SZ 512
+#define SPIBASE_BYT_EN BIT(1)
+
+#define SPIBASE_LPT 0x3800
+#define SPIBASE_LPT_SZ 512
+#define BCR 0xdc
+#define BCR_WPD BIT(0)
+
+#define SPIBASE_APL_SZ 4096
+
#define GPIOBASE_ICH0 0x58
#define GPIOCTRL_ICH0 0x5C
#define GPIOBASE_ICH6 0x48
@@ -133,6 +145,12 @@
},
};
+static struct resource intel_spi_res[] = {
+ {
+ .flags = IORESOURCE_MEM,
+ }
+};
+
static struct mfd_cell lpc_ich_wdt_cell = {
.name = "iTCO_wdt",
.num_resources = ARRAY_SIZE(wdt_ich_res),
@@ -147,6 +165,14 @@
.ignore_resource_conflicts = true,
};
+
+static struct mfd_cell lpc_ich_spi_cell = {
+ .name = "intel-spi",
+ .num_resources = ARRAY_SIZE(intel_spi_res),
+ .resources = intel_spi_res,
+ .ignore_resource_conflicts = true,
+};
+
/* chipset related info */
enum lpc_chipsets {
LPC_ICH = 0, /* ICH */
@@ -216,6 +242,7 @@
LPC_BRASWELL, /* Braswell SoC */
LPC_LEWISBURG, /* Lewisburg */
LPC_9S, /* 9 Series */
+ LPC_APL, /* Apollo Lake SoC */
};
static struct lpc_ich_info lpc_chipset_info[] = {
@@ -494,10 +521,12 @@
.name = "Lynx Point",
.iTCO_version = 2,
.gpio_version = ICH_V5_GPIO,
+ .spi_type = INTEL_SPI_LPT,
},
[LPC_LPT_LP] = {
.name = "Lynx Point_LP",
.iTCO_version = 2,
+ .spi_type = INTEL_SPI_LPT,
},
[LPC_WBG] = {
.name = "Wellsburg",
@@ -511,6 +540,7 @@
[LPC_BAYTRAIL] = {
.name = "Bay Trail SoC",
.iTCO_version = 3,
+ .spi_type = INTEL_SPI_BYT,
},
[LPC_COLETO] = {
.name = "Coleto Creek",
@@ -519,10 +549,12 @@
[LPC_WPT_LP] = {
.name = "Wildcat Point_LP",
.iTCO_version = 2,
+ .spi_type = INTEL_SPI_LPT,
},
[LPC_BRASWELL] = {
.name = "Braswell SoC",
.iTCO_version = 3,
+ .spi_type = INTEL_SPI_BYT,
},
[LPC_LEWISBURG] = {
.name = "Lewisburg",
@@ -533,6 +565,10 @@
.iTCO_version = 2,
.gpio_version = ICH_V5_GPIO,
},
+ [LPC_APL] = {
+ .name = "Apollo Lake SoC",
+ .spi_type = INTEL_SPI_BXT,
+ },
};
/*
@@ -681,6 +717,7 @@
{ PCI_VDEVICE(INTEL, 0x3b14), LPC_3420},
{ PCI_VDEVICE(INTEL, 0x3b16), LPC_3450},
{ PCI_VDEVICE(INTEL, 0x5031), LPC_EP80579},
+ { PCI_VDEVICE(INTEL, 0x5ae8), LPC_APL},
{ PCI_VDEVICE(INTEL, 0x8c40), LPC_LPT},
{ PCI_VDEVICE(INTEL, 0x8c41), LPC_LPT},
{ PCI_VDEVICE(INTEL, 0x8c42), LPC_LPT},
@@ -1056,6 +1093,94 @@
return ret;
}
+static int lpc_ich_init_spi(struct pci_dev *dev)
+{
+ struct lpc_ich_priv *priv = pci_get_drvdata(dev);
+ struct resource *res = &intel_spi_res[0];
+ struct intel_spi_boardinfo *info;
+ u32 spi_base, rcba, bcr;
+
+ info = devm_kzalloc(&dev->dev, sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return -ENOMEM;
+
+ info->type = lpc_chipset_info[priv->chipset].spi_type;
+
+ switch (info->type) {
+ case INTEL_SPI_BYT:
+ pci_read_config_dword(dev, SPIBASE_BYT, &spi_base);
+ if (spi_base & SPIBASE_BYT_EN) {
+ res->start = spi_base & ~(SPIBASE_BYT_SZ - 1);
+ res->end = res->start + SPIBASE_BYT_SZ - 1;
+ }
+ break;
+
+ case INTEL_SPI_LPT:
+ pci_read_config_dword(dev, RCBABASE, &rcba);
+ if (rcba & 1) {
+ spi_base = round_down(rcba, SPIBASE_LPT_SZ);
+ res->start = spi_base + SPIBASE_LPT;
+ res->end = res->start + SPIBASE_LPT_SZ - 1;
+
+ /*
+ * Try to make the flash chip writeable now by
+ * setting BCR_WPD. It it fails we tell the driver
+ * that it can only read the chip.
+ */
+ pci_read_config_dword(dev, BCR, &bcr);
+ if (!(bcr & BCR_WPD)) {
+ bcr |= BCR_WPD;
+ pci_write_config_dword(dev, BCR, bcr);
+ pci_read_config_dword(dev, BCR, &bcr);
+ }
+ info->writeable = !!(bcr & BCR_WPD);
+ }
+ break;
+
+ case INTEL_SPI_BXT: {
+ unsigned int p2sb = PCI_DEVFN(13, 0);
+ unsigned int spi = PCI_DEVFN(13, 2);
+ struct pci_bus *bus = dev->bus;
+
+ /*
+ * The P2SB is hidden by BIOS and we need to unhide it in
+ * order to read BAR of the SPI flash device. Once that is
+ * done we hide it again.
+ */
+ pci_bus_write_config_byte(bus, p2sb, 0xe1, 0x0);
+ pci_bus_read_config_dword(bus, spi, PCI_BASE_ADDRESS_0,
+ &spi_base);
+ if (spi_base != ~0) {
+ res->start = spi_base & 0xfffffff0;
+ res->end = res->start + SPIBASE_APL_SZ - 1;
+
+ pci_bus_read_config_dword(bus, spi, BCR, &bcr);
+ if (!(bcr & BCR_WPD)) {
+ bcr |= BCR_WPD;
+ pci_bus_write_config_dword(bus, spi, BCR, bcr);
+ pci_bus_read_config_dword(bus, spi, BCR, &bcr);
+ }
+ info->writeable = !!(bcr & BCR_WPD);
+ }
+
+ pci_bus_write_config_byte(bus, p2sb, 0xe1, 0x1);
+ break;
+ }
+
+ default:
+ return -EINVAL;
+ }
+
+ if (!res->start)
+ return -ENODEV;
+
+ lpc_ich_spi_cell.platform_data = info;
+ lpc_ich_spi_cell.pdata_size = sizeof(*info);
+
+ return mfd_add_devices(&dev->dev, PLATFORM_DEVID_NONE,
+ &lpc_ich_spi_cell, 1, NULL, 0, NULL);
+}
+
static int lpc_ich_probe(struct pci_dev *dev,
const struct pci_device_id *id)
{
@@ -1099,6 +1224,12 @@
cell_added = true;
}
+ if (lpc_chipset_info[priv->chipset].spi_type) {
+ ret = lpc_ich_init_spi(dev);
+ if (!ret)
+ cell_added = true;
+ }
+
/*
* We only care if at least one or none of the cells registered
* successfully.
diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c
index 18e05ca..3600c99 100644
--- a/drivers/misc/mei/bus-fixup.c
+++ b/drivers/misc/mei/bus-fixup.c
@@ -152,6 +152,9 @@
{
int ret;
+ if (!cldev->bus->hbm_f_os_supported)
+ return;
+
ret = mei_cldev_enable(cldev);
if (ret)
return;
diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c
index e32a923..a617aa5 100644
--- a/drivers/misc/mei/debugfs.c
+++ b/drivers/misc/mei/debugfs.c
@@ -180,6 +180,8 @@
dev->hbm_f_ev_supported);
pos += scnprintf(buf + pos, bufsz - pos, "\tFA: %01d\n",
dev->hbm_f_fa_supported);
+ pos += scnprintf(buf + pos, bufsz - pos, "\tOS: %01d\n",
+ dev->hbm_f_os_supported);
}
pos += scnprintf(buf + pos, bufsz - pos, "pg: %s, %s\n",
diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c
index dd7f15a..25b4a1b 100644
--- a/drivers/misc/mei/hbm.c
+++ b/drivers/misc/mei/hbm.c
@@ -989,6 +989,10 @@
/* Fixed Address Client Support */
if (dev->version.major_version >= HBM_MAJOR_VERSION_FA)
dev->hbm_f_fa_supported = 1;
+
+ /* OS ver message Support */
+ if (dev->version.major_version >= HBM_MAJOR_VERSION_OS)
+ dev->hbm_f_os_supported = 1;
}
/**
diff --git a/drivers/misc/mei/hw.h b/drivers/misc/mei/hw.h
index 9daf3f9..e1e4d47 100644
--- a/drivers/misc/mei/hw.h
+++ b/drivers/misc/mei/hw.h
@@ -76,6 +76,12 @@
#define HBM_MINOR_VERSION_FA 0
#define HBM_MAJOR_VERSION_FA 2
+/*
+ * MEI version with OS ver message support
+ */
+#define HBM_MINOR_VERSION_OS 0
+#define HBM_MAJOR_VERSION_OS 2
+
/* Host bus message command opcode */
#define MEI_HBM_CMD_OP_MSK 0x7f
/* Host bus message command RESPONSE */
diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h
index 699693c..8dadb98 100644
--- a/drivers/misc/mei/mei_dev.h
+++ b/drivers/misc/mei/mei_dev.h
@@ -406,6 +406,7 @@
* @hbm_f_ev_supported : hbm feature event notification
* @hbm_f_fa_supported : hbm feature fixed address client
* @hbm_f_ie_supported : hbm feature immediate reply to enum request
+ * @hbm_f_os_supported : hbm feature support OS ver message
*
* @me_clients_rwsem: rw lock over me_clients list
* @me_clients : list of FW clients
@@ -487,6 +488,7 @@
unsigned int hbm_f_ev_supported:1;
unsigned int hbm_f_fa_supported:1;
unsigned int hbm_f_ie_supported:1;
+ unsigned int hbm_f_os_supported:1;
struct rw_semaphore me_clients_rwsem;
struct list_head me_clients;
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index b61b52f9..0fccca0 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1706,10 +1706,10 @@
err = mmc_select_hs400(card);
if (err)
goto free_card;
- } else if (mmc_card_hs(card)) {
+ } else {
/* Select the desired bus width optionally */
err = mmc_select_bus_width(card);
- if (err > 0) {
+ if (err > 0 && mmc_card_hs(card)) {
err = mmc_select_hs_ddr(card);
if (err)
goto free_card;
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index b11c345..e6ea850 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -506,9 +506,6 @@
}
} while (busy);
- if (host->ops->card_busy && send_status)
- return mmc_switch_status(card);
-
return 0;
}
@@ -577,24 +574,26 @@
if (!use_busy_signal)
goto out;
- /* Switch to new timing before poll and check switch status. */
- if (timing)
- mmc_set_timing(host, timing);
-
/*If SPI or used HW busy detection above, then we don't need to poll. */
if (((host->caps & MMC_CAP_WAIT_WHILE_BUSY) && use_r1b_resp) ||
- mmc_host_is_spi(host)) {
- if (send_status)
- err = mmc_switch_status(card);
+ mmc_host_is_spi(host))
goto out_tim;
- }
/* Let's try to poll to find out when the command is completed. */
err = mmc_poll_for_busy(card, timeout_ms, send_status, retry_crc_err);
+ if (err)
+ goto out;
out_tim:
- if (err && timing)
- mmc_set_timing(host, old_timing);
+ /* Switch to new timing before check switch status. */
+ if (timing)
+ mmc_set_timing(host, timing);
+
+ if (send_status) {
+ err = mmc_switch_status(card);
+ if (err && timing)
+ mmc_set_timing(host, old_timing);
+ }
out:
mmc_retune_release(host);
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index b44306b..73db085 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -3354,10 +3354,11 @@
if (!slot)
continue;
- if (slot->mmc->pm_flags & MMC_PM_KEEP_POWER) {
+ if (slot->mmc->pm_flags & MMC_PM_KEEP_POWER)
dw_mci_set_ios(slot->mmc, &slot->mmc->ios);
- dw_mci_setup_bus(slot, true);
- }
+
+ /* Force setup bus to guarantee available clock output */
+ dw_mci_setup_bus(slot, true);
}
/* Now that slots are all setup, we can enable card detect */
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index b352760..0973935 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -578,13 +578,15 @@
{
struct meson_host *host = dev_id;
struct mmc_request *mrq;
- struct mmc_command *cmd = host->cmd;
+ struct mmc_command *cmd;
u32 irq_en, status, raw_status;
irqreturn_t ret = IRQ_HANDLED;
if (WARN_ON(!host))
return IRQ_NONE;
+ cmd = host->cmd;
+
mrq = host->mrq;
if (WARN_ON(!mrq))
@@ -670,10 +672,10 @@
int ret = IRQ_HANDLED;
if (WARN_ON(!mrq))
- ret = IRQ_NONE;
+ return IRQ_NONE;
if (WARN_ON(!cmd))
- ret = IRQ_NONE;
+ return IRQ_NONE;
data = cmd->data;
if (data) {
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 01a8047..b597244 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1023,7 +1023,12 @@
if (!host->busy_status && busy_resp &&
!(status & (MCI_CMDCRCFAIL|MCI_CMDTIMEOUT)) &&
(readl(base + MMCISTATUS) & host->variant->busy_detect_flag)) {
- /* Unmask the busy IRQ */
+
+ /* Clear the busy start IRQ */
+ writel(host->variant->busy_detect_mask,
+ host->base + MMCICLEAR);
+
+ /* Unmask the busy end IRQ */
writel(readl(base + MMCIMASK0) |
host->variant->busy_detect_mask,
base + MMCIMASK0);
@@ -1038,10 +1043,14 @@
/*
* At this point we are not busy with a command, we have
- * not received a new busy request, mask the busy IRQ and
- * fall through to process the IRQ.
+ * not received a new busy request, clear and mask the busy
+ * end IRQ and fall through to process the IRQ.
*/
if (host->busy_status) {
+
+ writel(host->variant->busy_detect_mask,
+ host->base + MMCICLEAR);
+
writel(readl(base + MMCIMASK0) &
~host->variant->busy_detect_mask,
base + MMCIMASK0);
@@ -1283,12 +1292,21 @@
}
/*
- * We intentionally clear the MCI_ST_CARDBUSY IRQ here (if it's
- * enabled) since the HW seems to be triggering the IRQ on both
- * edges while monitoring DAT0 for busy completion.
+ * We intentionally clear the MCI_ST_CARDBUSY IRQ (if it's
+ * enabled) in mmci_cmd_irq() function where ST Micro busy
+ * detection variant is handled. Considering the HW seems to be
+ * triggering the IRQ on both edges while monitoring DAT0 for
+ * busy completion and that same status bit is used to monitor
+ * start and end of busy detection, special care must be taken
+ * to make sure that both start and end interrupts are always
+ * cleared one after the other.
*/
status &= readl(host->base + MMCIMASK0);
- writel(status, host->base + MMCICLEAR);
+ if (host->variant->busy_detect)
+ writel(status & ~host->variant->busy_detect_mask,
+ host->base + MMCICLEAR);
+ else
+ writel(status, host->base + MMCICLEAR);
dev_dbg(mmc_dev(host->mmc), "irq0 (data+cmd) %08x\n", status);
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index 44ecebd..c8b8ac6 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -309,6 +309,9 @@
cmd0 = BF_SSP(cmd->opcode, CMD0_CMD);
cmd1 = cmd->arg;
+ if (cmd->opcode == MMC_STOP_TRANSMISSION)
+ cmd0 |= BM_SSP_CMD0_APPEND_8CYC;
+
if (host->sdio_irq_en) {
ctrl0 |= BM_SSP_CTRL0_SDIO_IRQ_CHECK;
cmd0 |= BM_SSP_CMD0_CONT_CLKING_EN | BM_SSP_CMD0_SLOW_CLKING_EN;
@@ -417,8 +420,7 @@
ssp->base + HW_SSP_BLOCK_SIZE);
}
- if ((cmd->opcode == MMC_STOP_TRANSMISSION) ||
- (cmd->opcode == SD_IO_RW_EXTENDED))
+ if (cmd->opcode == SD_IO_RW_EXTENDED)
cmd0 |= BM_SSP_CMD0_APPEND_8CYC;
cmd1 = cmd->arg;
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 160f695..278a5a4 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -395,7 +395,8 @@
/* Power on the SDHCI controller and its children */
acpi_device_fix_up_power(device);
list_for_each_entry(child, &device->children, node)
- acpi_device_fix_up_power(child);
+ if (child->status.present && child->status.enabled)
+ acpi_device_fix_up_power(child);
if (acpi_bus_get_status(device) || !device->status.present)
return -ENODEV;
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 2390980..0def995 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2733,7 +2733,8 @@
if (intmask & SDHCI_INT_RETUNE)
mmc_retune_needed(host->mmc);
- if (intmask & SDHCI_INT_CARD_INT) {
+ if ((intmask & SDHCI_INT_CARD_INT) &&
+ (host->ier & SDHCI_INT_CARD_INT)) {
sdhci_enable_sdio_irq_nolock(host, false);
host->thread_isr |= SDHCI_INT_CARD_INT;
result = IRQ_WAKE_THREAD;
diff --git a/drivers/mtd/bcm47xxpart.c b/drivers/mtd/bcm47xxpart.c
index 283ff7e..d10fa6c 100644
--- a/drivers/mtd/bcm47xxpart.c
+++ b/drivers/mtd/bcm47xxpart.c
@@ -9,6 +9,7 @@
*
*/
+#include <linux/bcm47xx_nvram.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/slab.h>
@@ -83,6 +84,91 @@
return "rootfs";
}
+static int bcm47xxpart_parse_trx(struct mtd_info *master,
+ struct mtd_partition *trx,
+ struct mtd_partition *parts,
+ size_t parts_len)
+{
+ struct trx_header header;
+ size_t bytes_read;
+ int curr_part = 0;
+ int i, err;
+
+ if (parts_len < 3) {
+ pr_warn("No enough space to add TRX partitions!\n");
+ return -ENOMEM;
+ }
+
+ err = mtd_read(master, trx->offset, sizeof(header), &bytes_read,
+ (uint8_t *)&header);
+ if (err && !mtd_is_bitflip(err)) {
+ pr_err("mtd_read error while reading TRX header: %d\n", err);
+ return err;
+ }
+
+ i = 0;
+
+ /* We have LZMA loader if offset[2] points to sth */
+ if (header.offset[2]) {
+ bcm47xxpart_add_part(&parts[curr_part++], "loader",
+ trx->offset + header.offset[i], 0);
+ i++;
+ }
+
+ if (header.offset[i]) {
+ bcm47xxpart_add_part(&parts[curr_part++], "linux",
+ trx->offset + header.offset[i], 0);
+ i++;
+ }
+
+ if (header.offset[i]) {
+ size_t offset = trx->offset + header.offset[i];
+ const char *name = bcm47xxpart_trx_data_part_name(master,
+ offset);
+
+ bcm47xxpart_add_part(&parts[curr_part++], name, offset, 0);
+ i++;
+ }
+
+ /*
+ * Assume that every partition ends at the beginning of the one it is
+ * followed by.
+ */
+ for (i = 0; i < curr_part; i++) {
+ u64 next_part_offset = (i < curr_part - 1) ?
+ parts[i + 1].offset :
+ trx->offset + trx->size;
+
+ parts[i].size = next_part_offset - parts[i].offset;
+ }
+
+ return curr_part;
+}
+
+/**
+ * bcm47xxpart_bootpartition - gets index of TRX partition used by bootloader
+ *
+ * Some devices may have more than one TRX partition. In such case one of them
+ * is the main one and another a failsafe one. Bootloader may fallback to the
+ * failsafe firmware if it detects corruption of the main image.
+ *
+ * This function provides info about currently used TRX partition. It's the one
+ * containing kernel started by the bootloader.
+ */
+static int bcm47xxpart_bootpartition(void)
+{
+ char buf[4];
+ int bootpartition;
+
+ /* Check CFE environment variable */
+ if (bcm47xx_nvram_getenv("bootpartition", buf, sizeof(buf)) > 0) {
+ if (!kstrtoint(buf, 0, &bootpartition))
+ return bootpartition;
+ }
+
+ return 0;
+}
+
static int bcm47xxpart_parse(struct mtd_info *master,
const struct mtd_partition **pparts,
struct mtd_part_parser_data *data)
@@ -93,9 +179,8 @@
size_t bytes_read;
uint32_t offset;
uint32_t blocksize = master->erasesize;
- struct trx_header *trx;
- int trx_part = -1;
- int last_trx_part = -1;
+ int trx_parts[2]; /* Array with indexes of TRX partitions */
+ int trx_num = 0; /* Number of found TRX partitions */
int possible_nvram_sizes[] = { 0x8000, 0xF000, 0x10000, };
int err;
@@ -182,54 +267,18 @@
/* TRX */
if (buf[0x000 / 4] == TRX_MAGIC) {
- if (BCM47XXPART_MAX_PARTS - curr_part < 4) {
- pr_warn("Not enough partitions left to register trx, scanning stopped!\n");
- break;
- }
+ struct trx_header *trx;
- trx = (struct trx_header *)buf;
-
- trx_part = curr_part;
+ if (trx_num >= ARRAY_SIZE(trx_parts))
+ pr_warn("No enough space to store another TRX found at 0x%X\n",
+ offset);
+ else
+ trx_parts[trx_num++] = curr_part;
bcm47xxpart_add_part(&parts[curr_part++], "firmware",
offset, 0);
- i = 0;
- /* We have LZMA loader if offset[2] points to sth */
- if (trx->offset[2]) {
- bcm47xxpart_add_part(&parts[curr_part++],
- "loader",
- offset + trx->offset[i],
- 0);
- i++;
- }
-
- if (trx->offset[i]) {
- bcm47xxpart_add_part(&parts[curr_part++],
- "linux",
- offset + trx->offset[i],
- 0);
- i++;
- }
-
- /*
- * Pure rootfs size is known and can be calculated as:
- * trx->length - trx->offset[i]. We don't fill it as
- * we want to have jffs2 (overlay) in the same mtd.
- */
- if (trx->offset[i]) {
- const char *name;
-
- name = bcm47xxpart_trx_data_part_name(master, offset + trx->offset[i]);
- bcm47xxpart_add_part(&parts[curr_part++],
- name,
- offset + trx->offset[i],
- 0);
- i++;
- }
-
- last_trx_part = curr_part - 1;
-
/* Jump to the end of TRX */
+ trx = (struct trx_header *)buf;
offset = roundup(offset + trx->length, blocksize);
/* Next loop iteration will increase the offset */
offset -= blocksize;
@@ -307,9 +356,23 @@
parts[i + 1].offset : master->size;
parts[i].size = next_part_offset - parts[i].offset;
- if (i == last_trx_part && trx_part >= 0)
- parts[trx_part].size = next_part_offset -
- parts[trx_part].offset;
+ }
+
+ /* If there was TRX parse it now */
+ for (i = 0; i < trx_num; i++) {
+ struct mtd_partition *trx = &parts[trx_parts[i]];
+
+ if (i == bcm47xxpart_bootpartition()) {
+ int num_parts;
+
+ num_parts = bcm47xxpart_parse_trx(master, trx,
+ parts + curr_part,
+ BCM47XXPART_MAX_PARTS - curr_part);
+ if (num_parts > 0)
+ curr_part += num_parts;
+ } else {
+ trx->name = "failsafe";
+ }
}
*pparts = parts;
diff --git a/drivers/mtd/devices/bcm47xxsflash.c b/drivers/mtd/devices/bcm47xxsflash.c
index 514be04..e2bd818 100644
--- a/drivers/mtd/devices/bcm47xxsflash.c
+++ b/drivers/mtd/devices/bcm47xxsflash.c
@@ -105,15 +105,33 @@
size_t *retlen, u_char *buf)
{
struct bcm47xxsflash *b47s = mtd->priv;
+ size_t orig_len = len;
/* Check address range */
if ((from + len) > mtd->size)
return -EINVAL;
- memcpy_fromio(buf, b47s->window + from, len);
- *retlen = len;
+ /* Read as much as possible using fast MMIO window */
+ if (from < BCM47XXSFLASH_WINDOW_SZ) {
+ size_t memcpy_len;
- return len;
+ memcpy_len = min(len, (size_t)(BCM47XXSFLASH_WINDOW_SZ - from));
+ memcpy_fromio(buf, b47s->window + from, memcpy_len);
+ from += memcpy_len;
+ len -= memcpy_len;
+ buf += memcpy_len;
+ }
+
+ /* Use indirect access for content out of the window */
+ for (; len; len--) {
+ b47s->cc_write(b47s, BCMA_CC_FLASHADDR, from++);
+ bcm47xxsflash_cmd(b47s, OPCODE_ST_READ4B);
+ *buf++ = b47s->cc_read(b47s, BCMA_CC_FLASHDATA);
+ }
+
+ *retlen = orig_len;
+
+ return orig_len;
}
static int bcm47xxsflash_write_st(struct mtd_info *mtd, u32 offset, size_t len,
@@ -284,7 +302,6 @@
b47s = devm_kzalloc(dev, sizeof(*b47s), GFP_KERNEL);
if (!b47s)
return -ENOMEM;
- sflash->priv = b47s;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!res) {
@@ -334,6 +351,8 @@
b47s->size = sflash->size;
bcm47xxsflash_fill_mtd(b47s, &pdev->dev);
+ platform_set_drvdata(pdev, b47s);
+
err = mtd_device_parse_register(&b47s->mtd, probes, NULL, NULL, 0);
if (err) {
pr_err("Failed to register MTD device: %d\n", err);
@@ -349,8 +368,7 @@
static int bcm47xxsflash_bcma_remove(struct platform_device *pdev)
{
- struct bcma_sflash *sflash = dev_get_platdata(&pdev->dev);
- struct bcm47xxsflash *b47s = sflash->priv;
+ struct bcm47xxsflash *b47s = platform_get_drvdata(pdev);
mtd_device_unregister(&b47s->mtd);
iounmap(b47s->window);
diff --git a/drivers/mtd/devices/bcm47xxsflash.h b/drivers/mtd/devices/bcm47xxsflash.h
index 1564b62..b2d7b38 100644
--- a/drivers/mtd/devices/bcm47xxsflash.h
+++ b/drivers/mtd/devices/bcm47xxsflash.h
@@ -3,6 +3,8 @@
#include <linux/mtd/mtd.h>
+#define BCM47XXSFLASH_WINDOW_SZ SZ_16M
+
/* Used for ST flashes only. */
#define OPCODE_ST_WREN 0x0006 /* Write Enable */
#define OPCODE_ST_WRDIS 0x0004 /* Write Disable */
@@ -16,6 +18,7 @@
#define OPCODE_ST_RES 0x03ab /* Read Electronic Signature */
#define OPCODE_ST_CSA 0x1000 /* Keep chip select asserted */
#define OPCODE_ST_SSE 0x0220 /* Sub-sector Erase */
+#define OPCODE_ST_READ4B 0x6313 /* Read Data Bytes in 4Byte addressing mode */
/* Used for Atmel flashes only. */
#define OPCODE_AT_READ 0x07e8
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 9cf7fcd..c4df3b1 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -172,7 +172,8 @@
t[1].rx_buf = buf;
t[1].rx_nbits = m25p80_rx_nbits(nor);
- t[1].len = min(len, spi_max_transfer_size(spi));
+ t[1].len = min3(len, spi_max_transfer_size(spi),
+ spi_max_message_size(spi) - t[0].len);
spi_message_add_tail(&t[1], &m);
ret = spi_sync(spi, &m);
@@ -288,7 +289,6 @@
* should be kept for backward compatibility.
*/
{"at25df321a"}, {"at25df641"}, {"at26df081a"},
- {"mr25h256"},
{"mx25l4005a"}, {"mx25l1606e"}, {"mx25l6405d"}, {"mx25l12805d"},
{"mx25l25635e"},{"mx66l51235l"},
{"n25q064"}, {"n25q128a11"}, {"n25q128a13"}, {"n25q512a"},
@@ -305,6 +305,11 @@
{"m25p40-nonjedec"}, {"m25p80-nonjedec"}, {"m25p16-nonjedec"},
{"m25p32-nonjedec"}, {"m25p64-nonjedec"}, {"m25p128-nonjedec"},
+ /* Everspin MRAMs (non-JEDEC) */
+ { "mr25h256" }, /* 256 Kib, 40 MHz */
+ { "mr25h10" }, /* 1 Mib, 40 MHz */
+ { "mr25h40" }, /* 4 Mib, 40 MHz */
+
{ },
};
MODULE_DEVICE_TABLE(spi, m25p_ids);
diff --git a/drivers/mtd/devices/serial_flash_cmds.h b/drivers/mtd/devices/serial_flash_cmds.h
index f59a125..8b81e15 100644
--- a/drivers/mtd/devices/serial_flash_cmds.h
+++ b/drivers/mtd/devices/serial_flash_cmds.h
@@ -18,19 +18,12 @@
#define SPINOR_OP_RDVCR 0x85
/* JEDEC Standard - Serial Flash Discoverable Parmeters (SFDP) Commands */
-#define SPINOR_OP_READ_1_2_2 0xbb /* DUAL I/O READ */
-#define SPINOR_OP_READ_1_4_4 0xeb /* QUAD I/O READ */
-
#define SPINOR_OP_WRITE 0x02 /* PAGE PROGRAM */
#define SPINOR_OP_WRITE_1_1_2 0xa2 /* DUAL INPUT PROGRAM */
#define SPINOR_OP_WRITE_1_2_2 0xd2 /* DUAL INPUT EXT PROGRAM */
#define SPINOR_OP_WRITE_1_1_4 0x32 /* QUAD INPUT PROGRAM */
#define SPINOR_OP_WRITE_1_4_4 0x12 /* QUAD INPUT EXT PROGRAM */
-/* READ commands with 32-bit addressing */
-#define SPINOR_OP_READ4_1_2_2 0xbc
-#define SPINOR_OP_READ4_1_4_4 0xec
-
/* Configuration flags */
#define FLASH_FLAG_SINGLE 0x000000ff
#define FLASH_FLAG_READ_WRITE 0x00000001
diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c
index 5454b41..804313a 100644
--- a/drivers/mtd/devices/st_spi_fsm.c
+++ b/drivers/mtd/devices/st_spi_fsm.c
@@ -507,13 +507,13 @@
* - 'FAST' variants configured for 8 dummy cycles (see note above.)
*/
static struct seq_rw_config n25q_read4_configs[] = {
- {FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ4_1_4_4, 0, 4, 4, 0x00, 0, 8},
- {FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ4_1_1_4, 0, 1, 4, 0x00, 0, 8},
- {FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ4_1_2_2, 0, 2, 2, 0x00, 0, 8},
- {FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ4_1_1_2, 0, 1, 2, 0x00, 0, 8},
- {FLASH_FLAG_READ_FAST, SPINOR_OP_READ4_FAST, 0, 1, 1, 0x00, 0, 8},
- {FLASH_FLAG_READ_WRITE, SPINOR_OP_READ4, 0, 1, 1, 0x00, 0, 0},
- {0x00, 0, 0, 0, 0, 0x00, 0, 0},
+ {FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B, 0, 4, 4, 0x00, 0, 8},
+ {FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B, 0, 1, 4, 0x00, 0, 8},
+ {FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B, 0, 2, 2, 0x00, 0, 8},
+ {FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ_1_1_2_4B, 0, 1, 2, 0x00, 0, 8},
+ {FLASH_FLAG_READ_FAST, SPINOR_OP_READ_FAST_4B, 0, 1, 1, 0x00, 0, 8},
+ {FLASH_FLAG_READ_WRITE, SPINOR_OP_READ_4B, 0, 1, 1, 0x00, 0, 0},
+ {0x00, 0, 0, 0, 0, 0x00, 0, 0},
};
/*
@@ -553,13 +553,13 @@
* entering a state that is incompatible with the SPIBoot Controller.
*/
static struct seq_rw_config stfsm_s25fl_read4_configs[] = {
- {FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ4_1_4_4, 0, 4, 4, 0x00, 2, 4},
- {FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ4_1_1_4, 0, 1, 4, 0x00, 0, 8},
- {FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ4_1_2_2, 0, 2, 2, 0x00, 4, 0},
- {FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ4_1_1_2, 0, 1, 2, 0x00, 0, 8},
- {FLASH_FLAG_READ_FAST, SPINOR_OP_READ4_FAST, 0, 1, 1, 0x00, 0, 8},
- {FLASH_FLAG_READ_WRITE, SPINOR_OP_READ4, 0, 1, 1, 0x00, 0, 0},
- {0x00, 0, 0, 0, 0, 0x00, 0, 0},
+ {FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B, 0, 4, 4, 0x00, 2, 4},
+ {FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B, 0, 1, 4, 0x00, 0, 8},
+ {FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B, 0, 2, 2, 0x00, 4, 0},
+ {FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ_1_1_2_4B, 0, 1, 2, 0x00, 0, 8},
+ {FLASH_FLAG_READ_FAST, SPINOR_OP_READ_FAST_4B, 0, 1, 1, 0x00, 0, 8},
+ {FLASH_FLAG_READ_WRITE, SPINOR_OP_READ_4B, 0, 1, 1, 0x00, 0, 0},
+ {0x00, 0, 0, 0, 0, 0x00, 0, 0},
};
static struct seq_rw_config stfsm_s25fl_write4_configs[] = {
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index 5bcc896..542fdf8 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -75,7 +75,7 @@
taken from OF device tree.
config MTD_PHYSMAP_OF_VERSATILE
- bool "Support ARM Versatile physmap OF"
+ bool "ARM Versatile OF-based physical memory map handling"
depends on MTD_PHYSMAP_OF
depends on MFD_SYSCON
default y if (ARCH_INTEGRATOR || ARCH_VERSATILE || ARCH_REALVIEW)
@@ -84,6 +84,16 @@
platforms, basically to add a VPP (write protection) callback so
the flash can be taken out of write protection.
+config MTD_PHYSMAP_OF_GEMINI
+ bool "Cortina Gemini OF-based physical memory map handling"
+ depends on MTD_PHYSMAP_OF
+ depends on MFD_SYSCON
+ default ARCH_GEMINI
+ help
+ This provides some extra DT physmap parsing for the Gemini
+ platforms, some detection and setting up parallel mode on the
+ external interface.
+
config MTD_PMC_MSP_EVM
tristate "CFI Flash device mapped on PMC-Sierra MSP"
depends on PMC_MSP && MTD_CFI
diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile
index 644f7d3..aef1846 100644
--- a/drivers/mtd/maps/Makefile
+++ b/drivers/mtd/maps/Makefile
@@ -17,10 +17,13 @@
obj-$(CONFIG_MTD_TSUNAMI) += tsunami_flash.o
obj-$(CONFIG_MTD_PXA2XX) += pxa2xx-flash.o
obj-$(CONFIG_MTD_PHYSMAP) += physmap.o
-obj-$(CONFIG_MTD_PHYSMAP_OF) += physmap_of.o
ifdef CONFIG_MTD_PHYSMAP_OF_VERSATILE
-obj-$(CONFIG_MTD_PHYSMAP_OF) += physmap_of_versatile.o
+physmap_of-objs += physmap_of_versatile.o
endif
+ifdef CONFIG_MTD_PHYSMAP_OF_GEMINI
+physmap_of-objs += physmap_of_gemini.o
+endif
+obj-$(CONFIG_MTD_PHYSMAP_OF) += physmap_of.o
obj-$(CONFIG_MTD_PISMO) += pismo.o
obj-$(CONFIG_MTD_PMC_MSP_EVM) += pmcmsp-flash.o
obj-$(CONFIG_MTD_PCMCIA) += pcmciamtd.o
diff --git a/drivers/mtd/maps/ichxrom.c b/drivers/mtd/maps/ichxrom.c
index e17d02a..976d42f 100644
--- a/drivers/mtd/maps/ichxrom.c
+++ b/drivers/mtd/maps/ichxrom.c
@@ -57,10 +57,12 @@
{
struct ichxrom_map_info *map, *scratch;
u16 word;
+ int ret;
/* Disable writes through the rom window */
- pci_read_config_word(window->pdev, BIOS_CNTL, &word);
- pci_write_config_word(window->pdev, BIOS_CNTL, word & ~1);
+ ret = pci_read_config_word(window->pdev, BIOS_CNTL, &word);
+ if (!ret)
+ pci_write_config_word(window->pdev, BIOS_CNTL, word & ~1);
pci_dev_put(window->pdev);
/* Free all of the mtd devices */
diff --git a/drivers/mtd/maps/lantiq-flash.c b/drivers/mtd/maps/lantiq-flash.c
index c8febb3..3e33ab6 100644
--- a/drivers/mtd/maps/lantiq-flash.c
+++ b/drivers/mtd/maps/lantiq-flash.c
@@ -4,7 +4,7 @@
* by the Free Software Foundation.
*
* Copyright (C) 2004 Liu Peng Infineon IFAP DC COM CPE
- * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ * Copyright (C) 2010 John Crispin <john@phrozen.org>
*/
#include <linux/err.h>
@@ -209,5 +209,5 @@
module_platform_driver(ltq_mtd_driver);
MODULE_LICENSE("GPL");
-MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
+MODULE_AUTHOR("John Crispin <john@phrozen.org>");
MODULE_DESCRIPTION("Lantiq SoC NOR");
diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index 3fad359..14e8909 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -24,6 +24,7 @@
#include <linux/of_address.h>
#include <linux/of_platform.h>
#include <linux/slab.h>
+#include "physmap_of_gemini.h"
#include "physmap_of_versatile.h"
struct of_flash_list {
@@ -241,11 +242,13 @@
info->list[i].map.size = res_size;
info->list[i].map.bankwidth = be32_to_cpup(width);
info->list[i].map.device_node = dp;
- err = of_flash_probe_versatile(dev, dp, &info->list[i].map);
- if (err) {
- dev_err(&dev->dev, "Can't probe Versatile VPP\n");
+
+ err = of_flash_probe_gemini(dev, dp, &info->list[i].map);
+ if (err)
return err;
- }
+ err = of_flash_probe_versatile(dev, dp, &info->list[i].map);
+ if (err)
+ return err;
err = -ENOMEM;
info->list[i].map.virt = ioremap(info->list[i].map.phys,
diff --git a/drivers/mtd/maps/physmap_of_gemini.c b/drivers/mtd/maps/physmap_of_gemini.c
new file mode 100644
index 0000000..9d371cd
--- /dev/null
+++ b/drivers/mtd/maps/physmap_of_gemini.c
@@ -0,0 +1,117 @@
+/*
+ * Cortina Systems Gemini OF physmap add-on
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * This SoC has an elaborate flash control register, so we need to
+ * detect and set it up when booting on this platform.
+ */
+#include <linux/export.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/mtd/map.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/bitops.h>
+#include "physmap_of_gemini.h"
+
+/*
+ * The Flash-relevant parts of the global status register
+ * These would also be relevant for a NAND driver.
+ */
+#define GLOBAL_STATUS 0x04
+#define FLASH_TYPE_MASK (0x3 << 24)
+#define FLASH_TYPE_NAND_2K (0x3 << 24)
+#define FLASH_TYPE_NAND_512 (0x2 << 24)
+#define FLASH_TYPE_PARALLEL (0x1 << 24)
+#define FLASH_TYPE_SERIAL (0x0 << 24)
+/* if parallel */
+#define FLASH_WIDTH_16BIT (1 << 23) /* else 8 bit */
+/* if serial */
+#define FLASH_ATMEL (1 << 23) /* else STM */
+
+#define FLASH_SIZE_MASK (0x3 << 21)
+#define NAND_256M (0x3 << 21) /* and more */
+#define NAND_128M (0x2 << 21)
+#define NAND_64M (0x1 << 21)
+#define NAND_32M (0x0 << 21)
+#define ATMEL_16M (0x3 << 21) /* and more */
+#define ATMEL_8M (0x2 << 21)
+#define ATMEL_4M_2M (0x1 << 21)
+#define ATMEL_1M (0x0 << 21) /* and less */
+#define STM_32M (1 << 22) /* and more */
+#define STM_16M (0 << 22) /* and less */
+
+#define FLASH_PARALLEL_HIGH_PIN_CNT (1 << 20) /* else low pin cnt */
+
+/* Miscellaneous Control Register */
+#define GLOBAL_MISC_CTRL 0x30
+#define FLASH_PADS_MASK 0x07
+#define NAND_PADS_DISABLE BIT(2)
+#define PFLASH_PADS_DISABLE BIT(1)
+#define SFLASH_PADS_DISABLE BIT(0)
+
+static const struct of_device_id syscon_match[] = {
+ { .compatible = "cortina,gemini-syscon" },
+ { },
+};
+
+int of_flash_probe_gemini(struct platform_device *pdev,
+ struct device_node *np,
+ struct map_info *map)
+{
+ static struct regmap *rmap;
+ struct device *dev = &pdev->dev;
+ u32 val;
+ int ret;
+
+ /* Multiplatform guard */
+ if (!of_device_is_compatible(np, "cortina,gemini-flash"))
+ return 0;
+
+ rmap = syscon_regmap_lookup_by_phandle(np, "syscon");
+ if (IS_ERR(rmap)) {
+ dev_err(dev, "no syscon\n");
+ return PTR_ERR(rmap);
+ }
+
+ ret = regmap_read(rmap, GLOBAL_STATUS, &val);
+ if (ret) {
+ dev_err(dev, "failed to read global status register\n");
+ return -ENODEV;
+ }
+ dev_dbg(dev, "global status reg: %08x\n", val);
+
+ /*
+ * It would be contradictory if a physmap flash was NOT parallel.
+ */
+ if ((val & FLASH_TYPE_MASK) != FLASH_TYPE_PARALLEL) {
+ dev_err(dev, "flash is not parallel\n");
+ return -ENODEV;
+ }
+
+ /*
+ * Complain if DT data and hardware definition is different.
+ */
+ if (val & FLASH_WIDTH_16BIT) {
+ if (map->bankwidth != 2)
+ dev_warn(dev, "flash hardware say flash is 16 bit wide but DT says it is %d bits wide\n",
+ map->bankwidth * 8);
+ } else {
+ if (map->bankwidth != 1)
+ dev_warn(dev, "flash hardware say flash is 8 bit wide but DT says it is %d bits wide\n",
+ map->bankwidth * 8);
+ }
+
+ /* Activate parallel (NOR flash) mode */
+ ret = regmap_update_bits(rmap, GLOBAL_MISC_CTRL,
+ FLASH_PADS_MASK,
+ SFLASH_PADS_DISABLE | NAND_PADS_DISABLE);
+ if (ret) {
+ dev_err(dev, "unable to set up physmap pads\n");
+ return -ENODEV;
+ }
+
+ dev_info(&pdev->dev, "initialized Gemini-specific physmap control\n");
+
+ return 0;
+}
diff --git a/drivers/mtd/maps/physmap_of_gemini.h b/drivers/mtd/maps/physmap_of_gemini.h
new file mode 100644
index 0000000..c675025
--- /dev/null
+++ b/drivers/mtd/maps/physmap_of_gemini.h
@@ -0,0 +1,16 @@
+#include <linux/of.h>
+#include <linux/mtd/map.h>
+
+#ifdef CONFIG_MTD_PHYSMAP_OF_GEMINI
+int of_flash_probe_gemini(struct platform_device *pdev,
+ struct device_node *np,
+ struct map_info *map);
+#else
+static inline
+int of_flash_probe_gemini(struct platform_device *pdev,
+ struct device_node *np,
+ struct map_info *map)
+{
+ return 0;
+}
+#endif
diff --git a/drivers/mtd/maps/physmap_of_versatile.c b/drivers/mtd/maps/physmap_of_versatile.c
index 0f39b2a..8c6ccde 100644
--- a/drivers/mtd/maps/physmap_of_versatile.c
+++ b/drivers/mtd/maps/physmap_of_versatile.c
@@ -252,4 +252,3 @@
return 0;
}
-EXPORT_SYMBOL_GPL(of_flash_probe_versatile);
diff --git a/drivers/mtd/maps/pmcmsp-flash.c b/drivers/mtd/maps/pmcmsp-flash.c
index f9fa3fa..2051f28 100644
--- a/drivers/mtd/maps/pmcmsp-flash.c
+++ b/drivers/mtd/maps/pmcmsp-flash.c
@@ -139,15 +139,13 @@
}
msp_maps[i].bankwidth = 1;
- msp_maps[i].name = kmalloc(7, GFP_KERNEL);
+ msp_maps[i].name = kstrndup(flash_name, 7, GFP_KERNEL);
if (!msp_maps[i].name) {
iounmap(msp_maps[i].virt);
kfree(msp_parts[i]);
goto cleanup_loop;
}
- msp_maps[i].name = strncpy(msp_maps[i].name, flash_name, 7);
-
for (j = 0; j < pcnt; j++) {
part_name[5] = '0' + i;
part_name[7] = '0' + j;
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index ce5ccc5..3568294 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -451,7 +451,7 @@
* data. For our userspace tools it is important to dump areas
* with ECC errors!
* For kernel internal usage it also might return -EUCLEAN
- * to signal the caller that a bitflip has occured and has
+ * to signal the caller that a bitflip has occurred and has
* been corrected by the ECC algorithm.
*
* Note: currently the standard NAND function, nand_read_oob_std,
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 052772f..66a9ded 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1128,7 +1128,7 @@
* @oobecc: OOB region struct filled with the appropriate ECC position
* information
*
- * This functions return ECC section information in the OOB area. I you want
+ * This function returns ECC section information in the OOB area. If you want
* to get all the ECC bytes information, then you should call
* mtd_ooblayout_ecc(mtd, section++, oobecc) until it returns -ERANGE.
*
@@ -1160,7 +1160,7 @@
* @oobfree: OOB region struct filled with the appropriate free position
* information
*
- * This functions return free bytes position in the OOB area. I you want
+ * This function returns free bytes position in the OOB area. If you want
* to get all the free bytes information, then you should call
* mtd_ooblayout_free(mtd, section++, oobfree) until it returns -ERANGE.
*
@@ -1190,7 +1190,7 @@
* @iter: iterator function. Should be either mtd_ooblayout_free or
* mtd_ooblayout_ecc depending on the region type you're searching for
*
- * This functions returns the section id and oobregion information of a
+ * This function returns the section id and oobregion information of a
* specific byte. For example, say you want to know where the 4th ECC byte is
* stored, you'll use:
*
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index fccdd49..ea5e530 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -349,6 +349,14 @@
.free = part_ooblayout_free,
};
+static int part_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len)
+{
+ struct mtd_part *part = mtd_to_part(mtd);
+
+ return part->master->_max_bad_blocks(part->master,
+ ofs + part->offset, len);
+}
+
static inline void free_partition(struct mtd_part *p)
{
kfree(p->mtd.name);
@@ -424,6 +432,7 @@
slave->mtd.dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) ?
&master->dev :
master->dev.parent;
+ slave->mtd.dev.of_node = part->of_node;
slave->mtd._read = part_read;
slave->mtd._write = part_write;
@@ -475,6 +484,8 @@
slave->mtd._block_isbad = part_block_isbad;
if (master->_block_markbad)
slave->mtd._block_markbad = part_block_markbad;
+ if (master->_max_bad_blocks)
+ slave->mtd._max_bad_blocks = part_max_bad_blocks;
if (master->_get_device)
slave->mtd._get_device = part_get_device;
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 353a9dd..6d4d567 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -426,6 +426,8 @@
config MTD_NAND_OXNAS
tristate "NAND Flash support for Oxford Semiconductor SoC"
+ depends on ARCH_OXNAS || COMPILE_TEST
+ depends on HAS_IOMEM
help
This enables the NAND flash controller on Oxford Semiconductor SoCs.
@@ -534,13 +536,14 @@
config MTD_NAND_FSMC
tristate "Support for NAND on ST Micros FSMC"
+ depends on OF
depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300
help
Enables support for NAND Flash chips on the ST Microelectronics
Flexible Static Memory Controller (FSMC)
config MTD_NAND_XWAY
- tristate "Support for NAND on Lantiq XWAY SoC"
+ bool "Support for NAND on Lantiq XWAY SoC"
depends on LANTIQ && SOC_TYPE_XWAY
help
Enables support for NAND Flash chips on Lantiq XWAY SoCs. NAND is attached
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index 0a177b1..d1570f5 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -258,9 +258,15 @@
int bufnum = nctrl->page & priv->bufnum_mask;
int sector = bufnum * chip->ecc.steps;
int sector_end = sector + chip->ecc.steps - 1;
+ __be32 *eccstat_regs;
+
+ if (ctrl->version >= FSL_IFC_VERSION_2_0_0)
+ eccstat_regs = ifc->ifc_nand.v2_nand_eccstat;
+ else
+ eccstat_regs = ifc->ifc_nand.v1_nand_eccstat;
for (i = sector / 4; i <= sector_end / 4; i++)
- eccstat[i] = ifc_in32(&ifc->ifc_nand.nand_eccstat[i]);
+ eccstat[i] = ifc_in32(&eccstat_regs[i]);
for (i = sector; i <= sector_end; i++) {
errors = check_read_ecc(mtd, ctrl, eccstat, i);
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index 4924b43..bda1e46 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -35,10 +35,133 @@
#include <linux/mtd/partitions.h>
#include <linux/io.h>
#include <linux/slab.h>
-#include <linux/mtd/fsmc.h>
#include <linux/amba/bus.h>
#include <mtd/mtd-abi.h>
+#define FSMC_NAND_BW8 1
+#define FSMC_NAND_BW16 2
+
+#define FSMC_MAX_NOR_BANKS 4
+#define FSMC_MAX_NAND_BANKS 4
+
+#define FSMC_FLASH_WIDTH8 1
+#define FSMC_FLASH_WIDTH16 2
+
+/* fsmc controller registers for NOR flash */
+#define CTRL 0x0
+ /* ctrl register definitions */
+ #define BANK_ENABLE (1 << 0)
+ #define MUXED (1 << 1)
+ #define NOR_DEV (2 << 2)
+ #define WIDTH_8 (0 << 4)
+ #define WIDTH_16 (1 << 4)
+ #define RSTPWRDWN (1 << 6)
+ #define WPROT (1 << 7)
+ #define WRT_ENABLE (1 << 12)
+ #define WAIT_ENB (1 << 13)
+
+#define CTRL_TIM 0x4
+ /* ctrl_tim register definitions */
+
+#define FSMC_NOR_BANK_SZ 0x8
+#define FSMC_NOR_REG_SIZE 0x40
+
+#define FSMC_NOR_REG(base, bank, reg) (base + \
+ FSMC_NOR_BANK_SZ * (bank) + \
+ reg)
+
+/* fsmc controller registers for NAND flash */
+#define PC 0x00
+ /* pc register definitions */
+ #define FSMC_RESET (1 << 0)
+ #define FSMC_WAITON (1 << 1)
+ #define FSMC_ENABLE (1 << 2)
+ #define FSMC_DEVTYPE_NAND (1 << 3)
+ #define FSMC_DEVWID_8 (0 << 4)
+ #define FSMC_DEVWID_16 (1 << 4)
+ #define FSMC_ECCEN (1 << 6)
+ #define FSMC_ECCPLEN_512 (0 << 7)
+ #define FSMC_ECCPLEN_256 (1 << 7)
+ #define FSMC_TCLR_1 (1)
+ #define FSMC_TCLR_SHIFT (9)
+ #define FSMC_TCLR_MASK (0xF)
+ #define FSMC_TAR_1 (1)
+ #define FSMC_TAR_SHIFT (13)
+ #define FSMC_TAR_MASK (0xF)
+#define STS 0x04
+ /* sts register definitions */
+ #define FSMC_CODE_RDY (1 << 15)
+#define COMM 0x08
+ /* comm register definitions */
+ #define FSMC_TSET_0 0
+ #define FSMC_TSET_SHIFT 0
+ #define FSMC_TSET_MASK 0xFF
+ #define FSMC_TWAIT_6 6
+ #define FSMC_TWAIT_SHIFT 8
+ #define FSMC_TWAIT_MASK 0xFF
+ #define FSMC_THOLD_4 4
+ #define FSMC_THOLD_SHIFT 16
+ #define FSMC_THOLD_MASK 0xFF
+ #define FSMC_THIZ_1 1
+ #define FSMC_THIZ_SHIFT 24
+ #define FSMC_THIZ_MASK 0xFF
+#define ATTRIB 0x0C
+#define IOATA 0x10
+#define ECC1 0x14
+#define ECC2 0x18
+#define ECC3 0x1C
+#define FSMC_NAND_BANK_SZ 0x20
+
+#define FSMC_NAND_REG(base, bank, reg) (base + FSMC_NOR_REG_SIZE + \
+ (FSMC_NAND_BANK_SZ * (bank)) + \
+ reg)
+
+#define FSMC_BUSY_WAIT_TIMEOUT (1 * HZ)
+
+struct fsmc_nand_timings {
+ uint8_t tclr;
+ uint8_t tar;
+ uint8_t thiz;
+ uint8_t thold;
+ uint8_t twait;
+ uint8_t tset;
+};
+
+enum access_mode {
+ USE_DMA_ACCESS = 1,
+ USE_WORD_ACCESS,
+};
+
+/**
+ * fsmc_nand_platform_data - platform specific NAND controller config
+ * @nand_timings: timing setup for the physical NAND interface
+ * @partitions: partition table for the platform, use a default fallback
+ * if this is NULL
+ * @nr_partitions: the number of partitions in the previous entry
+ * @options: different options for the driver
+ * @width: bus width
+ * @bank: default bank
+ * @select_bank: callback to select a certain bank, this is
+ * platform-specific. If the controller only supports one bank
+ * this may be set to NULL
+ */
+struct fsmc_nand_platform_data {
+ struct fsmc_nand_timings *nand_timings;
+ struct mtd_partition *partitions;
+ unsigned int nr_partitions;
+ unsigned int options;
+ unsigned int width;
+ unsigned int bank;
+
+ enum access_mode mode;
+
+ void (*select_bank)(uint32_t bank, uint32_t busw);
+
+ /* priv structures for dma accesses */
+ void *read_dma_priv;
+ void *write_dma_priv;
+};
+
static int fsmc_ecc1_ooblayout_ecc(struct mtd_info *mtd, int section,
struct mtd_oob_region *oobregion)
{
@@ -714,7 +837,6 @@
return true;
}
-#ifdef CONFIG_OF
static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
struct device_node *np)
{
@@ -757,13 +879,6 @@
}
return 0;
}
-#else
-static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
- struct device_node *np)
-{
- return -ENOSYS;
-}
-#endif
/*
* fsmc_nand_probe - Probe function
@@ -782,19 +897,15 @@
u32 pid;
int i;
- if (np) {
- pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
- pdev->dev.platform_data = pdata;
- ret = fsmc_nand_probe_config_dt(pdev, np);
- if (ret) {
- dev_err(&pdev->dev, "no platform data\n");
- return -ENODEV;
- }
- }
+ pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+ if (!pdata)
+ return -ENOMEM;
- if (!pdata) {
- dev_err(&pdev->dev, "platform data is NULL\n");
- return -EINVAL;
+ pdev->dev.platform_data = pdata;
+ ret = fsmc_nand_probe_config_dt(pdev, np);
+ if (ret) {
+ dev_err(&pdev->dev, "no platform data\n");
+ return -ENODEV;
}
/* Allocate memory for the device structure (and zero it) */
diff --git a/drivers/mtd/nand/lpc32xx_mlc.c b/drivers/mtd/nand/lpc32xx_mlc.c
index 5553a5d..846a66c 100644
--- a/drivers/mtd/nand/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/lpc32xx_mlc.c
@@ -775,7 +775,7 @@
init_completion(&host->comp_controller);
host->irq = platform_get_irq(pdev, 0);
- if ((host->irq < 0) || (host->irq >= NR_IRQS)) {
+ if (host->irq < 0) {
dev_err(&pdev->dev, "failed to get platform irq\n");
res = -EINVAL;
goto err_exit3;
diff --git a/drivers/mtd/nand/lpc32xx_slc.c b/drivers/mtd/nand/lpc32xx_slc.c
index 53bafe2..a0669a3 100644
--- a/drivers/mtd/nand/lpc32xx_slc.c
+++ b/drivers/mtd/nand/lpc32xx_slc.c
@@ -797,22 +797,17 @@
struct resource *rc;
int res;
- rc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (rc == NULL) {
- dev_err(&pdev->dev, "No memory resource found for device\n");
- return -EBUSY;
- }
-
/* Allocate memory for the device structure (and zero it) */
host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
if (!host)
return -ENOMEM;
- host->io_base_dma = rc->start;
+ rc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
host->io_base = devm_ioremap_resource(&pdev->dev, rc);
if (IS_ERR(host->io_base))
return PTR_ERR(host->io_base);
+ host->io_base_dma = rc->start;
if (pdev->dev.of_node)
host->ncfg = lpc32xx_parse_dt(&pdev->dev);
if (!host->ncfg) {
diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c
index 6c3eed3..6c517c6 100644
--- a/drivers/mtd/nand/mtk_nand.c
+++ b/drivers/mtd/nand/mtk_nand.c
@@ -1383,7 +1383,6 @@
nfc->regs = devm_ioremap_resource(dev, res);
if (IS_ERR(nfc->regs)) {
ret = PTR_ERR(nfc->regs);
- dev_err(dev, "no nfi base\n");
goto release_ecc;
}
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index ec1c28a..1492c12 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3263,6 +3263,42 @@
}
/**
+ * nand_max_bad_blocks - [MTD Interface] Max number of bad blocks for an mtd
+ * @mtd: MTD device structure
+ * @ofs: offset relative to mtd start
+ * @len: length of mtd
+ */
+static int nand_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ u32 part_start_block;
+ u32 part_end_block;
+ u32 part_start_die;
+ u32 part_end_die;
+
+ /*
+ * max_bb_per_die and blocks_per_die used to determine
+ * the maximum bad block count.
+ */
+ if (!chip->max_bb_per_die || !chip->blocks_per_die)
+ return -ENOTSUPP;
+
+ /* Get the start and end of the partition in erase blocks. */
+ part_start_block = mtd_div_by_eb(ofs, mtd);
+ part_end_block = mtd_div_by_eb(len, mtd) + part_start_block - 1;
+
+ /* Get the start and end LUNs of the partition. */
+ part_start_die = part_start_block / chip->blocks_per_die;
+ part_end_die = part_end_block / chip->blocks_per_die;
+
+ /*
+ * Look up the bad blocks per unit and multiply by the number of units
+ * that the partition spans.
+ */
+ return chip->max_bb_per_die * (part_end_die - part_start_die + 1);
+}
+
+/**
* nand_onfi_set_features- [REPLACEABLE] set features for ONFI nand
* @mtd: MTD device structure
* @chip: nand chip info structure
@@ -3592,6 +3628,9 @@
chip->chipsize *= (uint64_t)mtd->erasesize * p->lun_count;
chip->bits_per_cell = p->bits_per_cell;
+ chip->max_bb_per_die = le16_to_cpu(p->bb_per_lun);
+ chip->blocks_per_die = le32_to_cpu(p->blocks_per_lun);
+
if (onfi_feature(chip) & ONFI_FEATURE_16_BIT_BUS)
*busw = NAND_BUSWIDTH_16;
else
@@ -4815,6 +4854,7 @@
mtd->_block_isreserved = nand_block_isreserved;
mtd->_block_isbad = nand_block_isbad;
mtd->_block_markbad = nand_block_markbad;
+ mtd->_max_bad_blocks = nand_max_bad_blocks;
mtd->writebufsize = mtd->writesize;
/*
diff --git a/drivers/mtd/nand/nand_ids.c b/drivers/mtd/nand/nand_ids.c
index b3a332f..4a2f75b 100644
--- a/drivers/mtd/nand/nand_ids.c
+++ b/drivers/mtd/nand/nand_ids.c
@@ -185,6 +185,7 @@
{NAND_MFR_SANDISK, "SanDisk"},
{NAND_MFR_INTEL, "Intel"},
{NAND_MFR_ATO, "ATO"},
+ {NAND_MFR_WINBOND, "Winbond"},
{0x0, "Unknown"}
};
diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c
index e40482a..0eeeb8b 100644
--- a/drivers/mtd/nand/sunxi_nand.c
+++ b/drivers/mtd/nand/sunxi_nand.c
@@ -321,6 +321,10 @@
ret = wait_for_completion_timeout(&nfc->complete,
msecs_to_jiffies(timeout_ms));
+ if (!ret)
+ ret = -ETIMEDOUT;
+ else
+ ret = 0;
writel(0, nfc->regs + NFC_REG_INT);
} else {
@@ -518,6 +522,8 @@
u32 tmp;
while (len > offs) {
+ bool poll = false;
+
cnt = min(len - offs, NFC_SRAM_SIZE);
ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
@@ -528,7 +534,11 @@
tmp = NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD;
writel(tmp, nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+ /* Arbitrary limit for polling mode */
+ if (cnt < 64)
+ poll = true;
+
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, poll, 0);
if (ret)
break;
@@ -551,6 +561,8 @@
u32 tmp;
while (len > offs) {
+ bool poll = false;
+
cnt = min(len - offs, NFC_SRAM_SIZE);
ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
@@ -563,7 +575,11 @@
NFC_ACCESS_DIR;
writel(tmp, nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+ /* Arbitrary limit for polling mode */
+ if (cnt < 64)
+ poll = true;
+
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, poll, 0);
if (ret)
break;
@@ -588,10 +604,6 @@
struct sunxi_nfc *nfc = to_sunxi_nfc(sunxi_nand->nand.controller);
int ret;
- ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
- if (ret)
- return;
-
if (dat == NAND_CMD_NONE && (ctrl & NAND_NCE) &&
!(ctrl & (NAND_CLE | NAND_ALE))) {
u32 cmd = 0;
@@ -621,6 +633,10 @@
writel(sunxi_nand->addr[1],
nfc->regs + NFC_REG_ADDR_HIGH);
+ ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
+ if (ret)
+ return;
+
writel(cmd, nfc->regs + NFC_REG_CMD);
sunxi_nand->addr[0] = 0;
sunxi_nand->addr[1] = 0;
@@ -957,7 +973,7 @@
writel(NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD | NFC_ECC_OP,
nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0);
sunxi_nfc_randomizer_disable(mtd);
if (ret)
return ret;
@@ -1069,7 +1085,7 @@
writel(NFC_PAGE_OP | NFC_DATA_SWAP_METHOD | NFC_DATA_TRANS,
nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0);
if (ret)
dmaengine_terminate_all(nfc->dmac);
@@ -1189,7 +1205,7 @@
NFC_ACCESS_DIR | NFC_ECC_OP,
nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0);
sunxi_nfc_randomizer_disable(mtd);
if (ret)
return ret;
@@ -1428,7 +1444,7 @@
NFC_DATA_TRANS | NFC_ACCESS_DIR,
nfc->regs + NFC_REG_CMD);
- ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+ ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0);
if (ret)
dmaengine_terminate_all(nfc->dmac);
diff --git a/drivers/mtd/nand/tango_nand.c b/drivers/mtd/nand/tango_nand.c
index 28c7f47..4a5e948 100644
--- a/drivers/mtd/nand/tango_nand.c
+++ b/drivers/mtd/nand/tango_nand.c
@@ -632,11 +632,13 @@
if (IS_ERR(nfc->pbus_base))
return PTR_ERR(nfc->pbus_base);
+ writel_relaxed(MODE_RAW, nfc->pbus_base + PBUS_PAD_MODE);
+
clk = clk_get(&pdev->dev, NULL);
if (IS_ERR(clk))
return PTR_ERR(clk);
- nfc->chan = dma_request_chan(&pdev->dev, "nfc_sbox");
+ nfc->chan = dma_request_chan(&pdev->dev, "rxtx");
if (IS_ERR(nfc->chan))
return PTR_ERR(nfc->chan);
diff --git a/drivers/mtd/nand/xway_nand.c b/drivers/mtd/nand/xway_nand.c
index 1f2948c..ddee400 100644
--- a/drivers/mtd/nand/xway_nand.c
+++ b/drivers/mtd/nand/xway_nand.c
@@ -3,7 +3,7 @@
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*
- * Copyright © 2012 John Crispin <blogic@openwrt.org>
+ * Copyright © 2012 John Crispin <john@phrozen.org>
* Copyright © 2016 Hauke Mehrtens <hauke@hauke-m.de>
*/
@@ -232,7 +232,6 @@
{ .compatible = "lantiq,nand-xway" },
{},
};
-MODULE_DEVICE_TABLE(of, xway_nand_match);
static struct platform_driver xway_nand_driver = {
.probe = xway_nand_probe,
@@ -243,6 +242,4 @@
},
};
-module_platform_driver(xway_nand_driver);
-
-MODULE_LICENSE("GPL");
+builtin_platform_driver(xway_nand_driver);
diff --git a/drivers/mtd/ofpart.c b/drivers/mtd/ofpart.c
index ede407d..4644701 100644
--- a/drivers/mtd/ofpart.c
+++ b/drivers/mtd/ofpart.c
@@ -108,6 +108,7 @@
parts[i].offset = of_read_number(reg, a_cells);
parts[i].size = of_read_number(reg + a_cells, s_cells);
+ parts[i].of_node = pp;
partname = of_get_property(pp, "label", &len);
if (!partname)
diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
index 4a682ee..7252087 100644
--- a/drivers/mtd/spi-nor/Kconfig
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -29,6 +29,16 @@
Please note that some tools/drivers/filesystems may not work with
4096 B erase size (e.g. UBIFS requires 15 KiB as a minimum).
+config SPI_ASPEED_SMC
+ tristate "Aspeed flash controllers in SPI mode"
+ depends on ARCH_ASPEED || COMPILE_TEST
+ depends on HAS_IOMEM && OF
+ help
+ This enables support for the Firmware Memory controller (FMC)
+ in the Aspeed AST2500/AST2400 SoCs when attached to SPI NOR chips,
+ and support for the SPI flash memory controller (SPI) for
+ the host firmware. The implementation only supports SPI NOR.
+
config SPI_ATMEL_QUADSPI
tristate "Atmel Quad SPI Controller"
depends on ARCH_AT91 || (ARM && COMPILE_TEST)
@@ -40,7 +50,7 @@
config SPI_CADENCE_QUADSPI
tristate "Cadence Quad SPI controller"
- depends on OF && ARM
+ depends on OF && (ARM || COMPILE_TEST)
help
Enable support for the Cadence Quad SPI Flash controller.
@@ -76,4 +86,24 @@
Flash. Enable this option if you have a device with a SPIFI
controller and want to access the Flash as a mtd device.
+config SPI_INTEL_SPI
+ tristate
+
+config SPI_INTEL_SPI_PLATFORM
+ tristate "Intel PCH/PCU SPI flash platform driver" if EXPERT
+ depends on X86
+ select SPI_INTEL_SPI
+ help
+ This enables platform support for the Intel PCH/PCU SPI
+ controller in master mode. This controller is present in modern
+ Intel hardware and is used to hold BIOS and other persistent
+ settings. Using this driver it is possible to upgrade BIOS
+ directly from Linux.
+
+ Say N here unless you know what you are doing. Overwriting the
+ SPI flash may render the system unbootable.
+
+ To compile this driver as a module, choose M here: the module
+ will be called intel-spi-platform.
+
endif # MTD_SPI_NOR
diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile
index 121695e..72238a7 100644
--- a/drivers/mtd/spi-nor/Makefile
+++ b/drivers/mtd/spi-nor/Makefile
@@ -1,7 +1,10 @@
obj-$(CONFIG_MTD_SPI_NOR) += spi-nor.o
+obj-$(CONFIG_SPI_ASPEED_SMC) += aspeed-smc.o
obj-$(CONFIG_SPI_ATMEL_QUADSPI) += atmel-quadspi.o
obj-$(CONFIG_SPI_CADENCE_QUADSPI) += cadence-quadspi.o
obj-$(CONFIG_SPI_FSL_QUADSPI) += fsl-quadspi.o
obj-$(CONFIG_SPI_HISI_SFC) += hisi-sfc.o
obj-$(CONFIG_MTD_MT81xx_NOR) += mtk-quadspi.o
obj-$(CONFIG_SPI_NXP_SPIFI) += nxp-spifi.o
+obj-$(CONFIG_SPI_INTEL_SPI) += intel-spi.o
+obj-$(CONFIG_SPI_INTEL_SPI_PLATFORM) += intel-spi-platform.o
diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c
new file mode 100644
index 0000000..56051d3
--- /dev/null
+++ b/drivers/mtd/spi-nor/aspeed-smc.c
@@ -0,0 +1,754 @@
+/*
+ * ASPEED Static Memory Controller driver
+ *
+ * Copyright (c) 2015-2016, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/bug.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/sysfs.h>
+
+#define DEVICE_NAME "aspeed-smc"
+
+/*
+ * The driver only support SPI flash
+ */
+enum aspeed_smc_flash_type {
+ smc_type_nor = 0,
+ smc_type_nand = 1,
+ smc_type_spi = 2,
+};
+
+struct aspeed_smc_chip;
+
+struct aspeed_smc_info {
+ u32 maxsize; /* maximum size of chip window */
+ u8 nce; /* number of chip enables */
+ bool hastype; /* flash type field exists in config reg */
+ u8 we0; /* shift for write enable bit for CE0 */
+ u8 ctl0; /* offset in regs of ctl for CE0 */
+
+ void (*set_4b)(struct aspeed_smc_chip *chip);
+};
+
+static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip);
+static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip);
+
+static const struct aspeed_smc_info fmc_2400_info = {
+ .maxsize = 64 * 1024 * 1024,
+ .nce = 5,
+ .hastype = true,
+ .we0 = 16,
+ .ctl0 = 0x10,
+ .set_4b = aspeed_smc_chip_set_4b,
+};
+
+static const struct aspeed_smc_info spi_2400_info = {
+ .maxsize = 64 * 1024 * 1024,
+ .nce = 1,
+ .hastype = false,
+ .we0 = 0,
+ .ctl0 = 0x04,
+ .set_4b = aspeed_smc_chip_set_4b_spi_2400,
+};
+
+static const struct aspeed_smc_info fmc_2500_info = {
+ .maxsize = 256 * 1024 * 1024,
+ .nce = 3,
+ .hastype = true,
+ .we0 = 16,
+ .ctl0 = 0x10,
+ .set_4b = aspeed_smc_chip_set_4b,
+};
+
+static const struct aspeed_smc_info spi_2500_info = {
+ .maxsize = 128 * 1024 * 1024,
+ .nce = 2,
+ .hastype = false,
+ .we0 = 16,
+ .ctl0 = 0x10,
+ .set_4b = aspeed_smc_chip_set_4b,
+};
+
+enum aspeed_smc_ctl_reg_value {
+ smc_base, /* base value without mode for other commands */
+ smc_read, /* command reg for (maybe fast) reads */
+ smc_write, /* command reg for writes */
+ smc_max,
+};
+
+struct aspeed_smc_controller;
+
+struct aspeed_smc_chip {
+ int cs;
+ struct aspeed_smc_controller *controller;
+ void __iomem *ctl; /* control register */
+ void __iomem *ahb_base; /* base of chip window */
+ u32 ctl_val[smc_max]; /* control settings */
+ enum aspeed_smc_flash_type type; /* what type of flash */
+ struct spi_nor nor;
+};
+
+struct aspeed_smc_controller {
+ struct device *dev;
+
+ struct mutex mutex; /* controller access mutex */
+ const struct aspeed_smc_info *info; /* type info of controller */
+ void __iomem *regs; /* controller registers */
+ void __iomem *ahb_base; /* per-chip windows resource */
+
+ struct aspeed_smc_chip *chips[0]; /* pointers to attached chips */
+};
+
+/*
+ * SPI Flash Configuration Register (AST2500 SPI)
+ * or
+ * Type setting Register (AST2500 FMC).
+ * CE0 and CE1 can only be of type SPI. CE2 can be of type NOR but the
+ * driver does not support it.
+ */
+#define CONFIG_REG 0x0
+#define CONFIG_DISABLE_LEGACY BIT(31) /* 1 */
+
+#define CONFIG_CE2_WRITE BIT(18)
+#define CONFIG_CE1_WRITE BIT(17)
+#define CONFIG_CE0_WRITE BIT(16)
+
+#define CONFIG_CE2_TYPE BIT(4) /* AST2500 FMC only */
+#define CONFIG_CE1_TYPE BIT(2) /* AST2500 FMC only */
+#define CONFIG_CE0_TYPE BIT(0) /* AST2500 FMC only */
+
+/*
+ * CE Control Register
+ */
+#define CE_CONTROL_REG 0x4
+
+/*
+ * CEx Control Register
+ */
+#define CONTROL_AAF_MODE BIT(31)
+#define CONTROL_IO_MODE_MASK GENMASK(30, 28)
+#define CONTROL_IO_DUAL_DATA BIT(29)
+#define CONTROL_IO_DUAL_ADDR_DATA (BIT(29) | BIT(28))
+#define CONTROL_IO_QUAD_DATA BIT(30)
+#define CONTROL_IO_QUAD_ADDR_DATA (BIT(30) | BIT(28))
+#define CONTROL_CE_INACTIVE_SHIFT 24
+#define CONTROL_CE_INACTIVE_MASK GENMASK(27, \
+ CONTROL_CE_INACTIVE_SHIFT)
+/* 0 = 16T ... 15 = 1T T=HCLK */
+#define CONTROL_COMMAND_SHIFT 16
+#define CONTROL_DUMMY_COMMAND_OUT BIT(15)
+#define CONTROL_IO_DUMMY_HI BIT(14)
+#define CONTROL_IO_DUMMY_HI_SHIFT 14
+#define CONTROL_CLK_DIV4 BIT(13) /* others */
+#define CONTROL_IO_ADDRESS_4B BIT(13) /* AST2400 SPI */
+#define CONTROL_RW_MERGE BIT(12)
+#define CONTROL_IO_DUMMY_LO_SHIFT 6
+#define CONTROL_IO_DUMMY_LO GENMASK(7, \
+ CONTROL_IO_DUMMY_LO_SHIFT)
+#define CONTROL_IO_DUMMY_MASK (CONTROL_IO_DUMMY_HI | \
+ CONTROL_IO_DUMMY_LO)
+#define CONTROL_IO_DUMMY_SET(dummy) \
+ (((((dummy) >> 2) & 0x1) << CONTROL_IO_DUMMY_HI_SHIFT) | \
+ (((dummy) & 0x3) << CONTROL_IO_DUMMY_LO_SHIFT))
+
+#define CONTROL_CLOCK_FREQ_SEL_SHIFT 8
+#define CONTROL_CLOCK_FREQ_SEL_MASK GENMASK(11, \
+ CONTROL_CLOCK_FREQ_SEL_SHIFT)
+#define CONTROL_LSB_FIRST BIT(5)
+#define CONTROL_CLOCK_MODE_3 BIT(4)
+#define CONTROL_IN_DUAL_DATA BIT(3)
+#define CONTROL_CE_STOP_ACTIVE_CONTROL BIT(2)
+#define CONTROL_COMMAND_MODE_MASK GENMASK(1, 0)
+#define CONTROL_COMMAND_MODE_NORMAL 0
+#define CONTROL_COMMAND_MODE_FREAD 1
+#define CONTROL_COMMAND_MODE_WRITE 2
+#define CONTROL_COMMAND_MODE_USER 3
+
+#define CONTROL_KEEP_MASK \
+ (CONTROL_AAF_MODE | CONTROL_CE_INACTIVE_MASK | CONTROL_CLK_DIV4 | \
+ CONTROL_IO_DUMMY_MASK | CONTROL_CLOCK_FREQ_SEL_MASK | \
+ CONTROL_LSB_FIRST | CONTROL_CLOCK_MODE_3)
+
+/*
+ * The Segment Register uses a 8MB unit to encode the start address
+ * and the end address of the mapping window of a flash SPI slave :
+ *
+ * | byte 1 | byte 2 | byte 3 | byte 4 |
+ * +--------+--------+--------+--------+
+ * | end | start | 0 | 0 |
+ */
+#define SEGMENT_ADDR_REG0 0x30
+#define SEGMENT_ADDR_START(_r) ((((_r) >> 16) & 0xFF) << 23)
+#define SEGMENT_ADDR_END(_r) ((((_r) >> 24) & 0xFF) << 23)
+
+/*
+ * In user mode all data bytes read or written to the chip decode address
+ * range are transferred to or from the SPI bus. The range is treated as a
+ * fifo of arbitratry 1, 2, or 4 byte width but each write has to be aligned
+ * to its size. The address within the multiple 8kB range is ignored when
+ * sending bytes to the SPI bus.
+ *
+ * On the arm architecture, as of Linux version 4.3, memcpy_fromio and
+ * memcpy_toio on little endian targets use the optimized memcpy routines
+ * that were designed for well behavied memory storage. These routines
+ * have a stutter if the source and destination are not both word aligned,
+ * once with a duplicate access to the source after aligning to the
+ * destination to a word boundary, and again with a duplicate access to
+ * the source when the final byte count is not word aligned.
+ *
+ * When writing or reading the fifo this stutter discards data or sends
+ * too much data to the fifo and can not be used by this driver.
+ *
+ * While the low level io string routines that implement the insl family do
+ * the desired accesses and memory increments, the cross architecture io
+ * macros make them essentially impossible to use on a memory mapped address
+ * instead of a a token from the call to iomap of an io port.
+ *
+ * These fifo routines use readl and friends to a constant io port and update
+ * the memory buffer pointer and count via explicit code. The final updates
+ * to len are optimistically suppressed.
+ */
+static int aspeed_smc_read_from_ahb(void *buf, void __iomem *src, size_t len)
+{
+ size_t offset = 0;
+
+ if (IS_ALIGNED((uintptr_t)src, sizeof(uintptr_t)) &&
+ IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) {
+ ioread32_rep(src, buf, len >> 2);
+ offset = len & ~0x3;
+ len -= offset;
+ }
+ ioread8_rep(src, (u8 *)buf + offset, len);
+ return 0;
+}
+
+static int aspeed_smc_write_to_ahb(void __iomem *dst, const void *buf,
+ size_t len)
+{
+ size_t offset = 0;
+
+ if (IS_ALIGNED((uintptr_t)dst, sizeof(uintptr_t)) &&
+ IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) {
+ iowrite32_rep(dst, buf, len >> 2);
+ offset = len & ~0x3;
+ len -= offset;
+ }
+ iowrite8_rep(dst, (const u8 *)buf + offset, len);
+ return 0;
+}
+
+static inline u32 aspeed_smc_chip_write_bit(struct aspeed_smc_chip *chip)
+{
+ return BIT(chip->controller->info->we0 + chip->cs);
+}
+
+static void aspeed_smc_chip_check_config(struct aspeed_smc_chip *chip)
+{
+ struct aspeed_smc_controller *controller = chip->controller;
+ u32 reg;
+
+ reg = readl(controller->regs + CONFIG_REG);
+
+ if (reg & aspeed_smc_chip_write_bit(chip))
+ return;
+
+ dev_dbg(controller->dev, "config write is not set ! @%p: 0x%08x\n",
+ controller->regs + CONFIG_REG, reg);
+ reg |= aspeed_smc_chip_write_bit(chip);
+ writel(reg, controller->regs + CONFIG_REG);
+}
+
+static void aspeed_smc_start_user(struct spi_nor *nor)
+{
+ struct aspeed_smc_chip *chip = nor->priv;
+ u32 ctl = chip->ctl_val[smc_base];
+
+ /*
+ * When the chip is controlled in user mode, we need write
+ * access to send the opcodes to it. So check the config.
+ */
+ aspeed_smc_chip_check_config(chip);
+
+ ctl |= CONTROL_COMMAND_MODE_USER |
+ CONTROL_CE_STOP_ACTIVE_CONTROL;
+ writel(ctl, chip->ctl);
+
+ ctl &= ~CONTROL_CE_STOP_ACTIVE_CONTROL;
+ writel(ctl, chip->ctl);
+}
+
+static void aspeed_smc_stop_user(struct spi_nor *nor)
+{
+ struct aspeed_smc_chip *chip = nor->priv;
+
+ u32 ctl = chip->ctl_val[smc_read];
+ u32 ctl2 = ctl | CONTROL_COMMAND_MODE_USER |
+ CONTROL_CE_STOP_ACTIVE_CONTROL;
+
+ writel(ctl2, chip->ctl); /* stop user CE control */
+ writel(ctl, chip->ctl); /* default to fread or read mode */
+}
+
+static int aspeed_smc_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+ struct aspeed_smc_chip *chip = nor->priv;
+
+ mutex_lock(&chip->controller->mutex);
+ return 0;
+}
+
+static void aspeed_smc_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+ struct aspeed_smc_chip *chip = nor->priv;
+
+ mutex_unlock(&chip->controller->mutex);
+}
+
+static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+ struct aspeed_smc_chip *chip = nor->priv;
+
+ aspeed_smc_start_user(nor);
+ aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1);
+ aspeed_smc_read_from_ahb(buf, chip->ahb_base, len);
+ aspeed_smc_stop_user(nor);
+ return 0;
+}
+
+static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+ int len)
+{
+ struct aspeed_smc_chip *chip = nor->priv;
+
+ aspeed_smc_start_user(nor);
+ aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1);
+ aspeed_smc_write_to_ahb(chip->ahb_base, buf, len);
+ aspeed_smc_stop_user(nor);
+ return 0;
+}
+
+static void aspeed_smc_send_cmd_addr(struct spi_nor *nor, u8 cmd, u32 addr)
+{
+ struct aspeed_smc_chip *chip = nor->priv;
+ __be32 temp;
+ u32 cmdaddr;
+
+ switch (nor->addr_width) {
+ default:
+ WARN_ONCE(1, "Unexpected address width %u, defaulting to 3\n",
+ nor->addr_width);
+ /* FALLTHROUGH */
+ case 3:
+ cmdaddr = addr & 0xFFFFFF;
+ cmdaddr |= cmd << 24;
+
+ temp = cpu_to_be32(cmdaddr);
+ aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4);
+ break;
+ case 4:
+ temp = cpu_to_be32(addr);
+ aspeed_smc_write_to_ahb(chip->ahb_base, &cmd, 1);
+ aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4);
+ break;
+ }
+}
+
+static ssize_t aspeed_smc_read_user(struct spi_nor *nor, loff_t from,
+ size_t len, u_char *read_buf)
+{
+ struct aspeed_smc_chip *chip = nor->priv;
+ int i;
+ u8 dummy = 0xFF;
+
+ aspeed_smc_start_user(nor);
+ aspeed_smc_send_cmd_addr(nor, nor->read_opcode, from);
+ for (i = 0; i < chip->nor.read_dummy / 8; i++)
+ aspeed_smc_write_to_ahb(chip->ahb_base, &dummy, sizeof(dummy));
+
+ aspeed_smc_read_from_ahb(read_buf, chip->ahb_base, len);
+ aspeed_smc_stop_user(nor);
+ return len;
+}
+
+static ssize_t aspeed_smc_write_user(struct spi_nor *nor, loff_t to,
+ size_t len, const u_char *write_buf)
+{
+ struct aspeed_smc_chip *chip = nor->priv;
+
+ aspeed_smc_start_user(nor);
+ aspeed_smc_send_cmd_addr(nor, nor->program_opcode, to);
+ aspeed_smc_write_to_ahb(chip->ahb_base, write_buf, len);
+ aspeed_smc_stop_user(nor);
+ return len;
+}
+
+static int aspeed_smc_unregister(struct aspeed_smc_controller *controller)
+{
+ struct aspeed_smc_chip *chip;
+ int n;
+
+ for (n = 0; n < controller->info->nce; n++) {
+ chip = controller->chips[n];
+ if (chip)
+ mtd_device_unregister(&chip->nor.mtd);
+ }
+
+ return 0;
+}
+
+static int aspeed_smc_remove(struct platform_device *dev)
+{
+ return aspeed_smc_unregister(platform_get_drvdata(dev));
+}
+
+static const struct of_device_id aspeed_smc_matches[] = {
+ { .compatible = "aspeed,ast2400-fmc", .data = &fmc_2400_info },
+ { .compatible = "aspeed,ast2400-spi", .data = &spi_2400_info },
+ { .compatible = "aspeed,ast2500-fmc", .data = &fmc_2500_info },
+ { .compatible = "aspeed,ast2500-spi", .data = &spi_2500_info },
+ { }
+};
+MODULE_DEVICE_TABLE(of, aspeed_smc_matches);
+
+/*
+ * Each chip has a mapping window defined by a segment address
+ * register defining a start and an end address on the AHB bus. These
+ * addresses can be configured to fit the chip size and offer a
+ * contiguous memory region across chips. For the moment, we only
+ * check that each chip segment is valid.
+ */
+static void __iomem *aspeed_smc_chip_base(struct aspeed_smc_chip *chip,
+ struct resource *res)
+{
+ struct aspeed_smc_controller *controller = chip->controller;
+ u32 offset = 0;
+ u32 reg;
+
+ if (controller->info->nce > 1) {
+ reg = readl(controller->regs + SEGMENT_ADDR_REG0 +
+ chip->cs * 4);
+
+ if (SEGMENT_ADDR_START(reg) >= SEGMENT_ADDR_END(reg))
+ return NULL;
+
+ offset = SEGMENT_ADDR_START(reg) - res->start;
+ }
+
+ return controller->ahb_base + offset;
+}
+
+static void aspeed_smc_chip_enable_write(struct aspeed_smc_chip *chip)
+{
+ struct aspeed_smc_controller *controller = chip->controller;
+ u32 reg;
+
+ reg = readl(controller->regs + CONFIG_REG);
+
+ reg |= aspeed_smc_chip_write_bit(chip);
+ writel(reg, controller->regs + CONFIG_REG);
+}
+
+static void aspeed_smc_chip_set_type(struct aspeed_smc_chip *chip, int type)
+{
+ struct aspeed_smc_controller *controller = chip->controller;
+ u32 reg;
+
+ chip->type = type;
+
+ reg = readl(controller->regs + CONFIG_REG);
+ reg &= ~(3 << (chip->cs * 2));
+ reg |= chip->type << (chip->cs * 2);
+ writel(reg, controller->regs + CONFIG_REG);
+}
+
+/*
+ * The AST2500 FMC flash controller should be strapped by hardware, or
+ * autodetected, but the AST2500 SPI flash needs to be set.
+ */
+static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip)
+{
+ struct aspeed_smc_controller *controller = chip->controller;
+ u32 reg;
+
+ if (chip->controller->info == &spi_2500_info) {
+ reg = readl(controller->regs + CE_CONTROL_REG);
+ reg |= 1 << chip->cs;
+ writel(reg, controller->regs + CE_CONTROL_REG);
+ }
+}
+
+/*
+ * The AST2400 SPI flash controller does not have a CE Control
+ * register. It uses the CE0 control register to set 4Byte mode at the
+ * controller level.
+ */
+static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip)
+{
+ chip->ctl_val[smc_base] |= CONTROL_IO_ADDRESS_4B;
+ chip->ctl_val[smc_read] |= CONTROL_IO_ADDRESS_4B;
+}
+
+static int aspeed_smc_chip_setup_init(struct aspeed_smc_chip *chip,
+ struct resource *res)
+{
+ struct aspeed_smc_controller *controller = chip->controller;
+ const struct aspeed_smc_info *info = controller->info;
+ u32 reg, base_reg;
+
+ /*
+ * Always turn on the write enable bit to allow opcodes to be
+ * sent in user mode.
+ */
+ aspeed_smc_chip_enable_write(chip);
+
+ /* The driver only supports SPI type flash */
+ if (info->hastype)
+ aspeed_smc_chip_set_type(chip, smc_type_spi);
+
+ /*
+ * Configure chip base address in memory
+ */
+ chip->ahb_base = aspeed_smc_chip_base(chip, res);
+ if (!chip->ahb_base) {
+ dev_warn(chip->nor.dev, "CE segment window closed.\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Get value of the inherited control register. U-Boot usually
+ * does some timing calibration on the FMC chip, so it's good
+ * to keep them. In the future, we should handle calibration
+ * from Linux.
+ */
+ reg = readl(chip->ctl);
+ dev_dbg(controller->dev, "control register: %08x\n", reg);
+
+ base_reg = reg & CONTROL_KEEP_MASK;
+ if (base_reg != reg) {
+ dev_dbg(controller->dev,
+ "control register changed to: %08x\n",
+ base_reg);
+ }
+ chip->ctl_val[smc_base] = base_reg;
+
+ /*
+ * Retain the prior value of the control register as the
+ * default if it was normal access mode. Otherwise start with
+ * the sanitized base value set to read mode.
+ */
+ if ((reg & CONTROL_COMMAND_MODE_MASK) ==
+ CONTROL_COMMAND_MODE_NORMAL)
+ chip->ctl_val[smc_read] = reg;
+ else
+ chip->ctl_val[smc_read] = chip->ctl_val[smc_base] |
+ CONTROL_COMMAND_MODE_NORMAL;
+
+ dev_dbg(controller->dev, "default control register: %08x\n",
+ chip->ctl_val[smc_read]);
+ return 0;
+}
+
+static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
+{
+ struct aspeed_smc_controller *controller = chip->controller;
+ const struct aspeed_smc_info *info = controller->info;
+ u32 cmd;
+
+ if (chip->nor.addr_width == 4 && info->set_4b)
+ info->set_4b(chip);
+
+ /*
+ * base mode has not been optimized yet. use it for writes.
+ */
+ chip->ctl_val[smc_write] = chip->ctl_val[smc_base] |
+ chip->nor.program_opcode << CONTROL_COMMAND_SHIFT |
+ CONTROL_COMMAND_MODE_WRITE;
+
+ dev_dbg(controller->dev, "write control register: %08x\n",
+ chip->ctl_val[smc_write]);
+
+ /*
+ * TODO: Adjust clocks if fast read is supported and interpret
+ * SPI-NOR flags to adjust controller settings.
+ */
+ switch (chip->nor.flash_read) {
+ case SPI_NOR_NORMAL:
+ cmd = CONTROL_COMMAND_MODE_NORMAL;
+ break;
+ case SPI_NOR_FAST:
+ cmd = CONTROL_COMMAND_MODE_FREAD;
+ break;
+ default:
+ dev_err(chip->nor.dev, "unsupported SPI read mode\n");
+ return -EINVAL;
+ }
+
+ chip->ctl_val[smc_read] |= cmd |
+ CONTROL_IO_DUMMY_SET(chip->nor.read_dummy / 8);
+
+ dev_dbg(controller->dev, "base control register: %08x\n",
+ chip->ctl_val[smc_read]);
+ return 0;
+}
+
+static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
+ struct device_node *np, struct resource *r)
+{
+ const struct aspeed_smc_info *info = controller->info;
+ struct device *dev = controller->dev;
+ struct device_node *child;
+ unsigned int cs;
+ int ret = -ENODEV;
+
+ for_each_available_child_of_node(np, child) {
+ struct aspeed_smc_chip *chip;
+ struct spi_nor *nor;
+ struct mtd_info *mtd;
+
+ /* This driver does not support NAND or NOR flash devices. */
+ if (!of_device_is_compatible(child, "jedec,spi-nor"))
+ continue;
+
+ ret = of_property_read_u32(child, "reg", &cs);
+ if (ret) {
+ dev_err(dev, "Couldn't not read chip select.\n");
+ break;
+ }
+
+ if (cs >= info->nce) {
+ dev_err(dev, "Chip select %d out of range.\n",
+ cs);
+ ret = -ERANGE;
+ break;
+ }
+
+ if (controller->chips[cs]) {
+ dev_err(dev, "Chip select %d already in use by %s\n",
+ cs, dev_name(controller->chips[cs]->nor.dev));
+ ret = -EBUSY;
+ break;
+ }
+
+ chip = devm_kzalloc(controller->dev, sizeof(*chip), GFP_KERNEL);
+ if (!chip) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ chip->controller = controller;
+ chip->ctl = controller->regs + info->ctl0 + cs * 4;
+ chip->cs = cs;
+
+ nor = &chip->nor;
+ mtd = &nor->mtd;
+
+ nor->dev = dev;
+ nor->priv = chip;
+ spi_nor_set_flash_node(nor, child);
+ nor->read = aspeed_smc_read_user;
+ nor->write = aspeed_smc_write_user;
+ nor->read_reg = aspeed_smc_read_reg;
+ nor->write_reg = aspeed_smc_write_reg;
+ nor->prepare = aspeed_smc_prep;
+ nor->unprepare = aspeed_smc_unprep;
+
+ ret = aspeed_smc_chip_setup_init(chip, r);
+ if (ret)
+ break;
+
+ /*
+ * TODO: Add support for SPI_NOR_QUAD and SPI_NOR_DUAL
+ * attach when board support is present as determined
+ * by of property.
+ */
+ ret = spi_nor_scan(nor, NULL, SPI_NOR_NORMAL);
+ if (ret)
+ break;
+
+ ret = aspeed_smc_chip_setup_finish(chip);
+ if (ret)
+ break;
+
+ ret = mtd_device_register(mtd, NULL, 0);
+ if (ret)
+ break;
+
+ controller->chips[cs] = chip;
+ }
+
+ if (ret)
+ aspeed_smc_unregister(controller);
+
+ return ret;
+}
+
+static int aspeed_smc_probe(struct platform_device *pdev)
+{
+ struct device_node *np = pdev->dev.of_node;
+ struct device *dev = &pdev->dev;
+ struct aspeed_smc_controller *controller;
+ const struct of_device_id *match;
+ const struct aspeed_smc_info *info;
+ struct resource *res;
+ int ret;
+
+ match = of_match_device(aspeed_smc_matches, &pdev->dev);
+ if (!match || !match->data)
+ return -ENODEV;
+ info = match->data;
+
+ controller = devm_kzalloc(&pdev->dev, sizeof(*controller) +
+ info->nce * sizeof(controller->chips[0]), GFP_KERNEL);
+ if (!controller)
+ return -ENOMEM;
+ controller->info = info;
+ controller->dev = dev;
+
+ mutex_init(&controller->mutex);
+ platform_set_drvdata(pdev, controller);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ controller->regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(controller->regs))
+ return PTR_ERR(controller->regs);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ controller->ahb_base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(controller->ahb_base))
+ return PTR_ERR(controller->ahb_base);
+
+ ret = aspeed_smc_setup_flash(controller, np, res);
+ if (ret)
+ dev_err(dev, "Aspeed SMC probe failed %d\n", ret);
+
+ return ret;
+}
+
+static struct platform_driver aspeed_smc_driver = {
+ .probe = aspeed_smc_probe,
+ .remove = aspeed_smc_remove,
+ .driver = {
+ .name = DEVICE_NAME,
+ .of_match_table = aspeed_smc_matches,
+ }
+};
+
+module_platform_driver(aspeed_smc_driver);
+
+MODULE_DESCRIPTION("ASPEED Static Memory Controller Driver");
+MODULE_AUTHOR("Cedric Le Goater <clg@kaod.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index d489fbd..9f8102d 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -526,7 +526,8 @@
bytes_to_read *= cqspi->fifo_width;
bytes_to_read = bytes_to_read > remaining ?
remaining : bytes_to_read;
- readsl(ahb_base, rxbuf, DIV_ROUND_UP(bytes_to_read, 4));
+ ioread32_rep(ahb_base, rxbuf,
+ DIV_ROUND_UP(bytes_to_read, 4));
rxbuf += bytes_to_read;
remaining -= bytes_to_read;
bytes_to_read = cqspi_get_rd_sram_level(cqspi);
@@ -610,7 +611,8 @@
while (remaining > 0) {
write_bytes = remaining > page_size ? page_size : remaining;
- writesl(cqspi->ahb_base, txbuf, DIV_ROUND_UP(write_bytes, 4));
+ iowrite32_rep(cqspi->ahb_base, txbuf,
+ DIV_ROUND_UP(write_bytes, 4));
ret = wait_for_completion_timeout(&cqspi->transfer_complete,
msecs_to_jiffies
@@ -891,7 +893,7 @@
if (ret)
return ret;
- return (ret < 0) ? ret : len;
+ return len;
}
static ssize_t cqspi_read(struct spi_nor *nor, loff_t from,
@@ -911,7 +913,7 @@
if (ret)
return ret;
- return (ret < 0) ? ret : len;
+ return len;
}
static int cqspi_erase(struct spi_nor *nor, loff_t offs)
diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c
index b4d8953..1476135 100644
--- a/drivers/mtd/spi-nor/fsl-quadspi.c
+++ b/drivers/mtd/spi-nor/fsl-quadspi.c
@@ -193,7 +193,7 @@
#define QUADSPI_LUT_NUM 64
/* SEQID -- we can have 16 seqids at most. */
-#define SEQID_QUAD_READ 0
+#define SEQID_READ 0
#define SEQID_WREN 1
#define SEQID_WRDI 2
#define SEQID_RDSR 3
@@ -373,32 +373,26 @@
void __iomem *base = q->iobase;
int rxfifo = q->devtype_data->rxfifo;
u32 lut_base;
- u8 cmd, addrlen, dummy;
int i;
+ struct spi_nor *nor = &q->nor[0];
+ u8 addrlen = (nor->addr_width == 3) ? ADDR24BIT : ADDR32BIT;
+ u8 read_op = nor->read_opcode;
+ u8 read_dm = nor->read_dummy;
+
fsl_qspi_unlock_lut(q);
/* Clear all the LUT table */
for (i = 0; i < QUADSPI_LUT_NUM; i++)
qspi_writel(q, 0, base + QUADSPI_LUT_BASE + i * 4);
- /* Quad Read */
- lut_base = SEQID_QUAD_READ * 4;
+ /* Read */
+ lut_base = SEQID_READ * 4;
- if (q->nor_size <= SZ_16M) {
- cmd = SPINOR_OP_READ_1_1_4;
- addrlen = ADDR24BIT;
- dummy = 8;
- } else {
- /* use the 4-byte address */
- cmd = SPINOR_OP_READ_1_1_4;
- addrlen = ADDR32BIT;
- dummy = 8;
- }
-
- qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+ qspi_writel(q, LUT0(CMD, PAD1, read_op) | LUT1(ADDR, PAD1, addrlen),
base + QUADSPI_LUT(lut_base));
- qspi_writel(q, LUT0(DUMMY, PAD1, dummy) | LUT1(FSL_READ, PAD4, rxfifo),
+ qspi_writel(q, LUT0(DUMMY, PAD1, read_dm) |
+ LUT1(FSL_READ, PAD4, rxfifo),
base + QUADSPI_LUT(lut_base + 1));
/* Write enable */
@@ -409,16 +403,8 @@
/* Page Program */
lut_base = SEQID_PP * 4;
- if (q->nor_size <= SZ_16M) {
- cmd = SPINOR_OP_PP;
- addrlen = ADDR24BIT;
- } else {
- /* use the 4-byte address */
- cmd = SPINOR_OP_PP;
- addrlen = ADDR32BIT;
- }
-
- qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+ qspi_writel(q, LUT0(CMD, PAD1, nor->program_opcode) |
+ LUT1(ADDR, PAD1, addrlen),
base + QUADSPI_LUT(lut_base));
qspi_writel(q, LUT0(FSL_WRITE, PAD1, 0),
base + QUADSPI_LUT(lut_base + 1));
@@ -432,10 +418,8 @@
/* Erase a sector */
lut_base = SEQID_SE * 4;
- cmd = q->nor[0].erase_opcode;
- addrlen = q->nor_size <= SZ_16M ? ADDR24BIT : ADDR32BIT;
-
- qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+ qspi_writel(q, LUT0(CMD, PAD1, nor->erase_opcode) |
+ LUT1(ADDR, PAD1, addrlen),
base + QUADSPI_LUT(lut_base));
/* Erase the whole chip */
@@ -484,7 +468,7 @@
{
switch (cmd) {
case SPINOR_OP_READ_1_1_4:
- return SEQID_QUAD_READ;
+ return SEQID_READ;
case SPINOR_OP_WREN:
return SEQID_WREN;
case SPINOR_OP_WRDI:
diff --git a/drivers/mtd/spi-nor/intel-spi-platform.c b/drivers/mtd/spi-nor/intel-spi-platform.c
new file mode 100644
index 0000000..5c943df
--- /dev/null
+++ b/drivers/mtd/spi-nor/intel-spi-platform.c
@@ -0,0 +1,57 @@
+/*
+ * Intel PCH/PCU SPI flash platform driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "intel-spi.h"
+
+static int intel_spi_platform_probe(struct platform_device *pdev)
+{
+ struct intel_spi_boardinfo *info;
+ struct intel_spi *ispi;
+ struct resource *mem;
+
+ info = dev_get_platdata(&pdev->dev);
+ if (!info)
+ return -EINVAL;
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ ispi = intel_spi_probe(&pdev->dev, mem, info);
+ if (IS_ERR(ispi))
+ return PTR_ERR(ispi);
+
+ platform_set_drvdata(pdev, ispi);
+ return 0;
+}
+
+static int intel_spi_platform_remove(struct platform_device *pdev)
+{
+ struct intel_spi *ispi = platform_get_drvdata(pdev);
+
+ return intel_spi_remove(ispi);
+}
+
+static struct platform_driver intel_spi_platform_driver = {
+ .probe = intel_spi_platform_probe,
+ .remove = intel_spi_platform_remove,
+ .driver = {
+ .name = "intel-spi",
+ },
+};
+
+module_platform_driver(intel_spi_platform_driver);
+
+MODULE_DESCRIPTION("Intel PCH/PCU SPI flash platform driver");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:intel-spi");
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
new file mode 100644
index 0000000..a10f602
--- /dev/null
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -0,0 +1,777 @@
+/*
+ * Intel PCH/PCU SPI flash driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sizes.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/platform_data/intel-spi.h>
+
+#include "intel-spi.h"
+
+/* Offsets are from @ispi->base */
+#define BFPREG 0x00
+
+#define HSFSTS_CTL 0x04
+#define HSFSTS_CTL_FSMIE BIT(31)
+#define HSFSTS_CTL_FDBC_SHIFT 24
+#define HSFSTS_CTL_FDBC_MASK (0x3f << HSFSTS_CTL_FDBC_SHIFT)
+
+#define HSFSTS_CTL_FCYCLE_SHIFT 17
+#define HSFSTS_CTL_FCYCLE_MASK (0x0f << HSFSTS_CTL_FCYCLE_SHIFT)
+/* HW sequencer opcodes */
+#define HSFSTS_CTL_FCYCLE_READ (0x00 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_WRITE (0x02 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_ERASE (0x03 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_ERASE_64K (0x04 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_RDID (0x06 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_WRSR (0x07 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_RDSR (0x08 << HSFSTS_CTL_FCYCLE_SHIFT)
+
+#define HSFSTS_CTL_FGO BIT(16)
+#define HSFSTS_CTL_FLOCKDN BIT(15)
+#define HSFSTS_CTL_FDV BIT(14)
+#define HSFSTS_CTL_SCIP BIT(5)
+#define HSFSTS_CTL_AEL BIT(2)
+#define HSFSTS_CTL_FCERR BIT(1)
+#define HSFSTS_CTL_FDONE BIT(0)
+
+#define FADDR 0x08
+#define DLOCK 0x0c
+#define FDATA(n) (0x10 + ((n) * 4))
+
+#define FRACC 0x50
+
+#define FREG(n) (0x54 + ((n) * 4))
+#define FREG_BASE_MASK 0x3fff
+#define FREG_LIMIT_SHIFT 16
+#define FREG_LIMIT_MASK (0x03fff << FREG_LIMIT_SHIFT)
+
+/* Offset is from @ispi->pregs */
+#define PR(n) ((n) * 4)
+#define PR_WPE BIT(31)
+#define PR_LIMIT_SHIFT 16
+#define PR_LIMIT_MASK (0x3fff << PR_LIMIT_SHIFT)
+#define PR_RPE BIT(15)
+#define PR_BASE_MASK 0x3fff
+/* Last PR is GPR0 */
+#define PR_NUM (5 + 1)
+
+/* Offsets are from @ispi->sregs */
+#define SSFSTS_CTL 0x00
+#define SSFSTS_CTL_FSMIE BIT(23)
+#define SSFSTS_CTL_DS BIT(22)
+#define SSFSTS_CTL_DBC_SHIFT 16
+#define SSFSTS_CTL_SPOP BIT(11)
+#define SSFSTS_CTL_ACS BIT(10)
+#define SSFSTS_CTL_SCGO BIT(9)
+#define SSFSTS_CTL_COP_SHIFT 12
+#define SSFSTS_CTL_FRS BIT(7)
+#define SSFSTS_CTL_DOFRS BIT(6)
+#define SSFSTS_CTL_AEL BIT(4)
+#define SSFSTS_CTL_FCERR BIT(3)
+#define SSFSTS_CTL_FDONE BIT(2)
+#define SSFSTS_CTL_SCIP BIT(0)
+
+#define PREOP_OPTYPE 0x04
+#define OPMENU0 0x08
+#define OPMENU1 0x0c
+
+/* CPU specifics */
+#define BYT_PR 0x74
+#define BYT_SSFSTS_CTL 0x90
+#define BYT_BCR 0xfc
+#define BYT_BCR_WPD BIT(0)
+#define BYT_FREG_NUM 5
+
+#define LPT_PR 0x74
+#define LPT_SSFSTS_CTL 0x90
+#define LPT_FREG_NUM 5
+
+#define BXT_PR 0x84
+#define BXT_SSFSTS_CTL 0xa0
+#define BXT_FREG_NUM 12
+
+#define INTEL_SPI_TIMEOUT 5000 /* ms */
+#define INTEL_SPI_FIFO_SZ 64
+
+/**
+ * struct intel_spi - Driver private data
+ * @dev: Device pointer
+ * @info: Pointer to board specific info
+ * @nor: SPI NOR layer structure
+ * @base: Beginning of MMIO space
+ * @pregs: Start of protection registers
+ * @sregs: Start of software sequencer registers
+ * @nregions: Maximum number of regions
+ * @writeable: Is the chip writeable
+ * @swseq: Use SW sequencer in register reads/writes
+ * @erase_64k: 64k erase supported
+ * @opcodes: Opcodes which are supported. This are programmed by BIOS
+ * before it locks down the controller.
+ * @preopcodes: Preopcodes which are supported.
+ */
+struct intel_spi {
+ struct device *dev;
+ const struct intel_spi_boardinfo *info;
+ struct spi_nor nor;
+ void __iomem *base;
+ void __iomem *pregs;
+ void __iomem *sregs;
+ size_t nregions;
+ bool writeable;
+ bool swseq;
+ bool erase_64k;
+ u8 opcodes[8];
+ u8 preopcodes[2];
+};
+
+static bool writeable;
+module_param(writeable, bool, 0);
+MODULE_PARM_DESC(writeable, "Enable write access to SPI flash chip (default=0)");
+
+static void intel_spi_dump_regs(struct intel_spi *ispi)
+{
+ u32 value;
+ int i;
+
+ dev_dbg(ispi->dev, "BFPREG=0x%08x\n", readl(ispi->base + BFPREG));
+
+ value = readl(ispi->base + HSFSTS_CTL);
+ dev_dbg(ispi->dev, "HSFSTS_CTL=0x%08x\n", value);
+ if (value & HSFSTS_CTL_FLOCKDN)
+ dev_dbg(ispi->dev, "-> Locked\n");
+
+ dev_dbg(ispi->dev, "FADDR=0x%08x\n", readl(ispi->base + FADDR));
+ dev_dbg(ispi->dev, "DLOCK=0x%08x\n", readl(ispi->base + DLOCK));
+
+ for (i = 0; i < 16; i++)
+ dev_dbg(ispi->dev, "FDATA(%d)=0x%08x\n",
+ i, readl(ispi->base + FDATA(i)));
+
+ dev_dbg(ispi->dev, "FRACC=0x%08x\n", readl(ispi->base + FRACC));
+
+ for (i = 0; i < ispi->nregions; i++)
+ dev_dbg(ispi->dev, "FREG(%d)=0x%08x\n", i,
+ readl(ispi->base + FREG(i)));
+ for (i = 0; i < PR_NUM; i++)
+ dev_dbg(ispi->dev, "PR(%d)=0x%08x\n", i,
+ readl(ispi->pregs + PR(i)));
+
+ value = readl(ispi->sregs + SSFSTS_CTL);
+ dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value);
+ dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n",
+ readl(ispi->sregs + PREOP_OPTYPE));
+ dev_dbg(ispi->dev, "OPMENU0=0x%08x\n", readl(ispi->sregs + OPMENU0));
+ dev_dbg(ispi->dev, "OPMENU1=0x%08x\n", readl(ispi->sregs + OPMENU1));
+
+ if (ispi->info->type == INTEL_SPI_BYT)
+ dev_dbg(ispi->dev, "BCR=0x%08x\n", readl(ispi->base + BYT_BCR));
+
+ dev_dbg(ispi->dev, "Protected regions:\n");
+ for (i = 0; i < PR_NUM; i++) {
+ u32 base, limit;
+
+ value = readl(ispi->pregs + PR(i));
+ if (!(value & (PR_WPE | PR_RPE)))
+ continue;
+
+ limit = (value & PR_LIMIT_MASK) >> PR_LIMIT_SHIFT;
+ base = value & PR_BASE_MASK;
+
+ dev_dbg(ispi->dev, " %02d base: 0x%08x limit: 0x%08x [%c%c]\n",
+ i, base << 12, (limit << 12) | 0xfff,
+ value & PR_WPE ? 'W' : '.',
+ value & PR_RPE ? 'R' : '.');
+ }
+
+ dev_dbg(ispi->dev, "Flash regions:\n");
+ for (i = 0; i < ispi->nregions; i++) {
+ u32 region, base, limit;
+
+ region = readl(ispi->base + FREG(i));
+ base = region & FREG_BASE_MASK;
+ limit = (region & FREG_LIMIT_MASK) >> FREG_LIMIT_SHIFT;
+
+ if (base >= limit || (i > 0 && limit == 0))
+ dev_dbg(ispi->dev, " %02d disabled\n", i);
+ else
+ dev_dbg(ispi->dev, " %02d base: 0x%08x limit: 0x%08x\n",
+ i, base << 12, (limit << 12) | 0xfff);
+ }
+
+ dev_dbg(ispi->dev, "Using %cW sequencer for register access\n",
+ ispi->swseq ? 'S' : 'H');
+}
+
+/* Reads max INTEL_SPI_FIFO_SZ bytes from the device fifo */
+static int intel_spi_read_block(struct intel_spi *ispi, void *buf, size_t size)
+{
+ size_t bytes;
+ int i = 0;
+
+ if (size > INTEL_SPI_FIFO_SZ)
+ return -EINVAL;
+
+ while (size > 0) {
+ bytes = min_t(size_t, size, 4);
+ memcpy_fromio(buf, ispi->base + FDATA(i), bytes);
+ size -= bytes;
+ buf += bytes;
+ i++;
+ }
+
+ return 0;
+}
+
+/* Writes max INTEL_SPI_FIFO_SZ bytes to the device fifo */
+static int intel_spi_write_block(struct intel_spi *ispi, const void *buf,
+ size_t size)
+{
+ size_t bytes;
+ int i = 0;
+
+ if (size > INTEL_SPI_FIFO_SZ)
+ return -EINVAL;
+
+ while (size > 0) {
+ bytes = min_t(size_t, size, 4);
+ memcpy_toio(ispi->base + FDATA(i), buf, bytes);
+ size -= bytes;
+ buf += bytes;
+ i++;
+ }
+
+ return 0;
+}
+
+static int intel_spi_wait_hw_busy(struct intel_spi *ispi)
+{
+ u32 val;
+
+ return readl_poll_timeout(ispi->base + HSFSTS_CTL, val,
+ !(val & HSFSTS_CTL_SCIP), 0,
+ INTEL_SPI_TIMEOUT * 1000);
+}
+
+static int intel_spi_wait_sw_busy(struct intel_spi *ispi)
+{
+ u32 val;
+
+ return readl_poll_timeout(ispi->sregs + SSFSTS_CTL, val,
+ !(val & SSFSTS_CTL_SCIP), 0,
+ INTEL_SPI_TIMEOUT * 1000);
+}
+
+static int intel_spi_init(struct intel_spi *ispi)
+{
+ u32 opmenu0, opmenu1, val;
+ int i;
+
+ switch (ispi->info->type) {
+ case INTEL_SPI_BYT:
+ ispi->sregs = ispi->base + BYT_SSFSTS_CTL;
+ ispi->pregs = ispi->base + BYT_PR;
+ ispi->nregions = BYT_FREG_NUM;
+
+ if (writeable) {
+ /* Disable write protection */
+ val = readl(ispi->base + BYT_BCR);
+ if (!(val & BYT_BCR_WPD)) {
+ val |= BYT_BCR_WPD;
+ writel(val, ispi->base + BYT_BCR);
+ val = readl(ispi->base + BYT_BCR);
+ }
+
+ ispi->writeable = !!(val & BYT_BCR_WPD);
+ }
+
+ break;
+
+ case INTEL_SPI_LPT:
+ ispi->sregs = ispi->base + LPT_SSFSTS_CTL;
+ ispi->pregs = ispi->base + LPT_PR;
+ ispi->nregions = LPT_FREG_NUM;
+ break;
+
+ case INTEL_SPI_BXT:
+ ispi->sregs = ispi->base + BXT_SSFSTS_CTL;
+ ispi->pregs = ispi->base + BXT_PR;
+ ispi->nregions = BXT_FREG_NUM;
+ ispi->erase_64k = true;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ /* Disable #SMI generation */
+ val = readl(ispi->base + HSFSTS_CTL);
+ val &= ~HSFSTS_CTL_FSMIE;
+ writel(val, ispi->base + HSFSTS_CTL);
+
+ /*
+ * BIOS programs allowed opcodes and then locks down the register.
+ * So read back what opcodes it decided to support. That's the set
+ * we are going to support as well.
+ */
+ opmenu0 = readl(ispi->sregs + OPMENU0);
+ opmenu1 = readl(ispi->sregs + OPMENU1);
+
+ /*
+ * Some controllers can only do basic operations using hardware
+ * sequencer. All other operations are supposed to be carried out
+ * using software sequencer. If we find that BIOS has programmed
+ * opcodes for the software sequencer we use that over the hardware
+ * sequencer.
+ */
+ if (opmenu0 && opmenu1) {
+ for (i = 0; i < ARRAY_SIZE(ispi->opcodes) / 2; i++) {
+ ispi->opcodes[i] = opmenu0 >> i * 8;
+ ispi->opcodes[i + 4] = opmenu1 >> i * 8;
+ }
+
+ val = readl(ispi->sregs + PREOP_OPTYPE);
+ ispi->preopcodes[0] = val;
+ ispi->preopcodes[1] = val >> 8;
+
+ /* Disable #SMI generation from SW sequencer */
+ val = readl(ispi->sregs + SSFSTS_CTL);
+ val &= ~SSFSTS_CTL_FSMIE;
+ writel(val, ispi->sregs + SSFSTS_CTL);
+
+ ispi->swseq = true;
+ }
+
+ intel_spi_dump_regs(ispi);
+
+ return 0;
+}
+
+static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(ispi->opcodes); i++)
+ if (ispi->opcodes[i] == opcode)
+ return i;
+ return -EINVAL;
+}
+
+static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
+ int len)
+{
+ u32 val, status;
+ int ret;
+
+ val = readl(ispi->base + HSFSTS_CTL);
+ val &= ~(HSFSTS_CTL_FCYCLE_MASK | HSFSTS_CTL_FDBC_MASK);
+
+ switch (opcode) {
+ case SPINOR_OP_RDID:
+ val |= HSFSTS_CTL_FCYCLE_RDID;
+ break;
+ case SPINOR_OP_WRSR:
+ val |= HSFSTS_CTL_FCYCLE_WRSR;
+ break;
+ case SPINOR_OP_RDSR:
+ val |= HSFSTS_CTL_FCYCLE_RDSR;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ val |= (len - 1) << HSFSTS_CTL_FDBC_SHIFT;
+ val |= HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+ val |= HSFSTS_CTL_FGO;
+ writel(val, ispi->base + HSFSTS_CTL);
+
+ ret = intel_spi_wait_hw_busy(ispi);
+ if (ret)
+ return ret;
+
+ status = readl(ispi->base + HSFSTS_CTL);
+ if (status & HSFSTS_CTL_FCERR)
+ return -EIO;
+ else if (status & HSFSTS_CTL_AEL)
+ return -EACCES;
+
+ return 0;
+}
+
+static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
+ int len)
+{
+ u32 val, status;
+ int ret;
+
+ ret = intel_spi_opcode_index(ispi, opcode);
+ if (ret < 0)
+ return ret;
+
+ val = (len << SSFSTS_CTL_DBC_SHIFT) | SSFSTS_CTL_DS;
+ val |= ret << SSFSTS_CTL_COP_SHIFT;
+ val |= SSFSTS_CTL_FCERR | SSFSTS_CTL_FDONE;
+ val |= SSFSTS_CTL_SCGO;
+ writel(val, ispi->sregs + SSFSTS_CTL);
+
+ ret = intel_spi_wait_sw_busy(ispi);
+ if (ret)
+ return ret;
+
+ status = readl(ispi->base + SSFSTS_CTL);
+ if (status & SSFSTS_CTL_FCERR)
+ return -EIO;
+ else if (status & SSFSTS_CTL_AEL)
+ return -EACCES;
+
+ return 0;
+}
+
+static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+ struct intel_spi *ispi = nor->priv;
+ int ret;
+
+ /* Address of the first chip */
+ writel(0, ispi->base + FADDR);
+
+ if (ispi->swseq)
+ ret = intel_spi_sw_cycle(ispi, opcode, buf, len);
+ else
+ ret = intel_spi_hw_cycle(ispi, opcode, buf, len);
+
+ if (ret)
+ return ret;
+
+ return intel_spi_read_block(ispi, buf, len);
+}
+
+static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+ struct intel_spi *ispi = nor->priv;
+ int ret;
+
+ /*
+ * This is handled with atomic operation and preop code in Intel
+ * controller so skip it here now.
+ */
+ if (opcode == SPINOR_OP_WREN)
+ return 0;
+
+ writel(0, ispi->base + FADDR);
+
+ /* Write the value beforehand */
+ ret = intel_spi_write_block(ispi, buf, len);
+ if (ret)
+ return ret;
+
+ if (ispi->swseq)
+ return intel_spi_sw_cycle(ispi, opcode, buf, len);
+ return intel_spi_hw_cycle(ispi, opcode, buf, len);
+}
+
+static ssize_t intel_spi_read(struct spi_nor *nor, loff_t from, size_t len,
+ u_char *read_buf)
+{
+ struct intel_spi *ispi = nor->priv;
+ size_t block_size, retlen = 0;
+ u32 val, status;
+ ssize_t ret;
+
+ switch (nor->read_opcode) {
+ case SPINOR_OP_READ:
+ case SPINOR_OP_READ_FAST:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ while (len > 0) {
+ block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
+
+ writel(from, ispi->base + FADDR);
+
+ val = readl(ispi->base + HSFSTS_CTL);
+ val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK);
+ val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+ val |= (block_size - 1) << HSFSTS_CTL_FDBC_SHIFT;
+ val |= HSFSTS_CTL_FCYCLE_READ;
+ val |= HSFSTS_CTL_FGO;
+ writel(val, ispi->base + HSFSTS_CTL);
+
+ ret = intel_spi_wait_hw_busy(ispi);
+ if (ret)
+ return ret;
+
+ status = readl(ispi->base + HSFSTS_CTL);
+ if (status & HSFSTS_CTL_FCERR)
+ ret = -EIO;
+ else if (status & HSFSTS_CTL_AEL)
+ ret = -EACCES;
+
+ if (ret < 0) {
+ dev_err(ispi->dev, "read error: %llx: %#x\n", from,
+ status);
+ return ret;
+ }
+
+ ret = intel_spi_read_block(ispi, read_buf, block_size);
+ if (ret)
+ return ret;
+
+ len -= block_size;
+ from += block_size;
+ retlen += block_size;
+ read_buf += block_size;
+ }
+
+ return retlen;
+}
+
+static ssize_t intel_spi_write(struct spi_nor *nor, loff_t to, size_t len,
+ const u_char *write_buf)
+{
+ struct intel_spi *ispi = nor->priv;
+ size_t block_size, retlen = 0;
+ u32 val, status;
+ ssize_t ret;
+
+ while (len > 0) {
+ block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
+
+ writel(to, ispi->base + FADDR);
+
+ val = readl(ispi->base + HSFSTS_CTL);
+ val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK);
+ val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+ val |= (block_size - 1) << HSFSTS_CTL_FDBC_SHIFT;
+ val |= HSFSTS_CTL_FCYCLE_WRITE;
+
+ /* Write enable */
+ if (ispi->preopcodes[1] == SPINOR_OP_WREN)
+ val |= SSFSTS_CTL_SPOP;
+ val |= SSFSTS_CTL_ACS;
+ writel(val, ispi->base + HSFSTS_CTL);
+
+ ret = intel_spi_write_block(ispi, write_buf, block_size);
+ if (ret) {
+ dev_err(ispi->dev, "failed to write block\n");
+ return ret;
+ }
+
+ /* Start the write now */
+ val = readl(ispi->base + HSFSTS_CTL);
+ writel(val | HSFSTS_CTL_FGO, ispi->base + HSFSTS_CTL);
+
+ ret = intel_spi_wait_hw_busy(ispi);
+ if (ret) {
+ dev_err(ispi->dev, "timeout\n");
+ return ret;
+ }
+
+ status = readl(ispi->base + HSFSTS_CTL);
+ if (status & HSFSTS_CTL_FCERR)
+ ret = -EIO;
+ else if (status & HSFSTS_CTL_AEL)
+ ret = -EACCES;
+
+ if (ret < 0) {
+ dev_err(ispi->dev, "write error: %llx: %#x\n", to,
+ status);
+ return ret;
+ }
+
+ len -= block_size;
+ to += block_size;
+ retlen += block_size;
+ write_buf += block_size;
+ }
+
+ return retlen;
+}
+
+static int intel_spi_erase(struct spi_nor *nor, loff_t offs)
+{
+ size_t erase_size, len = nor->mtd.erasesize;
+ struct intel_spi *ispi = nor->priv;
+ u32 val, status, cmd;
+ int ret;
+
+ /* If the hardware can do 64k erase use that when possible */
+ if (len >= SZ_64K && ispi->erase_64k) {
+ cmd = HSFSTS_CTL_FCYCLE_ERASE_64K;
+ erase_size = SZ_64K;
+ } else {
+ cmd = HSFSTS_CTL_FCYCLE_ERASE;
+ erase_size = SZ_4K;
+ }
+
+ while (len > 0) {
+ writel(offs, ispi->base + FADDR);
+
+ val = readl(ispi->base + HSFSTS_CTL);
+ val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK);
+ val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+ val |= cmd;
+ val |= HSFSTS_CTL_FGO;
+ writel(val, ispi->base + HSFSTS_CTL);
+
+ ret = intel_spi_wait_hw_busy(ispi);
+ if (ret)
+ return ret;
+
+ status = readl(ispi->base + HSFSTS_CTL);
+ if (status & HSFSTS_CTL_FCERR)
+ return -EIO;
+ else if (status & HSFSTS_CTL_AEL)
+ return -EACCES;
+
+ offs += erase_size;
+ len -= erase_size;
+ }
+
+ return 0;
+}
+
+static bool intel_spi_is_protected(const struct intel_spi *ispi,
+ unsigned int base, unsigned int limit)
+{
+ int i;
+
+ for (i = 0; i < PR_NUM; i++) {
+ u32 pr_base, pr_limit, pr_value;
+
+ pr_value = readl(ispi->pregs + PR(i));
+ if (!(pr_value & (PR_WPE | PR_RPE)))
+ continue;
+
+ pr_limit = (pr_value & PR_LIMIT_MASK) >> PR_LIMIT_SHIFT;
+ pr_base = pr_value & PR_BASE_MASK;
+
+ if (pr_base >= base && pr_limit <= limit)
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * There will be a single partition holding all enabled flash regions. We
+ * call this "BIOS".
+ */
+static void intel_spi_fill_partition(struct intel_spi *ispi,
+ struct mtd_partition *part)
+{
+ u64 end;
+ int i;
+
+ memset(part, 0, sizeof(*part));
+
+ /* Start from the mandatory descriptor region */
+ part->size = 4096;
+ part->name = "BIOS";
+
+ /*
+ * Now try to find where this partition ends based on the flash
+ * region registers.
+ */
+ for (i = 1; i < ispi->nregions; i++) {
+ u32 region, base, limit;
+
+ region = readl(ispi->base + FREG(i));
+ base = region & FREG_BASE_MASK;
+ limit = (region & FREG_LIMIT_MASK) >> FREG_LIMIT_SHIFT;
+
+ if (base >= limit || limit == 0)
+ continue;
+
+ /*
+ * If any of the regions have protection bits set, make the
+ * whole partition read-only to be on the safe side.
+ */
+ if (intel_spi_is_protected(ispi, base, limit))
+ ispi->writeable = 0;
+
+ end = (limit << 12) + 4096;
+ if (end > part->size)
+ part->size = end;
+ }
+}
+
+struct intel_spi *intel_spi_probe(struct device *dev,
+ struct resource *mem, const struct intel_spi_boardinfo *info)
+{
+ struct mtd_partition part;
+ struct intel_spi *ispi;
+ int ret;
+
+ if (!info || !mem)
+ return ERR_PTR(-EINVAL);
+
+ ispi = devm_kzalloc(dev, sizeof(*ispi), GFP_KERNEL);
+ if (!ispi)
+ return ERR_PTR(-ENOMEM);
+
+ ispi->base = devm_ioremap_resource(dev, mem);
+ if (IS_ERR(ispi->base))
+ return ispi->base;
+
+ ispi->dev = dev;
+ ispi->info = info;
+ ispi->writeable = info->writeable;
+
+ ret = intel_spi_init(ispi);
+ if (ret)
+ return ERR_PTR(ret);
+
+ ispi->nor.dev = ispi->dev;
+ ispi->nor.priv = ispi;
+ ispi->nor.read_reg = intel_spi_read_reg;
+ ispi->nor.write_reg = intel_spi_write_reg;
+ ispi->nor.read = intel_spi_read;
+ ispi->nor.write = intel_spi_write;
+ ispi->nor.erase = intel_spi_erase;
+
+ ret = spi_nor_scan(&ispi->nor, NULL, SPI_NOR_NORMAL);
+ if (ret) {
+ dev_info(dev, "failed to locate the chip\n");
+ return ERR_PTR(ret);
+ }
+
+ intel_spi_fill_partition(ispi, &part);
+
+ /* Prevent writes if not explicitly enabled */
+ if (!ispi->writeable || !writeable)
+ ispi->nor.mtd.flags &= ~MTD_WRITEABLE;
+
+ ret = mtd_device_parse_register(&ispi->nor.mtd, NULL, NULL, &part, 1);
+ if (ret)
+ return ERR_PTR(ret);
+
+ return ispi;
+}
+EXPORT_SYMBOL_GPL(intel_spi_probe);
+
+int intel_spi_remove(struct intel_spi *ispi)
+{
+ return mtd_device_unregister(&ispi->nor.mtd);
+}
+EXPORT_SYMBOL_GPL(intel_spi_remove);
+
+MODULE_DESCRIPTION("Intel PCH/PCU SPI flash core driver");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/spi-nor/intel-spi.h b/drivers/mtd/spi-nor/intel-spi.h
new file mode 100644
index 0000000..5ab7dc2
--- /dev/null
+++ b/drivers/mtd/spi-nor/intel-spi.h
@@ -0,0 +1,24 @@
+/*
+ * Intel PCH/PCU SPI flash driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef INTEL_SPI_H
+#define INTEL_SPI_H
+
+#include <linux/platform_data/intel-spi.h>
+
+struct intel_spi;
+struct resource;
+
+struct intel_spi *intel_spi_probe(struct device *dev,
+ struct resource *mem, const struct intel_spi_boardinfo *info);
+int intel_spi_remove(struct intel_spi *ispi);
+
+#endif /* INTEL_SPI_H */
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index da7cd69..1ae872b 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -75,6 +75,16 @@
* bit. Must be used with
* SPI_NOR_HAS_LOCK.
*/
+#define SPI_S3AN BIT(10) /*
+ * Xilinx Spartan 3AN In-System Flash
+ * (MFR cannot be used for probing
+ * because it has the same value as
+ * ATMEL flashes)
+ */
+#define SPI_NOR_4B_OPCODES BIT(11) /*
+ * Use dedicated 4byte address op codes
+ * to support memory size above 128Mib.
+ */
};
#define JEDEC_MFR(info) ((info)->id[0])
@@ -122,7 +132,7 @@
/*
* Read configuration register, returning its value in the
* location. Return the configuration register value.
- * Returns negative if error occured.
+ * Returns negative if error occurred.
*/
static int read_cr(struct spi_nor *nor)
{
@@ -188,6 +198,78 @@
return mtd->priv;
}
+
+static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size)
+{
+ size_t i;
+
+ for (i = 0; i < size; i++)
+ if (table[i][0] == opcode)
+ return table[i][1];
+
+ /* No conversion found, keep input op code. */
+ return opcode;
+}
+
+static inline u8 spi_nor_convert_3to4_read(u8 opcode)
+{
+ static const u8 spi_nor_3to4_read[][2] = {
+ { SPINOR_OP_READ, SPINOR_OP_READ_4B },
+ { SPINOR_OP_READ_FAST, SPINOR_OP_READ_FAST_4B },
+ { SPINOR_OP_READ_1_1_2, SPINOR_OP_READ_1_1_2_4B },
+ { SPINOR_OP_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B },
+ { SPINOR_OP_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B },
+ { SPINOR_OP_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B },
+ };
+
+ return spi_nor_convert_opcode(opcode, spi_nor_3to4_read,
+ ARRAY_SIZE(spi_nor_3to4_read));
+}
+
+static inline u8 spi_nor_convert_3to4_program(u8 opcode)
+{
+ static const u8 spi_nor_3to4_program[][2] = {
+ { SPINOR_OP_PP, SPINOR_OP_PP_4B },
+ { SPINOR_OP_PP_1_1_4, SPINOR_OP_PP_1_1_4_4B },
+ { SPINOR_OP_PP_1_4_4, SPINOR_OP_PP_1_4_4_4B },
+ };
+
+ return spi_nor_convert_opcode(opcode, spi_nor_3to4_program,
+ ARRAY_SIZE(spi_nor_3to4_program));
+}
+
+static inline u8 spi_nor_convert_3to4_erase(u8 opcode)
+{
+ static const u8 spi_nor_3to4_erase[][2] = {
+ { SPINOR_OP_BE_4K, SPINOR_OP_BE_4K_4B },
+ { SPINOR_OP_BE_32K, SPINOR_OP_BE_32K_4B },
+ { SPINOR_OP_SE, SPINOR_OP_SE_4B },
+ };
+
+ return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase,
+ ARRAY_SIZE(spi_nor_3to4_erase));
+}
+
+static void spi_nor_set_4byte_opcodes(struct spi_nor *nor,
+ const struct flash_info *info)
+{
+ /* Do some manufacturer fixups first */
+ switch (JEDEC_MFR(info)) {
+ case SNOR_MFR_SPANSION:
+ /* No small sector erase for 4-byte command set */
+ nor->erase_opcode = SPINOR_OP_SE;
+ nor->mtd.erasesize = info->sector_size;
+ break;
+
+ default:
+ break;
+ }
+
+ nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode);
+ nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode);
+ nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode);
+}
+
/* Enable/disable 4-byte addressing mode. */
static inline int set_4byte(struct spi_nor *nor, const struct flash_info *info,
int enable)
@@ -217,6 +299,21 @@
return nor->write_reg(nor, SPINOR_OP_BRWR, nor->cmd_buf, 1);
}
}
+
+static int s3an_sr_ready(struct spi_nor *nor)
+{
+ int ret;
+ u8 val;
+
+ ret = nor->read_reg(nor, SPINOR_OP_XRDSR, &val, 1);
+ if (ret < 0) {
+ dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+ return ret;
+ }
+
+ return !!(val & XSR_RDY);
+}
+
static inline int spi_nor_sr_ready(struct spi_nor *nor)
{
int sr = read_sr(nor);
@@ -238,7 +335,11 @@
static int spi_nor_ready(struct spi_nor *nor)
{
int sr, fsr;
- sr = spi_nor_sr_ready(nor);
+
+ if (nor->flags & SNOR_F_READY_XSR_RDY)
+ sr = s3an_sr_ready(nor);
+ else
+ sr = spi_nor_sr_ready(nor);
if (sr < 0)
return sr;
fsr = nor->flags & SNOR_F_USE_FSR ? spi_nor_fsr_ready(nor) : 1;
@@ -320,6 +421,27 @@
}
/*
+ * This code converts an address to the Default Address Mode, that has non
+ * power of two page sizes. We must support this mode because it is the default
+ * mode supported by Xilinx tools, it can access the whole flash area and
+ * changing over to the Power-of-two mode is irreversible and corrupts the
+ * original data.
+ * Addr can safely be unsigned int, the biggest S3AN device is smaller than
+ * 4 MiB.
+ */
+static loff_t spi_nor_s3an_addr_convert(struct spi_nor *nor, unsigned int addr)
+{
+ unsigned int offset;
+ unsigned int page;
+
+ offset = addr % nor->page_size;
+ page = addr / nor->page_size;
+ page <<= (nor->page_size > 512) ? 10 : 9;
+
+ return page | offset;
+}
+
+/*
* Initiate the erasure of a single sector
*/
static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
@@ -327,6 +449,9 @@
u8 buf[SPI_NOR_MAX_ADDR_WIDTH];
int i;
+ if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT)
+ addr = spi_nor_s3an_addr_convert(nor, addr);
+
if (nor->erase)
return nor->erase(nor, addr);
@@ -368,7 +493,7 @@
return ret;
/* whole-chip erase? */
- if (len == mtd->size) {
+ if (len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) {
unsigned long timeout;
write_enable(nor);
@@ -782,6 +907,19 @@
.addr_width = (_addr_width), \
.flags = (_flags),
+#define S3AN_INFO(_jedec_id, _n_sectors, _page_size) \
+ .id = { \
+ ((_jedec_id) >> 16) & 0xff, \
+ ((_jedec_id) >> 8) & 0xff, \
+ (_jedec_id) & 0xff \
+ }, \
+ .id_len = 3, \
+ .sector_size = (8*_page_size), \
+ .n_sectors = (_n_sectors), \
+ .page_size = _page_size, \
+ .addr_width = 3, \
+ .flags = SPI_NOR_NO_FR | SPI_S3AN,
+
/* NOTE: double check command sets and memory organization when you add
* more nor chips. This current list focusses on newer chips, which
* have been converging on command sets which including JEDEC ID.
@@ -821,7 +959,7 @@
{ "en25s64", INFO(0x1c3817, 0, 64 * 1024, 128, SECT_4K) },
/* ESMT */
- { "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K) },
+ { "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K | SPI_NOR_HAS_LOCK) },
/* Everspin */
{ "mr25h256", CAT25_INFO( 32 * 1024, 1, 256, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
@@ -833,6 +971,11 @@
/* GigaDevice */
{
+ "gd25q16", INFO(0xc84015, 0, 64 * 1024, 32,
+ SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+ SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+ },
+ {
"gd25q32", INFO(0xc84016, 0, 64 * 1024, 64,
SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
@@ -1014,6 +1157,13 @@
{ "cat25c09", CAT25_INFO( 128, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
{ "cat25c17", CAT25_INFO( 256, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
{ "cat25128", CAT25_INFO(2048, 8, 64, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+
+ /* Xilinx S3AN Internal Flash */
+ { "3S50AN", S3AN_INFO(0x1f2200, 64, 264) },
+ { "3S200AN", S3AN_INFO(0x1f2400, 256, 264) },
+ { "3S400AN", S3AN_INFO(0x1f2400, 256, 264) },
+ { "3S700AN", S3AN_INFO(0x1f2500, 512, 264) },
+ { "3S1400AN", S3AN_INFO(0x1f2600, 512, 528) },
{ },
};
@@ -1054,7 +1204,12 @@
return ret;
while (len) {
- ret = nor->read(nor, from, len, buf);
+ loff_t addr = from;
+
+ if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT)
+ addr = spi_nor_s3an_addr_convert(nor, addr);
+
+ ret = nor->read(nor, addr, len, buf);
if (ret == 0) {
/* We shouldn't see 0-length reads */
ret = -EIO;
@@ -1175,17 +1330,32 @@
for (i = 0; i < len; ) {
ssize_t written;
+ loff_t addr = to + i;
- page_offset = (to + i) & (nor->page_size - 1);
- WARN_ONCE(page_offset,
- "Writing at offset %zu into a NOR page. Writing partial pages may decrease reliability and increase wear of NOR flash.",
- page_offset);
+ /*
+ * If page_size is a power of two, the offset can be quickly
+ * calculated with an AND operation. On the other cases we
+ * need to do a modulus operation (more expensive).
+ * Power of two numbers have only one bit set and we can use
+ * the instruction hweight32 to detect if we need to do a
+ * modulus (do_div()) or not.
+ */
+ if (hweight32(nor->page_size) == 1) {
+ page_offset = addr & (nor->page_size - 1);
+ } else {
+ uint64_t aux = addr;
+
+ page_offset = do_div(aux, nor->page_size);
+ }
/* the size of data remaining on the first page */
page_remain = min_t(size_t,
nor->page_size - page_offset, len - i);
+ if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT)
+ addr = spi_nor_s3an_addr_convert(nor, addr);
+
write_enable(nor);
- ret = nor->write(nor, to + i, page_remain, buf + i);
+ ret = nor->write(nor, addr, page_remain, buf + i);
if (ret < 0)
goto write_err;
written = ret;
@@ -1216,6 +1386,9 @@
val = read_sr(nor);
if (val < 0)
return val;
+ if (val & SR_QUAD_EN_MX)
+ return 0;
+
write_enable(nor);
write_sr(nor, val | SR_QUAD_EN_MX);
@@ -1236,7 +1409,7 @@
* Write status Register and configuration register with 2 bytes
* The first byte will be written to the status register, while the
* second byte will be written to the configuration register.
- * Return negative if error occured.
+ * Return negative if error occurred.
*/
static int write_sr_cr(struct spi_nor *nor, u16 val)
{
@@ -1312,6 +1485,47 @@
return 0;
}
+static int s3an_nor_scan(const struct flash_info *info, struct spi_nor *nor)
+{
+ int ret;
+ u8 val;
+
+ ret = nor->read_reg(nor, SPINOR_OP_XRDSR, &val, 1);
+ if (ret < 0) {
+ dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+ return ret;
+ }
+
+ nor->erase_opcode = SPINOR_OP_XSE;
+ nor->program_opcode = SPINOR_OP_XPP;
+ nor->read_opcode = SPINOR_OP_READ;
+ nor->flags |= SNOR_F_NO_OP_CHIP_ERASE;
+
+ /*
+ * This flashes have a page size of 264 or 528 bytes (known as
+ * Default addressing mode). It can be changed to a more standard
+ * Power of two mode where the page size is 256/512. This comes
+ * with a price: there is 3% less of space, the data is corrupted
+ * and the page size cannot be changed back to default addressing
+ * mode.
+ *
+ * The current addressing mode can be read from the XRDSR register
+ * and should not be changed, because is a destructive operation.
+ */
+ if (val & XSR_PAGESIZE) {
+ /* Flash in Power of 2 mode */
+ nor->page_size = (nor->page_size == 264) ? 256 : 512;
+ nor->mtd.writebufsize = nor->page_size;
+ nor->mtd.size = 8 * nor->page_size * info->n_sectors;
+ nor->mtd.erasesize = 8 * nor->page_size;
+ } else {
+ /* Flash in Default addressing mode */
+ nor->flags |= SNOR_F_S3AN_ADDR_DEFAULT;
+ }
+
+ return 0;
+}
+
int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
{
const struct flash_info *info = NULL;
@@ -1360,6 +1574,14 @@
mutex_init(&nor->lock);
/*
+ * Make sure the XSR_RDY flag is set before calling
+ * spi_nor_wait_till_ready(). Xilinx S3AN share MFR
+ * with Atmel spi-nor
+ */
+ if (info->flags & SPI_S3AN)
+ nor->flags |= SNOR_F_READY_XSR_RDY;
+
+ /*
* Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up
* with the software protection bits set
*/
@@ -1483,27 +1705,10 @@
else if (mtd->size > 0x1000000) {
/* enable 4-byte addressing if the device exceeds 16MiB */
nor->addr_width = 4;
- if (JEDEC_MFR(info) == SNOR_MFR_SPANSION) {
- /* Dedicated 4-byte command set */
- switch (nor->flash_read) {
- case SPI_NOR_QUAD:
- nor->read_opcode = SPINOR_OP_READ4_1_1_4;
- break;
- case SPI_NOR_DUAL:
- nor->read_opcode = SPINOR_OP_READ4_1_1_2;
- break;
- case SPI_NOR_FAST:
- nor->read_opcode = SPINOR_OP_READ4_FAST;
- break;
- case SPI_NOR_NORMAL:
- nor->read_opcode = SPINOR_OP_READ4;
- break;
- }
- nor->program_opcode = SPINOR_OP_PP_4B;
- /* No small sector erase for 4-byte command set */
- nor->erase_opcode = SPINOR_OP_SE_4B;
- mtd->erasesize = info->sector_size;
- } else
+ if (JEDEC_MFR(info) == SNOR_MFR_SPANSION ||
+ info->flags & SPI_NOR_4B_OPCODES)
+ spi_nor_set_4byte_opcodes(nor, info);
+ else
set_4byte(nor, info, 1);
} else {
nor->addr_width = 3;
@@ -1517,6 +1722,12 @@
nor->read_dummy = spi_nor_read_dummy_cycles(nor);
+ if (info->flags & SPI_S3AN) {
+ ret = s3an_nor_scan(info, nor);
+ if (ret)
+ return ret;
+ }
+
dev_info(dev, "%s (%lld Kbytes)\n", info->name,
(long long)mtd->size >> 10);
diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c
index 7be393c..cf7c189 100644
--- a/drivers/net/can/c_can/c_can_pci.c
+++ b/drivers/net/can/c_can/c_can_pci.c
@@ -161,6 +161,7 @@
dev->irq = pdev->irq;
priv->base = addr;
+ priv->device = &pdev->dev;
if (!c_can_pci_data->freq) {
dev_err(&pdev->dev, "no clock frequency defined\n");
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 680d1ff..6749b18 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -948,7 +948,12 @@
netif_napi_add(ndev, &priv->napi, ti_hecc_rx_poll,
HECC_DEF_NAPI_WEIGHT);
- clk_enable(priv->clk);
+ err = clk_prepare_enable(priv->clk);
+ if (err) {
+ dev_err(&pdev->dev, "clk_prepare_enable() failed\n");
+ goto probe_exit_clk;
+ }
+
err = register_candev(ndev);
if (err) {
dev_err(&pdev->dev, "register_candev() failed\n");
@@ -981,7 +986,7 @@
struct ti_hecc_priv *priv = netdev_priv(ndev);
unregister_candev(ndev);
- clk_disable(priv->clk);
+ clk_disable_unprepare(priv->clk);
clk_put(priv->clk);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
iounmap(priv->base);
@@ -1006,7 +1011,7 @@
hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_PDR);
priv->can.state = CAN_STATE_SLEEPING;
- clk_disable(priv->clk);
+ clk_disable_unprepare(priv->clk);
return 0;
}
@@ -1015,8 +1020,11 @@
{
struct net_device *dev = platform_get_drvdata(pdev);
struct ti_hecc_priv *priv = netdev_priv(dev);
+ int err;
- clk_enable(priv->clk);
+ err = clk_prepare_enable(priv->clk);
+ if (err)
+ return err;
hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_PDR);
priv->can.state = CAN_STATE_ERROR_ACTIVE;
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index c12d261..3872ab9 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -1152,6 +1152,12 @@
if (skb == NULL)
break;
np->rx_info[i].mapping = pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE);
+ if (pci_dma_mapping_error(np->pci_dev,
+ np->rx_info[i].mapping)) {
+ dev_kfree_skb(skb);
+ np->rx_info[i].skb = NULL;
+ break;
+ }
/* Grrr, we cannot offset to correctly align the IP header. */
np->rx_ring[i].rxaddr = cpu_to_dma(np->rx_info[i].mapping | RxDescValid);
}
@@ -1182,8 +1188,9 @@
{
struct netdev_private *np = netdev_priv(dev);
unsigned int entry;
+ unsigned int prev_tx;
u32 status;
- int i;
+ int i, j;
/*
* be cautious here, wrapping the queue has weird semantics
@@ -1201,6 +1208,7 @@
}
#endif /* ZEROCOPY && HAS_BROKEN_FIRMWARE */
+ prev_tx = np->cur_tx;
entry = np->cur_tx % TX_RING_SIZE;
for (i = 0; i < skb_num_frags(skb); i++) {
int wrap_ring = 0;
@@ -1234,6 +1242,11 @@
skb_frag_size(this_frag),
PCI_DMA_TODEVICE);
}
+ if (pci_dma_mapping_error(np->pci_dev,
+ np->tx_info[entry].mapping)) {
+ dev->stats.tx_dropped++;
+ goto err_out;
+ }
np->tx_ring[entry].addr = cpu_to_dma(np->tx_info[entry].mapping);
np->tx_ring[entry].status = cpu_to_le32(status);
@@ -1268,8 +1281,30 @@
netif_stop_queue(dev);
return NETDEV_TX_OK;
-}
+err_out:
+ entry = prev_tx % TX_RING_SIZE;
+ np->tx_info[entry].skb = NULL;
+ if (i > 0) {
+ pci_unmap_single(np->pci_dev,
+ np->tx_info[entry].mapping,
+ skb_first_frag_len(skb),
+ PCI_DMA_TODEVICE);
+ np->tx_info[entry].mapping = 0;
+ entry = (entry + np->tx_info[entry].used_slots) % TX_RING_SIZE;
+ for (j = 1; j < i; j++) {
+ pci_unmap_single(np->pci_dev,
+ np->tx_info[entry].mapping,
+ skb_frag_size(
+ &skb_shinfo(skb)->frags[j-1]),
+ PCI_DMA_TODEVICE);
+ entry++;
+ }
+ }
+ dev_kfree_skb_any(skb);
+ np->cur_tx = prev_tx;
+ return NETDEV_TX_OK;
+}
/* The interrupt handler does all of the Rx thread work and cleans up
after the Tx thread. */
@@ -1569,6 +1604,12 @@
break; /* Better luck next round. */
np->rx_info[entry].mapping =
pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE);
+ if (pci_dma_mapping_error(np->pci_dev,
+ np->rx_info[entry].mapping)) {
+ dev_kfree_skb(skb);
+ np->rx_info[entry].skb = NULL;
+ break;
+ }
np->rx_ring[entry].rxaddr =
cpu_to_dma(np->rx_info[entry].mapping | RxDescValid);
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 5b7ba25..8a280e7 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -891,6 +891,8 @@
#define PCS_V1_WINDOW_SELECT 0x03fc
#define PCS_V2_WINDOW_DEF 0x9060
#define PCS_V2_WINDOW_SELECT 0x9064
+#define PCS_V2_RV_WINDOW_DEF 0x1060
+#define PCS_V2_RV_WINDOW_SELECT 0x1064
/* PCS register entry bit positions and sizes */
#define PCS_V2_WINDOW_DEF_OFFSET_INDEX 6
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index aaf0350..a7d16db 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1151,7 +1151,7 @@
offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
spin_lock_irqsave(&pdata->xpcs_lock, flags);
- XPCS32_IOWRITE(pdata, PCS_V2_WINDOW_SELECT, index);
+ XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
mmd_data = XPCS16_IOREAD(pdata, offset);
spin_unlock_irqrestore(&pdata->xpcs_lock, flags);
@@ -1183,7 +1183,7 @@
offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
spin_lock_irqsave(&pdata->xpcs_lock, flags);
- XPCS32_IOWRITE(pdata, PCS_V2_WINDOW_SELECT, index);
+ XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
XPCS16_IOWRITE(pdata, offset, mmd_data);
spin_unlock_irqrestore(&pdata->xpcs_lock, flags);
}
@@ -3407,8 +3407,10 @@
/* Flush Tx queues */
ret = xgbe_flush_tx_queues(pdata);
- if (ret)
+ if (ret) {
+ netdev_err(pdata->netdev, "error flushing TX queues\n");
return ret;
+ }
/*
* Initialize DMA related features
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 9943629..1c87cc2 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1070,7 +1070,9 @@
DBGPR("-->xgbe_start\n");
- hw_if->init(pdata);
+ ret = hw_if->init(pdata);
+ if (ret)
+ return ret;
xgbe_napi_enable(pdata, 1);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index e76b7f6..c2730f1 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -265,6 +265,7 @@
struct xgbe_prv_data *pdata;
struct device *dev = &pdev->dev;
void __iomem * const *iomap_table;
+ struct pci_dev *rdev;
unsigned int ma_lo, ma_hi;
unsigned int reg;
int bar_mask;
@@ -326,8 +327,20 @@
if (netif_msg_probe(pdata))
dev_dbg(dev, "xpcs_regs = %p\n", pdata->xpcs_regs);
+ /* Set the PCS indirect addressing definition registers */
+ rdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0));
+ if (rdev &&
+ (rdev->vendor == PCI_VENDOR_ID_AMD) && (rdev->device == 0x15d0)) {
+ pdata->xpcs_window_def_reg = PCS_V2_RV_WINDOW_DEF;
+ pdata->xpcs_window_sel_reg = PCS_V2_RV_WINDOW_SELECT;
+ } else {
+ pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF;
+ pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT;
+ }
+ pci_dev_put(rdev);
+
/* Configure the PCS indirect addressing support */
- reg = XPCS32_IOREAD(pdata, PCS_V2_WINDOW_DEF);
+ reg = XPCS32_IOREAD(pdata, pdata->xpcs_window_def_reg);
pdata->xpcs_window = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, OFFSET);
pdata->xpcs_window <<= 6;
pdata->xpcs_window_size = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, SIZE);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index f52a9bd..0010881 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -955,6 +955,8 @@
/* XPCS indirect addressing lock */
spinlock_t xpcs_lock;
+ unsigned int xpcs_window_def_reg;
+ unsigned int xpcs_window_sel_reg;
unsigned int xpcs_window;
unsigned int xpcs_window_size;
unsigned int xpcs_window_mask;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index c8f5255..7dcc907 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -685,8 +685,6 @@
return -ENOMEM;
}
- alx_reinit_rings(alx);
-
return 0;
}
@@ -703,7 +701,7 @@
if (alx->qnapi[0] && alx->qnapi[0]->rxq)
kfree(alx->qnapi[0]->rxq->bufs);
- if (!alx->descmem.virt)
+ if (alx->descmem.virt)
dma_free_coherent(&alx->hw.pdev->dev,
alx->descmem.size,
alx->descmem.virt,
@@ -984,6 +982,7 @@
alx_free_rings(alx);
alx_free_napis(alx);
alx_disable_advanced_intr(alx);
+ alx_init_intr(alx, false);
err = alx_alloc_napis(alx);
if (err)
@@ -1241,6 +1240,12 @@
if (err)
goto out_free_rings;
+ /* must be called after alx_request_irq because the chip stops working
+ * if we copy the dma addresses in alx_init_ring_ptrs twice when
+ * requesting msi-x interrupts failed
+ */
+ alx_reinit_rings(alx);
+
netif_set_real_num_tx_queues(alx->dev, alx->num_txq);
netif_set_real_num_rx_queues(alx->dev, alx->num_rxq);
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 3b14d51..c483618 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -913,6 +913,8 @@
priv->old_link = 0;
priv->old_duplex = -1;
priv->old_pause = -1;
+ } else {
+ phydev = NULL;
}
/* mask all interrupts and request them */
@@ -1083,7 +1085,7 @@
enet_dmac_writel(priv, priv->dma_chan_int_mask,
ENETDMAC_IRMASK, priv->tx_chan);
- if (priv->has_phy)
+ if (phydev)
phy_start(phydev);
else
bcm_enet_adjust_link(dev);
@@ -1126,7 +1128,7 @@
free_irq(dev->irq, dev);
out_phy_disconnect:
- if (priv->has_phy)
+ if (phydev)
phy_disconnect(phydev);
return ret;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 7e8cf21..744ed6d 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -710,11 +710,8 @@
unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
unsigned int pkts_compl = 0, bytes_compl = 0;
struct bcm_sysport_cb *cb;
- struct netdev_queue *txq;
u32 hw_ind;
- txq = netdev_get_tx_queue(ndev, ring->index);
-
/* Compute how many descriptors have been processed since last call */
hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
@@ -745,9 +742,6 @@
ring->c_index = c_index;
- if (netif_tx_queue_stopped(txq) && pkts_compl)
- netif_tx_wake_queue(txq);
-
netif_dbg(priv, tx_done, ndev,
"ring=%d c_index=%d pkts_compl=%d, bytes_compl=%d\n",
ring->index, ring->c_index, pkts_compl, bytes_compl);
@@ -759,16 +753,33 @@
static unsigned int bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
struct bcm_sysport_tx_ring *ring)
{
+ struct netdev_queue *txq;
unsigned int released;
unsigned long flags;
+ txq = netdev_get_tx_queue(priv->netdev, ring->index);
+
spin_lock_irqsave(&ring->lock, flags);
released = __bcm_sysport_tx_reclaim(priv, ring);
+ if (released)
+ netif_tx_wake_queue(txq);
+
spin_unlock_irqrestore(&ring->lock, flags);
return released;
}
+/* Locked version of the per-ring TX reclaim, but does not wake the queue */
+static void bcm_sysport_tx_clean(struct bcm_sysport_priv *priv,
+ struct bcm_sysport_tx_ring *ring)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ring->lock, flags);
+ __bcm_sysport_tx_reclaim(priv, ring);
+ spin_unlock_irqrestore(&ring->lock, flags);
+}
+
static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget)
{
struct bcm_sysport_tx_ring *ring =
@@ -1252,7 +1263,7 @@
napi_disable(&ring->napi);
netif_napi_del(&ring->napi);
- bcm_sysport_tx_reclaim(priv, ring);
+ bcm_sysport_tx_clean(priv, ring);
kfree(ring->cbs);
ring->cbs = NULL;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9608cb4..4fcc6a8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1099,7 +1099,7 @@
{
#ifdef CONFIG_INET
struct tcphdr *th;
- int len, nw_off, tcp_opt_len;
+ int len, nw_off, tcp_opt_len = 0;
if (tcp_ts)
tcp_opt_len = 12;
@@ -5314,17 +5314,12 @@
if ((link_info->support_auto_speeds | diff) !=
link_info->support_auto_speeds) {
/* An advertised speed is no longer supported, so we need to
- * update the advertisement settings. See bnxt_reset() for
- * comments about the rtnl_lock() sequence below.
+ * update the advertisement settings. Caller holds RTNL
+ * so we can modify link settings.
*/
- clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
- rtnl_lock();
link_info->advertising = link_info->support_auto_speeds;
- if (test_bit(BNXT_STATE_OPEN, &bp->state) &&
- (link_info->autoneg & BNXT_AUTONEG_SPEED))
+ if (link_info->autoneg & BNXT_AUTONEG_SPEED)
bnxt_hwrm_set_link_setting(bp, true, false);
- set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
- rtnl_unlock();
}
return 0;
}
@@ -6200,29 +6195,37 @@
mod_timer(&bp->timer, jiffies + bp->current_interval);
}
-/* Only called from bnxt_sp_task() */
-static void bnxt_reset(struct bnxt *bp, bool silent)
+static void bnxt_rtnl_lock_sp(struct bnxt *bp)
{
- /* bnxt_reset_task() calls bnxt_close_nic() which waits
- * for BNXT_STATE_IN_SP_TASK to clear.
- * If there is a parallel dev_close(), bnxt_close() may be holding
+ /* We are called from bnxt_sp_task which has BNXT_STATE_IN_SP_TASK
+ * set. If the device is being closed, bnxt_close() may be holding
* rtnl() and waiting for BNXT_STATE_IN_SP_TASK to clear. So we
* must clear BNXT_STATE_IN_SP_TASK before holding rtnl().
*/
clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
rtnl_lock();
- if (test_bit(BNXT_STATE_OPEN, &bp->state))
- bnxt_reset_task(bp, silent);
+}
+
+static void bnxt_rtnl_unlock_sp(struct bnxt *bp)
+{
set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
rtnl_unlock();
}
+/* Only called from bnxt_sp_task() */
+static void bnxt_reset(struct bnxt *bp, bool silent)
+{
+ bnxt_rtnl_lock_sp(bp);
+ if (test_bit(BNXT_STATE_OPEN, &bp->state))
+ bnxt_reset_task(bp, silent);
+ bnxt_rtnl_unlock_sp(bp);
+}
+
static void bnxt_cfg_ntp_filters(struct bnxt *);
static void bnxt_sp_task(struct work_struct *work)
{
struct bnxt *bp = container_of(work, struct bnxt, sp_task);
- int rc;
set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
smp_mb__after_atomic();
@@ -6236,16 +6239,6 @@
if (test_and_clear_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event))
bnxt_cfg_ntp_filters(bp);
- if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
- if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT,
- &bp->sp_event))
- bnxt_hwrm_phy_qcaps(bp);
-
- rc = bnxt_update_link(bp, true);
- if (rc)
- netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
- rc);
- }
if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event))
bnxt_hwrm_exec_fwd_req(bp);
if (test_and_clear_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event)) {
@@ -6266,18 +6259,39 @@
bnxt_hwrm_tunnel_dst_port_free(
bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE);
}
+ if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
+ bnxt_hwrm_port_qstats(bp);
+
+ /* These functions below will clear BNXT_STATE_IN_SP_TASK. They
+ * must be the last functions to be called before exiting.
+ */
+ if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
+ int rc = 0;
+
+ if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT,
+ &bp->sp_event))
+ bnxt_hwrm_phy_qcaps(bp);
+
+ bnxt_rtnl_lock_sp(bp);
+ if (test_bit(BNXT_STATE_OPEN, &bp->state))
+ rc = bnxt_update_link(bp, true);
+ bnxt_rtnl_unlock_sp(bp);
+ if (rc)
+ netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
+ rc);
+ }
+ if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) {
+ bnxt_rtnl_lock_sp(bp);
+ if (test_bit(BNXT_STATE_OPEN, &bp->state))
+ bnxt_get_port_module_status(bp);
+ bnxt_rtnl_unlock_sp(bp);
+ }
if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event))
bnxt_reset(bp, false);
if (test_and_clear_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event))
bnxt_reset(bp, true);
- if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event))
- bnxt_get_port_module_status(bp);
-
- if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
- bnxt_hwrm_port_qstats(bp);
-
smp_mb__before_atomic();
clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
}
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index c0fb80a..baba2db 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -43,13 +43,13 @@
#define DEFAULT_RX_RING_SIZE 512 /* must be power of 2 */
#define MIN_RX_RING_SIZE 64
#define MAX_RX_RING_SIZE 8192
-#define RX_RING_BYTES(bp) (sizeof(struct macb_dma_desc) \
+#define RX_RING_BYTES(bp) (macb_dma_desc_get_size(bp) \
* (bp)->rx_ring_size)
#define DEFAULT_TX_RING_SIZE 512 /* must be power of 2 */
#define MIN_TX_RING_SIZE 64
#define MAX_TX_RING_SIZE 4096
-#define TX_RING_BYTES(bp) (sizeof(struct macb_dma_desc) \
+#define TX_RING_BYTES(bp) (macb_dma_desc_get_size(bp) \
* (bp)->tx_ring_size)
/* level of occupied TX descriptors under which we wake up TX process */
@@ -78,6 +78,37 @@
*/
#define MACB_HALT_TIMEOUT 1230
+/* DMA buffer descriptor might be different size
+ * depends on hardware configuration.
+ */
+static unsigned int macb_dma_desc_get_size(struct macb *bp)
+{
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+ return sizeof(struct macb_dma_desc) + sizeof(struct macb_dma_desc_64);
+#endif
+ return sizeof(struct macb_dma_desc);
+}
+
+static unsigned int macb_adj_dma_desc_idx(struct macb *bp, unsigned int idx)
+{
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+ /* Dma buffer descriptor is 4 words length (instead of 2 words)
+ * for 64b GEM.
+ */
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+ idx <<= 1;
+#endif
+ return idx;
+}
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+static struct macb_dma_desc_64 *macb_64b_desc(struct macb *bp, struct macb_dma_desc *desc)
+{
+ return (struct macb_dma_desc_64 *)((void *)desc + sizeof(struct macb_dma_desc));
+}
+#endif
+
/* Ring buffer accessors */
static unsigned int macb_tx_ring_wrap(struct macb *bp, unsigned int index)
{
@@ -87,7 +118,9 @@
static struct macb_dma_desc *macb_tx_desc(struct macb_queue *queue,
unsigned int index)
{
- return &queue->tx_ring[macb_tx_ring_wrap(queue->bp, index)];
+ index = macb_tx_ring_wrap(queue->bp, index);
+ index = macb_adj_dma_desc_idx(queue->bp, index);
+ return &queue->tx_ring[index];
}
static struct macb_tx_skb *macb_tx_skb(struct macb_queue *queue,
@@ -101,7 +134,7 @@
dma_addr_t offset;
offset = macb_tx_ring_wrap(queue->bp, index) *
- sizeof(struct macb_dma_desc);
+ macb_dma_desc_get_size(queue->bp);
return queue->tx_ring_dma + offset;
}
@@ -113,7 +146,9 @@
static struct macb_dma_desc *macb_rx_desc(struct macb *bp, unsigned int index)
{
- return &bp->rx_ring[macb_rx_ring_wrap(bp, index)];
+ index = macb_rx_ring_wrap(bp, index);
+ index = macb_adj_dma_desc_idx(bp, index);
+ return &bp->rx_ring[index];
}
static void *macb_rx_buffer(struct macb *bp, unsigned int index)
@@ -560,12 +595,32 @@
}
}
-static inline void macb_set_addr(struct macb_dma_desc *desc, dma_addr_t addr)
+static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_t addr)
{
- desc->addr = (u32)addr;
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- desc->addrh = (u32)(addr >> 32);
+ struct macb_dma_desc_64 *desc_64;
+
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B) {
+ desc_64 = macb_64b_desc(bp, desc);
+ desc_64->addrh = upper_32_bits(addr);
+ }
#endif
+ desc->addr = lower_32_bits(addr);
+}
+
+static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc)
+{
+ dma_addr_t addr = 0;
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+ struct macb_dma_desc_64 *desc_64;
+
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B) {
+ desc_64 = macb_64b_desc(bp, desc);
+ addr = ((u64)(desc_64->addrh) << 32);
+ }
+#endif
+ addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr));
+ return addr;
}
static void macb_tx_error_task(struct work_struct *work)
@@ -649,16 +704,17 @@
/* Set end of TX queue */
desc = macb_tx_desc(queue, 0);
- macb_set_addr(desc, 0);
+ macb_set_addr(bp, desc, 0);
desc->ctrl = MACB_BIT(TX_USED);
/* Make descriptor updates visible to hardware */
wmb();
/* Reinitialize the TX desc queue */
- queue_writel(queue, TBQP, (u32)(queue->tx_ring_dma));
+ queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- queue_writel(queue, TBQPH, (u32)(queue->tx_ring_dma >> 32));
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+ queue_writel(queue, TBQPH, upper_32_bits(queue->tx_ring_dma));
#endif
/* Make TX ring reflect state of hardware */
queue->tx_head = 0;
@@ -750,6 +806,7 @@
unsigned int entry;
struct sk_buff *skb;
dma_addr_t paddr;
+ struct macb_dma_desc *desc;
while (CIRC_SPACE(bp->rx_prepared_head, bp->rx_tail,
bp->rx_ring_size) > 0) {
@@ -759,6 +816,7 @@
rmb();
bp->rx_prepared_head++;
+ desc = macb_rx_desc(bp, entry);
if (!bp->rx_skbuff[entry]) {
/* allocate sk_buff for this free entry in ring */
@@ -782,14 +840,14 @@
if (entry == bp->rx_ring_size - 1)
paddr |= MACB_BIT(RX_WRAP);
- macb_set_addr(&(bp->rx_ring[entry]), paddr);
- bp->rx_ring[entry].ctrl = 0;
+ macb_set_addr(bp, desc, paddr);
+ desc->ctrl = 0;
/* properly align Ethernet header */
skb_reserve(skb, NET_IP_ALIGN);
} else {
- bp->rx_ring[entry].addr &= ~MACB_BIT(RX_USED);
- bp->rx_ring[entry].ctrl = 0;
+ desc->addr &= ~MACB_BIT(RX_USED);
+ desc->ctrl = 0;
}
}
@@ -835,16 +893,13 @@
bool rxused;
entry = macb_rx_ring_wrap(bp, bp->rx_tail);
- desc = &bp->rx_ring[entry];
+ desc = macb_rx_desc(bp, entry);
/* Make hw descriptor updates visible to CPU */
rmb();
rxused = (desc->addr & MACB_BIT(RX_USED)) ? true : false;
- addr = MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- addr |= ((u64)(desc->addrh) << 32);
-#endif
+ addr = macb_get_addr(bp, desc);
ctrl = desc->ctrl;
if (!rxused)
@@ -987,15 +1042,17 @@
static inline void macb_init_rx_ring(struct macb *bp)
{
dma_addr_t addr;
+ struct macb_dma_desc *desc = NULL;
int i;
addr = bp->rx_buffers_dma;
for (i = 0; i < bp->rx_ring_size; i++) {
- bp->rx_ring[i].addr = addr;
- bp->rx_ring[i].ctrl = 0;
+ desc = macb_rx_desc(bp, i);
+ macb_set_addr(bp, desc, addr);
+ desc->ctrl = 0;
addr += bp->rx_buffer_size;
}
- bp->rx_ring[bp->rx_ring_size - 1].addr |= MACB_BIT(RX_WRAP);
+ desc->addr |= MACB_BIT(RX_WRAP);
bp->rx_tail = 0;
}
@@ -1008,15 +1065,14 @@
for (tail = bp->rx_tail; budget > 0; tail++) {
struct macb_dma_desc *desc = macb_rx_desc(bp, tail);
- u32 addr, ctrl;
+ u32 ctrl;
/* Make hw descriptor updates visible to CPU */
rmb();
- addr = desc->addr;
ctrl = desc->ctrl;
- if (!(addr & MACB_BIT(RX_USED)))
+ if (!(desc->addr & MACB_BIT(RX_USED)))
break;
if (ctrl & MACB_BIT(RX_SOF)) {
@@ -1336,7 +1392,7 @@
i = tx_head;
entry = macb_tx_ring_wrap(bp, i);
ctrl = MACB_BIT(TX_USED);
- desc = &queue->tx_ring[entry];
+ desc = macb_tx_desc(queue, entry);
desc->ctrl = ctrl;
if (lso_ctrl) {
@@ -1358,7 +1414,7 @@
i--;
entry = macb_tx_ring_wrap(bp, i);
tx_skb = &queue->tx_skb[entry];
- desc = &queue->tx_ring[entry];
+ desc = macb_tx_desc(queue, entry);
ctrl = (u32)tx_skb->size;
if (eof) {
@@ -1379,7 +1435,7 @@
ctrl |= MACB_BF(MSS_MFS, mss_mfs);
/* Set TX buffer descriptor */
- macb_set_addr(desc, tx_skb->mapping);
+ macb_set_addr(bp, desc, tx_skb->mapping);
/* desc->addr must be visible to hardware before clearing
* 'TX_USED' bit in desc->ctrl.
*/
@@ -1586,11 +1642,9 @@
if (!skb)
continue;
- desc = &bp->rx_ring[i];
- addr = MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- addr |= ((u64)(desc->addrh) << 32);
-#endif
+ desc = macb_rx_desc(bp, i);
+ addr = macb_get_addr(bp, desc);
+
dma_unmap_single(&bp->pdev->dev, addr, bp->rx_buffer_size,
DMA_FROM_DEVICE);
dev_kfree_skb_any(skb);
@@ -1711,15 +1765,17 @@
static void gem_init_rings(struct macb *bp)
{
struct macb_queue *queue;
+ struct macb_dma_desc *desc = NULL;
unsigned int q;
int i;
for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
for (i = 0; i < bp->tx_ring_size; i++) {
- queue->tx_ring[i].addr = 0;
- queue->tx_ring[i].ctrl = MACB_BIT(TX_USED);
+ desc = macb_tx_desc(queue, i);
+ macb_set_addr(bp, desc, 0);
+ desc->ctrl = MACB_BIT(TX_USED);
}
- queue->tx_ring[bp->tx_ring_size - 1].ctrl |= MACB_BIT(TX_WRAP);
+ desc->ctrl |= MACB_BIT(TX_WRAP);
queue->tx_head = 0;
queue->tx_tail = 0;
}
@@ -1733,16 +1789,18 @@
static void macb_init_rings(struct macb *bp)
{
int i;
+ struct macb_dma_desc *desc = NULL;
macb_init_rx_ring(bp);
for (i = 0; i < bp->tx_ring_size; i++) {
- bp->queues[0].tx_ring[i].addr = 0;
- bp->queues[0].tx_ring[i].ctrl = MACB_BIT(TX_USED);
+ desc = macb_tx_desc(&bp->queues[0], i);
+ macb_set_addr(bp, desc, 0);
+ desc->ctrl = MACB_BIT(TX_USED);
}
bp->queues[0].tx_head = 0;
bp->queues[0].tx_tail = 0;
- bp->queues[0].tx_ring[bp->tx_ring_size - 1].ctrl |= MACB_BIT(TX_WRAP);
+ desc->ctrl |= MACB_BIT(TX_WRAP);
}
static void macb_reset_hw(struct macb *bp)
@@ -1863,7 +1921,8 @@
dmacfg &= ~GEM_BIT(TXCOEN);
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- dmacfg |= GEM_BIT(ADDR64);
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+ dmacfg |= GEM_BIT(ADDR64);
#endif
netdev_dbg(bp->dev, "Cadence configure DMA with 0x%08x\n",
dmacfg);
@@ -1910,14 +1969,16 @@
macb_configure_dma(bp);
/* Initialize TX and RX buffers */
- macb_writel(bp, RBQP, (u32)(bp->rx_ring_dma));
+ macb_writel(bp, RBQP, lower_32_bits(bp->rx_ring_dma));
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- macb_writel(bp, RBQPH, (u32)(bp->rx_ring_dma >> 32));
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+ macb_writel(bp, RBQPH, upper_32_bits(bp->rx_ring_dma));
#endif
for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
- queue_writel(queue, TBQP, (u32)(queue->tx_ring_dma));
+ queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- queue_writel(queue, TBQPH, (u32)(queue->tx_ring_dma >> 32));
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+ queue_writel(queue, TBQPH, upper_32_bits(queue->tx_ring_dma));
#endif
/* Enable interrupts */
@@ -2627,7 +2688,8 @@
queue->IMR = GEM_IMR(hw_q - 1);
queue->TBQP = GEM_TBQP(hw_q - 1);
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- queue->TBQPH = GEM_TBQPH(hw_q -1);
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+ queue->TBQPH = GEM_TBQPH(hw_q - 1);
#endif
} else {
/* queue0 uses legacy registers */
@@ -2637,7 +2699,8 @@
queue->IMR = MACB_IMR;
queue->TBQP = MACB_TBQP;
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- queue->TBQPH = MACB_TBQPH;
+ if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+ queue->TBQPH = MACB_TBQPH;
#endif
}
@@ -2730,13 +2793,14 @@
static int at91ether_start(struct net_device *dev)
{
struct macb *lp = netdev_priv(dev);
+ struct macb_dma_desc *desc;
dma_addr_t addr;
u32 ctl;
int i;
lp->rx_ring = dma_alloc_coherent(&lp->pdev->dev,
(AT91ETHER_MAX_RX_DESCR *
- sizeof(struct macb_dma_desc)),
+ macb_dma_desc_get_size(lp)),
&lp->rx_ring_dma, GFP_KERNEL);
if (!lp->rx_ring)
return -ENOMEM;
@@ -2748,7 +2812,7 @@
if (!lp->rx_buffers) {
dma_free_coherent(&lp->pdev->dev,
AT91ETHER_MAX_RX_DESCR *
- sizeof(struct macb_dma_desc),
+ macb_dma_desc_get_size(lp),
lp->rx_ring, lp->rx_ring_dma);
lp->rx_ring = NULL;
return -ENOMEM;
@@ -2756,13 +2820,14 @@
addr = lp->rx_buffers_dma;
for (i = 0; i < AT91ETHER_MAX_RX_DESCR; i++) {
- lp->rx_ring[i].addr = addr;
- lp->rx_ring[i].ctrl = 0;
+ desc = macb_rx_desc(lp, i);
+ macb_set_addr(lp, desc, addr);
+ desc->ctrl = 0;
addr += AT91ETHER_MAX_RBUFF_SZ;
}
/* Set the Wrap bit on the last descriptor */
- lp->rx_ring[AT91ETHER_MAX_RX_DESCR - 1].addr |= MACB_BIT(RX_WRAP);
+ desc->addr |= MACB_BIT(RX_WRAP);
/* Reset buffer index */
lp->rx_tail = 0;
@@ -2834,7 +2899,7 @@
dma_free_coherent(&lp->pdev->dev,
AT91ETHER_MAX_RX_DESCR *
- sizeof(struct macb_dma_desc),
+ macb_dma_desc_get_size(lp),
lp->rx_ring, lp->rx_ring_dma);
lp->rx_ring = NULL;
@@ -2885,13 +2950,15 @@
static void at91ether_rx(struct net_device *dev)
{
struct macb *lp = netdev_priv(dev);
+ struct macb_dma_desc *desc;
unsigned char *p_recv;
struct sk_buff *skb;
unsigned int pktlen;
- while (lp->rx_ring[lp->rx_tail].addr & MACB_BIT(RX_USED)) {
+ desc = macb_rx_desc(lp, lp->rx_tail);
+ while (desc->addr & MACB_BIT(RX_USED)) {
p_recv = lp->rx_buffers + lp->rx_tail * AT91ETHER_MAX_RBUFF_SZ;
- pktlen = MACB_BF(RX_FRMLEN, lp->rx_ring[lp->rx_tail].ctrl);
+ pktlen = MACB_BF(RX_FRMLEN, desc->ctrl);
skb = netdev_alloc_skb(dev, pktlen + 2);
if (skb) {
skb_reserve(skb, 2);
@@ -2905,17 +2972,19 @@
lp->stats.rx_dropped++;
}
- if (lp->rx_ring[lp->rx_tail].ctrl & MACB_BIT(RX_MHASH_MATCH))
+ if (desc->ctrl & MACB_BIT(RX_MHASH_MATCH))
lp->stats.multicast++;
/* reset ownership bit */
- lp->rx_ring[lp->rx_tail].addr &= ~MACB_BIT(RX_USED);
+ desc->addr &= ~MACB_BIT(RX_USED);
/* wrap after last buffer */
if (lp->rx_tail == AT91ETHER_MAX_RX_DESCR - 1)
lp->rx_tail = 0;
else
lp->rx_tail++;
+
+ desc = macb_rx_desc(lp, lp->rx_tail);
}
}
@@ -3211,8 +3280,11 @@
device_init_wakeup(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET);
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- if (GEM_BFEXT(DBWDEF, gem_readl(bp, DCFG1)) > GEM_DBW32)
+ if (GEM_BFEXT(DAW64, gem_readl(bp, DCFG6))) {
dma_set_mask(&pdev->dev, DMA_BIT_MASK(44));
+ bp->hw_dma_cap = HW_DMA_CAP_64B;
+ } else
+ bp->hw_dma_cap = HW_DMA_CAP_32B;
#endif
spin_lock_init(&bp->lock);
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index d67adad..fc8550a 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -385,6 +385,8 @@
/* Bitfields in DCFG6. */
#define GEM_PBUF_LSO_OFFSET 27
#define GEM_PBUF_LSO_SIZE 1
+#define GEM_DAW64_OFFSET 23
+#define GEM_DAW64_SIZE 1
/* Constants for CLK */
#define MACB_CLK_DIV8 0
@@ -487,12 +489,20 @@
struct macb_dma_desc {
u32 addr;
u32 ctrl;
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
- u32 addrh;
- u32 resvd;
-#endif
};
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+enum macb_hw_dma_cap {
+ HW_DMA_CAP_32B,
+ HW_DMA_CAP_64B,
+};
+
+struct macb_dma_desc_64 {
+ u32 addrh;
+ u32 resvd;
+};
+#endif
+
/* DMA descriptor bitfields */
#define MACB_RX_USED_OFFSET 0
#define MACB_RX_USED_SIZE 1
@@ -874,6 +884,10 @@
unsigned int jumbo_max_len;
u32 wol;
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+ enum macb_hw_dma_cap hw_dma_cap;
+#endif
};
static inline bool macb_is_gem(struct macb *bp)
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 9211c75..1e46952 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -31,6 +31,7 @@
u8 lmac_type;
u8 lane_to_sds;
bool use_training;
+ bool autoneg;
bool link_up;
int lmacid; /* ID within BGX */
int lmacid_bd; /* ID on board */
@@ -47,8 +48,9 @@
struct bgx {
u8 bgx_id;
struct lmac lmac[MAX_LMAC_PER_BGX];
- int lmac_count;
+ u8 lmac_count;
u8 max_lmac;
+ u8 acpi_lmac_idx;
void __iomem *reg_base;
struct pci_dev *pdev;
bool is_dlm;
@@ -460,7 +462,17 @@
/* power down, reset autoneg, autoneg enable */
cfg = bgx_reg_read(bgx, lmacid, BGX_GMP_PCS_MRX_CTL);
cfg &= ~PCS_MRX_CTL_PWR_DN;
- cfg |= (PCS_MRX_CTL_RST_AN | PCS_MRX_CTL_AN_EN);
+ cfg |= PCS_MRX_CTL_RST_AN;
+ if (lmac->phydev) {
+ cfg |= PCS_MRX_CTL_AN_EN;
+ } else {
+ /* In scenarios where PHY driver is not present or it's a
+ * non-standard PHY, FW sets AN_EN to inform Linux driver
+ * to do auto-neg and link polling or not.
+ */
+ if (cfg & PCS_MRX_CTL_AN_EN)
+ lmac->autoneg = true;
+ }
bgx_reg_write(bgx, lmacid, BGX_GMP_PCS_MRX_CTL, cfg);
if (lmac->lmac_type == BGX_MODE_QSGMII) {
@@ -471,7 +483,7 @@
return 0;
}
- if (lmac->lmac_type == BGX_MODE_SGMII) {
+ if ((lmac->lmac_type == BGX_MODE_SGMII) && lmac->phydev) {
if (bgx_poll_reg(bgx, lmacid, BGX_GMP_PCS_MRX_STATUS,
PCS_MRX_STATUS_AN_CPT, false)) {
dev_err(&bgx->pdev->dev, "BGX AN_CPT not completed\n");
@@ -677,12 +689,71 @@
return -1;
}
+static void bgx_poll_for_sgmii_link(struct lmac *lmac)
+{
+ u64 pcs_link, an_result;
+ u8 speed;
+
+ pcs_link = bgx_reg_read(lmac->bgx, lmac->lmacid,
+ BGX_GMP_PCS_MRX_STATUS);
+
+ /*Link state bit is sticky, read it again*/
+ if (!(pcs_link & PCS_MRX_STATUS_LINK))
+ pcs_link = bgx_reg_read(lmac->bgx, lmac->lmacid,
+ BGX_GMP_PCS_MRX_STATUS);
+
+ if (bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_GMP_PCS_MRX_STATUS,
+ PCS_MRX_STATUS_AN_CPT, false)) {
+ lmac->link_up = false;
+ lmac->last_speed = SPEED_UNKNOWN;
+ lmac->last_duplex = DUPLEX_UNKNOWN;
+ goto next_poll;
+ }
+
+ lmac->link_up = ((pcs_link & PCS_MRX_STATUS_LINK) != 0) ? true : false;
+ an_result = bgx_reg_read(lmac->bgx, lmac->lmacid,
+ BGX_GMP_PCS_ANX_AN_RESULTS);
+
+ speed = (an_result >> 3) & 0x3;
+ lmac->last_duplex = (an_result >> 1) & 0x1;
+ switch (speed) {
+ case 0:
+ lmac->last_speed = 10;
+ break;
+ case 1:
+ lmac->last_speed = 100;
+ break;
+ case 2:
+ lmac->last_speed = 1000;
+ break;
+ default:
+ lmac->link_up = false;
+ lmac->last_speed = SPEED_UNKNOWN;
+ lmac->last_duplex = DUPLEX_UNKNOWN;
+ break;
+ }
+
+next_poll:
+
+ if (lmac->last_link != lmac->link_up) {
+ if (lmac->link_up)
+ bgx_sgmii_change_link_state(lmac);
+ lmac->last_link = lmac->link_up;
+ }
+
+ queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 3);
+}
+
static void bgx_poll_for_link(struct work_struct *work)
{
struct lmac *lmac;
u64 spu_link, smu_link;
lmac = container_of(work, struct lmac, dwork.work);
+ if (lmac->is_sgmii) {
+ bgx_poll_for_sgmii_link(lmac);
+ return;
+ }
/* Receive link is latching low. Force it high and verify it */
bgx_reg_modify(lmac->bgx, lmac->lmacid,
@@ -774,9 +845,21 @@
(lmac->lmac_type != BGX_MODE_XLAUI) &&
(lmac->lmac_type != BGX_MODE_40G_KR) &&
(lmac->lmac_type != BGX_MODE_10G_KR)) {
- if (!lmac->phydev)
- return -ENODEV;
-
+ if (!lmac->phydev) {
+ if (lmac->autoneg) {
+ bgx_reg_write(bgx, lmacid,
+ BGX_GMP_PCS_LINKX_TIMER,
+ PCS_LINKX_TIMER_COUNT);
+ goto poll;
+ } else {
+ /* Default to below link speed and duplex */
+ lmac->link_up = true;
+ lmac->last_speed = 1000;
+ lmac->last_duplex = 1;
+ bgx_sgmii_change_link_state(lmac);
+ return 0;
+ }
+ }
lmac->phydev->dev_flags = 0;
if (phy_connect_direct(&lmac->netdev, lmac->phydev,
@@ -785,15 +868,17 @@
return -ENODEV;
phy_start_aneg(lmac->phydev);
- } else {
- lmac->check_link = alloc_workqueue("check_link", WQ_UNBOUND |
- WQ_MEM_RECLAIM, 1);
- if (!lmac->check_link)
- return -ENOMEM;
- INIT_DELAYED_WORK(&lmac->dwork, bgx_poll_for_link);
- queue_delayed_work(lmac->check_link, &lmac->dwork, 0);
+ return 0;
}
+poll:
+ lmac->check_link = alloc_workqueue("check_link", WQ_UNBOUND |
+ WQ_MEM_RECLAIM, 1);
+ if (!lmac->check_link)
+ return -ENOMEM;
+ INIT_DELAYED_WORK(&lmac->dwork, bgx_poll_for_link);
+ queue_delayed_work(lmac->check_link, &lmac->dwork, 0);
+
return 0;
}
@@ -1143,13 +1228,13 @@
if (acpi_bus_get_device(handle, &adev))
goto out;
- acpi_get_mac_address(dev, adev, bgx->lmac[bgx->lmac_count].mac);
+ acpi_get_mac_address(dev, adev, bgx->lmac[bgx->acpi_lmac_idx].mac);
- SET_NETDEV_DEV(&bgx->lmac[bgx->lmac_count].netdev, dev);
+ SET_NETDEV_DEV(&bgx->lmac[bgx->acpi_lmac_idx].netdev, dev);
- bgx->lmac[bgx->lmac_count].lmacid = bgx->lmac_count;
+ bgx->lmac[bgx->acpi_lmac_idx].lmacid = bgx->acpi_lmac_idx;
+ bgx->acpi_lmac_idx++; /* move to next LMAC */
out:
- bgx->lmac_count++;
return AE_OK;
}
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index c18ebfe..a60f189 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -153,10 +153,15 @@
#define PCS_MRX_CTL_LOOPBACK1 BIT_ULL(14)
#define PCS_MRX_CTL_RESET BIT_ULL(15)
#define BGX_GMP_PCS_MRX_STATUS 0x30008
+#define PCS_MRX_STATUS_LINK BIT_ULL(2)
#define PCS_MRX_STATUS_AN_CPT BIT_ULL(5)
+#define BGX_GMP_PCS_ANX_ADV 0x30010
#define BGX_GMP_PCS_ANX_AN_RESULTS 0x30020
+#define BGX_GMP_PCS_LINKX_TIMER 0x30040
+#define PCS_LINKX_TIMER_COUNT 0x1E84
#define BGX_GMP_PCS_SGM_AN_ADV 0x30068
#define BGX_GMP_PCS_MISCX_CTL 0x30078
+#define PCS_MISC_CTL_MODE BIT_ULL(8)
#define PCS_MISC_CTL_DISP_EN BIT_ULL(13)
#define PCS_MISC_CTL_GMX_ENO BIT_ULL(11)
#define PCS_MISC_CTL_SAMP_PT_MASK 0x7Full
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_xcv.c b/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
index 67befed..578c7f8 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
@@ -116,8 +116,7 @@
int speed = 2;
if (!xcv) {
- dev_err(&xcv->pdev->dev,
- "XCV init not done, probe may have failed\n");
+ pr_err("XCV init not done, probe may have failed\n");
return;
}
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 0e74529..30e8550 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1118,7 +1118,7 @@
err:
mutex_unlock(&adapter->mcc_lock);
- if (status == MCC_STATUS_UNAUTHORIZED_REQUEST)
+ if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
status = -EPERM;
return status;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index ec010ce..cd49a54 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -318,6 +318,13 @@
if (ether_addr_equal(addr->sa_data, adapter->dev_mac))
return 0;
+ /* BE3 VFs without FILTMGMT privilege are not allowed to set its MAC
+ * address
+ */
+ if (BEx_chip(adapter) && be_virtfn(adapter) &&
+ !check_privilege(adapter, BE_PRIV_FILTMGMT))
+ return -EPERM;
+
/* if device is not running, copy MAC to netdev->dev_addr */
if (!netif_running(netdev))
goto done;
@@ -355,8 +362,10 @@
status = -EPERM;
goto err;
}
-done:
+
+ /* Remember currently programmed MAC */
ether_addr_copy(adapter->dev_mac, addr->sa_data);
+done:
ether_addr_copy(netdev->dev_addr, addr->sa_data);
dev_info(dev, "MAC address changed to %pM\n", addr->sa_data);
return 0;
@@ -3609,7 +3618,13 @@
static void be_disable_if_filters(struct be_adapter *adapter)
{
- be_dev_mac_del(adapter, adapter->pmac_id[0]);
+ /* Don't delete MAC on BE3 VFs without FILTMGMT privilege */
+ if (!BEx_chip(adapter) || !be_virtfn(adapter) ||
+ check_privilege(adapter, BE_PRIV_FILTMGMT)) {
+ be_dev_mac_del(adapter, adapter->pmac_id[0]);
+ eth_zero_addr(adapter->dev_mac);
+ }
+
be_clear_uc_list(adapter);
be_clear_mc_list(adapter);
@@ -3762,11 +3777,27 @@
if (status)
return status;
- /* For BE3 VFs, the PF programs the initial MAC address */
- if (!(BEx_chip(adapter) && be_virtfn(adapter))) {
+ /* Normally this condition usually true as the ->dev_mac is zeroed.
+ * But on BE3 VFs the initial MAC is pre-programmed by PF and
+ * subsequent be_dev_mac_add() can fail (after fresh boot)
+ */
+ if (!ether_addr_equal(adapter->dev_mac, adapter->netdev->dev_addr)) {
+ int old_pmac_id = -1;
+
+ /* Remember old programmed MAC if any - can happen on BE3 VF */
+ if (!is_zero_ether_addr(adapter->dev_mac))
+ old_pmac_id = adapter->pmac_id[0];
+
status = be_dev_mac_add(adapter, adapter->netdev->dev_addr);
if (status)
return status;
+
+ /* Delete the old programmed MAC as we successfully programmed
+ * a new MAC
+ */
+ if (old_pmac_id >= 0 && old_pmac_id != adapter->pmac_id[0])
+ be_dev_mac_del(adapter, old_pmac_id);
+
ether_addr_copy(adapter->dev_mac, adapter->netdev->dev_addr);
}
@@ -4540,6 +4571,10 @@
memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
+
+ /* Initial MAC for BE3 VFs is already programmed by PF */
+ if (BEx_chip(adapter) && be_virtfn(adapter))
+ memcpy(adapter->dev_mac, mac, ETH_ALEN);
}
return 0;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index c9b7ad6..726b569 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -1668,7 +1668,7 @@
free_buffers:
/* compensate sw bpool counter changes */
- for (i--; i > 0; i--) {
+ for (i--; i >= 0; i--) {
dpaa_bp = dpaa_bpid2pool(sgt[i].bpid);
if (dpaa_bp) {
count_ptr = this_cpu_ptr(dpaa_bp->percpu_count);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 38160c2..8be7034 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2910,6 +2910,7 @@
struct netdev_hw_addr *ha;
unsigned int i, bit, data, crc, tmp;
unsigned char hash;
+ unsigned int hash_high = 0, hash_low = 0;
if (ndev->flags & IFF_PROMISC) {
tmp = readl(fep->hwp + FEC_R_CNTRL);
@@ -2932,11 +2933,7 @@
return;
}
- /* Clear filter and add the addresses in hash register
- */
- writel(0, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
- writel(0, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
-
+ /* Add the addresses in hash register */
netdev_for_each_mc_addr(ha, ndev) {
/* calculate crc32 value of mac address */
crc = 0xffffffff;
@@ -2954,16 +2951,14 @@
*/
hash = (crc >> (32 - FEC_HASH_BITS)) & 0x3f;
- if (hash > 31) {
- tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
- tmp |= 1 << (hash - 32);
- writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
- } else {
- tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_LOW);
- tmp |= 1 << hash;
- writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
- }
+ if (hash > 31)
+ hash_high |= 1 << (hash - 32);
+ else
+ hash_low |= 1 << hash;
}
+
+ writel(hash_high, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
+ writel(hash_low, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
}
/* Set a MAC change in hardware. */
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index a6e7afa..957bfc2 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2010,8 +2010,8 @@
if (!rxb->page)
continue;
- dma_unmap_single(rx_queue->dev, rxb->dma,
- PAGE_SIZE, DMA_FROM_DEVICE);
+ dma_unmap_page(rx_queue->dev, rxb->dma,
+ PAGE_SIZE, DMA_FROM_DEVICE);
__free_page(rxb->page);
rxb->page = NULL;
@@ -2948,7 +2948,7 @@
}
/* try reuse page */
- if (unlikely(page_count(page) != 1))
+ if (unlikely(page_count(page) != 1 || page_is_pfmemalloc(page)))
return false;
/* change offset to the other half */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 8722668..8fa18fc 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -1014,9 +1014,7 @@
static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
{
- u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
- writel(value, reg_addr + reg);
+ writel(value, base + reg);
}
#define dsaf_write_dev(a, reg, value) \
@@ -1024,9 +1022,7 @@
static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg)
{
- u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
- return readl(reg_addr + reg);
+ return readl(base + reg);
}
static inline void dsaf_write_syscon(struct regmap *base, u32 reg, u32 value)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 672b646..8aed728 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -305,8 +305,8 @@
struct hns_nic_ring_data *ring_data)
{
struct hns_nic_priv *priv = netdev_priv(ndev);
- struct device *dev = priv->dev;
struct hnae_ring *ring = ring_data->ring;
+ struct device *dev = ring_to_dev(ring);
struct netdev_queue *dev_queue;
struct skb_frag_struct *frag;
int buf_num;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index a831f94..309f5c6 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1601,8 +1601,11 @@
netdev->netdev_ops = &ibmveth_netdev_ops;
netdev->ethtool_ops = &netdev_ethtool_ops;
SET_NETDEV_DEV(netdev, &dev->dev);
- netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
- NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+ netdev->hw_features = NETIF_F_SG;
+ if (vio_get_attribute(dev, "ibm,illan-options", NULL) != NULL) {
+ netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+ NETIF_F_RXCSUM;
+ }
netdev->features |= netdev->hw_features;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index c125966..a07b8d7 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -189,9 +189,10 @@
}
ltb->map_id = adapter->map_id;
adapter->map_id++;
+
+ init_completion(&adapter->fw_done);
send_request_map(adapter, ltb->addr,
ltb->size, ltb->map_id);
- init_completion(&adapter->fw_done);
wait_for_completion(&adapter->fw_done);
return 0;
}
@@ -505,7 +506,7 @@
adapter->rx_pool = NULL;
rx_pool_arr_alloc_failed:
for (i = 0; i < adapter->req_rx_queues; i++)
- napi_enable(&adapter->napi[i]);
+ napi_disable(&adapter->napi[i]);
alloc_napi_failed:
return -ENOMEM;
}
@@ -1121,10 +1122,10 @@
crq.request_statistics.ioba = cpu_to_be32(adapter->stats_token);
crq.request_statistics.len =
cpu_to_be32(sizeof(struct ibmvnic_statistics));
- ibmvnic_send_crq(adapter, &crq);
/* Wait for data to be written */
init_completion(&adapter->stats_done);
+ ibmvnic_send_crq(adapter, &crq);
wait_for_completion(&adapter->stats_done);
for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++)
@@ -1496,7 +1497,7 @@
adapter->req_rx_queues = adapter->opt_rx_comp_queues;
adapter->req_rx_add_queues = adapter->max_rx_add_queues;
- adapter->req_mtu = adapter->max_mtu;
+ adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
}
total_queues = adapter->req_tx_queues + adapter->req_rx_queues;
@@ -2185,12 +2186,12 @@
if (!found) {
dev_err(dev, "Couldn't find error id %x\n",
- crq->request_error_rsp.error_id);
+ be32_to_cpu(crq->request_error_rsp.error_id));
return;
}
dev_err(dev, "Detailed info for error id %x:",
- crq->request_error_rsp.error_id);
+ be32_to_cpu(crq->request_error_rsp.error_id));
for (i = 0; i < error_buff->len; i++) {
pr_cont("%02x", (int)error_buff->buff[i]);
@@ -2269,8 +2270,8 @@
dev_err(dev, "Firmware reports %serror id %x, cause %d\n",
crq->error_indication.
flags & IBMVNIC_FATAL_ERROR ? "FATAL " : "",
- crq->error_indication.error_id,
- crq->error_indication.error_cause);
+ be32_to_cpu(crq->error_indication.error_id),
+ be16_to_cpu(crq->error_indication.error_cause));
error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC);
if (!error_buff)
@@ -2388,10 +2389,10 @@
case PARTIALSUCCESS:
dev_info(dev, "req=%lld, rsp=%ld in %s queue, retrying.\n",
*req_value,
- (long int)be32_to_cpu(crq->request_capability_rsp.
+ (long int)be64_to_cpu(crq->request_capability_rsp.
number), name);
release_sub_crqs_no_irqs(adapter);
- *req_value = be32_to_cpu(crq->request_capability_rsp.number);
+ *req_value = be64_to_cpu(crq->request_capability_rsp.number);
init_sub_crqs(adapter, 1);
return;
default:
@@ -2626,12 +2627,12 @@
break;
case MIN_MTU:
adapter->min_mtu = be64_to_cpu(crq->query_capability.number);
- netdev->min_mtu = adapter->min_mtu;
+ netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu);
break;
case MAX_MTU:
adapter->max_mtu = be64_to_cpu(crq->query_capability.number);
- netdev->max_mtu = adapter->max_mtu;
+ netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu);
break;
case MAX_MULTICAST_FILTERS:
@@ -2799,9 +2800,9 @@
crq.collect_fw_trace.correlator = adapter->ras_comps[num].correlator;
crq.collect_fw_trace.ioba = cpu_to_be32(trace_tok);
crq.collect_fw_trace.len = adapter->ras_comps[num].trace_buff_size;
- ibmvnic_send_crq(adapter, &crq);
init_completion(&adapter->fw_done);
+ ibmvnic_send_crq(adapter, &crq);
wait_for_completion(&adapter->fw_done);
if (*ppos + len > be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
@@ -3581,9 +3582,9 @@
memset(&crq, 0, sizeof(crq));
crq.request_dump_size.first = IBMVNIC_CRQ_CMD;
crq.request_dump_size.cmd = REQUEST_DUMP_SIZE;
- ibmvnic_send_crq(adapter, &crq);
init_completion(&adapter->fw_done);
+ ibmvnic_send_crq(adapter, &crq);
wait_for_completion(&adapter->fw_done);
seq_write(seq, adapter->dump_data, adapter->dump_data_size);
@@ -3629,8 +3630,8 @@
}
}
- send_version_xchg(adapter);
reinit_completion(&adapter->init_done);
+ send_version_xchg(adapter);
if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
dev_err(dev, "Passive init timeout\n");
goto task_failed;
@@ -3640,9 +3641,9 @@
if (adapter->renegotiate) {
adapter->renegotiate = false;
release_sub_crqs_no_irqs(adapter);
- send_cap_queries(adapter);
reinit_completion(&adapter->init_done);
+ send_cap_queries(adapter);
if (!wait_for_completion_timeout(&adapter->init_done,
timeout)) {
dev_err(dev, "Passive init timeout\n");
@@ -3656,9 +3657,7 @@
goto task_failed;
netdev->real_num_tx_queues = adapter->req_tx_queues;
- netdev->mtu = adapter->req_mtu;
- netdev->min_mtu = adapter->min_mtu;
- netdev->max_mtu = adapter->max_mtu;
+ netdev->mtu = adapter->req_mtu - ETH_HLEN;
if (adapter->failover) {
adapter->failover = false;
@@ -3772,9 +3771,9 @@
adapter->debugfs_dump = ent;
}
}
- ibmvnic_send_crq_init(adapter);
init_completion(&adapter->init_done);
+ ibmvnic_send_crq_init(adapter);
if (!wait_for_completion_timeout(&adapter->init_done, timeout))
return 0;
@@ -3782,9 +3781,9 @@
if (adapter->renegotiate) {
adapter->renegotiate = false;
release_sub_crqs_no_irqs(adapter);
- send_cap_queries(adapter);
reinit_completion(&adapter->init_done);
+ send_cap_queries(adapter);
if (!wait_for_completion_timeout(&adapter->init_done,
timeout))
return 0;
@@ -3798,7 +3797,7 @@
}
netdev->real_num_tx_queues = adapter->req_tx_queues;
- netdev->mtu = adapter->req_mtu;
+ netdev->mtu = adapter->req_mtu - ETH_HLEN;
rc = register_netdev(netdev);
if (rc) {
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 3dd8788..1c29c86 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2517,7 +2517,7 @@
}
const struct of_device_id of_mtk_match[] = {
- { .compatible = "mediatek,mt7623-eth" },
+ { .compatible = "mediatek,mt2701-eth" },
{},
};
MODULE_DEVICE_TABLE(of, of_mtk_match);
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index c7e9399..53daa6c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -158,7 +158,7 @@
return -ETIMEDOUT;
}
-static int mlx4_comm_internal_err(u32 slave_read)
+int mlx4_comm_internal_err(u32 slave_read)
{
return (u32)COMM_CHAN_EVENT_INTERNAL_ERR ==
(slave_read & (u32)COMM_CHAN_EVENT_INTERNAL_ERR) ? 1 : 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index a849da9..6b86353 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -101,13 +101,19 @@
{
struct mlx4_cq *cq;
+ rcu_read_lock();
cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree,
cqn & (dev->caps.num_cqs - 1));
+ rcu_read_unlock();
+
if (!cq) {
mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn);
return;
}
+ /* Acessing the CQ outside of rcu_read_lock is safe, because
+ * the CQ is freed only after interrupt handling is completed.
+ */
++cq->arm_sn;
cq->comp(cq);
@@ -118,23 +124,19 @@
struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table;
struct mlx4_cq *cq;
- spin_lock(&cq_table->lock);
-
+ rcu_read_lock();
cq = radix_tree_lookup(&cq_table->tree, cqn & (dev->caps.num_cqs - 1));
- if (cq)
- atomic_inc(&cq->refcount);
-
- spin_unlock(&cq_table->lock);
+ rcu_read_unlock();
if (!cq) {
- mlx4_warn(dev, "Async event for bogus CQ %08x\n", cqn);
+ mlx4_dbg(dev, "Async event for bogus CQ %08x\n", cqn);
return;
}
+ /* Acessing the CQ outside of rcu_read_lock is safe, because
+ * the CQ is freed only after interrupt handling is completed.
+ */
cq->event(cq, event_type);
-
- if (atomic_dec_and_test(&cq->refcount))
- complete(&cq->free);
}
static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
@@ -301,9 +303,9 @@
if (err)
return err;
- spin_lock_irq(&cq_table->lock);
+ spin_lock(&cq_table->lock);
err = radix_tree_insert(&cq_table->tree, cq->cqn, cq);
- spin_unlock_irq(&cq_table->lock);
+ spin_unlock(&cq_table->lock);
if (err)
goto err_icm;
@@ -349,9 +351,9 @@
return 0;
err_radix:
- spin_lock_irq(&cq_table->lock);
+ spin_lock(&cq_table->lock);
radix_tree_delete(&cq_table->tree, cq->cqn);
- spin_unlock_irq(&cq_table->lock);
+ spin_unlock(&cq_table->lock);
err_icm:
mlx4_cq_free_icm(dev, cq->cqn);
@@ -370,15 +372,15 @@
if (err)
mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn);
+ spin_lock(&cq_table->lock);
+ radix_tree_delete(&cq_table->tree, cq->cqn);
+ spin_unlock(&cq_table->lock);
+
synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq);
if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq !=
priv->eq_table.eq[MLX4_EQ_ASYNC].irq)
synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
- spin_lock_irq(&cq_table->lock);
- radix_tree_delete(&cq_table->tree, cq->cqn);
- spin_unlock_irq(&cq_table->lock);
-
if (atomic_dec_and_test(&cq->refcount))
complete(&cq->free);
wait_for_completion(&cq->free);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index d9c9f86..9aa4226 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1099,7 +1099,7 @@
memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
new_prof.tx_ring_size = tx_size;
new_prof.rx_ring_size = rx_size;
- err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+ err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
if (err)
goto out;
@@ -1732,8 +1732,6 @@
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- memset(channel, 0, sizeof(*channel));
-
channel->max_rx = MAX_RX_RINGS;
channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP;
@@ -1752,10 +1750,7 @@
int xdp_count;
int err = 0;
- if (channel->other_count || channel->combined_count ||
- channel->tx_count > MLX4_EN_MAX_TX_RING_P_UP ||
- channel->rx_count > MAX_RX_RINGS ||
- !channel->tx_count || !channel->rx_count)
+ if (!channel->tx_count || !channel->rx_count)
return -EINVAL;
tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
@@ -1779,7 +1774,7 @@
new_prof.tx_ring_num[TX_XDP] = xdp_count;
new_prof.rx_ring_num = channel->rx_count;
- err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+ err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
if (err)
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 4910d9a..3b4961a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1748,8 +1748,11 @@
/* Process all completions if exist to prevent
* the queues freezing if they are full
*/
- for (i = 0; i < priv->rx_ring_num; i++)
+ for (i = 0; i < priv->rx_ring_num; i++) {
+ local_bh_disable();
napi_schedule(&priv->rx_cq[i]->napi);
+ local_bh_enable();
+ }
netif_tx_start_all_queues(dev);
netif_device_attach(dev);
@@ -2039,6 +2042,8 @@
if (priv->tx_cq[t] && priv->tx_cq[t][i])
mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]);
}
+ kfree(priv->tx_ring[t]);
+ kfree(priv->tx_cq[t]);
}
for (i = 0; i < priv->rx_ring_num; i++) {
@@ -2181,9 +2186,11 @@
int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
struct mlx4_en_priv *tmp,
- struct mlx4_en_port_profile *prof)
+ struct mlx4_en_port_profile *prof,
+ bool carry_xdp_prog)
{
- int t;
+ struct bpf_prog *xdp_prog;
+ int i, t;
mlx4_en_copy_priv(tmp, priv, prof);
@@ -2197,6 +2204,23 @@
}
return -ENOMEM;
}
+
+ /* All rx_rings has the same xdp_prog. Pick the first one. */
+ xdp_prog = rcu_dereference_protected(
+ priv->rx_ring[0]->xdp_prog,
+ lockdep_is_held(&priv->mdev->state_lock));
+
+ if (xdp_prog && carry_xdp_prog) {
+ xdp_prog = bpf_prog_add(xdp_prog, tmp->rx_ring_num);
+ if (IS_ERR(xdp_prog)) {
+ mlx4_en_free_resources(tmp);
+ return PTR_ERR(xdp_prog);
+ }
+ for (i = 0; i < tmp->rx_ring_num; i++)
+ rcu_assign_pointer(tmp->rx_ring[i]->xdp_prog,
+ xdp_prog);
+ }
+
return 0;
}
@@ -2211,7 +2235,6 @@
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
- int t;
en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);
@@ -2245,11 +2268,6 @@
mlx4_en_free_resources(priv);
mutex_unlock(&mdev->state_lock);
- for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
- kfree(priv->tx_ring[t]);
- kfree(priv->tx_cq[t]);
- }
-
free_netdev(dev);
}
@@ -2752,7 +2770,7 @@
en_warn(priv, "Reducing the number of TX rings, to not exceed the max total rings number.\n");
}
- err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+ err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, false);
if (err) {
if (prog)
bpf_prog_sub(prog, priv->rx_ring_num - 1);
@@ -3496,7 +3514,7 @@
memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config));
- err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+ err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
if (err)
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index eac527e..cc003fd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -514,8 +514,11 @@
return;
for (ring = 0; ring < priv->rx_ring_num; ring++) {
- if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+ if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) {
+ local_bh_disable();
napi_reschedule(&priv->rx_cq[ring]->napi);
+ local_bh_enable();
+ }
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index cd3638e..0509996 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -554,8 +554,9 @@
break;
case MLX4_EVENT_TYPE_SRQ_LIMIT:
- mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n",
- __func__);
+ mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n",
+ __func__, be32_to_cpu(eqe->event.srq.srqn),
+ eq->eqn);
case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR:
if (mlx4_is_master(dev)) {
/* forward only to slave owning the SRQ */
@@ -570,15 +571,19 @@
eq->eqn, eq->cons_index, ret);
break;
}
- mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
- __func__, slave,
- be32_to_cpu(eqe->event.srq.srqn),
- eqe->type, eqe->subtype);
+ if (eqe->type ==
+ MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)
+ mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
+ __func__, slave,
+ be32_to_cpu(eqe->event.srq.srqn),
+ eqe->type, eqe->subtype);
if (!ret && slave != dev->caps.function) {
- mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
- __func__, eqe->type,
- eqe->subtype, slave);
+ if (eqe->type ==
+ MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)
+ mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
+ __func__, eqe->type,
+ eqe->subtype, slave);
mlx4_slave_event(dev, slave, eqe);
break;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 0e8b7c4..8258d08 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -222,6 +222,18 @@
return;
mlx4_stop_catas_poll(dev);
+ if (dev->persist->interface_state & MLX4_INTERFACE_STATE_DELETION &&
+ mlx4_is_slave(dev)) {
+ /* In mlx4_remove_one on a VF */
+ u32 slave_read =
+ swab32(readl(&mlx4_priv(dev)->mfunc.comm->slave_read));
+
+ if (mlx4_comm_internal_err(slave_read)) {
+ mlx4_dbg(dev, "%s: comm channel is down, entering error state.\n",
+ __func__);
+ mlx4_enter_error_state(dev->persist);
+ }
+ }
mutex_lock(&intf_mutex);
list_for_each_entry(intf, &intf_list, list)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 88ee7d8..086920b6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1220,6 +1220,7 @@
void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);
void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
+int mlx4_comm_internal_err(u32 slave_read);
int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
enum mlx4_port_type *type);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index ba1c6cd..cec59bc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -679,7 +679,8 @@
int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
struct mlx4_en_priv *tmp,
- struct mlx4_en_port_profile *prof);
+ struct mlx4_en_port_profile *prof,
+ bool carry_xdp_prog);
void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv,
struct mlx4_en_priv *tmp);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 56185a0..1822382 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2980,6 +2980,9 @@
put_res(dev, slave, srqn, RES_SRQ);
qp->srq = srq;
}
+
+ /* Save param3 for dynamic changes from VST back to VGT */
+ qp->param3 = qpc->param3;
put_res(dev, slave, rcqn, RES_CQ);
put_res(dev, slave, mtt_base, RES_MTT);
res_end_move(dev, slave, RES_QP, qpn);
@@ -3772,7 +3775,6 @@
int qpn = vhcr->in_modifier & 0x7fffff;
struct res_qp *qp;
u8 orig_sched_queue;
- __be32 orig_param3 = qpc->param3;
u8 orig_vlan_control = qpc->pri_path.vlan_control;
u8 orig_fvl_rx = qpc->pri_path.fvl_rx;
u8 orig_pri_path_fl = qpc->pri_path.fl;
@@ -3814,7 +3816,6 @@
*/
if (!err) {
qp->sched_queue = orig_sched_queue;
- qp->param3 = orig_param3;
qp->vlan_control = orig_vlan_control;
qp->fvl_rx = orig_fvl_rx;
qp->pri_path_fl = orig_pri_path_fl;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3797cc7..caa837e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1728,7 +1728,7 @@
if (cmd->cmdif_rev > CMD_IF_REV) {
dev_err(&dev->pdev->dev, "driver does not support command interface version. driver %d, firmware %d\n",
CMD_IF_REV, cmd->cmdif_rev);
- err = -ENOTSUPP;
+ err = -EOPNOTSUPP;
goto err_free_page;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 951dbd5..d5ecb8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -791,7 +791,8 @@
int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd);
int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix);
-void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv);
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
+ enum mlx5e_traffic_types tt);
int mlx5e_open_locked(struct net_device *netdev);
int mlx5e_close_locked(struct net_device *netdev);
@@ -863,12 +864,12 @@
static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv)
{
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv)
{
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
#else
int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index f0b460f..0523ed4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -89,7 +89,7 @@
int i;
if (!MLX5_CAP_GEN(priv->mdev, ets))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
ets->ets_cap = mlx5_max_tc(priv->mdev) + 1;
for (i = 0; i < ets->ets_cap; i++) {
@@ -236,7 +236,7 @@
int err;
if (!MLX5_CAP_GEN(priv->mdev, ets))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
err = mlx5e_dbcnl_validate_ets(netdev, ets);
if (err)
@@ -402,7 +402,7 @@
struct mlx5_core_dev *mdev = priv->mdev;
struct ieee_ets ets;
struct ieee_pfc pfc;
- int err = -ENOTSUPP;
+ int err = -EOPNOTSUPP;
int i;
if (!MLX5_CAP_GEN(mdev, ets))
@@ -511,6 +511,11 @@
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5_core_dev *mdev = priv->mdev;
+ if (!MLX5_CAP_GEN(priv->mdev, ets)) {
+ netdev_err(netdev, "%s, ets is not supported\n", __func__);
+ return;
+ }
+
if (priority >= CEE_DCBX_MAX_PRIO) {
netdev_err(netdev,
"%s, priority is out of range\n", __func__);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 33a399a..bb67863 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -543,7 +543,6 @@
struct ethtool_channels *ch)
{
struct mlx5e_priv *priv = netdev_priv(dev);
- int ncv = mlx5e_get_max_num_channels(priv->mdev);
unsigned int count = ch->combined_count;
bool arfs_enabled;
bool was_opened;
@@ -554,16 +553,6 @@
__func__);
return -EINVAL;
}
- if (ch->rx_count || ch->tx_count) {
- netdev_info(dev, "%s: separate rx/tx count not supported\n",
- __func__);
- return -EINVAL;
- }
- if (count > ncv) {
- netdev_info(dev, "%s: count (%d) > max (%d)\n",
- __func__, count, ncv);
- return -EINVAL;
- }
if (priv->params.num_channels == count)
return 0;
@@ -606,7 +595,7 @@
struct mlx5e_priv *priv = netdev_priv(netdev);
if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
coal->rx_coalesce_usecs = priv->params.rx_cq_moderation.usec;
coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation.pkts;
@@ -631,7 +620,7 @@
int i;
if (!MLX5_CAP_GEN(mdev, cq_moderation))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
mutex_lock(&priv->state_lock);
@@ -991,15 +980,18 @@
static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
{
- struct mlx5_core_dev *mdev = priv->mdev;
void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
- int i;
+ struct mlx5_core_dev *mdev = priv->mdev;
+ int ctxlen = MLX5_ST_SZ_BYTES(tirc);
+ int tt;
MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
- mlx5e_build_tir_ctx_hash(tirc, priv);
- for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
- mlx5_core_modify_tir(mdev, priv->indir_tir[i].tirn, in, inlen);
+ for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+ memset(tirc, 0, ctxlen);
+ mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
+ mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
+ }
}
static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
@@ -1007,6 +999,7 @@
{
struct mlx5e_priv *priv = netdev_priv(dev);
int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+ bool hash_changed = false;
void *in;
if ((hfunc != ETH_RSS_HASH_NO_CHANGE) &&
@@ -1028,14 +1021,21 @@
mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
}
- if (key)
+ if (hfunc != ETH_RSS_HASH_NO_CHANGE &&
+ hfunc != priv->params.rss_hfunc) {
+ priv->params.rss_hfunc = hfunc;
+ hash_changed = true;
+ }
+
+ if (key) {
memcpy(priv->params.toeplitz_hash_key, key,
sizeof(priv->params.toeplitz_hash_key));
+ hash_changed = hash_changed ||
+ priv->params.rss_hfunc == ETH_RSS_HASH_TOP;
+ }
- if (hfunc != ETH_RSS_HASH_NO_CHANGE)
- priv->params.rss_hfunc = hfunc;
-
- mlx5e_modify_tirs_hash(priv, in, inlen);
+ if (hash_changed)
+ mlx5e_modify_tirs_hash(priv, in, inlen);
mutex_unlock(&priv->state_lock);
@@ -1307,7 +1307,7 @@
u32 mlx5_wol_mode;
if (!wol_supported)
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (wol->wolopts & ~wol_supported)
return -EINVAL;
@@ -1437,7 +1437,7 @@
if (rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE &&
!MLX5_CAP_GEN(mdev, cq_period_start_from_cqe))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (!rx_mode_changed)
return 0;
@@ -1463,7 +1463,7 @@
bool reset;
if (!MLX5_CAP_GEN(mdev, cqe_compression))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (enable && priv->tstamp.hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE) {
netdev_err(netdev, "Can't enable cqe compression while timestamping is enabled.\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 1fe80de..a0e5a69 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -1089,7 +1089,7 @@
MLX5_FLOW_NAMESPACE_KERNEL);
if (!priv->fs.ns)
- return -EINVAL;
+ return -EOPNOTSUPP;
err = mlx5e_arfs_create_tables(priv);
if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index d088eff..f33f72d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -92,7 +92,7 @@
ns = mlx5_get_flow_namespace(priv->mdev,
MLX5_FLOW_NAMESPACE_ETHTOOL);
if (!ns)
- return ERR_PTR(-ENOTSUPP);
+ return ERR_PTR(-EOPNOTSUPP);
table_size = min_t(u32, BIT(MLX5_CAP_FLOWTABLE(priv->mdev,
flow_table_properties_nic_receive.log_max_ft_size)),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2b7dd31..f14ca33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2022,8 +2022,23 @@
MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout);
}
-void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv)
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
+ enum mlx5e_traffic_types tt)
{
+ void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+
+#define MLX5_HASH_IP (MLX5_HASH_FIELD_SEL_SRC_IP |\
+ MLX5_HASH_FIELD_SEL_DST_IP)
+
+#define MLX5_HASH_IP_L4PORTS (MLX5_HASH_FIELD_SEL_SRC_IP |\
+ MLX5_HASH_FIELD_SEL_DST_IP |\
+ MLX5_HASH_FIELD_SEL_L4_SPORT |\
+ MLX5_HASH_FIELD_SEL_L4_DPORT)
+
+#define MLX5_HASH_IP_IPSEC_SPI (MLX5_HASH_FIELD_SEL_SRC_IP |\
+ MLX5_HASH_FIELD_SEL_DST_IP |\
+ MLX5_HASH_FIELD_SEL_IPSEC_SPI)
+
MLX5_SET(tirc, tirc, rx_hash_fn,
mlx5e_rx_hash_fn(priv->params.rss_hfunc));
if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
@@ -2035,6 +2050,88 @@
MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
memcpy(rss_key, priv->params.toeplitz_hash_key, len);
}
+
+ switch (tt) {
+ case MLX5E_TT_IPV4_TCP:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV4);
+ MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+ MLX5_L4_PROT_TYPE_TCP);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP_L4PORTS);
+ break;
+
+ case MLX5E_TT_IPV6_TCP:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV6);
+ MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+ MLX5_L4_PROT_TYPE_TCP);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP_L4PORTS);
+ break;
+
+ case MLX5E_TT_IPV4_UDP:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV4);
+ MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+ MLX5_L4_PROT_TYPE_UDP);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP_L4PORTS);
+ break;
+
+ case MLX5E_TT_IPV6_UDP:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV6);
+ MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+ MLX5_L4_PROT_TYPE_UDP);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP_L4PORTS);
+ break;
+
+ case MLX5E_TT_IPV4_IPSEC_AH:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV4);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP_IPSEC_SPI);
+ break;
+
+ case MLX5E_TT_IPV6_IPSEC_AH:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV6);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP_IPSEC_SPI);
+ break;
+
+ case MLX5E_TT_IPV4_IPSEC_ESP:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV4);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP_IPSEC_SPI);
+ break;
+
+ case MLX5E_TT_IPV6_IPSEC_ESP:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV6);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP_IPSEC_SPI);
+ break;
+
+ case MLX5E_TT_IPV4:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV4);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP);
+ break;
+
+ case MLX5E_TT_IPV6:
+ MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+ MLX5_L3_PROT_TYPE_IPV6);
+ MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+ MLX5_HASH_IP);
+ break;
+ default:
+ WARN_ONCE(true, "%s: bad traffic type!\n", __func__);
+ }
}
static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
@@ -2404,110 +2501,13 @@
static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
enum mlx5e_traffic_types tt)
{
- void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
-
MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
-#define MLX5_HASH_IP (MLX5_HASH_FIELD_SEL_SRC_IP |\
- MLX5_HASH_FIELD_SEL_DST_IP)
-
-#define MLX5_HASH_IP_L4PORTS (MLX5_HASH_FIELD_SEL_SRC_IP |\
- MLX5_HASH_FIELD_SEL_DST_IP |\
- MLX5_HASH_FIELD_SEL_L4_SPORT |\
- MLX5_HASH_FIELD_SEL_L4_DPORT)
-
-#define MLX5_HASH_IP_IPSEC_SPI (MLX5_HASH_FIELD_SEL_SRC_IP |\
- MLX5_HASH_FIELD_SEL_DST_IP |\
- MLX5_HASH_FIELD_SEL_IPSEC_SPI)
-
mlx5e_build_tir_ctx_lro(tirc, priv);
MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
- mlx5e_build_tir_ctx_hash(tirc, priv);
-
- switch (tt) {
- case MLX5E_TT_IPV4_TCP:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV4);
- MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
- MLX5_L4_PROT_TYPE_TCP);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP_L4PORTS);
- break;
-
- case MLX5E_TT_IPV6_TCP:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV6);
- MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
- MLX5_L4_PROT_TYPE_TCP);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP_L4PORTS);
- break;
-
- case MLX5E_TT_IPV4_UDP:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV4);
- MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
- MLX5_L4_PROT_TYPE_UDP);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP_L4PORTS);
- break;
-
- case MLX5E_TT_IPV6_UDP:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV6);
- MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
- MLX5_L4_PROT_TYPE_UDP);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP_L4PORTS);
- break;
-
- case MLX5E_TT_IPV4_IPSEC_AH:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV4);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP_IPSEC_SPI);
- break;
-
- case MLX5E_TT_IPV6_IPSEC_AH:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV6);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP_IPSEC_SPI);
- break;
-
- case MLX5E_TT_IPV4_IPSEC_ESP:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV4);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP_IPSEC_SPI);
- break;
-
- case MLX5E_TT_IPV6_IPSEC_ESP:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV6);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP_IPSEC_SPI);
- break;
-
- case MLX5E_TT_IPV4:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV4);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP);
- break;
-
- case MLX5E_TT_IPV6:
- MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
- MLX5_L3_PROT_TYPE_IPV6);
- MLX5_SET(rx_hash_field_select, hfso, selected_fields,
- MLX5_HASH_IP);
- break;
- default:
- WARN_ONCE(true,
- "mlx5e_build_indir_tir_ctx: bad traffic type!\n");
- }
+ mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
}
static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
@@ -3331,7 +3331,7 @@
static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
{
if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (!MLX5_CAP_GEN(mdev, eth_net_offloads) ||
!MLX5_CAP_GEN(mdev, nic_flow_table) ||
!MLX5_CAP_ETH(mdev, csum_cap) ||
@@ -3343,7 +3343,7 @@
< 3) {
mlx5_core_warn(mdev,
"Not creating net device, some required device capabilities are missing\n");
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable))
mlx5_core_warn(mdev, "Self loop back prevention is not supported\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 0e2fb3e..06d5e6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -193,6 +193,9 @@
return false;
}
+ if (unlikely(page_is_pfmemalloc(dma_info->page)))
+ return false;
+
cache->page_cache[cache->tail] = *dma_info;
cache->tail = tail_next;
return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 118cea5..2ebbe80 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -663,23 +663,26 @@
__be32 *saddr,
int *out_ttl)
{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct rtable *rt;
struct neighbour *n = NULL;
int ttl;
#if IS_ENABLED(CONFIG_INET)
+ int ret;
+
rt = ip_route_output_key(dev_net(mirred_dev), fl4);
- if (IS_ERR(rt))
- return PTR_ERR(rt);
+ ret = PTR_ERR_OR_ZERO(rt);
+ if (ret)
+ return ret;
#else
return -EOPNOTSUPP;
#endif
-
- if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) {
- pr_warn("%s: can't offload, devices not on same HW e-switch\n", __func__);
- ip_rt_put(rt);
- return -EOPNOTSUPP;
- }
+ /* if the egress device isn't on the same HW e-switch, we use the uplink */
+ if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev))
+ *out_dev = mlx5_eswitch_get_uplink_netdev(esw);
+ else
+ *out_dev = rt->dst.dev;
ttl = ip4_dst_hoplimit(&rt->dst);
n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
@@ -690,7 +693,6 @@
*out_n = n;
*saddr = fl4->saddr;
*out_ttl = ttl;
- *out_dev = rt->dst.dev;
return 0;
}
@@ -741,8 +743,8 @@
struct flowi4 fl4 = {};
char *encap_header;
int encap_size;
- __be32 saddr = 0;
- int ttl = 0;
+ __be32 saddr;
+ int ttl;
int err;
encap_header = kzalloc(max_encap_size, GFP_KERNEL);
@@ -1085,10 +1087,14 @@
mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+ preempt_disable();
+
tcf_exts_to_list(f->exts, &actions);
list_for_each_entry(a, &actions, list)
tcf_action_stats_update(a, bytes, packets, lastuse);
+ preempt_enable();
+
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index f14d9c9..d0c8bf0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -133,7 +133,7 @@
if (!MLX5_CAP_ESW(dev, vport_cvlan_strip) ||
!MLX5_CAP_ESW(dev, vport_cvlan_insert_if_not_exist))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
esw_debug(dev, "Set Vport[%d] VLAN %d qos %d set=%x\n",
vport, vlan, qos, set_flags);
@@ -353,7 +353,7 @@
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
if (!root_ns) {
esw_warn(dev, "Failed to get FDB flow namespace\n");
- return -ENOMEM;
+ return -EOPNOTSUPP;
}
flow_group_in = mlx5_vzalloc(inlen);
@@ -962,7 +962,7 @@
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS);
if (!root_ns) {
esw_warn(dev, "Failed to get E-Switch egress flow namespace\n");
- return -EIO;
+ return -EOPNOTSUPP;
}
flow_group_in = mlx5_vzalloc(inlen);
@@ -1079,7 +1079,7 @@
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS);
if (!root_ns) {
esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n");
- return -EIO;
+ return -EOPNOTSUPP;
}
flow_group_in = mlx5_vzalloc(inlen);
@@ -1630,7 +1630,7 @@
if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) ||
!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
if (!MLX5_CAP_ESW_INGRESS_ACL(esw->dev, ft_support))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 03293ed..595f7c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -166,7 +166,7 @@
return 0;
out_notsupp:
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
@@ -424,6 +424,7 @@
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
if (!root_ns) {
esw_warn(dev, "Failed to get FDB flow namespace\n");
+ err = -EOPNOTSUPP;
goto ns_err;
}
@@ -535,7 +536,7 @@
ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS);
if (!ns) {
esw_warn(esw->dev, "Failed to get offloads flow namespace\n");
- return -ENOMEM;
+ return -EOPNOTSUPP;
}
ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0, 0);
@@ -655,7 +656,7 @@
esw_warn(esw->dev, "Failed setting eswitch to offloads, err %d\n", err);
err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
if (err1)
- esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err);
+ esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err1);
}
if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) {
if (mlx5_eswitch_inline_mode_get(esw,
@@ -674,9 +675,14 @@
int vport;
int err;
+ /* disable PF RoCE so missed packets don't go through RoCE steering */
+ mlx5_dev_list_lock();
+ mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+ mlx5_dev_list_unlock();
+
err = esw_create_offloads_fdb_table(esw, nvports);
if (err)
- return err;
+ goto create_fdb_err;
err = esw_create_offloads_table(esw);
if (err)
@@ -696,11 +702,6 @@
goto err_reps;
}
- /* disable PF RoCE so missed packets don't go through RoCE steering */
- mlx5_dev_list_lock();
- mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
- mlx5_dev_list_unlock();
-
return 0;
err_reps:
@@ -717,6 +718,13 @@
create_ft_err:
esw_destroy_offloads_fdb_table(esw);
+
+create_fdb_err:
+ /* enable back PF RoCE */
+ mlx5_dev_list_lock();
+ mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+ mlx5_dev_list_unlock();
+
return err;
}
@@ -724,11 +732,6 @@
{
int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
- /* enable back PF RoCE */
- mlx5_dev_list_lock();
- mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
- mlx5_dev_list_unlock();
-
mlx5_eswitch_disable_sriov(esw);
err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
if (err) {
@@ -738,6 +741,11 @@
esw_warn(esw->dev, "Failed setting eswitch back to offloads, err %d\n", err);
}
+ /* enable back PF RoCE */
+ mlx5_dev_list_lock();
+ mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+ mlx5_dev_list_unlock();
+
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index c4478ec..b53fc85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -322,7 +322,7 @@
flow_table_properties_nic_receive.
flow_modify_en);
if (!atomic_mod_cap)
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
opmod = 1;
return mlx5_cmd_set_fte(dev, opmod, modify_mask, ft, group_id, fte);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 0ac7a2f..6346a8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1822,7 +1822,7 @@
struct mlx5_flow_table *ft;
ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR);
- if (!ns)
+ if (WARN_ON(!ns))
return -EINVAL;
ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL, 0);
if (IS_ERR(ft)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d01e9f2..3c315eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -807,7 +807,7 @@
return 0;
}
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index d2ec9d2..fd12e0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -620,7 +620,7 @@
u32 out[MLX5_ST_SZ_DW(qtct_reg)];
if (!MLX5_CAP_GEN(mdev, ets))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
return mlx5_core_access_reg(mdev, in, inlen, out, sizeof(out),
MLX5_REG_QETCR, 0, 1);
@@ -632,7 +632,7 @@
u32 in[MLX5_ST_SZ_DW(qtct_reg)];
if (!MLX5_CAP_GEN(mdev, ets))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
memset(in, 0, sizeof(in));
return mlx5_core_access_reg(mdev, in, sizeof(in), out, outlen,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 269e440..7129c30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -532,7 +532,7 @@
if (!MLX5_CAP_GEN(mdev, vport_group_manager))
return -EACCES;
if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
in = mlx5_vzalloc(inlen);
if (!in)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index d147ddd..0af3338 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -209,21 +209,21 @@
/* pci_eqe_cmd_token
* Command completion event - token
*/
-MLXSW_ITEM32(pci, eqe, cmd_token, 0x08, 16, 16);
+MLXSW_ITEM32(pci, eqe, cmd_token, 0x00, 16, 16);
/* pci_eqe_cmd_status
* Command completion event - status
*/
-MLXSW_ITEM32(pci, eqe, cmd_status, 0x08, 0, 8);
+MLXSW_ITEM32(pci, eqe, cmd_status, 0x00, 0, 8);
/* pci_eqe_cmd_out_param_h
* Command completion event - output parameter - higher part
*/
-MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x0C, 0, 32);
+MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x04, 0, 32);
/* pci_eqe_cmd_out_param_l
* Command completion event - output parameter - lower part
*/
-MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x10, 0, 32);
+MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x08, 0, 32);
#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d768c7b..003093a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -684,6 +684,7 @@
dev_kfree_skb_any(skb_orig);
return NETDEV_TX_OK;
}
+ dev_consume_skb_any(skb_orig);
}
if (eth_skb_pad(skb)) {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 01d0efa..9e494a4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1172,7 +1172,8 @@
static int
mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop_group *nh_grp)
+ struct mlxsw_sp_nexthop_group *nh_grp,
+ bool reallocate)
{
u32 adj_index = nh_grp->adj_index; /* base */
struct mlxsw_sp_nexthop *nh;
@@ -1187,7 +1188,7 @@
continue;
}
- if (nh->update) {
+ if (nh->update || reallocate) {
err = mlxsw_sp_nexthop_mac_update(mlxsw_sp,
adj_index, nh);
if (err)
@@ -1248,7 +1249,8 @@
/* Nothing was added or removed, so no need to reallocate. Just
* update MAC on existing adjacency indexes.
*/
- err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp);
+ err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp,
+ false);
if (err) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
goto set_trap;
@@ -1276,7 +1278,7 @@
nh_grp->adj_index_valid = 1;
nh_grp->adj_index = adj_index;
nh_grp->ecmp_size = ecmp_size;
- err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp);
+ err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, true);
if (err) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
goto set_trap;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 150ccf5..2e88115e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -345,6 +345,7 @@
dev_kfree_skb_any(skb_orig);
return NETDEV_TX_OK;
}
+ dev_consume_skb_any(skb_orig);
}
mlxsw_sx_txhdr_construct(skb, &tx_info);
/* TX header is consumed by HW on the way so we shouldn't count its
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 8e5cb76..873ce2c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -297,7 +297,7 @@
list_del(&p_pkt->list_entry);
b_last_packet = list_empty(&p_tx->active_descq);
list_add_tail(&p_pkt->list_entry, &p_tx->free_descq);
- if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO) {
+ if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO) {
struct qed_ooo_buffer *p_buffer;
p_buffer = (struct qed_ooo_buffer *)p_pkt->cookie;
@@ -309,7 +309,7 @@
b_last_frag =
p_tx->cur_completing_bd_idx == p_pkt->bd_used;
tx_frag = p_pkt->bds_set[0].tx_frag;
- if (p_ll2_conn->gsi_enable)
+ if (p_ll2_conn->conn.gsi_enable)
qed_ll2b_release_tx_gsi_packet(p_hwfn,
p_ll2_conn->
my_id,
@@ -378,7 +378,7 @@
spin_unlock_irqrestore(&p_tx->lock, flags);
tx_frag = p_pkt->bds_set[0].tx_frag;
- if (p_ll2_conn->gsi_enable)
+ if (p_ll2_conn->conn.gsi_enable)
qed_ll2b_complete_tx_gsi_packet(p_hwfn,
p_ll2_conn->my_id,
p_pkt->cookie,
@@ -550,7 +550,7 @@
list_move_tail(&p_pkt->list_entry, &p_rx->free_descq);
- if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO) {
+ if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO) {
struct qed_ooo_buffer *p_buffer;
p_buffer = (struct qed_ooo_buffer *)p_pkt->cookie;
@@ -738,7 +738,7 @@
rc = qed_ll2_prepare_tx_packet(p_hwfn, p_ll2_conn->my_id, 1,
p_buffer->vlan, bd_flags,
l4_hdr_offset_w,
- p_ll2_conn->tx_dest, 0,
+ p_ll2_conn->conn.tx_dest, 0,
first_frag,
p_buffer->packet_length,
p_buffer, true);
@@ -858,7 +858,7 @@
u16 buf_idx;
int rc = 0;
- if (p_ll2_info->conn_type != QED_LL2_TYPE_ISCSI_OOO)
+ if (p_ll2_info->conn.conn_type != QED_LL2_TYPE_ISCSI_OOO)
return rc;
if (!rx_num_ooo_buffers)
@@ -901,7 +901,7 @@
qed_ll2_establish_connection_ooo(struct qed_hwfn *p_hwfn,
struct qed_ll2_info *p_ll2_conn)
{
- if (p_ll2_conn->conn_type != QED_LL2_TYPE_ISCSI_OOO)
+ if (p_ll2_conn->conn.conn_type != QED_LL2_TYPE_ISCSI_OOO)
return;
qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info);
@@ -913,7 +913,7 @@
{
struct qed_ooo_buffer *p_buffer;
- if (p_ll2_conn->conn_type != QED_LL2_TYPE_ISCSI_OOO)
+ if (p_ll2_conn->conn.conn_type != QED_LL2_TYPE_ISCSI_OOO)
return;
qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info);
@@ -945,23 +945,19 @@
{
struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
u8 *handle = &hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id;
- struct qed_ll2_info *ll2_info;
+ struct qed_ll2_conn ll2_info;
int rc;
- ll2_info = kzalloc(sizeof(*ll2_info), GFP_KERNEL);
- if (!ll2_info)
- return -ENOMEM;
- ll2_info->conn_type = QED_LL2_TYPE_ISCSI_OOO;
- ll2_info->mtu = params->mtu;
- ll2_info->rx_drop_ttl0_flg = params->drop_ttl0_packets;
- ll2_info->rx_vlan_removal_en = params->rx_vlan_stripping;
- ll2_info->tx_tc = OOO_LB_TC;
- ll2_info->tx_dest = CORE_TX_DEST_LB;
+ ll2_info.conn_type = QED_LL2_TYPE_ISCSI_OOO;
+ ll2_info.mtu = params->mtu;
+ ll2_info.rx_drop_ttl0_flg = params->drop_ttl0_packets;
+ ll2_info.rx_vlan_removal_en = params->rx_vlan_stripping;
+ ll2_info.tx_tc = OOO_LB_TC;
+ ll2_info.tx_dest = CORE_TX_DEST_LB;
- rc = qed_ll2_acquire_connection(hwfn, ll2_info,
+ rc = qed_ll2_acquire_connection(hwfn, &ll2_info,
QED_LL2_RX_SIZE, QED_LL2_TX_SIZE,
handle);
- kfree(ll2_info);
if (rc) {
DP_INFO(cdev, "Failed to acquire LL2 OOO connection\n");
goto out;
@@ -1006,7 +1002,7 @@
struct qed_ll2_info *p_ll2_conn,
u8 action_on_error)
{
- enum qed_ll2_conn_type conn_type = p_ll2_conn->conn_type;
+ enum qed_ll2_conn_type conn_type = p_ll2_conn->conn.conn_type;
struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue;
struct core_rx_start_ramrod_data *p_ramrod = NULL;
struct qed_spq_entry *p_ent = NULL;
@@ -1032,7 +1028,7 @@
p_ramrod->sb_index = p_rx->rx_sb_index;
p_ramrod->complete_event_flg = 1;
- p_ramrod->mtu = cpu_to_le16(p_ll2_conn->mtu);
+ p_ramrod->mtu = cpu_to_le16(p_ll2_conn->conn.mtu);
DMA_REGPAIR_LE(p_ramrod->bd_base,
p_rx->rxq_chain.p_phys_addr);
cqe_pbl_size = (u16)qed_chain_get_page_cnt(&p_rx->rcq_chain);
@@ -1040,8 +1036,8 @@
DMA_REGPAIR_LE(p_ramrod->cqe_pbl_addr,
qed_chain_get_pbl_phys(&p_rx->rcq_chain));
- p_ramrod->drop_ttl0_flg = p_ll2_conn->rx_drop_ttl0_flg;
- p_ramrod->inner_vlan_removal_en = p_ll2_conn->rx_vlan_removal_en;
+ p_ramrod->drop_ttl0_flg = p_ll2_conn->conn.rx_drop_ttl0_flg;
+ p_ramrod->inner_vlan_removal_en = p_ll2_conn->conn.rx_vlan_removal_en;
p_ramrod->queue_id = p_ll2_conn->queue_id;
p_ramrod->main_func_queue = (conn_type == QED_LL2_TYPE_ISCSI_OOO) ? 0
: 1;
@@ -1056,14 +1052,14 @@
}
p_ramrod->action_on_error.error_type = action_on_error;
- p_ramrod->gsi_offload_flag = p_ll2_conn->gsi_enable;
+ p_ramrod->gsi_offload_flag = p_ll2_conn->conn.gsi_enable;
return qed_spq_post(p_hwfn, p_ent, NULL);
}
static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
struct qed_ll2_info *p_ll2_conn)
{
- enum qed_ll2_conn_type conn_type = p_ll2_conn->conn_type;
+ enum qed_ll2_conn_type conn_type = p_ll2_conn->conn.conn_type;
struct qed_ll2_tx_queue *p_tx = &p_ll2_conn->tx_queue;
struct core_tx_start_ramrod_data *p_ramrod = NULL;
struct qed_spq_entry *p_ent = NULL;
@@ -1075,7 +1071,7 @@
if (!QED_LL2_TX_REGISTERED(p_ll2_conn))
return 0;
- if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO)
+ if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO)
p_ll2_conn->tx_stats_en = 0;
else
p_ll2_conn->tx_stats_en = 1;
@@ -1096,7 +1092,7 @@
p_ramrod->sb_id = cpu_to_le16(qed_int_get_sp_sb_id(p_hwfn));
p_ramrod->sb_index = p_tx->tx_sb_index;
- p_ramrod->mtu = cpu_to_le16(p_ll2_conn->mtu);
+ p_ramrod->mtu = cpu_to_le16(p_ll2_conn->conn.mtu);
p_ramrod->stats_en = p_ll2_conn->tx_stats_en;
p_ramrod->stats_id = p_ll2_conn->tx_stats_id;
@@ -1106,7 +1102,7 @@
p_ramrod->pbl_size = cpu_to_le16(pbl_size);
memset(&pq_params, 0, sizeof(pq_params));
- pq_params.core.tc = p_ll2_conn->tx_tc;
+ pq_params.core.tc = p_ll2_conn->conn.tx_tc;
pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
p_ramrod->qm_pq_id = cpu_to_le16(pq_id);
@@ -1123,7 +1119,7 @@
DP_NOTICE(p_hwfn, "Unknown connection type: %d\n", conn_type);
}
- p_ramrod->gsi_offload_flag = p_ll2_conn->gsi_enable;
+ p_ramrod->gsi_offload_flag = p_ll2_conn->conn.gsi_enable;
return qed_spq_post(p_hwfn, p_ent, NULL);
}
@@ -1224,7 +1220,7 @@
DP_VERBOSE(p_hwfn, QED_MSG_LL2,
"Allocated LL2 Rxq [Type %08x] with 0x%08x buffers\n",
- p_ll2_info->conn_type, rx_num_desc);
+ p_ll2_info->conn.conn_type, rx_num_desc);
out:
return rc;
@@ -1262,7 +1258,7 @@
DP_VERBOSE(p_hwfn, QED_MSG_LL2,
"Allocated LL2 Txq [Type %08x] with 0x%08x buffers\n",
- p_ll2_info->conn_type, tx_num_desc);
+ p_ll2_info->conn.conn_type, tx_num_desc);
out:
if (rc)
@@ -1273,7 +1269,7 @@
}
int qed_ll2_acquire_connection(struct qed_hwfn *p_hwfn,
- struct qed_ll2_info *p_params,
+ struct qed_ll2_conn *p_params,
u16 rx_num_desc,
u16 tx_num_desc,
u8 *p_connection_handle)
@@ -1302,15 +1298,7 @@
if (!p_ll2_info)
return -EBUSY;
- p_ll2_info->conn_type = p_params->conn_type;
- p_ll2_info->mtu = p_params->mtu;
- p_ll2_info->rx_drop_ttl0_flg = p_params->rx_drop_ttl0_flg;
- p_ll2_info->rx_vlan_removal_en = p_params->rx_vlan_removal_en;
- p_ll2_info->tx_tc = p_params->tx_tc;
- p_ll2_info->tx_dest = p_params->tx_dest;
- p_ll2_info->ai_err_packet_too_big = p_params->ai_err_packet_too_big;
- p_ll2_info->ai_err_no_buf = p_params->ai_err_no_buf;
- p_ll2_info->gsi_enable = p_params->gsi_enable;
+ p_ll2_info->conn = *p_params;
rc = qed_ll2_acquire_connection_rx(p_hwfn, p_ll2_info, rx_num_desc);
if (rc)
@@ -1371,9 +1359,9 @@
SET_FIELD(action_on_error,
CORE_RX_ACTION_ON_ERROR_PACKET_TOO_BIG,
- p_ll2_conn->ai_err_packet_too_big);
+ p_ll2_conn->conn.ai_err_packet_too_big);
SET_FIELD(action_on_error,
- CORE_RX_ACTION_ON_ERROR_NO_BUFF, p_ll2_conn->ai_err_no_buf);
+ CORE_RX_ACTION_ON_ERROR_NO_BUFF, p_ll2_conn->conn.ai_err_no_buf);
return qed_sp_ll2_rx_queue_start(p_hwfn, p_ll2_conn, action_on_error);
}
@@ -1600,7 +1588,7 @@
"LL2 [q 0x%02x cid 0x%08x type 0x%08x] Tx Producer at [0x%04x] - set with a %04x bytes %02x BDs buffer at %08x:%08x\n",
p_ll2->queue_id,
p_ll2->cid,
- p_ll2->conn_type,
+ p_ll2->conn.conn_type,
prod_idx,
first_frag_len,
num_of_bds,
@@ -1676,7 +1664,7 @@
(NETIF_MSG_TX_QUEUED | QED_MSG_LL2),
"LL2 [q 0x%02x cid 0x%08x type 0x%08x] Doorbelled [producer 0x%04x]\n",
p_ll2_conn->queue_id,
- p_ll2_conn->cid, p_ll2_conn->conn_type, db_msg.spq_prod);
+ p_ll2_conn->cid, p_ll2_conn->conn.conn_type, db_msg.spq_prod);
}
int qed_ll2_prepare_tx_packet(struct qed_hwfn *p_hwfn,
@@ -1817,7 +1805,7 @@
qed_ll2_rxq_flush(p_hwfn, connection_handle);
}
- if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO)
+ if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO)
qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info);
return rc;
@@ -1993,7 +1981,7 @@
static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
{
- struct qed_ll2_info ll2_info;
+ struct qed_ll2_conn ll2_info;
struct qed_ll2_buffer *buffer, *tmp_buffer;
enum qed_ll2_conn_type conn_type;
struct qed_ptt *p_ptt;
@@ -2041,6 +2029,7 @@
/* Prepare the temporary ll2 information */
memset(&ll2_info, 0, sizeof(ll2_info));
+
ll2_info.conn_type = conn_type;
ll2_info.mtu = params->mtu;
ll2_info.rx_drop_ttl0_flg = params->drop_ttl0_packets;
@@ -2120,7 +2109,6 @@
}
ether_addr_copy(cdev->ll2_mac_address, params->ll2_mac_address);
-
return 0;
release_terminate_all:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index 6625a3a..3141792 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -112,15 +112,8 @@
bool b_completing_packet;
};
-struct qed_ll2_info {
- /* Lock protecting the state of LL2 */
- struct mutex mutex;
+struct qed_ll2_conn {
enum qed_ll2_conn_type conn_type;
- u32 cid;
- u8 my_id;
- u8 queue_id;
- u8 tx_stats_id;
- bool b_active;
u16 mtu;
u8 rx_drop_ttl0_flg;
u8 rx_vlan_removal_en;
@@ -128,10 +121,21 @@
enum core_tx_dest tx_dest;
enum core_error_handle ai_err_packet_too_big;
enum core_error_handle ai_err_no_buf;
+ u8 gsi_enable;
+};
+
+struct qed_ll2_info {
+ /* Lock protecting the state of LL2 */
+ struct mutex mutex;
+ struct qed_ll2_conn conn;
+ u32 cid;
+ u8 my_id;
+ u8 queue_id;
+ u8 tx_stats_id;
+ bool b_active;
u8 tx_stats_en;
struct qed_ll2_rx_queue rx_queue;
struct qed_ll2_tx_queue tx_queue;
- u8 gsi_enable;
};
/**
@@ -149,7 +153,7 @@
* @return 0 on success, failure otherwise
*/
int qed_ll2_acquire_connection(struct qed_hwfn *p_hwfn,
- struct qed_ll2_info *p_params,
+ struct qed_ll2_conn *p_params,
u16 rx_num_desc,
u16 tx_num_desc,
u8 *p_connection_handle);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 2a16547..2dbdb32 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -2632,7 +2632,7 @@
{
struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
struct qed_roce_ll2_info *roce_ll2;
- struct qed_ll2_info ll2_params;
+ struct qed_ll2_conn ll2_params;
int rc;
if (!params) {
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-phy.c b/drivers/net/ethernet/qualcomm/emac/emac-phy.c
index 99a14df..2851b4c 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-phy.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-phy.c
@@ -201,6 +201,13 @@
else
adpt->phydev = mdiobus_get_phy(mii_bus, phy_addr);
+ /* of_phy_find_device() claims a reference to the phydev,
+ * so we do that here manually as well. When the driver
+ * later unloads, it can unilaterally drop the reference
+ * without worrying about ACPI vs DT.
+ */
+ if (adpt->phydev)
+ get_device(&adpt->phydev->mdio.dev);
} else {
struct device_node *phy_np;
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 422289c..f46d300 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -719,8 +719,7 @@
err_undo_napi:
netif_napi_del(&adpt->rx_q.napi);
err_undo_mdiobus:
- if (!has_acpi_companion(&pdev->dev))
- put_device(&adpt->phydev->mdio.dev);
+ put_device(&adpt->phydev->mdio.dev);
mdiobus_unregister(adpt->mii_bus);
err_undo_clocks:
emac_clks_teardown(adpt);
@@ -740,8 +739,7 @@
emac_clks_teardown(adpt);
- if (!has_acpi_companion(&pdev->dev))
- put_device(&adpt->phydev->mdio.dev);
+ put_device(&adpt->phydev->mdio.dev);
mdiobus_unregister(adpt->mii_bus);
free_netdev(netdev);
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 92d7692..301f487 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -179,6 +179,49 @@
.get_mdio_data = ravb_get_mdio_data,
};
+/* Free TX skb function for AVB-IP */
+static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only)
+{
+ struct ravb_private *priv = netdev_priv(ndev);
+ struct net_device_stats *stats = &priv->stats[q];
+ struct ravb_tx_desc *desc;
+ int free_num = 0;
+ int entry;
+ u32 size;
+
+ for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
+ bool txed;
+
+ entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] *
+ NUM_TX_DESC);
+ desc = &priv->tx_ring[q][entry];
+ txed = desc->die_dt == DT_FEMPTY;
+ if (free_txed_only && !txed)
+ break;
+ /* Descriptor type must be checked before all other reads */
+ dma_rmb();
+ size = le16_to_cpu(desc->ds_tagl) & TX_DS;
+ /* Free the original skb. */
+ if (priv->tx_skb[q][entry / NUM_TX_DESC]) {
+ dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
+ size, DMA_TO_DEVICE);
+ /* Last packet descriptor? */
+ if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) {
+ entry /= NUM_TX_DESC;
+ dev_kfree_skb_any(priv->tx_skb[q][entry]);
+ priv->tx_skb[q][entry] = NULL;
+ if (txed)
+ stats->tx_packets++;
+ }
+ free_num++;
+ }
+ if (txed)
+ stats->tx_bytes += size;
+ desc->die_dt = DT_EEMPTY;
+ }
+ return free_num;
+}
+
/* Free skb's and DMA buffers for Ethernet AVB */
static void ravb_ring_free(struct net_device *ndev, int q)
{
@@ -194,19 +237,21 @@
kfree(priv->rx_skb[q]);
priv->rx_skb[q] = NULL;
- /* Free TX skb ringbuffer */
- if (priv->tx_skb[q]) {
- for (i = 0; i < priv->num_tx_ring[q]; i++)
- dev_kfree_skb(priv->tx_skb[q][i]);
- }
- kfree(priv->tx_skb[q]);
- priv->tx_skb[q] = NULL;
-
/* Free aligned TX buffers */
kfree(priv->tx_align[q]);
priv->tx_align[q] = NULL;
if (priv->rx_ring[q]) {
+ for (i = 0; i < priv->num_rx_ring[q]; i++) {
+ struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i];
+
+ if (!dma_mapping_error(ndev->dev.parent,
+ le32_to_cpu(desc->dptr)))
+ dma_unmap_single(ndev->dev.parent,
+ le32_to_cpu(desc->dptr),
+ PKT_BUF_SZ,
+ DMA_FROM_DEVICE);
+ }
ring_size = sizeof(struct ravb_ex_rx_desc) *
(priv->num_rx_ring[q] + 1);
dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q],
@@ -215,12 +260,20 @@
}
if (priv->tx_ring[q]) {
+ ravb_tx_free(ndev, q, false);
+
ring_size = sizeof(struct ravb_tx_desc) *
(priv->num_tx_ring[q] * NUM_TX_DESC + 1);
dma_free_coherent(ndev->dev.parent, ring_size, priv->tx_ring[q],
priv->tx_desc_dma[q]);
priv->tx_ring[q] = NULL;
}
+
+ /* Free TX skb ringbuffer.
+ * SKBs are freed by ravb_tx_free() call above.
+ */
+ kfree(priv->tx_skb[q]);
+ priv->tx_skb[q] = NULL;
}
/* Format skb and descriptor buffer for Ethernet AVB */
@@ -431,44 +484,6 @@
return 0;
}
-/* Free TX skb function for AVB-IP */
-static int ravb_tx_free(struct net_device *ndev, int q)
-{
- struct ravb_private *priv = netdev_priv(ndev);
- struct net_device_stats *stats = &priv->stats[q];
- struct ravb_tx_desc *desc;
- int free_num = 0;
- int entry;
- u32 size;
-
- for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
- entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] *
- NUM_TX_DESC);
- desc = &priv->tx_ring[q][entry];
- if (desc->die_dt != DT_FEMPTY)
- break;
- /* Descriptor type must be checked before all other reads */
- dma_rmb();
- size = le16_to_cpu(desc->ds_tagl) & TX_DS;
- /* Free the original skb. */
- if (priv->tx_skb[q][entry / NUM_TX_DESC]) {
- dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
- size, DMA_TO_DEVICE);
- /* Last packet descriptor? */
- if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) {
- entry /= NUM_TX_DESC;
- dev_kfree_skb_any(priv->tx_skb[q][entry]);
- priv->tx_skb[q][entry] = NULL;
- stats->tx_packets++;
- }
- free_num++;
- }
- stats->tx_bytes += size;
- desc->die_dt = DT_EEMPTY;
- }
- return free_num;
-}
-
static void ravb_get_tx_tstamp(struct net_device *ndev)
{
struct ravb_private *priv = netdev_priv(ndev);
@@ -902,7 +917,7 @@
spin_lock_irqsave(&priv->lock, flags);
/* Clear TX interrupt */
ravb_write(ndev, ~mask, TIS);
- ravb_tx_free(ndev, q);
+ ravb_tx_free(ndev, q, true);
netif_wake_subqueue(ndev, q);
mmiowb();
spin_unlock_irqrestore(&priv->lock, flags);
@@ -926,14 +941,10 @@
/* Receive error message handling */
priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors;
priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors;
- if (priv->rx_over_errors != ndev->stats.rx_over_errors) {
+ if (priv->rx_over_errors != ndev->stats.rx_over_errors)
ndev->stats.rx_over_errors = priv->rx_over_errors;
- netif_err(priv, rx_err, ndev, "Receive Descriptor Empty\n");
- }
- if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) {
+ if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors)
ndev->stats.rx_fifo_errors = priv->rx_fifo_errors;
- netif_err(priv, rx_err, ndev, "Receive FIFO Overflow\n");
- }
out:
return budget - quota;
}
@@ -1508,6 +1519,19 @@
buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) +
entry / NUM_TX_DESC * DPTR_ALIGN;
len = PTR_ALIGN(skb->data, DPTR_ALIGN) - skb->data;
+ /* Zero length DMA descriptors are problematic as they seem to
+ * terminate DMA transfers. Avoid them by simply using a length of
+ * DPTR_ALIGN (4) when skb data is aligned to DPTR_ALIGN.
+ *
+ * As skb is guaranteed to have at least ETH_ZLEN (60) bytes of
+ * data by the call to skb_put_padto() above this is safe with
+ * respect to both the length of the first DMA descriptor (len)
+ * overflowing the available data and the length of the second DMA
+ * descriptor (skb->len - len) being negative.
+ */
+ if (len == 0)
+ len = DPTR_ALIGN;
+
memcpy(buffer, skb->data, len);
dma_addr = dma_map_single(ndev->dev.parent, buffer, len, DMA_TO_DEVICE);
if (dma_mapping_error(ndev->dev.parent, dma_addr))
@@ -1558,7 +1582,8 @@
priv->cur_tx[q] += NUM_TX_DESC;
if (priv->cur_tx[q] - priv->dirty_tx[q] >
- (priv->num_tx_ring[q] - 1) * NUM_TX_DESC && !ravb_tx_free(ndev, q))
+ (priv->num_tx_ring[q] - 1) * NUM_TX_DESC &&
+ !ravb_tx_free(ndev, q, true))
netif_stop_subqueue(ndev, q);
exit:
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index be3c91c..5484fd7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -305,8 +305,12 @@
{
void __iomem *ioaddr = hw->pcsr;
u32 intr_status = readl(ioaddr + GMAC_INT_STATUS);
+ u32 intr_mask = readl(ioaddr + GMAC_INT_MASK);
int ret = 0;
+ /* Discard masked bits */
+ intr_status &= ~intr_mask;
+
/* Not used events (e.g. MMC interrupts) are not handled. */
if ((intr_status & GMAC_INT_STATUS_MMCTIS))
x->mmc_tx_irq_n++;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a276a32..e3f6389 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3326,9 +3326,9 @@
(priv->plat->maxmtu >= ndev->min_mtu))
ndev->max_mtu = priv->plat->maxmtu;
else if (priv->plat->maxmtu < ndev->min_mtu)
- netdev_warn(priv->dev,
- "%s: warning: maxmtu having invalid value (%d)\n",
- __func__, priv->plat->maxmtu);
+ dev_warn(priv->device,
+ "%s: warning: maxmtu having invalid value (%d)\n",
+ __func__, priv->plat->maxmtu);
if (flow_ctrl)
priv->flow_ctrl = FLOW_AUTO; /* RX/TX pause on */
@@ -3340,7 +3340,8 @@
*/
if ((priv->synopsys_id >= DWMAC_CORE_3_50) && (!priv->plat->riwt_off)) {
priv->use_riwt = 1;
- netdev_info(priv->dev, "Enable RX Mitigation via HW Watchdog Timer\n");
+ dev_info(priv->device,
+ "Enable RX Mitigation via HW Watchdog Timer\n");
}
netif_napi_add(ndev, &priv->napi, stmmac_poll, 64);
@@ -3366,17 +3367,17 @@
/* MDIO bus Registration */
ret = stmmac_mdio_register(ndev);
if (ret < 0) {
- netdev_err(priv->dev,
- "%s: MDIO bus (id: %d) registration failed",
- __func__, priv->plat->bus_id);
+ dev_err(priv->device,
+ "%s: MDIO bus (id: %d) registration failed",
+ __func__, priv->plat->bus_id);
goto error_mdio_register;
}
}
ret = register_netdev(ndev);
if (ret) {
- netdev_err(priv->dev, "%s: ERROR %i registering the device\n",
- __func__, ret);
+ dev_err(priv->device, "%s: ERROR %i registering the device\n",
+ __func__, ret);
goto error_netdev_register;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 082cd48..36942f5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -351,6 +351,7 @@
if (of_phy_is_fixed_link(np))
of_phy_deregister_fixed_link(np);
of_node_put(plat->phy_node);
+ of_node_put(plat->mdio_node);
}
#else
struct plat_stmmacenet_data *
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index 77c88fc..9b8a30b 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -1210,7 +1210,7 @@
goto fail_alloc;
}
-#warning FIXME: unhardcode gpio&reset bits
+ /* FIXME: unhardcode gpio&reset bits */
ar7_gpio_disable(26);
ar7_gpio_disable(27);
ar7_device_reset(AR7_RESET_BIT_CPMAC_LO);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index b203143..6508822 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -3160,7 +3160,7 @@
{
struct platform_device *pdev = to_platform_device(dev);
struct net_device *ndev = platform_get_drvdata(pdev);
- struct cpsw_common *cpsw = netdev_priv(ndev);
+ struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
/* Select default pin state */
pinctrl_pm_select_default_state(dev);
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 93dc10b..aa02a03 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -100,6 +100,14 @@
/* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT)
+#ifdef __BIG_ENDIAN
+#define xemaclite_readl ioread32be
+#define xemaclite_writel iowrite32be
+#else
+#define xemaclite_readl ioread32
+#define xemaclite_writel iowrite32
+#endif
+
/**
* struct net_local - Our private per device data
* @ndev: instance of the network device
@@ -156,15 +164,15 @@
u32 reg_data;
/* Enable the Tx interrupts for the first Buffer */
- reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
- __raw_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
- drvdata->base_addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+ xemaclite_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
+ drvdata->base_addr + XEL_TSR_OFFSET);
/* Enable the Rx interrupts for the first buffer */
- __raw_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);
+ xemaclite_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);
/* Enable the Global Interrupt Enable */
- __raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+ xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
}
/**
@@ -179,17 +187,17 @@
u32 reg_data;
/* Disable the Global Interrupt Enable */
- __raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+ xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
/* Disable the Tx interrupts for the first buffer */
- reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
- __raw_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
- drvdata->base_addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+ xemaclite_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
+ drvdata->base_addr + XEL_TSR_OFFSET);
/* Disable the Rx interrupts for the first buffer */
- reg_data = __raw_readl(drvdata->base_addr + XEL_RSR_OFFSET);
- __raw_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
- drvdata->base_addr + XEL_RSR_OFFSET);
+ reg_data = xemaclite_readl(drvdata->base_addr + XEL_RSR_OFFSET);
+ xemaclite_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
+ drvdata->base_addr + XEL_RSR_OFFSET);
}
/**
@@ -321,7 +329,7 @@
byte_count = ETH_FRAME_LEN;
/* Check if the expected buffer is available */
- reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
XEL_TSR_XMIT_ACTIVE_MASK)) == 0) {
@@ -334,7 +342,7 @@
addr = (void __iomem __force *)((u32 __force)addr ^
XEL_BUFFER_OFFSET);
- reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
XEL_TSR_XMIT_ACTIVE_MASK)) != 0)
@@ -345,16 +353,16 @@
/* Write the frame to the buffer */
xemaclite_aligned_write(data, (u32 __force *) addr, byte_count);
- __raw_writel((byte_count & XEL_TPLR_LENGTH_MASK),
- addr + XEL_TPLR_OFFSET);
+ xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK),
+ addr + XEL_TPLR_OFFSET);
/* Update the Tx Status Register to indicate that there is a
* frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which
* is used by the interrupt handler to check whether a frame
* has been transmitted */
- reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK);
- __raw_writel(reg_data, addr + XEL_TSR_OFFSET);
+ xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET);
return 0;
}
@@ -369,7 +377,7 @@
*
* Return: Total number of bytes received
*/
-static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
+static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
{
void __iomem *addr;
u16 length, proto_type;
@@ -379,7 +387,7 @@
addr = (drvdata->base_addr + drvdata->next_rx_buf_to_use);
/* Verify which buffer has valid data */
- reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
if ((reg_data & XEL_RSR_RECV_DONE_MASK) == XEL_RSR_RECV_DONE_MASK) {
if (drvdata->rx_ping_pong != 0)
@@ -396,27 +404,28 @@
return 0; /* No data was available */
/* Verify that buffer has valid data */
- reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
if ((reg_data & XEL_RSR_RECV_DONE_MASK) !=
XEL_RSR_RECV_DONE_MASK)
return 0; /* No data was available */
}
/* Get the protocol type of the ethernet frame that arrived */
- proto_type = ((ntohl(__raw_readl(addr + XEL_HEADER_OFFSET +
+ proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET +
XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) &
XEL_RPLR_LENGTH_MASK);
/* Check if received ethernet frame is a raw ethernet frame
* or an IP packet or an ARP packet */
- if (proto_type > (ETH_FRAME_LEN + ETH_FCS_LEN)) {
+ if (proto_type > ETH_DATA_LEN) {
if (proto_type == ETH_P_IP) {
- length = ((ntohl(__raw_readl(addr +
+ length = ((ntohl(xemaclite_readl(addr +
XEL_HEADER_IP_LENGTH_OFFSET +
XEL_RXBUFF_OFFSET)) >>
XEL_HEADER_SHIFT) &
XEL_RPLR_LENGTH_MASK);
+ length = min_t(u16, length, ETH_DATA_LEN);
length += ETH_HLEN + ETH_FCS_LEN;
} else if (proto_type == ETH_P_ARP)
@@ -429,14 +438,17 @@
/* Use the length in the frame, plus the header and trailer */
length = proto_type + ETH_HLEN + ETH_FCS_LEN;
+ if (WARN_ON(length > maxlen))
+ length = maxlen;
+
/* Read from the EmacLite device */
xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET),
data, length);
/* Acknowledge the frame */
- reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
reg_data &= ~XEL_RSR_RECV_DONE_MASK;
- __raw_writel(reg_data, addr + XEL_RSR_OFFSET);
+ xemaclite_writel(reg_data, addr + XEL_RSR_OFFSET);
return length;
}
@@ -463,14 +475,14 @@
xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN);
- __raw_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
+ xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
/* Update the MAC address in the EmacLite */
- reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
- __raw_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
+ xemaclite_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);
/* Wait for EmacLite to finish with the MAC address update */
- while ((__raw_readl(addr + XEL_TSR_OFFSET) &
+ while ((xemaclite_readl(addr + XEL_TSR_OFFSET) &
XEL_TSR_PROG_MAC_ADDR) != 0)
;
}
@@ -603,7 +615,7 @@
skb_reserve(skb, 2);
- len = xemaclite_recv_data(lp, (u8 *) skb->data);
+ len = xemaclite_recv_data(lp, (u8 *) skb->data, len);
if (!len) {
dev->stats.rx_errors++;
@@ -640,32 +652,32 @@
u32 tx_status;
/* Check if there is Rx Data available */
- if ((__raw_readl(base_addr + XEL_RSR_OFFSET) &
+ if ((xemaclite_readl(base_addr + XEL_RSR_OFFSET) &
XEL_RSR_RECV_DONE_MASK) ||
- (__raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
+ (xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
& XEL_RSR_RECV_DONE_MASK))
xemaclite_rx_handler(dev);
/* Check if the Transmission for the first buffer is completed */
- tx_status = __raw_readl(base_addr + XEL_TSR_OFFSET);
+ tx_status = xemaclite_readl(base_addr + XEL_TSR_OFFSET);
if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {
tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
- __raw_writel(tx_status, base_addr + XEL_TSR_OFFSET);
+ xemaclite_writel(tx_status, base_addr + XEL_TSR_OFFSET);
tx_complete = true;
}
/* Check if the Transmission for the second buffer is completed */
- tx_status = __raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+ tx_status = xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {
tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
- __raw_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
- XEL_TSR_OFFSET);
+ xemaclite_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
+ XEL_TSR_OFFSET);
tx_complete = true;
}
@@ -698,7 +710,7 @@
/* wait for the MDIO interface to not be busy or timeout
after some time.
*/
- while (__raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
+ while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
XEL_MDIOCTRL_MDIOSTS_MASK) {
if (time_before_eq(end, jiffies)) {
WARN_ON(1);
@@ -734,17 +746,17 @@
* MDIO Address register. Set the Status bit in the MDIO Control
* register to start a MDIO read transaction.
*/
- ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
- __raw_writel(XEL_MDIOADDR_OP_MASK |
- ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
- lp->base_addr + XEL_MDIOADDR_OFFSET);
- __raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
- lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ xemaclite_writel(XEL_MDIOADDR_OP_MASK |
+ ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+ lp->base_addr + XEL_MDIOADDR_OFFSET);
+ xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+ lp->base_addr + XEL_MDIOCTRL_OFFSET);
if (xemaclite_mdio_wait(lp))
return -ETIMEDOUT;
- rc = __raw_readl(lp->base_addr + XEL_MDIORD_OFFSET);
+ rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET);
dev_dbg(&lp->ndev->dev,
"xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
@@ -781,13 +793,13 @@
* Data register. Finally, set the Status bit in the MDIO Control
* register to start a MDIO write transaction.
*/
- ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
- __raw_writel(~XEL_MDIOADDR_OP_MASK &
- ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
- lp->base_addr + XEL_MDIOADDR_OFFSET);
- __raw_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
- __raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
- lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ xemaclite_writel(~XEL_MDIOADDR_OP_MASK &
+ ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+ lp->base_addr + XEL_MDIOADDR_OFFSET);
+ xemaclite_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
+ xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+ lp->base_addr + XEL_MDIOCTRL_OFFSET);
return 0;
}
@@ -834,8 +846,8 @@
/* Enable the MDIO bus by asserting the enable bit in MDIO Control
* register.
*/
- __raw_writel(XEL_MDIOCTRL_MDIOEN_MASK,
- lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ xemaclite_writel(XEL_MDIOCTRL_MDIOEN_MASK,
+ lp->base_addr + XEL_MDIOCTRL_OFFSET);
bus = mdiobus_alloc();
if (!bus) {
@@ -1140,8 +1152,8 @@
}
/* Clear the Tx CSR's in case this is a restart */
- __raw_writel(0, lp->base_addr + XEL_TSR_OFFSET);
- __raw_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+ xemaclite_writel(0, lp->base_addr + XEL_TSR_OFFSET);
+ xemaclite_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
/* Set the MAC address in the EmacLite device */
xemaclite_update_address(lp, ndev->dev_addr);
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 8b6810b..99d3df7 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -69,7 +69,6 @@
struct socket *sock0;
struct socket *sock1u;
- struct net *net;
struct net_device *dev;
unsigned int hash_size;
@@ -316,7 +315,7 @@
netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk);
- xnet = !net_eq(gtp->net, dev_net(gtp->dev));
+ xnet = !net_eq(sock_net(sk), dev_net(gtp->dev));
switch (udp_sk(sk)->encap_type) {
case UDP_ENCAP_GTP0:
@@ -612,7 +611,7 @@
pktinfo.fl4.saddr, pktinfo.fl4.daddr,
pktinfo.iph->tos,
ip4_dst_hoplimit(&pktinfo.rt->dst),
- htons(IP_DF),
+ 0,
pktinfo.gtph_port, pktinfo.gtph_port,
true, false);
break;
@@ -658,7 +657,7 @@
static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
static void gtp_hashtable_free(struct gtp_dev *gtp);
static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
- int fd_gtp0, int fd_gtp1, struct net *src_net);
+ int fd_gtp0, int fd_gtp1);
static int gtp_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
@@ -675,7 +674,7 @@
fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
- err = gtp_encap_enable(dev, gtp, fd0, fd1, src_net);
+ err = gtp_encap_enable(dev, gtp, fd0, fd1);
if (err < 0)
goto out_err;
@@ -821,7 +820,7 @@
}
static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
- int fd_gtp0, int fd_gtp1, struct net *src_net)
+ int fd_gtp0, int fd_gtp1)
{
struct udp_tunnel_sock_cfg tuncfg = {NULL};
struct socket *sock0, *sock1u;
@@ -858,7 +857,6 @@
gtp->sock0 = sock0;
gtp->sock1u = sock1u;
- gtp->net = src_net;
tuncfg.sk_user_data = gtp;
tuncfg.encap_rcv = gtp_encap_recv;
@@ -1376,3 +1374,4 @@
MODULE_AUTHOR("Harald Welte <hwelte@sysmocom.de>");
MODULE_DESCRIPTION("Interface driver for GTP encapsulated traffic");
MODULE_ALIAS_RTNL_LINK("gtp");
+MODULE_ALIAS_GENL_FAMILY("gtp");
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index ece59c5..4a40a3d 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -648,8 +648,8 @@
{
/* Finish setting up the DEVICE info. */
dev->mtu = AX_MTU;
- dev->hard_header_len = 0;
- dev->addr_len = 0;
+ dev->hard_header_len = AX25_MAX_HEADER_LEN;
+ dev->addr_len = AX25_ADDR_LEN;
dev->type = ARPHRD_AX25;
dev->tx_queue_len = 10;
dev->header_ops = &ax25_header_ops;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 5a1cc08..86e5749 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1295,6 +1295,9 @@
ndev = hv_get_drvdata(device);
buffer = get_per_channel_state(channel);
+ /* commit_rd_index() -> hv_signal_on_read() needs this. */
+ init_cached_read_index(channel);
+
do {
desc = get_next_pkt_raw(channel);
if (desc != NULL) {
@@ -1347,6 +1350,9 @@
bufferlen = bytes_recvd;
}
+
+ init_cached_read_index(channel);
+
} while (1);
if (bufferlen > NETVSC_PACKET_SIZE)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c9414c0..fcab801 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -659,6 +659,7 @@
* policy filters on the host). Deliver these via the VF
* interface in the guest.
*/
+ rcu_read_lock();
vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
if (vf_netdev && (vf_netdev->flags & IFF_UP))
net = vf_netdev;
@@ -667,6 +668,7 @@
skb = netvsc_alloc_recv_skb(net, packet, csum_info, *data, vlan_tci);
if (unlikely(!skb)) {
++net->stats.rx_dropped;
+ rcu_read_unlock();
return NVSP_STAT_FAIL;
}
@@ -696,6 +698,7 @@
* TODO - use NAPI?
*/
netif_rx(skb);
+ rcu_read_unlock();
return 0;
}
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 46d53a6..76ba7ec 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -1715,9 +1715,9 @@
/* Reset */
if (gpio_is_valid(rstn)) {
udelay(1);
- gpio_set_value(rstn, 0);
+ gpio_set_value_cansleep(rstn, 0);
udelay(1);
- gpio_set_value(rstn, 1);
+ gpio_set_value_cansleep(rstn, 1);
usleep_range(120, 240);
}
diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index 1253f86..ef68851 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -117,13 +117,26 @@
{
struct usb_device *usb_dev = atusb->usb_dev;
int ret;
+ uint8_t *buffer;
uint8_t value;
+ buffer = kmalloc(1, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
dev_dbg(&usb_dev->dev, "atusb: reg = 0x%x\n", reg);
ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
ATUSB_REG_READ, ATUSB_REQ_FROM_DEV,
- 0, reg, &value, 1, 1000);
- return ret >= 0 ? value : ret;
+ 0, reg, buffer, 1, 1000);
+
+ if (ret >= 0) {
+ value = buffer[0];
+ kfree(buffer);
+ return value;
+ } else {
+ kfree(buffer);
+ return ret;
+ }
}
static int atusb_write_subreg(struct atusb *atusb, uint8_t reg, uint8_t mask,
@@ -549,13 +562,6 @@
atusb_set_frame_retries(struct ieee802154_hw *hw, s8 retries)
{
struct atusb *atusb = hw->priv;
- struct device *dev = &atusb->usb_dev->dev;
-
- if (atusb->fw_ver_maj == 0 && atusb->fw_ver_min < 3) {
- dev_info(dev, "Automatic frame retransmission is only available from "
- "firmware version 0.3. Please update if you want this feature.");
- return -EINVAL;
- }
return atusb_write_subreg(atusb, SR_MAX_FRAME_RETRIES, retries);
}
@@ -608,9 +614,13 @@
static int atusb_get_and_show_revision(struct atusb *atusb)
{
struct usb_device *usb_dev = atusb->usb_dev;
- unsigned char buffer[3];
+ unsigned char *buffer;
int ret;
+ buffer = kmalloc(3, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
/* Get a couple of the ATMega Firmware values */
ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
ATUSB_ID, ATUSB_REQ_FROM_DEV, 0, 0,
@@ -631,15 +641,20 @@
dev_info(&usb_dev->dev, "Please update to version 0.2 or newer");
}
+ kfree(buffer);
return ret;
}
static int atusb_get_and_show_build(struct atusb *atusb)
{
struct usb_device *usb_dev = atusb->usb_dev;
- char build[ATUSB_BUILD_SIZE + 1];
+ char *build;
int ret;
+ build = kmalloc(ATUSB_BUILD_SIZE + 1, GFP_KERNEL);
+ if (!build)
+ return -ENOMEM;
+
ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
ATUSB_BUILD, ATUSB_REQ_FROM_DEV, 0, 0,
build, ATUSB_BUILD_SIZE, 1000);
@@ -648,6 +663,7 @@
dev_info(&usb_dev->dev, "Firmware: build %s\n", build);
}
+ kfree(build);
return ret;
}
@@ -698,7 +714,7 @@
static int atusb_set_extended_addr(struct atusb *atusb)
{
struct usb_device *usb_dev = atusb->usb_dev;
- unsigned char buffer[IEEE802154_EXTENDED_ADDR_LEN];
+ unsigned char *buffer;
__le64 extended_addr;
u64 addr;
int ret;
@@ -710,12 +726,20 @@
return 0;
}
+ buffer = kmalloc(IEEE802154_EXTENDED_ADDR_LEN, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
/* Firmware is new enough so we fetch the address from EEPROM */
ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
ATUSB_EUI64_READ, ATUSB_REQ_FROM_DEV, 0, 0,
buffer, IEEE802154_EXTENDED_ADDR_LEN, 1000);
- if (ret < 0)
- dev_err(&usb_dev->dev, "failed to fetch extended address\n");
+ if (ret < 0) {
+ dev_err(&usb_dev->dev, "failed to fetch extended address, random address set\n");
+ ieee802154_random_extended_addr(&atusb->hw->phy->perm_extended_addr);
+ kfree(buffer);
+ return ret;
+ }
memcpy(&extended_addr, buffer, IEEE802154_EXTENDED_ADDR_LEN);
/* Check if read address is not empty and the unicast bit is set correctly */
@@ -729,6 +753,7 @@
&addr);
}
+ kfree(buffer);
return ret;
}
@@ -770,8 +795,7 @@
hw->parent = &usb_dev->dev;
hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT |
- IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_CSMA_PARAMS |
- IEEE802154_HW_FRAME_RETRIES;
+ IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_CSMA_PARAMS;
hw->phy->flags = WPAN_PHY_FLAG_TXPOWER | WPAN_PHY_FLAG_CCA_ED_LEVEL |
WPAN_PHY_FLAG_CCA_MODE;
@@ -800,6 +824,9 @@
atusb_get_and_show_build(atusb);
atusb_set_extended_addr(atusb);
+ if (atusb->fw_ver_maj >= 0 && atusb->fw_ver_min >= 3)
+ hw->flags |= IEEE802154_HW_FRAME_RETRIES;
+
ret = atusb_get_and_clear_error(atusb);
if (ret) {
dev_err(&atusb->usb_dev->dev,
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 1e05b7c..0844f84 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -164,6 +164,7 @@
{
dev->mtu = 64 * 1024;
dev->hard_header_len = ETH_HLEN; /* 14 */
+ dev->min_header_len = ETH_HLEN; /* 14 */
dev->addr_len = ETH_ALEN; /* 6 */
dev->type = ARPHRD_LOOPBACK; /* 0x0001*/
dev->flags = IFF_LOOPBACK;
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 5c26653..c27011b 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -681,7 +681,7 @@
size_t linear;
if (q->flags & IFF_VNET_HDR) {
- vnet_hdr_len = q->vnet_hdr_sz;
+ vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
err = -EINVAL;
if (len < vnet_hdr_len)
@@ -820,12 +820,12 @@
if (q->flags & IFF_VNET_HDR) {
struct virtio_net_hdr vnet_hdr;
- vnet_hdr_len = q->vnet_hdr_sz;
+ vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
if (iov_iter_count(iter) < vnet_hdr_len)
return -EINVAL;
if (virtio_net_hdr_from_skb(skb, &vnet_hdr,
- macvtap_is_little_endian(q)))
+ macvtap_is_little_endian(q), true))
BUG();
if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index e741bf6..b0492ef 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -21,6 +21,23 @@
MODULE_AUTHOR("Maxime Bizon <mbizon@freebox.fr>");
MODULE_LICENSE("GPL");
+static int bcm63xx_config_intr(struct phy_device *phydev)
+{
+ int reg, err;
+
+ reg = phy_read(phydev, MII_BCM63XX_IR);
+ if (reg < 0)
+ return reg;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ reg &= ~MII_BCM63XX_IR_GMASK;
+ else
+ reg |= MII_BCM63XX_IR_GMASK;
+
+ err = phy_write(phydev, MII_BCM63XX_IR, reg);
+ return err;
+}
+
static int bcm63xx_config_init(struct phy_device *phydev)
{
int reg, err;
@@ -55,7 +72,7 @@
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
.ack_interrupt = bcm_phy_ack_intr,
- .config_intr = bcm_phy_config_intr,
+ .config_intr = bcm63xx_config_intr,
}, {
/* same phy as above, with just a different OUI */
.phy_id = 0x002bdc00,
@@ -67,7 +84,7 @@
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
.ack_interrupt = bcm_phy_ack_intr,
- .config_intr = bcm_phy_config_intr,
+ .config_intr = bcm63xx_config_intr,
} };
module_phy_driver(bcm63xx_driver);
diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c
index 800b39f..a10d0e7 100644
--- a/drivers/net/phy/dp83848.c
+++ b/drivers/net/phy/dp83848.c
@@ -17,6 +17,7 @@
#include <linux/phy.h>
#define TI_DP83848C_PHY_ID 0x20005ca0
+#define TI_DP83620_PHY_ID 0x20005ce0
#define NS_DP83848C_PHY_ID 0x20005c90
#define TLK10X_PHY_ID 0x2000a210
#define TI_DP83822_PHY_ID 0x2000a240
@@ -77,6 +78,7 @@
static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
{ TI_DP83848C_PHY_ID, 0xfffffff0 },
{ NS_DP83848C_PHY_ID, 0xfffffff0 },
+ { TI_DP83620_PHY_ID, 0xfffffff0 },
{ TLK10X_PHY_ID, 0xfffffff0 },
{ TI_DP83822_PHY_ID, 0xfffffff0 },
{ }
@@ -106,6 +108,7 @@
static struct phy_driver dp83848_driver[] = {
DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY"),
DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"),
+ DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY"),
DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"),
DP83848_PHY_DRIVER(TI_DP83822_PHY_ID, "TI DP83822 10/100 Mbps PHY"),
};
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index e84ae08..ca1b462 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -132,12 +132,16 @@
ret = of_property_read_u32(of_node, "ti,rx-internal-delay",
&dp83867->rx_id_delay);
- if (ret)
+ if (ret &&
+ (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+ phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID))
return ret;
ret = of_property_read_u32(of_node, "ti,tx-internal-delay",
&dp83867->tx_id_delay);
- if (ret)
+ if (ret &&
+ (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+ phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID))
return ret;
return of_property_read_u32(of_node, "ti,fifo-depth",
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 0b78210..ed0d235 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1679,6 +1679,8 @@
.ack_interrupt = &marvell_ack_interrupt,
.config_intr = &marvell_config_intr,
.did_interrupt = &m88e1121_did_interrupt,
+ .get_wol = &m88e1318_get_wol,
+ .set_wol = &m88e1318_set_wol,
.resume = &marvell_resume,
.suspend = &marvell_suspend,
.get_sset_count = marvell_get_sset_count,
diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c
index c0b4e65..46fe1ae 100644
--- a/drivers/net/phy/mdio-bcm-iproc.c
+++ b/drivers/net/phy/mdio-bcm-iproc.c
@@ -81,8 +81,6 @@
if (rc)
return rc;
- iproc_mdio_config_clk(priv->base);
-
/* Prepare the read operation */
cmd = (MII_DATA_TA_VAL << MII_DATA_TA_SHIFT) |
(reg << MII_DATA_RA_SHIFT) |
@@ -112,8 +110,6 @@
if (rc)
return rc;
- iproc_mdio_config_clk(priv->base);
-
/* Prepare the write operation */
cmd = (MII_DATA_TA_VAL << MII_DATA_TA_SHIFT) |
(reg << MII_DATA_RA_SHIFT) |
@@ -163,6 +159,8 @@
bus->read = iproc_mdio_read;
bus->write = iproc_mdio_write;
+ iproc_mdio_config_clk(priv->base);
+
rc = of_mdiobus_register(bus, pdev->dev.of_node);
if (rc) {
dev_err(&pdev->dev, "MDIO bus registration failed\n");
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 9a77289..6742070 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1008,6 +1008,20 @@
.get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
.resume = genphy_resume,
+}, {
+ .phy_id = PHY_ID_KSZ8795,
+ .phy_id_mask = MICREL_PHY_ID_MASK,
+ .name = "Micrel KSZ8795",
+ .features = PHY_BASIC_FEATURES,
+ .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
+ .config_init = kszphy_config_init,
+ .config_aneg = ksz8873mll_config_aneg,
+ .read_status = ksz8873mll_read_status,
+ .get_sset_count = kszphy_get_sset_count,
+ .get_strings = kszphy_get_strings,
+ .get_stats = kszphy_get_stats,
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
} };
module_phy_driver(ksphy_driver);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 48da6e9..7cc1b7d 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -29,6 +29,7 @@
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/phy.h>
+#include <linux/phy_led_triggers.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/mdio.h>
@@ -649,14 +650,18 @@
* phy_trigger_machine - trigger the state machine to run
*
* @phydev: the phy_device struct
+ * @sync: indicate whether we should wait for the workqueue cancelation
*
* Description: There has been a change in state which requires that the
* state machine runs.
*/
-static void phy_trigger_machine(struct phy_device *phydev)
+static void phy_trigger_machine(struct phy_device *phydev, bool sync)
{
- cancel_delayed_work_sync(&phydev->state_queue);
+ if (sync)
+ cancel_delayed_work_sync(&phydev->state_queue);
+ else
+ cancel_delayed_work(&phydev->state_queue);
queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
}
@@ -693,7 +698,7 @@
phydev->state = PHY_HALTED;
mutex_unlock(&phydev->lock);
- phy_trigger_machine(phydev);
+ phy_trigger_machine(phydev, false);
}
/**
@@ -840,7 +845,7 @@
}
/* reschedule state queue work to run as soon as possible */
- phy_trigger_machine(phydev);
+ phy_trigger_machine(phydev, true);
return;
ignore:
@@ -942,7 +947,7 @@
if (do_resume)
phy_resume(phydev);
- phy_trigger_machine(phydev);
+ phy_trigger_machine(phydev, true);
}
EXPORT_SYMBOL(phy_start);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 92b0838..8c8e15b 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -908,6 +908,7 @@
struct module *ndev_owner = dev->dev.parent->driver->owner;
struct mii_bus *bus = phydev->mdio.bus;
struct device *d = &phydev->mdio.dev;
+ bool using_genphy = false;
int err;
/* For Ethernet device drivers that register their own MDIO bus, we
@@ -933,12 +934,22 @@
d->driver =
&genphy_driver[GENPHY_DRV_1G].mdiodrv.driver;
+ using_genphy = true;
+ }
+
+ if (!try_module_get(d->driver->owner)) {
+ dev_err(&dev->dev, "failed to get the device driver module\n");
+ err = -EIO;
+ goto error_put_device;
+ }
+
+ if (using_genphy) {
err = d->driver->probe(d);
if (err >= 0)
err = device_bind_driver(d);
if (err)
- goto error;
+ goto error_module_put;
}
if (phydev->attached_dev) {
@@ -975,7 +986,13 @@
return err;
error:
+ /* phy_detach() does all of the cleanup below */
phy_detach(phydev);
+ return err;
+
+error_module_put:
+ module_put(d->driver->owner);
+error_put_device:
put_device(d);
if (ndev_owner != bus->owner)
module_put(bus->owner);
@@ -1039,6 +1056,8 @@
phy_led_triggers_unregister(phydev);
+ module_put(phydev->mdio.dev.driver->owner);
+
/* If the device had no specific driver before (i.e. - it
* was using the generic driver), we unbind the device
* from the generic driver so that there's a chance a
diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c
index fa62bdf..94ca42e 100644
--- a/drivers/net/phy/phy_led_triggers.c
+++ b/drivers/net/phy/phy_led_triggers.c
@@ -12,6 +12,7 @@
*/
#include <linux/leds.h>
#include <linux/phy.h>
+#include <linux/phy_led_triggers.h>
#include <linux/netdevice.h>
static struct phy_led_trigger *phy_speed_to_led_trigger(struct phy_device *phy,
@@ -102,8 +103,10 @@
sizeof(struct phy_led_trigger) *
phy->phy_num_led_triggers,
GFP_KERNEL);
- if (!phy->phy_led_triggers)
- return -ENOMEM;
+ if (!phy->phy_led_triggers) {
+ err = -ENOMEM;
+ goto out_clear;
+ }
for (i = 0; i < phy->phy_num_led_triggers; i++) {
err = phy_led_trigger_register(phy, &phy->phy_led_triggers[i],
@@ -120,6 +123,8 @@
while (i--)
phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
devm_kfree(&phy->mdio.dev, phy->phy_led_triggers);
+out_clear:
+ phy->phy_num_led_triggers = 0;
return err;
}
EXPORT_SYMBOL_GPL(phy_led_triggers_register);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index cd8e02c..bfabe18 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1170,9 +1170,11 @@
}
if (tun->flags & IFF_VNET_HDR) {
- if (len < tun->vnet_hdr_sz)
+ int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
+
+ if (len < vnet_hdr_sz)
return -EINVAL;
- len -= tun->vnet_hdr_sz;
+ len -= vnet_hdr_sz;
if (!copy_from_iter_full(&gso, sizeof(gso), from))
return -EFAULT;
@@ -1183,7 +1185,7 @@
if (tun16_to_cpu(tun, gso.hdr_len) > len)
return -EINVAL;
- iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso));
+ iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
}
if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
@@ -1335,7 +1337,7 @@
vlan_hlen = VLAN_HLEN;
if (tun->flags & IFF_VNET_HDR)
- vnet_hdr_sz = tun->vnet_hdr_sz;
+ vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
total = skb->len + vlan_hlen + vnet_hdr_sz;
@@ -1360,7 +1362,7 @@
return -EINVAL;
if (virtio_net_hdr_from_skb(skb, &gso,
- tun_is_little_endian(tun))) {
+ tun_is_little_endian(tun), true)) {
struct skb_shared_info *sinfo = skb_shinfo(skb);
pr_err("unexpected GSO type: "
"0x%x, gso_size %d, hdr_len %d\n",
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 3daa41b..0acc9b64 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -776,7 +776,7 @@
struct net_device *netdev;
struct catc *catc;
u8 broadcast[ETH_ALEN];
- int i, pktsz;
+ int pktsz, ret;
if (usb_set_interface(usbdev,
intf->altsetting->desc.bInterfaceNumber, 1)) {
@@ -811,12 +811,8 @@
if ((!catc->ctrl_urb) || (!catc->tx_urb) ||
(!catc->rx_urb) || (!catc->irq_urb)) {
dev_err(&intf->dev, "No free urbs available.\n");
- usb_free_urb(catc->ctrl_urb);
- usb_free_urb(catc->tx_urb);
- usb_free_urb(catc->rx_urb);
- usb_free_urb(catc->irq_urb);
- free_netdev(netdev);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto fail_free;
}
/* The F5U011 has the same vendor/product as the netmate but a device version of 0x130 */
@@ -844,15 +840,24 @@
catc->irq_buf, 2, catc_irq_done, catc, 1);
if (!catc->is_f5u011) {
+ u32 *buf;
+ int i;
+
dev_dbg(dev, "Checking memory size\n");
- i = 0x12345678;
- catc_write_mem(catc, 0x7a80, &i, 4);
- i = 0x87654321;
- catc_write_mem(catc, 0xfa80, &i, 4);
- catc_read_mem(catc, 0x7a80, &i, 4);
+ buf = kmalloc(4, GFP_KERNEL);
+ if (!buf) {
+ ret = -ENOMEM;
+ goto fail_free;
+ }
+
+ *buf = 0x12345678;
+ catc_write_mem(catc, 0x7a80, buf, 4);
+ *buf = 0x87654321;
+ catc_write_mem(catc, 0xfa80, buf, 4);
+ catc_read_mem(catc, 0x7a80, buf, 4);
- switch (i) {
+ switch (*buf) {
case 0x12345678:
catc_set_reg(catc, TxBufCount, 8);
catc_set_reg(catc, RxBufCount, 32);
@@ -867,6 +872,8 @@
dev_dbg(dev, "32k Memory\n");
break;
}
+
+ kfree(buf);
dev_dbg(dev, "Getting MAC from SEEROM.\n");
@@ -913,16 +920,21 @@
usb_set_intfdata(intf, catc);
SET_NETDEV_DEV(netdev, &intf->dev);
- if (register_netdev(netdev) != 0) {
- usb_set_intfdata(intf, NULL);
- usb_free_urb(catc->ctrl_urb);
- usb_free_urb(catc->tx_urb);
- usb_free_urb(catc->rx_urb);
- usb_free_urb(catc->irq_urb);
- free_netdev(netdev);
- return -EIO;
- }
+ ret = register_netdev(netdev);
+ if (ret)
+ goto fail_clear_intfdata;
+
return 0;
+
+fail_clear_intfdata:
+ usb_set_intfdata(intf, NULL);
+fail_free:
+ usb_free_urb(catc->ctrl_urb);
+ usb_free_urb(catc->tx_urb);
+ usb_free_urb(catc->rx_urb);
+ usb_free_urb(catc->irq_urb);
+ free_netdev(netdev);
+ return ret;
}
static void catc_disconnect(struct usb_interface *intf)
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index fe7b288..86144f9 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -531,6 +531,7 @@
#define SAMSUNG_VENDOR_ID 0x04e8
#define LENOVO_VENDOR_ID 0x17ef
#define NVIDIA_VENDOR_ID 0x0955
+#define HP_VENDOR_ID 0x03f0
static const struct usb_device_id products[] = {
/* BLACKLIST !!
@@ -677,6 +678,13 @@
.driver_info = 0,
},
+/* HP lt2523 (Novatel E371) - handled by qmi_wwan */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(HP_VENDOR_ID, 0x421d, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = 0,
+},
+
/* AnyDATA ADU960S - handled by qmi_wwan */
{
USB_DEVICE_AND_INTERFACE_INFO(0x16d5, 0x650a, USB_CLASS_COMM,
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 24e803f..3667448 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -126,40 +126,61 @@
static int get_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data)
{
+ u8 *buf;
int ret;
+ buf = kmalloc(size, GFP_NOIO);
+ if (!buf)
+ return -ENOMEM;
+
ret = usb_control_msg(pegasus->usb, usb_rcvctrlpipe(pegasus->usb, 0),
PEGASUS_REQ_GET_REGS, PEGASUS_REQT_READ, 0,
- indx, data, size, 1000);
+ indx, buf, size, 1000);
if (ret < 0)
netif_dbg(pegasus, drv, pegasus->net,
"%s returned %d\n", __func__, ret);
+ else if (ret <= size)
+ memcpy(data, buf, ret);
+ kfree(buf);
return ret;
}
-static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data)
+static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size,
+ const void *data)
{
+ u8 *buf;
int ret;
+ buf = kmemdup(data, size, GFP_NOIO);
+ if (!buf)
+ return -ENOMEM;
+
ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0),
PEGASUS_REQ_SET_REGS, PEGASUS_REQT_WRITE, 0,
- indx, data, size, 100);
+ indx, buf, size, 100);
if (ret < 0)
netif_dbg(pegasus, drv, pegasus->net,
"%s returned %d\n", __func__, ret);
+ kfree(buf);
return ret;
}
static int set_register(pegasus_t *pegasus, __u16 indx, __u8 data)
{
+ u8 *buf;
int ret;
+ buf = kmemdup(&data, 1, GFP_NOIO);
+ if (!buf)
+ return -ENOMEM;
+
ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0),
PEGASUS_REQ_SET_REG, PEGASUS_REQT_WRITE, data,
- indx, &data, 1, 1000);
+ indx, buf, 1, 1000);
if (ret < 0)
netif_dbg(pegasus, drv, pegasus->net,
"%s returned %d\n", __func__, ret);
+ kfree(buf);
return ret;
}
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6fe1cdb..24d5272 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -654,6 +654,13 @@
USB_CDC_PROTO_NONE),
.driver_info = (unsigned long)&qmi_wwan_info,
},
+ { /* HP lt2523 (Novatel E371) */
+ USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d,
+ USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET,
+ USB_CDC_PROTO_NONE),
+ .driver_info = (unsigned long)&qmi_wwan_info,
+ },
{ /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
.driver_info = (unsigned long)&qmi_wwan_info,
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index be41856..ad42295 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -32,7 +32,7 @@
#define NETNEXT_VERSION "08"
/* Information for net */
-#define NET_VERSION "6"
+#define NET_VERSION "8"
#define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION
#define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -1730,7 +1730,7 @@
u8 checksum = CHECKSUM_NONE;
u32 opts2, opts3;
- if (tp->version == RTL_VER_01 || tp->version == RTL_VER_02)
+ if (!(tp->netdev->features & NETIF_F_RXCSUM))
goto return_result;
opts2 = le32_to_cpu(rx_desc->opts2);
@@ -1936,6 +1936,9 @@
napi_complete(napi);
if (!list_empty(&tp->rx_done))
napi_schedule(napi);
+ else if (!skb_queue_empty(&tp->tx_queue) &&
+ !list_empty(&tp->tx_free))
+ napi_schedule(napi);
}
return work_done;
@@ -3155,10 +3158,13 @@
if (!netif_carrier_ok(netdev)) {
tp->rtl_ops.enable(tp);
set_bit(RTL8152_SET_RX_MODE, &tp->flags);
+ netif_stop_queue(netdev);
napi_disable(&tp->napi);
netif_carrier_on(netdev);
rtl_start_rx(tp);
napi_enable(&tp->napi);
+ netif_wake_queue(netdev);
+ netif_info(tp, link, netdev, "carrier on\n");
}
} else {
if (netif_carrier_ok(netdev)) {
@@ -3166,6 +3172,7 @@
napi_disable(&tp->napi);
tp->rtl_ops.disable(tp);
napi_enable(&tp->napi);
+ netif_info(tp, link, netdev, "carrier off\n");
}
}
}
@@ -3515,12 +3522,12 @@
if (!netif_running(netdev))
return 0;
+ netif_stop_queue(netdev);
napi_disable(&tp->napi);
clear_bit(WORK_ENABLE, &tp->flags);
usb_kill_urb(tp->intr_urb);
cancel_delayed_work_sync(&tp->schedule);
if (netif_carrier_ok(netdev)) {
- netif_stop_queue(netdev);
mutex_lock(&tp->control);
tp->rtl_ops.disable(tp);
mutex_unlock(&tp->control);
@@ -3545,12 +3552,17 @@
if (netif_carrier_ok(netdev)) {
mutex_lock(&tp->control);
tp->rtl_ops.enable(tp);
+ rtl_start_rx(tp);
rtl8152_set_rx_mode(netdev);
mutex_unlock(&tp->control);
- netif_wake_queue(netdev);
}
napi_enable(&tp->napi);
+ netif_wake_queue(netdev);
+ usb_submit_urb(tp->intr_urb, GFP_KERNEL);
+
+ if (!list_empty(&tp->rx_done))
+ napi_schedule(&tp->napi);
return 0;
}
@@ -3572,6 +3584,8 @@
*/
if (!sw_linking && tp->rtl_ops.in_nway(tp))
return true;
+ else if (!skb_queue_empty(&tp->tx_queue))
+ return true;
else
return false;
}
@@ -3581,10 +3595,15 @@
struct net_device *netdev = tp->netdev;
int ret = 0;
+ set_bit(SELECTIVE_SUSPEND, &tp->flags);
+ smp_mb__after_atomic();
+
if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
u32 rcr = 0;
if (delay_autosuspend(tp)) {
+ clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+ smp_mb__after_atomic();
ret = -EBUSY;
goto out1;
}
@@ -3601,6 +3620,8 @@
if (!(ocp_data & RXFIFO_EMPTY)) {
rxdy_gated_en(tp, false);
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
+ clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+ smp_mb__after_atomic();
ret = -EBUSY;
goto out1;
}
@@ -3620,8 +3641,6 @@
}
}
- set_bit(SELECTIVE_SUSPEND, &tp->flags);
-
out1:
return ret;
}
@@ -3677,12 +3696,15 @@
if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
tp->rtl_ops.autosuspend_en(tp, false);
- clear_bit(SELECTIVE_SUSPEND, &tp->flags);
napi_disable(&tp->napi);
set_bit(WORK_ENABLE, &tp->flags);
if (netif_carrier_ok(tp->netdev))
rtl_start_rx(tp);
napi_enable(&tp->napi);
+ clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+ smp_mb__after_atomic();
+ if (!list_empty(&tp->rx_done))
+ napi_schedule(&tp->napi);
} else {
tp->rtl_ops.up(tp);
netif_carrier_off(tp->netdev);
@@ -4356,6 +4378,11 @@
NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
+ if (tp->version == RTL_VER_01) {
+ netdev->features &= ~NETIF_F_RXCSUM;
+ netdev->hw_features &= ~NETIF_F_RXCSUM;
+ }
+
netdev->ethtool_ops = &ops;
netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE);
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 95b7bd0..c81c791 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -155,16 +155,36 @@
*/
static int get_registers(rtl8150_t * dev, u16 indx, u16 size, void *data)
{
- return usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
- RTL8150_REQ_GET_REGS, RTL8150_REQT_READ,
- indx, 0, data, size, 500);
+ void *buf;
+ int ret;
+
+ buf = kmalloc(size, GFP_NOIO);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
+ RTL8150_REQ_GET_REGS, RTL8150_REQT_READ,
+ indx, 0, buf, size, 500);
+ if (ret > 0 && ret <= size)
+ memcpy(data, buf, ret);
+ kfree(buf);
+ return ret;
}
-static int set_registers(rtl8150_t * dev, u16 indx, u16 size, void *data)
+static int set_registers(rtl8150_t * dev, u16 indx, u16 size, const void *data)
{
- return usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
- RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE,
- indx, 0, data, size, 500);
+ void *buf;
+ int ret;
+
+ buf = kmemdup(data, size, GFP_NOIO);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
+ RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE,
+ indx, 0, buf, size, 500);
+ kfree(buf);
+ return ret;
}
static void async_set_reg_cb(struct urb *urb)
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index 12071f1..d9440bc 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -73,8 +73,6 @@
/* Private data structure */
struct sierra_net_data {
- u8 ethr_hdr_tmpl[ETH_HLEN]; /* ethernet header template for rx'd pkts */
-
u16 link_up; /* air link up or down */
u8 tx_hdr_template[4]; /* part of HIP hdr for tx'd packets */
@@ -122,6 +120,7 @@
/* LSI Protocol types */
#define SIERRA_NET_PROTOCOL_UMTS 0x01
+#define SIERRA_NET_PROTOCOL_UMTS_DS 0x04
/* LSI Coverage */
#define SIERRA_NET_COVERAGE_NONE 0x00
#define SIERRA_NET_COVERAGE_NOPACKET 0x01
@@ -129,7 +128,8 @@
/* LSI Session */
#define SIERRA_NET_SESSION_IDLE 0x00
/* LSI Link types */
-#define SIERRA_NET_AS_LINK_TYPE_IPv4 0x00
+#define SIERRA_NET_AS_LINK_TYPE_IPV4 0x00
+#define SIERRA_NET_AS_LINK_TYPE_IPV6 0x02
struct lsi_umts {
u8 protocol;
@@ -137,9 +137,14 @@
__be16 length;
/* eventually use a union for the rest - assume umts for now */
u8 coverage;
- u8 unused2[41];
+ u8 network_len; /* network name len */
+ u8 network[40]; /* network name (UCS2, bigendian) */
u8 session_state;
u8 unused3[33];
+} __packed;
+
+struct lsi_umts_single {
+ struct lsi_umts lsi;
u8 link_type;
u8 pdp_addr_len; /* NW-supplied PDP address len */
u8 pdp_addr[16]; /* NW-supplied PDP address (bigendian)) */
@@ -158,10 +163,31 @@
u8 reserved[8];
} __packed;
+struct lsi_umts_dual {
+ struct lsi_umts lsi;
+ u8 pdp_addr4_len; /* NW-supplied PDP IPv4 address len */
+ u8 pdp_addr4[4]; /* NW-supplied PDP IPv4 address (bigendian)) */
+ u8 pdp_addr6_len; /* NW-supplied PDP IPv6 address len */
+ u8 pdp_addr6[16]; /* NW-supplied PDP IPv6 address (bigendian)) */
+ u8 unused4[23];
+ u8 dns1_addr4_len; /* NW-supplied 1st DNS v4 address len (bigendian) */
+ u8 dns1_addr4[4]; /* NW-supplied 1st DNS v4 address */
+ u8 dns1_addr6_len; /* NW-supplied 1st DNS v6 address len */
+ u8 dns1_addr6[16]; /* NW-supplied 1st DNS v6 address (bigendian)*/
+ u8 dns2_addr4_len; /* NW-supplied 2nd DNS v4 address len (bigendian) */
+ u8 dns2_addr4[4]; /* NW-supplied 2nd DNS v4 address */
+ u8 dns2_addr6_len; /* NW-supplied 2nd DNS v6 address len */
+ u8 dns2_addr6[16]; /* NW-supplied 2nd DNS v6 address (bigendian)*/
+ u8 unused5[68];
+} __packed;
+
#define SIERRA_NET_LSI_COMMON_LEN 4
-#define SIERRA_NET_LSI_UMTS_LEN (sizeof(struct lsi_umts))
+#define SIERRA_NET_LSI_UMTS_LEN (sizeof(struct lsi_umts_single))
#define SIERRA_NET_LSI_UMTS_STATUS_LEN \
(SIERRA_NET_LSI_UMTS_LEN - SIERRA_NET_LSI_COMMON_LEN)
+#define SIERRA_NET_LSI_UMTS_DS_LEN (sizeof(struct lsi_umts_dual))
+#define SIERRA_NET_LSI_UMTS_DS_STATUS_LEN \
+ (SIERRA_NET_LSI_UMTS_DS_LEN - SIERRA_NET_LSI_COMMON_LEN)
/* Forward definitions */
static void sierra_sync_timer(unsigned long syncdata);
@@ -190,10 +216,11 @@
dev->data[0] = (unsigned long)priv;
}
-/* is packet IPv4 */
+/* is packet IPv4/IPv6 */
static inline int is_ip(struct sk_buff *skb)
{
- return skb->protocol == cpu_to_be16(ETH_P_IP);
+ return skb->protocol == cpu_to_be16(ETH_P_IP) ||
+ skb->protocol == cpu_to_be16(ETH_P_IPV6);
}
/*
@@ -349,46 +376,51 @@
static int sierra_net_parse_lsi(struct usbnet *dev, char *data, int datalen)
{
struct lsi_umts *lsi = (struct lsi_umts *)data;
+ u32 expected_length;
- if (datalen < sizeof(struct lsi_umts)) {
- netdev_err(dev->net, "%s: Data length %d, exp %Zu\n",
- __func__, datalen,
- sizeof(struct lsi_umts));
+ if (datalen < sizeof(struct lsi_umts_single)) {
+ netdev_err(dev->net, "%s: Data length %d, exp >= %Zu\n",
+ __func__, datalen, sizeof(struct lsi_umts_single));
return -1;
}
- if (lsi->length != cpu_to_be16(SIERRA_NET_LSI_UMTS_STATUS_LEN)) {
- netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n",
- __func__, be16_to_cpu(lsi->length),
- (u32)SIERRA_NET_LSI_UMTS_STATUS_LEN);
- return -1;
- }
-
- /* Validate the protocol - only support UMTS for now */
- if (lsi->protocol != SIERRA_NET_PROTOCOL_UMTS) {
- netdev_err(dev->net, "Protocol unsupported, 0x%02x\n",
- lsi->protocol);
- return -1;
- }
-
- /* Validate the link type */
- if (lsi->link_type != SIERRA_NET_AS_LINK_TYPE_IPv4) {
- netdev_err(dev->net, "Link type unsupported: 0x%02x\n",
- lsi->link_type);
- return -1;
- }
-
- /* Validate the coverage */
- if (lsi->coverage == SIERRA_NET_COVERAGE_NONE
- || lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) {
- netdev_err(dev->net, "No coverage, 0x%02x\n", lsi->coverage);
- return 0;
- }
-
/* Validate the session state */
if (lsi->session_state == SIERRA_NET_SESSION_IDLE) {
netdev_err(dev->net, "Session idle, 0x%02x\n",
- lsi->session_state);
+ lsi->session_state);
+ return 0;
+ }
+
+ /* Validate the protocol - only support UMTS for now */
+ if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS) {
+ struct lsi_umts_single *single = (struct lsi_umts_single *)lsi;
+
+ /* Validate the link type */
+ if (single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV4 &&
+ single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV6) {
+ netdev_err(dev->net, "Link type unsupported: 0x%02x\n",
+ single->link_type);
+ return -1;
+ }
+ expected_length = SIERRA_NET_LSI_UMTS_STATUS_LEN;
+ } else if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS_DS) {
+ expected_length = SIERRA_NET_LSI_UMTS_DS_STATUS_LEN;
+ } else {
+ netdev_err(dev->net, "Protocol unsupported, 0x%02x\n",
+ lsi->protocol);
+ return -1;
+ }
+
+ if (be16_to_cpu(lsi->length) != expected_length) {
+ netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n",
+ __func__, be16_to_cpu(lsi->length), expected_length);
+ return -1;
+ }
+
+ /* Validate the coverage */
+ if (lsi->coverage == SIERRA_NET_COVERAGE_NONE ||
+ lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) {
+ netdev_err(dev->net, "No coverage, 0x%02x\n", lsi->coverage);
return 0;
}
@@ -652,7 +684,6 @@
u8 numendpoints;
u16 fwattr = 0;
int status;
- struct ethhdr *eth;
struct sierra_net_data *priv;
static const u8 sync_tmplate[sizeof(priv->sync_msg)] = {
0x00, 0x00, SIERRA_NET_HIP_MSYNC_ID, 0x00};
@@ -690,11 +721,6 @@
dev->net->dev_addr[ETH_ALEN-2] = atomic_inc_return(&iface_counter);
dev->net->dev_addr[ETH_ALEN-1] = ifacenum;
- /* we will have to manufacture ethernet headers, prepare template */
- eth = (struct ethhdr *)priv->ethr_hdr_tmpl;
- memcpy(ð->h_dest, dev->net->dev_addr, ETH_ALEN);
- eth->h_proto = cpu_to_be16(ETH_P_IP);
-
/* prepare shutdown message template */
memcpy(priv->shdwn_msg, shdwn_tmplate, sizeof(priv->shdwn_msg));
/* set context index initially to 0 - prepares tx hdr template */
@@ -824,9 +850,14 @@
skb_pull(skb, hh.hdrlen);
- /* We are going to accept this packet, prepare it */
- memcpy(skb->data, sierra_net_get_private(dev)->ethr_hdr_tmpl,
- ETH_HLEN);
+ /* We are going to accept this packet, prepare it.
+ * In case protocol is IPv6, keep it, otherwise force IPv4.
+ */
+ skb_reset_mac_header(skb);
+ if (eth_hdr(skb)->h_proto != cpu_to_be16(ETH_P_IPV6))
+ eth_hdr(skb)->h_proto = cpu_to_be16(ETH_P_IP);
+ eth_zero_addr(eth_hdr(skb)->h_source);
+ memcpy(eth_hdr(skb)->h_dest, dev->net->dev_addr, ETH_ALEN);
/* Last packet in batch handled by usbnet */
if (hh.payload_len.word == skb->len)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 4a10500..765c2d6 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -48,8 +48,16 @@
*/
DECLARE_EWMA(pkt_len, 1, 64)
+/* With mergeable buffers we align buffer address and use the low bits to
+ * encode its true size. Buffer size is up to 1 page so we need to align to
+ * square root of page size to ensure we reserve enough bits to encode the true
+ * size.
+ */
+#define MERGEABLE_BUFFER_MIN_ALIGN_SHIFT ((PAGE_SHIFT + 1) / 2)
+
/* Minimum alignment for mergeable packet buffers. */
-#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256)
+#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, \
+ 1 << MERGEABLE_BUFFER_MIN_ALIGN_SHIFT)
#define VIRTNET_DRIVER_VERSION "1.0.0"
@@ -1104,7 +1112,7 @@
hdr = skb_vnet_hdr(skb);
if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
- virtio_is_little_endian(vi->vdev)))
+ virtio_is_little_endian(vi->vdev), false))
BUG();
if (vi->mergeable_rx_bufs)
@@ -1707,6 +1715,11 @@
u16 xdp_qp = 0, curr_qp;
int i, err;
+ if (prog && prog->xdp_adjust_head) {
+ netdev_warn(dev, "Does not support bpf_xdp_adjust_head()\n");
+ return -EOPNOTSUPP;
+ }
+
if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) ||
virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
@@ -1890,8 +1903,12 @@
put_page(vi->rq[i].alloc_frag.page);
}
-static bool is_xdp_queue(struct virtnet_info *vi, int q)
+static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
{
+ /* For small receive mode always use kfree_skb variants */
+ if (!vi->mergeable_rx_bufs)
+ return false;
+
if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
return false;
else if (q < vi->curr_queue_pairs)
@@ -1908,7 +1925,7 @@
for (i = 0; i < vi->max_queue_pairs; i++) {
struct virtqueue *vq = vi->sq[i].vq;
while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
- if (!is_xdp_queue(vi, i))
+ if (!is_xdp_raw_buffer_queue(vi, i))
dev_kfree_skb(buf);
else
put_page(virt_to_head_page(buf));
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index bb70dd5..30b04cf 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1798,7 +1798,7 @@
static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device *dev,
struct vxlan_sock *sock4,
struct sk_buff *skb, int oif, u8 tos,
- __be32 daddr, __be32 *saddr,
+ __be32 daddr, __be32 *saddr, __be16 dport, __be16 sport,
struct dst_cache *dst_cache,
const struct ip_tunnel_info *info)
{
@@ -1824,6 +1824,8 @@
fl4.flowi4_proto = IPPROTO_UDP;
fl4.daddr = daddr;
fl4.saddr = *saddr;
+ fl4.fl4_dport = dport;
+ fl4.fl4_sport = sport;
rt = ip_route_output_key(vxlan->net, &fl4);
if (likely(!IS_ERR(rt))) {
@@ -1851,6 +1853,7 @@
__be32 label,
const struct in6_addr *daddr,
struct in6_addr *saddr,
+ __be16 dport, __be16 sport,
struct dst_cache *dst_cache,
const struct ip_tunnel_info *info)
{
@@ -1877,6 +1880,8 @@
fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label);
fl6.flowi6_mark = skb->mark;
fl6.flowi6_proto = IPPROTO_UDP;
+ fl6.fl6_dport = dport;
+ fl6.fl6_sport = sport;
err = ipv6_stub->ipv6_dst_lookup(vxlan->net,
sock6->sock->sk,
@@ -2068,6 +2073,7 @@
rdst ? rdst->remote_ifindex : 0, tos,
dst->sin.sin_addr.s_addr,
&src->sin.sin_addr.s_addr,
+ dst_port, src_port,
dst_cache, info);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
@@ -2104,6 +2110,7 @@
rdst ? rdst->remote_ifindex : 0, tos,
label, &dst->sin6.sin6_addr,
&src->sin6.sin6_addr,
+ dst_port, src_port,
dst_cache, info);
if (IS_ERR(ndst)) {
err = PTR_ERR(ndst);
@@ -2261,7 +2268,7 @@
= container_of(p, struct vxlan_fdb, hlist);
unsigned long timeout;
- if (f->state & NUD_PERMANENT)
+ if (f->state & (NUD_PERMANENT | NUD_NOARP))
continue;
timeout = f->used + vxlan->cfg.age_interval * HZ;
@@ -2347,7 +2354,7 @@
}
/* Purge the forwarding table */
-static void vxlan_flush(struct vxlan_dev *vxlan)
+static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
{
unsigned int h;
@@ -2357,6 +2364,8 @@
hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
struct vxlan_fdb *f
= container_of(p, struct vxlan_fdb, hlist);
+ if (!do_all && (f->state & (NUD_PERMANENT | NUD_NOARP)))
+ continue;
/* the all_zeros_mac entry is deleted at vxlan_uninit */
if (!is_zero_ether_addr(f->eth_addr))
vxlan_fdb_destroy(vxlan, f);
@@ -2378,7 +2387,7 @@
del_timer_sync(&vxlan->age_timer);
- vxlan_flush(vxlan);
+ vxlan_flush(vxlan, false);
vxlan_sock_release(vxlan);
return ret;
@@ -2430,7 +2439,8 @@
rt = vxlan_get_route(vxlan, dev, sock4, skb, 0, info->key.tos,
info->key.u.ipv4.dst,
- &info->key.u.ipv4.src, NULL, info);
+ &info->key.u.ipv4.src, dport, sport,
+ &info->dst_cache, info);
if (IS_ERR(rt))
return PTR_ERR(rt);
ip_rt_put(rt);
@@ -2441,7 +2451,8 @@
ndst = vxlan6_get_route(vxlan, dev, sock6, skb, 0, info->key.tos,
info->key.label, &info->key.u.ipv6.dst,
- &info->key.u.ipv6.src, NULL, info);
+ &info->key.u.ipv6.src, dport, sport,
+ &info->dst_cache, info);
if (IS_ERR(ndst))
return PTR_ERR(ndst);
dst_release(ndst);
@@ -2883,7 +2894,7 @@
memcpy(&vxlan->cfg, conf, sizeof(*conf));
if (!vxlan->cfg.dst_port) {
if (conf->flags & VXLAN_F_GPE)
- vxlan->cfg.dst_port = 4790; /* IANA assigned VXLAN-GPE port */
+ vxlan->cfg.dst_port = htons(4790); /* IANA VXLAN-GPE port */
else
vxlan->cfg.dst_port = default_port;
}
@@ -3051,6 +3062,8 @@
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
+ vxlan_flush(vxlan, true);
+
spin_lock(&vn->sock_lock);
if (!hlist_unhashed(&vxlan->hlist))
hlist_del_rcu(&vxlan->hlist);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
index d02ca14..8d3e53f 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
@@ -91,7 +91,7 @@
#define IWL8000_FW_PRE "iwlwifi-8000C-"
#define IWL8000_MODULE_FIRMWARE(api) \
- IWL8000_FW_PRE "-" __stringify(api) ".ucode"
+ IWL8000_FW_PRE __stringify(api) ".ucode"
#define IWL8265_FW_PRE "iwlwifi-8265-"
#define IWL8265_MODULE_FIRMWARE(api) \
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 636c8b0..09e9e2e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1164,9 +1164,10 @@
.frame_limit = IWL_FRAME_LIMIT,
};
- /* Make sure reserved queue is still marked as such (or allocated) */
- mvm->queue_info[mvm_sta->reserved_queue].status =
- IWL_MVM_QUEUE_RESERVED;
+ /* Make sure reserved queue is still marked as such (if allocated) */
+ if (mvm_sta->reserved_queue != IEEE80211_INVAL_HW_QUEUE)
+ mvm->queue_info[mvm_sta->reserved_queue].status =
+ IWL_MVM_QUEUE_RESERVED;
for (i = 0; i <= IWL_MAX_TID_COUNT; i++) {
struct iwl_mvm_tid_data *tid_data = &mvm_sta->tid_data[i];
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index 63a051b..bec7d9c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -843,8 +843,10 @@
return;
IWL_DEBUG_TEMP(mvm, "Thermal zone device unregister\n");
- thermal_zone_device_unregister(mvm->tz_device.tzone);
- mvm->tz_device.tzone = NULL;
+ if (mvm->tz_device.tzone) {
+ thermal_zone_device_unregister(mvm->tz_device.tzone);
+ mvm->tz_device.tzone = NULL;
+ }
}
static void iwl_mvm_cooling_device_unregister(struct iwl_mvm *mvm)
@@ -853,8 +855,10 @@
return;
IWL_DEBUG_TEMP(mvm, "Cooling device unregister\n");
- thermal_cooling_device_unregister(mvm->cooling_dev.cdev);
- mvm->cooling_dev.cdev = NULL;
+ if (mvm->cooling_dev.cdev) {
+ thermal_cooling_device_unregister(mvm->cooling_dev.cdev);
+ mvm->cooling_dev.cdev = NULL;
+ }
}
#endif /* CONFIG_THERMAL */
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
index 691ddef..a33a06d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
@@ -92,7 +92,7 @@
struct rtl_priv *rtlpriv = rtl_priv(hw);
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
- char *fw_name = "rtlwifi/rtl8192cfwU.bin";
+ char *fw_name;
rtl8192ce_bt_reg_init(hw);
@@ -164,8 +164,13 @@
}
/* request fw */
- if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
+ if (IS_VENDOR_UMC_A_CUT(rtlhal->version) &&
+ !IS_92C_SERIAL(rtlhal->version))
+ fw_name = "rtlwifi/rtl8192cfwU.bin";
+ else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
fw_name = "rtlwifi/rtl8192cfwU_B.bin";
+ else
+ fw_name = "rtlwifi/rtl8192cfw.bin";
rtlpriv->max_fw_size = 0x4000;
pr_info("Using firmware %s\n", fw_name);
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 3ce1f7d..530586b 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -113,10 +113,10 @@
* A subset of struct net_device_stats that contains only the
* fields that are updated in netback.c for each queue.
*/
- unsigned int rx_bytes;
- unsigned int rx_packets;
- unsigned int tx_bytes;
- unsigned int tx_packets;
+ u64 rx_bytes;
+ u64 rx_packets;
+ u64 tx_bytes;
+ u64 tx_packets;
/* Additional stats used by xenvif */
unsigned long rx_gso_checksum_fixup;
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index e30ffd2..50fa169 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -221,18 +221,18 @@
{
struct xenvif *vif = netdev_priv(dev);
struct xenvif_queue *queue = NULL;
- unsigned int num_queues = vif->num_queues;
- unsigned long rx_bytes = 0;
- unsigned long rx_packets = 0;
- unsigned long tx_bytes = 0;
- unsigned long tx_packets = 0;
+ u64 rx_bytes = 0;
+ u64 rx_packets = 0;
+ u64 tx_bytes = 0;
+ u64 tx_packets = 0;
unsigned int index;
+ spin_lock(&vif->lock);
if (vif->queues == NULL)
goto out;
/* Aggregate tx and rx stats from each queue */
- for (index = 0; index < num_queues; ++index) {
+ for (index = 0; index < vif->num_queues; ++index) {
queue = &vif->queues[index];
rx_bytes += queue->stats.rx_bytes;
rx_packets += queue->stats.rx_packets;
@@ -241,6 +241,8 @@
}
out:
+ spin_unlock(&vif->lock);
+
vif->dev->stats.rx_bytes = rx_bytes;
vif->dev->stats.rx_packets = rx_packets;
vif->dev->stats.tx_bytes = tx_bytes;
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 3124eae..85b742e 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -493,11 +493,22 @@
static void backend_disconnect(struct backend_info *be)
{
if (be->vif) {
+ unsigned int queue_index;
+
xen_unregister_watchers(be->vif);
#ifdef CONFIG_DEBUG_FS
xenvif_debugfs_delif(be->vif);
#endif /* CONFIG_DEBUG_FS */
xenvif_disconnect_data(be->vif);
+ for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index)
+ xenvif_deinit_queue(&be->vif->queues[queue_index]);
+
+ spin_lock(&be->vif->lock);
+ vfree(be->vif->queues);
+ be->vif->num_queues = 0;
+ be->vif->queues = NULL;
+ spin_unlock(&be->vif->lock);
+
xenvif_disconnect_ctrl(be->vif);
}
}
@@ -1034,6 +1045,8 @@
err:
if (be->vif->num_queues > 0)
xenvif_disconnect_data(be->vif); /* Clean up existing queues */
+ for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index)
+ xenvif_deinit_queue(&be->vif->queues[queue_index]);
vfree(be->vif->queues);
be->vif->queues = NULL;
be->vif->num_queues = 0;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index a479cd9..1e4125a 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -281,6 +281,7 @@
{
RING_IDX req_prod = queue->rx.req_prod_pvt;
int notify;
+ int err = 0;
if (unlikely(!netif_carrier_ok(queue->info->netdev)))
return;
@@ -295,8 +296,10 @@
struct xen_netif_rx_request *req;
skb = xennet_alloc_one_rx_buffer(queue);
- if (!skb)
+ if (!skb) {
+ err = -ENOMEM;
break;
+ }
id = xennet_rxidx(req_prod);
@@ -320,8 +323,13 @@
queue->rx.req_prod_pvt = req_prod;
- /* Not enough requests? Try again later. */
- if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN) {
+ /* Try again later if there are not enough requests or skb allocation
+ * failed.
+ * Enough requests is quantified as the sum of newly created slots and
+ * the unconsumed slots at the backend.
+ */
+ if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN ||
+ unlikely(err)) {
mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10));
return;
}
@@ -1379,6 +1387,8 @@
for (i = 0; i < num_queues && info->queues; ++i) {
struct netfront_queue *queue = &info->queues[i];
+ del_timer_sync(&queue->rx_refill_timer);
+
if (queue->tx_irq && (queue->tx_irq == queue->rx_irq))
unbind_from_irqhandler(queue->tx_irq, queue);
if (queue->tx_irq && (queue->tx_irq != queue->rx_irq)) {
@@ -1733,7 +1743,6 @@
if (netif_running(info->netdev))
napi_disable(&queue->napi);
- del_timer_sync(&queue->rx_refill_timer);
netif_napi_del(&queue->napi);
}
@@ -1822,27 +1831,19 @@
xennet_destroy_queues(info);
err = xennet_create_queues(info, &num_queues);
- if (err < 0)
- goto destroy_ring;
+ if (err < 0) {
+ xenbus_dev_fatal(dev, err, "creating queues");
+ kfree(info->queues);
+ info->queues = NULL;
+ goto out;
+ }
/* Create shared ring, alloc event channel -- for each queue */
for (i = 0; i < num_queues; ++i) {
queue = &info->queues[i];
err = setup_netfront(dev, queue, feature_split_evtchn);
- if (err) {
- /* setup_netfront() will tidy up the current
- * queue on error, but we need to clean up
- * those already allocated.
- */
- if (i > 0) {
- rtnl_lock();
- netif_set_real_num_tx_queues(info->netdev, i);
- rtnl_unlock();
- goto destroy_ring;
- } else {
- goto out;
- }
- }
+ if (err)
+ goto destroy_ring;
}
again:
@@ -1932,9 +1933,10 @@
xenbus_transaction_end(xbt, 1);
destroy_ring:
xennet_disconnect_backend(info);
- kfree(info->queues);
- info->queues = NULL;
+ xennet_destroy_queues(info);
out:
+ unregister_netdev(info->netdev);
+ xennet_free_netdev(info->netdev);
return err;
}
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c
index eca9688..c002384 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.c
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
@@ -1629,6 +1629,28 @@
/* Skylake Xeon NTB */
+static int skx_poll_link(struct intel_ntb_dev *ndev)
+{
+ u16 reg_val;
+ int rc;
+
+ ndev->reg->db_iowrite(ndev->db_link_mask,
+ ndev->self_mmio +
+ ndev->self_reg->db_clear);
+
+ rc = pci_read_config_word(ndev->ntb.pdev,
+ SKX_LINK_STATUS_OFFSET, ®_val);
+ if (rc)
+ return 0;
+
+ if (reg_val == ndev->lnk_sta)
+ return 0;
+
+ ndev->lnk_sta = reg_val;
+
+ return 1;
+}
+
static u64 skx_db_ioread(void __iomem *mmio)
{
return ioread64(mmio);
@@ -2852,7 +2874,7 @@
};
static const struct intel_ntb_reg skx_reg = {
- .poll_link = xeon_poll_link,
+ .poll_link = skx_poll_link,
.link_is_up = xeon_link_is_up,
.db_ioread = skx_db_ioread,
.db_iowrite = skx_db_iowrite,
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index f81aa4b..02ca45f 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1802,7 +1802,7 @@
node = dev_to_node(&ndev->dev);
- free_queue = ffs(nt->qp_bitmap);
+ free_queue = ffs(nt->qp_bitmap_free);
if (!free_queue)
goto err;
@@ -2273,9 +2273,8 @@
static void __exit ntb_transport_exit(void)
{
- debugfs_remove_recursive(nt_debugfs_dir);
-
ntb_unregister_client(&ntb_transport_client);
bus_unregister(&ntb_transport_bus);
+ debugfs_remove_recursive(nt_debugfs_dir);
}
module_exit(ntb_transport_exit);
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index e75d4fd..434e1d4 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -265,6 +265,8 @@
if (dma_submit_error(cookie))
goto err_set_unmap;
+ dmaengine_unmap_put(unmap);
+
atomic_inc(&pctx->dma_sync);
dma_async_issue_pending(chan);
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 6307088..ce3e8df 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -52,17 +52,17 @@
kfree(nsblk);
}
-static struct device_type namespace_io_device_type = {
+static const struct device_type namespace_io_device_type = {
.name = "nd_namespace_io",
.release = namespace_io_release,
};
-static struct device_type namespace_pmem_device_type = {
+static const struct device_type namespace_pmem_device_type = {
.name = "nd_namespace_pmem",
.release = namespace_pmem_release,
};
-static struct device_type namespace_blk_device_type = {
+static const struct device_type namespace_blk_device_type = {
.name = "nd_namespace_blk",
.release = namespace_blk_release,
};
@@ -957,25 +957,28 @@
{
resource_size_t allocated = 0, available = 0;
struct nd_region *nd_region = to_nd_region(dev->parent);
+ struct nd_namespace_common *ndns = to_ndns(dev);
struct nd_mapping *nd_mapping;
struct nvdimm_drvdata *ndd;
struct nd_label_id label_id;
u32 flags = 0, remainder;
+ int rc, i, id = -1;
u8 *uuid = NULL;
- int rc, i;
- if (dev->driver || to_ndns(dev)->claim)
+ if (dev->driver || ndns->claim)
return -EBUSY;
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
uuid = nspm->uuid;
+ id = nspm->id;
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
uuid = nsblk->uuid;
flags = NSLABEL_FLAG_LOCAL;
+ id = nsblk->id;
}
/*
@@ -1034,20 +1037,17 @@
nd_namespace_pmem_set_resource(nd_region, nspm,
val * nd_region->ndr_mappings);
- } else if (is_namespace_blk(dev)) {
- struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
-
- /*
- * Try to delete the namespace if we deleted all of its
- * allocation, this is not the seed device for the
- * region, and it is not actively claimed by a btt
- * instance.
- */
- if (val == 0 && nd_region->ns_seed != dev
- && !nsblk->common.claim)
- nd_device_unregister(dev, ND_ASYNC);
}
+ /*
+ * Try to delete the namespace if we deleted all of its
+ * allocation, this is not the seed or 0th device for the
+ * region, and it is not actively claimed by a btt, pfn, or dax
+ * instance.
+ */
+ if (val == 0 && id != 0 && nd_region->ns_seed != dev && !ndns->claim)
+ nd_device_unregister(dev, ND_ASYNC);
+
return rc;
}
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index a2ac9e6..6c033c9 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -627,15 +627,12 @@
size = resource_size(&nsio->res);
npfns = (size - start_pad - end_trunc - SZ_8K) / SZ_4K;
if (nd_pfn->mode == PFN_MODE_PMEM) {
- unsigned long memmap_size;
-
/*
* vmemmap_populate_hugepages() allocates the memmap array in
* HPAGE_SIZE chunks.
*/
- memmap_size = ALIGN(64 * npfns, HPAGE_SIZE);
- offset = ALIGN(start + SZ_8K + memmap_size + dax_label_reserve,
- nd_pfn->align) - start;
+ offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve,
+ max(nd_pfn->align, HPAGE_SIZE)) - start;
} else if (nd_pfn->mode == PFN_MODE_RAM)
offset = ALIGN(start + SZ_8K + dax_label_reserve,
nd_pfn->align) - start;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 7282d74..5b536be 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -90,7 +90,9 @@
rc = memcpy_from_pmem(mem + off, pmem_addr, len);
kunmap_atomic(mem);
- return rc;
+ if (rc)
+ return -EIO;
+ return 0;
}
static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 2fc86dc..8a3c3e3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1106,12 +1106,7 @@
if (ret)
return ret;
- /* Checking for ctrl->tagset is a trick to avoid sleeping on module
- * load, since we only need the quirk on reset_controller. Notice
- * that the HGST device needs this delay only in firmware activation
- * procedure; unfortunately we have no (easy) way to verify this.
- */
- if ((ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY) && ctrl->tagset)
+ if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY)
msleep(NVME_QUIRK_DELAY_AMOUNT);
return nvme_wait_ready(ctrl, cap, false);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index aa0bc60..e65041c 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1654,23 +1654,22 @@
struct nvme_fc_fcp_op *op)
{
struct nvmefc_fcp_req *freq = &op->fcp_req;
- u32 map_len = nvme_map_len(rq);
enum dma_data_direction dir;
int ret;
freq->sg_cnt = 0;
- if (!map_len)
+ if (!blk_rq_payload_bytes(rq))
return 0;
freq->sg_table.sgl = freq->first_sgl;
- ret = sg_alloc_table_chained(&freq->sg_table, rq->nr_phys_segments,
- freq->sg_table.sgl);
+ ret = sg_alloc_table_chained(&freq->sg_table,
+ blk_rq_nr_phys_segments(rq), freq->sg_table.sgl);
if (ret)
return -ENOMEM;
op->nents = blk_rq_map_sg(rq->q, rq, freq->sg_table.sgl);
- WARN_ON(op->nents > rq->nr_phys_segments);
+ WARN_ON(op->nents > blk_rq_nr_phys_segments(rq));
dir = (rq_data_dir(rq) == WRITE) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl,
op->nents, dir);
@@ -1854,7 +1853,7 @@
if (ret)
return ret;
- data_len = nvme_map_len(rq);
+ data_len = blk_rq_payload_bytes(rq);
if (data_len)
io_dir = ((rq_data_dir(rq) == WRITE) ?
NVMEFC_FCP_WRITE : NVMEFC_FCP_READ);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 6377e14..aead6d0 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -225,14 +225,6 @@
return (sector >> (ns->lba_shift - 9));
}
-static inline unsigned nvme_map_len(struct request *rq)
-{
- if (req_op(rq) == REQ_OP_DISCARD)
- return sizeof(struct nvme_dsm_range);
- else
- return blk_rq_bytes(rq);
-}
-
static inline void nvme_cleanup_cmd(struct request *req)
{
if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 19beeb7..3faefab 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -306,11 +306,11 @@
return (__le64 **)(iod->sg + blk_rq_nr_phys_segments(req));
}
-static int nvme_init_iod(struct request *rq, unsigned size,
- struct nvme_dev *dev)
+static int nvme_init_iod(struct request *rq, struct nvme_dev *dev)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(rq);
int nseg = blk_rq_nr_phys_segments(rq);
+ unsigned int size = blk_rq_payload_bytes(rq);
if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
iod->sg = kmalloc(nvme_iod_alloc_size(dev, size, nseg), GFP_ATOMIC);
@@ -420,12 +420,11 @@
}
#endif
-static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req,
- int total_len)
+static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
struct dma_pool *pool;
- int length = total_len;
+ int length = blk_rq_payload_bytes(req);
struct scatterlist *sg = iod->sg;
int dma_len = sg_dma_len(sg);
u64 dma_addr = sg_dma_address(sg);
@@ -501,7 +500,7 @@
}
static int nvme_map_data(struct nvme_dev *dev, struct request *req,
- unsigned size, struct nvme_command *cmnd)
+ struct nvme_command *cmnd)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
struct request_queue *q = req->q;
@@ -519,7 +518,7 @@
DMA_ATTR_NO_WARN))
goto out;
- if (!nvme_setup_prps(dev, req, size))
+ if (!nvme_setup_prps(dev, req))
goto out_unmap;
ret = BLK_MQ_RQ_QUEUE_ERROR;
@@ -580,7 +579,6 @@
struct nvme_dev *dev = nvmeq->dev;
struct request *req = bd->rq;
struct nvme_command cmnd;
- unsigned map_len;
int ret = BLK_MQ_RQ_QUEUE_OK;
/*
@@ -600,13 +598,12 @@
if (ret != BLK_MQ_RQ_QUEUE_OK)
return ret;
- map_len = nvme_map_len(req);
- ret = nvme_init_iod(req, map_len, dev);
+ ret = nvme_init_iod(req, dev);
if (ret != BLK_MQ_RQ_QUEUE_OK)
goto out_free_cmd;
if (blk_rq_nr_phys_segments(req))
- ret = nvme_map_data(dev, req, map_len, &cmnd);
+ ret = nvme_map_data(dev, req, &cmnd);
if (ret != BLK_MQ_RQ_QUEUE_OK)
goto out_cleanup_iod;
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index f587af3..557f29b 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -981,8 +981,7 @@
}
static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
- struct request *rq, unsigned int map_len,
- struct nvme_command *c)
+ struct request *rq, struct nvme_command *c)
{
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
struct nvme_rdma_device *dev = queue->device;
@@ -1014,9 +1013,9 @@
}
if (count == 1) {
- if (rq_data_dir(rq) == WRITE &&
- map_len <= nvme_rdma_inline_data_size(queue) &&
- nvme_rdma_queue_idx(queue))
+ if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) &&
+ blk_rq_payload_bytes(rq) <=
+ nvme_rdma_inline_data_size(queue))
return nvme_rdma_map_sg_inline(queue, req, c);
if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)
@@ -1422,7 +1421,7 @@
struct request *rq)
{
if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
- struct nvme_command *cmd = (struct nvme_command *)rq->cmd;
+ struct nvme_command *cmd = nvme_req(rq)->cmd;
if (rq->cmd_type != REQ_TYPE_DRV_PRIV ||
cmd->common.opcode != nvme_fabrics_command ||
@@ -1444,7 +1443,6 @@
struct nvme_command *c = sqe->data;
bool flush = false;
struct ib_device *dev;
- unsigned int map_len;
int ret;
WARN_ON_ONCE(rq->tag < 0);
@@ -1462,8 +1460,7 @@
blk_mq_start_request(rq);
- map_len = nvme_map_len(rq);
- ret = nvme_rdma_map_data(queue, rq, map_len, c);
+ ret = nvme_rdma_map_data(queue, rq, c);
if (ret < 0) {
dev_err(queue->ctrl->ctrl.device,
"Failed to map data (%d)\n", ret);
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 6f50741..be8c800 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -631,6 +631,7 @@
{
struct nvmet_subsys *subsys = to_subsys(item);
+ nvmet_subsys_del_ctrls(subsys);
nvmet_subsys_put(subsys);
}
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index b1d66ed..fc5ba2f 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -200,7 +200,7 @@
pr_err("ctrl %d keep-alive timer (%d seconds) expired!\n",
ctrl->cntlid, ctrl->kato);
- ctrl->ops->delete_ctrl(ctrl);
+ nvmet_ctrl_fatal_error(ctrl);
}
static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
@@ -816,6 +816,9 @@
list_del(&ctrl->subsys_entry);
mutex_unlock(&subsys->lock);
+ flush_work(&ctrl->async_event_work);
+ cancel_work_sync(&ctrl->fatal_err_work);
+
ida_simple_remove(&subsys->cntlid_ida, ctrl->cntlid);
nvmet_subsys_put(subsys);
@@ -935,6 +938,16 @@
kfree(subsys);
}
+void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys)
+{
+ struct nvmet_ctrl *ctrl;
+
+ mutex_lock(&subsys->lock);
+ list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+ ctrl->ops->delete_ctrl(ctrl);
+ mutex_unlock(&subsys->lock);
+}
+
void nvmet_subsys_put(struct nvmet_subsys *subsys)
{
kref_put(&subsys->ref, nvmet_subsys_free);
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 173e842..ba57f98 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1314,7 +1314,7 @@
(struct fcnvme_ls_disconnect_rqst *)iod->rqstbuf;
struct fcnvme_ls_disconnect_acc *acc =
(struct fcnvme_ls_disconnect_acc *)iod->rspbuf;
- struct nvmet_fc_tgt_queue *queue;
+ struct nvmet_fc_tgt_queue *queue = NULL;
struct nvmet_fc_tgt_assoc *assoc;
int ret = 0;
bool del_assoc = false;
@@ -1348,7 +1348,18 @@
assoc = nvmet_fc_find_target_assoc(tgtport,
be64_to_cpu(rqst->associd.association_id));
iod->assoc = assoc;
- if (!assoc)
+ if (assoc) {
+ if (rqst->discon_cmd.scope ==
+ FCNVME_DISCONN_CONNECTION) {
+ queue = nvmet_fc_find_target_queue(tgtport,
+ be64_to_cpu(
+ rqst->discon_cmd.id));
+ if (!queue) {
+ nvmet_fc_tgt_a_put(assoc);
+ ret = VERR_NO_CONN;
+ }
+ }
+ } else
ret = VERR_NO_ASSOC;
}
@@ -1373,21 +1384,18 @@
FCNVME_LS_DISCONNECT);
- if (rqst->discon_cmd.scope == FCNVME_DISCONN_CONNECTION) {
- queue = nvmet_fc_find_target_queue(tgtport,
- be64_to_cpu(rqst->discon_cmd.id));
- if (queue) {
- int qid = queue->qid;
+ /* are we to delete a Connection ID (queue) */
+ if (queue) {
+ int qid = queue->qid;
- nvmet_fc_delete_target_queue(queue);
+ nvmet_fc_delete_target_queue(queue);
- /* release the get taken by find_target_queue */
- nvmet_fc_tgt_q_put(queue);
+ /* release the get taken by find_target_queue */
+ nvmet_fc_tgt_q_put(queue);
- /* tear association down if io queue terminated */
- if (!qid)
- del_assoc = true;
- }
+ /* tear association down if io queue terminated */
+ if (!qid)
+ del_assoc = true;
}
/* release get taken in nvmet_fc_find_target_assoc */
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 23d5eb1..cc7ad06 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -282,6 +282,7 @@
struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
enum nvme_subsys_type type);
void nvmet_subsys_put(struct nvmet_subsys *subsys);
+void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys);
struct nvmet_ns *nvmet_find_namespace(struct nvmet_ctrl *ctrl, __le32 nsid);
void nvmet_put_namespace(struct nvmet_ns *ns);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 8c3760a..6099022 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -438,6 +438,10 @@
{
struct ib_recv_wr *bad_wr;
+ ib_dma_sync_single_for_device(ndev->device,
+ cmd->sge[0].addr, cmd->sge[0].length,
+ DMA_FROM_DEVICE);
+
if (ndev->srq)
return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
@@ -538,6 +542,11 @@
first_wr = &rsp->send_wr;
nvmet_rdma_post_recv(rsp->queue->dev, rsp->cmd);
+
+ ib_dma_sync_single_for_device(rsp->queue->dev->device,
+ rsp->send_sge.addr, rsp->send_sge.length,
+ DMA_TO_DEVICE);
+
if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) {
pr_err("sending cmd response failed\n");
nvmet_rdma_release_rsp(rsp);
@@ -698,6 +707,14 @@
cmd->n_rdma = 0;
cmd->req.port = queue->port;
+
+ ib_dma_sync_single_for_cpu(queue->dev->device,
+ cmd->cmd->sge[0].addr, cmd->cmd->sge[0].length,
+ DMA_FROM_DEVICE);
+ ib_dma_sync_single_for_cpu(queue->dev->device,
+ cmd->send_sge.addr, cmd->send_sge.length,
+ DMA_TO_DEVICE);
+
if (!nvmet_req_init(&cmd->req, &queue->nvme_cq,
&queue->nvme_sq, &nvmet_rdma_ops))
return;
diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c
index dd6d4cc..3858b87 100644
--- a/drivers/parport/parport_gsc.c
+++ b/drivers/parport/parport_gsc.c
@@ -293,7 +293,7 @@
p->irq = PARPORT_IRQ_NONE;
}
if (p->irq != PARPORT_IRQ_NONE) {
- printk(", irq %d", p->irq);
+ pr_cont(", irq %d", p->irq);
if (p->dma == PARPORT_DMA_AUTO) {
p->dma = PARPORT_DMA_NONE;
@@ -303,8 +303,8 @@
is mandatory (see above) */
p->dma = PARPORT_DMA_NONE;
- printk(" [");
-#define printmode(x) {if(p->modes&PARPORT_MODE_##x){printk("%s%s",f?",":"",#x);f++;}}
+ pr_cont(" [");
+#define printmode(x) {if(p->modes&PARPORT_MODE_##x){pr_cont("%s%s",f?",":"",#x);f++;}}
{
int f = 0;
printmode(PCSPP);
@@ -315,7 +315,7 @@
// printmode(DMA);
}
#undef printmode
- printk("]\n");
+ pr_cont("]\n");
if (p->irq != PARPORT_IRQ_NONE) {
if (request_irq (p->irq, parport_irq_handler,
diff --git a/drivers/pci/host/pci-xgene-msi.c b/drivers/pci/host/pci-xgene-msi.c
index 1f38d08..f1b633b 100644
--- a/drivers/pci/host/pci-xgene-msi.c
+++ b/drivers/pci/host/pci-xgene-msi.c
@@ -517,7 +517,7 @@
rc = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "pci/xgene:online",
xgene_msi_hwirq_alloc, NULL);
- if (rc)
+ if (rc < 0)
goto err_cpuhp;
pci_xgene_online = rc;
rc = cpuhp_setup_state(CPUHP_PCI_XGENE_DEAD, "pci/xgene:dead", NULL,
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index bed1999..af8f6e9 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -807,11 +807,6 @@
{
u32 val;
- /* get iATU unroll support */
- pp->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pp);
- dev_dbg(pp->dev, "iATU unroll: %s\n",
- pp->iatu_unroll_enabled ? "enabled" : "disabled");
-
/* set the number of lanes */
val = dw_pcie_readl_rc(pp, PCIE_PORT_LINK_CONTROL);
val &= ~PORT_LINK_MODE_MASK;
@@ -882,6 +877,11 @@
* we should not program the ATU here.
*/
if (!pp->ops->rd_other_conf) {
+ /* get iATU unroll support */
+ pp->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pp);
+ dev_dbg(pp->dev, "iATU unroll: %s\n",
+ pp->iatu_unroll_enabled ? "enabled" : "disabled");
+
dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
PCIE_ATU_TYPE_MEM, pp->mem_base,
pp->mem_bus_addr, pp->mem_size);
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 10c9c0b..ec0b4c1 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -31,7 +31,6 @@
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
-#include <linux/pm_runtime.h>
#include <linux/pci.h>
#include "../pci.h"
#include "pciehp.h"
@@ -99,7 +98,6 @@
pciehp_green_led_blink(p_slot);
/* Check link training status */
- pm_runtime_get_sync(&ctrl->pcie->port->dev);
retval = pciehp_check_link_status(ctrl);
if (retval) {
ctrl_err(ctrl, "Failed to check link status\n");
@@ -120,14 +118,12 @@
if (retval != -EEXIST)
goto err_exit;
}
- pm_runtime_put(&ctrl->pcie->port->dev);
pciehp_green_led_on(p_slot);
pciehp_set_attention_status(p_slot, 0);
return 0;
err_exit:
- pm_runtime_put(&ctrl->pcie->port->dev);
set_slot_off(ctrl, p_slot);
return retval;
}
@@ -141,9 +137,7 @@
int retval;
struct controller *ctrl = p_slot->ctrl;
- pm_runtime_get_sync(&ctrl->pcie->port->dev);
retval = pciehp_unconfigure_device(p_slot);
- pm_runtime_put(&ctrl->pcie->port->dev);
if (retval)
return retval;
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 50c5003..7f73bac 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1206,6 +1206,16 @@
if (flags & PCI_IRQ_AFFINITY) {
if (!affd)
affd = &msi_default_affd;
+
+ if (affd->pre_vectors + affd->post_vectors > min_vecs)
+ return -EINVAL;
+
+ /*
+ * If there aren't any vectors left after applying the pre/post
+ * vectors don't bother with assigning affinity.
+ */
+ if (affd->pre_vectors + affd->post_vectors == min_vecs)
+ affd = NULL;
} else {
if (WARN_ON(affd))
affd = NULL;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a881c0d..7904d02 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2241,10 +2241,13 @@
return false;
/*
- * Hotplug ports handled by firmware in System Management Mode
+ * Hotplug interrupts cannot be delivered if the link is down,
+ * so parents of a hotplug port must stay awake. In addition,
+ * hotplug ports handled by firmware in System Management Mode
* may not be put into D3 by the OS (Thunderbolt on non-Macs).
+ * For simplicity, disallow in general for now.
*/
- if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge))
+ if (bridge->is_hotplug_bridge)
return false;
if (pci_bridge_d3_force)
@@ -2276,10 +2279,7 @@
!pci_pme_capable(dev, PCI_D3cold)) ||
/* If it is a bridge it must be allowed to go to D3. */
- !pci_power_manageable(dev) ||
-
- /* Hotplug interrupts cannot be delivered if the link is down. */
- dev->is_hotplug_bridge)
+ !pci_power_manageable(dev))
*d3cold_ok = false;
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 17ac1dc..3dd8bcb 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -532,25 +532,32 @@
link = kzalloc(sizeof(*link), GFP_KERNEL);
if (!link)
return NULL;
+
INIT_LIST_HEAD(&link->sibling);
INIT_LIST_HEAD(&link->children);
INIT_LIST_HEAD(&link->link);
link->pdev = pdev;
- if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) {
+
+ /*
+ * Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe
+ * hierarchies.
+ */
+ if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT ||
+ pci_pcie_type(pdev) == PCI_EXP_TYPE_PCIE_BRIDGE) {
+ link->root = link;
+ } else {
struct pcie_link_state *parent;
+
parent = pdev->bus->parent->self->link_state;
if (!parent) {
kfree(link);
return NULL;
}
+
link->parent = parent;
+ link->root = link->parent->root;
list_add(&link->link, &parent->children);
}
- /* Setup a pointer to the root port link */
- if (!link->parent)
- link->root = link;
- else
- link->root = link->parent->root;
list_add(&link->sibling, &link_list);
pdev->link_state = link;
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 7175293..2dd1c68 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -433,6 +433,17 @@
return 0;
}
+/**
+ * pcie_pme_remove - Prepare PCIe PME service device for removal.
+ * @srv - PCIe service device to remove.
+ */
+static void pcie_pme_remove(struct pcie_device *srv)
+{
+ pcie_pme_suspend(srv);
+ free_irq(srv->irq, srv);
+ kfree(get_service_data(srv));
+}
+
static struct pcie_port_service_driver pcie_pme_driver = {
.name = "pcie_pme",
.port_type = PCI_EXP_TYPE_ROOT_PORT,
@@ -441,6 +452,7 @@
.probe = pcie_pme_probe,
.suspend = pcie_pme_suspend,
.resume = pcie_pme_resume,
+ .remove = pcie_pme_remove,
};
/**
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index e164b5c..204960e 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1169,6 +1169,7 @@
pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
if (!pos)
return;
+
pdev->pcie_cap = pos;
pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, ®16);
pdev->pcie_flags_reg = reg16;
@@ -1176,13 +1177,14 @@
pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD;
/*
- * A Root Port is always the upstream end of a Link. No PCIe
- * component has two Links. Two Links are connected by a Switch
- * that has a Port on each Link and internal logic to connect the
- * two Ports.
+ * A Root Port or a PCI-to-PCIe bridge is always the upstream end
+ * of a Link. No PCIe component has two Links. Two Links are
+ * connected by a Switch that has a Port on each Link and internal
+ * logic to connect the two Ports.
*/
type = pci_pcie_type(pdev);
- if (type == PCI_EXP_TYPE_ROOT_PORT)
+ if (type == PCI_EXP_TYPE_ROOT_PORT ||
+ type == PCI_EXP_TYPE_PCIE_BRIDGE)
pdev->has_secondary_link = 1;
else if (type == PCI_EXP_TYPE_UPSTREAM ||
type == PCI_EXP_TYPE_DOWNSTREAM) {
diff --git a/drivers/pinctrl/berlin/berlin-bg4ct.c b/drivers/pinctrl/berlin/berlin-bg4ct.c
index 0917204..c617ec4 100644
--- a/drivers/pinctrl/berlin/berlin-bg4ct.c
+++ b/drivers/pinctrl/berlin/berlin-bg4ct.c
@@ -217,7 +217,7 @@
BERLIN_PINCTRL_GROUP("SCRD0_CRD_PRES", 0xc, 0x3, 0x15,
BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO20 */
BERLIN_PINCTRL_FUNCTION(0x1, "scrd0"), /* crd pres */
- BERLIN_PINCTRL_FUNCTION(0x1, "sd1a")), /* DAT3 */
+ BERLIN_PINCTRL_FUNCTION(0x3, "sd1a")), /* DAT3 */
BERLIN_PINCTRL_GROUP("SPI1_SS0n", 0xc, 0x3, 0x18,
BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS0n */
BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO37 */
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 3730063..d94aef1 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -731,16 +731,23 @@
int reg)
{
struct byt_community *comm = byt_get_community(vg, offset);
- u32 reg_offset = 0;
+ u32 reg_offset;
if (!comm)
return NULL;
offset -= comm->pin_base;
- if (reg == BYT_INT_STAT_REG)
+ switch (reg) {
+ case BYT_INT_STAT_REG:
reg_offset = (offset / 32) * 4;
- else
+ break;
+ case BYT_DEBOUNCE_REG:
+ reg_offset = 0;
+ break;
+ default:
reg_offset = comm->pad_map[offset] * 16;
+ break;
+ }
return comm->reg_base + reg_offset + reg;
}
@@ -1092,6 +1099,7 @@
enum pin_config_param param = pinconf_to_config_param(*config);
void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
unsigned long flags;
u32 conf, pull, val, debounce;
u16 arg = 0;
@@ -1128,7 +1136,7 @@
return -EINVAL;
raw_spin_lock_irqsave(&vg->lock, flags);
- debounce = readl(byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG));
+ debounce = readl(db_reg);
raw_spin_unlock_irqrestore(&vg->lock, flags);
switch (debounce & BYT_DEBOUNCE_PULSE_MASK) {
@@ -1176,6 +1184,7 @@
unsigned int param, arg;
void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
unsigned long flags;
u32 conf, val, debounce;
int i, ret = 0;
@@ -1238,36 +1247,44 @@
break;
case PIN_CONFIG_INPUT_DEBOUNCE:
- debounce = readl(byt_gpio_reg(vg, offset,
- BYT_DEBOUNCE_REG));
- conf &= ~BYT_DEBOUNCE_PULSE_MASK;
+ debounce = readl(db_reg);
+ debounce &= ~BYT_DEBOUNCE_PULSE_MASK;
+
+ if (arg)
+ conf |= BYT_DEBOUNCE_EN;
+ else
+ conf &= ~BYT_DEBOUNCE_EN;
switch (arg) {
case 375:
- conf |= BYT_DEBOUNCE_PULSE_375US;
+ debounce |= BYT_DEBOUNCE_PULSE_375US;
break;
case 750:
- conf |= BYT_DEBOUNCE_PULSE_750US;
+ debounce |= BYT_DEBOUNCE_PULSE_750US;
break;
case 1500:
- conf |= BYT_DEBOUNCE_PULSE_1500US;
+ debounce |= BYT_DEBOUNCE_PULSE_1500US;
break;
case 3000:
- conf |= BYT_DEBOUNCE_PULSE_3MS;
+ debounce |= BYT_DEBOUNCE_PULSE_3MS;
break;
case 6000:
- conf |= BYT_DEBOUNCE_PULSE_6MS;
+ debounce |= BYT_DEBOUNCE_PULSE_6MS;
break;
case 12000:
- conf |= BYT_DEBOUNCE_PULSE_12MS;
+ debounce |= BYT_DEBOUNCE_PULSE_12MS;
break;
case 24000:
- conf |= BYT_DEBOUNCE_PULSE_24MS;
+ debounce |= BYT_DEBOUNCE_PULSE_24MS;
break;
default:
- ret = -EINVAL;
+ if (arg)
+ ret = -EINVAL;
+ break;
}
+ if (!ret)
+ writel(debounce, db_reg);
break;
default:
ret = -ENOTSUPP;
@@ -1606,7 +1623,9 @@
continue;
}
+ raw_spin_lock(&vg->lock);
pending = readl(reg);
+ raw_spin_unlock(&vg->lock);
for_each_set_bit(pin, &pending, 32) {
virq = irq_find_mapping(vg->chip.irqdomain, base + pin);
generic_handle_irq(virq);
@@ -1617,6 +1636,8 @@
static void byt_gpio_irq_init_hw(struct byt_gpio *vg)
{
+ struct gpio_chip *gc = &vg->chip;
+ struct device *dev = &vg->pdev->dev;
void __iomem *reg;
u32 base, value;
int i;
@@ -1638,10 +1659,12 @@
}
value = readl(reg);
- if ((value & BYT_PIN_MUX) == byt_get_gpio_mux(vg, i) &&
- !(value & BYT_DIRECT_IRQ_EN)) {
+ if (value & BYT_DIRECT_IRQ_EN) {
+ clear_bit(i, gc->irq_valid_mask);
+ dev_dbg(dev, "excluding GPIO %d from IRQ domain\n", i);
+ } else if ((value & BYT_PIN_MUX) == byt_get_gpio_mux(vg, i)) {
byt_gpio_clear_triggering(vg, i);
- dev_dbg(&vg->pdev->dev, "disabling GPIO %d\n", i);
+ dev_dbg(dev, "disabling GPIO %d\n", i);
}
}
@@ -1680,6 +1703,7 @@
gc->can_sleep = false;
gc->parent = &vg->pdev->dev;
gc->ngpio = vg->soc_data->npins;
+ gc->irq_need_valid_mask = true;
#ifdef CONFIG_PM_SLEEP
vg->saved_context = devm_kcalloc(&vg->pdev->dev, gc->ngpio,
diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c
index 59cb7a6..901b356 100644
--- a/drivers/pinctrl/intel/pinctrl-broxton.c
+++ b/drivers/pinctrl/intel/pinctrl-broxton.c
@@ -19,7 +19,7 @@
#define BXT_PAD_OWN 0x020
#define BXT_HOSTSW_OWN 0x080
-#define BXT_PADCFGLOCK 0x090
+#define BXT_PADCFGLOCK 0x060
#define BXT_GPI_IE 0x110
#define BXT_COMMUNITY(s, e) \
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 1e13967..6df35dc 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -353,6 +353,21 @@
return 0;
}
+static void __intel_gpio_set_direction(void __iomem *padcfg0, bool input)
+{
+ u32 value;
+
+ value = readl(padcfg0);
+ if (input) {
+ value &= ~PADCFG0_GPIORXDIS;
+ value |= PADCFG0_GPIOTXDIS;
+ } else {
+ value &= ~PADCFG0_GPIOTXDIS;
+ value |= PADCFG0_GPIORXDIS;
+ }
+ writel(value, padcfg0);
+}
+
static int intel_gpio_request_enable(struct pinctrl_dev *pctldev,
struct pinctrl_gpio_range *range,
unsigned pin)
@@ -375,11 +390,11 @@
/* Disable SCI/SMI/NMI generation */
value &= ~(PADCFG0_GPIROUTIOXAPIC | PADCFG0_GPIROUTSCI);
value &= ~(PADCFG0_GPIROUTSMI | PADCFG0_GPIROUTNMI);
- /* Disable TX buffer and enable RX (this will be input) */
- value &= ~PADCFG0_GPIORXDIS;
- value |= PADCFG0_GPIOTXDIS;
writel(value, padcfg0);
+ /* Disable TX buffer and enable RX (this will be input) */
+ __intel_gpio_set_direction(padcfg0, true);
+
raw_spin_unlock_irqrestore(&pctrl->lock, flags);
return 0;
@@ -392,18 +407,11 @@
struct intel_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
void __iomem *padcfg0;
unsigned long flags;
- u32 value;
raw_spin_lock_irqsave(&pctrl->lock, flags);
padcfg0 = intel_get_padcfg(pctrl, pin, PADCFG0);
-
- value = readl(padcfg0);
- if (input)
- value |= PADCFG0_GPIOTXDIS;
- else
- value &= ~PADCFG0_GPIOTXDIS;
- writel(value, padcfg0);
+ __intel_gpio_set_direction(padcfg0, input);
raw_spin_unlock_irqrestore(&pctrl->lock, flags);
diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c
index b218961..4d4ef42 100644
--- a/drivers/pinctrl/intel/pinctrl-merrifield.c
+++ b/drivers/pinctrl/intel/pinctrl-merrifield.c
@@ -794,6 +794,9 @@
unsigned int i;
int ret;
+ if (!mrfld_buf_available(mp, pin))
+ return -ENOTSUPP;
+
for (i = 0; i < nconfigs; i++) {
switch (pinconf_to_config_param(configs[i])) {
case PIN_CONFIG_BIAS_DISABLE:
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
index c3928aa..e0bca4d 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
@@ -253,9 +253,8 @@
static const unsigned int uart_rx_ao_a_pins[] = { PIN(GPIOAO_1, 0) };
static const unsigned int uart_cts_ao_a_pins[] = { PIN(GPIOAO_2, 0) };
static const unsigned int uart_rts_ao_a_pins[] = { PIN(GPIOAO_3, 0) };
-static const unsigned int uart_tx_ao_b_pins[] = { PIN(GPIOAO_0, 0) };
-static const unsigned int uart_rx_ao_b_pins[] = { PIN(GPIOAO_1, 0),
- PIN(GPIOAO_5, 0) };
+static const unsigned int uart_tx_ao_b_pins[] = { PIN(GPIOAO_4, 0) };
+static const unsigned int uart_rx_ao_b_pins[] = { PIN(GPIOAO_5, 0) };
static const unsigned int uart_cts_ao_b_pins[] = { PIN(GPIOAO_2, 0) };
static const unsigned int uart_rts_ao_b_pins[] = { PIN(GPIOAO_3, 0) };
@@ -498,7 +497,7 @@
GPIO_GROUP(GPIOAO_13, 0),
/* bank AO */
- GROUP(uart_tx_ao_b, 0, 26),
+ GROUP(uart_tx_ao_b, 0, 24),
GROUP(uart_rx_ao_b, 0, 25),
GROUP(uart_tx_ao_a, 0, 12),
GROUP(uart_rx_ao_a, 0, 11),
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxl.c b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
index 25694f7..b69743b 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxl.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
@@ -214,9 +214,8 @@
static const unsigned int uart_rx_ao_a_pins[] = { PIN(GPIOAO_1, 0) };
static const unsigned int uart_cts_ao_a_pins[] = { PIN(GPIOAO_2, 0) };
static const unsigned int uart_rts_ao_a_pins[] = { PIN(GPIOAO_3, 0) };
-static const unsigned int uart_tx_ao_b_pins[] = { PIN(GPIOAO_0, 0) };
-static const unsigned int uart_rx_ao_b_pins[] = { PIN(GPIOAO_1, 0),
- PIN(GPIOAO_5, 0) };
+static const unsigned int uart_tx_ao_b_pins[] = { PIN(GPIOAO_4, 0) };
+static const unsigned int uart_rx_ao_b_pins[] = { PIN(GPIOAO_5, 0) };
static const unsigned int uart_cts_ao_b_pins[] = { PIN(GPIOAO_2, 0) };
static const unsigned int uart_rts_ao_b_pins[] = { PIN(GPIOAO_3, 0) };
@@ -409,7 +408,7 @@
GPIO_GROUP(GPIOAO_9, 0),
/* bank AO */
- GROUP(uart_tx_ao_b, 0, 26),
+ GROUP(uart_tx_ao_b, 0, 24),
GROUP(uart_rx_ao_b, 0, 25),
GROUP(uart_tx_ao_a, 0, 12),
GROUP(uart_rx_ao_a, 0, 11),
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index c9a1469..537b520 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -202,6 +202,8 @@
i = 128;
pin_num = AMD_GPIO_PINS_BANK2 + i;
break;
+ default:
+ return;
}
for (; i < pin_num; i++) {
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 0eb51e3..207a8de 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -564,8 +564,7 @@
val = arg / 10 - 1;
break;
case PIN_CONFIG_BIAS_DISABLE:
- val = 0;
- break;
+ continue;
case PIN_CONFIG_BIAS_PULL_UP:
if (arg == 0)
return -EINVAL;
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
index aa8bd97..9668633 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
@@ -561,7 +561,7 @@
0, 0, 0, 0};
static const unsigned ether_rmii_pins[] = {30, 31, 32, 33, 34, 35, 36, 37, 39,
41, 42, 45};
-static const int ether_rmii_muxvals[] = {1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1};
+static const int ether_rmii_muxvals[] = {0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1};
static const unsigned i2c0_pins[] = {63, 64};
static const int i2c0_muxvals[] = {0, 0};
static const unsigned i2c1_pins[] = {65, 66};
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 410741a..f46ece2 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -813,6 +813,7 @@
case 8:
case 7:
case 6:
+ case 1:
ideapad_input_report(priv, vpc_bit);
break;
case 5:
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index 1fc0de8..3617705 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -77,7 +77,7 @@
input_set_capability(input, EV_KEY, KEY_POWER);
- error = request_threaded_irq(irq, NULL, mfld_pb_isr, 0,
+ error = request_threaded_irq(irq, NULL, mfld_pb_isr, IRQF_ONESHOT,
DRIVER_NAME, input);
if (error) {
dev_err(&pdev->dev, "Unable to request irq %d for mfld power"
diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c
index 97b4c3a..25f15df 100644
--- a/drivers/platform/x86/mlx-platform.c
+++ b/drivers/platform/x86/mlx-platform.c
@@ -326,7 +326,7 @@
return 0;
fail_platform_mux_register:
- for (i--; i > 0 ; i--)
+ while (--i >= 0)
platform_device_unregister(priv->pdev_mux[i]);
platform_device_unregister(priv->pdev_i2c);
fail_alloc:
diff --git a/drivers/platform/x86/surface3-wmi.c b/drivers/platform/x86/surface3-wmi.c
index cbf4d83..25b1769 100644
--- a/drivers/platform/x86/surface3-wmi.c
+++ b/drivers/platform/x86/surface3-wmi.c
@@ -139,7 +139,7 @@
static int s3_wmi_check_platform_device(struct device *dev, void *data)
{
- struct acpi_device *adev, *ts_adev;
+ struct acpi_device *adev, *ts_adev = NULL;
acpi_handle handle;
acpi_status status;
@@ -244,13 +244,11 @@
return 0;
}
-#ifdef CONFIG_PM
-static int s3_wmi_resume(struct device *dev)
+static int __maybe_unused s3_wmi_resume(struct device *dev)
{
s3_wmi_send_lid_state();
return 0;
}
-#endif
static SIMPLE_DEV_PM_OPS(s3_wmi_pm, NULL, s3_wmi_resume);
static struct platform_driver s3_wmi_driver = {
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index abeb772..b8caccc 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -32,7 +32,7 @@
config POWER_RESET_AT91_SAMA5D2_SHDWC
tristate "Atmel AT91 SAMA5D2-Compatible shutdown controller driver"
- depends on ARCH_AT91 || COMPILE_TEST
+ depends on ARCH_AT91
default SOC_SAMA5
help
This driver supports the alternate shutdown controller for some Atmel
diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c
index a85dd4d..c6c3bee 100644
--- a/drivers/power/reset/at91-poweroff.c
+++ b/drivers/power/reset/at91-poweroff.c
@@ -14,9 +14,12 @@
#include <linux/io.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_address.h>
#include <linux/platform_device.h>
#include <linux/printk.h>
+#include <soc/at91/at91sam9_ddrsdr.h>
+
#define AT91_SHDW_CR 0x00 /* Shut Down Control Register */
#define AT91_SHDW_SHDW BIT(0) /* Shut Down command */
#define AT91_SHDW_KEY (0xa5 << 24) /* KEY Password */
@@ -50,6 +53,7 @@
static void __iomem *at91_shdwc_base;
static struct clk *sclk;
+static void __iomem *mpddrc_base;
static void __init at91_wakeup_status(void)
{
@@ -73,6 +77,29 @@
writel(AT91_SHDW_KEY | AT91_SHDW_SHDW, at91_shdwc_base + AT91_SHDW_CR);
}
+static void at91_lpddr_poweroff(void)
+{
+ asm volatile(
+ /* Align to cache lines */
+ ".balign 32\n\t"
+
+ /* Ensure AT91_SHDW_CR is in the TLB by reading it */
+ " ldr r6, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+ /* Power down SDRAM0 */
+ " str %1, [%0, #" __stringify(AT91_DDRSDRC_LPR) "]\n\t"
+ /* Shutdown CPU */
+ " str %3, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+ " b .\n\t"
+ :
+ : "r" (mpddrc_base),
+ "r" cpu_to_le32(AT91_DDRSDRC_LPDDR2_PWOFF),
+ "r" (at91_shdwc_base),
+ "r" cpu_to_le32(AT91_SHDW_KEY | AT91_SHDW_SHDW)
+ : "r0");
+}
+
static int at91_poweroff_get_wakeup_mode(struct device_node *np)
{
const char *pm;
@@ -124,6 +151,8 @@
static int __init at91_poweroff_probe(struct platform_device *pdev)
{
struct resource *res;
+ struct device_node *np;
+ u32 ddr_type;
int ret;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -150,12 +179,30 @@
pm_power_off = at91_poweroff;
+ np = of_find_compatible_node(NULL, NULL, "atmel,sama5d3-ddramc");
+ if (!np)
+ return 0;
+
+ mpddrc_base = of_iomap(np, 0);
+ of_node_put(np);
+
+ if (!mpddrc_base)
+ return 0;
+
+ ddr_type = readl(mpddrc_base + AT91_DDRSDRC_MDR) & AT91_DDRSDRC_MD;
+ if ((ddr_type == AT91_DDRSDRC_MD_LPDDR2) ||
+ (ddr_type == AT91_DDRSDRC_MD_LPDDR3))
+ pm_power_off = at91_lpddr_poweroff;
+ else
+ iounmap(mpddrc_base);
+
return 0;
}
static int __exit at91_poweroff_remove(struct platform_device *pdev)
{
- if (pm_power_off == at91_poweroff)
+ if (pm_power_off == at91_poweroff ||
+ pm_power_off == at91_lpddr_poweroff)
pm_power_off = NULL;
clk_disable_unprepare(sclk);
@@ -163,6 +210,11 @@
return 0;
}
+static const struct of_device_id at91_ramc_of_match[] = {
+ { .compatible = "atmel,sama5d3-ddramc", },
+ { /* sentinel */ }
+};
+
static const struct of_device_id at91_poweroff_of_match[] = {
{ .compatible = "atmel,at91sam9260-shdwc", },
{ .compatible = "atmel,at91sam9rl-shdwc", },
diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c
index 568580c..b99769f 100644
--- a/drivers/power/reset/at91-reset.c
+++ b/drivers/power/reset/at91-reset.c
@@ -134,6 +134,15 @@
return NOTIFY_DONE;
}
+static int samx7_restart(struct notifier_block *this, unsigned long mode,
+ void *cmd)
+{
+ writel(cpu_to_le32(AT91_RSTC_KEY | AT91_RSTC_PROCRST),
+ at91_rstc_base);
+
+ return NOTIFY_DONE;
+}
+
static void __init at91_reset_status(struct platform_device *pdev)
{
u32 reg = readl(at91_rstc_base + AT91_RSTC_SR);
@@ -173,6 +182,7 @@
{ .compatible = "atmel,at91sam9260-rstc", .data = at91sam9260_restart },
{ .compatible = "atmel,at91sam9g45-rstc", .data = at91sam9g45_restart },
{ .compatible = "atmel,sama5d3-rstc", .data = sama5d3_restart },
+ { .compatible = "atmel,samx7-rstc", .data = samx7_restart },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, at91_reset_of_match);
@@ -238,20 +248,12 @@
return 0;
}
-static const struct platform_device_id at91_reset_plat_match[] = {
- { "at91-sam9260-reset", (unsigned long)at91sam9260_restart },
- { "at91-sam9g45-reset", (unsigned long)at91sam9g45_restart },
- { /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(platform, at91_reset_plat_match);
-
static struct platform_driver at91_reset_driver = {
.remove = __exit_p(at91_reset_remove),
.driver = {
.name = "at91-reset",
.of_match_table = at91_reset_of_match,
},
- .id_table = at91_reset_plat_match,
};
module_platform_driver_probe(at91_reset_driver, at91_reset_probe);
diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c
index 8a5ac97..90b0b5a 100644
--- a/drivers/power/reset/at91-sama5d2_shdwc.c
+++ b/drivers/power/reset/at91-sama5d2_shdwc.c
@@ -22,9 +22,12 @@
#include <linux/io.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_address.h>
#include <linux/platform_device.h>
#include <linux/printk.h>
+#include <soc/at91/at91sam9_ddrsdr.h>
+
#define SLOW_CLOCK_FREQ 32768
#define AT91_SHDW_CR 0x00 /* Shut Down Control Register */
@@ -75,6 +78,7 @@
*/
static struct shdwc *at91_shdwc;
static struct clk *sclk;
+static void __iomem *mpddrc_base;
static const unsigned long long sdwc_dbc_period[] = {
0, 3, 32, 512, 4096, 32768,
@@ -108,6 +112,29 @@
at91_shdwc->at91_shdwc_base + AT91_SHDW_CR);
}
+static void at91_lpddr_poweroff(void)
+{
+ asm volatile(
+ /* Align to cache lines */
+ ".balign 32\n\t"
+
+ /* Ensure AT91_SHDW_CR is in the TLB by reading it */
+ " ldr r6, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+ /* Power down SDRAM0 */
+ " str %1, [%0, #" __stringify(AT91_DDRSDRC_LPR) "]\n\t"
+ /* Shutdown CPU */
+ " str %3, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+ " b .\n\t"
+ :
+ : "r" (mpddrc_base),
+ "r" cpu_to_le32(AT91_DDRSDRC_LPDDR2_PWOFF),
+ "r" (at91_shdwc->at91_shdwc_base),
+ "r" cpu_to_le32(AT91_SHDW_KEY | AT91_SHDW_SHDW)
+ : "r0");
+}
+
static u32 at91_shdwc_debouncer_value(struct platform_device *pdev,
u32 in_period_us)
{
@@ -212,6 +239,8 @@
{
struct resource *res;
const struct of_device_id *match;
+ struct device_node *np;
+ u32 ddr_type;
int ret;
if (!pdev->dev.of_node)
@@ -249,6 +278,23 @@
pm_power_off = at91_poweroff;
+ np = of_find_compatible_node(NULL, NULL, "atmel,sama5d3-ddramc");
+ if (!np)
+ return 0;
+
+ mpddrc_base = of_iomap(np, 0);
+ of_node_put(np);
+
+ if (!mpddrc_base)
+ return 0;
+
+ ddr_type = readl(mpddrc_base + AT91_DDRSDRC_MDR) & AT91_DDRSDRC_MD;
+ if ((ddr_type == AT91_DDRSDRC_MD_LPDDR2) ||
+ (ddr_type == AT91_DDRSDRC_MD_LPDDR3))
+ pm_power_off = at91_lpddr_poweroff;
+ else
+ iounmap(mpddrc_base);
+
return 0;
}
@@ -256,7 +302,8 @@
{
struct shdwc *shdw = platform_get_drvdata(pdev);
- if (pm_power_off == at91_poweroff)
+ if (pm_power_off == at91_poweroff ||
+ pm_power_off == at91_lpddr_poweroff)
pm_power_off = NULL;
/* Reset values to disable wake-up features */
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index 76806a0..da54ac8 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -164,6 +164,12 @@
Say Y to include support for SBS battery driver for SBS-compliant
gas gauges.
+config CHARGER_SBS
+ tristate "SBS Compliant charger"
+ depends on I2C
+ help
+ Say Y to include support for SBS compilant battery chargers.
+
config BATTERY_BQ27XXX
tristate "BQ27xxx battery driver"
help
@@ -214,6 +220,18 @@
This driver can also be built as a module. If so, the module will be
called da9150-fg.
+config CHARGER_AXP20X
+ tristate "X-Powers AXP20X and AXP22X AC power supply driver"
+ depends on MFD_AXP20X
+ depends on AXP20X_ADC
+ depends on IIO
+ help
+ Say Y here to enable support for X-Powers AXP20X and AXP22X PMICs' AC
+ power supply.
+
+ This driver can also be built as a module. If so, the module will be
+ called axp20x_ac_power.
+
config AXP288_CHARGER
tristate "X-Powers AXP288 Charger"
depends on MFD_AXP20X && EXTCON_AXP288
@@ -292,13 +310,6 @@
This driver can be build as a module. If so, the module will be
called jz4740-battery.
-config BATTERY_INTEL_MID
- tristate "Battery driver for Intel MID platforms"
- depends on INTEL_SCU_IPC && SPI
- help
- Say Y here to enable the battery driver on Intel MID
- platforms.
-
config BATTERY_RX51
tristate "Nokia RX-51 (N900) battery driver"
depends on TWL4030_MADC
@@ -370,6 +381,16 @@
Say Y to enable support for the battery charger control sysfs and
platform data of MAX14577/77836 MUICs.
+config CHARGER_DETECTOR_MAX14656
+ tristate "Maxim MAX14656 USB charger detector"
+ depends on I2C
+ depends on OF
+ help
+ Say Y to enable support for the Maxim MAX14656 USB charger detector.
+ The device is compliant with the USB Battery Charging Specification
+ Revision 1.2 and can be found e.g. in Kindle 4/5th generation
+ readers and certain LG devices.
+
config CHARGER_MAX77693
tristate "Maxim MAX77693 battery charger driver"
depends on MFD_MAX77693
@@ -395,6 +416,7 @@
depends on MFD_SPMI_PMIC || COMPILE_TEST
depends on OF
depends on EXTCON
+ depends on REGULATOR
help
Say Y to include support for the Switch-Mode Battery Charger and
Boost (SMBB) hardware found in Qualcomm PM8941 PMICs. The charger
diff --git a/drivers/power/supply/Makefile b/drivers/power/supply/Makefile
index 36c599d..3789a2c 100644
--- a/drivers/power/supply/Makefile
+++ b/drivers/power/supply/Makefile
@@ -18,6 +18,7 @@
obj-$(CONFIG_BATTERY_88PM860X) += 88pm860x_battery.o
obj-$(CONFIG_BATTERY_ACT8945A) += act8945a_charger.o
+obj-$(CONFIG_CHARGER_AXP20X) += axp20x_ac_power.o
obj-$(CONFIG_BATTERY_DS2760) += ds2760_battery.o
obj-$(CONFIG_BATTERY_DS2780) += ds2780_battery.o
obj-$(CONFIG_BATTERY_DS2781) += ds2781_battery.o
@@ -31,6 +32,7 @@
obj-$(CONFIG_BATTERY_IPAQ_MICRO) += ipaq_micro_battery.o
obj-$(CONFIG_BATTERY_WM97XX) += wm97xx_battery.o
obj-$(CONFIG_BATTERY_SBS) += sbs-battery.o
+obj-$(CONFIG_CHARGER_SBS) += sbs-charger.o
obj-$(CONFIG_BATTERY_BQ27XXX) += bq27xxx_battery.o
obj-$(CONFIG_BATTERY_BQ27XXX_I2C) += bq27xxx_battery_i2c.o
obj-$(CONFIG_BATTERY_DA9030) += da9030_battery.o
@@ -47,7 +49,6 @@
obj-$(CONFIG_CHARGER_88PM860X) += 88pm860x_charger.o
obj-$(CONFIG_CHARGER_PCF50633) += pcf50633-charger.o
obj-$(CONFIG_BATTERY_JZ4740) += jz4740-battery.o
-obj-$(CONFIG_BATTERY_INTEL_MID) += intel_mid_battery.o
obj-$(CONFIG_BATTERY_RX51) += rx51_battery.o
obj-$(CONFIG_AB8500_BM) += ab8500_bmdata.o ab8500_charger.o ab8500_fg.o ab8500_btemp.o abx500_chargalg.o pm2301_charger.o
obj-$(CONFIG_CHARGER_ISP1704) += isp1704_charger.o
@@ -58,6 +59,7 @@
obj-$(CONFIG_CHARGER_GPIO) += gpio-charger.o
obj-$(CONFIG_CHARGER_MANAGER) += charger-manager.o
obj-$(CONFIG_CHARGER_MAX14577) += max14577_charger.o
+obj-$(CONFIG_CHARGER_DETECTOR_MAX14656) += max14656_charger_detector.o
obj-$(CONFIG_CHARGER_MAX77693) += max77693_charger.o
obj-$(CONFIG_CHARGER_MAX8997) += max8997_charger.o
obj-$(CONFIG_CHARGER_MAX8998) += max8998_charger.o
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index 6ffdc18..f7a35eb 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -76,8 +76,8 @@
* @dev: Pointer to the structure device
* @node: List of AB8500 BTEMPs, hence prepared for reentrance
* @curr_source: What current source we use, in uA
- * @bat_temp: Dispatched battery temperature in degree Celcius
- * @prev_bat_temp Last measured battery temperature in degree Celcius
+ * @bat_temp: Dispatched battery temperature in degree Celsius
+ * @prev_bat_temp Last measured battery temperature in degree Celsius
* @parent: Pointer to the struct ab8500
* @gpadc: Pointer to the struct gpadc
* @fg: Pointer to the struct fg
@@ -123,10 +123,7 @@
*/
struct ab8500_btemp *ab8500_btemp_get(void)
{
- struct ab8500_btemp *btemp;
- btemp = list_first_entry(&ab8500_btemp_list, struct ab8500_btemp, node);
-
- return btemp;
+ return list_first_entry(&ab8500_btemp_list, struct ab8500_btemp, node);
}
EXPORT_SYMBOL(ab8500_btemp_get);
@@ -464,13 +461,13 @@
* @tbl_size: size of the resistance to temperature table
* @res: resistance to calculate the temperature from
*
- * This function returns the battery temperature in degrees Celcius
+ * This function returns the battery temperature in degrees Celsius
* based on the NTC resistance.
*/
static int ab8500_btemp_res_to_temp(struct ab8500_btemp *di,
const struct abx500_res_to_temp *tbl, int tbl_size, int res)
{
- int i, temp;
+ int i;
/*
* Calculate the formula for the straight line
* Simple interpolation if we are within
@@ -488,9 +485,8 @@
i++;
}
- temp = tbl[i].temp + ((tbl[i + 1].temp - tbl[i].temp) *
+ return tbl[i].temp + ((tbl[i + 1].temp - tbl[i].temp) *
(res - tbl[i].resist)) / (tbl[i + 1].resist - tbl[i].resist);
- return temp;
}
/**
diff --git a/drivers/power/supply/axp20x_ac_power.c b/drivers/power/supply/axp20x_ac_power.c
new file mode 100644
index 0000000..38f4e87
--- /dev/null
+++ b/drivers/power/supply/axp20x_ac_power.c
@@ -0,0 +1,253 @@
+/*
+ * AXP20X and AXP22X PMICs' ACIN power supply driver
+ *
+ * Copyright (C) 2016 Free Electrons
+ * Quentin Schulz <quentin.schulz@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/axp20x.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/iio/consumer.h>
+
+#define AXP20X_PWR_STATUS_ACIN_PRESENT BIT(7)
+#define AXP20X_PWR_STATUS_ACIN_AVAIL BIT(6)
+
+#define DRVNAME "axp20x-ac-power-supply"
+
+struct axp20x_ac_power {
+ struct regmap *regmap;
+ struct power_supply *supply;
+ struct iio_channel *acin_v;
+ struct iio_channel *acin_i;
+};
+
+static irqreturn_t axp20x_ac_power_irq(int irq, void *devid)
+{
+ struct axp20x_ac_power *power = devid;
+
+ power_supply_changed(power->supply);
+
+ return IRQ_HANDLED;
+}
+
+static int axp20x_ac_power_get_property(struct power_supply *psy,
+ enum power_supply_property psp,
+ union power_supply_propval *val)
+{
+ struct axp20x_ac_power *power = power_supply_get_drvdata(psy);
+ int ret, reg;
+
+ switch (psp) {
+ case POWER_SUPPLY_PROP_HEALTH:
+ ret = regmap_read(power->regmap, AXP20X_PWR_INPUT_STATUS, ®);
+ if (ret)
+ return ret;
+
+ if (reg & AXP20X_PWR_STATUS_ACIN_PRESENT) {
+ val->intval = POWER_SUPPLY_HEALTH_GOOD;
+ return 0;
+ }
+
+ val->intval = POWER_SUPPLY_HEALTH_UNKNOWN;
+ return 0;
+
+ case POWER_SUPPLY_PROP_PRESENT:
+ ret = regmap_read(power->regmap, AXP20X_PWR_INPUT_STATUS, ®);
+ if (ret)
+ return ret;
+
+ val->intval = !!(reg & AXP20X_PWR_STATUS_ACIN_PRESENT);
+ return 0;
+
+ case POWER_SUPPLY_PROP_ONLINE:
+ ret = regmap_read(power->regmap, AXP20X_PWR_INPUT_STATUS, ®);
+ if (ret)
+ return ret;
+
+ val->intval = !!(reg & AXP20X_PWR_STATUS_ACIN_AVAIL);
+ return 0;
+
+ case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+ ret = iio_read_channel_processed(power->acin_v, &val->intval);
+ if (ret)
+ return ret;
+
+ /* IIO framework gives mV but Power Supply framework gives uV */
+ val->intval *= 1000;
+
+ return 0;
+
+ case POWER_SUPPLY_PROP_CURRENT_NOW:
+ ret = iio_read_channel_processed(power->acin_i, &val->intval);
+ if (ret)
+ return ret;
+
+ /* IIO framework gives mA but Power Supply framework gives uA */
+ val->intval *= 1000;
+
+ return 0;
+
+ default:
+ return -EINVAL;
+ }
+
+ return -EINVAL;
+}
+
+static enum power_supply_property axp20x_ac_power_properties[] = {
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_ONLINE,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+};
+
+static enum power_supply_property axp22x_ac_power_properties[] = {
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_ONLINE,
+};
+
+static const struct power_supply_desc axp20x_ac_power_desc = {
+ .name = "axp20x-ac",
+ .type = POWER_SUPPLY_TYPE_MAINS,
+ .properties = axp20x_ac_power_properties,
+ .num_properties = ARRAY_SIZE(axp20x_ac_power_properties),
+ .get_property = axp20x_ac_power_get_property,
+};
+
+static const struct power_supply_desc axp22x_ac_power_desc = {
+ .name = "axp22x-ac",
+ .type = POWER_SUPPLY_TYPE_MAINS,
+ .properties = axp22x_ac_power_properties,
+ .num_properties = ARRAY_SIZE(axp22x_ac_power_properties),
+ .get_property = axp20x_ac_power_get_property,
+};
+
+struct axp_data {
+ const struct power_supply_desc *power_desc;
+ bool acin_adc;
+};
+
+static const struct axp_data axp20x_data = {
+ .power_desc = &axp20x_ac_power_desc,
+ .acin_adc = true,
+};
+
+static const struct axp_data axp22x_data = {
+ .power_desc = &axp22x_ac_power_desc,
+ .acin_adc = false,
+};
+
+static int axp20x_ac_power_probe(struct platform_device *pdev)
+{
+ struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
+ struct power_supply_config psy_cfg = {};
+ struct axp20x_ac_power *power;
+ struct axp_data *axp_data;
+ static const char * const irq_names[] = { "ACIN_PLUGIN", "ACIN_REMOVAL",
+ NULL };
+ int i, irq, ret;
+
+ if (!of_device_is_available(pdev->dev.of_node))
+ return -ENODEV;
+
+ if (!axp20x) {
+ dev_err(&pdev->dev, "Parent drvdata not set\n");
+ return -EINVAL;
+ }
+
+ power = devm_kzalloc(&pdev->dev, sizeof(*power), GFP_KERNEL);
+ if (!power)
+ return -ENOMEM;
+
+ axp_data = (struct axp_data *)of_device_get_match_data(&pdev->dev);
+
+ if (axp_data->acin_adc) {
+ power->acin_v = devm_iio_channel_get(&pdev->dev, "acin_v");
+ if (IS_ERR(power->acin_v)) {
+ if (PTR_ERR(power->acin_v) == -ENODEV)
+ return -EPROBE_DEFER;
+ return PTR_ERR(power->acin_v);
+ }
+
+ power->acin_i = devm_iio_channel_get(&pdev->dev, "acin_i");
+ if (IS_ERR(power->acin_i)) {
+ if (PTR_ERR(power->acin_i) == -ENODEV)
+ return -EPROBE_DEFER;
+ return PTR_ERR(power->acin_i);
+ }
+ }
+
+ power->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+
+ platform_set_drvdata(pdev, power);
+
+ psy_cfg.of_node = pdev->dev.of_node;
+ psy_cfg.drv_data = power;
+
+ power->supply = devm_power_supply_register(&pdev->dev,
+ axp_data->power_desc,
+ &psy_cfg);
+ if (IS_ERR(power->supply))
+ return PTR_ERR(power->supply);
+
+ /* Request irqs after registering, as irqs may trigger immediately */
+ for (i = 0; irq_names[i]; i++) {
+ irq = platform_get_irq_byname(pdev, irq_names[i]);
+ if (irq < 0) {
+ dev_warn(&pdev->dev, "No IRQ for %s: %d\n",
+ irq_names[i], irq);
+ continue;
+ }
+ irq = regmap_irq_get_virq(axp20x->regmap_irqc, irq);
+ ret = devm_request_any_context_irq(&pdev->dev, irq,
+ axp20x_ac_power_irq, 0,
+ DRVNAME, power);
+ if (ret < 0)
+ dev_warn(&pdev->dev, "Error requesting %s IRQ: %d\n",
+ irq_names[i], ret);
+ }
+
+ return 0;
+}
+
+static const struct of_device_id axp20x_ac_power_match[] = {
+ {
+ .compatible = "x-powers,axp202-ac-power-supply",
+ .data = (void *)&axp20x_data,
+ }, {
+ .compatible = "x-powers,axp221-ac-power-supply",
+ .data = (void *)&axp22x_data,
+ }, { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, axp20x_ac_power_match);
+
+static struct platform_driver axp20x_ac_power_driver = {
+ .probe = axp20x_ac_power_probe,
+ .driver = {
+ .name = DRVNAME,
+ .of_match_table = axp20x_ac_power_match,
+ },
+};
+
+module_platform_driver(axp20x_ac_power_driver);
+
+MODULE_AUTHOR("Quentin Schulz <quentin.schulz@free-electrons.com>");
+MODULE_DESCRIPTION("AXP20X and AXP22X PMICs' AC power supply driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/power/supply/axp20x_usb_power.c b/drivers/power/supply/axp20x_usb_power.c
index 6af6feb..2397c48 100644
--- a/drivers/power/supply/axp20x_usb_power.c
+++ b/drivers/power/supply/axp20x_usb_power.c
@@ -17,10 +17,12 @@
#include <linux/mfd/axp20x.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/power_supply.h>
#include <linux/regmap.h>
#include <linux/slab.h>
+#include <linux/iio/consumer.h>
#define DRVNAME "axp20x-usb-power-supply"
@@ -30,6 +32,8 @@
#define AXP20X_USB_STATUS_VBUS_VALID BIT(2)
#define AXP20X_VBUS_VHOLD_uV(b) (4000000 + (((b) >> 3) & 7) * 100000)
+#define AXP20X_VBUS_VHOLD_MASK GENMASK(5, 3)
+#define AXP20X_VBUS_VHOLD_OFFSET 3
#define AXP20X_VBUS_CLIMIT_MASK 3
#define AXP20X_VBUC_CLIMIT_900mA 0
#define AXP20X_VBUC_CLIMIT_500mA 1
@@ -45,6 +49,9 @@
struct device_node *np;
struct regmap *regmap;
struct power_supply *supply;
+ enum axp20x_variants axp20x_id;
+ struct iio_channel *vbus_v;
+ struct iio_channel *vbus_i;
};
static irqreturn_t axp20x_usb_power_irq(int irq, void *devid)
@@ -72,6 +79,20 @@
val->intval = AXP20X_VBUS_VHOLD_uV(v);
return 0;
case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+ if (IS_ENABLED(CONFIG_AXP20X_ADC)) {
+ ret = iio_read_channel_processed(power->vbus_v,
+ &val->intval);
+ if (ret)
+ return ret;
+
+ /*
+ * IIO framework gives mV but Power Supply framework
+ * gives uV.
+ */
+ val->intval *= 1000;
+ return 0;
+ }
+
ret = axp20x_read_variable_width(power->regmap,
AXP20X_VBUS_V_ADC_H, 12);
if (ret < 0)
@@ -86,12 +107,10 @@
switch (v & AXP20X_VBUS_CLIMIT_MASK) {
case AXP20X_VBUC_CLIMIT_100mA:
- if (of_device_is_compatible(power->np,
- "x-powers,axp202-usb-power-supply")) {
- val->intval = 100000;
- } else {
+ if (power->axp20x_id == AXP221_ID)
val->intval = -1; /* No 100mA limit */
- }
+ else
+ val->intval = 100000;
break;
case AXP20X_VBUC_CLIMIT_500mA:
val->intval = 500000;
@@ -105,6 +124,20 @@
}
return 0;
case POWER_SUPPLY_PROP_CURRENT_NOW:
+ if (IS_ENABLED(CONFIG_AXP20X_ADC)) {
+ ret = iio_read_channel_processed(power->vbus_i,
+ &val->intval);
+ if (ret)
+ return ret;
+
+ /*
+ * IIO framework gives mA but Power Supply framework
+ * gives uA.
+ */
+ val->intval *= 1000;
+ return 0;
+ }
+
ret = axp20x_read_variable_width(power->regmap,
AXP20X_VBUS_I_ADC_H, 12);
if (ret < 0)
@@ -130,8 +163,7 @@
val->intval = POWER_SUPPLY_HEALTH_GOOD;
- if (of_device_is_compatible(power->np,
- "x-powers,axp202-usb-power-supply")) {
+ if (power->axp20x_id == AXP202_ID) {
ret = regmap_read(power->regmap,
AXP20X_USB_OTG_STATUS, &v);
if (ret)
@@ -155,6 +187,81 @@
return 0;
}
+static int axp20x_usb_power_set_voltage_min(struct axp20x_usb_power *power,
+ int intval)
+{
+ int val;
+
+ switch (intval) {
+ case 4000000:
+ case 4100000:
+ case 4200000:
+ case 4300000:
+ case 4400000:
+ case 4500000:
+ case 4600000:
+ case 4700000:
+ val = (intval - 4000000) / 100000;
+ return regmap_update_bits(power->regmap,
+ AXP20X_VBUS_IPSOUT_MGMT,
+ AXP20X_VBUS_VHOLD_MASK,
+ val << AXP20X_VBUS_VHOLD_OFFSET);
+ default:
+ return -EINVAL;
+ }
+
+ return -EINVAL;
+}
+
+static int axp20x_usb_power_set_current_max(struct axp20x_usb_power *power,
+ int intval)
+{
+ int val;
+
+ switch (intval) {
+ case 100000:
+ if (power->axp20x_id == AXP221_ID)
+ return -EINVAL;
+ case 500000:
+ case 900000:
+ val = (900000 - intval) / 400000;
+ return regmap_update_bits(power->regmap,
+ AXP20X_VBUS_IPSOUT_MGMT,
+ AXP20X_VBUS_CLIMIT_MASK, val);
+ default:
+ return -EINVAL;
+ }
+
+ return -EINVAL;
+}
+
+static int axp20x_usb_power_set_property(struct power_supply *psy,
+ enum power_supply_property psp,
+ const union power_supply_propval *val)
+{
+ struct axp20x_usb_power *power = power_supply_get_drvdata(psy);
+
+ switch (psp) {
+ case POWER_SUPPLY_PROP_VOLTAGE_MIN:
+ return axp20x_usb_power_set_voltage_min(power, val->intval);
+
+ case POWER_SUPPLY_PROP_CURRENT_MAX:
+ return axp20x_usb_power_set_current_max(power, val->intval);
+
+ default:
+ return -EINVAL;
+ }
+
+ return -EINVAL;
+}
+
+static int axp20x_usb_power_prop_writeable(struct power_supply *psy,
+ enum power_supply_property psp)
+{
+ return psp == POWER_SUPPLY_PROP_VOLTAGE_MIN ||
+ psp == POWER_SUPPLY_PROP_CURRENT_MAX;
+}
+
static enum power_supply_property axp20x_usb_power_properties[] = {
POWER_SUPPLY_PROP_HEALTH,
POWER_SUPPLY_PROP_PRESENT,
@@ -178,7 +285,9 @@
.type = POWER_SUPPLY_TYPE_USB,
.properties = axp20x_usb_power_properties,
.num_properties = ARRAY_SIZE(axp20x_usb_power_properties),
+ .property_is_writeable = axp20x_usb_power_prop_writeable,
.get_property = axp20x_usb_power_get_property,
+ .set_property = axp20x_usb_power_set_property,
};
static const struct power_supply_desc axp22x_usb_power_desc = {
@@ -186,9 +295,41 @@
.type = POWER_SUPPLY_TYPE_USB,
.properties = axp22x_usb_power_properties,
.num_properties = ARRAY_SIZE(axp22x_usb_power_properties),
+ .property_is_writeable = axp20x_usb_power_prop_writeable,
.get_property = axp20x_usb_power_get_property,
+ .set_property = axp20x_usb_power_set_property,
};
+static int configure_iio_channels(struct platform_device *pdev,
+ struct axp20x_usb_power *power)
+{
+ power->vbus_v = devm_iio_channel_get(&pdev->dev, "vbus_v");
+ if (IS_ERR(power->vbus_v)) {
+ if (PTR_ERR(power->vbus_v) == -ENODEV)
+ return -EPROBE_DEFER;
+ return PTR_ERR(power->vbus_v);
+ }
+
+ power->vbus_i = devm_iio_channel_get(&pdev->dev, "vbus_i");
+ if (IS_ERR(power->vbus_i)) {
+ if (PTR_ERR(power->vbus_i) == -ENODEV)
+ return -EPROBE_DEFER;
+ return PTR_ERR(power->vbus_i);
+ }
+
+ return 0;
+}
+
+static int configure_adc_registers(struct axp20x_usb_power *power)
+{
+ /* Enable vbus voltage and current measurement */
+ return regmap_update_bits(power->regmap, AXP20X_ADC_EN1,
+ AXP20X_ADC_EN1_VBUS_CURR |
+ AXP20X_ADC_EN1_VBUS_VOLT,
+ AXP20X_ADC_EN1_VBUS_CURR |
+ AXP20X_ADC_EN1_VBUS_VOLT);
+}
+
static int axp20x_usb_power_probe(struct platform_device *pdev)
{
struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
@@ -214,11 +355,13 @@
if (!power)
return -ENOMEM;
+ power->axp20x_id = (enum axp20x_variants)of_device_get_match_data(
+ &pdev->dev);
+
power->np = pdev->dev.of_node;
power->regmap = axp20x->regmap;
- if (of_device_is_compatible(power->np,
- "x-powers,axp202-usb-power-supply")) {
+ if (power->axp20x_id == AXP202_ID) {
/* Enable vbus valid checking */
ret = regmap_update_bits(power->regmap, AXP20X_VBUS_MON,
AXP20X_VBUS_MON_VBUS_VALID,
@@ -226,17 +369,18 @@
if (ret)
return ret;
- /* Enable vbus voltage and current measurement */
- ret = regmap_update_bits(power->regmap, AXP20X_ADC_EN1,
- AXP20X_ADC_EN1_VBUS_CURR | AXP20X_ADC_EN1_VBUS_VOLT,
- AXP20X_ADC_EN1_VBUS_CURR | AXP20X_ADC_EN1_VBUS_VOLT);
+ if (IS_ENABLED(CONFIG_AXP20X_ADC))
+ ret = configure_iio_channels(pdev, power);
+ else
+ ret = configure_adc_registers(power);
+
if (ret)
return ret;
usb_power_desc = &axp20x_usb_power_desc;
irq_names = axp20x_irq_names;
- } else if (of_device_is_compatible(power->np,
- "x-powers,axp221-usb-power-supply")) {
+ } else if (power->axp20x_id == AXP221_ID ||
+ power->axp20x_id == AXP223_ID) {
usb_power_desc = &axp22x_usb_power_desc;
irq_names = axp22x_irq_names;
} else {
@@ -273,9 +417,16 @@
}
static const struct of_device_id axp20x_usb_power_match[] = {
- { .compatible = "x-powers,axp202-usb-power-supply" },
- { .compatible = "x-powers,axp221-usb-power-supply" },
- { }
+ {
+ .compatible = "x-powers,axp202-usb-power-supply",
+ .data = (void *)AXP202_ID,
+ }, {
+ .compatible = "x-powers,axp221-usb-power-supply",
+ .data = (void *)AXP221_ID,
+ }, {
+ .compatible = "x-powers,axp223-usb-power-supply",
+ .data = (void *)AXP223_ID,
+ }, { /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, axp20x_usb_power_match);
diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c
index 75b8e0c..6be2fe2 100644
--- a/drivers/power/supply/axp288_charger.c
+++ b/drivers/power/supply/axp288_charger.c
@@ -90,20 +90,6 @@
#define CHRG_VLTFC_0C 0xA5 /* 0 DegC */
#define CHRG_VHTFC_45C 0x1F /* 45 DegC */
-#define BAT_IRQ_CFG_CHRG_DONE (1 << 2)
-#define BAT_IRQ_CFG_CHRG_START (1 << 3)
-#define BAT_IRQ_CFG_BAT_SAFE_EXIT (1 << 4)
-#define BAT_IRQ_CFG_BAT_SAFE_ENTER (1 << 5)
-#define BAT_IRQ_CFG_BAT_DISCON (1 << 6)
-#define BAT_IRQ_CFG_BAT_CONN (1 << 7)
-#define BAT_IRQ_CFG_BAT_MASK 0xFC
-
-#define TEMP_IRQ_CFG_QCBTU (1 << 4)
-#define TEMP_IRQ_CFG_CBTU (1 << 5)
-#define TEMP_IRQ_CFG_QCBTO (1 << 6)
-#define TEMP_IRQ_CFG_CBTO (1 << 7)
-#define TEMP_IRQ_CFG_MASK 0xF0
-
#define FG_CNTL_OCV_ADJ_EN (1 << 3)
#define CV_4100MV 4100 /* 4100mV */
@@ -127,6 +113,10 @@
#define ILIM_3000MA 3000 /* 3000mA */
#define AXP288_EXTCON_DEV_NAME "axp288_extcon"
+#define USB_HOST_EXTCON_DEV_NAME "INT3496:00"
+
+static const unsigned int cable_ids[] =
+ { EXTCON_CHG_USB_SDP, EXTCON_CHG_USB_CDP, EXTCON_CHG_USB_DCP };
enum {
VBUS_OV_IRQ = 0,
@@ -143,7 +133,6 @@
struct axp288_chrg_info {
struct platform_device *pdev;
- struct axp20x_chrg_pdata *pdata;
struct regmap *regmap;
struct regmap_irq_chip_data *regmap_irqc;
int irq[CHRG_INTR_END];
@@ -163,20 +152,16 @@
struct extcon_dev *edev;
bool connected;
enum power_supply_type chg_type;
- struct notifier_block nb;
+ struct notifier_block nb[ARRAY_SIZE(cable_ids)];
struct work_struct work;
} cable;
- int health;
int inlmt;
int cc;
int cv;
int max_cc;
int max_cv;
- bool online;
- bool present;
- bool enable_charger;
- bool is_charger_enabled;
+ int is_charger_enabled;
};
static inline int axp288_charger_set_cc(struct axp288_chrg_info *info, int cc)
@@ -305,6 +290,9 @@
{
int ret;
+ if ((int)enable == info->is_charger_enabled)
+ return 0;
+
if (enable)
ret = regmap_update_bits(info->regmap, AXP20X_CHRG_CTRL1,
CHRG_CCCV_CHG_EN, CHRG_CCCV_CHG_EN);
@@ -430,8 +418,7 @@
ret = axp288_charger_is_present(info);
if (ret < 0)
goto psy_get_prop_fail;
- info->present = ret;
- val->intval = info->present;
+ val->intval = ret;
break;
case POWER_SUPPLY_PROP_ONLINE:
/* Check for OTG case first */
@@ -442,8 +429,7 @@
ret = axp288_charger_is_online(info);
if (ret < 0)
goto psy_get_prop_fail;
- info->online = ret;
- val->intval = info->online;
+ val->intval = ret;
break;
case POWER_SUPPLY_PROP_HEALTH:
val->intval = axp288_get_charger_health(info);
@@ -576,20 +562,20 @@
struct axp288_chrg_info *info =
container_of(work, struct axp288_chrg_info, cable.work);
int ret, current_limit;
- bool changed = false;
struct extcon_dev *edev = info->cable.edev;
bool old_connected = info->cable.connected;
+ enum power_supply_type old_chg_type = info->cable.chg_type;
/* Determine cable/charger type */
- if (extcon_get_cable_state_(edev, EXTCON_CHG_USB_SDP) > 0) {
+ if (extcon_get_state(edev, EXTCON_CHG_USB_SDP) > 0) {
dev_dbg(&info->pdev->dev, "USB SDP charger is connected");
info->cable.connected = true;
info->cable.chg_type = POWER_SUPPLY_TYPE_USB;
- } else if (extcon_get_cable_state_(edev, EXTCON_CHG_USB_CDP) > 0) {
+ } else if (extcon_get_state(edev, EXTCON_CHG_USB_CDP) > 0) {
dev_dbg(&info->pdev->dev, "USB CDP charger is connected");
info->cable.connected = true;
info->cable.chg_type = POWER_SUPPLY_TYPE_USB_CDP;
- } else if (extcon_get_cable_state_(edev, EXTCON_CHG_USB_DCP) > 0) {
+ } else if (extcon_get_state(edev, EXTCON_CHG_USB_DCP) > 0) {
dev_dbg(&info->pdev->dev, "USB DCP charger is connected");
info->cable.connected = true;
info->cable.chg_type = POWER_SUPPLY_TYPE_USB_DCP;
@@ -601,22 +587,15 @@
}
/* Cable status changed */
- if (old_connected != info->cable.connected)
- changed = true;
-
- if (!changed)
+ if (old_connected == info->cable.connected &&
+ old_chg_type == info->cable.chg_type)
return;
mutex_lock(&info->lock);
- if (info->is_charger_enabled && !info->cable.connected) {
- info->enable_charger = false;
- ret = axp288_charger_enable_charger(info, info->enable_charger);
- if (ret < 0)
- dev_err(&info->pdev->dev,
- "cannot disable charger (%d)", ret);
+ if (info->cable.connected) {
+ axp288_charger_enable_charger(info, false);
- } else if (!info->is_charger_enabled && info->cable.connected) {
switch (info->cable.chg_type) {
case POWER_SUPPLY_TYPE_USB:
current_limit = ILIM_500MA;
@@ -635,36 +614,49 @@
/* Set vbus current limit first, then enable charger */
ret = axp288_charger_set_vbus_inlmt(info, current_limit);
- if (ret < 0) {
+ if (ret == 0)
+ axp288_charger_enable_charger(info, true);
+ else
dev_err(&info->pdev->dev,
"error setting current limit (%d)", ret);
- } else {
- info->enable_charger = (current_limit > 0);
- ret = axp288_charger_enable_charger(info,
- info->enable_charger);
- if (ret < 0)
- dev_err(&info->pdev->dev,
- "cannot enable charger (%d)", ret);
- }
+ } else {
+ axp288_charger_enable_charger(info, false);
}
- if (changed)
- info->health = axp288_get_charger_health(info);
-
mutex_unlock(&info->lock);
- if (changed)
- power_supply_changed(info->psy_usb);
+ power_supply_changed(info->psy_usb);
}
-static int axp288_charger_handle_cable_evt(struct notifier_block *nb,
- unsigned long event, void *param)
+/*
+ * We need 3 copies of this, because there is no way to find out for which
+ * cable id we are being called from the passed in arguments; and we must
+ * have a separate nb for each extcon_register_notifier call.
+ */
+static int axp288_charger_handle_cable0_evt(struct notifier_block *nb,
+ unsigned long event, void *param)
{
struct axp288_chrg_info *info =
- container_of(nb, struct axp288_chrg_info, cable.nb);
-
+ container_of(nb, struct axp288_chrg_info, cable.nb[0]);
schedule_work(&info->cable.work);
+ return NOTIFY_OK;
+}
+static int axp288_charger_handle_cable1_evt(struct notifier_block *nb,
+ unsigned long event, void *param)
+{
+ struct axp288_chrg_info *info =
+ container_of(nb, struct axp288_chrg_info, cable.nb[1]);
+ schedule_work(&info->cable.work);
+ return NOTIFY_OK;
+}
+
+static int axp288_charger_handle_cable2_evt(struct notifier_block *nb,
+ unsigned long event, void *param)
+{
+ struct axp288_chrg_info *info =
+ container_of(nb, struct axp288_chrg_info, cable.nb[2]);
+ schedule_work(&info->cable.work);
return NOTIFY_OK;
}
@@ -672,7 +664,17 @@
{
struct axp288_chrg_info *info =
container_of(work, struct axp288_chrg_info, otg.work);
- int ret;
+ struct extcon_dev *edev = info->otg.cable;
+ int ret, usb_host = extcon_get_state(edev, EXTCON_USB_HOST);
+
+ dev_dbg(&info->pdev->dev, "external connector USB-Host is %s\n",
+ usb_host ? "attached" : "detached");
+
+ /*
+ * Set usb_id_short flag to avoid running charger detection logic
+ * in case usb host.
+ */
+ info->otg.id_short = usb_host;
/* Disable VBUS path before enabling the 5V boost */
ret = axp288_charger_vbus_path_select(info, !info->otg.id_short);
@@ -685,135 +687,109 @@
{
struct axp288_chrg_info *info =
container_of(nb, struct axp288_chrg_info, otg.id_nb);
- struct extcon_dev *edev = info->otg.cable;
- int usb_host = extcon_get_cable_state_(edev, EXTCON_USB_HOST);
- dev_dbg(&info->pdev->dev, "external connector USB-Host is %s\n",
- usb_host ? "attached" : "detached");
-
- /*
- * Set usb_id_short flag to avoid running charger detection logic
- * in case usb host.
- */
- info->otg.id_short = usb_host;
schedule_work(&info->otg.work);
return NOTIFY_OK;
}
-static void charger_init_hw_regs(struct axp288_chrg_info *info)
+static int charger_init_hw_regs(struct axp288_chrg_info *info)
{
int ret, cc, cv;
unsigned int val;
/* Program temperature thresholds */
ret = regmap_write(info->regmap, AXP20X_V_LTF_CHRG, CHRG_VLTFC_0C);
- if (ret < 0)
- dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+ if (ret < 0) {
+ dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
AXP20X_V_LTF_CHRG, ret);
+ return ret;
+ }
ret = regmap_write(info->regmap, AXP20X_V_HTF_CHRG, CHRG_VHTFC_45C);
- if (ret < 0)
- dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+ if (ret < 0) {
+ dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
AXP20X_V_HTF_CHRG, ret);
+ return ret;
+ }
/* Do not turn-off charger o/p after charge cycle ends */
ret = regmap_update_bits(info->regmap,
AXP20X_CHRG_CTRL2,
- CNTL2_CHG_OUT_TURNON, 1);
- if (ret < 0)
- dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+ CNTL2_CHG_OUT_TURNON, CNTL2_CHG_OUT_TURNON);
+ if (ret < 0) {
+ dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
AXP20X_CHRG_CTRL2, ret);
-
- /* Enable interrupts */
- ret = regmap_update_bits(info->regmap,
- AXP20X_IRQ2_EN,
- BAT_IRQ_CFG_BAT_MASK, 1);
- if (ret < 0)
- dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
- AXP20X_IRQ2_EN, ret);
-
- ret = regmap_update_bits(info->regmap, AXP20X_IRQ3_EN,
- TEMP_IRQ_CFG_MASK, 1);
- if (ret < 0)
- dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
- AXP20X_IRQ3_EN, ret);
+ return ret;
+ }
/* Setup ending condition for charging to be 10% of I(chrg) */
ret = regmap_update_bits(info->regmap,
AXP20X_CHRG_CTRL1,
CHRG_CCCV_ITERM_20P, 0);
- if (ret < 0)
- dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+ if (ret < 0) {
+ dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
AXP20X_CHRG_CTRL1, ret);
+ return ret;
+ }
/* Disable OCV-SOC curve calibration */
ret = regmap_update_bits(info->regmap,
AXP20X_CC_CTRL,
FG_CNTL_OCV_ADJ_EN, 0);
- if (ret < 0)
- dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+ if (ret < 0) {
+ dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
AXP20X_CC_CTRL, ret);
-
- /* Init charging current and voltage */
- info->max_cc = info->pdata->max_cc;
- info->max_cv = info->pdata->max_cv;
+ return ret;
+ }
/* Read current charge voltage and current limit */
ret = regmap_read(info->regmap, AXP20X_CHRG_CTRL1, &val);
if (ret < 0) {
- /* Assume default if cannot read */
- info->cc = info->pdata->def_cc;
- info->cv = info->pdata->def_cv;
- } else {
- /* Determine charge voltage */
- cv = (val & CHRG_CCCV_CV_MASK) >> CHRG_CCCV_CV_BIT_POS;
- switch (cv) {
- case CHRG_CCCV_CV_4100MV:
- info->cv = CV_4100MV;
- break;
- case CHRG_CCCV_CV_4150MV:
- info->cv = CV_4150MV;
- break;
- case CHRG_CCCV_CV_4200MV:
- info->cv = CV_4200MV;
- break;
- case CHRG_CCCV_CV_4350MV:
- info->cv = CV_4350MV;
- break;
- default:
- info->cv = INT_MAX;
- break;
- }
-
- /* Determine charge current limit */
- cc = (ret & CHRG_CCCV_CC_MASK) >> CHRG_CCCV_CC_BIT_POS;
- cc = (cc * CHRG_CCCV_CC_LSB_RES) + CHRG_CCCV_CC_OFFSET;
- info->cc = cc;
-
- /* Program default charging voltage and current */
- cc = min(info->pdata->def_cc, info->max_cc);
- cv = min(info->pdata->def_cv, info->max_cv);
-
- ret = axp288_charger_set_cc(info, cc);
- if (ret < 0)
- dev_warn(&info->pdev->dev,
- "error(%d) in setting CC\n", ret);
-
- ret = axp288_charger_set_cv(info, cv);
- if (ret < 0)
- dev_warn(&info->pdev->dev,
- "error(%d) in setting CV\n", ret);
+ dev_err(&info->pdev->dev, "register(%x) read error(%d)\n",
+ AXP20X_CHRG_CTRL1, ret);
+ return ret;
}
+
+ /* Determine charge voltage */
+ cv = (val & CHRG_CCCV_CV_MASK) >> CHRG_CCCV_CV_BIT_POS;
+ switch (cv) {
+ case CHRG_CCCV_CV_4100MV:
+ info->cv = CV_4100MV;
+ break;
+ case CHRG_CCCV_CV_4150MV:
+ info->cv = CV_4150MV;
+ break;
+ case CHRG_CCCV_CV_4200MV:
+ info->cv = CV_4200MV;
+ break;
+ case CHRG_CCCV_CV_4350MV:
+ info->cv = CV_4350MV;
+ break;
+ }
+
+ /* Determine charge current limit */
+ cc = (ret & CHRG_CCCV_CC_MASK) >> CHRG_CCCV_CC_BIT_POS;
+ cc = (cc * CHRG_CCCV_CC_LSB_RES) + CHRG_CCCV_CC_OFFSET;
+ info->cc = cc;
+
+ /*
+ * Do not allow the user to configure higher settings then those
+ * set by the firmware
+ */
+ info->max_cv = info->cv;
+ info->max_cc = info->cc;
+
+ return 0;
}
static int axp288_charger_probe(struct platform_device *pdev)
{
int ret, i, pirq;
struct axp288_chrg_info *info;
+ struct device *dev = &pdev->dev;
struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
struct power_supply_config charger_cfg = {};
-
info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
if (!info)
return -ENOMEM;
@@ -821,15 +797,8 @@
info->pdev = pdev;
info->regmap = axp20x->regmap;
info->regmap_irqc = axp20x->regmap_irqc;
- info->pdata = pdev->dev.platform_data;
-
- if (!info->pdata) {
- /* Try ACPI provided pdata via device properties */
- if (!device_property_present(&pdev->dev,
- "axp288_charger_data\n"))
- dev_err(&pdev->dev, "failed to get platform data\n");
- return -ENODEV;
- }
+ info->cable.chg_type = -1;
+ info->is_charger_enabled = -1;
info->cable.edev = extcon_get_extcon_dev(AXP288_EXTCON_DEV_NAME);
if (info->cable.edev == NULL) {
@@ -838,63 +807,55 @@
return -EPROBE_DEFER;
}
- /* Register for extcon notification */
- INIT_WORK(&info->cable.work, axp288_charger_extcon_evt_worker);
- info->cable.nb.notifier_call = axp288_charger_handle_cable_evt;
- ret = extcon_register_notifier(info->cable.edev, EXTCON_CHG_USB_SDP,
- &info->cable.nb);
- if (ret) {
- dev_err(&info->pdev->dev,
- "failed to register extcon notifier for SDP %d\n", ret);
- return ret;
- }
-
- ret = extcon_register_notifier(info->cable.edev, EXTCON_CHG_USB_CDP,
- &info->cable.nb);
- if (ret) {
- dev_err(&info->pdev->dev,
- "failed to register extcon notifier for CDP %d\n", ret);
- extcon_unregister_notifier(info->cable.edev,
- EXTCON_CHG_USB_SDP, &info->cable.nb);
- return ret;
- }
-
- ret = extcon_register_notifier(info->cable.edev, EXTCON_CHG_USB_DCP,
- &info->cable.nb);
- if (ret) {
- dev_err(&info->pdev->dev,
- "failed to register extcon notifier for DCP %d\n", ret);
- extcon_unregister_notifier(info->cable.edev,
- EXTCON_CHG_USB_SDP, &info->cable.nb);
- extcon_unregister_notifier(info->cable.edev,
- EXTCON_CHG_USB_CDP, &info->cable.nb);
- return ret;
+ info->otg.cable = extcon_get_extcon_dev(USB_HOST_EXTCON_DEV_NAME);
+ if (info->otg.cable == NULL) {
+ dev_dbg(dev, "EXTCON_USB_HOST is not ready, probe deferred\n");
+ return -EPROBE_DEFER;
}
platform_set_drvdata(pdev, info);
mutex_init(&info->lock);
+ ret = charger_init_hw_regs(info);
+ if (ret)
+ return ret;
+
/* Register with power supply class */
charger_cfg.drv_data = info;
- info->psy_usb = power_supply_register(&pdev->dev, &axp288_charger_desc,
- &charger_cfg);
+ info->psy_usb = devm_power_supply_register(dev, &axp288_charger_desc,
+ &charger_cfg);
if (IS_ERR(info->psy_usb)) {
- dev_err(&pdev->dev, "failed to register power supply charger\n");
ret = PTR_ERR(info->psy_usb);
- goto psy_reg_failed;
+ dev_err(dev, "failed to register power supply: %d\n", ret);
+ return ret;
}
+ /* Register for extcon notification */
+ INIT_WORK(&info->cable.work, axp288_charger_extcon_evt_worker);
+ info->cable.nb[0].notifier_call = axp288_charger_handle_cable0_evt;
+ info->cable.nb[1].notifier_call = axp288_charger_handle_cable1_evt;
+ info->cable.nb[2].notifier_call = axp288_charger_handle_cable2_evt;
+ for (i = 0; i < ARRAY_SIZE(cable_ids); i++) {
+ ret = devm_extcon_register_notifier(dev, info->cable.edev,
+ cable_ids[i], &info->cable.nb[i]);
+ if (ret) {
+ dev_err(dev, "failed to register extcon notifier for %u: %d\n",
+ cable_ids[i], ret);
+ return ret;
+ }
+ }
+ schedule_work(&info->cable.work);
+
/* Register for OTG notification */
INIT_WORK(&info->otg.work, axp288_charger_otg_evt_worker);
info->otg.id_nb.notifier_call = axp288_charger_handle_otg_evt;
- ret = extcon_register_notifier(info->otg.cable, EXTCON_USB_HOST,
- &info->otg.id_nb);
- if (ret)
- dev_warn(&pdev->dev, "failed to register otg notifier\n");
-
- if (info->otg.cable)
- info->otg.id_short = extcon_get_cable_state_(
- info->otg.cable, EXTCON_USB_HOST);
+ ret = devm_extcon_register_notifier(&pdev->dev, info->otg.cable,
+ EXTCON_USB_HOST, &info->otg.id_nb);
+ if (ret) {
+ dev_err(dev, "failed to register EXTCON_USB_HOST notifier\n");
+ return ret;
+ }
+ schedule_work(&info->otg.work);
/* Register charger interrupts */
for (i = 0; i < CHRG_INTR_END; i++) {
@@ -903,8 +864,7 @@
if (info->irq[i] < 0) {
dev_warn(&info->pdev->dev,
"failed to get virtual interrupt=%d\n", pirq);
- ret = info->irq[i];
- goto intr_reg_failed;
+ return info->irq[i];
}
ret = devm_request_threaded_irq(&info->pdev->dev, info->irq[i],
NULL, axp288_charger_irq_thread_handler,
@@ -912,51 +872,22 @@
if (ret) {
dev_err(&pdev->dev, "failed to request interrupt=%d\n",
info->irq[i]);
- goto intr_reg_failed;
+ return ret;
}
}
- charger_init_hw_regs(info);
-
- return 0;
-
-intr_reg_failed:
- if (info->otg.cable)
- extcon_unregister_notifier(info->otg.cable, EXTCON_USB_HOST,
- &info->otg.id_nb);
- power_supply_unregister(info->psy_usb);
-psy_reg_failed:
- extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_SDP,
- &info->cable.nb);
- extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_CDP,
- &info->cable.nb);
- extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_DCP,
- &info->cable.nb);
- return ret;
-}
-
-static int axp288_charger_remove(struct platform_device *pdev)
-{
- struct axp288_chrg_info *info = dev_get_drvdata(&pdev->dev);
-
- if (info->otg.cable)
- extcon_unregister_notifier(info->otg.cable, EXTCON_USB_HOST,
- &info->otg.id_nb);
-
- extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_SDP,
- &info->cable.nb);
- extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_CDP,
- &info->cable.nb);
- extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_DCP,
- &info->cable.nb);
- power_supply_unregister(info->psy_usb);
-
return 0;
}
+static const struct platform_device_id axp288_charger_id_table[] = {
+ { .name = "axp288_charger" },
+ {},
+};
+MODULE_DEVICE_TABLE(platform, axp288_charger_id_table);
+
static struct platform_driver axp288_charger_driver = {
.probe = axp288_charger_probe,
- .remove = axp288_charger_remove,
+ .id_table = axp288_charger_id_table,
.driver = {
.name = "axp288_charger",
},
diff --git a/drivers/power/supply/axp288_fuel_gauge.c b/drivers/power/supply/axp288_fuel_gauge.c
index 539eb41..a8dcabc 100644
--- a/drivers/power/supply/axp288_fuel_gauge.c
+++ b/drivers/power/supply/axp288_fuel_gauge.c
@@ -29,6 +29,7 @@
#include <linux/iio/consumer.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <asm/unaligned.h>
#define CHRG_STAT_BAT_SAFE_MODE (1 << 3)
#define CHRG_STAT_BAT_VALID (1 << 4)
@@ -49,23 +50,6 @@
#define CHRG_CCCV_CV_4350MV 0x3 /* 4.35V */
#define CHRG_CCCV_CHG_EN (1 << 7)
-#define CV_4100 4100 /* 4100mV */
-#define CV_4150 4150 /* 4150mV */
-#define CV_4200 4200 /* 4200mV */
-#define CV_4350 4350 /* 4350mV */
-
-#define TEMP_IRQ_CFG_QWBTU (1 << 0)
-#define TEMP_IRQ_CFG_WBTU (1 << 1)
-#define TEMP_IRQ_CFG_QWBTO (1 << 2)
-#define TEMP_IRQ_CFG_WBTO (1 << 3)
-#define TEMP_IRQ_CFG_MASK 0xf
-
-#define FG_IRQ_CFG_LOWBATT_WL2 (1 << 0)
-#define FG_IRQ_CFG_LOWBATT_WL1 (1 << 1)
-#define FG_IRQ_CFG_LOWBATT_MASK 0x3
-#define LOWBAT_IRQ_STAT_LOWBATT_WL2 (1 << 0)
-#define LOWBAT_IRQ_STAT_LOWBATT_WL1 (1 << 1)
-
#define FG_CNTL_OCV_ADJ_STAT (1 << 2)
#define FG_CNTL_OCV_ADJ_EN (1 << 3)
#define FG_CNTL_CAP_ADJ_STAT (1 << 4)
@@ -73,17 +57,15 @@
#define FG_CNTL_CC_EN (1 << 6)
#define FG_CNTL_GAUGE_EN (1 << 7)
+#define FG_15BIT_WORD_VALID (1 << 15)
+#define FG_15BIT_VAL_MASK 0x7fff
+
#define FG_REP_CAP_VALID (1 << 7)
#define FG_REP_CAP_VAL_MASK 0x7F
#define FG_DES_CAP1_VALID (1 << 7)
-#define FG_DES_CAP1_VAL_MASK 0x7F
-#define FG_DES_CAP0_VAL_MASK 0xFF
#define FG_DES_CAP_RES_LSB 1456 /* 1.456mAhr */
-#define FG_CC_MTR1_VALID (1 << 7)
-#define FG_CC_MTR1_VAL_MASK 0x7F
-#define FG_CC_MTR0_VAL_MASK 0xFF
#define FG_DES_CC_RES_LSB 1456 /* 1.456mAhr */
#define FG_OCV_CAP_VALID (1 << 7)
@@ -104,9 +86,7 @@
/* 1.1mV per LSB expressed in uV */
#define VOLTAGE_FROM_ADC(a) ((a * 11) / 10)
-/* properties converted to tenths of degrees, uV, uA, uW */
-#define PROP_TEMP(a) ((a) * 10)
-#define UNPROP_TEMP(a) ((a) / 10)
+/* properties converted to uV, uA */
#define PROP_VOLT(a) ((a) * 1000)
#define PROP_CURR(a) ((a) * 1000)
@@ -122,13 +102,13 @@
struct axp288_fg_info {
struct platform_device *pdev;
- struct axp20x_fg_pdata *pdata;
struct regmap *regmap;
struct regmap_irq_chip_data *regmap_irqc;
int irq[AXP288_FG_INTR_NUM];
struct power_supply *bat;
struct mutex lock;
int status;
+ int max_volt;
struct delayed_work status_monitor;
struct dentry *debug_file;
};
@@ -138,22 +118,14 @@
POWER_SUPPLY_PROP_PRESENT,
POWER_SUPPLY_PROP_HEALTH,
POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN,
- POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
POWER_SUPPLY_PROP_VOLTAGE_NOW,
POWER_SUPPLY_PROP_VOLTAGE_OCV,
POWER_SUPPLY_PROP_CURRENT_NOW,
POWER_SUPPLY_PROP_CAPACITY,
POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN,
- POWER_SUPPLY_PROP_TEMP,
- POWER_SUPPLY_PROP_TEMP_MAX,
- POWER_SUPPLY_PROP_TEMP_MIN,
- POWER_SUPPLY_PROP_TEMP_ALERT_MIN,
- POWER_SUPPLY_PROP_TEMP_ALERT_MAX,
POWER_SUPPLY_PROP_TECHNOLOGY,
POWER_SUPPLY_PROP_CHARGE_FULL,
POWER_SUPPLY_PROP_CHARGE_NOW,
- POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
- POWER_SUPPLY_PROP_MODEL_NAME,
};
static int fuel_gauge_reg_readb(struct axp288_fg_info *info, int reg)
@@ -169,8 +141,10 @@
break;
}
- if (ret < 0)
+ if (ret < 0) {
dev_err(&info->pdev->dev, "axp288 reg read err:%d\n", ret);
+ return ret;
+ }
return val;
}
@@ -187,6 +161,44 @@
return ret;
}
+static int fuel_gauge_read_15bit_word(struct axp288_fg_info *info, int reg)
+{
+ unsigned char buf[2];
+ int ret;
+
+ ret = regmap_bulk_read(info->regmap, reg, buf, 2);
+ if (ret < 0) {
+ dev_err(&info->pdev->dev, "Error reading reg 0x%02x err: %d\n",
+ reg, ret);
+ return ret;
+ }
+
+ ret = get_unaligned_be16(buf);
+ if (!(ret & FG_15BIT_WORD_VALID)) {
+ dev_err(&info->pdev->dev, "Error reg 0x%02x contents not valid\n",
+ reg);
+ return -ENXIO;
+ }
+
+ return ret & FG_15BIT_VAL_MASK;
+}
+
+static int fuel_gauge_read_12bit_word(struct axp288_fg_info *info, int reg)
+{
+ unsigned char buf[2];
+ int ret;
+
+ ret = regmap_bulk_read(info->regmap, reg, buf, 2);
+ if (ret < 0) {
+ dev_err(&info->pdev->dev, "Error reading reg 0x%02x err: %d\n",
+ reg, ret);
+ return ret;
+ }
+
+ /* 12-bit data values have upper 8 bits in buf[0], lower 4 in buf[1] */
+ return (buf[0] << 4) | ((buf[1] >> 4) & 0x0f);
+}
+
static int pmic_read_adc_val(const char *name, int *raw_val,
struct axp288_fg_info *info)
{
@@ -247,24 +259,15 @@
seq_printf(s, " FG_RDC0[%02x] : %02x\n",
AXP288_FG_RDC0_REG,
fuel_gauge_reg_readb(info, AXP288_FG_RDC0_REG));
- seq_printf(s, " FG_OCVH[%02x] : %02x\n",
+ seq_printf(s, " FG_OCV[%02x] : %04x\n",
AXP288_FG_OCVH_REG,
- fuel_gauge_reg_readb(info, AXP288_FG_OCVH_REG));
- seq_printf(s, " FG_OCVL[%02x] : %02x\n",
- AXP288_FG_OCVL_REG,
- fuel_gauge_reg_readb(info, AXP288_FG_OCVL_REG));
- seq_printf(s, "FG_DES_CAP1[%02x] : %02x\n",
+ fuel_gauge_read_12bit_word(info, AXP288_FG_OCVH_REG));
+ seq_printf(s, " FG_DES_CAP[%02x] : %04x\n",
AXP288_FG_DES_CAP1_REG,
- fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG));
- seq_printf(s, "FG_DES_CAP0[%02x] : %02x\n",
- AXP288_FG_DES_CAP0_REG,
- fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP0_REG));
- seq_printf(s, " FG_CC_MTR1[%02x] : %02x\n",
+ fuel_gauge_read_15bit_word(info, AXP288_FG_DES_CAP1_REG));
+ seq_printf(s, " FG_CC_MTR[%02x] : %04x\n",
AXP288_FG_CC_MTR1_REG,
- fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR1_REG));
- seq_printf(s, " FG_CC_MTR0[%02x] : %02x\n",
- AXP288_FG_CC_MTR0_REG,
- fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR0_REG));
+ fuel_gauge_read_15bit_word(info, AXP288_FG_CC_MTR1_REG));
seq_printf(s, " FG_OCV_CAP[%02x] : %02x\n",
AXP288_FG_OCV_CAP_REG,
fuel_gauge_reg_readb(info, AXP288_FG_OCV_CAP_REG));
@@ -417,143 +420,27 @@
return ret;
}
-static int temp_to_adc(struct axp288_fg_info *info, int tval)
-{
- int rntc = 0, i, ret, adc_val;
- int rmin, rmax, tmin, tmax;
- int tcsz = info->pdata->tcsz;
-
- /* get the Rntc resitance value for this temp */
- if (tval > info->pdata->thermistor_curve[0][1]) {
- rntc = info->pdata->thermistor_curve[0][0];
- } else if (tval <= info->pdata->thermistor_curve[tcsz-1][1]) {
- rntc = info->pdata->thermistor_curve[tcsz-1][0];
- } else {
- for (i = 1; i < tcsz; i++) {
- if (tval > info->pdata->thermistor_curve[i][1]) {
- rmin = info->pdata->thermistor_curve[i-1][0];
- rmax = info->pdata->thermistor_curve[i][0];
- tmin = info->pdata->thermistor_curve[i-1][1];
- tmax = info->pdata->thermistor_curve[i][1];
- rntc = rmin + ((rmax - rmin) *
- (tval - tmin) / (tmax - tmin));
- break;
- }
- }
- }
-
- /* we need the current to calculate the proper adc voltage */
- ret = fuel_gauge_reg_readb(info, AXP20X_ADC_RATE);
- if (ret < 0) {
- dev_err(&info->pdev->dev, "%s:read err:%d\n", __func__, ret);
- ret = 0x30;
- }
-
- /*
- * temperature is proportional to NTS thermistor resistance
- * ADC_RATE[5-4] determines current, 00=20uA,01=40uA,10=60uA,11=80uA
- * [12-bit ADC VAL] = R_NTC(Ω) * current / 800
- */
- adc_val = rntc * (20 + (20 * ((ret >> 4) & 0x3))) / 800;
-
- return adc_val;
-}
-
-static int adc_to_temp(struct axp288_fg_info *info, int adc_val)
-{
- int ret, r, i, tval = 0;
- int rmin, rmax, tmin, tmax;
- int tcsz = info->pdata->tcsz;
-
- ret = fuel_gauge_reg_readb(info, AXP20X_ADC_RATE);
- if (ret < 0) {
- dev_err(&info->pdev->dev, "%s:read err:%d\n", __func__, ret);
- ret = 0x30;
- }
-
- /*
- * temperature is proportional to NTS thermistor resistance
- * ADC_RATE[5-4] determines current, 00=20uA,01=40uA,10=60uA,11=80uA
- * R_NTC(Ω) = [12-bit ADC VAL] * 800 / current
- */
- r = adc_val * 800 / (20 + (20 * ((ret >> 4) & 0x3)));
-
- if (r < info->pdata->thermistor_curve[0][0]) {
- tval = info->pdata->thermistor_curve[0][1];
- } else if (r >= info->pdata->thermistor_curve[tcsz-1][0]) {
- tval = info->pdata->thermistor_curve[tcsz-1][1];
- } else {
- for (i = 1; i < tcsz; i++) {
- if (r < info->pdata->thermistor_curve[i][0]) {
- rmin = info->pdata->thermistor_curve[i-1][0];
- rmax = info->pdata->thermistor_curve[i][0];
- tmin = info->pdata->thermistor_curve[i-1][1];
- tmax = info->pdata->thermistor_curve[i][1];
- tval = tmin + ((tmax - tmin) *
- (r - rmin) / (rmax - rmin));
- break;
- }
- }
- }
-
- return tval;
-}
-
-static int fuel_gauge_get_btemp(struct axp288_fg_info *info, int *btemp)
-{
- int ret, raw_val = 0;
-
- ret = pmic_read_adc_val("axp288-batt-temp", &raw_val, info);
- if (ret < 0)
- goto temp_read_fail;
-
- *btemp = adc_to_temp(info, raw_val);
-
-temp_read_fail:
- return ret;
-}
-
static int fuel_gauge_get_vocv(struct axp288_fg_info *info, int *vocv)
{
- int ret, value;
+ int ret;
- /* 12-bit data value, upper 8 in OCVH, lower 4 in OCVL */
- ret = fuel_gauge_reg_readb(info, AXP288_FG_OCVH_REG);
- if (ret < 0)
- goto vocv_read_fail;
- value = ret << 4;
+ ret = fuel_gauge_read_12bit_word(info, AXP288_FG_OCVH_REG);
+ if (ret >= 0)
+ *vocv = VOLTAGE_FROM_ADC(ret);
- ret = fuel_gauge_reg_readb(info, AXP288_FG_OCVL_REG);
- if (ret < 0)
- goto vocv_read_fail;
- value |= (ret & 0xf);
-
- *vocv = VOLTAGE_FROM_ADC(value);
-vocv_read_fail:
return ret;
}
static int fuel_gauge_battery_health(struct axp288_fg_info *info)
{
- int temp, vocv;
- int ret, health = POWER_SUPPLY_HEALTH_UNKNOWN;
-
- ret = fuel_gauge_get_btemp(info, &temp);
- if (ret < 0)
- goto health_read_fail;
+ int ret, vocv, health = POWER_SUPPLY_HEALTH_UNKNOWN;
ret = fuel_gauge_get_vocv(info, &vocv);
if (ret < 0)
goto health_read_fail;
- if (vocv > info->pdata->max_volt)
+ if (vocv > info->max_volt)
health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
- else if (temp > info->pdata->max_temp)
- health = POWER_SUPPLY_HEALTH_OVERHEAT;
- else if (temp < info->pdata->min_temp)
- health = POWER_SUPPLY_HEALTH_COLD;
- else if (vocv < info->pdata->min_volt)
- health = POWER_SUPPLY_HEALTH_DEAD;
else
health = POWER_SUPPLY_HEALTH_GOOD;
@@ -561,28 +448,6 @@
return health;
}
-static int fuel_gauge_set_high_btemp_alert(struct axp288_fg_info *info)
-{
- int ret, adc_val;
-
- /* program temperature threshold as 1/16 ADC value */
- adc_val = temp_to_adc(info, info->pdata->max_temp);
- ret = fuel_gauge_reg_writeb(info, AXP20X_V_HTF_DISCHRG, adc_val >> 4);
-
- return ret;
-}
-
-static int fuel_gauge_set_low_btemp_alert(struct axp288_fg_info *info)
-{
- int ret, adc_val;
-
- /* program temperature threshold as 1/16 ADC value */
- adc_val = temp_to_adc(info, info->pdata->min_temp);
- ret = fuel_gauge_reg_writeb(info, AXP20X_V_LTF_DISCHRG, adc_val >> 4);
-
- return ret;
-}
-
static int fuel_gauge_get_property(struct power_supply *ps,
enum power_supply_property prop,
union power_supply_propval *val)
@@ -643,58 +508,25 @@
goto fuel_gauge_read_err;
val->intval = (ret & 0x0f);
break;
- case POWER_SUPPLY_PROP_TEMP:
- ret = fuel_gauge_get_btemp(info, &value);
- if (ret < 0)
- goto fuel_gauge_read_err;
- val->intval = PROP_TEMP(value);
- break;
- case POWER_SUPPLY_PROP_TEMP_MAX:
- case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
- val->intval = PROP_TEMP(info->pdata->max_temp);
- break;
- case POWER_SUPPLY_PROP_TEMP_MIN:
- case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
- val->intval = PROP_TEMP(info->pdata->min_temp);
- break;
case POWER_SUPPLY_PROP_TECHNOLOGY:
val->intval = POWER_SUPPLY_TECHNOLOGY_LION;
break;
case POWER_SUPPLY_PROP_CHARGE_NOW:
- ret = fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR1_REG);
+ ret = fuel_gauge_read_15bit_word(info, AXP288_FG_CC_MTR1_REG);
if (ret < 0)
goto fuel_gauge_read_err;
- value = (ret & FG_CC_MTR1_VAL_MASK) << 8;
- ret = fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR0_REG);
- if (ret < 0)
- goto fuel_gauge_read_err;
- value |= (ret & FG_CC_MTR0_VAL_MASK);
- val->intval = value * FG_DES_CAP_RES_LSB;
+ val->intval = ret * FG_DES_CAP_RES_LSB;
break;
case POWER_SUPPLY_PROP_CHARGE_FULL:
- ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG);
+ ret = fuel_gauge_read_15bit_word(info, AXP288_FG_DES_CAP1_REG);
if (ret < 0)
goto fuel_gauge_read_err;
- value = (ret & FG_DES_CAP1_VAL_MASK) << 8;
- ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP0_REG);
- if (ret < 0)
- goto fuel_gauge_read_err;
- value |= (ret & FG_DES_CAP0_VAL_MASK);
- val->intval = value * FG_DES_CAP_RES_LSB;
- break;
- case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
- val->intval = PROP_CURR(info->pdata->design_cap);
+ val->intval = ret * FG_DES_CAP_RES_LSB;
break;
case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
- val->intval = PROP_VOLT(info->pdata->max_volt);
- break;
- case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
- val->intval = PROP_VOLT(info->pdata->min_volt);
- break;
- case POWER_SUPPLY_PROP_MODEL_NAME:
- val->strval = info->pdata->battid;
+ val->intval = PROP_VOLT(info->max_volt);
break;
default:
mutex_unlock(&info->lock);
@@ -718,35 +550,6 @@
mutex_lock(&info->lock);
switch (prop) {
- case POWER_SUPPLY_PROP_STATUS:
- info->status = val->intval;
- break;
- case POWER_SUPPLY_PROP_TEMP_MIN:
- case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
- if ((val->intval < PD_DEF_MIN_TEMP) ||
- (val->intval > PD_DEF_MAX_TEMP)) {
- ret = -EINVAL;
- break;
- }
- info->pdata->min_temp = UNPROP_TEMP(val->intval);
- ret = fuel_gauge_set_low_btemp_alert(info);
- if (ret < 0)
- dev_err(&info->pdev->dev,
- "temp alert min set fail:%d\n", ret);
- break;
- case POWER_SUPPLY_PROP_TEMP_MAX:
- case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
- if ((val->intval < PD_DEF_MIN_TEMP) ||
- (val->intval > PD_DEF_MAX_TEMP)) {
- ret = -EINVAL;
- break;
- }
- info->pdata->max_temp = UNPROP_TEMP(val->intval);
- ret = fuel_gauge_set_high_btemp_alert(info);
- if (ret < 0)
- dev_err(&info->pdev->dev,
- "temp alert max set fail:%d\n", ret);
- break;
case POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN:
if ((val->intval < 0) || (val->intval > 15)) {
ret = -EINVAL;
@@ -774,11 +577,6 @@
int ret;
switch (psp) {
- case POWER_SUPPLY_PROP_STATUS:
- case POWER_SUPPLY_PROP_TEMP_MIN:
- case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
- case POWER_SUPPLY_PROP_TEMP_MAX:
- case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
case POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN:
ret = 1;
break;
@@ -863,158 +661,6 @@
.external_power_changed = fuel_gauge_external_power_changed,
};
-static int fuel_gauge_set_lowbatt_thresholds(struct axp288_fg_info *info)
-{
- int ret;
- u8 reg_val;
-
- ret = fuel_gauge_reg_readb(info, AXP20X_FG_RES);
- if (ret < 0) {
- dev_err(&info->pdev->dev, "%s:read err:%d\n", __func__, ret);
- return ret;
- }
- ret = (ret & FG_REP_CAP_VAL_MASK);
-
- if (ret > FG_LOW_CAP_WARN_THR)
- reg_val = FG_LOW_CAP_WARN_THR;
- else if (ret > FG_LOW_CAP_CRIT_THR)
- reg_val = FG_LOW_CAP_CRIT_THR;
- else
- reg_val = FG_LOW_CAP_SHDN_THR;
-
- reg_val |= FG_LOW_CAP_THR1_VAL;
- ret = fuel_gauge_reg_writeb(info, AXP288_FG_LOW_CAP_REG, reg_val);
- if (ret < 0)
- dev_err(&info->pdev->dev, "%s:write err:%d\n", __func__, ret);
-
- return ret;
-}
-
-static int fuel_gauge_program_vbatt_full(struct axp288_fg_info *info)
-{
- int ret;
- u8 val;
-
- ret = fuel_gauge_reg_readb(info, AXP20X_CHRG_CTRL1);
- if (ret < 0)
- goto fg_prog_ocv_fail;
- else
- val = (ret & ~CHRG_CCCV_CV_MASK);
-
- switch (info->pdata->max_volt) {
- case CV_4100:
- val |= (CHRG_CCCV_CV_4100MV << CHRG_CCCV_CV_BIT_POS);
- break;
- case CV_4150:
- val |= (CHRG_CCCV_CV_4150MV << CHRG_CCCV_CV_BIT_POS);
- break;
- case CV_4200:
- val |= (CHRG_CCCV_CV_4200MV << CHRG_CCCV_CV_BIT_POS);
- break;
- case CV_4350:
- val |= (CHRG_CCCV_CV_4350MV << CHRG_CCCV_CV_BIT_POS);
- break;
- default:
- val |= (CHRG_CCCV_CV_4200MV << CHRG_CCCV_CV_BIT_POS);
- break;
- }
-
- ret = fuel_gauge_reg_writeb(info, AXP20X_CHRG_CTRL1, val);
-fg_prog_ocv_fail:
- return ret;
-}
-
-static int fuel_gauge_program_design_cap(struct axp288_fg_info *info)
-{
- int ret;
-
- ret = fuel_gauge_reg_writeb(info,
- AXP288_FG_DES_CAP1_REG, info->pdata->cap1);
- if (ret < 0)
- goto fg_prog_descap_fail;
-
- ret = fuel_gauge_reg_writeb(info,
- AXP288_FG_DES_CAP0_REG, info->pdata->cap0);
-
-fg_prog_descap_fail:
- return ret;
-}
-
-static int fuel_gauge_program_ocv_curve(struct axp288_fg_info *info)
-{
- int ret = 0, i;
-
- for (i = 0; i < OCV_CURVE_SIZE; i++) {
- ret = fuel_gauge_reg_writeb(info,
- AXP288_FG_OCV_CURVE_REG + i, info->pdata->ocv_curve[i]);
- if (ret < 0)
- goto fg_prog_ocv_fail;
- }
-
-fg_prog_ocv_fail:
- return ret;
-}
-
-static int fuel_gauge_program_rdc_vals(struct axp288_fg_info *info)
-{
- int ret;
-
- ret = fuel_gauge_reg_writeb(info,
- AXP288_FG_RDC1_REG, info->pdata->rdc1);
- if (ret < 0)
- goto fg_prog_ocv_fail;
-
- ret = fuel_gauge_reg_writeb(info,
- AXP288_FG_RDC0_REG, info->pdata->rdc0);
-
-fg_prog_ocv_fail:
- return ret;
-}
-
-static void fuel_gauge_init_config_regs(struct axp288_fg_info *info)
-{
- int ret;
-
- /*
- * check if the config data is already
- * programmed and if so just return.
- */
-
- ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG);
- if (ret < 0) {
- dev_warn(&info->pdev->dev, "CAP1 reg read err!!\n");
- } else if (!(ret & FG_DES_CAP1_VALID)) {
- dev_info(&info->pdev->dev, "FG data needs to be initialized\n");
- } else {
- dev_info(&info->pdev->dev, "FG data is already initialized\n");
- return;
- }
-
- ret = fuel_gauge_program_vbatt_full(info);
- if (ret < 0)
- dev_err(&info->pdev->dev, "set vbatt full fail:%d\n", ret);
-
- ret = fuel_gauge_program_design_cap(info);
- if (ret < 0)
- dev_err(&info->pdev->dev, "set design cap fail:%d\n", ret);
-
- ret = fuel_gauge_program_rdc_vals(info);
- if (ret < 0)
- dev_err(&info->pdev->dev, "set rdc fail:%d\n", ret);
-
- ret = fuel_gauge_program_ocv_curve(info);
- if (ret < 0)
- dev_err(&info->pdev->dev, "set ocv curve fail:%d\n", ret);
-
- ret = fuel_gauge_set_lowbatt_thresholds(info);
- if (ret < 0)
- dev_err(&info->pdev->dev, "lowbatt thr set fail:%d\n", ret);
-
- ret = fuel_gauge_reg_writeb(info, AXP20X_CC_CTRL, 0xef);
- if (ret < 0)
- dev_err(&info->pdev->dev, "gauge cntl set fail:%d\n", ret);
-}
-
static void fuel_gauge_init_irq(struct axp288_fg_info *info)
{
int ret, i, pirq;
@@ -1052,29 +698,6 @@
}
}
-static void fuel_gauge_init_hw_regs(struct axp288_fg_info *info)
-{
- int ret;
- unsigned int val;
-
- ret = fuel_gauge_set_high_btemp_alert(info);
- if (ret < 0)
- dev_err(&info->pdev->dev, "high batt temp set fail:%d\n", ret);
-
- ret = fuel_gauge_set_low_btemp_alert(info);
- if (ret < 0)
- dev_err(&info->pdev->dev, "low batt temp set fail:%d\n", ret);
-
- /* enable interrupts */
- val = fuel_gauge_reg_readb(info, AXP20X_IRQ3_EN);
- val |= TEMP_IRQ_CFG_MASK;
- fuel_gauge_reg_writeb(info, AXP20X_IRQ3_EN, val);
-
- val = fuel_gauge_reg_readb(info, AXP20X_IRQ4_EN);
- val |= FG_IRQ_CFG_LOWBATT_MASK;
- val = fuel_gauge_reg_writeb(info, AXP20X_IRQ4_EN, val);
-}
-
static int axp288_fuel_gauge_probe(struct platform_device *pdev)
{
int ret = 0;
@@ -1090,15 +713,39 @@
info->regmap = axp20x->regmap;
info->regmap_irqc = axp20x->regmap_irqc;
info->status = POWER_SUPPLY_STATUS_UNKNOWN;
- info->pdata = pdev->dev.platform_data;
- if (!info->pdata)
- return -ENODEV;
platform_set_drvdata(pdev, info);
mutex_init(&info->lock);
INIT_DELAYED_WORK(&info->status_monitor, fuel_gauge_status_monitor);
+ ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG);
+ if (ret < 0)
+ return ret;
+
+ if (!(ret & FG_DES_CAP1_VALID)) {
+ dev_err(&pdev->dev, "axp288 not configured by firmware\n");
+ return -ENODEV;
+ }
+
+ ret = fuel_gauge_reg_readb(info, AXP20X_CHRG_CTRL1);
+ if (ret < 0)
+ return ret;
+ switch ((ret & CHRG_CCCV_CV_MASK) >> CHRG_CCCV_CV_BIT_POS) {
+ case CHRG_CCCV_CV_4100MV:
+ info->max_volt = 4100;
+ break;
+ case CHRG_CCCV_CV_4150MV:
+ info->max_volt = 4150;
+ break;
+ case CHRG_CCCV_CV_4200MV:
+ info->max_volt = 4200;
+ break;
+ case CHRG_CCCV_CV_4350MV:
+ info->max_volt = 4350;
+ break;
+ }
+
psy_cfg.drv_data = info;
info->bat = power_supply_register(&pdev->dev, &fuel_gauge_desc, &psy_cfg);
if (IS_ERR(info->bat)) {
@@ -1108,12 +755,10 @@
}
fuel_gauge_create_debugfs(info);
- fuel_gauge_init_config_regs(info);
fuel_gauge_init_irq(info);
- fuel_gauge_init_hw_regs(info);
schedule_delayed_work(&info->status_monitor, STATUS_MON_DELAY_JIFFIES);
- return ret;
+ return 0;
}
static const struct platform_device_id axp288_fg_id_table[] = {
diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c
index 73e2f0b..c4770a9 100644
--- a/drivers/power/supply/bq2415x_charger.c
+++ b/drivers/power/supply/bq2415x_charger.c
@@ -1569,6 +1569,11 @@
acpi_id =
acpi_match_device(client->dev.driver->acpi_match_table,
&client->dev);
+ if (!acpi_id) {
+ dev_err(&client->dev, "failed to match device name\n");
+ ret = -ENODEV;
+ goto error_1;
+ }
name = kasprintf(GFP_KERNEL, "%s-%d", acpi_id->id, num);
}
if (!name) {
diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c
index e958433..a4f0849 100644
--- a/drivers/power/supply/bq24190_charger.c
+++ b/drivers/power/supply/bq24190_charger.c
@@ -144,10 +144,7 @@
* so the first read after a fault returns the latched value and subsequent
* reads return the current value. In order to return the fault status
* to the user, have the interrupt handler save the reg's value and retrieve
- * it in the appropriate health/status routine. Each routine has its own
- * flag indicating whether it should use the value stored by the last run
- * of the interrupt handler or do an actual reg read. That way each routine
- * can report back whatever fault may have occured.
+ * it in the appropriate health/status routine.
*/
struct bq24190_dev_info {
struct i2c_client *client;
@@ -159,10 +156,6 @@
unsigned int gpio_int;
unsigned int irq;
struct mutex f_reg_lock;
- bool first_time;
- bool charger_health_valid;
- bool battery_health_valid;
- bool battery_status_valid;
u8 f_reg;
u8 ss_reg;
u8 watchdog;
@@ -199,7 +192,7 @@
4400000
};
-/* REG06[1:0] (TREG) in tenths of degrees Celcius */
+/* REG06[1:0] (TREG) in tenths of degrees Celsius */
static const int bq24190_ictrc_treg_values[] = {
600, 800, 1000, 1200
};
@@ -636,21 +629,11 @@
union power_supply_propval *val)
{
u8 v;
- int health, ret;
+ int health;
mutex_lock(&bdi->f_reg_lock);
-
- if (bdi->charger_health_valid) {
- v = bdi->f_reg;
- bdi->charger_health_valid = false;
- mutex_unlock(&bdi->f_reg_lock);
- } else {
- mutex_unlock(&bdi->f_reg_lock);
-
- ret = bq24190_read(bdi, BQ24190_REG_F, &v);
- if (ret < 0)
- return ret;
- }
+ v = bdi->f_reg;
+ mutex_unlock(&bdi->f_reg_lock);
if (v & BQ24190_REG_F_BOOST_FAULT_MASK) {
/*
@@ -937,18 +920,8 @@
int status, ret;
mutex_lock(&bdi->f_reg_lock);
-
- if (bdi->battery_status_valid) {
- chrg_fault = bdi->f_reg;
- bdi->battery_status_valid = false;
- mutex_unlock(&bdi->f_reg_lock);
- } else {
- mutex_unlock(&bdi->f_reg_lock);
-
- ret = bq24190_read(bdi, BQ24190_REG_F, &chrg_fault);
- if (ret < 0)
- return ret;
- }
+ chrg_fault = bdi->f_reg;
+ mutex_unlock(&bdi->f_reg_lock);
chrg_fault &= BQ24190_REG_F_CHRG_FAULT_MASK;
chrg_fault >>= BQ24190_REG_F_CHRG_FAULT_SHIFT;
@@ -996,21 +969,11 @@
union power_supply_propval *val)
{
u8 v;
- int health, ret;
+ int health;
mutex_lock(&bdi->f_reg_lock);
-
- if (bdi->battery_health_valid) {
- v = bdi->f_reg;
- bdi->battery_health_valid = false;
- mutex_unlock(&bdi->f_reg_lock);
- } else {
- mutex_unlock(&bdi->f_reg_lock);
-
- ret = bq24190_read(bdi, BQ24190_REG_F, &v);
- if (ret < 0)
- return ret;
- }
+ v = bdi->f_reg;
+ mutex_unlock(&bdi->f_reg_lock);
if (v & BQ24190_REG_F_BAT_FAULT_MASK) {
health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
@@ -1197,9 +1160,12 @@
static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
{
struct bq24190_dev_info *bdi = data;
- bool alert_userspace = false;
+ const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK;
+ const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK
+ | BQ24190_REG_F_NTC_FAULT_MASK;
+ bool alert_charger = false, alert_battery = false;
u8 ss_reg = 0, f_reg = 0;
- int ret;
+ int i, ret;
pm_runtime_get_sync(bdi->dev);
@@ -1209,6 +1175,32 @@
goto out;
}
+ i = 0;
+ do {
+ ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg);
+ if (ret < 0) {
+ dev_err(bdi->dev, "Can't read F reg: %d\n", ret);
+ goto out;
+ }
+ } while (f_reg && ++i < 2);
+
+ if (f_reg != bdi->f_reg) {
+ dev_info(bdi->dev,
+ "Fault: boost %d, charge %d, battery %d, ntc %d\n",
+ !!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK),
+ !!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK),
+ !!(f_reg & BQ24190_REG_F_BAT_FAULT_MASK),
+ !!(f_reg & BQ24190_REG_F_NTC_FAULT_MASK));
+
+ mutex_lock(&bdi->f_reg_lock);
+ if ((bdi->f_reg & battery_mask_f) != (f_reg & battery_mask_f))
+ alert_battery = true;
+ if ((bdi->f_reg & ~battery_mask_f) != (f_reg & ~battery_mask_f))
+ alert_charger = true;
+ bdi->f_reg = f_reg;
+ mutex_unlock(&bdi->f_reg_lock);
+ }
+
if (ss_reg != bdi->ss_reg) {
/*
* The device is in host mode so when PG_STAT goes from 1->0
@@ -1225,47 +1217,17 @@
ret);
}
+ if ((bdi->ss_reg & battery_mask_ss) != (ss_reg & battery_mask_ss))
+ alert_battery = true;
+ if ((bdi->ss_reg & ~battery_mask_ss) != (ss_reg & ~battery_mask_ss))
+ alert_charger = true;
bdi->ss_reg = ss_reg;
- alert_userspace = true;
}
- mutex_lock(&bdi->f_reg_lock);
-
- ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg);
- if (ret < 0) {
- mutex_unlock(&bdi->f_reg_lock);
- dev_err(bdi->dev, "Can't read F reg: %d\n", ret);
- goto out;
- }
-
- if (f_reg != bdi->f_reg) {
- bdi->f_reg = f_reg;
- bdi->charger_health_valid = true;
- bdi->battery_health_valid = true;
- bdi->battery_status_valid = true;
-
- alert_userspace = true;
- }
-
- mutex_unlock(&bdi->f_reg_lock);
-
- /*
- * Sometimes bq24190 gives a steady trickle of interrupts even
- * though the watchdog timer is turned off and neither the STATUS
- * nor FAULT registers have changed. Weed out these sprurious
- * interrupts so userspace isn't alerted for no reason.
- * In addition, the chip always generates an interrupt after
- * register reset so we should ignore that one (the very first
- * interrupt received).
- */
- if (alert_userspace) {
- if (!bdi->first_time) {
- power_supply_changed(bdi->charger);
- power_supply_changed(bdi->battery);
- } else {
- bdi->first_time = false;
- }
- }
+ if (alert_charger)
+ power_supply_changed(bdi->charger);
+ if (alert_battery)
+ power_supply_changed(bdi->battery);
out:
pm_runtime_put_sync(bdi->dev);
@@ -1300,6 +1262,10 @@
goto out;
ret = bq24190_set_mode_host(bdi);
+ if (ret < 0)
+ goto out;
+
+ ret = bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
out:
pm_runtime_put_sync(bdi->dev);
return ret;
@@ -1375,10 +1341,8 @@
bdi->model = id->driver_data;
strncpy(bdi->model_name, id->name, I2C_NAME_SIZE);
mutex_init(&bdi->f_reg_lock);
- bdi->first_time = true;
- bdi->charger_health_valid = false;
- bdi->battery_health_valid = false;
- bdi->battery_status_valid = false;
+ bdi->f_reg = 0;
+ bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */
i2c_set_clientdata(client, bdi);
@@ -1392,22 +1356,13 @@
return -EINVAL;
}
- ret = devm_request_threaded_irq(dev, bdi->irq, NULL,
- bq24190_irq_handler_thread,
- IRQF_TRIGGER_RISING | IRQF_ONESHOT,
- "bq24190-charger", bdi);
- if (ret < 0) {
- dev_err(dev, "Can't set up irq handler\n");
- goto out1;
- }
-
pm_runtime_enable(dev);
pm_runtime_resume(dev);
ret = bq24190_hw_init(bdi);
if (ret < 0) {
dev_err(dev, "Hardware init failed\n");
- goto out2;
+ goto out1;
}
charger_cfg.drv_data = bdi;
@@ -1418,7 +1373,7 @@
if (IS_ERR(bdi->charger)) {
dev_err(dev, "Can't register charger\n");
ret = PTR_ERR(bdi->charger);
- goto out2;
+ goto out1;
}
battery_cfg.drv_data = bdi;
@@ -1427,27 +1382,39 @@
if (IS_ERR(bdi->battery)) {
dev_err(dev, "Can't register battery\n");
ret = PTR_ERR(bdi->battery);
- goto out3;
+ goto out2;
}
ret = bq24190_sysfs_create_group(bdi);
if (ret) {
dev_err(dev, "Can't create sysfs entries\n");
+ goto out3;
+ }
+
+ ret = devm_request_threaded_irq(dev, bdi->irq, NULL,
+ bq24190_irq_handler_thread,
+ IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+ "bq24190-charger", bdi);
+ if (ret < 0) {
+ dev_err(dev, "Can't set up irq handler\n");
goto out4;
}
return 0;
out4:
- power_supply_unregister(bdi->battery);
+ bq24190_sysfs_remove_group(bdi);
+
out3:
- power_supply_unregister(bdi->charger);
+ power_supply_unregister(bdi->battery);
+
out2:
- pm_runtime_disable(dev);
+ power_supply_unregister(bdi->charger);
+
out1:
+ pm_runtime_disable(dev);
if (bdi->gpio_int)
gpio_free(bdi->gpio_int);
-
return ret;
}
@@ -1488,12 +1455,13 @@
struct i2c_client *client = to_i2c_client(dev);
struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
- bdi->charger_health_valid = false;
- bdi->battery_health_valid = false;
- bdi->battery_status_valid = false;
+ bdi->f_reg = 0;
+ bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */
pm_runtime_get_sync(bdi->dev);
bq24190_register_reset(bdi);
+ bq24190_set_mode_host(bdi);
+ bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
pm_runtime_put_sync(bdi->dev);
/* Things may have changed while suspended so alert upper layer */
diff --git a/drivers/power/supply/bq24735-charger.c b/drivers/power/supply/bq24735-charger.c
index eb7783b..eb01453 100644
--- a/drivers/power/supply/bq24735-charger.c
+++ b/drivers/power/supply/bq24735-charger.c
@@ -50,6 +50,8 @@
struct bq24735_platform *pdata;
struct mutex lock;
struct gpio_desc *status_gpio;
+ struct delayed_work poll;
+ u32 poll_interval;
bool charging;
};
@@ -105,26 +107,6 @@
return bq24735_write_word(client, reg, tmp);
}
-static inline int bq24735_enable_charging(struct bq24735 *charger)
-{
- if (charger->pdata->ext_control)
- return 0;
-
- return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
- BQ24735_CHG_OPT_CHARGE_DISABLE,
- ~BQ24735_CHG_OPT_CHARGE_DISABLE);
-}
-
-static inline int bq24735_disable_charging(struct bq24735 *charger)
-{
- if (charger->pdata->ext_control)
- return 0;
-
- return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
- BQ24735_CHG_OPT_CHARGE_DISABLE,
- BQ24735_CHG_OPT_CHARGE_DISABLE);
-}
-
static int bq24735_config_charger(struct bq24735 *charger)
{
struct bq24735_platform *pdata = charger->pdata;
@@ -176,6 +158,31 @@
return 0;
}
+static inline int bq24735_enable_charging(struct bq24735 *charger)
+{
+ int ret;
+
+ if (charger->pdata->ext_control)
+ return 0;
+
+ ret = bq24735_config_charger(charger);
+ if (ret)
+ return ret;
+
+ return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
+ BQ24735_CHG_OPT_CHARGE_DISABLE, 0);
+}
+
+static inline int bq24735_disable_charging(struct bq24735 *charger)
+{
+ if (charger->pdata->ext_control)
+ return 0;
+
+ return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
+ BQ24735_CHG_OPT_CHARGE_DISABLE,
+ BQ24735_CHG_OPT_CHARGE_DISABLE);
+}
+
static bool bq24735_charger_is_present(struct bq24735 *charger)
{
if (charger->status_gpio) {
@@ -185,7 +192,7 @@
ac = bq24735_read_word(charger->client, BQ24735_CHG_OPT);
if (ac < 0) {
- dev_err(&charger->client->dev,
+ dev_dbg(&charger->client->dev,
"Failed to read charger options : %d\n",
ac);
return false;
@@ -210,11 +217,8 @@
return !(ret & BQ24735_CHG_OPT_CHARGE_DISABLE);
}
-static irqreturn_t bq24735_charger_isr(int irq, void *devid)
+static void bq24735_update(struct bq24735 *charger)
{
- struct power_supply *psy = devid;
- struct bq24735 *charger = to_bq24735(psy);
-
mutex_lock(&charger->lock);
if (charger->charging && bq24735_charger_is_present(charger))
@@ -224,11 +228,29 @@
mutex_unlock(&charger->lock);
- power_supply_changed(psy);
+ power_supply_changed(charger->charger);
+}
+
+static irqreturn_t bq24735_charger_isr(int irq, void *devid)
+{
+ struct power_supply *psy = devid;
+ struct bq24735 *charger = to_bq24735(psy);
+
+ bq24735_update(charger);
return IRQ_HANDLED;
}
+static void bq24735_poll(struct work_struct *work)
+{
+ struct bq24735 *charger = container_of(work, struct bq24735, poll.work);
+
+ bq24735_update(charger);
+
+ schedule_delayed_work(&charger->poll,
+ msecs_to_jiffies(charger->poll_interval));
+}
+
static int bq24735_charger_get_property(struct power_supply *psy,
enum power_supply_property psp,
union power_supply_propval *val)
@@ -276,7 +298,6 @@
mutex_unlock(&charger->lock);
if (ret)
return ret;
- bq24735_config_charger(charger);
break;
case POWER_SUPPLY_STATUS_DISCHARGING:
case POWER_SUPPLY_STATUS_NOT_CHARGING:
@@ -395,7 +416,7 @@
return ret;
}
- if (!charger->status_gpio || bq24735_charger_is_present(charger)) {
+ if (bq24735_charger_is_present(charger)) {
ret = bq24735_read_word(client, BQ24735_MANUFACTURER_ID);
if (ret < 0) {
dev_err(&client->dev, "Failed to read manufacturer id : %d\n",
@@ -416,16 +437,7 @@
"device id mismatch. 0x000b != 0x%04x\n", ret);
return -ENODEV;
}
- }
- ret = bq24735_config_charger(charger);
- if (ret < 0) {
- dev_err(&client->dev, "failed in configuring charger");
- return ret;
- }
-
- /* check for AC adapter presence */
- if (bq24735_charger_is_present(charger)) {
ret = bq24735_enable_charging(charger);
if (ret < 0) {
dev_err(&client->dev, "Failed to enable charging\n");
@@ -456,11 +468,32 @@
client->irq, ret);
return ret;
}
+ } else {
+ ret = device_property_read_u32(&client->dev, "poll-interval",
+ &charger->poll_interval);
+ if (ret)
+ return 0;
+ if (!charger->poll_interval)
+ return 0;
+
+ INIT_DELAYED_WORK(&charger->poll, bq24735_poll);
+ schedule_delayed_work(&charger->poll,
+ msecs_to_jiffies(charger->poll_interval));
}
return 0;
}
+static int bq24735_charger_remove(struct i2c_client *client)
+{
+ struct bq24735 *charger = i2c_get_clientdata(client);
+
+ if (charger->poll_interval)
+ cancel_delayed_work_sync(&charger->poll);
+
+ return 0;
+}
+
static const struct i2c_device_id bq24735_charger_id[] = {
{ "bq24735-charger", 0 },
{}
@@ -479,6 +512,7 @@
.of_match_table = bq24735_match_ids,
},
.probe = bq24735_charger_probe,
+ .remove = bq24735_charger_remove,
.id_table = bq24735_charger_id,
};
diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 08c36b8..398801a 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -22,8 +22,14 @@
* http://www.ti.com/product/bq27010
* http://www.ti.com/product/bq27210
* http://www.ti.com/product/bq27500
+ * http://www.ti.com/product/bq27510-g1
+ * http://www.ti.com/product/bq27510-g2
* http://www.ti.com/product/bq27510-g3
* http://www.ti.com/product/bq27520-g4
+ * http://www.ti.com/product/bq27520-g1
+ * http://www.ti.com/product/bq27520-g2
+ * http://www.ti.com/product/bq27520-g3
+ * http://www.ti.com/product/bq27520-g4
* http://www.ti.com/product/bq27530-g1
* http://www.ti.com/product/bq27531-g1
* http://www.ti.com/product/bq27541-g1
@@ -145,7 +151,7 @@
[BQ27XXX_REG_DCAP] = 0x76,
[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
},
- [BQ27500] = {
+ [BQ2750X] = {
[BQ27XXX_REG_CTRL] = 0x00,
[BQ27XXX_REG_TEMP] = 0x06,
[BQ27XXX_REG_INT_TEMP] = 0x28,
@@ -164,7 +170,7 @@
[BQ27XXX_REG_DCAP] = 0x3c,
[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
},
- [BQ27510] = {
+ [BQ2751X] = {
[BQ27XXX_REG_CTRL] = 0x00,
[BQ27XXX_REG_TEMP] = 0x06,
[BQ27XXX_REG_INT_TEMP] = 0x28,
@@ -183,6 +189,158 @@
[BQ27XXX_REG_DCAP] = 0x2e,
[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
},
+ [BQ27500] = {
+ [BQ27XXX_REG_CTRL] = 0x00,
+ [BQ27XXX_REG_TEMP] = 0x06,
+ [BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_VOLT] = 0x08,
+ [BQ27XXX_REG_AI] = 0x14,
+ [BQ27XXX_REG_FLAGS] = 0x0a,
+ [BQ27XXX_REG_TTE] = 0x16,
+ [BQ27XXX_REG_TTF] = 0x18,
+ [BQ27XXX_REG_TTES] = 0x1c,
+ [BQ27XXX_REG_TTECP] = 0x26,
+ [BQ27XXX_REG_NAC] = 0x0c,
+ [BQ27XXX_REG_FCC] = 0x12,
+ [BQ27XXX_REG_CYCT] = 0x2a,
+ [BQ27XXX_REG_AE] = 0x22,
+ [BQ27XXX_REG_SOC] = 0x2c,
+ [BQ27XXX_REG_DCAP] = 0x3c,
+ [BQ27XXX_REG_AP] = 0x24,
+ },
+ [BQ27510G1] = {
+ [BQ27XXX_REG_CTRL] = 0x00,
+ [BQ27XXX_REG_TEMP] = 0x06,
+ [BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_VOLT] = 0x08,
+ [BQ27XXX_REG_AI] = 0x14,
+ [BQ27XXX_REG_FLAGS] = 0x0a,
+ [BQ27XXX_REG_TTE] = 0x16,
+ [BQ27XXX_REG_TTF] = 0x18,
+ [BQ27XXX_REG_TTES] = 0x1c,
+ [BQ27XXX_REG_TTECP] = 0x26,
+ [BQ27XXX_REG_NAC] = 0x0c,
+ [BQ27XXX_REG_FCC] = 0x12,
+ [BQ27XXX_REG_CYCT] = 0x2a,
+ [BQ27XXX_REG_AE] = 0x22,
+ [BQ27XXX_REG_SOC] = 0x2c,
+ [BQ27XXX_REG_DCAP] = 0x3c,
+ [BQ27XXX_REG_AP] = 0x24,
+ },
+ [BQ27510G2] = {
+ [BQ27XXX_REG_CTRL] = 0x00,
+ [BQ27XXX_REG_TEMP] = 0x06,
+ [BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_VOLT] = 0x08,
+ [BQ27XXX_REG_AI] = 0x14,
+ [BQ27XXX_REG_FLAGS] = 0x0a,
+ [BQ27XXX_REG_TTE] = 0x16,
+ [BQ27XXX_REG_TTF] = 0x18,
+ [BQ27XXX_REG_TTES] = 0x1c,
+ [BQ27XXX_REG_TTECP] = 0x26,
+ [BQ27XXX_REG_NAC] = 0x0c,
+ [BQ27XXX_REG_FCC] = 0x12,
+ [BQ27XXX_REG_CYCT] = 0x2a,
+ [BQ27XXX_REG_AE] = 0x22,
+ [BQ27XXX_REG_SOC] = 0x2c,
+ [BQ27XXX_REG_DCAP] = 0x3c,
+ [BQ27XXX_REG_AP] = 0x24,
+ },
+ [BQ27510G3] = {
+ [BQ27XXX_REG_CTRL] = 0x00,
+ [BQ27XXX_REG_TEMP] = 0x06,
+ [BQ27XXX_REG_INT_TEMP] = 0x28,
+ [BQ27XXX_REG_VOLT] = 0x08,
+ [BQ27XXX_REG_AI] = 0x14,
+ [BQ27XXX_REG_FLAGS] = 0x0a,
+ [BQ27XXX_REG_TTE] = 0x16,
+ [BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_TTES] = 0x1a,
+ [BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_NAC] = 0x0c,
+ [BQ27XXX_REG_FCC] = 0x12,
+ [BQ27XXX_REG_CYCT] = 0x1e,
+ [BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_SOC] = 0x20,
+ [BQ27XXX_REG_DCAP] = 0x2e,
+ [BQ27XXX_REG_AP] = INVALID_REG_ADDR,
+ },
+ [BQ27520G1] = {
+ [BQ27XXX_REG_CTRL] = 0x00,
+ [BQ27XXX_REG_TEMP] = 0x06,
+ [BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_VOLT] = 0x08,
+ [BQ27XXX_REG_AI] = 0x14,
+ [BQ27XXX_REG_FLAGS] = 0x0a,
+ [BQ27XXX_REG_TTE] = 0x16,
+ [BQ27XXX_REG_TTF] = 0x18,
+ [BQ27XXX_REG_TTES] = 0x1c,
+ [BQ27XXX_REG_TTECP] = 0x26,
+ [BQ27XXX_REG_NAC] = 0x0c,
+ [BQ27XXX_REG_FCC] = 0x12,
+ [BQ27XXX_REG_CYCT] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_AE] = 0x22,
+ [BQ27XXX_REG_SOC] = 0x2c,
+ [BQ27XXX_REG_DCAP] = 0x3c,
+ [BQ27XXX_REG_AP] = 0x24,
+ },
+ [BQ27520G2] = {
+ [BQ27XXX_REG_CTRL] = 0x00,
+ [BQ27XXX_REG_TEMP] = 0x06,
+ [BQ27XXX_REG_INT_TEMP] = 0x36,
+ [BQ27XXX_REG_VOLT] = 0x08,
+ [BQ27XXX_REG_AI] = 0x14,
+ [BQ27XXX_REG_FLAGS] = 0x0a,
+ [BQ27XXX_REG_TTE] = 0x16,
+ [BQ27XXX_REG_TTF] = 0x18,
+ [BQ27XXX_REG_TTES] = 0x1c,
+ [BQ27XXX_REG_TTECP] = 0x26,
+ [BQ27XXX_REG_NAC] = 0x0c,
+ [BQ27XXX_REG_FCC] = 0x12,
+ [BQ27XXX_REG_CYCT] = 0x2a,
+ [BQ27XXX_REG_AE] = 0x22,
+ [BQ27XXX_REG_SOC] = 0x2c,
+ [BQ27XXX_REG_DCAP] = 0x3c,
+ [BQ27XXX_REG_AP] = 0x24,
+ },
+ [BQ27520G3] = {
+ [BQ27XXX_REG_CTRL] = 0x00,
+ [BQ27XXX_REG_TEMP] = 0x06,
+ [BQ27XXX_REG_INT_TEMP] = 0x36,
+ [BQ27XXX_REG_VOLT] = 0x08,
+ [BQ27XXX_REG_AI] = 0x14,
+ [BQ27XXX_REG_FLAGS] = 0x0a,
+ [BQ27XXX_REG_TTE] = 0x16,
+ [BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_TTES] = 0x1c,
+ [BQ27XXX_REG_TTECP] = 0x26,
+ [BQ27XXX_REG_NAC] = 0x0c,
+ [BQ27XXX_REG_FCC] = 0x12,
+ [BQ27XXX_REG_CYCT] = 0x2a,
+ [BQ27XXX_REG_AE] = 0x22,
+ [BQ27XXX_REG_SOC] = 0x2c,
+ [BQ27XXX_REG_DCAP] = 0x3c,
+ [BQ27XXX_REG_AP] = 0x24,
+ },
+ [BQ27520G4] = {
+ [BQ27XXX_REG_CTRL] = 0x00,
+ [BQ27XXX_REG_TEMP] = 0x06,
+ [BQ27XXX_REG_INT_TEMP] = 0x28,
+ [BQ27XXX_REG_VOLT] = 0x08,
+ [BQ27XXX_REG_AI] = 0x14,
+ [BQ27XXX_REG_FLAGS] = 0x0a,
+ [BQ27XXX_REG_TTE] = 0x16,
+ [BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_TTES] = 0x1c,
+ [BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_NAC] = 0x0c,
+ [BQ27XXX_REG_FCC] = 0x12,
+ [BQ27XXX_REG_CYCT] = 0x1e,
+ [BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_SOC] = 0x20,
+ [BQ27XXX_REG_DCAP] = INVALID_REG_ADDR,
+ [BQ27XXX_REG_AP] = INVALID_REG_ADDR,
+ },
[BQ27530] = {
[BQ27XXX_REG_CTRL] = 0x00,
[BQ27XXX_REG_TEMP] = 0x06,
@@ -303,7 +461,7 @@
POWER_SUPPLY_PROP_MANUFACTURER,
};
-static enum power_supply_property bq27500_battery_props[] = {
+static enum power_supply_property bq2750x_battery_props[] = {
POWER_SUPPLY_PROP_STATUS,
POWER_SUPPLY_PROP_PRESENT,
POWER_SUPPLY_PROP_VOLTAGE_NOW,
@@ -321,7 +479,7 @@
POWER_SUPPLY_PROP_MANUFACTURER,
};
-static enum power_supply_property bq27510_battery_props[] = {
+static enum power_supply_property bq2751x_battery_props[] = {
POWER_SUPPLY_PROP_STATUS,
POWER_SUPPLY_PROP_PRESENT,
POWER_SUPPLY_PROP_VOLTAGE_NOW,
@@ -339,6 +497,165 @@
POWER_SUPPLY_PROP_MANUFACTURER,
};
+static enum power_supply_property bq27500_battery_props[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+ POWER_SUPPLY_PROP_CAPACITY,
+ POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+ POWER_SUPPLY_PROP_TEMP,
+ POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+ POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+ POWER_SUPPLY_PROP_TECHNOLOGY,
+ POWER_SUPPLY_PROP_CHARGE_FULL,
+ POWER_SUPPLY_PROP_CHARGE_NOW,
+ POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+ POWER_SUPPLY_PROP_CYCLE_COUNT,
+ POWER_SUPPLY_PROP_ENERGY_NOW,
+ POWER_SUPPLY_PROP_POWER_AVG,
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27510g1_battery_props[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+ POWER_SUPPLY_PROP_CAPACITY,
+ POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+ POWER_SUPPLY_PROP_TEMP,
+ POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+ POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+ POWER_SUPPLY_PROP_TECHNOLOGY,
+ POWER_SUPPLY_PROP_CHARGE_FULL,
+ POWER_SUPPLY_PROP_CHARGE_NOW,
+ POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+ POWER_SUPPLY_PROP_CYCLE_COUNT,
+ POWER_SUPPLY_PROP_ENERGY_NOW,
+ POWER_SUPPLY_PROP_POWER_AVG,
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27510g2_battery_props[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+ POWER_SUPPLY_PROP_CAPACITY,
+ POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+ POWER_SUPPLY_PROP_TEMP,
+ POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+ POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+ POWER_SUPPLY_PROP_TECHNOLOGY,
+ POWER_SUPPLY_PROP_CHARGE_FULL,
+ POWER_SUPPLY_PROP_CHARGE_NOW,
+ POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+ POWER_SUPPLY_PROP_CYCLE_COUNT,
+ POWER_SUPPLY_PROP_ENERGY_NOW,
+ POWER_SUPPLY_PROP_POWER_AVG,
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27510g3_battery_props[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+ POWER_SUPPLY_PROP_CAPACITY,
+ POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+ POWER_SUPPLY_PROP_TEMP,
+ POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+ POWER_SUPPLY_PROP_TECHNOLOGY,
+ POWER_SUPPLY_PROP_CHARGE_FULL,
+ POWER_SUPPLY_PROP_CHARGE_NOW,
+ POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+ POWER_SUPPLY_PROP_CYCLE_COUNT,
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27520g1_battery_props[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+ POWER_SUPPLY_PROP_CAPACITY,
+ POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+ POWER_SUPPLY_PROP_TEMP,
+ POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+ POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+ POWER_SUPPLY_PROP_TECHNOLOGY,
+ POWER_SUPPLY_PROP_CHARGE_FULL,
+ POWER_SUPPLY_PROP_CHARGE_NOW,
+ POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+ POWER_SUPPLY_PROP_ENERGY_NOW,
+ POWER_SUPPLY_PROP_POWER_AVG,
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27520g2_battery_props[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+ POWER_SUPPLY_PROP_CAPACITY,
+ POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+ POWER_SUPPLY_PROP_TEMP,
+ POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+ POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+ POWER_SUPPLY_PROP_TECHNOLOGY,
+ POWER_SUPPLY_PROP_CHARGE_FULL,
+ POWER_SUPPLY_PROP_CHARGE_NOW,
+ POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+ POWER_SUPPLY_PROP_CYCLE_COUNT,
+ POWER_SUPPLY_PROP_ENERGY_NOW,
+ POWER_SUPPLY_PROP_POWER_AVG,
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27520g3_battery_props[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+ POWER_SUPPLY_PROP_CAPACITY,
+ POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+ POWER_SUPPLY_PROP_TEMP,
+ POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+ POWER_SUPPLY_PROP_TECHNOLOGY,
+ POWER_SUPPLY_PROP_CHARGE_FULL,
+ POWER_SUPPLY_PROP_CHARGE_NOW,
+ POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+ POWER_SUPPLY_PROP_CYCLE_COUNT,
+ POWER_SUPPLY_PROP_ENERGY_NOW,
+ POWER_SUPPLY_PROP_POWER_AVG,
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27520g4_battery_props[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+ POWER_SUPPLY_PROP_CAPACITY,
+ POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+ POWER_SUPPLY_PROP_TEMP,
+ POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+ POWER_SUPPLY_PROP_TECHNOLOGY,
+ POWER_SUPPLY_PROP_CHARGE_FULL,
+ POWER_SUPPLY_PROP_CHARGE_NOW,
+ POWER_SUPPLY_PROP_CYCLE_COUNT,
+ POWER_SUPPLY_PROP_HEALTH,
+ POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
static enum power_supply_property bq27530_battery_props[] = {
POWER_SUPPLY_PROP_STATUS,
POWER_SUPPLY_PROP_PRESENT,
@@ -421,8 +738,16 @@
} bq27xxx_battery_props[] = {
BQ27XXX_PROP(BQ27000, bq27000_battery_props),
BQ27XXX_PROP(BQ27010, bq27010_battery_props),
+ BQ27XXX_PROP(BQ2750X, bq2750x_battery_props),
+ BQ27XXX_PROP(BQ2751X, bq2751x_battery_props),
BQ27XXX_PROP(BQ27500, bq27500_battery_props),
- BQ27XXX_PROP(BQ27510, bq27510_battery_props),
+ BQ27XXX_PROP(BQ27510G1, bq27510g1_battery_props),
+ BQ27XXX_PROP(BQ27510G2, bq27510g2_battery_props),
+ BQ27XXX_PROP(BQ27510G3, bq27510g3_battery_props),
+ BQ27XXX_PROP(BQ27520G1, bq27520g1_battery_props),
+ BQ27XXX_PROP(BQ27520G2, bq27520g2_battery_props),
+ BQ27XXX_PROP(BQ27520G3, bq27520g3_battery_props),
+ BQ27XXX_PROP(BQ27520G4, bq27520g4_battery_props),
BQ27XXX_PROP(BQ27530, bq27530_battery_props),
BQ27XXX_PROP(BQ27541, bq27541_battery_props),
BQ27XXX_PROP(BQ27545, bq27545_battery_props),
@@ -674,13 +999,26 @@
*/
static bool bq27xxx_battery_overtemp(struct bq27xxx_device_info *di, u16 flags)
{
- if (di->chip == BQ27500 || di->chip == BQ27510 ||
- di->chip == BQ27541 || di->chip == BQ27545)
+ switch (di->chip) {
+ case BQ2750X:
+ case BQ2751X:
+ case BQ27500:
+ case BQ27510G1:
+ case BQ27510G2:
+ case BQ27510G3:
+ case BQ27520G1:
+ case BQ27520G2:
+ case BQ27520G3:
+ case BQ27520G4:
+ case BQ27541:
+ case BQ27545:
return flags & (BQ27XXX_FLAG_OTC | BQ27XXX_FLAG_OTD);
- if (di->chip == BQ27530 || di->chip == BQ27421)
+ case BQ27530:
+ case BQ27421:
return flags & BQ27XXX_FLAG_OT;
-
- return false;
+ default:
+ return false;
+ }
}
/*
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 5c5c3a6..c68fbc3 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -148,9 +148,17 @@
static const struct i2c_device_id bq27xxx_i2c_id_table[] = {
{ "bq27200", BQ27000 },
{ "bq27210", BQ27010 },
- { "bq27500", BQ27500 },
- { "bq27510", BQ27510 },
- { "bq27520", BQ27510 },
+ { "bq27500", BQ2750X },
+ { "bq27510", BQ2751X },
+ { "bq27520", BQ2751X },
+ { "bq27500-1", BQ27500 },
+ { "bq27510g1", BQ27510G1 },
+ { "bq27510g2", BQ27510G2 },
+ { "bq27510g3", BQ27510G3 },
+ { "bq27520g1", BQ27520G1 },
+ { "bq27520g2", BQ27520G2 },
+ { "bq27520g3", BQ27520G3 },
+ { "bq27520g4", BQ27520G4 },
{ "bq27530", BQ27530 },
{ "bq27531", BQ27530 },
{ "bq27541", BQ27541 },
@@ -173,6 +181,14 @@
{ .compatible = "ti,bq27500" },
{ .compatible = "ti,bq27510" },
{ .compatible = "ti,bq27520" },
+ { .compatible = "ti,bq27500-1" },
+ { .compatible = "ti,bq27510g1" },
+ { .compatible = "ti,bq27510g2" },
+ { .compatible = "ti,bq27510g3" },
+ { .compatible = "ti,bq27520g1" },
+ { .compatible = "ti,bq27520g2" },
+ { .compatible = "ti,bq27520g3" },
+ { .compatible = "ti,bq27520g4" },
{ .compatible = "ti,bq27530" },
{ .compatible = "ti,bq27531" },
{ .compatible = "ti,bq27541" },
diff --git a/drivers/power/supply/gpio-charger.c b/drivers/power/supply/gpio-charger.c
index c5869b1..001731e 100644
--- a/drivers/power/supply/gpio-charger.c
+++ b/drivers/power/supply/gpio-charger.c
@@ -14,7 +14,7 @@
*/
#include <linux/device.h>
-#include <linux/gpio.h>
+#include <linux/gpio.h> /* For legacy platform data */
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
@@ -23,7 +23,7 @@
#include <linux/power_supply.h>
#include <linux/slab.h>
#include <linux/of.h>
-#include <linux/of_gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/power/gpio-charger.h>
@@ -34,6 +34,8 @@
struct power_supply *charger;
struct power_supply_desc charger_desc;
+ struct gpio_desc *gpiod;
+ bool legacy_gpio_requested;
};
static irqreturn_t gpio_charger_irq(int irq, void *devid)
@@ -58,7 +60,8 @@
switch (psp) {
case POWER_SUPPLY_PROP_ONLINE:
- val->intval = !!gpio_get_value_cansleep(pdata->gpio);
+ val->intval = gpiod_get_value_cansleep(gpio_charger->gpiod);
+ /* This xor is only ever used with legacy pdata GPIO */
val->intval ^= pdata->gpio_active_low;
break;
default:
@@ -78,7 +81,6 @@
struct device_node *np = dev->of_node;
struct gpio_charger_platform_data *pdata;
const char *chargetype;
- enum of_gpio_flags flags;
int ret;
if (!np)
@@ -89,16 +91,6 @@
return ERR_PTR(-ENOMEM);
pdata->name = np->name;
-
- pdata->gpio = of_get_gpio_flags(np, 0, &flags);
- if (pdata->gpio < 0) {
- if (pdata->gpio != -EPROBE_DEFER)
- dev_err(dev, "could not get charger gpio\n");
- return ERR_PTR(pdata->gpio);
- }
-
- pdata->gpio_active_low = !!(flags & OF_GPIO_ACTIVE_LOW);
-
pdata->type = POWER_SUPPLY_TYPE_UNKNOWN;
ret = of_property_read_string(np, "charger-type", &chargetype);
if (ret >= 0) {
@@ -144,11 +136,6 @@
}
}
- if (!gpio_is_valid(pdata->gpio)) {
- dev_err(&pdev->dev, "Invalid gpio pin\n");
- return -EINVAL;
- }
-
gpio_charger = devm_kzalloc(&pdev->dev, sizeof(*gpio_charger),
GFP_KERNEL);
if (!gpio_charger) {
@@ -156,6 +143,45 @@
return -ENOMEM;
}
+ /*
+ * This will fetch a GPIO descriptor from device tree, ACPI or
+ * boardfile descriptor tables. It's good to try this first.
+ */
+ gpio_charger->gpiod = devm_gpiod_get(&pdev->dev, NULL, GPIOD_IN);
+
+ /*
+ * If this fails and we're not using device tree, try the
+ * legacy platform data method.
+ */
+ if (IS_ERR(gpio_charger->gpiod) && !pdev->dev.of_node) {
+ /* Non-DT: use legacy GPIO numbers */
+ if (!gpio_is_valid(pdata->gpio)) {
+ dev_err(&pdev->dev, "Invalid gpio pin in pdata\n");
+ return -EINVAL;
+ }
+ ret = gpio_request(pdata->gpio, dev_name(&pdev->dev));
+ if (ret) {
+ dev_err(&pdev->dev, "Failed to request gpio pin: %d\n",
+ ret);
+ return ret;
+ }
+ gpio_charger->legacy_gpio_requested = true;
+ ret = gpio_direction_input(pdata->gpio);
+ if (ret) {
+ dev_err(&pdev->dev, "Failed to set gpio to input: %d\n",
+ ret);
+ goto err_gpio_free;
+ }
+ /* Then convert this to gpiod for now */
+ gpio_charger->gpiod = gpio_to_desc(pdata->gpio);
+ } else if (IS_ERR(gpio_charger->gpiod)) {
+ /* Just try again if this happens */
+ if (PTR_ERR(gpio_charger->gpiod) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+ dev_err(&pdev->dev, "error getting GPIO descriptor\n");
+ return PTR_ERR(gpio_charger->gpiod);
+ }
+
charger_desc = &gpio_charger->charger_desc;
charger_desc->name = pdata->name ? pdata->name : "gpio-charger";
@@ -169,17 +195,6 @@
psy_cfg.of_node = pdev->dev.of_node;
psy_cfg.drv_data = gpio_charger;
- ret = gpio_request(pdata->gpio, dev_name(&pdev->dev));
- if (ret) {
- dev_err(&pdev->dev, "Failed to request gpio pin: %d\n", ret);
- goto err_free;
- }
- ret = gpio_direction_input(pdata->gpio);
- if (ret) {
- dev_err(&pdev->dev, "Failed to set gpio to input: %d\n", ret);
- goto err_gpio_free;
- }
-
gpio_charger->pdata = pdata;
gpio_charger->charger = power_supply_register(&pdev->dev,
@@ -191,7 +206,7 @@
goto err_gpio_free;
}
- irq = gpio_to_irq(pdata->gpio);
+ irq = gpiod_to_irq(gpio_charger->gpiod);
if (irq > 0) {
ret = request_any_context_irq(irq, gpio_charger_irq,
IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
@@ -209,8 +224,8 @@
return 0;
err_gpio_free:
- gpio_free(pdata->gpio);
-err_free:
+ if (gpio_charger->legacy_gpio_requested)
+ gpio_free(pdata->gpio);
return ret;
}
@@ -223,7 +238,8 @@
power_supply_unregister(gpio_charger->charger);
- gpio_free(gpio_charger->pdata->gpio);
+ if (gpio_charger->legacy_gpio_requested)
+ gpio_free(gpio_charger->pdata->gpio);
return 0;
}
diff --git a/drivers/power/supply/intel_mid_battery.c b/drivers/power/supply/intel_mid_battery.c
deleted file mode 100644
index dc7feef..0000000
--- a/drivers/power/supply/intel_mid_battery.c
+++ /dev/null
@@ -1,795 +0,0 @@
-/*
- * intel_mid_battery.c - Intel MID PMIC Battery Driver
- *
- * Copyright (C) 2009 Intel Corporation
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- * Author: Nithish Mahalingam <nithish.mahalingam@intel.com>
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/err.h>
-#include <linux/interrupt.h>
-#include <linux/workqueue.h>
-#include <linux/jiffies.h>
-#include <linux/param.h>
-#include <linux/device.h>
-#include <linux/spi/spi.h>
-#include <linux/platform_device.h>
-#include <linux/power_supply.h>
-
-#include <asm/intel_scu_ipc.h>
-
-#define DRIVER_NAME "pmic_battery"
-
-/*********************************************************************
- * Generic defines
- *********************************************************************/
-
-static int debug;
-module_param(debug, int, 0444);
-MODULE_PARM_DESC(debug, "Flag to enable PMIC Battery debug messages.");
-
-#define PMIC_BATT_DRV_INFO_UPDATED 1
-#define PMIC_BATT_PRESENT 1
-#define PMIC_BATT_NOT_PRESENT 0
-#define PMIC_USB_PRESENT PMIC_BATT_PRESENT
-#define PMIC_USB_NOT_PRESENT PMIC_BATT_NOT_PRESENT
-
-/* pmic battery register related */
-#define PMIC_BATT_CHR_SCHRGINT_ADDR 0xD2
-#define PMIC_BATT_CHR_SBATOVP_MASK (1 << 1)
-#define PMIC_BATT_CHR_STEMP_MASK (1 << 2)
-#define PMIC_BATT_CHR_SCOMP_MASK (1 << 3)
-#define PMIC_BATT_CHR_SUSBDET_MASK (1 << 4)
-#define PMIC_BATT_CHR_SBATDET_MASK (1 << 5)
-#define PMIC_BATT_CHR_SDCLMT_MASK (1 << 6)
-#define PMIC_BATT_CHR_SUSBOVP_MASK (1 << 7)
-#define PMIC_BATT_CHR_EXCPT_MASK 0x86
-
-#define PMIC_BATT_ADC_ACCCHRG_MASK (1 << 31)
-#define PMIC_BATT_ADC_ACCCHRGVAL_MASK 0x7FFFFFFF
-
-/* pmic ipc related */
-#define PMIC_BATT_CHR_IPC_FCHRG_SUBID 0x4
-#define PMIC_BATT_CHR_IPC_TCHRG_SUBID 0x6
-
-/* types of battery charging */
-enum batt_charge_type {
- BATT_USBOTG_500MA_CHARGE,
- BATT_USBOTG_TRICKLE_CHARGE,
-};
-
-/* valid battery events */
-enum batt_event {
- BATT_EVENT_BATOVP_EXCPT,
- BATT_EVENT_USBOVP_EXCPT,
- BATT_EVENT_TEMP_EXCPT,
- BATT_EVENT_DCLMT_EXCPT,
- BATT_EVENT_EXCPT
-};
-
-
-/*********************************************************************
- * Battery properties
- *********************************************************************/
-
-/*
- * pmic battery info
- */
-struct pmic_power_module_info {
- bool is_dev_info_updated;
- struct device *dev;
- /* pmic battery data */
- unsigned long update_time; /* jiffies when data read */
- unsigned int usb_is_present;
- unsigned int batt_is_present;
- unsigned int batt_health;
- unsigned int usb_health;
- unsigned int batt_status;
- unsigned int batt_charge_now; /* in mAS */
- unsigned int batt_prev_charge_full; /* in mAS */
- unsigned int batt_charge_rate; /* in units per second */
-
- struct power_supply *usb;
- struct power_supply *batt;
- int irq; /* GPE_ID or IRQ# */
- struct workqueue_struct *monitor_wqueue;
- struct delayed_work monitor_battery;
- struct work_struct handler;
-};
-
-static unsigned int delay_time = 2000; /* in ms */
-
-/*
- * pmic ac properties
- */
-static enum power_supply_property pmic_usb_props[] = {
- POWER_SUPPLY_PROP_PRESENT,
- POWER_SUPPLY_PROP_HEALTH,
-};
-
-/*
- * pmic battery properties
- */
-static enum power_supply_property pmic_battery_props[] = {
- POWER_SUPPLY_PROP_STATUS,
- POWER_SUPPLY_PROP_HEALTH,
- POWER_SUPPLY_PROP_PRESENT,
- POWER_SUPPLY_PROP_CHARGE_NOW,
- POWER_SUPPLY_PROP_CHARGE_FULL,
-};
-
-
-/*
- * Glue functions for talking to the IPC
- */
-
-struct battery_property {
- u32 capacity; /* Charger capacity */
- u8 crnt; /* Quick charge current value*/
- u8 volt; /* Fine adjustment of constant charge voltage */
- u8 prot; /* CHRGPROT register value */
- u8 prot2; /* CHRGPROT1 register value */
- u8 timer; /* Charging timer */
-};
-
-#define IPCMSG_BATTERY 0xEF
-
-/* Battery coulomb counter accumulator commands */
-#define IPC_CMD_CC_WR 0 /* Update coulomb counter value */
-#define IPC_CMD_CC_RD 1 /* Read coulomb counter value */
-#define IPC_CMD_BATTERY_PROPERTY 2 /* Read Battery property */
-
-/**
- * pmic_scu_ipc_battery_cc_read - read battery cc
- * @value: battery coulomb counter read
- *
- * Reads the battery couloumb counter value, returns 0 on success, or
- * an error code
- *
- * This function may sleep. Locking for SCU accesses is handled for
- * the caller.
- */
-static int pmic_scu_ipc_battery_cc_read(u32 *value)
-{
- return intel_scu_ipc_command(IPCMSG_BATTERY, IPC_CMD_CC_RD,
- NULL, 0, value, 1);
-}
-
-/**
- * pmic_scu_ipc_battery_property_get - fetch properties
- * @prop: battery properties
- *
- * Retrieve the battery properties from the power management
- *
- * This function may sleep. Locking for SCU accesses is handled for
- * the caller.
- */
-static int pmic_scu_ipc_battery_property_get(struct battery_property *prop)
-{
- u32 data[3];
- u8 *p = (u8 *)&data[1];
- int err = intel_scu_ipc_command(IPCMSG_BATTERY,
- IPC_CMD_BATTERY_PROPERTY, NULL, 0, data, 3);
-
- prop->capacity = data[0];
- prop->crnt = *p++;
- prop->volt = *p++;
- prop->prot = *p++;
- prop->prot2 = *p++;
- prop->timer = *p++;
-
- return err;
-}
-
-/**
- * pmic_scu_ipc_set_charger - set charger
- * @charger: charger to select
- *
- * Switch the charging mode for the SCU
- */
-
-static int pmic_scu_ipc_set_charger(int charger)
-{
- return intel_scu_ipc_simple_command(IPCMSG_BATTERY, charger);
-}
-
-/**
- * pmic_battery_log_event - log battery events
- * @event: battery event to be logged
- * Context: can sleep
- *
- * There are multiple battery events which may be of interest to users;
- * this battery function logs the different battery events onto the
- * kernel log messages.
- */
-static void pmic_battery_log_event(enum batt_event event)
-{
- printk(KERN_WARNING "pmic-battery: ");
- switch (event) {
- case BATT_EVENT_BATOVP_EXCPT:
- printk(KERN_CONT "battery overvoltage condition\n");
- break;
- case BATT_EVENT_USBOVP_EXCPT:
- printk(KERN_CONT "usb charger overvoltage condition\n");
- break;
- case BATT_EVENT_TEMP_EXCPT:
- printk(KERN_CONT "high battery temperature condition\n");
- break;
- case BATT_EVENT_DCLMT_EXCPT:
- printk(KERN_CONT "over battery charge current condition\n");
- break;
- default:
- printk(KERN_CONT "charger/battery exception %d\n", event);
- break;
- }
-}
-
-/**
- * pmic_battery_read_status - read battery status information
- * @pbi: device info structure to update the read information
- * Context: can sleep
- *
- * PMIC power source information need to be updated based on the data read
- * from the PMIC battery registers.
- *
- */
-static void pmic_battery_read_status(struct pmic_power_module_info *pbi)
-{
- unsigned int update_time_intrvl;
- unsigned int chrg_val;
- u32 ccval;
- u8 r8;
- struct battery_property batt_prop;
- int batt_present = 0;
- int usb_present = 0;
- int batt_exception = 0;
-
- /* make sure the last batt_status read happened delay_time before */
- if (pbi->update_time && time_before(jiffies, pbi->update_time +
- msecs_to_jiffies(delay_time)))
- return;
-
- update_time_intrvl = jiffies_to_msecs(jiffies - pbi->update_time);
- pbi->update_time = jiffies;
-
- /* read coulomb counter registers and schrgint register */
- if (pmic_scu_ipc_battery_cc_read(&ccval)) {
- dev_warn(pbi->dev, "%s(): ipc config cmd failed\n",
- __func__);
- return;
- }
-
- if (intel_scu_ipc_ioread8(PMIC_BATT_CHR_SCHRGINT_ADDR, &r8)) {
- dev_warn(pbi->dev, "%s(): ipc pmic read failed\n",
- __func__);
- return;
- }
-
- /*
- * set pmic_power_module_info members based on pmic register values
- * read.
- */
-
- /* set batt_is_present */
- if (r8 & PMIC_BATT_CHR_SBATDET_MASK) {
- pbi->batt_is_present = PMIC_BATT_PRESENT;
- batt_present = 1;
- } else {
- pbi->batt_is_present = PMIC_BATT_NOT_PRESENT;
- pbi->batt_health = POWER_SUPPLY_HEALTH_UNKNOWN;
- pbi->batt_status = POWER_SUPPLY_STATUS_UNKNOWN;
- }
-
- /* set batt_health */
- if (batt_present) {
- if (r8 & PMIC_BATT_CHR_SBATOVP_MASK) {
- pbi->batt_health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
- pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
- pmic_battery_log_event(BATT_EVENT_BATOVP_EXCPT);
- batt_exception = 1;
- } else if (r8 & PMIC_BATT_CHR_STEMP_MASK) {
- pbi->batt_health = POWER_SUPPLY_HEALTH_OVERHEAT;
- pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
- pmic_battery_log_event(BATT_EVENT_TEMP_EXCPT);
- batt_exception = 1;
- } else {
- pbi->batt_health = POWER_SUPPLY_HEALTH_GOOD;
- if (r8 & PMIC_BATT_CHR_SDCLMT_MASK) {
- /* PMIC will change charging current automatically */
- pmic_battery_log_event(BATT_EVENT_DCLMT_EXCPT);
- }
- }
- }
-
- /* set usb_is_present */
- if (r8 & PMIC_BATT_CHR_SUSBDET_MASK) {
- pbi->usb_is_present = PMIC_USB_PRESENT;
- usb_present = 1;
- } else {
- pbi->usb_is_present = PMIC_USB_NOT_PRESENT;
- pbi->usb_health = POWER_SUPPLY_HEALTH_UNKNOWN;
- }
-
- if (usb_present) {
- if (r8 & PMIC_BATT_CHR_SUSBOVP_MASK) {
- pbi->usb_health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
- pmic_battery_log_event(BATT_EVENT_USBOVP_EXCPT);
- } else {
- pbi->usb_health = POWER_SUPPLY_HEALTH_GOOD;
- }
- }
-
- chrg_val = ccval & PMIC_BATT_ADC_ACCCHRGVAL_MASK;
-
- /* set batt_prev_charge_full to battery capacity the first time */
- if (!pbi->is_dev_info_updated) {
- if (pmic_scu_ipc_battery_property_get(&batt_prop)) {
- dev_warn(pbi->dev, "%s(): ipc config cmd failed\n",
- __func__);
- return;
- }
- pbi->batt_prev_charge_full = batt_prop.capacity;
- }
-
- /* set batt_status */
- if (batt_present && !batt_exception) {
- if (r8 & PMIC_BATT_CHR_SCOMP_MASK) {
- pbi->batt_status = POWER_SUPPLY_STATUS_FULL;
- pbi->batt_prev_charge_full = chrg_val;
- } else if (ccval & PMIC_BATT_ADC_ACCCHRG_MASK) {
- pbi->batt_status = POWER_SUPPLY_STATUS_DISCHARGING;
- } else {
- pbi->batt_status = POWER_SUPPLY_STATUS_CHARGING;
- }
- }
-
- /* set batt_charge_rate */
- if (pbi->is_dev_info_updated && batt_present && !batt_exception) {
- if (pbi->batt_status == POWER_SUPPLY_STATUS_DISCHARGING) {
- if (pbi->batt_charge_now - chrg_val) {
- pbi->batt_charge_rate = ((pbi->batt_charge_now -
- chrg_val) * 1000 * 60) /
- update_time_intrvl;
- }
- } else if (pbi->batt_status == POWER_SUPPLY_STATUS_CHARGING) {
- if (chrg_val - pbi->batt_charge_now) {
- pbi->batt_charge_rate = ((chrg_val -
- pbi->batt_charge_now) * 1000 * 60) /
- update_time_intrvl;
- }
- } else
- pbi->batt_charge_rate = 0;
- } else {
- pbi->batt_charge_rate = -1;
- }
-
- /* batt_charge_now */
- if (batt_present && !batt_exception)
- pbi->batt_charge_now = chrg_val;
- else
- pbi->batt_charge_now = -1;
-
- pbi->is_dev_info_updated = PMIC_BATT_DRV_INFO_UPDATED;
-}
-
-/**
- * pmic_usb_get_property - usb power source get property
- * @psy: usb power supply context
- * @psp: usb power source property
- * @val: usb power source property value
- * Context: can sleep
- *
- * PMIC usb power source property needs to be provided to power_supply
- * subsytem for it to provide the information to users.
- */
-static int pmic_usb_get_property(struct power_supply *psy,
- enum power_supply_property psp,
- union power_supply_propval *val)
-{
- struct pmic_power_module_info *pbi = power_supply_get_drvdata(psy);
-
- /* update pmic_power_module_info members */
- pmic_battery_read_status(pbi);
-
- switch (psp) {
- case POWER_SUPPLY_PROP_PRESENT:
- val->intval = pbi->usb_is_present;
- break;
- case POWER_SUPPLY_PROP_HEALTH:
- val->intval = pbi->usb_health;
- break;
- default:
- return -EINVAL;
- }
-
- return 0;
-}
-
-static inline unsigned long mAStouAh(unsigned long v)
-{
- /* seconds to hours, mA to µA */
- return (v * 1000) / 3600;
-}
-
-/**
- * pmic_battery_get_property - battery power source get property
- * @psy: battery power supply context
- * @psp: battery power source property
- * @val: battery power source property value
- * Context: can sleep
- *
- * PMIC battery power source property needs to be provided to power_supply
- * subsytem for it to provide the information to users.
- */
-static int pmic_battery_get_property(struct power_supply *psy,
- enum power_supply_property psp,
- union power_supply_propval *val)
-{
- struct pmic_power_module_info *pbi = power_supply_get_drvdata(psy);
-
- /* update pmic_power_module_info members */
- pmic_battery_read_status(pbi);
-
- switch (psp) {
- case POWER_SUPPLY_PROP_STATUS:
- val->intval = pbi->batt_status;
- break;
- case POWER_SUPPLY_PROP_HEALTH:
- val->intval = pbi->batt_health;
- break;
- case POWER_SUPPLY_PROP_PRESENT:
- val->intval = pbi->batt_is_present;
- break;
- case POWER_SUPPLY_PROP_CHARGE_NOW:
- val->intval = mAStouAh(pbi->batt_charge_now);
- break;
- case POWER_SUPPLY_PROP_CHARGE_FULL:
- val->intval = mAStouAh(pbi->batt_prev_charge_full);
- break;
- default:
- return -EINVAL;
- }
-
- return 0;
-}
-
-/**
- * pmic_battery_monitor - monitor battery status
- * @work: work structure
- * Context: can sleep
- *
- * PMIC battery status needs to be monitored for any change
- * and information needs to be frequently updated.
- */
-static void pmic_battery_monitor(struct work_struct *work)
-{
- struct pmic_power_module_info *pbi = container_of(work,
- struct pmic_power_module_info, monitor_battery.work);
-
- /* update pmic_power_module_info members */
- pmic_battery_read_status(pbi);
- queue_delayed_work(pbi->monitor_wqueue, &pbi->monitor_battery, HZ * 10);
-}
-
-/**
- * pmic_battery_set_charger - set battery charger
- * @pbi: device info structure
- * @chrg: charge mode to set battery charger in
- * Context: can sleep
- *
- * PMIC battery charger needs to be enabled based on the usb charge
- * capabilities connected to the platform.
- */
-static int pmic_battery_set_charger(struct pmic_power_module_info *pbi,
- enum batt_charge_type chrg)
-{
- int retval;
-
- /* set usblmt bits and chrgcntl register bits appropriately */
- switch (chrg) {
- case BATT_USBOTG_500MA_CHARGE:
- retval = pmic_scu_ipc_set_charger(PMIC_BATT_CHR_IPC_FCHRG_SUBID);
- break;
- case BATT_USBOTG_TRICKLE_CHARGE:
- retval = pmic_scu_ipc_set_charger(PMIC_BATT_CHR_IPC_TCHRG_SUBID);
- break;
- default:
- dev_warn(pbi->dev, "%s(): out of range usb charger "
- "charge detected\n", __func__);
- return -EINVAL;
- }
-
- if (retval) {
- dev_warn(pbi->dev, "%s(): ipc pmic read failed\n",
- __func__);
- return retval;
- }
-
- return 0;
-}
-
-/**
- * pmic_battery_interrupt_handler - pmic battery interrupt handler
- * Context: interrupt context
- *
- * PMIC battery interrupt handler which will be called with either
- * battery full condition occurs or usb otg & battery connect
- * condition occurs.
- */
-static irqreturn_t pmic_battery_interrupt_handler(int id, void *dev)
-{
- struct pmic_power_module_info *pbi = dev;
-
- schedule_work(&pbi->handler);
-
- return IRQ_HANDLED;
-}
-
-/**
- * pmic_battery_handle_intrpt - pmic battery service interrupt
- * @work: work structure
- * Context: can sleep
- *
- * PMIC battery needs to either update the battery status as full
- * if it detects battery full condition caused the interrupt or needs
- * to enable battery charger if it detects usb and battery detect
- * caused the source of interrupt.
- */
-static void pmic_battery_handle_intrpt(struct work_struct *work)
-{
- struct pmic_power_module_info *pbi = container_of(work,
- struct pmic_power_module_info, handler);
- enum batt_charge_type chrg;
- u8 r8;
-
- if (intel_scu_ipc_ioread8(PMIC_BATT_CHR_SCHRGINT_ADDR, &r8)) {
- dev_warn(pbi->dev, "%s(): ipc pmic read failed\n",
- __func__);
- return;
- }
- /* find the cause of the interrupt */
- if (r8 & PMIC_BATT_CHR_SBATDET_MASK) {
- pbi->batt_is_present = PMIC_BATT_PRESENT;
- } else {
- pbi->batt_is_present = PMIC_BATT_NOT_PRESENT;
- pbi->batt_health = POWER_SUPPLY_HEALTH_UNKNOWN;
- pbi->batt_status = POWER_SUPPLY_STATUS_UNKNOWN;
- return;
- }
-
- if (r8 & PMIC_BATT_CHR_EXCPT_MASK) {
- pbi->batt_health = POWER_SUPPLY_HEALTH_UNKNOWN;
- pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
- pbi->usb_health = POWER_SUPPLY_HEALTH_UNKNOWN;
- pmic_battery_log_event(BATT_EVENT_EXCPT);
- return;
- } else {
- pbi->batt_health = POWER_SUPPLY_HEALTH_GOOD;
- pbi->usb_health = POWER_SUPPLY_HEALTH_GOOD;
- }
-
- if (r8 & PMIC_BATT_CHR_SCOMP_MASK) {
- u32 ccval;
- pbi->batt_status = POWER_SUPPLY_STATUS_FULL;
-
- if (pmic_scu_ipc_battery_cc_read(&ccval)) {
- dev_warn(pbi->dev, "%s(): ipc config cmd "
- "failed\n", __func__);
- return;
- }
- pbi->batt_prev_charge_full = ccval &
- PMIC_BATT_ADC_ACCCHRGVAL_MASK;
- return;
- }
-
- if (r8 & PMIC_BATT_CHR_SUSBDET_MASK) {
- pbi->usb_is_present = PMIC_USB_PRESENT;
- } else {
- pbi->usb_is_present = PMIC_USB_NOT_PRESENT;
- pbi->usb_health = POWER_SUPPLY_HEALTH_UNKNOWN;
- return;
- }
-
- /* setup battery charging */
-
-#if 0
- /* check usb otg power capability and set charger accordingly */
- retval = langwell_udc_maxpower(&power);
- if (retval) {
- dev_warn(pbi->dev,
- "%s(): usb otg power query failed with error code %d\n",
- __func__, retval);
- return;
- }
-
- if (power >= 500)
- chrg = BATT_USBOTG_500MA_CHARGE;
- else
-#endif
- chrg = BATT_USBOTG_TRICKLE_CHARGE;
-
- /* enable battery charging */
- if (pmic_battery_set_charger(pbi, chrg)) {
- dev_warn(pbi->dev,
- "%s(): failed to set up battery charging\n", __func__);
- return;
- }
-
- dev_dbg(pbi->dev,
- "pmic-battery: %s() - setting up battery charger successful\n",
- __func__);
-}
-
-/*
- * Description of power supplies
- */
-static const struct power_supply_desc pmic_usb_desc = {
- .name = "pmic-usb",
- .type = POWER_SUPPLY_TYPE_USB,
- .properties = pmic_usb_props,
- .num_properties = ARRAY_SIZE(pmic_usb_props),
- .get_property = pmic_usb_get_property,
-};
-
-static const struct power_supply_desc pmic_batt_desc = {
- .name = "pmic-batt",
- .type = POWER_SUPPLY_TYPE_BATTERY,
- .properties = pmic_battery_props,
- .num_properties = ARRAY_SIZE(pmic_battery_props),
- .get_property = pmic_battery_get_property,
-};
-
-/**
- * pmic_battery_probe - pmic battery initialize
- * @irq: pmic battery device irq
- * @dev: pmic battery device structure
- * Context: can sleep
- *
- * PMIC battery initializes its internal data structue and other
- * infrastructure components for it to work as expected.
- */
-static int probe(int irq, struct device *dev)
-{
- int retval = 0;
- struct pmic_power_module_info *pbi;
- struct power_supply_config psy_cfg = {};
-
- dev_dbg(dev, "pmic-battery: found pmic battery device\n");
-
- pbi = kzalloc(sizeof(*pbi), GFP_KERNEL);
- if (!pbi) {
- dev_err(dev, "%s(): memory allocation failed\n",
- __func__);
- return -ENOMEM;
- }
-
- pbi->dev = dev;
- pbi->irq = irq;
- dev_set_drvdata(dev, pbi);
- psy_cfg.drv_data = pbi;
-
- /* initialize all required framework before enabling interrupts */
- INIT_WORK(&pbi->handler, pmic_battery_handle_intrpt);
- INIT_DELAYED_WORK(&pbi->monitor_battery, pmic_battery_monitor);
- pbi->monitor_wqueue = alloc_workqueue(dev_name(dev), WQ_MEM_RECLAIM, 0);
- if (!pbi->monitor_wqueue) {
- dev_err(dev, "%s(): wqueue init failed\n", __func__);
- retval = -ESRCH;
- goto wqueue_failed;
- }
-
- /* register interrupt */
- retval = request_irq(pbi->irq, pmic_battery_interrupt_handler,
- 0, DRIVER_NAME, pbi);
- if (retval) {
- dev_err(dev, "%s(): cannot get IRQ\n", __func__);
- goto requestirq_failed;
- }
-
- /* register pmic-batt with power supply subsystem */
- pbi->batt = power_supply_register(dev, &pmic_usb_desc, &psy_cfg);
- if (IS_ERR(pbi->batt)) {
- dev_err(dev,
- "%s(): failed to register pmic battery device with power supply subsystem\n",
- __func__);
- retval = PTR_ERR(pbi->batt);
- goto power_reg_failed;
- }
-
- dev_dbg(dev, "pmic-battery: %s() - pmic battery device "
- "registration with power supply subsystem successful\n",
- __func__);
-
- queue_delayed_work(pbi->monitor_wqueue, &pbi->monitor_battery, HZ * 1);
-
- /* register pmic-usb with power supply subsystem */
- pbi->usb = power_supply_register(dev, &pmic_batt_desc, &psy_cfg);
- if (IS_ERR(pbi->usb)) {
- dev_err(dev,
- "%s(): failed to register pmic usb device with power supply subsystem\n",
- __func__);
- retval = PTR_ERR(pbi->usb);
- goto power_reg_failed_1;
- }
-
- if (debug)
- printk(KERN_INFO "pmic-battery: %s() - pmic usb device "
- "registration with power supply subsystem successful\n",
- __func__);
-
- return retval;
-
-power_reg_failed_1:
- power_supply_unregister(pbi->batt);
-power_reg_failed:
- cancel_delayed_work_sync(&pbi->monitor_battery);
-requestirq_failed:
- destroy_workqueue(pbi->monitor_wqueue);
-wqueue_failed:
- kfree(pbi);
-
- return retval;
-}
-
-static int platform_pmic_battery_probe(struct platform_device *pdev)
-{
- return probe(pdev->id, &pdev->dev);
-}
-
-/**
- * pmic_battery_remove - pmic battery finalize
- * @dev: pmic battery device structure
- * Context: can sleep
- *
- * PMIC battery finalizes its internal data structue and other
- * infrastructure components that it initialized in
- * pmic_battery_probe.
- */
-
-static int platform_pmic_battery_remove(struct platform_device *pdev)
-{
- struct pmic_power_module_info *pbi = platform_get_drvdata(pdev);
-
- free_irq(pbi->irq, pbi);
- cancel_delayed_work_sync(&pbi->monitor_battery);
- destroy_workqueue(pbi->monitor_wqueue);
-
- power_supply_unregister(pbi->usb);
- power_supply_unregister(pbi->batt);
-
- cancel_work_sync(&pbi->handler);
- kfree(pbi);
- return 0;
-}
-
-static struct platform_driver platform_pmic_battery_driver = {
- .driver = {
- .name = DRIVER_NAME,
- },
- .probe = platform_pmic_battery_probe,
- .remove = platform_pmic_battery_remove,
-};
-
-module_platform_driver(platform_pmic_battery_driver);
-
-MODULE_AUTHOR("Nithish Mahalingam <nithish.mahalingam@intel.com>");
-MODULE_DESCRIPTION("Intel Moorestown PMIC Battery Driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/power/supply/max14656_charger_detector.c b/drivers/power/supply/max14656_charger_detector.c
new file mode 100644
index 0000000..b91b1d2
--- /dev/null
+++ b/drivers/power/supply/max14656_charger_detector.c
@@ -0,0 +1,327 @@
+/*
+ * Maxim MAX14656 / AL32 USB Charger Detector driver
+ *
+ * Copyright (C) 2014 LG Electronics, Inc
+ * Copyright (C) 2016 Alexander Kurz <akurz@blala.de>
+ *
+ * Components from Maxim AL32 Charger detection Driver for MX50 Yoshi Board
+ * Copyright (C) Amazon Technologies Inc. All rights reserved.
+ * Manish Lachwani (lachwani@lab126.com)
+ *
+ * This package is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/of_device.h>
+#include <linux/workqueue.h>
+#include <linux/power_supply.h>
+
+#define MAX14656_MANUFACTURER "Maxim Integrated"
+#define MAX14656_NAME "max14656"
+
+#define MAX14656_DEVICE_ID 0x00
+#define MAX14656_INTERRUPT_1 0x01
+#define MAX14656_INTERRUPT_2 0x02
+#define MAX14656_STATUS_1 0x03
+#define MAX14656_STATUS_2 0x04
+#define MAX14656_INTMASK_1 0x05
+#define MAX14656_INTMASK_2 0x06
+#define MAX14656_CONTROL_1 0x07
+#define MAX14656_CONTROL_2 0x08
+#define MAX14656_CONTROL_3 0x09
+
+#define DEVICE_VENDOR_MASK 0xf0
+#define DEVICE_REV_MASK 0x0f
+#define INT_EN_REG_MASK BIT(4)
+#define CHG_TYPE_INT_MASK BIT(0)
+#define STATUS1_VB_VALID_MASK BIT(4)
+#define STATUS1_CHG_TYPE_MASK 0xf
+#define INT1_DCD_TIMEOUT_MASK BIT(7)
+#define CONTROL1_DEFAULT 0x0d
+#define CONTROL1_INT_EN BIT(4)
+#define CONTROL1_INT_ACTIVE_HIGH BIT(5)
+#define CONTROL1_EDGE BIT(7)
+#define CONTROL2_DEFAULT 0x8e
+#define CONTROL2_ADC_EN BIT(0)
+#define CONTROL3_DEFAULT 0x8d
+
+enum max14656_chg_type {
+ MAX14656_NO_CHARGER = 0,
+ MAX14656_SDP_CHARGER,
+ MAX14656_CDP_CHARGER,
+ MAX14656_DCP_CHARGER,
+ MAX14656_APPLE_500MA_CHARGER,
+ MAX14656_APPLE_1A_CHARGER,
+ MAX14656_APPLE_2A_CHARGER,
+ MAX14656_SPECIAL_500MA_CHARGER,
+ MAX14656_APPLE_12W,
+ MAX14656_CHARGER_LAST
+};
+
+static const struct max14656_chg_type_props {
+ enum power_supply_type type;
+} chg_type_props[] = {
+ { POWER_SUPPLY_TYPE_UNKNOWN },
+ { POWER_SUPPLY_TYPE_USB },
+ { POWER_SUPPLY_TYPE_USB_CDP },
+ { POWER_SUPPLY_TYPE_USB_DCP },
+ { POWER_SUPPLY_TYPE_USB_DCP },
+ { POWER_SUPPLY_TYPE_USB_DCP },
+ { POWER_SUPPLY_TYPE_USB_DCP },
+ { POWER_SUPPLY_TYPE_USB_DCP },
+ { POWER_SUPPLY_TYPE_USB },
+};
+
+struct max14656_chip {
+ struct i2c_client *client;
+ struct power_supply *detect_psy;
+ struct power_supply_desc psy_desc;
+ struct delayed_work irq_work;
+
+ int irq;
+ int online;
+};
+
+static int max14656_read_reg(struct i2c_client *client, int reg, u8 *val)
+{
+ s32 ret;
+
+ ret = i2c_smbus_read_byte_data(client, reg);
+ if (ret < 0) {
+ dev_err(&client->dev,
+ "i2c read fail: can't read from %02x: %d\n",
+ reg, ret);
+ return ret;
+ }
+ *val = ret;
+ return 0;
+}
+
+static int max14656_write_reg(struct i2c_client *client, int reg, u8 val)
+{
+ s32 ret;
+
+ ret = i2c_smbus_write_byte_data(client, reg, val);
+ if (ret < 0) {
+ dev_err(&client->dev,
+ "i2c write fail: can't write %02x to %02x: %d\n",
+ val, reg, ret);
+ return ret;
+ }
+ return 0;
+}
+
+static int max14656_read_block_reg(struct i2c_client *client, u8 reg,
+ u8 length, u8 *val)
+{
+ int ret;
+
+ ret = i2c_smbus_read_i2c_block_data(client, reg, length, val);
+ if (ret < 0) {
+ dev_err(&client->dev, "failed to block read reg 0x%x: %d\n",
+ reg, ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+#define REG_TOTAL_NUM 5
+static void max14656_irq_worker(struct work_struct *work)
+{
+ struct max14656_chip *chip =
+ container_of(work, struct max14656_chip, irq_work.work);
+
+ u8 buf[REG_TOTAL_NUM];
+ u8 chg_type;
+ int ret = 0;
+
+ ret = max14656_read_block_reg(chip->client, MAX14656_DEVICE_ID,
+ REG_TOTAL_NUM, buf);
+
+ if ((buf[MAX14656_STATUS_1] & STATUS1_VB_VALID_MASK) &&
+ (buf[MAX14656_STATUS_1] & STATUS1_CHG_TYPE_MASK)) {
+ chg_type = buf[MAX14656_STATUS_1] & STATUS1_CHG_TYPE_MASK;
+ if (chg_type < MAX14656_CHARGER_LAST)
+ chip->psy_desc.type = chg_type_props[chg_type].type;
+ else
+ chip->psy_desc.type = POWER_SUPPLY_TYPE_UNKNOWN;
+ chip->online = 1;
+ } else {
+ chip->online = 0;
+ chip->psy_desc.type = POWER_SUPPLY_TYPE_UNKNOWN;
+ }
+
+ power_supply_changed(chip->detect_psy);
+}
+
+static irqreturn_t max14656_irq(int irq, void *dev_id)
+{
+ struct max14656_chip *chip = dev_id;
+
+ schedule_delayed_work(&chip->irq_work, msecs_to_jiffies(100));
+
+ return IRQ_HANDLED;
+}
+
+static int max14656_hw_init(struct max14656_chip *chip)
+{
+ uint8_t val = 0;
+ uint8_t rev;
+ struct i2c_client *client = chip->client;
+
+ if (max14656_read_reg(client, MAX14656_DEVICE_ID, &val))
+ return -ENODEV;
+
+ if ((val & DEVICE_VENDOR_MASK) != 0x20) {
+ dev_err(&client->dev, "wrong vendor ID %d\n",
+ ((val & DEVICE_VENDOR_MASK) >> 4));
+ return -ENODEV;
+ }
+ rev = val & DEVICE_REV_MASK;
+
+ /* Turn on ADC_EN */
+ if (max14656_write_reg(client, MAX14656_CONTROL_2, CONTROL2_ADC_EN))
+ return -EINVAL;
+
+ /* turn on interrupts and low power mode */
+ if (max14656_write_reg(client, MAX14656_CONTROL_1,
+ CONTROL1_DEFAULT |
+ CONTROL1_INT_EN |
+ CONTROL1_INT_ACTIVE_HIGH |
+ CONTROL1_EDGE))
+ return -EINVAL;
+
+ if (max14656_write_reg(client, MAX14656_INTMASK_1, 0x3))
+ return -EINVAL;
+
+ if (max14656_write_reg(client, MAX14656_INTMASK_2, 0x1))
+ return -EINVAL;
+
+ dev_info(&client->dev, "detected revision %d\n", rev);
+ return 0;
+}
+
+static int max14656_get_property(struct power_supply *psy,
+ enum power_supply_property psp,
+ union power_supply_propval *val)
+{
+ struct max14656_chip *chip = power_supply_get_drvdata(psy);
+
+ switch (psp) {
+ case POWER_SUPPLY_PROP_ONLINE:
+ val->intval = chip->online;
+ break;
+ case POWER_SUPPLY_PROP_MODEL_NAME:
+ val->strval = MAX14656_NAME;
+ break;
+ case POWER_SUPPLY_PROP_MANUFACTURER:
+ val->strval = MAX14656_MANUFACTURER;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static enum power_supply_property max14656_battery_props[] = {
+ POWER_SUPPLY_PROP_ONLINE,
+ POWER_SUPPLY_PROP_MODEL_NAME,
+ POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static int max14656_probe(struct i2c_client *client,
+ const struct i2c_device_id *id)
+{
+ struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
+ struct device *dev = &client->dev;
+ struct power_supply_config psy_cfg = {};
+ struct max14656_chip *chip;
+ int irq = client->irq;
+ int ret = 0;
+
+ if (irq <= 0) {
+ dev_err(dev, "invalid irq number: %d\n", irq);
+ return -ENODEV;
+ }
+
+ if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
+ dev_err(dev, "No support for SMBUS_BYTE_DATA\n");
+ return -ENODEV;
+ }
+
+ chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+ if (!chip)
+ return -ENOMEM;
+
+ psy_cfg.drv_data = chip;
+ chip->client = client;
+ chip->online = 0;
+ chip->psy_desc.name = MAX14656_NAME;
+ chip->psy_desc.type = POWER_SUPPLY_TYPE_UNKNOWN;
+ chip->psy_desc.properties = max14656_battery_props;
+ chip->psy_desc.num_properties = ARRAY_SIZE(max14656_battery_props);
+ chip->psy_desc.get_property = max14656_get_property;
+ chip->irq = irq;
+
+ ret = max14656_hw_init(chip);
+ if (ret)
+ return -ENODEV;
+
+ INIT_DELAYED_WORK(&chip->irq_work, max14656_irq_worker);
+
+ ret = devm_request_irq(dev, chip->irq, max14656_irq,
+ IRQF_TRIGGER_FALLING,
+ MAX14656_NAME, chip);
+ if (ret) {
+ dev_err(dev, "request_irq %d failed\n", chip->irq);
+ return -EINVAL;
+ }
+ enable_irq_wake(chip->irq);
+
+ chip->detect_psy = devm_power_supply_register(dev,
+ &chip->psy_desc, &psy_cfg);
+ if (IS_ERR(chip->detect_psy)) {
+ dev_err(dev, "power_supply_register failed\n");
+ return -EINVAL;
+ }
+
+ schedule_delayed_work(&chip->irq_work, msecs_to_jiffies(2000));
+
+ return 0;
+}
+
+static const struct i2c_device_id max14656_id[] = {
+ { "max14656", 0 },
+ {}
+};
+MODULE_DEVICE_TABLE(i2c, max14656_id);
+
+static const struct of_device_id max14656_match_table[] = {
+ { .compatible = "maxim,max14656", },
+ {}
+};
+MODULE_DEVICE_TABLE(of, max14656_match_table);
+
+static struct i2c_driver max14656_i2c_driver = {
+ .driver = {
+ .name = "max14656",
+ .of_match_table = max14656_match_table,
+ },
+ .probe = max14656_probe,
+ .id_table = max14656_id,
+};
+module_i2c_driver(max14656_i2c_driver);
+
+MODULE_DESCRIPTION("MAX14656 USB charger detector");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/supply/max8997_charger.c b/drivers/power/supply/max8997_charger.c
index 290ddc1..fa86100 100644
--- a/drivers/power/supply/max8997_charger.c
+++ b/drivers/power/supply/max8997_charger.c
@@ -148,10 +148,8 @@
charger = devm_kzalloc(&pdev->dev, sizeof(struct charger_data),
GFP_KERNEL);
- if (charger == NULL) {
- dev_err(&pdev->dev, "Cannot allocate memory.\n");
+ if (!charger)
return -ENOMEM;
- }
platform_set_drvdata(pdev, charger);
@@ -161,7 +159,7 @@
psy_cfg.drv_data = charger;
- charger->battery = power_supply_register(&pdev->dev,
+ charger->battery = devm_power_supply_register(&pdev->dev,
&max8997_battery_desc,
&psy_cfg);
if (IS_ERR(charger->battery)) {
@@ -172,14 +170,6 @@
return 0;
}
-static int max8997_battery_remove(struct platform_device *pdev)
-{
- struct charger_data *charger = platform_get_drvdata(pdev);
-
- power_supply_unregister(charger->battery);
- return 0;
-}
-
static const struct platform_device_id max8997_battery_id[] = {
{ "max8997-battery", 0 },
{ }
@@ -191,7 +181,6 @@
.name = "max8997-battery",
},
.probe = max8997_battery_probe,
- .remove = max8997_battery_remove,
.id_table = max8997_battery_id,
};
diff --git a/drivers/power/supply/pcf50633-charger.c b/drivers/power/supply/pcf50633-charger.c
index d05597b..b3c1873 100644
--- a/drivers/power/supply/pcf50633-charger.c
+++ b/drivers/power/supply/pcf50633-charger.c
@@ -393,7 +393,6 @@
{
struct power_supply_config psy_cfg = {};
struct pcf50633_mbc *mbc;
- int ret;
int i;
u8 mbcs1;
@@ -419,8 +418,7 @@
&psy_cfg);
if (IS_ERR(mbc->adapter)) {
dev_err(mbc->pcf->dev, "failed to register adapter\n");
- ret = PTR_ERR(mbc->adapter);
- return ret;
+ return PTR_ERR(mbc->adapter);
}
mbc->usb = power_supply_register(&pdev->dev, &pcf50633_mbc_usb_desc,
@@ -428,8 +426,7 @@
if (IS_ERR(mbc->usb)) {
dev_err(mbc->pcf->dev, "failed to register usb\n");
power_supply_unregister(mbc->adapter);
- ret = PTR_ERR(mbc->usb);
- return ret;
+ return PTR_ERR(mbc->usb);
}
mbc->ac = power_supply_register(&pdev->dev, &pcf50633_mbc_ac_desc,
@@ -438,12 +435,10 @@
dev_err(mbc->pcf->dev, "failed to register ac\n");
power_supply_unregister(mbc->adapter);
power_supply_unregister(mbc->usb);
- ret = PTR_ERR(mbc->ac);
- return ret;
+ return PTR_ERR(mbc->ac);
}
- ret = sysfs_create_group(&pdev->dev.kobj, &mbc_attr_group);
- if (ret)
+ if (sysfs_create_group(&pdev->dev.kobj, &mbc_attr_group))
dev_err(mbc->pcf->dev, "failed to create sysfs entries\n");
mbcs1 = pcf50633_reg_read(mbc->pcf, PCF50633_REG_MBCS1);
diff --git a/drivers/power/supply/qcom_smbb.c b/drivers/power/supply/qcom_smbb.c
index b5896ba..f6a0d24 100644
--- a/drivers/power/supply/qcom_smbb.c
+++ b/drivers/power/supply/qcom_smbb.c
@@ -35,6 +35,7 @@
#include <linux/regmap.h>
#include <linux/slab.h>
#include <linux/extcon.h>
+#include <linux/regulator/driver.h>
#define SMBB_CHG_VMAX 0x040
#define SMBB_CHG_VSAFE 0x041
@@ -72,6 +73,8 @@
#define BTC_CTRL_HOT_EXT_N BIT(0)
#define SMBB_USB_IMAX 0x344
+#define SMBB_USB_OTG_CTL 0x348
+#define OTG_CTL_EN BIT(0)
#define SMBB_USB_ENUM_TIMER_STOP 0x34e
#define ENUM_TIMER_STOP BIT(0)
#define SMBB_USB_SEC_ACCESS 0x3d0
@@ -125,6 +128,9 @@
struct power_supply *dc_psy;
struct power_supply *bat_psy;
struct regmap *regmap;
+
+ struct regulator_desc otg_rdesc;
+ struct regulator_dev *otg_reg;
};
static const unsigned int smbb_usb_extcon_cable[] = {
@@ -378,7 +384,7 @@
struct smbb_charger *chg = _data;
smbb_set_line_flag(chg, irq, STATUS_USBIN_VALID);
- extcon_set_cable_state_(chg->edev, EXTCON_USB,
+ extcon_set_state_sync(chg->edev, EXTCON_USB,
chg->status & STATUS_USBIN_VALID);
power_supply_changed(chg->usb_psy);
@@ -787,12 +793,56 @@
.property_is_writeable = smbb_charger_writable_property,
};
+static int smbb_chg_otg_enable(struct regulator_dev *rdev)
+{
+ struct smbb_charger *chg = rdev_get_drvdata(rdev);
+ int rc;
+
+ rc = regmap_update_bits(chg->regmap, chg->addr + SMBB_USB_OTG_CTL,
+ OTG_CTL_EN, OTG_CTL_EN);
+ if (rc)
+ dev_err(chg->dev, "failed to update OTG_CTL\n");
+ return rc;
+}
+
+static int smbb_chg_otg_disable(struct regulator_dev *rdev)
+{
+ struct smbb_charger *chg = rdev_get_drvdata(rdev);
+ int rc;
+
+ rc = regmap_update_bits(chg->regmap, chg->addr + SMBB_USB_OTG_CTL,
+ OTG_CTL_EN, 0);
+ if (rc)
+ dev_err(chg->dev, "failed to update OTG_CTL\n");
+ return rc;
+}
+
+static int smbb_chg_otg_is_enabled(struct regulator_dev *rdev)
+{
+ struct smbb_charger *chg = rdev_get_drvdata(rdev);
+ unsigned int value = 0;
+ int rc;
+
+ rc = regmap_read(chg->regmap, chg->addr + SMBB_USB_OTG_CTL, &value);
+ if (rc)
+ dev_err(chg->dev, "failed to read OTG_CTL\n");
+
+ return !!(value & OTG_CTL_EN);
+}
+
+static const struct regulator_ops smbb_chg_otg_ops = {
+ .enable = smbb_chg_otg_enable,
+ .disable = smbb_chg_otg_disable,
+ .is_enabled = smbb_chg_otg_is_enabled,
+};
+
static int smbb_charger_probe(struct platform_device *pdev)
{
struct power_supply_config bat_cfg = {};
struct power_supply_config usb_cfg = {};
struct power_supply_config dc_cfg = {};
struct smbb_charger *chg;
+ struct regulator_config config = { };
int rc, i;
chg = devm_kzalloc(&pdev->dev, sizeof(*chg), GFP_KERNEL);
@@ -905,6 +955,26 @@
}
}
+ /*
+ * otg regulator is used to control VBUS voltage direction
+ * when USB switches between host and gadget mode
+ */
+ chg->otg_rdesc.id = -1;
+ chg->otg_rdesc.name = "otg-vbus";
+ chg->otg_rdesc.ops = &smbb_chg_otg_ops;
+ chg->otg_rdesc.owner = THIS_MODULE;
+ chg->otg_rdesc.type = REGULATOR_VOLTAGE;
+ chg->otg_rdesc.supply_name = "usb-otg-in";
+ chg->otg_rdesc.of_match = "otg-vbus";
+
+ config.dev = &pdev->dev;
+ config.driver_data = chg;
+
+ chg->otg_reg = devm_regulator_register(&pdev->dev, &chg->otg_rdesc,
+ &config);
+ if (IS_ERR(chg->otg_reg))
+ return PTR_ERR(chg->otg_reg);
+
chg->jeita_ext_temp = of_property_read_bool(pdev->dev.of_node,
"qcom,jeita-extended-temp-range");
diff --git a/drivers/power/supply/sbs-charger.c b/drivers/power/supply/sbs-charger.c
new file mode 100644
index 0000000..353765a
--- /dev/null
+++ b/drivers/power/supply/sbs-charger.c
@@ -0,0 +1,274 @@
+/*
+ * Copyright (c) 2016, Prodys S.L.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This adds support for sbs-charger compilant chips as defined here:
+ * http://sbs-forum.org/specs/sbc110.pdf
+ *
+ * Implemetation based on sbs-battery.c
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/power_supply.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/gpio.h>
+#include <linux/regmap.h>
+#include <linux/of_gpio.h>
+#include <linux/bitops.h>
+
+#define SBS_CHARGER_REG_SPEC_INFO 0x11
+#define SBS_CHARGER_REG_STATUS 0x13
+#define SBS_CHARGER_REG_ALARM_WARNING 0x16
+
+#define SBS_CHARGER_STATUS_CHARGE_INHIBITED BIT(1)
+#define SBS_CHARGER_STATUS_RES_COLD BIT(9)
+#define SBS_CHARGER_STATUS_RES_HOT BIT(10)
+#define SBS_CHARGER_STATUS_BATTERY_PRESENT BIT(14)
+#define SBS_CHARGER_STATUS_AC_PRESENT BIT(15)
+
+#define SBS_CHARGER_POLL_TIME 500
+
+struct sbs_info {
+ struct i2c_client *client;
+ struct power_supply *power_supply;
+ struct regmap *regmap;
+ struct delayed_work work;
+ unsigned int last_state;
+};
+
+static int sbs_get_property(struct power_supply *psy,
+ enum power_supply_property psp,
+ union power_supply_propval *val)
+{
+ struct sbs_info *chip = power_supply_get_drvdata(psy);
+ unsigned int reg;
+
+ reg = chip->last_state;
+
+ switch (psp) {
+ case POWER_SUPPLY_PROP_PRESENT:
+ val->intval = !!(reg & SBS_CHARGER_STATUS_BATTERY_PRESENT);
+ break;
+
+ case POWER_SUPPLY_PROP_ONLINE:
+ val->intval = !!(reg & SBS_CHARGER_STATUS_AC_PRESENT);
+ break;
+
+ case POWER_SUPPLY_PROP_STATUS:
+ val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
+
+ if (!(reg & SBS_CHARGER_STATUS_BATTERY_PRESENT))
+ val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
+ else if (reg & SBS_CHARGER_STATUS_AC_PRESENT &&
+ !(reg & SBS_CHARGER_STATUS_CHARGE_INHIBITED))
+ val->intval = POWER_SUPPLY_STATUS_CHARGING;
+ else
+ val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+
+ break;
+
+ case POWER_SUPPLY_PROP_HEALTH:
+ if (reg & SBS_CHARGER_STATUS_RES_COLD)
+ val->intval = POWER_SUPPLY_HEALTH_COLD;
+ if (reg & SBS_CHARGER_STATUS_RES_HOT)
+ val->intval = POWER_SUPPLY_HEALTH_OVERHEAT;
+ else
+ val->intval = POWER_SUPPLY_HEALTH_GOOD;
+
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int sbs_check_state(struct sbs_info *chip)
+{
+ unsigned int reg;
+ int ret;
+
+ ret = regmap_read(chip->regmap, SBS_CHARGER_REG_STATUS, ®);
+ if (!ret && reg != chip->last_state) {
+ chip->last_state = reg;
+ power_supply_changed(chip->power_supply);
+ return 1;
+ }
+
+ return 0;
+}
+
+static void sbs_delayed_work(struct work_struct *work)
+{
+ struct sbs_info *chip = container_of(work, struct sbs_info, work.work);
+
+ sbs_check_state(chip);
+
+ schedule_delayed_work(&chip->work,
+ msecs_to_jiffies(SBS_CHARGER_POLL_TIME));
+}
+
+static irqreturn_t sbs_irq_thread(int irq, void *data)
+{
+ struct sbs_info *chip = data;
+ int ret;
+
+ ret = sbs_check_state(chip);
+
+ return ret ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static enum power_supply_property sbs_properties[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_PRESENT,
+ POWER_SUPPLY_PROP_ONLINE,
+ POWER_SUPPLY_PROP_HEALTH,
+};
+
+static bool sbs_readable_reg(struct device *dev, unsigned int reg)
+{
+ if (reg < SBS_CHARGER_REG_SPEC_INFO)
+ return false;
+ else
+ return true;
+}
+
+static bool sbs_volatile_reg(struct device *dev, unsigned int reg)
+{
+ switch (reg) {
+ case SBS_CHARGER_REG_STATUS:
+ return true;
+ }
+
+ return false;
+}
+
+static const struct regmap_config sbs_regmap = {
+ .reg_bits = 8,
+ .val_bits = 16,
+ .max_register = SBS_CHARGER_REG_ALARM_WARNING,
+ .readable_reg = sbs_readable_reg,
+ .volatile_reg = sbs_volatile_reg,
+ .val_format_endian = REGMAP_ENDIAN_LITTLE, /* since based on SMBus */
+};
+
+static const struct power_supply_desc sbs_desc = {
+ .name = "sbs-charger",
+ .type = POWER_SUPPLY_TYPE_MAINS,
+ .properties = sbs_properties,
+ .num_properties = ARRAY_SIZE(sbs_properties),
+ .get_property = sbs_get_property,
+};
+
+static int sbs_probe(struct i2c_client *client,
+ const struct i2c_device_id *id)
+{
+ struct power_supply_config psy_cfg = {};
+ struct sbs_info *chip;
+ int ret, val;
+
+ chip = devm_kzalloc(&client->dev, sizeof(struct sbs_info), GFP_KERNEL);
+ if (!chip)
+ return -ENOMEM;
+
+ chip->client = client;
+ psy_cfg.of_node = client->dev.of_node;
+ psy_cfg.drv_data = chip;
+
+ i2c_set_clientdata(client, chip);
+
+ chip->regmap = devm_regmap_init_i2c(client, &sbs_regmap);
+ if (IS_ERR(chip->regmap))
+ return PTR_ERR(chip->regmap);
+
+ /*
+ * Before we register, we need to make sure we can actually talk
+ * to the battery.
+ */
+ ret = regmap_read(chip->regmap, SBS_CHARGER_REG_STATUS, &val);
+ if (ret) {
+ dev_err(&client->dev, "Failed to get device status\n");
+ return ret;
+ }
+ chip->last_state = val;
+
+ chip->power_supply = devm_power_supply_register(&client->dev, &sbs_desc,
+ &psy_cfg);
+ if (IS_ERR(chip->power_supply)) {
+ dev_err(&client->dev, "Failed to register power supply\n");
+ return PTR_ERR(chip->power_supply);
+ }
+
+ /*
+ * The sbs-charger spec doesn't impose the use of an interrupt. So in
+ * the case it wasn't provided we use polling in order get the charger's
+ * status.
+ */
+ if (client->irq) {
+ ret = devm_request_threaded_irq(&client->dev, client->irq,
+ NULL, sbs_irq_thread,
+ IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+ dev_name(&client->dev), chip);
+ if (ret) {
+ dev_err(&client->dev, "Failed to request irq, %d\n", ret);
+ return ret;
+ }
+ } else {
+ INIT_DELAYED_WORK(&chip->work, sbs_delayed_work);
+ schedule_delayed_work(&chip->work,
+ msecs_to_jiffies(SBS_CHARGER_POLL_TIME));
+ }
+
+ dev_info(&client->dev,
+ "%s: smart charger device registered\n", client->name);
+
+ return 0;
+}
+
+static int sbs_remove(struct i2c_client *client)
+{
+ struct sbs_info *chip = i2c_get_clientdata(client);
+
+ cancel_delayed_work_sync(&chip->work);
+
+ return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id sbs_dt_ids[] = {
+ { .compatible = "sbs,sbs-charger" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, sbs_dt_ids);
+#endif
+
+static const struct i2c_device_id sbs_id[] = {
+ { "sbs-charger", 0 },
+ { }
+};
+MODULE_DEVICE_TABLE(i2c, sbs_id);
+
+static struct i2c_driver sbs_driver = {
+ .probe = sbs_probe,
+ .remove = sbs_remove,
+ .id_table = sbs_id,
+ .driver = {
+ .name = "sbs-charger",
+ .of_match_table = of_match_ptr(sbs_dt_ids),
+ },
+};
+module_i2c_driver(sbs_driver);
+
+MODULE_AUTHOR("Nicolas Saenz Julienne <nicolassaenzj@gmail.com>");
+MODULE_DESCRIPTION("SBS smart charger driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/supply/tps65217_charger.c b/drivers/power/supply/tps65217_charger.c
index 9fd019f..29b61e8 100644
--- a/drivers/power/supply/tps65217_charger.c
+++ b/drivers/power/supply/tps65217_charger.c
@@ -35,22 +35,22 @@
#include <linux/mfd/core.h>
#include <linux/mfd/tps65217.h>
+#define CHARGER_STATUS_PRESENT (TPS65217_STATUS_ACPWR | TPS65217_STATUS_USBPWR)
+#define NUM_CHARGER_IRQS 2
#define POLL_INTERVAL (HZ * 2)
struct tps65217_charger {
struct tps65217 *tps;
struct device *dev;
- struct power_supply *ac;
+ struct power_supply *psy;
- int ac_online;
- int prev_ac_online;
+ int online;
+ int prev_online;
struct task_struct *poll_task;
-
- int irq;
};
-static enum power_supply_property tps65217_ac_props[] = {
+static enum power_supply_property tps65217_charger_props[] = {
POWER_SUPPLY_PROP_ONLINE,
};
@@ -95,7 +95,7 @@
int ret;
/* charger already enabled */
- if (charger->ac_online)
+ if (charger->online)
return 0;
dev_dbg(charger->dev, "%s: enable charging\n", __func__);
@@ -110,19 +110,19 @@
return ret;
}
- charger->ac_online = 1;
+ charger->online = 1;
return 0;
}
-static int tps65217_ac_get_property(struct power_supply *psy,
- enum power_supply_property psp,
- union power_supply_propval *val)
+static int tps65217_charger_get_property(struct power_supply *psy,
+ enum power_supply_property psp,
+ union power_supply_propval *val)
{
struct tps65217_charger *charger = power_supply_get_drvdata(psy);
if (psp == POWER_SUPPLY_PROP_ONLINE) {
- val->intval = charger->ac_online;
+ val->intval = charger->online;
return 0;
}
return -EINVAL;
@@ -133,7 +133,7 @@
int ret, val;
struct tps65217_charger *charger = dev;
- charger->prev_ac_online = charger->ac_online;
+ charger->prev_online = charger->online;
ret = tps65217_reg_read(charger->tps, TPS65217_REG_STATUS, &val);
if (ret < 0) {
@@ -144,8 +144,8 @@
dev_dbg(charger->dev, "%s: 0x%x\n", __func__, val);
- /* check for AC status bit */
- if (val & TPS65217_STATUS_ACPWR) {
+ /* check for charger status bit */
+ if (val & CHARGER_STATUS_PRESENT) {
ret = tps65217_enable_charging(charger);
if (ret) {
dev_err(charger->dev,
@@ -153,11 +153,11 @@
return IRQ_HANDLED;
}
} else {
- charger->ac_online = 0;
+ charger->online = 0;
}
- if (charger->prev_ac_online != charger->ac_online)
- power_supply_changed(charger->ac);
+ if (charger->prev_online != charger->online)
+ power_supply_changed(charger->psy);
ret = tps65217_reg_read(charger->tps, TPS65217_REG_CHGCONFIG0, &val);
if (ret < 0) {
@@ -188,11 +188,11 @@
}
static const struct power_supply_desc tps65217_charger_desc = {
- .name = "tps65217-ac",
+ .name = "tps65217-charger",
.type = POWER_SUPPLY_TYPE_MAINS,
- .get_property = tps65217_ac_get_property,
- .properties = tps65217_ac_props,
- .num_properties = ARRAY_SIZE(tps65217_ac_props),
+ .get_property = tps65217_charger_get_property,
+ .properties = tps65217_charger_props,
+ .num_properties = ARRAY_SIZE(tps65217_charger_props),
};
static int tps65217_charger_probe(struct platform_device *pdev)
@@ -200,8 +200,10 @@
struct tps65217 *tps = dev_get_drvdata(pdev->dev.parent);
struct tps65217_charger *charger;
struct power_supply_config cfg = {};
- int irq;
+ struct task_struct *poll_task;
+ int irq[NUM_CHARGER_IRQS];
int ret;
+ int i;
dev_dbg(&pdev->dev, "%s\n", __func__);
@@ -216,18 +218,16 @@
cfg.of_node = pdev->dev.of_node;
cfg.drv_data = charger;
- charger->ac = devm_power_supply_register(&pdev->dev,
- &tps65217_charger_desc,
- &cfg);
- if (IS_ERR(charger->ac)) {
+ charger->psy = devm_power_supply_register(&pdev->dev,
+ &tps65217_charger_desc,
+ &cfg);
+ if (IS_ERR(charger->psy)) {
dev_err(&pdev->dev, "failed: power supply register\n");
- return PTR_ERR(charger->ac);
+ return PTR_ERR(charger->psy);
}
- irq = platform_get_irq_byname(pdev, "AC");
- if (irq < 0)
- irq = -ENXIO;
- charger->irq = irq;
+ irq[0] = platform_get_irq_byname(pdev, "USB");
+ irq[1] = platform_get_irq_byname(pdev, "AC");
ret = tps65217_config_charger(charger);
if (ret < 0) {
@@ -235,29 +235,36 @@
return ret;
}
- if (irq != -ENXIO) {
- ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
+ /* Create a polling thread if an interrupt is invalid */
+ if (irq[0] < 0 || irq[1] < 0) {
+ poll_task = kthread_run(tps65217_charger_poll_task,
+ charger, "ktps65217charger");
+ if (IS_ERR(poll_task)) {
+ ret = PTR_ERR(poll_task);
+ dev_err(charger->dev,
+ "Unable to run kthread err %d\n", ret);
+ return ret;
+ }
+
+ charger->poll_task = poll_task;
+ return 0;
+ }
+
+ /* Create IRQ threads for charger interrupts */
+ for (i = 0; i < NUM_CHARGER_IRQS; i++) {
+ ret = devm_request_threaded_irq(&pdev->dev, irq[i], NULL,
tps65217_charger_irq,
0, "tps65217-charger",
charger);
if (ret) {
dev_err(charger->dev,
- "Unable to register irq %d err %d\n", irq,
+ "Unable to register irq %d err %d\n", irq[i],
ret);
return ret;
}
/* Check current state */
- tps65217_charger_irq(irq, charger);
- } else {
- charger->poll_task = kthread_run(tps65217_charger_poll_task,
- charger, "ktps65217charger");
- if (IS_ERR(charger->poll_task)) {
- ret = PTR_ERR(charger->poll_task);
- dev_err(charger->dev,
- "Unable to run kthread err %d\n", ret);
- return ret;
- }
+ tps65217_charger_irq(-1, charger);
}
return 0;
@@ -267,7 +274,7 @@
{
struct tps65217_charger *charger = platform_get_drvdata(pdev);
- if (charger->irq == -ENXIO)
+ if (charger->poll_task)
kthread_stop(charger->poll_task);
return 0;
diff --git a/drivers/power/supply/wm97xx_battery.c b/drivers/power/supply/wm97xx_battery.c
index e3edb31..bd4f666 100644
--- a/drivers/power/supply/wm97xx_battery.c
+++ b/drivers/power/supply/wm97xx_battery.c
@@ -175,11 +175,6 @@
if (dev->id != -1)
return -EINVAL;
- if (!pdata) {
- dev_err(&dev->dev, "No platform_data supplied\n");
- return -EINVAL;
- }
-
if (gpio_is_valid(pdata->charge_gpio)) {
ret = gpio_request(pdata->charge_gpio, "BATT CHRG");
if (ret)
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index e6a512e..a3ade9e 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -272,7 +272,7 @@
64, AXP806_DCDCD_V_CTRL, 0x3f, AXP806_PWR_OUT_CTRL1,
BIT(3)),
AXP_DESC(AXP806, DCDCE, "dcdce", "vine", 1100, 3400, 100,
- AXP806_DCDCB_V_CTRL, 0x1f, AXP806_PWR_OUT_CTRL1, BIT(4)),
+ AXP806_DCDCE_V_CTRL, 0x1f, AXP806_PWR_OUT_CTRL1, BIT(4)),
AXP_DESC(AXP806, ALDO1, "aldo1", "aldoin", 700, 3300, 100,
AXP806_ALDO1_V_CTRL, 0x1f, AXP806_PWR_OUT_CTRL1, BIT(5)),
AXP_DESC(AXP806, ALDO2, "aldo2", "aldoin", 700, 3400, 100,
diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c
index a43b0e8..988a747 100644
--- a/drivers/regulator/fixed.c
+++ b/drivers/regulator/fixed.c
@@ -30,9 +30,6 @@
#include <linux/of_gpio.h>
#include <linux/regulator/of_regulator.h>
#include <linux/regulator/machine.h>
-#include <linux/acpi.h>
-#include <linux/property.h>
-#include <linux/gpio/consumer.h>
struct fixed_voltage_data {
struct regulator_desc desc;
@@ -97,44 +94,6 @@
return config;
}
-/**
- * acpi_get_fixed_voltage_config - extract fixed_voltage_config structure info
- * @dev: device requesting for fixed_voltage_config
- * @desc: regulator description
- *
- * Populates fixed_voltage_config structure by extracting data through ACPI
- * interface, returns a pointer to the populated structure of NULL if memory
- * alloc fails.
- */
-static struct fixed_voltage_config *
-acpi_get_fixed_voltage_config(struct device *dev,
- const struct regulator_desc *desc)
-{
- struct fixed_voltage_config *config;
- const char *supply_name;
- struct gpio_desc *gpiod;
- int ret;
-
- config = devm_kzalloc(dev, sizeof(*config), GFP_KERNEL);
- if (!config)
- return ERR_PTR(-ENOMEM);
-
- ret = device_property_read_string(dev, "supply-name", &supply_name);
- if (!ret)
- config->supply_name = supply_name;
-
- gpiod = gpiod_get(dev, "gpio", GPIOD_ASIS);
- if (IS_ERR(gpiod))
- return ERR_PTR(-ENODEV);
-
- config->gpio = desc_to_gpio(gpiod);
- config->enable_high = device_property_read_bool(dev,
- "enable-active-high");
- gpiod_put(gpiod);
-
- return config;
-}
-
static struct regulator_ops fixed_voltage_ops = {
};
@@ -155,11 +114,6 @@
&drvdata->desc);
if (IS_ERR(config))
return PTR_ERR(config);
- } else if (ACPI_HANDLE(&pdev->dev)) {
- config = acpi_get_fixed_voltage_config(&pdev->dev,
- &drvdata->desc);
- if (IS_ERR(config))
- return PTR_ERR(config);
} else {
config = dev_get_platdata(&pdev->dev);
}
diff --git a/drivers/regulator/twl6030-regulator.c b/drivers/regulator/twl6030-regulator.c
index 4864b9d..7161910 100644
--- a/drivers/regulator/twl6030-regulator.c
+++ b/drivers/regulator/twl6030-regulator.c
@@ -452,7 +452,7 @@
vsel = 62;
else if ((min_uV > 1800000) && (min_uV <= 1900000))
vsel = 61;
- else if ((min_uV > 1350000) && (min_uV <= 1800000))
+ else if ((min_uV > 1500000) && (min_uV <= 1800000))
vsel = 60;
else if ((min_uV > 1350000) && (min_uV <= 1500000))
vsel = 59;
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 9a507e7..90b05c7 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -396,9 +396,6 @@
goto unwind_vring_allocations;
}
- /* track the rvdevs list reference */
- kref_get(&rvdev->refcount);
-
list_add_tail(&rvdev->node, &rproc->rvdevs);
rproc_add_subdev(rproc, &rvdev->subdev,
@@ -889,13 +886,15 @@
/*
* Create a copy of the resource table. When a virtio device starts
* and calls vring_new_virtqueue() the address of the allocated vring
- * will be stored in the table_ptr. Before the device is started,
- * table_ptr will be copied into device memory.
+ * will be stored in the cached_table. Before the device is started,
+ * cached_table will be copied into device memory.
*/
- rproc->table_ptr = kmemdup(table, tablesz, GFP_KERNEL);
- if (!rproc->table_ptr)
+ rproc->cached_table = kmemdup(table, tablesz, GFP_KERNEL);
+ if (!rproc->cached_table)
goto clean_up;
+ rproc->table_ptr = rproc->cached_table;
+
/* reset max_notifyid */
rproc->max_notifyid = -1;
@@ -914,16 +913,18 @@
}
/*
- * The starting device has been given the rproc->table_ptr as the
+ * The starting device has been given the rproc->cached_table as the
* resource table. The address of the vring along with the other
- * allocated resources (carveouts etc) is stored in table_ptr.
+ * allocated resources (carveouts etc) is stored in cached_table.
* In order to pass this information to the remote device we must copy
* this information to device memory. We also update the table_ptr so
* that any subsequent changes will be applied to the loaded version.
*/
loaded_table = rproc_find_loaded_rsc_table(rproc, fw);
- if (loaded_table)
- memcpy(loaded_table, rproc->table_ptr, tablesz);
+ if (loaded_table) {
+ memcpy(loaded_table, rproc->cached_table, tablesz);
+ rproc->table_ptr = loaded_table;
+ }
/* power up the remote processor */
ret = rproc->ops->start(rproc);
@@ -951,7 +952,8 @@
clean_up_resources:
rproc_resource_cleanup(rproc);
clean_up:
- kfree(rproc->table_ptr);
+ kfree(rproc->cached_table);
+ rproc->cached_table = NULL;
rproc->table_ptr = NULL;
rproc_disable_iommu(rproc);
@@ -1185,7 +1187,8 @@
rproc_disable_iommu(rproc);
/* Free the copy of the resource table */
- kfree(rproc->table_ptr);
+ kfree(rproc->cached_table);
+ rproc->cached_table = NULL;
rproc->table_ptr = NULL;
/* if in crash state, unlock crash handler */
diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index 10368ed..b6f5f1e 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -163,7 +163,7 @@
}
ret = rstc->rcdev->ops->reset(rstc->rcdev, rstc->id);
- if (rstc->shared && !ret)
+ if (rstc->shared && ret)
atomic_dec(&rstc->triggered_count);
return ret;
diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c
index a79cb5a..1cfb775 100644
--- a/drivers/rpmsg/rpmsg_core.c
+++ b/drivers/rpmsg/rpmsg_core.c
@@ -453,8 +453,8 @@
struct device *dev = &rpdev->dev;
int ret;
- dev_set_name(&rpdev->dev, "%s:%s",
- dev_name(dev->parent), rpdev->id.name);
+ dev_set_name(&rpdev->dev, "%s.%s.%d.%d", dev_name(dev->parent),
+ rpdev->id.name, rpdev->src, rpdev->dst);
rpdev->dev.bus = &rpmsg_bus;
rpdev->dev.release = rpmsg_release_device;
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index c93c5a8..5dc673d 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1551,12 +1551,15 @@
will be called rtc-mpc5121.
config RTC_DRV_JZ4740
- bool "Ingenic JZ4740 SoC"
+ tristate "Ingenic JZ4740 SoC"
depends on MACH_INGENIC || COMPILE_TEST
help
If you say yes here you get support for the Ingenic JZ47xx SoCs RTC
controllers.
+ This driver can also be buillt as a module. If so, the module
+ will be called rtc-jz4740.
+
config RTC_DRV_LPC24XX
tristate "NXP RTC for LPC178x/18xx/408x/43xx"
depends on ARCH_LPC18XX || COMPILE_TEST
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 72918c1..64989af 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -17,6 +17,7 @@
#include <linux/clk.h>
#include <linux/io.h>
#include <linux/kernel.h>
+#include <linux/module.h>
#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/reboot.h>
@@ -294,7 +295,7 @@
JZ_REG_RTC_RESET_COUNTER, reset_counter_ticks);
jz4740_rtc_poweroff(dev_for_power_off);
- machine_halt();
+ kernel_halt();
}
static const struct of_device_id jz4740_rtc_of_match[] = {
@@ -302,6 +303,7 @@
{ .compatible = "ingenic,jz4780-rtc", .data = (void *)ID_JZ4780 },
{},
};
+MODULE_DEVICE_TABLE(of, jz4740_rtc_of_match);
static int jz4740_rtc_probe(struct platform_device *pdev)
{
@@ -429,6 +431,7 @@
{ "jz4780-rtc", ID_JZ4780 },
{}
};
+MODULE_DEVICE_TABLE(platform, jz4740_rtc_ids);
static struct platform_driver jz4740_rtc_driver = {
.probe = jz4740_rtc_probe,
@@ -440,4 +443,9 @@
.id_table = jz4740_rtc_ids,
};
-builtin_platform_driver(jz4740_rtc_driver);
+module_platform_driver(jz4740_rtc_driver);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RTC driver for the JZ4740 SoC\n");
+MODULE_ALIAS("platform:jz4740-rtc");
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 75f820ca..27ff38f 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -1583,7 +1583,7 @@
int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
{
struct zfcp_qdio *qdio = wka_port->adapter->qdio;
- struct zfcp_fsf_req *req = NULL;
+ struct zfcp_fsf_req *req;
int retval = -EIO;
spin_lock_irq(&qdio->req_q_lock);
@@ -1612,7 +1612,7 @@
zfcp_fsf_req_free(req);
out:
spin_unlock_irq(&qdio->req_q_lock);
- if (req && !IS_ERR(req))
+ if (!retval)
zfcp_dbf_rec_run_wka("fsowp_1", wka_port, req->req_id);
return retval;
}
@@ -1638,7 +1638,7 @@
int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
{
struct zfcp_qdio *qdio = wka_port->adapter->qdio;
- struct zfcp_fsf_req *req = NULL;
+ struct zfcp_fsf_req *req;
int retval = -EIO;
spin_lock_irq(&qdio->req_q_lock);
@@ -1667,7 +1667,7 @@
zfcp_fsf_req_free(req);
out:
spin_unlock_irq(&qdio->req_q_lock);
- if (req && !IS_ERR(req))
+ if (!retval)
zfcp_dbf_rec_run_wka("fscwp_1", wka_port, req->req_id);
return retval;
}
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 639ed4e..070c4da 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -145,6 +145,7 @@
#define CCW_CMD_WRITE_CONF 0x21
#define CCW_CMD_WRITE_STATUS 0x31
#define CCW_CMD_READ_VQ_CONF 0x32
+#define CCW_CMD_READ_STATUS 0x72
#define CCW_CMD_SET_IND_ADAPTER 0x73
#define CCW_CMD_SET_VIRTIO_REV 0x83
@@ -160,6 +161,7 @@
#define VIRTIO_CCW_DOING_SET_CONF_IND 0x04000000
#define VIRTIO_CCW_DOING_SET_IND_ADAPTER 0x08000000
#define VIRTIO_CCW_DOING_SET_VIRTIO_REV 0x10000000
+#define VIRTIO_CCW_DOING_READ_STATUS 0x20000000
#define VIRTIO_CCW_INTPARM_MASK 0xffff0000
static struct virtio_ccw_device *to_vc_device(struct virtio_device *vdev)
@@ -452,7 +454,7 @@
* This may happen on device detach.
*/
if (ret && (ret != -ENODEV))
- dev_warn(&vq->vdev->dev, "Error %d while deleting queue %d",
+ dev_warn(&vq->vdev->dev, "Error %d while deleting queue %d\n",
ret, index);
vring_del_virtqueue(vq);
@@ -892,6 +894,28 @@
static u8 virtio_ccw_get_status(struct virtio_device *vdev)
{
struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+ u8 old_status = *vcdev->status;
+ struct ccw1 *ccw;
+
+ if (vcdev->revision < 1)
+ return *vcdev->status;
+
+ ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+ if (!ccw)
+ return old_status;
+
+ ccw->cmd_code = CCW_CMD_READ_STATUS;
+ ccw->flags = 0;
+ ccw->count = sizeof(*vcdev->status);
+ ccw->cda = (__u32)(unsigned long)vcdev->status;
+ ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_STATUS);
+/*
+ * If the channel program failed (should only happen if the device
+ * was hotunplugged, and then we clean up via the machine check
+ * handler anyway), vcdev->status was not overwritten and we just
+ * return the old status, which is fine.
+*/
+ kfree(ccw);
return *vcdev->status;
}
@@ -920,7 +944,7 @@
kfree(ccw);
}
-static struct virtio_config_ops virtio_ccw_config_ops = {
+static const struct virtio_config_ops virtio_ccw_config_ops = {
.get_features = virtio_ccw_get_features,
.finalize_features = virtio_ccw_finalize_features,
.get = virtio_ccw_get_config,
@@ -987,6 +1011,7 @@
case VIRTIO_CCW_DOING_READ_CONFIG:
case VIRTIO_CCW_DOING_WRITE_CONFIG:
case VIRTIO_CCW_DOING_WRITE_STATUS:
+ case VIRTIO_CCW_DOING_READ_STATUS:
case VIRTIO_CCW_DOING_SET_VQ:
case VIRTIO_CCW_DOING_SET_IND:
case VIRTIO_CCW_DOING_SET_CONF_IND:
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 4f56b10..5b48bed 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -50,9 +50,13 @@
static inline int aac_is_msix_mode(struct aac_dev *dev)
{
- u32 status;
+ u32 status = 0;
- status = src_readl(dev, MUnit.OMR);
+ if (dev->pdev->device == PMC_DEVICE_S6 ||
+ dev->pdev->device == PMC_DEVICE_S7 ||
+ dev->pdev->device == PMC_DEVICE_S8) {
+ status = src_readl(dev, MUnit.OMR);
+ }
return (status & AAC_INT_MODE_MSIX);
}
diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c
index d9e1521..5caf5f3 100644
--- a/drivers/scsi/bfa/bfad.c
+++ b/drivers/scsi/bfa/bfad.c
@@ -64,9 +64,9 @@
u32 bfi_image_cb_size, bfi_image_ct_size, bfi_image_ct2_size;
u32 *bfi_image_cb, *bfi_image_ct, *bfi_image_ct2;
-#define BFAD_FW_FILE_CB "cbfw-3.2.3.0.bin"
-#define BFAD_FW_FILE_CT "ctfw-3.2.3.0.bin"
-#define BFAD_FW_FILE_CT2 "ct2fw-3.2.3.0.bin"
+#define BFAD_FW_FILE_CB "cbfw-3.2.5.1.bin"
+#define BFAD_FW_FILE_CT "ctfw-3.2.5.1.bin"
+#define BFAD_FW_FILE_CT2 "ct2fw-3.2.5.1.bin"
static u32 *bfad_load_fwimg(struct pci_dev *pdev);
static void bfad_free_fwimg(void);
diff --git a/drivers/scsi/bfa/bfad_bsg.c b/drivers/scsi/bfa/bfad_bsg.c
index a9a0016..b2e8c0d 100644
--- a/drivers/scsi/bfa/bfad_bsg.c
+++ b/drivers/scsi/bfa/bfad_bsg.c
@@ -3363,7 +3363,7 @@
struct bfad_fcxp *drv_fcxp;
struct bfa_fcs_lport_s *fcs_port;
struct bfa_fcs_rport_s *fcs_rport;
- struct fc_bsg_request *bsg_request = bsg_request;
+ struct fc_bsg_request *bsg_request = job->request;
struct fc_bsg_reply *bsg_reply = job->reply;
uint32_t command_type = bsg_request->msgcode;
unsigned long flags;
diff --git a/drivers/scsi/bfa/bfad_drv.h b/drivers/scsi/bfa/bfad_drv.h
index f9e8620..cfcfff4 100644
--- a/drivers/scsi/bfa/bfad_drv.h
+++ b/drivers/scsi/bfa/bfad_drv.h
@@ -58,7 +58,7 @@
#ifdef BFA_DRIVER_VERSION
#define BFAD_DRIVER_VERSION BFA_DRIVER_VERSION
#else
-#define BFAD_DRIVER_VERSION "3.2.25.0"
+#define BFAD_DRIVER_VERSION "3.2.25.1"
#endif
#define BFAD_PROTO_NAME FCPI_NAME
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 9ddc920..9e4b770 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -248,6 +248,7 @@
struct completion *remove_wait; /* device remove thread blocks */
atomic_t in_flight; /* io counter */
+ bool internal_reset_inprogress;
u32 _reserved; /* fill hole */
unsigned long state_flags; /* protected by host lock */
enum fnic_state state;
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 2544a37..adb3d58 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -2581,6 +2581,19 @@
unsigned long wait_host_tmo;
struct Scsi_Host *shost = sc->device->host;
struct fc_lport *lp = shost_priv(shost);
+ struct fnic *fnic = lport_priv(lp);
+ unsigned long flags;
+
+ spin_lock_irqsave(&fnic->fnic_lock, flags);
+ if (fnic->internal_reset_inprogress == 0) {
+ fnic->internal_reset_inprogress = 1;
+ } else {
+ spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+ FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+ "host reset in progress skipping another host reset\n");
+ return SUCCESS;
+ }
+ spin_unlock_irqrestore(&fnic->fnic_lock, flags);
/*
* If fnic_reset is successful, wait for fabric login to complete
@@ -2601,6 +2614,9 @@
}
}
+ spin_lock_irqsave(&fnic->fnic_lock, flags);
+ fnic->internal_reset_inprogress = 0;
+ spin_unlock_irqrestore(&fnic->fnic_lock, flags);
return ret;
}
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 3d3768a..0f80779 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -46,6 +46,7 @@
#define INITIAL_SRP_LIMIT 800
#define DEFAULT_MAX_SECTORS 256
+#define MAX_TXU 1024 * 1024
static uint max_vdma_size = MAX_H_COPY_RDMA;
@@ -1391,7 +1392,7 @@
}
info = dma_alloc_coherent(&vscsi->dma_dev->dev, sizeof(*info), &token,
- GFP_KERNEL);
+ GFP_ATOMIC);
if (!info) {
dev_err(&vscsi->dev, "bad dma_alloc_coherent %p\n",
iue->target);
@@ -1443,7 +1444,7 @@
info->mad_version = cpu_to_be32(MAD_VERSION_1);
info->os_type = cpu_to_be32(LINUX);
memset(&info->port_max_txu[0], 0, sizeof(info->port_max_txu));
- info->port_max_txu[0] = cpu_to_be32(128 * PAGE_SIZE);
+ info->port_max_txu[0] = cpu_to_be32(MAX_TXU);
dma_wmb();
rc = h_copy_rdma(sizeof(*info), vscsi->dds.window[LOCAL].liobn,
@@ -1509,7 +1510,7 @@
}
cap = dma_alloc_coherent(&vscsi->dma_dev->dev, olen, &token,
- GFP_KERNEL);
+ GFP_ATOMIC);
if (!cap) {
dev_err(&vscsi->dev, "bad dma_alloc_coherent %p\n",
iue->target);
@@ -3585,7 +3586,7 @@
1, 1);
if (rc) {
pr_err("srp_transfer_data() failed: %d\n", rc);
- return -EAGAIN;
+ return -EIO;
}
/*
* We now tell TCM to add this WRITE CDB directly into the TCM storage
@@ -3815,6 +3816,7 @@
static const struct target_core_fabric_ops ibmvscsis_ops = {
.module = THIS_MODULE,
.name = "ibmvscsis",
+ .max_data_sg_nents = MAX_TXU / PAGE_SIZE,
.get_fabric_name = ibmvscsis_get_fabric_name,
.tpg_get_wwn = ibmvscsis_get_fabric_wwn,
.tpg_get_tag = ibmvscsis_get_tag,
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 7a88295..63bef45 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -3590,12 +3590,14 @@
} else {
buf_ptr1 = (struct lpfc_dmabuf *) elsiocb->context2;
lpfc_els_free_data(phba, buf_ptr1);
+ elsiocb->context2 = NULL;
}
}
if (elsiocb->context3) {
buf_ptr = (struct lpfc_dmabuf *) elsiocb->context3;
lpfc_els_free_bpl(phba, buf_ptr);
+ elsiocb->context3 = NULL;
}
lpfc_sli_release_iocbq(phba, elsiocb);
return 0;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 4faa767..a78a3df 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -5954,18 +5954,25 @@
free_vfi_bmask:
kfree(phba->sli4_hba.vfi_bmask);
+ phba->sli4_hba.vfi_bmask = NULL;
free_xri_ids:
kfree(phba->sli4_hba.xri_ids);
+ phba->sli4_hba.xri_ids = NULL;
free_xri_bmask:
kfree(phba->sli4_hba.xri_bmask);
+ phba->sli4_hba.xri_bmask = NULL;
free_vpi_ids:
kfree(phba->vpi_ids);
+ phba->vpi_ids = NULL;
free_vpi_bmask:
kfree(phba->vpi_bmask);
+ phba->vpi_bmask = NULL;
free_rpi_ids:
kfree(phba->sli4_hba.rpi_ids);
+ phba->sli4_hba.rpi_ids = NULL;
free_rpi_bmask:
kfree(phba->sli4_hba.rpi_bmask);
+ phba->sli4_hba.rpi_bmask = NULL;
err_exit:
return rc;
}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 394fe13..dcb33f4 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -393,6 +393,7 @@
* @eedp_enable: eedp support enable bit
* @eedp_type: 0(type_1), 1(type_2), 2(type_3)
* @eedp_block_length: block size
+ * @ata_command_pending: SATL passthrough outstanding for device
*/
struct MPT3SAS_DEVICE {
struct MPT3SAS_TARGET *sas_target;
@@ -404,6 +405,17 @@
u8 ignore_delay_remove;
/* Iopriority Command Handling */
u8 ncq_prio_enable;
+ /*
+ * Bug workaround for SATL handling: the mpt2/3sas firmware
+ * doesn't return BUSY or TASK_SET_FULL for subsequent
+ * commands while a SATL pass through is in operation as the
+ * spec requires, it simply does nothing with them until the
+ * pass through completes, causing them possibly to timeout if
+ * the passthrough is a long executing command (like format or
+ * secure erase). This variable allows us to do the right
+ * thing while a SATL command is pending.
+ */
+ unsigned long ata_command_pending;
};
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b5c966e..0b5b423 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -51,6 +51,7 @@
#include <linux/workqueue.h>
#include <linux/delay.h>
#include <linux/pci.h>
+#include <linux/pci-aspm.h>
#include <linux/interrupt.h>
#include <linux/aer.h>
#include <linux/raid_class.h>
@@ -3899,9 +3900,18 @@
}
}
-static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd)
+static int _scsih_set_satl_pending(struct scsi_cmnd *scmd, bool pending)
{
- return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16);
+ struct MPT3SAS_DEVICE *priv = scmd->device->hostdata;
+
+ if (scmd->cmnd[0] != ATA_12 && scmd->cmnd[0] != ATA_16)
+ return 0;
+
+ if (pending)
+ return test_and_set_bit(0, &priv->ata_command_pending);
+
+ clear_bit(0, &priv->ata_command_pending);
+ return 0;
}
/**
@@ -3925,9 +3935,7 @@
if (!scmd)
continue;
count++;
- if (ata_12_16_cmd(scmd))
- scsi_internal_device_unblock(scmd->device,
- SDEV_RUNNING);
+ _scsih_set_satl_pending(scmd, false);
mpt3sas_base_free_smid(ioc, smid);
scsi_dma_unmap(scmd);
if (ioc->pci_error_recovery)
@@ -4063,13 +4071,6 @@
if (ioc->logging_level & MPT_DEBUG_SCSI)
scsi_print_command(scmd);
- /*
- * Lock the device for any subsequent command until command is
- * done.
- */
- if (ata_12_16_cmd(scmd))
- scsi_internal_device_block(scmd->device);
-
sas_device_priv_data = scmd->device->hostdata;
if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
scmd->result = DID_NO_CONNECT << 16;
@@ -4083,6 +4084,19 @@
return 0;
}
+ /*
+ * Bug work around for firmware SATL handling. The loop
+ * is based on atomic operations and ensures consistency
+ * since we're lockless at this point
+ */
+ do {
+ if (test_bit(0, &sas_device_priv_data->ata_command_pending)) {
+ scmd->result = SAM_STAT_BUSY;
+ scmd->scsi_done(scmd);
+ return 0;
+ }
+ } while (_scsih_set_satl_pending(scmd, true));
+
sas_target_priv_data = sas_device_priv_data->sas_target;
/* invalid device handle */
@@ -4644,14 +4658,14 @@
struct MPT3SAS_DEVICE *sas_device_priv_data;
u32 response_code = 0;
unsigned long flags;
+ unsigned int sector_sz;
mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
if (scmd == NULL)
return 1;
- if (ata_12_16_cmd(scmd))
- scsi_internal_device_unblock(scmd->device, SDEV_RUNNING);
+ _scsih_set_satl_pending(scmd, false);
mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
@@ -4703,6 +4717,20 @@
}
xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
+
+ /* In case of bogus fw or device, we could end up having
+ * unaligned partial completion. We can force alignment here,
+ * then scsi-ml does not need to handle this misbehavior.
+ */
+ sector_sz = scmd->device->sector_size;
+ if (unlikely(scmd->request->cmd_type == REQ_TYPE_FS && sector_sz &&
+ xfer_cnt % sector_sz)) {
+ sdev_printk(KERN_INFO, scmd->device,
+ "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
+ xfer_cnt, sector_sz);
+ xfer_cnt = round_down(xfer_cnt, sector_sz);
+ }
+
scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
log_info = le32_to_cpu(mpi_reply->IOCLogInfo);
@@ -8734,6 +8762,8 @@
switch (hba_mpi_version) {
case MPI2_VERSION:
+ pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S |
+ PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
/* Use mpt2sas driver host template for SAS 2.0 HBA's */
shost = scsi_host_alloc(&mpt2sas_driver_template,
sizeof(struct MPT3SAS_ADAPTER));
diff --git a/drivers/scsi/qedi/Kconfig b/drivers/scsi/qedi/Kconfig
index 23ca8a2..2133145 100644
--- a/drivers/scsi/qedi/Kconfig
+++ b/drivers/scsi/qedi/Kconfig
@@ -1,6 +1,6 @@
config QEDI
tristate "QLogic QEDI 25/40/100Gb iSCSI Initiator Driver Support"
- depends on PCI && SCSI
+ depends on PCI && SCSI && UIO
depends on QED
select SCSI_ISCSI_ATTRS
select QED_LL2
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 47eb4d5..f201f40 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -243,12 +243,15 @@
struct qla_hw_data *ha = vha->hw;
ssize_t rval = 0;
- if (ha->optrom_state != QLA_SREADING)
- return 0;
-
mutex_lock(&ha->optrom_mutex);
+
+ if (ha->optrom_state != QLA_SREADING)
+ goto out;
+
rval = memory_read_from_buffer(buf, count, &off, ha->optrom_buffer,
ha->optrom_region_size);
+
+out:
mutex_unlock(&ha->optrom_mutex);
return rval;
@@ -263,14 +266,19 @@
struct device, kobj)));
struct qla_hw_data *ha = vha->hw;
- if (ha->optrom_state != QLA_SWRITING)
+ mutex_lock(&ha->optrom_mutex);
+
+ if (ha->optrom_state != QLA_SWRITING) {
+ mutex_unlock(&ha->optrom_mutex);
return -EINVAL;
- if (off > ha->optrom_region_size)
+ }
+ if (off > ha->optrom_region_size) {
+ mutex_unlock(&ha->optrom_mutex);
return -ERANGE;
+ }
if (off + count > ha->optrom_region_size)
count = ha->optrom_region_size - off;
- mutex_lock(&ha->optrom_mutex);
memcpy(&ha->optrom_buffer[off], buf, count);
mutex_unlock(&ha->optrom_mutex);
@@ -753,7 +761,6 @@
struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
struct device, kobj)));
int type;
- int rval = 0;
port_id_t did;
type = simple_strtol(buf, NULL, 10);
@@ -767,7 +774,7 @@
ql_log(ql_log_info, vha, 0x70e4, "%s: %d\n", __func__, type);
- rval = qla24xx_els_dcmd_iocb(vha, ELS_DCMD_LOGO, did);
+ qla24xx_els_dcmd_iocb(vha, ELS_DCMD_LOGO, did);
return count;
}
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index f7df01b..5b1287a 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -1556,7 +1556,8 @@
struct atio {
uint8_t entry_type; /* Entry type. */
uint8_t entry_count; /* Entry count. */
- uint8_t data[58];
+ __le16 attr_n_length;
+ uint8_t data[56];
uint32_t signature;
#define ATIO_PROCESSED 0xDEADDEAD /* Signature */
};
@@ -2732,7 +2733,7 @@
#define QLA_MSIX_FW_MODE(m) (((m) & (BIT_7|BIT_8|BIT_9)) >> 7)
#define QLA_MSIX_FW_MODE_1(m) (QLA_MSIX_FW_MODE(m) == 1)
-#define QLA_MSIX_DEFAULT 0x00
+#define QLA_BASE_VECTORS 2 /* default + RSP */
#define QLA_MSIX_RSP_Q 0x01
#define QLA_ATIO_VECTOR 0x02
#define QLA_MSIX_QPAIR_MULTIQ_RSP_Q 0x03
@@ -2754,7 +2755,6 @@
uint16_t entry;
char name[30];
void *handle;
- struct irq_affinity_notify irq_notify;
int cpuid;
};
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 632d5f3..7b6317c 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -1191,7 +1191,7 @@
/* Wait for soft-reset to complete. */
RD_REG_DWORD(®->ctrl_status);
- for (cnt = 0; cnt < 6000000; cnt++) {
+ for (cnt = 0; cnt < 60; cnt++) {
barrier();
if ((RD_REG_DWORD(®->ctrl_status) &
CSRX_ISP_SOFT_RESET) == 0)
@@ -1234,7 +1234,7 @@
RD_REG_DWORD(®->hccr);
RD_REG_WORD(®->mailbox0);
- for (cnt = 6000000; RD_REG_WORD(®->mailbox0) != 0 &&
+ for (cnt = 60; RD_REG_WORD(®->mailbox0) != 0 &&
rval == QLA_SUCCESS; cnt--) {
barrier();
if (cnt)
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 5093ca9..a94b0b6 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -19,10 +19,6 @@
static void qla2x00_status_cont_entry(struct rsp_que *, sts_cont_entry_t *);
static void qla2x00_error_entry(scsi_qla_host_t *, struct rsp_que *,
sts_entry_t *);
-static void qla_irq_affinity_notify(struct irq_affinity_notify *,
- const cpumask_t *);
-static void qla_irq_affinity_release(struct kref *);
-
/**
* qla2100_intr_handler() - Process interrupts for the ISP2100 and ISP2200.
@@ -2496,6 +2492,10 @@
if (pkt->entry_status & RF_BUSY)
res = DID_BUS_BUSY << 16;
+ if (pkt->entry_type == NOTIFY_ACK_TYPE &&
+ pkt->handle == QLA_TGT_SKIP_HANDLE)
+ return;
+
sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
if (sp) {
sp->done(ha, sp, res);
@@ -2572,14 +2572,6 @@
if (!vha->flags.online)
return;
- if (rsp->msix && rsp->msix->cpuid != smp_processor_id()) {
- /* if kernel does not notify qla of IRQ's CPU change,
- * then set it here.
- */
- rsp->msix->cpuid = smp_processor_id();
- ha->tgt.rspq_vector_cpuid = rsp->msix->cpuid;
- }
-
while (rsp->ring_ptr->signature != RESPONSE_PROCESSED) {
pkt = (struct sts_entry_24xx *)rsp->ring_ptr;
@@ -3018,13 +3010,20 @@
static int
qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
{
-#define MIN_MSIX_COUNT 2
int i, ret;
struct qla_msix_entry *qentry;
scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
+ struct irq_affinity desc = {
+ .pre_vectors = QLA_BASE_VECTORS,
+ };
- ret = pci_alloc_irq_vectors(ha->pdev, MIN_MSIX_COUNT, ha->msix_count,
- PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+ if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha))
+ desc.pre_vectors++;
+
+ ret = pci_alloc_irq_vectors_affinity(ha->pdev, QLA_BASE_VECTORS,
+ ha->msix_count, PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
+ &desc);
+
if (ret < 0) {
ql_log(ql_log_fatal, vha, 0x00c7,
"MSI-X: Failed to enable support, "
@@ -3069,13 +3068,10 @@
qentry->have_irq = 0;
qentry->in_use = 0;
qentry->handle = NULL;
- qentry->irq_notify.notify = qla_irq_affinity_notify;
- qentry->irq_notify.release = qla_irq_affinity_release;
- qentry->cpuid = -1;
}
/* Enable MSI-X vectors for the base queue */
- for (i = 0; i < (QLA_MSIX_RSP_Q + 1); i++) {
+ for (i = 0; i < QLA_BASE_VECTORS; i++) {
qentry = &ha->msix_entries[i];
qentry->handle = rsp;
rsp->msix = qentry;
@@ -3093,18 +3089,6 @@
goto msix_register_fail;
qentry->have_irq = 1;
qentry->in_use = 1;
-
- /* Register for CPU affinity notification. */
- irq_set_affinity_notifier(qentry->vector, &qentry->irq_notify);
-
- /* Schedule work (ie. trigger a notification) to read cpu
- * mask for this specific irq.
- * kref_get is required because
- * irq_affinity_notify() will do
- * kref_put().
- */
- kref_get(&qentry->irq_notify.kref);
- schedule_work(&qentry->irq_notify.work);
}
/*
@@ -3258,7 +3242,7 @@
* from a probe failure context.
*/
if (!ha->rsp_q_map || !ha->rsp_q_map[0])
- return;
+ goto free_irqs;
rsp = ha->rsp_q_map[0];
if (ha->flags.msix_enabled) {
@@ -3278,6 +3262,7 @@
free_irq(pci_irq_vector(ha->pdev, 0), rsp);
}
+free_irqs:
pci_free_irq_vectors(ha->pdev);
}
@@ -3301,49 +3286,3 @@
msix->handle = qpair;
return ret;
}
-
-
-/* irq_set_affinity/irqbalance will trigger notification of cpu mask update */
-static void qla_irq_affinity_notify(struct irq_affinity_notify *notify,
- const cpumask_t *mask)
-{
- struct qla_msix_entry *e =
- container_of(notify, struct qla_msix_entry, irq_notify);
- struct qla_hw_data *ha;
- struct scsi_qla_host *base_vha;
- struct rsp_que *rsp = e->handle;
-
- /* user is recommended to set mask to just 1 cpu */
- e->cpuid = cpumask_first(mask);
-
- ha = rsp->hw;
- base_vha = pci_get_drvdata(ha->pdev);
-
- ql_dbg(ql_dbg_init, base_vha, 0xffff,
- "%s: host %ld : vector %d cpu %d \n", __func__,
- base_vha->host_no, e->vector, e->cpuid);
-
- if (e->have_irq) {
- if ((IS_QLA83XX(ha) || IS_QLA27XX(ha)) &&
- (e->entry == QLA83XX_RSPQ_MSIX_ENTRY_NUMBER)) {
- ha->tgt.rspq_vector_cpuid = e->cpuid;
- ql_dbg(ql_dbg_init, base_vha, 0xffff,
- "%s: host%ld: rspq vector %d cpu %d runtime change\n",
- __func__, base_vha->host_no, e->vector, e->cpuid);
- }
- }
-}
-
-static void qla_irq_affinity_release(struct kref *ref)
-{
- struct irq_affinity_notify *notify =
- container_of(ref, struct irq_affinity_notify, kref);
- struct qla_msix_entry *e =
- container_of(notify, struct qla_msix_entry, irq_notify);
- struct rsp_que *rsp = e->handle;
- struct scsi_qla_host *base_vha = pci_get_drvdata(rsp->hw->pdev);
-
- ql_dbg(ql_dbg_init, base_vha, 0xffff,
- "%s: host%ld: vector %d cpu %d\n", __func__,
- base_vha->host_no, e->vector, e->cpuid);
-}
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 2819ceb..67f64db 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -10,7 +10,7 @@
#include <linux/delay.h>
#include <linux/gfp.h>
-struct rom_cmd {
+static struct rom_cmd {
uint16_t cmd;
} rom_cmds[] = {
{ MBC_LOAD_RAM },
@@ -101,12 +101,12 @@
return QLA_FUNCTION_TIMEOUT;
}
- /* if PCI error, then avoid mbx processing.*/
- if (test_bit(PCI_ERR, &base_vha->dpc_flags)) {
+ /* if PCI error, then avoid mbx processing.*/
+ if (test_bit(PCI_ERR, &base_vha->dpc_flags)) {
ql_log(ql_log_warn, vha, 0x1191,
"PCI error, exiting.\n");
return QLA_FUNCTION_TIMEOUT;
- }
+ }
reg = ha->iobase;
io_lock_on = base_vha->flags.init_done;
@@ -323,20 +323,33 @@
}
} else {
- uint16_t mb0;
- uint32_t ictrl;
+ uint16_t mb[8];
+ uint32_t ictrl, host_status, hccr;
uint16_t w;
if (IS_FWI2_CAPABLE(ha)) {
- mb0 = RD_REG_WORD(®->isp24.mailbox0);
+ mb[0] = RD_REG_WORD(®->isp24.mailbox0);
+ mb[1] = RD_REG_WORD(®->isp24.mailbox1);
+ mb[2] = RD_REG_WORD(®->isp24.mailbox2);
+ mb[3] = RD_REG_WORD(®->isp24.mailbox3);
+ mb[7] = RD_REG_WORD(®->isp24.mailbox7);
ictrl = RD_REG_DWORD(®->isp24.ictrl);
+ host_status = RD_REG_DWORD(®->isp24.host_status);
+ hccr = RD_REG_DWORD(®->isp24.hccr);
+
+ ql_log(ql_log_warn, vha, 0x1119,
+ "MBX Command timeout for cmd %x, iocontrol=%x jiffies=%lx "
+ "mb[0-3]=[0x%x 0x%x 0x%x 0x%x] mb7 0x%x host_status 0x%x hccr 0x%x\n",
+ command, ictrl, jiffies, mb[0], mb[1], mb[2], mb[3],
+ mb[7], host_status, hccr);
+
} else {
- mb0 = RD_MAILBOX_REG(ha, ®->isp, 0);
+ mb[0] = RD_MAILBOX_REG(ha, ®->isp, 0);
ictrl = RD_REG_WORD(®->isp.ictrl);
+ ql_dbg(ql_dbg_mbx + ql_dbg_buffer, vha, 0x1119,
+ "MBX Command timeout for cmd %x, iocontrol=%x jiffies=%lx "
+ "mb[0]=0x%x\n", command, ictrl, jiffies, mb[0]);
}
- ql_dbg(ql_dbg_mbx + ql_dbg_buffer, vha, 0x1119,
- "MBX Command timeout for cmd %x, iocontrol=%x jiffies=%lx "
- "mb[0]=0x%x\n", command, ictrl, jiffies, mb0);
ql_dump_regs(ql_dbg_mbx + ql_dbg_buffer, vha, 0x1019);
/* Capture FW dump only, if PCI device active */
@@ -684,7 +697,6 @@
mbx_cmd_t mc;
mbx_cmd_t *mcp = &mc;
struct qla_hw_data *ha = vha->hw;
- int configured_count;
ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x111a,
"Entered %s.\n", __func__);
@@ -707,7 +719,6 @@
/*EMPTY*/
ql_dbg(ql_dbg_mbx, vha, 0x111b, "Failed=%x.\n", rval);
} else {
- configured_count = mcp->mb[11];
ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x118c,
"Done %s.\n", __func__);
}
diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c
index 54380b4..0a1723c 100644
--- a/drivers/scsi/qla2xxx/qla_nx.c
+++ b/drivers/scsi/qla2xxx/qla_nx.c
@@ -42,6 +42,11 @@
(crb_addr_xform[QLA82XX_HW_PX_MAP_CRB_##name] = \
QLA82XX_HW_CRB_HUB_AGT_ADR_##name << 20)
+const int MD_MIU_TEST_AGT_RDDATA[] = {
+ 0x410000A8, 0x410000AC,
+ 0x410000B8, 0x410000BC
+};
+
static void qla82xx_crb_addr_transform_setup(void)
{
qla82xx_crb_addr_transform(XDMA);
diff --git a/drivers/scsi/qla2xxx/qla_nx.h b/drivers/scsi/qla2xxx/qla_nx.h
index 6201dce..77624ea 100644
--- a/drivers/scsi/qla2xxx/qla_nx.h
+++ b/drivers/scsi/qla2xxx/qla_nx.h
@@ -1176,8 +1176,7 @@
#define MD_MIU_TEST_AGT_ADDR_LO 0x41000094
#define MD_MIU_TEST_AGT_ADDR_HI 0x41000098
-static const int MD_MIU_TEST_AGT_RDDATA[] = { 0x410000A8, 0x410000AC,
- 0x410000B8, 0x410000BC };
+extern const int MD_MIU_TEST_AGT_RDDATA[4];
#define CRB_NIU_XG_PAUSE_CTL_P0 0x1
#define CRB_NIU_XG_PAUSE_CTL_P1 0x8
diff --git a/drivers/scsi/qla2xxx/qla_nx2.c b/drivers/scsi/qla2xxx/qla_nx2.c
index 007192d..dc1ec9b 100644
--- a/drivers/scsi/qla2xxx/qla_nx2.c
+++ b/drivers/scsi/qla2xxx/qla_nx2.c
@@ -15,6 +15,23 @@
#define TIMEOUT_100_MS 100
+static const uint32_t qla8044_reg_tbl[] = {
+ QLA8044_PEG_HALT_STATUS1,
+ QLA8044_PEG_HALT_STATUS2,
+ QLA8044_PEG_ALIVE_COUNTER,
+ QLA8044_CRB_DRV_ACTIVE,
+ QLA8044_CRB_DEV_STATE,
+ QLA8044_CRB_DRV_STATE,
+ QLA8044_CRB_DRV_SCRATCH,
+ QLA8044_CRB_DEV_PART_INFO1,
+ QLA8044_CRB_IDC_VER_MAJOR,
+ QLA8044_FW_VER_MAJOR,
+ QLA8044_FW_VER_MINOR,
+ QLA8044_FW_VER_SUB,
+ QLA8044_CMDPEG_STATE,
+ QLA8044_ASIC_TEMP,
+};
+
/* 8044 Flash Read/Write functions */
uint32_t
qla8044_rd_reg(struct qla_hw_data *ha, ulong addr)
diff --git a/drivers/scsi/qla2xxx/qla_nx2.h b/drivers/scsi/qla2xxx/qla_nx2.h
index 02fe3c4..83c1b7e 100644
--- a/drivers/scsi/qla2xxx/qla_nx2.h
+++ b/drivers/scsi/qla2xxx/qla_nx2.h
@@ -535,23 +535,6 @@
#define CRB_CMDPEG_CHECK_RETRY_COUNT 60
#define CRB_CMDPEG_CHECK_DELAY 500
-static const uint32_t qla8044_reg_tbl[] = {
- QLA8044_PEG_HALT_STATUS1,
- QLA8044_PEG_HALT_STATUS2,
- QLA8044_PEG_ALIVE_COUNTER,
- QLA8044_CRB_DRV_ACTIVE,
- QLA8044_CRB_DEV_STATE,
- QLA8044_CRB_DRV_STATE,
- QLA8044_CRB_DRV_SCRATCH,
- QLA8044_CRB_DEV_PART_INFO1,
- QLA8044_CRB_IDC_VER_MAJOR,
- QLA8044_FW_VER_MAJOR,
- QLA8044_FW_VER_MINOR,
- QLA8044_FW_VER_SUB,
- QLA8044_CMDPEG_STATE,
- QLA8044_ASIC_TEMP,
-};
-
/* MiniDump Structures */
/* Driver_code is for driver to write some info about the entry
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 8521cfe..4066046 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -466,7 +466,7 @@
continue;
rsp = ha->rsp_q_map[cnt];
- clear_bit(cnt, ha->req_qid_map);
+ clear_bit(cnt, ha->rsp_qid_map);
ha->rsp_q_map[cnt] = NULL;
spin_unlock_irqrestore(&ha->hardware_lock, flags);
qla2x00_free_rsp_que(ha, rsp);
@@ -1616,7 +1616,7 @@
/* Don't abort commands in adapter during EEH
* recovery as it's not accessible/responding.
*/
- if (!ha->flags.eeh_busy) {
+ if (GET_CMD_SP(sp) && !ha->flags.eeh_busy) {
/* Get a reference to the sp and drop the lock.
* The reference ensures this sp->done() call
* - and not the call in qla2xxx_eh_abort() -
@@ -3662,7 +3662,7 @@
sizeof(struct ct6_dsd), 0,
SLAB_HWCACHE_ALIGN, NULL);
if (!ctx_cachep)
- goto fail_free_gid_list;
+ goto fail_free_srb_mempool;
}
ha->ctx_mempool = mempool_create_slab_pool(SRB_MIN_REQ,
ctx_cachep);
@@ -3815,7 +3815,7 @@
ha->loop_id_map = kzalloc(BITS_TO_LONGS(LOOPID_MAP_SIZE) * sizeof(long),
GFP_KERNEL);
if (!ha->loop_id_map)
- goto fail_async_pd;
+ goto fail_loop_id_map;
else {
qla2x00_set_reserved_loop_ids(ha);
ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0123,
@@ -3824,6 +3824,8 @@
return 0;
+fail_loop_id_map:
+ dma_pool_free(ha->s_dma_pool, ha->async_pd, ha->async_pd_dma);
fail_async_pd:
dma_pool_free(ha->s_dma_pool, ha->ex_init_cb, ha->ex_init_cb_dma);
fail_ex_init_cb:
@@ -3851,6 +3853,10 @@
dma_pool_free(ha->s_dma_pool, ha->ms_iocb, ha->ms_iocb_dma);
ha->ms_iocb = NULL;
ha->ms_iocb_dma = 0;
+
+ if (ha->sns_cmd)
+ dma_free_coherent(&ha->pdev->dev, sizeof(struct sns_cmd_pkt),
+ ha->sns_cmd, ha->sns_cmd_dma);
fail_dma_pool:
if (IS_QLA82XX(ha) || ql2xenabledif) {
dma_pool_destroy(ha->fcp_cmnd_dma_pool);
@@ -3868,10 +3874,12 @@
kfree(ha->nvram);
ha->nvram = NULL;
fail_free_ctx_mempool:
- mempool_destroy(ha->ctx_mempool);
+ if (ha->ctx_mempool)
+ mempool_destroy(ha->ctx_mempool);
ha->ctx_mempool = NULL;
fail_free_srb_mempool:
- mempool_destroy(ha->srb_mempool);
+ if (ha->srb_mempool)
+ mempool_destroy(ha->srb_mempool);
ha->srb_mempool = NULL;
fail_free_gid_list:
dma_free_coherent(&ha->pdev->dev, qla2x00_gid_list_size(ha),
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index bff9689..e4fda84 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -668,11 +668,9 @@
{
struct qla_hw_data *ha = vha->hw;
struct qla_tgt_sess *sess = NULL;
- uint32_t unpacked_lun, lun = 0;
uint16_t loop_id;
int res = 0;
struct imm_ntfy_from_isp *n = (struct imm_ntfy_from_isp *)iocb;
- struct atio_from_isp *a = (struct atio_from_isp *)iocb;
unsigned long flags;
loop_id = le16_to_cpu(n->u.isp24.nport_handle);
@@ -725,11 +723,7 @@
"loop_id %d)\n", vha->host_no, sess, sess->port_name,
mcmd, loop_id);
- lun = a->u.isp24.fcp_cmnd.lun;
- unpacked_lun = scsilun_to_int((struct scsi_lun *)&lun);
-
- return qlt_issue_task_mgmt(sess, unpacked_lun, mcmd,
- iocb, QLA24XX_MGMT_SEND_NACK);
+ return qlt_issue_task_mgmt(sess, 0, mcmd, iocb, QLA24XX_MGMT_SEND_NACK);
}
/* ha->tgt.sess_lock supposed to be held on entry */
@@ -3067,7 +3061,7 @@
pkt->entry_type = NOTIFY_ACK_TYPE;
pkt->entry_count = 1;
- pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK;
+ pkt->handle = QLA_TGT_SKIP_HANDLE;
nack = (struct nack_to_isp *)pkt;
nack->ox_id = ntfy->ox_id;
@@ -3110,6 +3104,9 @@
#if 0 /* Todo */
if (rc == -ENOMEM)
qlt_alloc_qfull_cmd(vha, imm, 0, 0);
+#else
+ if (rc) {
+ }
#endif
goto done;
}
@@ -6457,12 +6454,29 @@
if (!vha->flags.online)
return;
- while (ha->tgt.atio_ring_ptr->signature != ATIO_PROCESSED) {
+ while ((ha->tgt.atio_ring_ptr->signature != ATIO_PROCESSED) ||
+ fcpcmd_is_corrupted(ha->tgt.atio_ring_ptr)) {
pkt = (struct atio_from_isp *)ha->tgt.atio_ring_ptr;
cnt = pkt->u.raw.entry_count;
- qlt_24xx_atio_pkt_all_vps(vha, (struct atio_from_isp *)pkt,
- ha_locked);
+ if (unlikely(fcpcmd_is_corrupted(ha->tgt.atio_ring_ptr))) {
+ /*
+ * This packet is corrupted. The header + payload
+ * can not be trusted. There is no point in passing
+ * it further up.
+ */
+ ql_log(ql_log_warn, vha, 0xffff,
+ "corrupted fcp frame SID[%3phN] OXID[%04x] EXCG[%x] %64phN\n",
+ pkt->u.isp24.fcp_hdr.s_id,
+ be16_to_cpu(pkt->u.isp24.fcp_hdr.ox_id),
+ le32_to_cpu(pkt->u.isp24.exchange_addr), pkt);
+
+ adjust_corrupted_atio(pkt);
+ qlt_send_term_exchange(vha, NULL, pkt, ha_locked, 0);
+ } else {
+ qlt_24xx_atio_pkt_all_vps(vha,
+ (struct atio_from_isp *)pkt, ha_locked);
+ }
for (i = 0; i < cnt; i++) {
ha->tgt.atio_ring_index++;
@@ -6545,6 +6559,13 @@
/* Disable Full Login after LIP */
nv->host_p &= cpu_to_le32(~BIT_10);
+
+ /*
+ * clear BIT 15 explicitly as we have seen at least
+ * a couple of instances where this was set and this
+ * was causing the firmware to not be initialized.
+ */
+ nv->firmware_options_1 &= cpu_to_le32(~BIT_15);
/* Enable target PRLI control */
nv->firmware_options_2 |= cpu_to_le32(BIT_14);
} else {
@@ -6560,9 +6581,6 @@
return;
}
- /* out-of-order frames reassembly */
- nv->firmware_options_3 |= BIT_6|BIT_9;
-
if (ha->tgt.enable_class_2) {
if (vha->flags.init_done)
fc_host_supported_classes(vha->host) =
@@ -6629,11 +6647,17 @@
/* Disable ini mode, if requested */
if (!qla_ini_mode_enabled(vha))
nv->firmware_options_1 |= cpu_to_le32(BIT_5);
-
/* Disable Full Login after LIP */
nv->firmware_options_1 &= cpu_to_le32(~BIT_13);
/* Enable initial LIP */
nv->firmware_options_1 &= cpu_to_le32(~BIT_9);
+ /*
+ * clear BIT 15 explicitly as we have seen at
+ * least a couple of instances where this was set
+ * and this was causing the firmware to not be
+ * initialized.
+ */
+ nv->firmware_options_1 &= cpu_to_le32(~BIT_15);
if (ql2xtgt_tape_enable)
/* Enable FC tape support */
nv->firmware_options_2 |= cpu_to_le32(BIT_12);
@@ -6658,9 +6682,6 @@
return;
}
- /* out-of-order frames reassembly */
- nv->firmware_options_3 |= BIT_6|BIT_9;
-
if (ha->tgt.enable_class_2) {
if (vha->flags.init_done)
fc_host_supported_classes(vha->host) =
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index f26c5f6..0824a81 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -427,13 +427,33 @@
struct {
uint8_t entry_type; /* Entry type. */
uint8_t entry_count; /* Entry count. */
- uint8_t data[58];
+ __le16 attr_n_length;
+#define FCP_CMD_LENGTH_MASK 0x0fff
+#define FCP_CMD_LENGTH_MIN 0x38
+ uint8_t data[56];
uint32_t signature;
#define ATIO_PROCESSED 0xDEADDEAD /* Signature */
} raw;
} u;
} __packed;
+static inline int fcpcmd_is_corrupted(struct atio *atio)
+{
+ if (atio->entry_type == ATIO_TYPE7 &&
+ (le16_to_cpu(atio->attr_n_length & FCP_CMD_LENGTH_MASK) <
+ FCP_CMD_LENGTH_MIN))
+ return 1;
+ else
+ return 0;
+}
+
+/* adjust corrupted atio so we won't trip over the same entry again. */
+static inline void adjust_corrupted_atio(struct atio_from_isp *atio)
+{
+ atio->u.raw.attr_n_length = cpu_to_le16(FCP_CMD_LENGTH_MIN);
+ atio->u.isp24.fcp_cmnd.add_cdb_len = 0;
+}
+
#define CTIO_TYPE7 0x12 /* Continue target I/O entry (for 24xx) */
/*
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index 36935c9..8a58ef3 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -433,6 +433,18 @@
count++;
}
}
+ } else if (QLA_TGT_MODE_ENABLED() &&
+ ent->t263.queue_type == T263_QUEUE_TYPE_ATIO) {
+ struct qla_hw_data *ha = vha->hw;
+ struct atio *atr = ha->tgt.atio_ring;
+
+ if (atr || !buf) {
+ length = ha->tgt.atio_q_length;
+ qla27xx_insert16(0, buf, len);
+ qla27xx_insert16(length, buf, len);
+ qla27xx_insertbuf(atr, length * sizeof(*atr), buf, len);
+ count++;
+ }
} else {
ql_dbg(ql_dbg_misc, vha, 0xd026,
"%s: unknown queue %x\n", __func__, ent->t263.queue_type);
@@ -676,6 +688,18 @@
count++;
}
}
+ } else if (QLA_TGT_MODE_ENABLED() &&
+ ent->t274.queue_type == T274_QUEUE_TYPE_ATIO_SHAD) {
+ struct qla_hw_data *ha = vha->hw;
+ struct atio *atr = ha->tgt.atio_ring_ptr;
+
+ if (atr || !buf) {
+ qla27xx_insert16(0, buf, len);
+ qla27xx_insert16(1, buf, len);
+ qla27xx_insert32(ha->tgt.atio_q_in ?
+ readl(ha->tgt.atio_q_in) : 0, buf, len);
+ count++;
+ }
} else {
ql_dbg(ql_dbg_misc, vha, 0xd02f,
"%s: unknown queue %x\n", __func__, ent->t274.queue_type);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index dd28c69..3084983 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1800,7 +1800,7 @@
{
return sprintf(page,
"TCM QLOGIC QLA2XXX NPIV capable fabric module %s on %s/%s on "
- UTS_RELEASE"\n", TCM_QLA2XXX_VERSION, utsname()->sysname,
+ UTS_RELEASE"\n", QLA2XXX_VERSION, utsname()->sysname,
utsname()->machine);
}
@@ -1906,7 +1906,7 @@
int ret;
pr_debug("TCM QLOGIC QLA2XXX fabric module %s on %s/%s on "
- UTS_RELEASE"\n", TCM_QLA2XXX_VERSION, utsname()->sysname,
+ UTS_RELEASE"\n", QLA2XXX_VERSION, utsname()->sysname,
utsname()->machine);
ret = target_register_template(&tcm_qla2xxx_ops);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index 37e026a..cf8430b 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -1,7 +1,6 @@
#include <target/target_core_base.h>
#include <linux/btree.h>
-#define TCM_QLA2XXX_VERSION "v0.1"
/* length of ASCII WWPNs including pad */
#define TCM_QLA2XXX_NAMELEN 32
/*
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index c35b6de..78db07f 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1018,7 +1018,7 @@
count = blk_rq_map_sg(req->q, req, sdb->table.sgl);
BUG_ON(count > sdb->table.nents);
sdb->table.nents = count;
- sdb->length = blk_rq_bytes(req);
+ sdb->length = blk_rq_payload_bytes(req);
return BLKPREP_OK;
}
@@ -1040,7 +1040,8 @@
bool is_mq = (rq->mq_ctx != NULL);
int error;
- BUG_ON(!blk_rq_nr_phys_segments(rq));
+ if (WARN_ON_ONCE(!blk_rq_nr_phys_segments(rq)))
+ return -EINVAL;
error = scsi_init_sgtable(rq, &cmd->sdb);
if (error)
@@ -2893,7 +2894,7 @@
* request queue.
*/
if (q->mq_ops) {
- blk_mq_stop_hw_queues(q);
+ blk_mq_quiesce_queue(q);
} else {
spin_lock_irqsave(q->queue_lock, flags);
blk_stop_queue(q);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index b193304..1f5d92a 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -871,11 +871,11 @@
cmd->allowed = SD_MAX_RETRIES;
/*
- * For WRITE_SAME the data transferred in the DATA IN buffer is
+ * For WRITE SAME the data transferred via the DATA OUT buffer is
* different from the amount of data actually written to the target.
*
- * We set up __data_len to the amount of data transferred from the
- * DATA IN buffer so that blk_rq_map_sg set up the proper S/G list
+ * We set up __data_len to the amount of data transferred via the
+ * DATA OUT buffer so that blk_rq_map_sg sets up the proper S/G list
* to transfer a single sector of data first, but then reset it to
* the amount of data to be written right after so that the I/O path
* knows how much to actually write.
@@ -2600,7 +2600,8 @@
if (sdp->broken_fua) {
sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n");
sdkp->DPOFUA = 0;
- } else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) {
+ } else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw &&
+ !sdkp->device->use_16_for_rw) {
sd_first_printk(KERN_NOTICE, sdkp,
"Uses READ/WRITE(6), disabling FUA\n");
sdkp->DPOFUA = 0;
@@ -2783,13 +2784,21 @@
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q);
}
- sdkp->zoned = (buffer[8] >> 4) & 3;
- if (sdkp->zoned == 1)
- q->limits.zoned = BLK_ZONED_HA;
- else if (sdkp->device->type == TYPE_ZBC)
+ if (sdkp->device->type == TYPE_ZBC) {
+ /* Host-managed */
q->limits.zoned = BLK_ZONED_HM;
- else
- q->limits.zoned = BLK_ZONED_NONE;
+ } else {
+ sdkp->zoned = (buffer[8] >> 4) & 3;
+ if (sdkp->zoned == 1)
+ /* Host-aware */
+ q->limits.zoned = BLK_ZONED_HA;
+ else
+ /*
+ * Treat drive-managed devices as
+ * regular block devices.
+ */
+ q->limits.zoned = BLK_ZONED_NONE;
+ }
if (blk_queue_is_zoned(q) && sdkp->first_scan)
sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n",
q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware");
diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 8c9a35c..50adabb 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -587,7 +587,7 @@
ses_enclosure_data_process(edev, to_scsi_device(edev->edev.parent), 0);
- if (scsi_is_sas_rphy(&sdev->sdev_gendev))
+ if (scsi_is_sas_rphy(sdev->sdev_target->dev.parent))
efd.addr = sas_get_address(sdev);
if (efd.addr) {
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index dbe5b4b..121de0a 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1753,6 +1753,10 @@
return res;
iov_iter_truncate(&i, hp->dxfer_len);
+ if (!iov_iter_count(&i)) {
+ kfree(iov);
+ return -EINVAL;
+ }
res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC);
kfree(iov);
diff --git a/drivers/scsi/snic/snic_main.c b/drivers/scsi/snic/snic_main.c
index 396b32d..7cf70aa 100644
--- a/drivers/scsi/snic/snic_main.c
+++ b/drivers/scsi/snic/snic_main.c
@@ -591,6 +591,7 @@
if (!pool) {
SNIC_HOST_ERR(shost, "dflt sgl pool creation failed\n");
+ ret = -ENOMEM;
goto err_free_res;
}
@@ -601,6 +602,7 @@
if (!pool) {
SNIC_HOST_ERR(shost, "max sgl pool creation failed\n");
+ ret = -ENOMEM;
goto err_free_dflt_sgl_pool;
}
@@ -611,6 +613,7 @@
if (!pool) {
SNIC_HOST_ERR(shost, "snic tmreq info pool creation failed.\n");
+ ret = -ENOMEM;
goto err_free_max_sgl_pool;
}
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index ec91bd0..c680d76 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -534,7 +534,9 @@
{
struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc);
+ unsigned long flags;
int req_size;
+ int ret;
BUG_ON(scsi_sg_count(sc) > shost->sg_tablesize);
@@ -562,8 +564,15 @@
req_size = sizeof(cmd->req.cmd);
}
- if (virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)) != 0)
+ ret = virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd));
+ if (ret == -EIO) {
+ cmd->resp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+ spin_lock_irqsave(&req_vq->vq_lock, flags);
+ virtscsi_complete_cmd(vscsi, cmd);
+ spin_unlock_irqrestore(&req_vq->vq_lock, flags);
+ } else if (ret != 0) {
return SCSI_MLQUEUE_HOST_BUSY;
+ }
return 0;
}
diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index 8823cc8..5bb3760 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -459,6 +459,7 @@
if (IS_ERR(task)) {
dev_err(dev, "can't create rproc_boot thread\n");
+ ret = PTR_ERR(task);
goto err_put_rproc;
}
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index ec4aa25..2922a99 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -378,6 +378,7 @@
config SPI_FSL_DSPI
tristate "Freescale DSPI controller"
select REGMAP_MMIO
+ depends on HAS_DMA
depends on SOC_VF610 || SOC_LS1021A || ARCH_LAYERSCAPE || COMPILE_TEST
help
This enables support for the Freescale DSPI controller in master
diff --git a/drivers/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c
index e89da0a..0314c6b9 100644
--- a/drivers/spi/spi-armada-3700.c
+++ b/drivers/spi/spi-armada-3700.c
@@ -800,7 +800,7 @@
struct spi_master *master;
struct a3700_spi *spi;
u32 num_cs = 0;
- int ret = 0;
+ int irq, ret = 0;
master = spi_alloc_master(dev, sizeof(*spi));
if (!master) {
@@ -825,7 +825,7 @@
master->unprepare_message = a3700_spi_unprepare_message;
master->set_cs = a3700_spi_set_cs;
master->flags = SPI_MASTER_HALF_DUPLEX;
- master->mode_bits |= (SPI_RX_DUAL | SPI_RX_DUAL |
+ master->mode_bits |= (SPI_RX_DUAL | SPI_TX_DUAL |
SPI_RX_QUAD | SPI_TX_QUAD);
platform_set_drvdata(pdev, master);
@@ -846,12 +846,13 @@
goto error;
}
- spi->irq = platform_get_irq(pdev, 0);
- if (spi->irq < 0) {
- dev_err(dev, "could not get irq: %d\n", spi->irq);
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(dev, "could not get irq: %d\n", irq);
ret = -ENXIO;
goto error;
}
+ spi->irq = irq;
init_completion(&spi->done);
diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c
index 319225d..6ab4c77 100644
--- a/drivers/spi/spi-axi-spi-engine.c
+++ b/drivers/spi/spi-axi-spi-engine.c
@@ -494,7 +494,8 @@
SPI_ENGINE_VERSION_MAJOR(version),
SPI_ENGINE_VERSION_MINOR(version),
SPI_ENGINE_VERSION_PATCH(version));
- return -ENODEV;
+ ret = -ENODEV;
+ goto err_put_master;
}
spi_engine->clk = devm_clk_get(&pdev->dev, "s_axi_aclk");
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 14f9dea..d7843fd 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -371,7 +371,7 @@
/* default mode, does not need flex_cmd */
flex_mode = 0;
else
- command = SPINOR_OP_READ4_FAST;
+ command = SPINOR_OP_READ_FAST_4B;
break;
case SPI_NBITS_DUAL:
bpc = 0x00000001;
@@ -384,7 +384,7 @@
} else {
command = SPINOR_OP_READ_1_1_2;
if (spans_4byte)
- command = SPINOR_OP_READ4_1_1_2;
+ command = SPINOR_OP_READ_1_1_2_4B;
}
break;
case SPI_NBITS_QUAD:
@@ -399,7 +399,7 @@
} else {
command = SPINOR_OP_READ_1_1_4;
if (spans_4byte)
- command = SPINOR_OP_READ4_1_1_4;
+ command = SPINOR_OP_READ_1_1_4_4B;
}
break;
default:
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index d36c11b..02fb967 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -646,7 +646,7 @@
buf = t->rx_buf;
t->rx_dma = dma_map_single(&spi->dev, buf,
t->len, DMA_FROM_DEVICE);
- if (!t->rx_dma) {
+ if (dma_mapping_error(&spi->dev, !t->rx_dma)) {
ret = -EFAULT;
goto err_rx_map;
}
@@ -660,7 +660,7 @@
buf = (void *)t->tx_buf;
t->tx_dma = dma_map_single(&spi->dev, buf,
t->len, DMA_TO_DEVICE);
- if (!t->tx_dma) {
+ if (dma_mapping_error(&spi->dev, t->tx_dma)) {
ret = -EFAULT;
goto err_tx_map;
}
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index e31971f9..837cb8d 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -274,11 +274,11 @@
static void mid_spi_dma_stop(struct dw_spi *dws)
{
if (test_bit(TX_BUSY, &dws->dma_chan_busy)) {
- dmaengine_terminate_all(dws->txchan);
+ dmaengine_terminate_sync(dws->txchan);
clear_bit(TX_BUSY, &dws->dma_chan_busy);
}
if (test_bit(RX_BUSY, &dws->dma_chan_busy)) {
- dmaengine_terminate_all(dws->rxchan);
+ dmaengine_terminate_sync(dws->rxchan);
clear_bit(RX_BUSY, &dws->dma_chan_busy);
}
}
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index b715a26..054012f 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -107,7 +107,10 @@
static int dw_spi_debugfs_init(struct dw_spi *dws)
{
- dws->debugfs = debugfs_create_dir("dw_spi", NULL);
+ char name[128];
+
+ snprintf(name, 128, "dw_spi-%s", dev_name(&dws->master->dev));
+ dws->debugfs = debugfs_create_dir(name, NULL);
if (!dws->debugfs)
return -ENOMEM;
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index dd7b5b4..d6239fa 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1690,6 +1690,7 @@
pxa2xx_spi_write(drv_data, SSCR1, tmp);
tmp = SSCR0_SCR(2) | SSCR0_Motorola | SSCR0_DataSize(8);
pxa2xx_spi_write(drv_data, SSCR0, tmp);
+ break;
default:
tmp = SSCR1_RxTresh(RX_THRESH_DFLT) |
SSCR1_TxTresh(TX_THRESH_DFLT);
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 0012ad0..1f00eeb 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -973,14 +973,16 @@
};
static const struct of_device_id sh_msiof_match[] = {
- { .compatible = "renesas,sh-msiof", .data = &sh_data },
{ .compatible = "renesas,sh-mobile-msiof", .data = &sh_data },
{ .compatible = "renesas,msiof-r8a7790", .data = &r8a779x_data },
{ .compatible = "renesas,msiof-r8a7791", .data = &r8a779x_data },
{ .compatible = "renesas,msiof-r8a7792", .data = &r8a779x_data },
{ .compatible = "renesas,msiof-r8a7793", .data = &r8a779x_data },
{ .compatible = "renesas,msiof-r8a7794", .data = &r8a779x_data },
+ { .compatible = "renesas,rcar-gen2-msiof", .data = &r8a779x_data },
{ .compatible = "renesas,msiof-r8a7796", .data = &r8a779x_data },
+ { .compatible = "renesas,rcar-gen3-msiof", .data = &r8a779x_data },
+ { .compatible = "renesas,sh-msiof", .data = &sh_data }, /* Deprecated */
{},
};
MODULE_DEVICE_TABLE(of, sh_msiof_match);
diff --git a/drivers/staging/greybus/timesync_platform.c b/drivers/staging/greybus/timesync_platform.c
index 113f3d6..27f75b1 100644
--- a/drivers/staging/greybus/timesync_platform.c
+++ b/drivers/staging/greybus/timesync_platform.c
@@ -45,12 +45,18 @@
int gb_timesync_platform_lock_bus(struct gb_timesync_svc *pdata)
{
+ if (!arche_platform_change_state_cb)
+ return 0;
+
return arche_platform_change_state_cb(ARCHE_PLATFORM_STATE_TIME_SYNC,
pdata);
}
void gb_timesync_platform_unlock_bus(void)
{
+ if (!arche_platform_change_state_cb)
+ return;
+
arche_platform_change_state_cb(ARCHE_PLATFORM_STATE_ACTIVE, NULL);
}
diff --git a/drivers/staging/lustre/lustre/llite/llite_mmap.c b/drivers/staging/lustre/lustre/llite/llite_mmap.c
index ee01f20..9afa6be 100644
--- a/drivers/staging/lustre/lustre/llite/llite_mmap.c
+++ b/drivers/staging/lustre/lustre/llite/llite_mmap.c
@@ -390,15 +390,13 @@
result = VM_FAULT_LOCKED;
break;
case -ENODATA:
+ case -EAGAIN:
case -EFAULT:
result = VM_FAULT_NOPAGE;
break;
case -ENOMEM:
result = VM_FAULT_OOM;
break;
- case -EAGAIN:
- result = VM_FAULT_RETRY;
- break;
default:
result = VM_FAULT_SIGBUS;
break;
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 1ebd13e..26929c4 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -352,7 +352,15 @@
kfree(new);
return -EINVAL;
}
- BUG_ON(orig->se_lun_acl != NULL);
+ if (orig->se_lun_acl != NULL) {
+ pr_warn_ratelimited("Detected existing explicit"
+ " se_lun_acl->se_lun_group reference for %s"
+ " mapped_lun: %llu, failing\n",
+ nacl->initiatorname, mapped_lun);
+ mutex_unlock(&nacl->lun_entry_mutex);
+ kfree(new);
+ return -EINVAL;
+ }
rcu_assign_pointer(new->se_lun, lun);
rcu_assign_pointer(new->se_lun_acl, lun_acl);
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 4879e70..df7b6e9 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -451,6 +451,7 @@
int *post_ret)
{
struct se_device *dev = cmd->se_dev;
+ sense_reason_t ret = TCM_NO_SENSE;
/*
* Only set SCF_COMPARE_AND_WRITE_POST to force a response fall-through
@@ -458,9 +459,12 @@
* sent to the backend driver.
*/
spin_lock_irq(&cmd->t_state_lock);
- if ((cmd->transport_state & CMD_T_SENT) && !cmd->scsi_status) {
+ if (cmd->transport_state & CMD_T_SENT) {
cmd->se_cmd_flags |= SCF_COMPARE_AND_WRITE_POST;
*post_ret = 1;
+
+ if (cmd->scsi_status == SAM_STAT_CHECK_CONDITION)
+ ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
spin_unlock_irq(&cmd->t_state_lock);
@@ -470,7 +474,7 @@
*/
up(&dev->caw_sem);
- return TCM_NO_SENSE;
+ return ret;
}
static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success,
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 7dfefd6..437591b 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -457,8 +457,20 @@
{
struct se_node_acl *nacl = container_of(kref,
struct se_node_acl, acl_kref);
+ struct se_portal_group *se_tpg = nacl->se_tpg;
- complete(&nacl->acl_free_comp);
+ if (!nacl->dynamic_stop) {
+ complete(&nacl->acl_free_comp);
+ return;
+ }
+
+ mutex_lock(&se_tpg->acl_node_mutex);
+ list_del(&nacl->acl_list);
+ mutex_unlock(&se_tpg->acl_node_mutex);
+
+ core_tpg_wait_for_nacl_pr_ref(nacl);
+ core_free_device_list_for_node(nacl, se_tpg);
+ kfree(nacl);
}
void target_put_nacl(struct se_node_acl *nacl)
@@ -499,12 +511,39 @@
void transport_free_session(struct se_session *se_sess)
{
struct se_node_acl *se_nacl = se_sess->se_node_acl;
+
/*
* Drop the se_node_acl->nacl_kref obtained from within
* core_tpg_get_initiator_node_acl().
*/
if (se_nacl) {
+ struct se_portal_group *se_tpg = se_nacl->se_tpg;
+ const struct target_core_fabric_ops *se_tfo = se_tpg->se_tpg_tfo;
+ unsigned long flags;
+
se_sess->se_node_acl = NULL;
+
+ /*
+ * Also determine if we need to drop the extra ->cmd_kref if
+ * it had been previously dynamically generated, and
+ * the endpoint is not caching dynamic ACLs.
+ */
+ mutex_lock(&se_tpg->acl_node_mutex);
+ if (se_nacl->dynamic_node_acl &&
+ !se_tfo->tpg_check_demo_mode_cache(se_tpg)) {
+ spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags);
+ if (list_empty(&se_nacl->acl_sess_list))
+ se_nacl->dynamic_stop = true;
+ spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags);
+
+ if (se_nacl->dynamic_stop)
+ list_del(&se_nacl->acl_list);
+ }
+ mutex_unlock(&se_tpg->acl_node_mutex);
+
+ if (se_nacl->dynamic_stop)
+ target_put_nacl(se_nacl);
+
target_put_nacl(se_nacl);
}
if (se_sess->sess_cmd_map) {
@@ -518,16 +557,12 @@
void transport_deregister_session(struct se_session *se_sess)
{
struct se_portal_group *se_tpg = se_sess->se_tpg;
- const struct target_core_fabric_ops *se_tfo;
- struct se_node_acl *se_nacl;
unsigned long flags;
- bool drop_nacl = false;
if (!se_tpg) {
transport_free_session(se_sess);
return;
}
- se_tfo = se_tpg->se_tpg_tfo;
spin_lock_irqsave(&se_tpg->session_lock, flags);
list_del(&se_sess->sess_list);
@@ -535,33 +570,15 @@
se_sess->fabric_sess_ptr = NULL;
spin_unlock_irqrestore(&se_tpg->session_lock, flags);
- /*
- * Determine if we need to do extra work for this initiator node's
- * struct se_node_acl if it had been previously dynamically generated.
- */
- se_nacl = se_sess->se_node_acl;
-
- mutex_lock(&se_tpg->acl_node_mutex);
- if (se_nacl && se_nacl->dynamic_node_acl) {
- if (!se_tfo->tpg_check_demo_mode_cache(se_tpg)) {
- list_del(&se_nacl->acl_list);
- drop_nacl = true;
- }
- }
- mutex_unlock(&se_tpg->acl_node_mutex);
-
- if (drop_nacl) {
- core_tpg_wait_for_nacl_pr_ref(se_nacl);
- core_free_device_list_for_node(se_nacl, se_tpg);
- se_sess->se_node_acl = NULL;
- kfree(se_nacl);
- }
pr_debug("TARGET_CORE[%s]: Deregistered fabric_sess\n",
se_tpg->se_tpg_tfo->get_fabric_name());
/*
* If last kref is dropping now for an explicit NodeACL, awake sleeping
* ->acl_free_comp caller to wakeup configfs se_node_acl->acl_group
* removal context from within transport_free_session() code.
+ *
+ * For dynamic ACL, target_put_nacl() uses target_complete_nacl()
+ * to release all remaining generate_node_acl=1 created ACL resources.
*/
transport_free_session(se_sess);
@@ -1693,6 +1710,10 @@
case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED:
case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED:
case TCM_COPY_TARGET_DEVICE_NOT_REACHABLE:
+ case TCM_TOO_MANY_TARGET_DESCS:
+ case TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE:
+ case TCM_TOO_MANY_SEGMENT_DESCS:
+ case TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE:
break;
case TCM_OUT_OF_RESOURCES:
sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -2808,6 +2829,26 @@
.key = ILLEGAL_REQUEST,
.asc = 0x26, /* INVALID FIELD IN PARAMETER LIST */
},
+ [TCM_TOO_MANY_TARGET_DESCS] = {
+ .key = ILLEGAL_REQUEST,
+ .asc = 0x26,
+ .ascq = 0x06, /* TOO MANY TARGET DESCRIPTORS */
+ },
+ [TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE] = {
+ .key = ILLEGAL_REQUEST,
+ .asc = 0x26,
+ .ascq = 0x07, /* UNSUPPORTED TARGET DESCRIPTOR TYPE CODE */
+ },
+ [TCM_TOO_MANY_SEGMENT_DESCS] = {
+ .key = ILLEGAL_REQUEST,
+ .asc = 0x26,
+ .ascq = 0x08, /* TOO MANY SEGMENT DESCRIPTORS */
+ },
+ [TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE] = {
+ .key = ILLEGAL_REQUEST,
+ .asc = 0x26,
+ .ascq = 0x09, /* UNSUPPORTED SEGMENT DESCRIPTOR TYPE CODE */
+ },
[TCM_PARAMETER_LIST_LENGTH_ERROR] = {
.key = ILLEGAL_REQUEST,
.asc = 0x1a, /* PARAMETER LIST LENGTH ERROR */
@@ -3086,7 +3127,6 @@
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
goto check_stop;
}
- cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
cmd->se_tfo->queue_tm_rsp(cmd);
@@ -3099,11 +3139,25 @@
struct se_cmd *cmd)
{
unsigned long flags;
+ bool aborted = false;
spin_lock_irqsave(&cmd->t_state_lock, flags);
- cmd->transport_state |= CMD_T_ACTIVE;
+ if (cmd->transport_state & CMD_T_ABORTED) {
+ aborted = true;
+ } else {
+ cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
+ cmd->transport_state |= CMD_T_ACTIVE;
+ }
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+ if (aborted) {
+ pr_warn_ratelimited("handle_tmr caught CMD_T_ABORTED TMR %d"
+ "ref_tag: %llu tag: %llu\n", cmd->se_tmr_req->function,
+ cmd->se_tmr_req->ref_task_tag, cmd->tag);
+ transport_cmd_check_stop_to_fabric(cmd);
+ return 0;
+ }
+
INIT_WORK(&cmd->work, target_tmr_work);
queue_work(cmd->se_dev->tmr_wq, &cmd->work);
return 0;
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 37d5cae..cac5a20 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -53,18 +53,13 @@
return 0;
}
-static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op *xop,
- bool src)
+static int target_xcopy_locate_se_dev_e4(const unsigned char *dev_wwn,
+ struct se_device **found_dev)
{
struct se_device *se_dev;
- unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN], *dev_wwn;
+ unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
int rc;
- if (src)
- dev_wwn = &xop->dst_tid_wwn[0];
- else
- dev_wwn = &xop->src_tid_wwn[0];
-
mutex_lock(&g_device_mutex);
list_for_each_entry(se_dev, &g_device_list, g_dev_node) {
@@ -78,15 +73,8 @@
if (rc != 0)
continue;
- if (src) {
- xop->dst_dev = se_dev;
- pr_debug("XCOPY 0xe4: Setting xop->dst_dev: %p from located"
- " se_dev\n", xop->dst_dev);
- } else {
- xop->src_dev = se_dev;
- pr_debug("XCOPY 0xe4: Setting xop->src_dev: %p from located"
- " se_dev\n", xop->src_dev);
- }
+ *found_dev = se_dev;
+ pr_debug("XCOPY 0xe4: located se_dev: %p\n", se_dev);
rc = target_depend_item(&se_dev->dev_group.cg_item);
if (rc != 0) {
@@ -110,7 +98,7 @@
}
static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op *xop,
- unsigned char *p, bool src)
+ unsigned char *p, unsigned short cscd_index)
{
unsigned char *desc = p;
unsigned short ript;
@@ -155,7 +143,13 @@
return -EINVAL;
}
- if (src) {
+ if (cscd_index != xop->stdi && cscd_index != xop->dtdi) {
+ pr_debug("XCOPY 0xe4: ignoring CSCD entry %d - neither src nor "
+ "dest\n", cscd_index);
+ return 0;
+ }
+
+ if (cscd_index == xop->stdi) {
memcpy(&xop->src_tid_wwn[0], &desc[8], XCOPY_NAA_IEEE_REGEX_LEN);
/*
* Determine if the source designator matches the local device
@@ -167,10 +161,15 @@
pr_debug("XCOPY 0xe4: Set xop->src_dev %p from source"
" received xop\n", xop->src_dev);
}
- } else {
+ }
+
+ if (cscd_index == xop->dtdi) {
memcpy(&xop->dst_tid_wwn[0], &desc[8], XCOPY_NAA_IEEE_REGEX_LEN);
/*
- * Determine if the destination designator matches the local device
+ * Determine if the destination designator matches the local
+ * device. If @cscd_index corresponds to both source (stdi) and
+ * destination (dtdi), or dtdi comes after stdi, then
+ * XCOL_DEST_RECV_OP wins.
*/
if (!memcmp(&xop->local_dev_wwn[0], &xop->dst_tid_wwn[0],
XCOPY_NAA_IEEE_REGEX_LEN)) {
@@ -190,20 +189,23 @@
{
struct se_device *local_dev = se_cmd->se_dev;
unsigned char *desc = p;
- int offset = tdll % XCOPY_TARGET_DESC_LEN, rc, ret = 0;
+ int offset = tdll % XCOPY_TARGET_DESC_LEN, rc;
+ unsigned short cscd_index = 0;
unsigned short start = 0;
- bool src = true;
*sense_ret = TCM_INVALID_PARAMETER_LIST;
if (offset != 0) {
pr_err("XCOPY target descriptor list length is not"
" multiple of %d\n", XCOPY_TARGET_DESC_LEN);
+ *sense_ret = TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE;
return -EINVAL;
}
- if (tdll > 64) {
+ if (tdll > RCR_OP_MAX_TARGET_DESC_COUNT * XCOPY_TARGET_DESC_LEN) {
pr_err("XCOPY target descriptor supports a maximum"
" two src/dest descriptors, tdll: %hu too large..\n", tdll);
+ /* spc4r37 6.4.3.4 CSCD DESCRIPTOR LIST LENGTH field */
+ *sense_ret = TCM_TOO_MANY_TARGET_DESCS;
return -EINVAL;
}
/*
@@ -215,37 +217,43 @@
while (start < tdll) {
/*
- * Check target descriptor identification with 0xE4 type with
- * use VPD 0x83 WWPN matching ..
+ * Check target descriptor identification with 0xE4 type, and
+ * compare the current index with the CSCD descriptor IDs in
+ * the segment descriptor. Use VPD 0x83 WWPN matching ..
*/
switch (desc[0]) {
case 0xe4:
rc = target_xcopy_parse_tiddesc_e4(se_cmd, xop,
- &desc[0], src);
+ &desc[0], cscd_index);
if (rc != 0)
goto out;
- /*
- * Assume target descriptors are in source -> destination order..
- */
- if (src)
- src = false;
- else
- src = true;
start += XCOPY_TARGET_DESC_LEN;
desc += XCOPY_TARGET_DESC_LEN;
- ret++;
+ cscd_index++;
break;
default:
pr_err("XCOPY unsupported descriptor type code:"
" 0x%02x\n", desc[0]);
+ *sense_ret = TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE;
goto out;
}
}
- if (xop->op_origin == XCOL_SOURCE_RECV_OP)
- rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, true);
- else
- rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, false);
+ switch (xop->op_origin) {
+ case XCOL_SOURCE_RECV_OP:
+ rc = target_xcopy_locate_se_dev_e4(xop->dst_tid_wwn,
+ &xop->dst_dev);
+ break;
+ case XCOL_DEST_RECV_OP:
+ rc = target_xcopy_locate_se_dev_e4(xop->src_tid_wwn,
+ &xop->src_dev);
+ break;
+ default:
+ pr_err("XCOPY CSCD descriptor IDs not found in CSCD list - "
+ "stdi: %hu dtdi: %hu\n", xop->stdi, xop->dtdi);
+ rc = -EINVAL;
+ break;
+ }
/*
* If a matching IEEE NAA 0x83 descriptor for the requested device
* is not located on this node, return COPY_ABORTED with ASQ/ASQC
@@ -262,7 +270,7 @@
pr_debug("XCOPY TGT desc: Dest dev: %p NAA IEEE WWN: 0x%16phN\n",
xop->dst_dev, &xop->dst_tid_wwn[0]);
- return ret;
+ return cscd_index;
out:
return -EINVAL;
@@ -284,6 +292,14 @@
xop->stdi = get_unaligned_be16(&desc[4]);
xop->dtdi = get_unaligned_be16(&desc[6]);
+
+ if (xop->stdi > XCOPY_CSCD_DESC_ID_LIST_OFF_MAX ||
+ xop->dtdi > XCOPY_CSCD_DESC_ID_LIST_OFF_MAX) {
+ pr_err("XCOPY segment desc 0x02: unsupported CSCD ID > 0x%x; stdi: %hu dtdi: %hu\n",
+ XCOPY_CSCD_DESC_ID_LIST_OFF_MAX, xop->stdi, xop->dtdi);
+ return -EINVAL;
+ }
+
pr_debug("XCOPY seg desc 0x02: desc_len: %hu stdi: %hu dtdi: %hu, DC: %d\n",
desc_len, xop->stdi, xop->dtdi, dc);
@@ -306,15 +322,25 @@
static int target_xcopy_parse_segment_descriptors(struct se_cmd *se_cmd,
struct xcopy_op *xop, unsigned char *p,
- unsigned int sdll)
+ unsigned int sdll, sense_reason_t *sense_ret)
{
unsigned char *desc = p;
unsigned int start = 0;
int offset = sdll % XCOPY_SEGMENT_DESC_LEN, rc, ret = 0;
+ *sense_ret = TCM_INVALID_PARAMETER_LIST;
+
if (offset != 0) {
pr_err("XCOPY segment descriptor list length is not"
" multiple of %d\n", XCOPY_SEGMENT_DESC_LEN);
+ *sense_ret = TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE;
+ return -EINVAL;
+ }
+ if (sdll > RCR_OP_MAX_SG_DESC_COUNT * XCOPY_SEGMENT_DESC_LEN) {
+ pr_err("XCOPY supports %u segment descriptor(s), sdll: %u too"
+ " large..\n", RCR_OP_MAX_SG_DESC_COUNT, sdll);
+ /* spc4r37 6.4.3.5 SEGMENT DESCRIPTOR LIST LENGTH field */
+ *sense_ret = TCM_TOO_MANY_SEGMENT_DESCS;
return -EINVAL;
}
@@ -335,6 +361,7 @@
default:
pr_err("XCOPY unsupported segment descriptor"
"type: 0x%02x\n", desc[0]);
+ *sense_ret = TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE;
goto out;
}
}
@@ -837,7 +864,7 @@
" CHECK_CONDITION -> sending response\n", rc);
ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
}
- target_complete_cmd(ec_cmd, SAM_STAT_CHECK_CONDITION);
+ target_complete_cmd(ec_cmd, ec_cmd->scsi_status);
}
sense_reason_t target_do_xcopy(struct se_cmd *se_cmd)
@@ -861,6 +888,16 @@
return TCM_UNSUPPORTED_SCSI_OPCODE;
}
+ if (se_cmd->data_length == 0) {
+ target_complete_cmd(se_cmd, SAM_STAT_GOOD);
+ return TCM_NO_SENSE;
+ }
+ if (se_cmd->data_length < XCOPY_HDR_LEN) {
+ pr_err("XCOPY parameter truncation: length %u < hdr_len %u\n",
+ se_cmd->data_length, XCOPY_HDR_LEN);
+ return TCM_PARAMETER_LIST_LENGTH_ERROR;
+ }
+
xop = kzalloc(sizeof(struct xcopy_op), GFP_KERNEL);
if (!xop) {
pr_err("Unable to allocate xcopy_op\n");
@@ -883,6 +920,12 @@
*/
tdll = get_unaligned_be16(&p[2]);
sdll = get_unaligned_be32(&p[8]);
+ if (tdll + sdll > RCR_OP_MAX_DESC_LIST_LEN) {
+ pr_err("XCOPY descriptor list length %u exceeds maximum %u\n",
+ tdll + sdll, RCR_OP_MAX_DESC_LIST_LEN);
+ ret = TCM_PARAMETER_LIST_LENGTH_ERROR;
+ goto out;
+ }
inline_dl = get_unaligned_be32(&p[12]);
if (inline_dl != 0) {
@@ -890,10 +933,32 @@
goto out;
}
+ if (se_cmd->data_length < (XCOPY_HDR_LEN + tdll + sdll + inline_dl)) {
+ pr_err("XCOPY parameter truncation: data length %u too small "
+ "for tdll: %hu sdll: %u inline_dl: %u\n",
+ se_cmd->data_length, tdll, sdll, inline_dl);
+ ret = TCM_PARAMETER_LIST_LENGTH_ERROR;
+ goto out;
+ }
+
pr_debug("Processing XCOPY with list_id: 0x%02x list_id_usage: 0x%02x"
" tdll: %hu sdll: %u inline_dl: %u\n", list_id, list_id_usage,
tdll, sdll, inline_dl);
+ /*
+ * skip over the target descriptors until segment descriptors
+ * have been passed - CSCD ids are needed to determine src and dest.
+ */
+ seg_desc = &p[16] + tdll;
+
+ rc = target_xcopy_parse_segment_descriptors(se_cmd, xop, seg_desc,
+ sdll, &ret);
+ if (rc <= 0)
+ goto out;
+
+ pr_debug("XCOPY: Processed %d segment descriptors, length: %u\n", rc,
+ rc * XCOPY_SEGMENT_DESC_LEN);
+
rc = target_xcopy_parse_target_descriptors(se_cmd, xop, &p[16], tdll, &ret);
if (rc <= 0)
goto out;
@@ -911,18 +976,8 @@
pr_debug("XCOPY: Processed %d target descriptors, length: %u\n", rc,
rc * XCOPY_TARGET_DESC_LEN);
- seg_desc = &p[16];
- seg_desc += (rc * XCOPY_TARGET_DESC_LEN);
-
- rc = target_xcopy_parse_segment_descriptors(se_cmd, xop, seg_desc, sdll);
- if (rc <= 0) {
- xcopy_pt_undepend_remotedev(xop);
- goto out;
- }
transport_kunmap_data_sg(se_cmd);
- pr_debug("XCOPY: Processed %d segment descriptors, length: %u\n", rc,
- rc * XCOPY_SEGMENT_DESC_LEN);
INIT_WORK(&xop->xop_work, target_xcopy_do_work);
queue_work(xcopy_wq, &xop->xop_work);
return TCM_NO_SENSE;
diff --git a/drivers/target/target_core_xcopy.h b/drivers/target/target_core_xcopy.h
index 4d3d4dd..7c0b105 100644
--- a/drivers/target/target_core_xcopy.h
+++ b/drivers/target/target_core_xcopy.h
@@ -1,10 +1,17 @@
#include <target/target_core_base.h>
+#define XCOPY_HDR_LEN 16
#define XCOPY_TARGET_DESC_LEN 32
#define XCOPY_SEGMENT_DESC_LEN 28
#define XCOPY_NAA_IEEE_REGEX_LEN 16
#define XCOPY_MAX_SECTORS 1024
+/*
+ * SPC4r37 6.4.6.1
+ * Table 150 — CSCD descriptor ID values
+ */
+#define XCOPY_CSCD_DESC_ID_LIST_OFF_MAX 0x07FF
+
enum xcopy_origin_list {
XCOL_SOURCE_RECV_OP = 0x01,
XCOL_DEST_RECV_OP = 0x02,
diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c
index b811b0f..4c77965 100644
--- a/drivers/thermal/rockchip_thermal.c
+++ b/drivers/thermal/rockchip_thermal.c
@@ -118,12 +118,12 @@
void (*control)(void __iomem *reg, bool on);
/* Per-sensor methods */
- int (*get_temp)(struct chip_tsadc_table table,
+ int (*get_temp)(const struct chip_tsadc_table *table,
int chn, void __iomem *reg, int *temp);
- void (*set_alarm_temp)(struct chip_tsadc_table table,
- int chn, void __iomem *reg, int temp);
- void (*set_tshut_temp)(struct chip_tsadc_table table,
- int chn, void __iomem *reg, int temp);
+ int (*set_alarm_temp)(const struct chip_tsadc_table *table,
+ int chn, void __iomem *reg, int temp);
+ int (*set_tshut_temp)(const struct chip_tsadc_table *table,
+ int chn, void __iomem *reg, int temp);
void (*set_tshut_mode)(int chn, void __iomem *reg, enum tshut_mode m);
/* Per-table methods */
@@ -317,6 +317,7 @@
{3452, 115000},
{3437, 120000},
{3421, 125000},
+ {0, 125000},
};
static const struct tsadc_table rk3368_code_table[] = {
@@ -397,59 +398,80 @@
{TSADCV3_DATA_MASK, 125000},
};
-static u32 rk_tsadcv2_temp_to_code(struct chip_tsadc_table table,
+static u32 rk_tsadcv2_temp_to_code(const struct chip_tsadc_table *table,
int temp)
{
int high, low, mid;
- u32 error = 0;
+ unsigned long num;
+ unsigned int denom;
+ u32 error = table->data_mask;
low = 0;
- high = table.length - 1;
+ high = (table->length - 1) - 1; /* ignore the last check for table */
mid = (high + low) / 2;
/* Return mask code data when the temp is over table range */
- if (temp < table.id[low].temp || temp > table.id[high].temp) {
- error = table.data_mask;
+ if (temp < table->id[low].temp || temp > table->id[high].temp)
goto exit;
- }
while (low <= high) {
- if (temp == table.id[mid].temp)
- return table.id[mid].code;
- else if (temp < table.id[mid].temp)
+ if (temp == table->id[mid].temp)
+ return table->id[mid].code;
+ else if (temp < table->id[mid].temp)
high = mid - 1;
else
low = mid + 1;
mid = (low + high) / 2;
}
+ /*
+ * The conversion code granularity provided by the table. Let's
+ * assume that the relationship between temperature and
+ * analog value between 2 table entries is linear and interpolate
+ * to produce less granular result.
+ */
+ num = abs(table->id[mid + 1].code - table->id[mid].code);
+ num *= temp - table->id[mid].temp;
+ denom = table->id[mid + 1].temp - table->id[mid].temp;
+
+ switch (table->mode) {
+ case ADC_DECREMENT:
+ return table->id[mid].code - (num / denom);
+ case ADC_INCREMENT:
+ return table->id[mid].code + (num / denom);
+ default:
+ pr_err("%s: unknown table mode: %d\n", __func__, table->mode);
+ return error;
+ }
+
exit:
- pr_err("Invalid the conversion, error=%d\n", error);
+ pr_err("%s: invalid temperature, temp=%d error=%d\n",
+ __func__, temp, error);
return error;
}
-static int rk_tsadcv2_code_to_temp(struct chip_tsadc_table table, u32 code,
- int *temp)
+static int rk_tsadcv2_code_to_temp(const struct chip_tsadc_table *table,
+ u32 code, int *temp)
{
unsigned int low = 1;
- unsigned int high = table.length - 1;
+ unsigned int high = table->length - 1;
unsigned int mid = (low + high) / 2;
unsigned int num;
unsigned long denom;
- WARN_ON(table.length < 2);
+ WARN_ON(table->length < 2);
- switch (table.mode) {
+ switch (table->mode) {
case ADC_DECREMENT:
- code &= table.data_mask;
- if (code < table.id[high].code)
+ code &= table->data_mask;
+ if (code <= table->id[high].code)
return -EAGAIN; /* Incorrect reading */
while (low <= high) {
- if (code >= table.id[mid].code &&
- code < table.id[mid - 1].code)
+ if (code >= table->id[mid].code &&
+ code < table->id[mid - 1].code)
break;
- else if (code < table.id[mid].code)
+ else if (code < table->id[mid].code)
low = mid + 1;
else
high = mid - 1;
@@ -458,15 +480,15 @@
}
break;
case ADC_INCREMENT:
- code &= table.data_mask;
- if (code < table.id[low].code)
+ code &= table->data_mask;
+ if (code < table->id[low].code)
return -EAGAIN; /* Incorrect reading */
while (low <= high) {
- if (code <= table.id[mid].code &&
- code > table.id[mid - 1].code)
+ if (code <= table->id[mid].code &&
+ code > table->id[mid - 1].code)
break;
- else if (code > table.id[mid].code)
+ else if (code > table->id[mid].code)
low = mid + 1;
else
high = mid - 1;
@@ -475,7 +497,8 @@
}
break;
default:
- pr_err("Invalid the conversion table\n");
+ pr_err("%s: unknown table mode: %d\n", __func__, table->mode);
+ return -EINVAL;
}
/*
@@ -484,10 +507,10 @@
* temperature between 2 table entries is linear and interpolate
* to produce less granular result.
*/
- num = table.id[mid].temp - table.id[mid - 1].temp;
- num *= abs(table.id[mid - 1].code - code);
- denom = abs(table.id[mid - 1].code - table.id[mid].code);
- *temp = table.id[mid - 1].temp + (num / denom);
+ num = table->id[mid].temp - table->id[mid - 1].temp;
+ num *= abs(table->id[mid - 1].code - code);
+ denom = abs(table->id[mid - 1].code - table->id[mid].code);
+ *temp = table->id[mid - 1].temp + (num / denom);
return 0;
}
@@ -638,7 +661,7 @@
writel_relaxed(val, regs + TSADCV2_AUTO_CON);
}
-static int rk_tsadcv2_get_temp(struct chip_tsadc_table table,
+static int rk_tsadcv2_get_temp(const struct chip_tsadc_table *table,
int chn, void __iomem *regs, int *temp)
{
u32 val;
@@ -648,39 +671,57 @@
return rk_tsadcv2_code_to_temp(table, val, temp);
}
-static void rk_tsadcv2_alarm_temp(struct chip_tsadc_table table,
- int chn, void __iomem *regs, int temp)
+static int rk_tsadcv2_alarm_temp(const struct chip_tsadc_table *table,
+ int chn, void __iomem *regs, int temp)
{
- u32 alarm_value, int_en;
+ u32 alarm_value;
+ u32 int_en, int_clr;
+
+ /*
+ * In some cases, some sensors didn't need the trip points, the
+ * set_trips will pass {-INT_MAX, INT_MAX} to trigger tsadc alarm
+ * in the end, ignore this case and disable the high temperature
+ * interrupt.
+ */
+ if (temp == INT_MAX) {
+ int_clr = readl_relaxed(regs + TSADCV2_INT_EN);
+ int_clr &= ~TSADCV2_INT_SRC_EN(chn);
+ writel_relaxed(int_clr, regs + TSADCV2_INT_EN);
+ return 0;
+ }
/* Make sure the value is valid */
alarm_value = rk_tsadcv2_temp_to_code(table, temp);
- if (alarm_value == table.data_mask)
- return;
+ if (alarm_value == table->data_mask)
+ return -ERANGE;
- writel_relaxed(alarm_value & table.data_mask,
+ writel_relaxed(alarm_value & table->data_mask,
regs + TSADCV2_COMP_INT(chn));
int_en = readl_relaxed(regs + TSADCV2_INT_EN);
int_en |= TSADCV2_INT_SRC_EN(chn);
writel_relaxed(int_en, regs + TSADCV2_INT_EN);
+
+ return 0;
}
-static void rk_tsadcv2_tshut_temp(struct chip_tsadc_table table,
- int chn, void __iomem *regs, int temp)
+static int rk_tsadcv2_tshut_temp(const struct chip_tsadc_table *table,
+ int chn, void __iomem *regs, int temp)
{
u32 tshut_value, val;
/* Make sure the value is valid */
tshut_value = rk_tsadcv2_temp_to_code(table, temp);
- if (tshut_value == table.data_mask)
- return;
+ if (tshut_value == table->data_mask)
+ return -ERANGE;
writel_relaxed(tshut_value, regs + TSADCV2_COMP_SHUT(chn));
/* TSHUT will be valid */
val = readl_relaxed(regs + TSADCV2_AUTO_CON);
writel_relaxed(val | TSADCV2_AUTO_SRC_EN(chn), regs + TSADCV2_AUTO_CON);
+
+ return 0;
}
static void rk_tsadcv2_tshut_mode(int chn, void __iomem *regs,
@@ -883,10 +924,8 @@
dev_dbg(&thermal->pdev->dev, "%s: sensor %d: low: %d, high %d\n",
__func__, sensor->id, low, high);
- tsadc->set_alarm_temp(tsadc->table,
- sensor->id, thermal->regs, high);
-
- return 0;
+ return tsadc->set_alarm_temp(&tsadc->table,
+ sensor->id, thermal->regs, high);
}
static int rockchip_thermal_get_temp(void *_sensor, int *out_temp)
@@ -896,7 +935,7 @@
const struct rockchip_tsadc_chip *tsadc = sensor->thermal->chip;
int retval;
- retval = tsadc->get_temp(tsadc->table,
+ retval = tsadc->get_temp(&tsadc->table,
sensor->id, thermal->regs, out_temp);
dev_dbg(&thermal->pdev->dev, "sensor %d - temp: %d, retval: %d\n",
sensor->id, *out_temp, retval);
@@ -982,8 +1021,12 @@
int error;
tsadc->set_tshut_mode(id, thermal->regs, thermal->tshut_mode);
- tsadc->set_tshut_temp(tsadc->table, id, thermal->regs,
+
+ error = tsadc->set_tshut_temp(&tsadc->table, id, thermal->regs,
thermal->tshut_temp);
+ if (error)
+ dev_err(&pdev->dev, "%s: invalid tshut=%d, error=%d\n",
+ __func__, thermal->tshut_temp, error);
sensor->thermal = thermal;
sensor->id = id;
@@ -1196,9 +1239,13 @@
thermal->chip->set_tshut_mode(id, thermal->regs,
thermal->tshut_mode);
- thermal->chip->set_tshut_temp(thermal->chip->table,
+
+ error = thermal->chip->set_tshut_temp(&thermal->chip->table,
id, thermal->regs,
thermal->tshut_temp);
+ if (error)
+ dev_err(&pdev->dev, "%s: invalid tshut=%d, error=%d\n",
+ __func__, thermal->tshut_temp, error);
}
thermal->chip->control(thermal->regs, true);
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 641faab..6555913 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -799,6 +799,11 @@
if (!strncmp(dev_name(dev), "thermal_zone",
sizeof("thermal_zone") - 1)) {
tz = to_thermal_zone(dev);
+ kfree(tz->trip_type_attrs);
+ kfree(tz->trip_temp_attrs);
+ kfree(tz->trip_hyst_attrs);
+ kfree(tz->trips_attribute_group.attrs);
+ kfree(tz->device.groups);
kfree(tz);
} else if (!strncmp(dev_name(dev), "cooling_device",
sizeof("cooling_device") - 1)) {
@@ -1305,10 +1310,6 @@
thermal_zone_device_set_polling(tz, 0);
- kfree(tz->trip_type_attrs);
- kfree(tz->trip_temp_attrs);
- kfree(tz->trip_hyst_attrs);
- kfree(tz->trips_attribute_group.attrs);
thermal_set_governor(tz, NULL);
thermal_remove_hwmon_sysfs(tz);
@@ -1316,7 +1317,6 @@
idr_destroy(&tz->idr);
mutex_destroy(&tz->lock);
device_unregister(&tz->device);
- kfree(tz->device.groups);
}
EXPORT_SYMBOL_GPL(thermal_zone_device_unregister);
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 61569a7..76e03a7 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -675,7 +675,7 @@
.device = uart_console_device,
.setup = univ8250_console_setup,
.match = univ8250_console_match,
- .flags = CON_PRINTBUFFER | CON_ANYTIME | CON_CONSDEV,
+ .flags = CON_PRINTBUFFER | CON_ANYTIME,
.index = -1,
.data = &serial8250_reg,
};
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index aa0166b..116436b 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -5642,17 +5642,15 @@
static void serial8250_io_resume(struct pci_dev *dev)
{
struct serial_private *priv = pci_get_drvdata(dev);
- const struct pciserial_board *board;
+ struct serial_private *new;
if (!priv)
return;
- board = priv->board;
- kfree(priv);
- priv = pciserial_init_ports(dev, board);
-
- if (!IS_ERR(priv)) {
- pci_set_drvdata(dev, priv);
+ new = pciserial_init_ports(dev, priv->board);
+ if (!IS_ERR(new)) {
+ pci_set_drvdata(dev, new);
+ kfree(priv);
}
}
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index fe4399b..c13fec4 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -1413,7 +1413,7 @@
* Enable previously disabled RX interrupts.
*/
if (!(p->port.rs485.flags & SER_RS485_RX_DURING_TX)) {
- serial8250_clear_fifos(p);
+ serial8250_clear_and_reinit_fifos(p);
p->ier |= UART_IER_RLSI | UART_IER_RDI;
serial_port_out(&p->port, UART_IER, p->ier);
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 168b10c..fabbe76 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -481,6 +481,14 @@
/* disable PDC transmit */
atmel_uart_writel(port, ATMEL_PDC_PTCR, ATMEL_PDC_TXTDIS);
}
+
+ /*
+ * Disable the transmitter.
+ * This is mandatory when DMA is used, otherwise the DMA buffer
+ * is fully transmitted.
+ */
+ atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXDIS);
+
/* Disable interrupts */
atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask);
@@ -513,6 +521,9 @@
/* Enable interrupts */
atmel_uart_writel(port, ATMEL_US_IER, atmel_port->tx_done_mask);
+
+ /* re-enable the transmitter */
+ atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXEN);
}
/*
@@ -798,6 +809,11 @@
*/
if (!uart_circ_empty(xmit))
atmel_tasklet_schedule(atmel_port, &atmel_port->tasklet_tx);
+ else if ((port->rs485.flags & SER_RS485_ENABLED) &&
+ !(port->rs485.flags & SER_RS485_RX_DURING_TX)) {
+ /* DMA done, stop TX, start RX for RS485 */
+ atmel_start_rx(port);
+ }
spin_unlock_irqrestore(&port->lock, flags);
}
@@ -900,12 +916,6 @@
desc->callback = atmel_complete_tx_dma;
desc->callback_param = atmel_port;
atmel_port->cookie_tx = dmaengine_submit(desc);
-
- } else {
- if (port->rs485.flags & SER_RS485_ENABLED) {
- /* DMA done, stop TX, start RX for RS485 */
- atmel_start_rx(port);
- }
}
if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 52bbd27..701c085 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -946,8 +946,8 @@
{
.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
INPUT_DEVICE_ID_MATCH_KEYBIT,
- .evbit = { BIT_MASK(EV_KEY) },
- .keybit = { BIT_MASK(KEY_LEFTALT) },
+ .evbit = { [BIT_WORD(EV_KEY)] = BIT_MASK(EV_KEY) },
+ .keybit = { [BIT_WORD(KEY_LEFTALT)] = BIT_MASK(KEY_LEFTALT) },
},
{ },
};
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index d2e50a2..24f9f98 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -37,6 +37,10 @@
/* CBM - Flash disk */
{ USB_DEVICE(0x0204, 0x6025), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* WORLDE easy key (easykey.25) MIDI controller */
+ { USB_DEVICE(0x0218, 0x0401), .driver_info =
+ USB_QUIRK_CONFIG_INTF_STRINGS },
+
/* HP 5300/5370C scanner */
{ USB_DEVICE(0x03f0, 0x0701), .driver_info =
USB_QUIRK_STRING_FETCH_255 },
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index 9548d3e..302b8f5 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -513,8 +513,8 @@
/* Gadget parameters */
bool g_dma;
bool g_dma_desc;
- u16 g_rx_fifo_size;
- u16 g_np_tx_fifo_size;
+ u32 g_rx_fifo_size;
+ u32 g_np_tx_fifo_size;
u32 g_tx_fifo_size[MAX_EPS_CHANNELS];
};
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index c55db4a..77c5fcf 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -3169,7 +3169,7 @@
/* keep other bits untouched (so e.g. forced modes are not lost) */
usbcfg = dwc2_readl(hsotg->regs + GUSBCFG);
usbcfg &= ~(GUSBCFG_TOUTCAL_MASK | GUSBCFG_PHYIF16 | GUSBCFG_SRPCAP |
- GUSBCFG_HNPCAP);
+ GUSBCFG_HNPCAP | GUSBCFG_USBTRDTIM_MASK);
if (hsotg->params.phy_type == DWC2_PHY_TYPE_PARAM_FS &&
(hsotg->params.speed == DWC2_SPEED_PARAM_FULL ||
@@ -3749,8 +3749,8 @@
__func__, epctrl, epctrl_reg);
/* Allocate DMA descriptor chain for non-ctrl endpoints */
- if (using_desc_dma(hsotg)) {
- hs_ep->desc_list = dma_alloc_coherent(hsotg->dev,
+ if (using_desc_dma(hsotg) && !hs_ep->desc_list) {
+ hs_ep->desc_list = dmam_alloc_coherent(hsotg->dev,
MAX_DMA_DESC_NUM_GENERIC *
sizeof(struct dwc2_dma_desc),
&hs_ep->desc_list_dma, GFP_ATOMIC);
@@ -3872,7 +3872,7 @@
error2:
if (ret && using_desc_dma(hsotg) && hs_ep->desc_list) {
- dma_free_coherent(hsotg->dev, MAX_DMA_DESC_NUM_GENERIC *
+ dmam_free_coherent(hsotg->dev, MAX_DMA_DESC_NUM_GENERIC *
sizeof(struct dwc2_dma_desc),
hs_ep->desc_list, hs_ep->desc_list_dma);
hs_ep->desc_list = NULL;
@@ -3902,14 +3902,6 @@
return -EINVAL;
}
- /* Remove DMA memory allocated for non-control Endpoints */
- if (using_desc_dma(hsotg)) {
- dma_free_coherent(hsotg->dev, MAX_DMA_DESC_NUM_GENERIC *
- sizeof(struct dwc2_dma_desc),
- hs_ep->desc_list, hs_ep->desc_list_dma);
- hs_ep->desc_list = NULL;
- }
-
epctrl_reg = dir_in ? DIEPCTL(index) : DOEPCTL(index);
spin_lock_irqsave(&hsotg->lock, flags);
@@ -4131,7 +4123,7 @@
/* keep other bits untouched (so e.g. forced modes are not lost) */
usbcfg = dwc2_readl(hsotg->regs + GUSBCFG);
usbcfg &= ~(GUSBCFG_TOUTCAL_MASK | GUSBCFG_PHYIF16 | GUSBCFG_SRPCAP |
- GUSBCFG_HNPCAP);
+ GUSBCFG_HNPCAP | GUSBCFG_USBTRDTIM_MASK);
/* set the PLL on, remove the HNP/SRP and set the PHY */
trdtim = (hsotg->phyif == GUSBCFG_PHYIF8) ? 9 : 5;
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index 911c3b3..46d0ad5 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -4367,6 +4367,9 @@
if (!HCD_HW_ACCESSIBLE(hcd))
goto unlock;
+ if (hsotg->op_state == OTG_STATE_B_PERIPHERAL)
+ goto unlock;
+
if (!hsotg->params.hibernation)
goto skip_power_saving;
@@ -4489,8 +4492,8 @@
{
#ifdef VERBOSE_DEBUG
struct dwc2_hsotg *hsotg = dwc2_hcd_to_hsotg(hcd);
- char *pipetype;
- char *speed;
+ char *pipetype = NULL;
+ char *speed = NULL;
dev_vdbg(hsotg->dev, "%s, urb %p\n", fn_name, urb);
dev_vdbg(hsotg->dev, " Device address: %d\n",
diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c
index 11fe68a..bcd1e19 100644
--- a/drivers/usb/dwc2/params.c
+++ b/drivers/usb/dwc2/params.c
@@ -385,16 +385,16 @@
}
/**
- * dwc2_set_param_u16() - Set a u16 parameter
+ * dwc2_set_param_u32() - Set a u32 parameter
*
* See dwc2_set_param().
*/
-static void dwc2_set_param_u16(struct dwc2_hsotg *hsotg, u16 *param,
+static void dwc2_set_param_u32(struct dwc2_hsotg *hsotg, u32 *param,
bool lookup, char *property, u16 legacy,
u16 def, u16 min, u16 max)
{
dwc2_set_param(hsotg, param, lookup, property,
- legacy, def, min, max, 2);
+ legacy, def, min, max, 4);
}
/**
@@ -1178,12 +1178,12 @@
* auto-detect if the hardware does not support the
* default.
*/
- dwc2_set_param_u16(hsotg, &p->g_rx_fifo_size,
+ dwc2_set_param_u32(hsotg, &p->g_rx_fifo_size,
true, "g-rx-fifo-size", 2048,
hw->rx_fifo_size,
16, hw->rx_fifo_size);
- dwc2_set_param_u16(hsotg, &p->g_np_tx_fifo_size,
+ dwc2_set_param_u32(hsotg, &p->g_np_tx_fifo_size,
true, "g-np-tx-fifo-size", 1024,
hw->dev_nperio_tx_fifo_size,
16, hw->dev_nperio_tx_fifo_size);
diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
index e27899b..e956306 100644
--- a/drivers/usb/dwc3/dwc3-exynos.c
+++ b/drivers/usb/dwc3/dwc3-exynos.c
@@ -138,7 +138,8 @@
exynos->axius_clk = devm_clk_get(dev, "usbdrd30_axius_clk");
if (IS_ERR(exynos->axius_clk)) {
dev_err(dev, "no AXI UpScaler clk specified\n");
- return -ENODEV;
+ ret = -ENODEV;
+ goto axius_clk_err;
}
clk_prepare_enable(exynos->axius_clk);
} else {
@@ -196,6 +197,7 @@
regulator_disable(exynos->vdd33);
err2:
clk_disable_unprepare(exynos->axius_clk);
+axius_clk_err:
clk_disable_unprepare(exynos->susp_clk);
clk_disable_unprepare(exynos->clk);
return ret;
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 002822d..49d685a 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2147,7 +2147,7 @@
cdev->os_desc_req->buf = kmalloc(4096, GFP_KERNEL);
if (!cdev->os_desc_req->buf) {
ret = -ENOMEM;
- kfree(cdev->os_desc_req);
+ usb_ep_free_request(ep0, cdev->os_desc_req);
goto end;
}
cdev->os_desc_req->context = cdev;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 365443c..e6a1745 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1806,7 +1806,7 @@
unsigned long flags;
spin_lock_irqsave(&func->ffs->eps_lock, flags);
- do {
+ while (count--) {
/* pending requests get nuked */
if (likely(ep->ep))
usb_ep_disable(ep->ep);
@@ -1817,7 +1817,7 @@
__ffs_epfile_read_buffer_free(epfile);
++epfile;
}
- } while (--count);
+ }
spin_unlock_irqrestore(&func->ffs->eps_lock, flags);
}
@@ -1831,7 +1831,7 @@
int ret = 0;
spin_lock_irqsave(&func->ffs->eps_lock, flags);
- do {
+ while(count--) {
struct usb_endpoint_descriptor *ds;
int desc_idx;
@@ -1867,7 +1867,7 @@
++ep;
++epfile;
- } while (--count);
+ }
spin_unlock_irqrestore(&func->ffs->eps_lock, flags);
return ret;
@@ -2269,6 +2269,8 @@
if (len < sizeof(*d) || h->interface >= ffs->interfaces_count)
return -EINVAL;
length = le32_to_cpu(d->dwSize);
+ if (len < length)
+ return -EINVAL;
type = le32_to_cpu(d->dwPropertyDataType);
if (type < USB_EXT_PROP_UNICODE ||
type > USB_EXT_PROP_UNICODE_MULTI) {
@@ -2277,6 +2279,11 @@
return -EINVAL;
}
pnl = le16_to_cpu(d->wPropertyNameLength);
+ if (length < 14 + pnl) {
+ pr_vdebug("invalid os descriptor length: %d pnl:%d (descriptor %d)\n",
+ length, pnl, type);
+ return -EINVAL;
+ }
pdl = le32_to_cpu(*(u32 *)((u8 *)data + 10 + pnl));
if (length != 14 + pnl + pdl) {
pr_vdebug("invalid os descriptor length: %d pnl:%d pdl:%d (descriptor %d)\n",
@@ -2363,6 +2370,9 @@
}
}
if (flags & (1 << i)) {
+ if (len < 4) {
+ goto error;
+ }
os_descs_count = get_unaligned_le32(data);
data += 4;
len -= 4;
@@ -2435,7 +2445,8 @@
ENTER();
- if (unlikely(get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC ||
+ if (unlikely(len < 16 ||
+ get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC ||
get_unaligned_le32(data + 4) != len))
goto error;
str_count = get_unaligned_le32(data + 8);
@@ -3448,12 +3459,12 @@
/* cleanup after autoconfig */
spin_lock_irqsave(&func->ffs->eps_lock, flags);
- do {
+ while (count--) {
if (ep->ep && ep->req)
usb_ep_free_request(ep->ep, ep->req);
ep->req = NULL;
++ep;
- } while (--count);
+ }
spin_unlock_irqrestore(&func->ffs->eps_lock, flags);
kfree(func->eps);
func->eps = NULL;
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index f3212db..12c7687 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -1978,7 +1978,8 @@
dev_err(&pdev->dev, "of_probe: name error(%d)\n", ret);
goto err;
}
- ep->ep.name = kasprintf(GFP_KERNEL, "ep%d", ep->index);
+ sprintf(ep->name, "ep%d", ep->index);
+ ep->ep.name = ep->name;
ep->ep_regs = udc->regs + USBA_EPT_BASE(i);
ep->dma_regs = udc->regs + USBA_DMA_BASE(i);
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.h b/drivers/usb/gadget/udc/atmel_usba_udc.h
index 3e1c9d5..b03b2eb 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.h
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.h
@@ -280,6 +280,7 @@
void __iomem *ep_regs;
void __iomem *dma_regs;
void __iomem *fifo;
+ char name[8];
struct usb_ep ep;
struct usba_udc *udc;
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index ddfab30..e5834dd 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -165,7 +165,7 @@
return -ENODEV;
/* Try to set 64-bit DMA first */
- if (WARN_ON(!pdev->dev.dma_mask))
+ if (!pdev->dev.dma_mask)
/* Platform did not initialize dma_mask */
ret = dma_coerce_mask_and_coherent(&pdev->dev,
DMA_BIT_MASK(64));
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 25f522b..e32029a 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -913,17 +913,6 @@
spin_lock_irqsave(&xhci->lock, flags);
ep->stop_cmds_pending--;
- if (xhci->xhc_state & XHCI_STATE_REMOVING) {
- spin_unlock_irqrestore(&xhci->lock, flags);
- return;
- }
- if (xhci->xhc_state & XHCI_STATE_DYING) {
- xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
- "Stop EP timer ran, but another timer marked "
- "xHCI as DYING, exiting.");
- spin_unlock_irqrestore(&xhci->lock, flags);
- return;
- }
if (!(ep->stop_cmds_pending == 0 && (ep->ep_state & EP_HALT_PENDING))) {
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Stop EP timer ran, but no command pending, "
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 0c8deb9..9a0ec11 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1534,19 +1534,6 @@
xhci_urb_free_priv(urb_priv);
return ret;
}
- if ((xhci->xhc_state & XHCI_STATE_DYING) ||
- (xhci->xhc_state & XHCI_STATE_HALTED)) {
- xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
- "Ep 0x%x: URB %p to be canceled on "
- "non-responsive xHCI host.",
- urb->ep->desc.bEndpointAddress, urb);
- /* Let the stop endpoint command watchdog timer (which set this
- * state) finish cleaning up the endpoint TD lists. We must
- * have caught it in the middle of dropping a lock and giving
- * back an URB.
- */
- goto done;
- }
ep_index = xhci_get_endpoint_index(&urb->ep->desc);
ep = &xhci->devs[urb->dev->slot_id]->eps[ep_index];
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index fca288bb..772f158 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -594,11 +594,11 @@
| MUSB_PORT_STAT_RESUME;
musb->rh_timer = jiffies
+ msecs_to_jiffies(USB_RESUME_TIMEOUT);
- musb->need_finish_resume = 1;
-
musb->xceiv->otg->state = OTG_STATE_A_HOST;
musb->is_active = 1;
musb_host_resume_root_hub(musb);
+ schedule_delayed_work(&musb->finish_resume_work,
+ msecs_to_jiffies(USB_RESUME_TIMEOUT));
break;
case OTG_STATE_B_WAIT_ACON:
musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
@@ -1925,6 +1925,14 @@
static void musb_irq_work(struct work_struct *data)
{
struct musb *musb = container_of(data, struct musb, irq_work.work);
+ int error;
+
+ error = pm_runtime_get_sync(musb->controller);
+ if (error < 0) {
+ dev_err(musb->controller, "Could not enable: %i\n", error);
+
+ return;
+ }
musb_pm_runtime_check_session(musb);
@@ -1932,6 +1940,9 @@
musb->xceiv_old_state = musb->xceiv->otg->state;
sysfs_notify(&musb->controller->kobj, NULL, "mode");
}
+
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
}
static void musb_recover_from_babble(struct musb *musb)
@@ -2710,11 +2721,6 @@
mask = MUSB_DEVCTL_BDEVICE | MUSB_DEVCTL_FSDEV | MUSB_DEVCTL_LSDEV;
if ((devctl & mask) != (musb->context.devctl & mask))
musb->port1_status = 0;
- if (musb->need_finish_resume) {
- musb->need_finish_resume = 0;
- schedule_delayed_work(&musb->finish_resume_work,
- msecs_to_jiffies(USB_RESUME_TIMEOUT));
- }
/*
* The USB HUB code expects the device to be in RPM_ACTIVE once it came
@@ -2766,12 +2772,6 @@
musb_restore_context(musb);
- if (musb->need_finish_resume) {
- musb->need_finish_resume = 0;
- schedule_delayed_work(&musb->finish_resume_work,
- msecs_to_jiffies(USB_RESUME_TIMEOUT));
- }
-
spin_lock_irqsave(&musb->lock, flags);
error = musb_run_resume_work(musb);
if (error)
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index ade902e..ce5a18c 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -410,7 +410,6 @@
/* is_suspended means USB B_PERIPHERAL suspend */
unsigned is_suspended:1;
- unsigned need_finish_resume :1;
/* may_wakeup means remote wakeup is enabled */
unsigned may_wakeup:1;
diff --git a/drivers/usb/musb/musb_debugfs.c b/drivers/usb/musb/musb_debugfs.c
index 4fef50e..dd70c88 100644
--- a/drivers/usb/musb/musb_debugfs.c
+++ b/drivers/usb/musb/musb_debugfs.c
@@ -114,6 +114,7 @@
unsigned i;
seq_printf(s, "MUSB (M)HDRC Register Dump\n");
+ pm_runtime_get_sync(musb->controller);
for (i = 0; i < ARRAY_SIZE(musb_regmap); i++) {
switch (musb_regmap[i].size) {
@@ -132,6 +133,8 @@
}
}
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
return 0;
}
@@ -145,7 +148,10 @@
struct musb *musb = s->private;
unsigned test;
+ pm_runtime_get_sync(musb->controller);
test = musb_readb(musb->mregs, MUSB_TESTMODE);
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
if (test & MUSB_TEST_FORCE_HOST)
seq_printf(s, "force host\n");
@@ -194,11 +200,12 @@
u8 test;
char buf[18];
+ pm_runtime_get_sync(musb->controller);
test = musb_readb(musb->mregs, MUSB_TESTMODE);
if (test) {
dev_err(musb->controller, "Error: test mode is already set. "
"Please do USB Bus Reset to start a new test.\n");
- return count;
+ goto ret;
}
memset(buf, 0x00, sizeof(buf));
@@ -234,6 +241,9 @@
musb_writeb(musb->mregs, MUSB_TESTMODE, test);
+ret:
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
return count;
}
@@ -254,8 +264,13 @@
switch (musb->xceiv->otg->state) {
case OTG_STATE_A_HOST:
case OTG_STATE_A_WAIT_BCON:
+ pm_runtime_get_sync(musb->controller);
+
reg = musb_readb(musb->mregs, MUSB_DEVCTL);
connect = reg & MUSB_DEVCTL_SESSION ? 1 : 0;
+
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
break;
default:
connect = -1;
@@ -284,6 +299,7 @@
if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
return -EFAULT;
+ pm_runtime_get_sync(musb->controller);
if (!strncmp(buf, "0", 1)) {
switch (musb->xceiv->otg->state) {
case OTG_STATE_A_HOST:
@@ -314,6 +330,8 @@
}
}
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
return count;
}
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index 2597b83..95aa523 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -95,6 +95,7 @@
unsigned baud_rate; /* set baud rate */
u8 line_control; /* set line control value RTS/DTR */
u8 line_status; /* active status of modem control inputs */
+ u8 lcr;
};
static void ch341_set_termios(struct tty_struct *tty,
@@ -112,6 +113,8 @@
r = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), request,
USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
value, index, NULL, 0, DEFAULT_TIMEOUT);
+ if (r < 0)
+ dev_err(&dev->dev, "failed to send control message: %d\n", r);
return r;
}
@@ -129,11 +132,24 @@
r = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), request,
USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
value, index, buf, bufsize, DEFAULT_TIMEOUT);
- return r;
+ if (r < bufsize) {
+ if (r >= 0) {
+ dev_err(&dev->dev,
+ "short control message received (%d < %u)\n",
+ r, bufsize);
+ r = -EIO;
+ }
+
+ dev_err(&dev->dev, "failed to receive control message: %d\n",
+ r);
+ return r;
+ }
+
+ return 0;
}
-static int ch341_init_set_baudrate(struct usb_device *dev,
- struct ch341_private *priv, unsigned ctrl)
+static int ch341_set_baudrate_lcr(struct usb_device *dev,
+ struct ch341_private *priv, u8 lcr)
{
short a;
int r;
@@ -156,9 +172,19 @@
factor = 0x10000 - factor;
a = (factor & 0xff00) | divisor;
- /* 0x9c is "enable SFR_UART Control register and timer" */
- r = ch341_control_out(dev, CH341_REQ_SERIAL_INIT,
- 0x9c | (ctrl << 8), a | 0x80);
+ /*
+ * CH341A buffers data until a full endpoint-size packet (32 bytes)
+ * has been received unless bit 7 is set.
+ */
+ a |= BIT(7);
+
+ r = ch341_control_out(dev, CH341_REQ_WRITE_REG, 0x1312, a);
+ if (r)
+ return r;
+
+ r = ch341_control_out(dev, CH341_REQ_WRITE_REG, 0x2518, lcr);
+ if (r)
+ return r;
return r;
}
@@ -170,9 +196,9 @@
static int ch341_get_status(struct usb_device *dev, struct ch341_private *priv)
{
+ const unsigned int size = 2;
char *buffer;
int r;
- const unsigned size = 8;
unsigned long flags;
buffer = kmalloc(size, GFP_KERNEL);
@@ -183,14 +209,9 @@
if (r < 0)
goto out;
- /* setup the private status if available */
- if (r == 2) {
- r = 0;
- spin_lock_irqsave(&priv->lock, flags);
- priv->line_status = (~(*buffer)) & CH341_BITS_MODEM_STAT;
- spin_unlock_irqrestore(&priv->lock, flags);
- } else
- r = -EPROTO;
+ spin_lock_irqsave(&priv->lock, flags);
+ priv->line_status = (~(*buffer)) & CH341_BITS_MODEM_STAT;
+ spin_unlock_irqrestore(&priv->lock, flags);
out: kfree(buffer);
return r;
@@ -200,9 +221,9 @@
static int ch341_configure(struct usb_device *dev, struct ch341_private *priv)
{
+ const unsigned int size = 2;
char *buffer;
int r;
- const unsigned size = 8;
buffer = kmalloc(size, GFP_KERNEL);
if (!buffer)
@@ -232,7 +253,7 @@
if (r < 0)
goto out;
- r = ch341_init_set_baudrate(dev, priv, 0);
+ r = ch341_set_baudrate_lcr(dev, priv, priv->lcr);
if (r < 0)
goto out;
@@ -258,7 +279,6 @@
spin_lock_init(&priv->lock);
priv->baud_rate = DEFAULT_BAUD_RATE;
- priv->line_control = CH341_BIT_RTS | CH341_BIT_DTR;
r = ch341_configure(port->serial->dev, priv);
if (r < 0)
@@ -320,7 +340,7 @@
r = ch341_configure(serial->dev, priv);
if (r)
- goto out;
+ return r;
if (tty)
ch341_set_termios(tty, port, NULL);
@@ -330,12 +350,19 @@
if (r) {
dev_err(&port->dev, "%s - failed to submit interrupt urb: %d\n",
__func__, r);
- goto out;
+ return r;
}
r = usb_serial_generic_open(tty, port);
+ if (r)
+ goto err_kill_interrupt_urb;
-out: return r;
+ return 0;
+
+err_kill_interrupt_urb:
+ usb_kill_urb(port->interrupt_in_urb);
+
+ return r;
}
/* Old_termios contains the original termios settings and
@@ -356,7 +383,6 @@
baud_rate = tty_get_baud_rate(tty);
- priv->baud_rate = baud_rate;
ctrl = CH341_LCR_ENABLE_RX | CH341_LCR_ENABLE_TX;
switch (C_CSIZE(tty)) {
@@ -386,22 +412,25 @@
ctrl |= CH341_LCR_STOP_BITS_2;
if (baud_rate) {
- spin_lock_irqsave(&priv->lock, flags);
- priv->line_control |= (CH341_BIT_DTR | CH341_BIT_RTS);
- spin_unlock_irqrestore(&priv->lock, flags);
- r = ch341_init_set_baudrate(port->serial->dev, priv, ctrl);
+ priv->baud_rate = baud_rate;
+
+ r = ch341_set_baudrate_lcr(port->serial->dev, priv, ctrl);
if (r < 0 && old_termios) {
priv->baud_rate = tty_termios_baud_rate(old_termios);
tty_termios_copy_hw(&tty->termios, old_termios);
+ } else if (r == 0) {
+ priv->lcr = ctrl;
}
- } else {
- spin_lock_irqsave(&priv->lock, flags);
- priv->line_control &= ~(CH341_BIT_DTR | CH341_BIT_RTS);
- spin_unlock_irqrestore(&priv->lock, flags);
}
- ch341_set_handshake(port->serial->dev, priv->line_control);
+ spin_lock_irqsave(&priv->lock, flags);
+ if (C_BAUD(tty) == B0)
+ priv->line_control &= ~(CH341_BIT_DTR | CH341_BIT_RTS);
+ else if (old_termios && (old_termios->c_cflag & CBAUD) == B0)
+ priv->line_control |= (CH341_BIT_DTR | CH341_BIT_RTS);
+ spin_unlock_irqrestore(&priv->lock, flags);
+ ch341_set_handshake(port->serial->dev, priv->line_control);
}
static void ch341_break_ctl(struct tty_struct *tty, int break_state)
@@ -576,14 +605,23 @@
static int ch341_reset_resume(struct usb_serial *serial)
{
- struct ch341_private *priv;
-
- priv = usb_get_serial_port_data(serial->port[0]);
+ struct usb_serial_port *port = serial->port[0];
+ struct ch341_private *priv = usb_get_serial_port_data(port);
+ int ret;
/* reconfigure ch341 serial port after bus-reset */
ch341_configure(serial->dev, priv);
- return 0;
+ if (tty_port_initialized(&port->port)) {
+ ret = usb_submit_urb(port->interrupt_in_urb, GFP_NOIO);
+ if (ret) {
+ dev_err(&port->dev, "failed to submit interrupt urb: %d\n",
+ ret);
+ return ret;
+ }
+ }
+
+ return usb_serial_generic_resume(serial);
}
static struct usb_serial_driver ch341_device = {
diff --git a/drivers/usb/serial/kl5kusb105.c b/drivers/usb/serial/kl5kusb105.c
index 0ee190f..6cb4575 100644
--- a/drivers/usb/serial/kl5kusb105.c
+++ b/drivers/usb/serial/kl5kusb105.c
@@ -192,10 +192,11 @@
status_buf, KLSI_STATUSBUF_LEN,
10000
);
- if (rc < 0)
- dev_err(&port->dev, "Reading line status failed (error = %d)\n",
- rc);
- else {
+ if (rc != KLSI_STATUSBUF_LEN) {
+ dev_err(&port->dev, "reading line status failed: %d\n", rc);
+ if (rc >= 0)
+ rc = -EIO;
+ } else {
status = get_unaligned_le16(status_buf);
dev_info(&port->serial->dev->dev, "read status %x %x\n",
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 7ce31a4..42cc72e 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -2007,6 +2007,7 @@
{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_6802, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD300, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, 0xff, 0xff, 0xff) }, /* HP lt2523 (Novatel E371) */
{ } /* Terminating entry */
};
MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 46fca6b..1db4b61 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -49,6 +49,7 @@
{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) },
{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) },
{ USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) },
+ { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID2) },
{ USB_DEVICE(ATEN_VENDOR_ID2, ATEN_PRODUCT_ID) },
{ USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID) },
{ USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID_UCSGT) },
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index e3b7af8..09d9be8 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -27,6 +27,7 @@
#define ATEN_VENDOR_ID 0x0557
#define ATEN_VENDOR_ID2 0x0547
#define ATEN_PRODUCT_ID 0x2008
+#define ATEN_PRODUCT_ID2 0x2118
#define IODATA_VENDOR_ID 0x04bb
#define IODATA_PRODUCT_ID 0x0a03
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 1bc6089..696458d 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -124,6 +124,7 @@
{USB_DEVICE(0x1410, 0xa021)}, /* Novatel Gobi 3000 Composite */
{USB_DEVICE(0x413c, 0x8193)}, /* Dell Gobi 3000 QDL */
{USB_DEVICE(0x413c, 0x8194)}, /* Dell Gobi 3000 Composite */
+ {USB_DEVICE(0x413c, 0x81a6)}, /* Dell DW5570 QDL (MC8805) */
{USB_DEVICE(0x1199, 0x68a4)}, /* Sierra Wireless QDL */
{USB_DEVICE(0x1199, 0x68a5)}, /* Sierra Wireless Modem */
{USB_DEVICE(0x1199, 0x68a8)}, /* Sierra Wireless QDL */
diff --git a/drivers/usb/wusbcore/crypto.c b/drivers/usb/wusbcore/crypto.c
index 79451f7..062c205 100644
--- a/drivers/usb/wusbcore/crypto.c
+++ b/drivers/usb/wusbcore/crypto.c
@@ -216,7 +216,6 @@
struct scatterlist sg[4], sg_dst;
void *dst_buf;
size_t dst_size;
- const u8 bzero[16] = { 0 };
u8 iv[crypto_skcipher_ivsize(tfm_cbc)];
size_t zero_padding;
@@ -261,7 +260,7 @@
sg_set_buf(&sg[1], &scratch->b1, sizeof(scratch->b1));
sg_set_buf(&sg[2], b, blen);
/* 0 if well behaved :) */
- sg_set_buf(&sg[3], bzero, zero_padding);
+ sg_set_page(&sg[3], ZERO_PAGE(0), zero_padding, 0);
sg_init_one(&sg_dst, dst_buf, dst_size);
skcipher_request_set_tfm(req, tfm_cbc);
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index c882357..59b3f62 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -1123,12 +1123,11 @@
mutex_lock(&container->lock);
ret = tce_iommu_create_default_window(container);
- if (ret)
- return ret;
-
- ret = tce_iommu_create_window(container, create.page_shift,
- create.window_size, create.levels,
- &create.start_addr);
+ if (!ret)
+ ret = tce_iommu_create_window(container,
+ create.page_shift,
+ create.window_size, create.levels,
+ &create.start_addr);
mutex_unlock(&container->lock);
@@ -1246,6 +1245,8 @@
static long tce_iommu_take_ownership_ddw(struct tce_container *container,
struct iommu_table_group *table_group)
{
+ long i, ret = 0;
+
if (!table_group->ops->create_table || !table_group->ops->set_window ||
!table_group->ops->release_ownership) {
WARN_ON_ONCE(1);
@@ -1254,7 +1255,27 @@
table_group->ops->take_ownership(table_group);
+ /* Set all windows to the new group */
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ struct iommu_table *tbl = container->tables[i];
+
+ if (!tbl)
+ continue;
+
+ ret = table_group->ops->set_window(table_group, i, tbl);
+ if (ret)
+ goto release_exit;
+ }
+
return 0;
+
+release_exit:
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
+ table_group->ops->unset_window(table_group, i);
+
+ table_group->ops->release_ownership(table_group);
+
+ return ret;
}
static int tce_iommu_attach_group(void *iommu_data,
@@ -1270,6 +1291,10 @@
/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
iommu_group_id(iommu_group), iommu_group); */
table_group = iommu_group_get_iommudata(iommu_group);
+ if (!table_group) {
+ ret = -ENODEV;
+ goto unlock_exit;
+ }
if (tce_groups_attached(container) && (!table_group->ops ||
!table_group->ops->take_ownership ||
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 9266271..b3cc33f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -36,7 +36,6 @@
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/workqueue.h>
-#include <linux/pid_namespace.h>
#include <linux/mdev.h>
#include <linux/notifier.h>
@@ -495,8 +494,7 @@
unsigned long *pfn_base, bool do_accounting)
{
unsigned long limit;
- bool lock_cap = ns_capable(task_active_pid_ns(dma->task)->user_ns,
- CAP_IPC_LOCK);
+ bool lock_cap = has_capability(dma->task, CAP_IPC_LOCK);
struct mm_struct *mm;
int ret;
bool rsvd;
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 253310c..fd6c8b6 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -843,7 +843,7 @@
struct iov_iter out_iter, in_iter, prot_iter, data_iter;
u64 tag;
u32 exp_data_len, data_direction;
- unsigned out, in;
+ unsigned int out = 0, in = 0;
int head, ret, prot_bytes;
size_t req_size, rsp_size = sizeof(struct virtio_scsi_cmd_resp);
size_t out_size, in_size;
@@ -2087,7 +2087,7 @@
NULL,
};
-static struct target_core_fabric_ops vhost_scsi_ops = {
+static const struct target_core_fabric_ops vhost_scsi_ops = {
.module = THIS_MODULE,
.name = "vhost",
.get_fabric_name = vhost_scsi_get_fabric_name,
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index d643260..8f99fe0 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -130,14 +130,14 @@
static void vhost_init_is_le(struct vhost_virtqueue *vq)
{
- if (vhost_has_feature(vq, VIRTIO_F_VERSION_1))
- vq->is_le = true;
+ vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1)
+ || virtio_legacy_is_little_endian();
}
#endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */
static void vhost_reset_is_le(struct vhost_virtqueue *vq)
{
- vq->is_le = virtio_legacy_is_little_endian();
+ vhost_init_is_le(vq);
}
struct vhost_flush_struct {
@@ -1714,10 +1714,8 @@
int r;
bool is_le = vq->is_le;
- if (!vq->private_data) {
- vhost_reset_is_le(vq);
+ if (!vq->private_data)
return 0;
- }
vhost_init_is_le(vq);
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index bbbf5885..ce5e63d 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -373,6 +373,7 @@
static int vhost_vsock_start(struct vhost_vsock *vsock)
{
+ struct vhost_virtqueue *vq;
size_t i;
int ret;
@@ -383,19 +384,20 @@
goto err;
for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
- struct vhost_virtqueue *vq = &vsock->vqs[i];
+ vq = &vsock->vqs[i];
mutex_lock(&vq->mutex);
if (!vhost_vq_access_ok(vq)) {
ret = -EFAULT;
- mutex_unlock(&vq->mutex);
goto err_vq;
}
if (!vq->private_data) {
vq->private_data = vsock;
- vhost_vq_init_access(vq);
+ ret = vhost_vq_init_access(vq);
+ if (ret)
+ goto err_vq;
}
mutex_unlock(&vq->mutex);
@@ -405,8 +407,11 @@
return 0;
err_vq:
+ vq->private_data = NULL;
+ mutex_unlock(&vq->mutex);
+
for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
- struct vhost_virtqueue *vq = &vsock->vqs[i];
+ vq = &vsock->vqs[i];
mutex_lock(&vq->mutex);
vq->private_data = NULL;
diff --git a/drivers/video/fbdev/core/fbcmap.c b/drivers/video/fbdev/core/fbcmap.c
index f89245b..68a1135 100644
--- a/drivers/video/fbdev/core/fbcmap.c
+++ b/drivers/video/fbdev/core/fbcmap.c
@@ -163,17 +163,18 @@
int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to)
{
- int tooff = 0, fromoff = 0;
- int size;
+ unsigned int tooff = 0, fromoff = 0;
+ size_t size;
if (to->start > from->start)
fromoff = to->start - from->start;
else
tooff = from->start - to->start;
- size = to->len - tooff;
- if (size > (int) (from->len - fromoff))
- size = from->len - fromoff;
- if (size <= 0)
+ if (fromoff >= from->len || tooff >= to->len)
+ return -EINVAL;
+
+ size = min_t(size_t, to->len - tooff, from->len - fromoff);
+ if (size == 0)
return -EINVAL;
size *= sizeof(u16);
@@ -187,17 +188,18 @@
int fb_cmap_to_user(const struct fb_cmap *from, struct fb_cmap_user *to)
{
- int tooff = 0, fromoff = 0;
- int size;
+ unsigned int tooff = 0, fromoff = 0;
+ size_t size;
if (to->start > from->start)
fromoff = to->start - from->start;
else
tooff = from->start - to->start;
- size = to->len - tooff;
- if (size > (int) (from->len - fromoff))
- size = from->len - fromoff;
- if (size <= 0)
+ if (fromoff >= from->len || tooff >= to->len)
+ return -EINVAL;
+
+ size = min_t(size_t, to->len - tooff, from->len - fromoff);
+ if (size == 0)
return -EINVAL;
size *= sizeof(u16);
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index d47a2fc..c71fde5 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -59,6 +59,7 @@
#define pr_fmt(fmt) "virtio-mmio: " fmt
#include <linux/acpi.h>
+#include <linux/dma-mapping.h>
#include <linux/highmem.h>
#include <linux/interrupt.h>
#include <linux/io.h>
@@ -498,6 +499,7 @@
struct virtio_mmio_device *vm_dev;
struct resource *mem;
unsigned long magic;
+ int rc;
mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!mem)
@@ -547,9 +549,25 @@
}
vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID);
- if (vm_dev->version == 1)
+ if (vm_dev->version == 1) {
writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+ rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
+ /*
+ * In the legacy case, ensure our coherently-allocated virtio
+ * ring will be at an address expressable as a 32-bit PFN.
+ */
+ if (!rc)
+ dma_set_coherent_mask(&pdev->dev,
+ DMA_BIT_MASK(32 + PAGE_SHIFT));
+ } else {
+ rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+ }
+ if (rc)
+ rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (rc)
+ dev_warn(&pdev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n");
+
platform_set_drvdata(pdev, vm_dev);
return register_virtio_device(&vm_dev->vdev);
diff --git a/drivers/vme/bridges/vme_ca91cx42.c b/drivers/vme/bridges/vme_ca91cx42.c
index 6b5ee89..7cc5122 100644
--- a/drivers/vme/bridges/vme_ca91cx42.c
+++ b/drivers/vme/bridges/vme_ca91cx42.c
@@ -464,7 +464,7 @@
vme_bound = ioread32(bridge->base + CA91CX42_VSI_BD[i]);
pci_offset = ioread32(bridge->base + CA91CX42_VSI_TO[i]);
- *pci_base = (dma_addr_t)vme_base + pci_offset;
+ *pci_base = (dma_addr_t)*vme_base + pci_offset;
*size = (unsigned long long)((vme_bound - *vme_base) + granularity);
*enabled = 0;
diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c
index 112ce42..2a165cc 100644
--- a/drivers/xen/platform-pci.c
+++ b/drivers/xen/platform-pci.c
@@ -42,6 +42,7 @@
static unsigned long platform_mmio;
static unsigned long platform_mmio_alloc;
static unsigned long platform_mmiolen;
+static uint64_t callback_via;
static unsigned long alloc_xen_mmio(unsigned long len)
{
@@ -54,6 +55,51 @@
return addr;
}
+static uint64_t get_callback_via(struct pci_dev *pdev)
+{
+ u8 pin;
+ int irq;
+
+ irq = pdev->irq;
+ if (irq < 16)
+ return irq; /* ISA IRQ */
+
+ pin = pdev->pin;
+
+ /* We don't know the GSI. Specify the PCI INTx line instead. */
+ return ((uint64_t)0x01 << HVM_CALLBACK_VIA_TYPE_SHIFT) | /* PCI INTx identifier */
+ ((uint64_t)pci_domain_nr(pdev->bus) << 32) |
+ ((uint64_t)pdev->bus->number << 16) |
+ ((uint64_t)(pdev->devfn & 0xff) << 8) |
+ ((uint64_t)(pin - 1) & 3);
+}
+
+static irqreturn_t do_hvm_evtchn_intr(int irq, void *dev_id)
+{
+ xen_hvm_evtchn_do_upcall();
+ return IRQ_HANDLED;
+}
+
+static int xen_allocate_irq(struct pci_dev *pdev)
+{
+ return request_irq(pdev->irq, do_hvm_evtchn_intr,
+ IRQF_NOBALANCING | IRQF_TRIGGER_RISING,
+ "xen-platform-pci", pdev);
+}
+
+static int platform_pci_resume(struct pci_dev *pdev)
+{
+ int err;
+ if (!xen_pv_domain())
+ return 0;
+ err = xen_set_callback_via(callback_via);
+ if (err) {
+ dev_err(&pdev->dev, "platform_pci_resume failure!\n");
+ return err;
+ }
+ return 0;
+}
+
static int platform_pci_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
{
@@ -92,6 +138,28 @@
platform_mmio = mmio_addr;
platform_mmiolen = mmio_len;
+ /*
+ * Xen HVM guests always use the vector callback mechanism.
+ * L1 Dom0 in a nested Xen environment is a PV guest inside in an
+ * HVM environment. It needs the platform-pci driver to get
+ * notifications from L0 Xen, but it cannot use the vector callback
+ * as it is not exported by L1 Xen.
+ */
+ if (xen_pv_domain()) {
+ ret = xen_allocate_irq(pdev);
+ if (ret) {
+ dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret);
+ goto out;
+ }
+ callback_via = get_callback_via(pdev);
+ ret = xen_set_callback_via(callback_via);
+ if (ret) {
+ dev_warn(&pdev->dev, "Unable to set the evtchn callback "
+ "err=%d\n", ret);
+ goto out;
+ }
+ }
+
max_nr_gframes = gnttab_max_grant_frames();
grant_frames = alloc_xen_mmio(PAGE_SIZE * max_nr_gframes);
ret = gnttab_setup_auto_xlat_frames(grant_frames);
@@ -123,6 +191,9 @@
.name = DRV_NAME,
.probe = platform_pci_probe,
.id_table = platform_pci_tbl,
+#ifdef CONFIG_PM
+ .resume_early = platform_pci_resume,
+#endif
};
builtin_pci_driver(platform_driver);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index f905d6e..f8afc6d 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -414,9 +414,9 @@
if (map == SWIOTLB_MAP_ERROR)
return DMA_ERROR_CODE;
+ dev_addr = xen_phys_to_bus(map);
xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
dev_addr, map & ~PAGE_MASK, size, dir, attrs);
- dev_addr = xen_phys_to_bus(map);
/*
* Ensure that the address returned is DMA'ble
@@ -575,13 +575,14 @@
sg_dma_len(sgl) = 0;
return 0;
}
+ dev_addr = xen_phys_to_bus(map);
xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT),
dev_addr,
map & ~PAGE_MASK,
sg->length,
dir,
attrs);
- sg->dma_address = xen_phys_to_bus(map);
+ sg->dma_address = dev_addr;
} else {
/* we are not interested in the dma_addr returned by
* xen_dma_map_page, only in the potential cache flushes executed
diff --git a/fs/Kconfig b/fs/Kconfig
index c2a377c..83eab52 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -38,6 +38,7 @@
bool "Direct Access (DAX) support"
depends on MMU
depends on !(ARM || MIPS || SPARC)
+ select FS_IOMAP
help
Direct Access (DAX) can be used on memory-backed block devices.
If the block device supports DAX and the filesystem supports DAX,
diff --git a/fs/aio.c b/fs/aio.c
index 4ab67e8..873b4ca 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1085,7 +1085,8 @@
* Tell lockdep we inherited freeze protection from submission
* thread.
*/
- __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+ if (S_ISREG(file_inode(file)->i_mode))
+ __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
file_end_write(file);
}
@@ -1525,7 +1526,8 @@
* by telling it the lock got released so that it doesn't
* complain about held lock when we return to userspace.
*/
- __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+ if (S_ISREG(file_inode(file)->i_mode))
+ __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
}
kfree(iovec);
return ret;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 29a02da..e7bf013 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1428,17 +1428,18 @@
* group-wide total, not its individual thread total.
*/
thread_group_cputime(p, &cputime);
- cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
- cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
+ prstatus->pr_utime = ns_to_timeval(cputime.utime);
+ prstatus->pr_stime = ns_to_timeval(cputime.stime);
} else {
- cputime_t utime, stime;
+ u64 utime, stime;
task_cputime(p, &utime, &stime);
- cputime_to_timeval(utime, &prstatus->pr_utime);
- cputime_to_timeval(stime, &prstatus->pr_stime);
+ prstatus->pr_utime = ns_to_timeval(utime);
+ prstatus->pr_stime = ns_to_timeval(stime);
}
- cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
- cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+
+ prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
+ prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
}
static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
@@ -2298,6 +2299,7 @@
goto end_coredump;
}
}
+ dump_truncate(cprm);
if (!elf_core_write_extra_data(cprm))
goto end_coredump;
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index d2e36f8..ffca4bb 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1349,17 +1349,17 @@
* group-wide total, not its individual thread total.
*/
thread_group_cputime(p, &cputime);
- cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
- cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
+ prstatus->pr_utime = ns_to_timeval(cputime.utime);
+ prstatus->pr_stime = ns_to_timeval(cputime.stime);
} else {
- cputime_t utime, stime;
+ u64 utime, stime;
task_cputime(p, &utime, &stime);
- cputime_to_timeval(utime, &prstatus->pr_utime);
- cputime_to_timeval(stime, &prstatus->pr_stime);
+ prstatus->pr_utime = ns_to_timeval(utime);
+ prstatus->pr_stime = ns_to_timeval(stime);
}
- cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
- cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+ prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
+ prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap;
prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 5db5d13..3c47614 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -331,7 +331,7 @@
struct blk_plug plug;
struct blkdev_dio *dio;
struct bio *bio;
- bool is_read = (iov_iter_rw(iter) == READ);
+ bool is_read = (iov_iter_rw(iter) == READ), is_sync;
loff_t pos = iocb->ki_pos;
blk_qc_t qc = BLK_QC_T_NONE;
int ret;
@@ -344,7 +344,7 @@
bio_get(bio); /* extra ref for the completion handler */
dio = container_of(bio, struct blkdev_dio, bio);
- dio->is_sync = is_sync_kiocb(iocb);
+ dio->is_sync = is_sync = is_sync_kiocb(iocb);
if (dio->is_sync)
dio->waiter = current;
else
@@ -398,7 +398,7 @@
}
blk_finish_plug(&plug);
- if (!dio->is_sync)
+ if (!is_sync)
return -EIOCBQUEUED;
for (;;) {
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 63d1977..ff0b0be 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -273,6 +273,8 @@
unsigned long flags;
while (1) {
+ void *wtag;
+
spin_lock_irqsave(lock, flags);
if (list_empty(list))
break;
@@ -299,11 +301,13 @@
spin_unlock_irqrestore(lock, flags);
/*
- * we don't want to call the ordered free functions
- * with the lock held though
+ * We don't want to call the ordered free functions with the
+ * lock held though. Save the work as tag for the trace event,
+ * because the callback could free the structure.
*/
+ wtag = work;
work->ordered_free(work);
- trace_btrfs_all_work_done(work);
+ trace_btrfs_all_work_done(wq->fs_info, wtag);
}
spin_unlock_irqrestore(lock, flags);
}
@@ -311,6 +315,7 @@
static void normal_work_helper(struct btrfs_work *work)
{
struct __btrfs_workqueue *wq;
+ void *wtag;
int need_order = 0;
/*
@@ -324,6 +329,8 @@
if (work->ordered_func)
need_order = 1;
wq = work->wq;
+ /* Safe for tracepoints in case work gets freed by the callback */
+ wtag = work;
trace_btrfs_work_sched(work);
thresh_exec_hook(wq);
@@ -333,7 +340,7 @@
run_ordered_work(wq);
}
if (!need_order)
- trace_btrfs_all_work_done(work);
+ trace_btrfs_all_work_done(wq->fs_info, wtag);
}
void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 7f39084..c4444d6 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1024,6 +1024,7 @@
unsigned long buf_offset;
unsigned long current_buf_start;
unsigned long start_byte;
+ unsigned long prev_start_byte;
unsigned long working_bytes = total_out - buf_start;
unsigned long bytes;
char *kaddr;
@@ -1071,26 +1072,34 @@
if (!bio->bi_iter.bi_size)
return 0;
bvec = bio_iter_iovec(bio, bio->bi_iter);
-
+ prev_start_byte = start_byte;
start_byte = page_offset(bvec.bv_page) - disk_start;
/*
- * make sure our new page is covered by this
- * working buffer
+ * We need to make sure we're only adjusting
+ * our offset into compression working buffer when
+ * we're switching pages. Otherwise we can incorrectly
+ * keep copying when we were actually done.
*/
- if (total_out <= start_byte)
- return 1;
+ if (start_byte != prev_start_byte) {
+ /*
+ * make sure our new page is covered by this
+ * working buffer
+ */
+ if (total_out <= start_byte)
+ return 1;
- /*
- * the next page in the biovec might not be adjacent
- * to the last page, but it might still be found
- * inside this working buffer. bump our offset pointer
- */
- if (total_out > start_byte &&
- current_buf_start < start_byte) {
- buf_offset = start_byte - buf_start;
- working_bytes = total_out - start_byte;
- current_buf_start = buf_start + buf_offset;
+ /*
+ * the next page in the biovec might not be adjacent
+ * to the last page, but it might still be found
+ * inside this working buffer. bump our offset pointer
+ */
+ if (total_out > start_byte &&
+ current_buf_start < start_byte) {
+ buf_offset = start_byte - buf_start;
+ working_bytes = total_out - start_byte;
+ current_buf_start = buf_start + buf_offset;
+ }
}
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e97302f..dcd2e79 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2522,11 +2522,11 @@
if (ref && ref->seq &&
btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
spin_unlock(&locked_ref->lock);
- btrfs_delayed_ref_unlock(locked_ref);
spin_lock(&delayed_refs->lock);
locked_ref->processing = 0;
delayed_refs->num_heads_ready++;
spin_unlock(&delayed_refs->lock);
+ btrfs_delayed_ref_unlock(locked_ref);
locked_ref = NULL;
cond_resched();
count++;
@@ -2572,7 +2572,10 @@
*/
if (must_insert_reserved)
locked_ref->must_insert_reserved = 1;
+ spin_lock(&delayed_refs->lock);
locked_ref->processing = 0;
+ delayed_refs->num_heads_ready++;
+ spin_unlock(&delayed_refs->lock);
btrfs_debug(fs_info,
"run_delayed_extent_op returned %d",
ret);
@@ -7384,7 +7387,8 @@
spin_unlock(&cluster->refill_lock);
- down_read(&used_bg->data_rwsem);
+ /* We should only have one-level nested. */
+ down_read_nested(&used_bg->data_rwsem, SINGLE_DEPTH_NESTING);
spin_lock(&cluster->refill_lock);
if (used_bg == cluster->block_group)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f2b281a..1e861a0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3835,10 +3835,7 @@
break;
case S_IFDIR:
inode->i_fop = &btrfs_dir_file_operations;
- if (root == fs_info->tree_root)
- inode->i_op = &btrfs_dir_ro_inode_operations;
- else
- inode->i_op = &btrfs_dir_inode_operations;
+ inode->i_op = &btrfs_dir_inode_operations;
break;
case S_IFLNK:
inode->i_op = &btrfs_symlink_inode_operations;
@@ -4505,8 +4502,19 @@
if (found_type > min_type) {
del_item = 1;
} else {
- if (item_end < new_size)
+ if (item_end < new_size) {
+ /*
+ * With NO_HOLES mode, for the following mapping
+ *
+ * [0-4k][hole][8k-12k]
+ *
+ * if truncating isize down to 6k, it ends up
+ * isize being 8k.
+ */
+ if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
+ last_size = new_size;
break;
+ }
if (found_key.offset >= new_size)
del_item = 1;
else
@@ -5710,6 +5718,7 @@
inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID;
inode->i_op = &btrfs_dir_ro_inode_operations;
+ inode->i_opflags &= ~IOP_XATTR;
inode->i_fop = &simple_dir_operations;
inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
inode->i_mtime = current_time(inode);
@@ -7059,7 +7068,7 @@
write_unlock(&em_tree->lock);
out:
- trace_btrfs_get_extent(root, em);
+ trace_btrfs_get_extent(root, inode, em);
btrfs_free_path(path);
if (trans) {
@@ -7215,7 +7224,6 @@
struct extent_map *em = NULL;
int ret;
- down_read(&BTRFS_I(inode)->dio_sem);
if (type != BTRFS_ORDERED_NOCOW) {
em = create_pinned_em(inode, start, len, orig_start,
block_start, block_len, orig_block_len,
@@ -7234,7 +7242,6 @@
em = ERR_PTR(ret);
}
out:
- up_read(&BTRFS_I(inode)->dio_sem);
return em;
}
@@ -7623,11 +7630,18 @@
* within our reservation, otherwise we need to adjust our inode
* counter appropriately.
*/
- if (dio_data->outstanding_extents) {
+ if (dio_data->outstanding_extents >= num_extents) {
dio_data->outstanding_extents -= num_extents;
} else {
+ /*
+ * If dio write length has been split due to no large enough
+ * contiguous space, we need to compensate our inode counter
+ * appropriately.
+ */
+ u64 num_needed = num_extents - dio_data->outstanding_extents;
+
spin_lock(&BTRFS_I(inode)->lock);
- BTRFS_I(inode)->outstanding_extents += num_extents;
+ BTRFS_I(inode)->outstanding_extents += num_needed;
spin_unlock(&BTRFS_I(inode)->lock);
}
}
@@ -8685,6 +8699,7 @@
dio_data.unsubmitted_oe_range_start = (u64)offset;
dio_data.unsubmitted_oe_range_end = (u64)offset;
current->journal_info = &dio_data;
+ down_read(&BTRFS_I(inode)->dio_sem);
} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
&BTRFS_I(inode)->runtime_flags)) {
inode_dio_end(inode);
@@ -8697,6 +8712,7 @@
iter, btrfs_get_blocks_direct, NULL,
btrfs_submit_direct, flags);
if (iov_iter_rw(iter) == WRITE) {
+ up_read(&BTRFS_I(inode)->dio_sem);
current->journal_info = NULL;
if (ret < 0 && ret != -EIOCBQUEUED) {
if (dio_data.reserve)
@@ -9205,6 +9221,7 @@
break;
}
+ btrfs_block_rsv_release(fs_info, rsv, -1);
ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv,
rsv, min_size, 0);
BUG_ON(ret); /* shouldn't happen */
@@ -10572,8 +10589,6 @@
static const struct inode_operations btrfs_dir_ro_inode_operations = {
.lookup = btrfs_lookup,
.permission = btrfs_permission,
- .get_acl = btrfs_get_acl,
- .set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
};
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 33f967d..21e51b0 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5653,6 +5653,10 @@
#ifdef CONFIG_COMPAT
long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
+ /*
+ * These all access 32-bit values anyway so no further
+ * handling is necessary.
+ */
switch (cmd) {
case FS_IOC32_GETFLAGS:
cmd = FS_IOC_GETFLAGS;
@@ -5663,8 +5667,6 @@
case FS_IOC32_GETVERSION:
cmd = FS_IOC_GETVERSION;
break;
- default:
- return -ENOIOCTLCMD;
}
return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f10bf52..eeffff8 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -37,6 +37,7 @@
*/
#define LOG_INODE_ALL 0
#define LOG_INODE_EXISTS 1
+#define LOG_OTHER_INODE 2
/*
* directory trouble cases
@@ -4641,7 +4642,7 @@
if (S_ISDIR(inode->i_mode) ||
(!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
&BTRFS_I(inode)->runtime_flags) &&
- inode_only == LOG_INODE_EXISTS))
+ inode_only >= LOG_INODE_EXISTS))
max_key.type = BTRFS_XATTR_ITEM_KEY;
else
max_key.type = (u8)-1;
@@ -4665,7 +4666,13 @@
return ret;
}
- mutex_lock(&BTRFS_I(inode)->log_mutex);
+ if (inode_only == LOG_OTHER_INODE) {
+ inode_only = LOG_INODE_EXISTS;
+ mutex_lock_nested(&BTRFS_I(inode)->log_mutex,
+ SINGLE_DEPTH_NESTING);
+ } else {
+ mutex_lock(&BTRFS_I(inode)->log_mutex);
+ }
/*
* a brute force approach to making sure we get the most uptodate
@@ -4817,7 +4824,7 @@
* unpin it.
*/
err = btrfs_log_inode(trans, root, other_inode,
- LOG_INODE_EXISTS,
+ LOG_OTHER_INODE,
0, LLONG_MAX, ctx);
iput(other_inode);
if (err)
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index 161342b..726f928 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -352,7 +352,5 @@
out:
btrfs_free_path(path);
- if (ret)
- btrfs_warn(fs_info, "btrfs_uuid_tree_iterate failed %d", ret);
- return 0;
+ return ret;
}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 9cd0c0e..e4b066c 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -502,9 +502,9 @@
dout(" head snapc %p has %d dirty pages\n",
snapc, ci->i_wrbuffer_ref_head);
if (truncate_size)
- *truncate_size = capsnap->truncate_size;
+ *truncate_size = ci->i_truncate_size;
if (truncate_seq)
- *truncate_seq = capsnap->truncate_seq;
+ *truncate_seq = ci->i_truncate_seq;
}
spin_unlock(&ci->i_ceph_lock);
return snapc;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index baea866..94fd76d 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2591,8 +2591,13 @@
add_wait_queue(&ci->i_cap_wq, &wait);
while (!try_get_cap_refs(ci, need, want, endoff,
- true, &_got, &err))
+ true, &_got, &err)) {
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+ }
remove_wait_queue(&ci->i_cap_wq, &wait);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index d7a9369..8ab1fdf 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1230,7 +1230,8 @@
struct ceph_mds_client *mdsc =
ceph_sb_to_client(dir->i_sb)->mdsc;
struct ceph_mds_request *req;
- int op, mask, err;
+ int op, err;
+ u32 mask;
if (flags & LOOKUP_RCU)
return -ECHILD;
@@ -1245,7 +1246,7 @@
mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
if (ceph_security_xattr_wanted(dir))
mask |= CEPH_CAP_XATTR_SHARED;
- req->r_args.getattr.mask = mask;
+ req->r_args.getattr.mask = cpu_to_le32(mask);
err = ceph_mdsc_do_request(mdsc, NULL, req);
switch (err) {
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 398e532..5e659d0 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -305,7 +305,8 @@
{
struct ceph_frag_tree_split *ls = (struct ceph_frag_tree_split*)l;
struct ceph_frag_tree_split *rs = (struct ceph_frag_tree_split*)r;
- return ceph_frag_compare(ls->frag, rs->frag);
+ return ceph_frag_compare(le32_to_cpu(ls->frag),
+ le32_to_cpu(rs->frag));
}
static bool is_frag_child(u32 f, struct ceph_inode_frag *frag)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 4f49253..c9d2e55 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -288,12 +288,13 @@
struct ceph_mds_reply_info_parsed *info,
u64 features)
{
- if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
+ u32 op = le32_to_cpu(info->head->op);
+
+ if (op == CEPH_MDS_OP_GETFILELOCK)
return parse_reply_info_filelock(p, end, info, features);
- else if (info->head->op == CEPH_MDS_OP_READDIR ||
- info->head->op == CEPH_MDS_OP_LSSNAP)
+ else if (op == CEPH_MDS_OP_READDIR || op == CEPH_MDS_OP_LSSNAP)
return parse_reply_info_dir(p, end, info, features);
- else if (info->head->op == CEPH_MDS_OP_CREATE)
+ else if (op == CEPH_MDS_OP_CREATE)
return parse_reply_info_create(p, end, info, features);
else
return -EIO;
@@ -2106,6 +2107,11 @@
dout("do_request mdsmap err %d\n", err);
goto finish;
}
+ if (mdsc->mdsmap->m_epoch == 0) {
+ dout("do_request no mdsmap, waiting for map\n");
+ list_add(&req->r_wait, &mdsc->waiting_for_map);
+ goto finish;
+ }
if (!(mdsc->fsc->mount_options->flags &
CEPH_MOUNT_OPT_MOUNTWAIT) &&
!ceph_mdsmap_is_cluster_available(mdsc->mdsmap)) {
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 8f6a2a5..a27fc87 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -285,6 +285,7 @@
rc = -ENOMEM;
goto error_exit;
}
+ spin_lock_init(&cifsFile->file_info_lock);
file->private_data = cifsFile;
cifsFile->tlink = cifs_get_tlink(tlink);
tcon = tlink_tcon(tlink);
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index 4d24d17..504b3c35 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -51,22 +51,8 @@
#define elf_prstatus compat_elf_prstatus
#define elf_prpsinfo compat_elf_prpsinfo
-/*
- * Compat version of cputime_to_compat_timeval, perhaps this
- * should be an inline in <linux/compat.h>.
- */
-static void cputime_to_compat_timeval(const cputime_t cputime,
- struct compat_timeval *value)
-{
- struct timeval tv;
- cputime_to_timeval(cputime, &tv);
- value->tv_sec = tv.tv_sec;
- value->tv_usec = tv.tv_usec;
-}
-
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
/*
* To use this file, asm/elf.h must define compat_elf_check_arch.
diff --git a/fs/coredump.c b/fs/coredump.c
index e525b60..ae6b056 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -833,3 +833,21 @@
return mod ? dump_skip(cprm, align - mod) : 1;
}
EXPORT_SYMBOL(dump_align);
+
+/*
+ * Ensures that file size is big enough to contain the current file
+ * postion. This prevents gdb from complaining about a truncated file
+ * if the last "write" to the file was dump_skip.
+ */
+void dump_truncate(struct coredump_params *cprm)
+{
+ struct file *file = cprm->file;
+ loff_t offset;
+
+ if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+ offset = file->f_op->llseek(file, 0, SEEK_CUR);
+ if (i_size_read(file->f_mapping->host) < offset)
+ do_truncate(file->f_path.dentry, offset, 0, file);
+ }
+}
+EXPORT_SYMBOL(dump_truncate);
diff --git a/fs/dax.c b/fs/dax.c
index ddcddfe..c45598b 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -990,7 +990,6 @@
}
EXPORT_SYMBOL_GPL(__dax_zero_page_range);
-#ifdef CONFIG_FS_IOMAP
static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
{
return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9);
@@ -1032,6 +1031,11 @@
struct blk_dax_ctl dax = { 0 };
ssize_t map_len;
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
+
dax.sector = dax_iomap_sector(iomap, pos);
dax.size = (length + offset + PAGE_SIZE - 1) & PAGE_MASK;
map_len = dax_map_atomic(iomap->bdev, &dax);
@@ -1428,4 +1432,3 @@
}
EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
#endif /* CONFIG_FS_DAX_PMD */
-#endif /* CONFIG_FS_IOMAP */
diff --git a/fs/dcache.c b/fs/dcache.c
index 769903d..95d71ed 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1336,8 +1336,11 @@
}
spin_lock(&dentry->d_lock);
if (!d_unlinked(dentry)) {
- dentry->d_flags |= DCACHE_MOUNTED;
- ret = 0;
+ ret = -EBUSY;
+ if (!d_mountpoint(dentry)) {
+ dentry->d_flags |= DCACHE_MOUNTED;
+ ret = 0;
+ }
}
spin_unlock(&dentry->d_lock);
out:
diff --git a/fs/direct-io.c b/fs/direct-io.c
index aeae8c0..c87bae4 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -906,6 +906,7 @@
struct buffer_head *map_bh)
{
const unsigned blkbits = sdio->blkbits;
+ const unsigned i_blkbits = blkbits + sdio->blkfactor;
int ret = 0;
while (sdio->block_in_file < sdio->final_block_in_request) {
@@ -949,7 +950,7 @@
clean_bdev_aliases(
map_bh->b_bdev,
map_bh->b_blocknr,
- map_bh->b_size >> blkbits);
+ map_bh->b_size >> i_blkbits);
}
if (!sdio->blkfactor)
diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig
index 36bea5a..c634874e 100644
--- a/fs/ext2/Kconfig
+++ b/fs/ext2/Kconfig
@@ -1,6 +1,5 @@
config EXT2_FS
tristate "Second extended fs support"
- select FS_IOMAP if FS_DAX
help
Ext2 is a standard Linux file system for hard disks.
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 7b90691..e38039f 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -37,7 +37,6 @@
select CRC16
select CRYPTO
select CRYPTO_CRC32C
- select FS_IOMAP if FS_DAX
help
This is the next generation of the ext3 filesystem.
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 0738f48..0d88024 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -713,8 +713,8 @@
}
sector = SECTOR_FROM_BLOCK(blkstart);
- if (sector & (bdev_zone_size(bdev) - 1) ||
- nr_sects != bdev_zone_size(bdev)) {
+ if (sector & (bdev_zone_sectors(bdev) - 1) ||
+ nr_sects != bdev_zone_sectors(bdev)) {
f2fs_msg(sbi->sb, KERN_INFO,
"(%d) %s: Unaligned discard attempted (block %x + %x)",
devi, sbi->s_ndevs ? FDEV(devi).path: "",
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 702638e..46fd30d 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1553,16 +1553,16 @@
return 0;
if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
- SECTOR_TO_BLOCK(bdev_zone_size(bdev)))
+ SECTOR_TO_BLOCK(bdev_zone_sectors(bdev)))
return -EINVAL;
- sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_size(bdev));
+ sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_sectors(bdev));
if (sbi->log_blocks_per_blkz && sbi->log_blocks_per_blkz !=
__ilog2_u32(sbi->blocks_per_blkz))
return -EINVAL;
sbi->log_blocks_per_blkz = __ilog2_u32(sbi->blocks_per_blkz);
FDEV(devi).nr_blkz = SECTOR_TO_BLOCK(nr_sectors) >>
sbi->log_blocks_per_blkz;
- if (nr_sectors & (bdev_zone_size(bdev) - 1))
+ if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
FDEV(devi).nr_blkz++;
FDEV(devi).blkz_type = kmalloc(FDEV(devi).nr_blkz, GFP_KERNEL);
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 43040721..40d6107 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -542,6 +542,7 @@
hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) {
if (invalidate)
set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
+ clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
}
} else {
@@ -560,6 +561,10 @@
wait_on_atomic_t(&cookie->n_active, fscache_wait_atomic_t,
TASK_UNINTERRUPTIBLE);
+ /* Make sure any pending writes are cancelled. */
+ if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
+ fscache_invalidate_writes(cookie);
+
/* Reset the cookie state if it wasn't relinquished */
if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) {
atomic_inc(&cookie->n_active);
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
index 9b28649..a8aa00be 100644
--- a/fs/fscache/netfs.c
+++ b/fs/fscache/netfs.c
@@ -48,6 +48,7 @@
cookie->flags = 1 << FSCACHE_COOKIE_ENABLED;
spin_lock_init(&cookie->lock);
+ spin_lock_init(&cookie->stores_lock);
INIT_HLIST_HEAD(&cookie->backing_objects);
/* check the netfs type is not already present */
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 9e792e3..7a182c8 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -30,6 +30,7 @@
static const struct fscache_state *fscache_object_available(struct fscache_object *, int);
static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int);
static const struct fscache_state *fscache_update_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_object_dead(struct fscache_object *, int);
#define __STATE_NAME(n) fscache_osm_##n
#define STATE(n) (&__STATE_NAME(n))
@@ -91,7 +92,7 @@
static WORK_STATE(KILL_OBJECT, "KILL", fscache_kill_object);
static WORK_STATE(KILL_DEPENDENTS, "KDEP", fscache_kill_dependents);
static WORK_STATE(DROP_OBJECT, "DROP", fscache_drop_object);
-static WORK_STATE(OBJECT_DEAD, "DEAD", (void*)2UL);
+static WORK_STATE(OBJECT_DEAD, "DEAD", fscache_object_dead);
static WAIT_STATE(WAIT_FOR_INIT, "?INI",
TRANSIT_TO(INIT_OBJECT, 1 << FSCACHE_OBJECT_EV_NEW_CHILD));
@@ -229,6 +230,10 @@
event = -1;
if (new_state == NO_TRANSIT) {
_debug("{OBJ%x} %s notrans", object->debug_id, state->name);
+ if (unlikely(state == STATE(OBJECT_DEAD))) {
+ _leave(" [dead]");
+ return;
+ }
fscache_enqueue_object(object);
event_mask = object->oob_event_mask;
goto unmask_events;
@@ -239,7 +244,7 @@
object->state = state = new_state;
if (state->work) {
- if (unlikely(state->work == ((void *)2UL))) {
+ if (unlikely(state == STATE(OBJECT_DEAD))) {
_leave(" [dead]");
return;
}
@@ -645,6 +650,12 @@
fscache_mark_object_dead(object);
object->oob_event_mask = 0;
+ if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) {
+ /* Reject any new read/write ops and abort any that are pending. */
+ clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+ fscache_cancel_all_ops(object);
+ }
+
if (list_empty(&object->dependents) &&
object->n_ops == 0 &&
object->n_children == 0)
@@ -1077,3 +1088,20 @@
}
}
EXPORT_SYMBOL(fscache_object_mark_killed);
+
+/*
+ * The object is dead. We can get here if an object gets queued by an event
+ * that would lead to its death (such as EV_KILL) when the dispatcher is
+ * already running (and so can be requeued) but hasn't yet cleared the event
+ * mask.
+ */
+static const struct fscache_state *fscache_object_dead(struct fscache_object *object,
+ int event)
+{
+ if (!test_and_set_bit(FSCACHE_OBJECT_RUN_AFTER_DEAD,
+ &object->flags))
+ return NO_TRANSIT;
+
+ WARN(true, "FS-Cache object redispatched after death");
+ return NO_TRANSIT;
+}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 70ea57c..f117926 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -399,6 +399,10 @@
static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
{
spin_lock(&fiq->waitq.lock);
+ if (test_bit(FR_FINISHED, &req->flags)) {
+ spin_unlock(&fiq->waitq.lock);
+ return;
+ }
if (list_empty(&req->intr_entry)) {
list_add_tail(&req->intr_entry, &fiq->interrupts);
wake_up_locked(&fiq->waitq);
@@ -1372,6 +1376,7 @@
* code can Oops if the buffer persists after module unload.
*/
bufs[page_nr].ops = &nosteal_pipe_buf_ops;
+ bufs[page_nr].flags = 0;
ret = add_to_pipe(pipe, &bufs[page_nr++]);
if (unlikely(ret < 0))
break;
@@ -2025,7 +2030,6 @@
struct fuse_req *req;
req = list_entry(head->next, struct fuse_req, list);
req->out.h.error = -ECONNABORTED;
- clear_bit(FR_PENDING, &req->flags);
clear_bit(FR_SENT, &req->flags);
list_del_init(&req->list);
request_end(fc, req);
@@ -2103,6 +2107,8 @@
spin_lock(&fiq->waitq.lock);
fiq->connected = 0;
list_splice_init(&fiq->pending, &to_end2);
+ list_for_each_entry(req, &to_end2, list)
+ clear_bit(FR_PENDING, &req->flags);
while (forget_pending(fiq))
kfree(dequeue_forget(fiq, 1, NULL));
wake_up_all_locked(&fiq->waitq);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 1f7c732..811fd89 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -68,7 +68,7 @@
if (sec || nsec) {
struct timespec64 ts = {
sec,
- max_t(u32, nsec, NSEC_PER_SEC - 1)
+ min_t(u32, nsec, NSEC_PER_SEC - 1)
};
return get_jiffies_64() + timespec64_to_jiffies(&ts);
diff --git a/fs/iomap.c b/fs/iomap.c
index 354a123..a51cb4c 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -114,6 +114,9 @@
BUG_ON(pos + len > iomap->offset + iomap->length);
+ if (fatal_signal_pending(current))
+ return -EINTR;
+
page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
if (!page)
return -ENOMEM;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8c51436..b6b194e 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -393,7 +393,7 @@
/* Do we need to erase the effects of a prior jbd2_journal_flush? */
if (journal->j_flags & JBD2_FLUSHED) {
jbd_debug(3, "super block updated\n");
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
/*
* We hold j_checkpoint_mutex so tail cannot change under us.
* We don't need any special data guarantees for writing sb
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a097048..d8a5d0a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -944,7 +944,7 @@
*/
void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
{
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
if (tid_gt(tid, journal->j_tail_sequence))
__jbd2_update_log_tail(journal, tid, block);
mutex_unlock(&journal->j_checkpoint_mutex);
@@ -1304,7 +1304,7 @@
journal->j_flags |= JBD2_FLUSHED;
} else {
/* Lock here to make assertions happy... */
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
/*
* Update log tail information. We use REQ_FUA since new
* transaction will start reusing journal space and so we
@@ -1691,7 +1691,7 @@
spin_lock(&journal->j_list_lock);
while (journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
err = jbd2_log_do_checkpoint(journal);
mutex_unlock(&journal->j_checkpoint_mutex);
/*
@@ -1713,7 +1713,7 @@
if (journal->j_sb_buffer) {
if (!is_journal_aborted(journal)) {
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
write_lock(&journal->j_state_lock);
journal->j_tail_sequence =
@@ -1955,7 +1955,7 @@
spin_lock(&journal->j_list_lock);
while (!err && journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
err = jbd2_log_do_checkpoint(journal);
mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_list_lock);
@@ -1965,7 +1965,7 @@
if (is_journal_aborted(journal))
return -EIO;
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
if (!err) {
err = jbd2_cleanup_journal_tail(journal);
if (err < 0) {
diff --git a/fs/libfs.c b/fs/libfs.c
index e973cd5..28d6f35 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -245,7 +245,8 @@
struct inode *root;
struct qstr d_name = QSTR_INIT(name, strlen(name));
- s = sget(fs_type, NULL, set_anon_super, MS_NOUSER, NULL);
+ s = sget_userns(fs_type, NULL, set_anon_super, MS_KERNMOUNT|MS_NOUSER,
+ &init_user_ns, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
diff --git a/fs/namespace.c b/fs/namespace.c
index b5b1259..487ba30 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -742,26 +742,50 @@
return NULL;
}
-static struct mountpoint *new_mountpoint(struct dentry *dentry)
+static struct mountpoint *get_mountpoint(struct dentry *dentry)
{
- struct hlist_head *chain = mp_hash(dentry);
- struct mountpoint *mp;
+ struct mountpoint *mp, *new = NULL;
int ret;
- mp = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
- if (!mp)
- return ERR_PTR(-ENOMEM);
-
- ret = d_set_mounted(dentry);
- if (ret) {
- kfree(mp);
- return ERR_PTR(ret);
+ if (d_mountpoint(dentry)) {
+mountpoint:
+ read_seqlock_excl(&mount_lock);
+ mp = lookup_mountpoint(dentry);
+ read_sequnlock_excl(&mount_lock);
+ if (mp)
+ goto done;
}
- mp->m_dentry = dentry;
- mp->m_count = 1;
- hlist_add_head(&mp->m_hash, chain);
- INIT_HLIST_HEAD(&mp->m_list);
+ if (!new)
+ new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
+ if (!new)
+ return ERR_PTR(-ENOMEM);
+
+
+ /* Exactly one processes may set d_mounted */
+ ret = d_set_mounted(dentry);
+
+ /* Someone else set d_mounted? */
+ if (ret == -EBUSY)
+ goto mountpoint;
+
+ /* The dentry is not available as a mountpoint? */
+ mp = ERR_PTR(ret);
+ if (ret)
+ goto done;
+
+ /* Add the new mountpoint to the hash table */
+ read_seqlock_excl(&mount_lock);
+ new->m_dentry = dentry;
+ new->m_count = 1;
+ hlist_add_head(&new->m_hash, mp_hash(dentry));
+ INIT_HLIST_HEAD(&new->m_list);
+ read_sequnlock_excl(&mount_lock);
+
+ mp = new;
+ new = NULL;
+done:
+ kfree(new);
return mp;
}
@@ -1595,11 +1619,11 @@
struct mount *mnt;
namespace_lock();
+ lock_mount_hash();
mp = lookup_mountpoint(dentry);
if (IS_ERR_OR_NULL(mp))
goto out_unlock;
- lock_mount_hash();
event++;
while (!hlist_empty(&mp->m_list)) {
mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
@@ -1609,9 +1633,9 @@
}
else umount_tree(mnt, UMOUNT_CONNECTED);
}
- unlock_mount_hash();
put_mountpoint(mp);
out_unlock:
+ unlock_mount_hash();
namespace_unlock();
}
@@ -2038,9 +2062,7 @@
namespace_lock();
mnt = lookup_mnt(path);
if (likely(!mnt)) {
- struct mountpoint *mp = lookup_mountpoint(dentry);
- if (!mp)
- mp = new_mountpoint(dentry);
+ struct mountpoint *mp = get_mountpoint(dentry);
if (IS_ERR(mp)) {
namespace_unlock();
inode_unlock(dentry->d_inode);
@@ -2059,7 +2081,11 @@
static void unlock_mount(struct mountpoint *where)
{
struct dentry *dentry = where->m_dentry;
+
+ read_seqlock_excl(&mount_lock);
put_mountpoint(where);
+ read_sequnlock_excl(&mount_lock);
+
namespace_unlock();
inode_unlock(dentry->d_inode);
}
@@ -3135,9 +3161,9 @@
touch_mnt_namespace(current->nsproxy->mnt_ns);
/* A moved mount should not expire automatically */
list_del_init(&new_mnt->mnt_expire);
+ put_mountpoint(root_mp);
unlock_mount_hash();
chroot_fs_refs(&root, &new);
- put_mountpoint(root_mp);
error = 0;
out4:
unlock_mount(old_mp);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6dcbc5d..0a0eaec 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -38,7 +38,6 @@
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/errno.h>
-#include <linux/file.h>
#include <linux/string.h>
#include <linux/ratelimit.h>
#include <linux/printk.h>
@@ -1083,7 +1082,8 @@
return nfs4_call_sync_sequence(clnt, server, msg, args, res);
}
-static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
+static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo,
+ unsigned long timestamp)
{
struct nfs_inode *nfsi = NFS_I(dir);
@@ -1099,6 +1099,7 @@
NFS_INO_INVALID_ACL;
}
dir->i_version = cinfo->after;
+ nfsi->read_cache_jiffies = timestamp;
nfsi->attr_gencount = nfs_inc_attr_generation_counter();
nfs_fscache_invalidate(dir);
spin_unlock(&dir->i_lock);
@@ -2391,11 +2392,13 @@
nfs_fattr_map_and_free_names(server, &data->f_attr);
if (o_arg->open_flags & O_CREAT) {
- update_changeattr(dir, &o_res->cinfo);
if (o_arg->open_flags & O_EXCL)
data->file_created = 1;
else if (o_res->cinfo.before != o_res->cinfo.after)
data->file_created = 1;
+ if (data->file_created || dir->i_version != o_res->cinfo.after)
+ update_changeattr(dir, &o_res->cinfo,
+ o_res->f_attr->time_start);
}
if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0)
server->caps &= ~NFS_CAP_POSIX_LOCK;
@@ -2697,7 +2700,8 @@
sattr->ia_valid |= ATTR_MTIME;
/* Except MODE, it seems harmless of setting twice. */
- if ((attrset[1] & FATTR4_WORD1_MODE))
+ if (opendata->o_arg.createmode != NFS4_CREATE_EXCLUSIVE &&
+ attrset[1] & FATTR4_WORD1_MODE)
sattr->ia_valid &= ~ATTR_MODE;
if (attrset[2] & FATTR4_WORD2_SECURITY_LABEL)
@@ -4073,11 +4077,12 @@
.rpc_argp = &args,
.rpc_resp = &res,
};
+ unsigned long timestamp = jiffies;
int status;
status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
if (status == 0)
- update_changeattr(dir, &res.cinfo);
+ update_changeattr(dir, &res.cinfo, timestamp);
return status;
}
@@ -4125,7 +4130,8 @@
if (nfs4_async_handle_error(task, res->server, NULL,
&data->timeout) == -EAGAIN)
return 0;
- update_changeattr(dir, &res->cinfo);
+ if (task->tk_status == 0)
+ update_changeattr(dir, &res->cinfo, res->dir_attr->time_start);
return 1;
}
@@ -4159,8 +4165,11 @@
if (nfs4_async_handle_error(task, res->server, NULL, &data->timeout) == -EAGAIN)
return 0;
- update_changeattr(old_dir, &res->old_cinfo);
- update_changeattr(new_dir, &res->new_cinfo);
+ if (task->tk_status == 0) {
+ update_changeattr(old_dir, &res->old_cinfo, res->old_fattr->time_start);
+ if (new_dir != old_dir)
+ update_changeattr(new_dir, &res->new_cinfo, res->new_fattr->time_start);
+ }
return 1;
}
@@ -4197,7 +4206,7 @@
status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
if (!status) {
- update_changeattr(dir, &res.cinfo);
+ update_changeattr(dir, &res.cinfo, res.fattr->time_start);
status = nfs_post_op_update_inode(inode, res.fattr);
if (!status)
nfs_setsecurity(inode, res.fattr, res.label);
@@ -4272,7 +4281,8 @@
int status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg,
&data->arg.seq_args, &data->res.seq_res, 1);
if (status == 0) {
- update_changeattr(dir, &data->res.dir_cinfo);
+ update_changeattr(dir, &data->res.dir_cinfo,
+ data->res.fattr->time_start);
status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.label);
}
return status;
@@ -6127,7 +6137,6 @@
p->server = server;
atomic_inc(&lsp->ls_count);
p->ctx = get_nfs_open_context(ctx);
- get_file(fl->fl_file);
memcpy(&p->fl, fl, sizeof(p->fl));
return p;
out_free_seqid:
@@ -6240,7 +6249,6 @@
nfs_free_seqid(data->arg.lock_seqid);
nfs4_put_lock_state(data->lsp);
put_nfs_open_context(data->ctx);
- fput(data->fl.fl_file);
kfree(data);
dprintk("%s: done!\n", __func__);
}
@@ -8483,6 +8491,7 @@
goto out;
}
+ nfs4_sequence_free_slot(&lgp->res.seq_res);
err = nfs4_handle_exception(server, nfs4err, exception);
if (!status) {
if (exception->retry)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 1d152f4..daeb94e 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1091,6 +1091,7 @@
case -NFS4ERR_BADXDR:
case -NFS4ERR_RESOURCE:
case -NFS4ERR_NOFILEHANDLE:
+ case -NFS4ERR_MOVED:
/* Non-seqid mutating errors */
return;
};
@@ -1729,7 +1730,6 @@
break;
case -NFS4ERR_STALE_CLIENTID:
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
- nfs4_state_clear_reclaim_reboot(clp);
nfs4_state_start_reclaim_reboot(clp);
break;
case -NFS4ERR_EXPIRED:
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 59554f3..dd04249 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1200,10 +1200,10 @@
send = pnfs_prepare_layoutreturn(lo, &stateid, NULL);
spin_unlock(&ino->i_lock);
- pnfs_free_lseg_list(&tmp_list);
if (send)
status = pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true);
out_put_layout_hdr:
+ pnfs_free_lseg_list(&tmp_list);
pnfs_put_layout_hdr(lo);
out:
dprintk("<-- %s status: %d\n", __func__, status);
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 596205d..1fc07a9 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -223,10 +223,11 @@
struct nfs4_layout_stateid *ls;
struct nfs4_stid *stp;
- stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache);
+ stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache,
+ nfsd4_free_layout_stateid);
if (!stp)
return NULL;
- stp->sc_free = nfsd4_free_layout_stateid;
+
get_nfs4_file(fp);
stp->sc_file = fp;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4b4beaa..a0dee8a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -633,8 +633,8 @@
return co;
}
-struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
- struct kmem_cache *slab)
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
+ void (*sc_free)(struct nfs4_stid *))
{
struct nfs4_stid *stid;
int new_id;
@@ -650,6 +650,8 @@
idr_preload_end();
if (new_id < 0)
goto out_free;
+
+ stid->sc_free = sc_free;
stid->sc_client = cl;
stid->sc_stateid.si_opaque.so_id = new_id;
stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
@@ -675,15 +677,12 @@
static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
{
struct nfs4_stid *stid;
- struct nfs4_ol_stateid *stp;
- stid = nfs4_alloc_stid(clp, stateid_slab);
+ stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid);
if (!stid)
return NULL;
- stp = openlockstateid(stid);
- stp->st_stid.sc_free = nfs4_free_ol_stateid;
- return stp;
+ return openlockstateid(stid);
}
static void nfs4_free_deleg(struct nfs4_stid *stid)
@@ -781,11 +780,10 @@
goto out_dec;
if (delegation_blocked(¤t_fh->fh_handle))
goto out_dec;
- dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
+ dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg));
if (dp == NULL)
goto out_dec;
- dp->dl_stid.sc_free = nfs4_free_deleg;
/*
* delegation seqid's are never incremented. The 4.1 special
* meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -5580,7 +5578,6 @@
stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
get_nfs4_file(fp);
stp->st_stid.sc_file = fp;
- stp->st_stid.sc_free = nfs4_free_lock_stateid;
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
@@ -5623,7 +5620,7 @@
lst = find_lock_stateid(lo, fi);
if (lst == NULL) {
spin_unlock(&clp->cl_lock);
- ns = nfs4_alloc_stid(clp, stateid_slab);
+ ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
if (ns == NULL)
return NULL;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 7ecf16b..8fae53c 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2440,7 +2440,9 @@
p++; /* to be backfilled later */
if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
- u32 *supp = nfsd_suppattrs[minorversion];
+ u32 supp[3];
+
+ memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp));
if (!IS_POSIXACL(dentry->d_inode))
supp[0] &= ~FATTR4_WORD0_ACL;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index c939936..4516e8b 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -603,8 +603,8 @@
__be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
stateid_t *stateid, unsigned char typemask,
struct nfs4_stid **s, struct nfsd_net *nn);
-struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
- struct kmem_cache *slab);
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
+ void (*sc_free)(struct nfs4_stid *));
void nfs4_unhash_stid(struct nfs4_stid *s);
void nfs4_put_stid(struct nfs4_stid *s);
void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 9ad48d9..023bb0b 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -154,29 +154,38 @@
static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
struct dentry **ret)
{
- const char *s = d->name.name;
+ /* Counting down from the end, since the prefix can change */
+ size_t rem = d->name.len - 1;
struct dentry *dentry = NULL;
int err;
- if (*s != '/')
+ if (d->name.name[0] != '/')
return ovl_lookup_single(base, d, d->name.name, d->name.len,
0, "", ret);
- while (*s++ == '/' && !IS_ERR_OR_NULL(base) && d_can_lookup(base)) {
+ while (!IS_ERR_OR_NULL(base) && d_can_lookup(base)) {
+ const char *s = d->name.name + d->name.len - rem;
const char *next = strchrnul(s, '/');
- size_t slen = strlen(s);
+ size_t thislen = next - s;
+ bool end = !next[0];
- if (WARN_ON(slen > d->name.len) ||
- WARN_ON(strcmp(d->name.name + d->name.len - slen, s)))
+ /* Verify we did not go off the rails */
+ if (WARN_ON(s[-1] != '/'))
return -EIO;
- err = ovl_lookup_single(base, d, s, next - s,
- d->name.len - slen, next, &base);
+ err = ovl_lookup_single(base, d, s, thislen,
+ d->name.len - rem, next, &base);
dput(dentry);
if (err)
return err;
dentry = base;
- s = next;
+ if (end)
+ break;
+
+ rem -= thislen + 1;
+
+ if (WARN_ON(rem >= d->name.len))
+ return -EIO;
}
*ret = dentry;
return 0;
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 5955220..c9d48dc 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -922,11 +922,10 @@
int error;
if (type == ACL_TYPE_ACCESS) {
- error = posix_acl_equiv_mode(acl, &inode->i_mode);
- if (error < 0)
- return 0;
- if (error == 0)
- acl = NULL;
+ error = posix_acl_update_mode(inode,
+ &inode->i_mode, &acl);
+ if (error)
+ return error;
}
inode->i_ctime = current_time(inode);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 51a4213..fe12b51 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -401,8 +401,8 @@
unsigned long long start_time;
unsigned long cmin_flt = 0, cmaj_flt = 0;
unsigned long min_flt = 0, maj_flt = 0;
- cputime_t cutime, cstime, utime, stime;
- cputime_t cgtime, gtime;
+ u64 cutime, cstime, utime, stime;
+ u64 cgtime, gtime;
unsigned long rsslim = 0;
char tcomm[sizeof(task->comm)];
unsigned long flags;
@@ -497,10 +497,10 @@
seq_put_decimal_ull(m, " ", cmin_flt);
seq_put_decimal_ull(m, " ", maj_flt);
seq_put_decimal_ull(m, " ", cmaj_flt);
- seq_put_decimal_ull(m, " ", cputime_to_clock_t(utime));
- seq_put_decimal_ull(m, " ", cputime_to_clock_t(stime));
- seq_put_decimal_ll(m, " ", cputime_to_clock_t(cutime));
- seq_put_decimal_ll(m, " ", cputime_to_clock_t(cstime));
+ seq_put_decimal_ull(m, " ", nsec_to_clock_t(utime));
+ seq_put_decimal_ull(m, " ", nsec_to_clock_t(stime));
+ seq_put_decimal_ll(m, " ", nsec_to_clock_t(cutime));
+ seq_put_decimal_ll(m, " ", nsec_to_clock_t(cstime));
seq_put_decimal_ll(m, " ", priority);
seq_put_decimal_ll(m, " ", nice);
seq_put_decimal_ll(m, " ", num_threads);
@@ -542,8 +542,8 @@
seq_put_decimal_ull(m, " ", task->rt_priority);
seq_put_decimal_ull(m, " ", task->policy);
seq_put_decimal_ull(m, " ", delayacct_blkio_ticks(task));
- seq_put_decimal_ull(m, " ", cputime_to_clock_t(gtime));
- seq_put_decimal_ll(m, " ", cputime_to_clock_t(cgtime));
+ seq_put_decimal_ull(m, " ", nsec_to_clock_t(gtime));
+ seq_put_decimal_ll(m, " ", nsec_to_clock_t(cgtime));
if (mm && permitted) {
seq_put_decimal_ull(m, " ", mm->start_data);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 8e7e61b..b1f7d30 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2179,7 +2179,7 @@
.llseek = generic_file_llseek,
};
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS)
struct timers_private {
struct pid *pid;
struct task_struct *task;
@@ -2936,7 +2936,7 @@
REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations),
#endif
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS)
REG("timers", S_IRUGO, proc_timers_operations),
#endif
REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations),
@@ -3179,6 +3179,8 @@
iter.tgid += 1, iter = next_tgid(ns, iter)) {
char name[PROC_NUMBUF];
int len;
+
+ cond_resched();
if (!has_pid_permissions(ns, iter.task, 2))
continue;
diff --git a/fs/proc/page.c b/fs/proc/page.c
index a2066e6..2726536 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -173,7 +173,8 @@
u |= kpf_copy_bit(k, KPF_ACTIVE, PG_active);
u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim);
- u |= kpf_copy_bit(k, KPF_SWAPCACHE, PG_swapcache);
+ if (PageSwapCache(page))
+ u |= 1 << KPF_SWAPCACHE;
u |= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked);
u |= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 55313d9..d4e37ac 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -709,7 +709,7 @@
ctl_dir = container_of(head, struct ctl_dir, header);
if (!dir_emit_dots(file, ctx))
- return 0;
+ goto out;
pos = 2;
@@ -719,6 +719,7 @@
break;
}
}
+out:
sysctl_head_finish(head);
return 0;
}
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index d700c42..e47c3e8 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -21,9 +21,9 @@
#ifdef arch_idle_time
-static cputime64_t get_idle_time(int cpu)
+static u64 get_idle_time(int cpu)
{
- cputime64_t idle;
+ u64 idle;
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
@@ -31,9 +31,9 @@
return idle;
}
-static cputime64_t get_iowait_time(int cpu)
+static u64 get_iowait_time(int cpu)
{
- cputime64_t iowait;
+ u64 iowait;
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
if (cpu_online(cpu) && nr_iowait_cpu(cpu))
@@ -45,32 +45,32 @@
static u64 get_idle_time(int cpu)
{
- u64 idle, idle_time = -1ULL;
+ u64 idle, idle_usecs = -1ULL;
if (cpu_online(cpu))
- idle_time = get_cpu_idle_time_us(cpu, NULL);
+ idle_usecs = get_cpu_idle_time_us(cpu, NULL);
- if (idle_time == -1ULL)
+ if (idle_usecs == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
else
- idle = usecs_to_cputime64(idle_time);
+ idle = idle_usecs * NSEC_PER_USEC;
return idle;
}
static u64 get_iowait_time(int cpu)
{
- u64 iowait, iowait_time = -1ULL;
+ u64 iowait, iowait_usecs = -1ULL;
if (cpu_online(cpu))
- iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+ iowait_usecs = get_cpu_iowait_time_us(cpu, NULL);
- if (iowait_time == -1ULL)
+ if (iowait_usecs == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
else
- iowait = usecs_to_cputime64(iowait_time);
+ iowait = iowait_usecs * NSEC_PER_USEC;
return iowait;
}
@@ -115,16 +115,16 @@
}
sum += arch_irq_stat();
- seq_put_decimal_ull(p, "cpu ", cputime64_to_clock_t(user));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice));
+ seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(user));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
seq_putc(p, '\n');
for_each_online_cpu(i) {
@@ -140,16 +140,16 @@
guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
seq_printf(p, "cpu%d", i);
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(user));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest));
- seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+ seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
seq_putc(p, '\n');
}
seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 33de567..7981c4f 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -5,23 +5,20 @@
#include <linux/seq_file.h>
#include <linux/time.h>
#include <linux/kernel_stat.h>
-#include <linux/cputime.h>
static int uptime_proc_show(struct seq_file *m, void *v)
{
struct timespec uptime;
struct timespec idle;
- u64 idletime;
u64 nsec;
u32 rem;
int i;
- idletime = 0;
+ nsec = 0;
for_each_possible_cpu(i)
- idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
+ nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
get_monotonic_boottime(&uptime);
- nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC;
idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
idle.tv_nsec = rem;
seq_printf(m, "%lu.%02lu %lu.%02lu\n",
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 27c059e..1d887ef 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -280,7 +280,7 @@
1, id, type, PSTORE_TYPE_PMSG, 0);
/* ftrace is last since it may want to dynamically allocate memory. */
- if (!prz_ok(prz)) {
+ if (!prz_ok(prz) && cxt->fprzs) {
if (!(cxt->flags & RAMOOPS_FLAG_FTRACE_PER_CPU)) {
prz = ramoops_get_next_prz(cxt->fprzs,
&cxt->ftrace_read_cnt, 1, id, type,
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index d0f8a38..0186fe6 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -74,6 +74,7 @@
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/uaccess.h>
+#include <linux/major.h>
#include "internal.h"
static struct kmem_cache *romfs_inode_cachep;
@@ -416,7 +417,22 @@
static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
- u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+ u64 id = 0;
+
+ /* When calling huge_encode_dev(),
+ * use sb->s_bdev->bd_dev when,
+ * - CONFIG_ROMFS_ON_BLOCK defined
+ * use sb->s_dev when,
+ * - CONFIG_ROMFS_ON_BLOCK undefined and
+ * - CONFIG_ROMFS_ON_MTD defined
+ * leave id as 0 when,
+ * - CONFIG_ROMFS_ON_BLOCK undefined and
+ * - CONFIG_ROMFS_ON_MTD undefined
+ */
+ if (sb->s_bdev)
+ id = huge_encode_dev(sb->s_bdev->bd_dev);
+ else if (sb->s_dev)
+ id = huge_encode_dev(sb->s_dev);
buf->f_type = ROMFS_MAGIC;
buf->f_namelen = ROMFS_MAXFN;
@@ -489,6 +505,11 @@
sb->s_flags |= MS_RDONLY | MS_NOATIME;
sb->s_op = &romfs_super_ops;
+#ifdef CONFIG_ROMFS_ON_MTD
+ /* Use same dev ID from the underlying mtdblock device */
+ if (sb->s_mtd)
+ sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index);
+#endif
/* read the image superblock and check it */
rsb = kmalloc(512, GFP_KERNEL);
if (!rsb)
diff --git a/fs/splice.c b/fs/splice.c
index 873d831..4ef78aa 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -204,6 +204,7 @@
buf->len = spd->partial[page_nr].len;
buf->private = spd->partial[page_nr].private;
buf->ops = spd->ops;
+ buf->flags = 0;
pipe->nrbufs++;
page_nr++;
diff --git a/fs/timerfd.c b/fs/timerfd.c
index c173cc1..384fa75 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -40,6 +40,7 @@
short unsigned settime_flags; /* to show in fdinfo */
struct rcu_head rcu;
struct list_head clist;
+ spinlock_t cancel_lock;
bool might_cancel;
};
@@ -112,7 +113,7 @@
rcu_read_unlock();
}
-static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+static void __timerfd_remove_cancel(struct timerfd_ctx *ctx)
{
if (ctx->might_cancel) {
ctx->might_cancel = false;
@@ -122,6 +123,13 @@
}
}
+static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+{
+ spin_lock(&ctx->cancel_lock);
+ __timerfd_remove_cancel(ctx);
+ spin_unlock(&ctx->cancel_lock);
+}
+
static bool timerfd_canceled(struct timerfd_ctx *ctx)
{
if (!ctx->might_cancel || ctx->moffs != KTIME_MAX)
@@ -132,6 +140,7 @@
static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
{
+ spin_lock(&ctx->cancel_lock);
if ((ctx->clockid == CLOCK_REALTIME ||
ctx->clockid == CLOCK_REALTIME_ALARM) &&
(flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) {
@@ -141,9 +150,10 @@
list_add_rcu(&ctx->clist, &cancel_list);
spin_unlock(&cancel_lock);
}
- } else if (ctx->might_cancel) {
- timerfd_remove_cancel(ctx);
+ } else {
+ __timerfd_remove_cancel(ctx);
}
+ spin_unlock(&ctx->cancel_lock);
}
static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
@@ -400,6 +410,7 @@
return -ENOMEM;
init_waitqueue_head(&ctx->wqh);
+ spin_lock_init(&ctx->cancel_lock);
ctx->clockid = clockid;
if (isalarm(ctx))
diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig
index 0a908ae..b0d0623 100644
--- a/fs/ubifs/Kconfig
+++ b/fs/ubifs/Kconfig
@@ -53,7 +53,7 @@
config UBIFS_FS_ENCRYPTION
bool "UBIFS Encryption"
- depends on UBIFS_FS
+ depends on UBIFS_FS && BLOCK
select FS_ENCRYPTION
default n
help
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 1c5331a..528369f 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -390,16 +390,6 @@
dbg_gen("dent '%pd', mode %#hx in dir ino %lu",
dentry, mode, dir->i_ino);
- if (ubifs_crypt_is_encrypted(dir)) {
- err = fscrypt_get_encryption_info(dir);
- if (err)
- return err;
-
- if (!fscrypt_has_encryption_key(dir)) {
- return -EPERM;
- }
- }
-
err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
if (err)
return err;
@@ -741,17 +731,9 @@
ubifs_assert(inode_is_locked(dir));
ubifs_assert(inode_is_locked(inode));
- if (ubifs_crypt_is_encrypted(dir)) {
- if (!fscrypt_has_permitted_context(dir, inode))
- return -EPERM;
-
- err = fscrypt_get_encryption_info(inode);
- if (err)
- return err;
-
- if (!fscrypt_has_encryption_key(inode))
- return -EPERM;
- }
+ if (ubifs_crypt_is_encrypted(dir) &&
+ !fscrypt_has_permitted_context(dir, inode))
+ return -EPERM;
err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
if (err)
@@ -1000,17 +982,6 @@
if (err)
return err;
- if (ubifs_crypt_is_encrypted(dir)) {
- err = fscrypt_get_encryption_info(dir);
- if (err)
- goto out_budg;
-
- if (!fscrypt_has_encryption_key(dir)) {
- err = -EPERM;
- goto out_budg;
- }
- }
-
err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
if (err)
goto out_budg;
@@ -1096,17 +1067,6 @@
return err;
}
- if (ubifs_crypt_is_encrypted(dir)) {
- err = fscrypt_get_encryption_info(dir);
- if (err)
- goto out_budg;
-
- if (!fscrypt_has_encryption_key(dir)) {
- err = -EPERM;
- goto out_budg;
- }
- }
-
err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
if (err)
goto out_budg;
@@ -1231,18 +1191,6 @@
goto out_inode;
}
- err = fscrypt_get_encryption_info(inode);
- if (err) {
- kfree(sd);
- goto out_inode;
- }
-
- if (!fscrypt_has_encryption_key(inode)) {
- kfree(sd);
- err = -EPERM;
- goto out_inode;
- }
-
ostr.name = sd->encrypted_path;
ostr.len = disk_link.len;
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 78d7136..da519ba 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -217,6 +217,9 @@
case FS_IOC32_SETFLAGS:
cmd = FS_IOC_SETFLAGS;
break;
+ case FS_IOC_SET_ENCRYPTION_POLICY:
+ case FS_IOC_GET_ENCRYPTION_POLICY:
+ break;
default:
return -ENOIOCTLCMD;
}
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index a459211..294519b 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -744,6 +744,7 @@
} else {
data->compr_size = 0;
+ out_len = compr_len;
}
dlen = UBIFS_DATA_NODE_SZ + out_len;
@@ -1319,6 +1320,7 @@
dn->compr_type = cpu_to_le16(compr_type);
dn->size = cpu_to_le32(*new_len);
*new_len = UBIFS_DATA_NODE_SZ + out_len;
+ err = 0;
out:
kfree(buf);
return err;
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 74ae2de..709aa09 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -34,6 +34,11 @@
#include <linux/slab.h>
#include "ubifs.h"
+static int try_read_node(const struct ubifs_info *c, void *buf, int type,
+ int len, int lnum, int offs);
+static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key,
+ struct ubifs_zbranch *zbr, void *node);
+
/*
* Returned codes of 'matches_name()' and 'fallible_matches_name()' functions.
* @NAME_LESS: name corresponding to the first argument is less than second
@@ -402,7 +407,19 @@
return 0;
}
- err = ubifs_tnc_read_node(c, zbr, node);
+ if (c->replaying) {
+ err = fallible_read_node(c, &zbr->key, zbr, node);
+ /*
+ * When the node was not found, return -ENOENT, 0 otherwise.
+ * Negative return codes stay as-is.
+ */
+ if (err == 0)
+ err = -ENOENT;
+ else if (err == 1)
+ err = 0;
+ } else {
+ err = ubifs_tnc_read_node(c, zbr, node);
+ }
if (err)
return err;
@@ -2857,7 +2874,11 @@
if (fname_len(nm) > 0) {
if (err) {
/* Handle collisions */
- err = resolve_collision(c, key, &znode, &n, nm);
+ if (c->replaying)
+ err = fallible_resolve_collision(c, key, &znode, &n,
+ nm, 0);
+ else
+ err = resolve_collision(c, key, &znode, &n, nm);
dbg_tnc("rc returned %d, znode %p, n %d",
err, znode, n);
if (unlikely(err < 0))
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index d96e2f3..43953e0 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -63,6 +63,7 @@
struct uffd_msg msg;
wait_queue_t wq;
struct userfaultfd_ctx *ctx;
+ bool waken;
};
struct userfaultfd_wake_range {
@@ -86,6 +87,12 @@
if (len && (start > uwq->msg.arg.pagefault.address ||
start + len <= uwq->msg.arg.pagefault.address))
goto out;
+ WRITE_ONCE(uwq->waken, true);
+ /*
+ * The implicit smp_mb__before_spinlock in try_to_wake_up()
+ * renders uwq->waken visible to other CPUs before the task is
+ * waken.
+ */
ret = wake_up_state(wq->private, mode);
if (ret)
/*
@@ -264,6 +271,7 @@
struct userfaultfd_wait_queue uwq;
int ret;
bool must_wait, return_to_userland;
+ long blocking_state;
BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
@@ -334,10 +342,13 @@
uwq.wq.private = current;
uwq.msg = userfault_msg(vmf->address, vmf->flags, reason);
uwq.ctx = ctx;
+ uwq.waken = false;
return_to_userland =
(vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
+ blocking_state = return_to_userland ? TASK_INTERRUPTIBLE :
+ TASK_KILLABLE;
spin_lock(&ctx->fault_pending_wqh.lock);
/*
@@ -350,8 +361,7 @@
* following the spin_unlock to happen before the list_add in
* __add_wait_queue.
*/
- set_current_state(return_to_userland ? TASK_INTERRUPTIBLE :
- TASK_KILLABLE);
+ set_current_state(blocking_state);
spin_unlock(&ctx->fault_pending_wqh.lock);
must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
@@ -364,6 +374,29 @@
wake_up_poll(&ctx->fd_wqh, POLLIN);
schedule();
ret |= VM_FAULT_MAJOR;
+
+ /*
+ * False wakeups can orginate even from rwsem before
+ * up_read() however userfaults will wait either for a
+ * targeted wakeup on the specific uwq waitqueue from
+ * wake_userfault() or for signals or for uffd
+ * release.
+ */
+ while (!READ_ONCE(uwq.waken)) {
+ /*
+ * This needs the full smp_store_mb()
+ * guarantee as the state write must be
+ * visible to other CPUs before reading
+ * uwq.waken from other CPUs.
+ */
+ set_current_state(blocking_state);
+ if (READ_ONCE(uwq.waken) ||
+ READ_ONCE(ctx->released) ||
+ (return_to_userland ? signal_pending(current) :
+ fatal_signal_pending(current)))
+ break;
+ schedule();
+ }
}
__set_current_state(TASK_RUNNING);
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index d346d42..33db69b 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -39,6 +39,7 @@
#include "xfs_rmap_btree.h"
#include "xfs_btree.h"
#include "xfs_refcount_btree.h"
+#include "xfs_ialloc_btree.h"
/*
* Per-AG Block Reservations
@@ -200,22 +201,30 @@
struct xfs_mount *mp = pag->pag_mount;
struct xfs_ag_resv *resv;
int error;
+ xfs_extlen_t reserved;
- resv = xfs_perag_resv(pag, type);
if (used > ask)
ask = used;
- resv->ar_asked = ask;
- resv->ar_reserved = resv->ar_orig_reserved = ask - used;
- mp->m_ag_max_usable -= ask;
+ reserved = ask - used;
- trace_xfs_ag_resv_init(pag, type, ask);
-
- error = xfs_mod_fdblocks(mp, -(int64_t)resv->ar_reserved, true);
- if (error)
+ error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
+ if (error) {
trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
error, _RET_IP_);
+ xfs_warn(mp,
+"Per-AG reservation for AG %u failed. Filesystem may run out of space.",
+ pag->pag_agno);
+ return error;
+ }
- return error;
+ mp->m_ag_max_usable -= ask;
+
+ resv = xfs_perag_resv(pag, type);
+ resv->ar_asked = ask;
+ resv->ar_reserved = resv->ar_orig_reserved = reserved;
+
+ trace_xfs_ag_resv_init(pag, type, ask);
+ return 0;
}
/* Create a per-AG block reservation. */
@@ -223,6 +232,8 @@
xfs_ag_resv_init(
struct xfs_perag *pag)
{
+ struct xfs_mount *mp = pag->pag_mount;
+ xfs_agnumber_t agno = pag->pag_agno;
xfs_extlen_t ask;
xfs_extlen_t used;
int error = 0;
@@ -231,23 +242,45 @@
if (pag->pag_meta_resv.ar_asked == 0) {
ask = used = 0;
- error = xfs_refcountbt_calc_reserves(pag->pag_mount,
- pag->pag_agno, &ask, &used);
+ error = xfs_refcountbt_calc_reserves(mp, agno, &ask, &used);
+ if (error)
+ goto out;
+
+ error = xfs_finobt_calc_reserves(mp, agno, &ask, &used);
if (error)
goto out;
error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
ask, used);
- if (error)
- goto out;
+ if (error) {
+ /*
+ * Because we didn't have per-AG reservations when the
+ * finobt feature was added we might not be able to
+ * reserve all needed blocks. Warn and fall back to the
+ * old and potentially buggy code in that case, but
+ * ensure we do have the reservation for the refcountbt.
+ */
+ ask = used = 0;
+
+ mp->m_inotbt_nores = true;
+
+ error = xfs_refcountbt_calc_reserves(mp, agno, &ask,
+ &used);
+ if (error)
+ goto out;
+
+ error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
+ ask, used);
+ if (error)
+ goto out;
+ }
}
/* Create the AGFL metadata reservation */
if (pag->pag_agfl_resv.ar_asked == 0) {
ask = used = 0;
- error = xfs_rmapbt_calc_reserves(pag->pag_mount, pag->pag_agno,
- &ask, &used);
+ error = xfs_rmapbt_calc_reserves(mp, agno, &ask, &used);
if (error)
goto out;
@@ -256,9 +289,16 @@
goto out;
}
+#ifdef DEBUG
+ /* need to read in the AGF for the ASSERT below to work */
+ error = xfs_alloc_pagf_init(pag->pag_mount, NULL, pag->pag_agno, 0);
+ if (error)
+ return error;
+
ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
xfs_perag_resv(pag, XFS_AG_RESV_AGFL)->ar_reserved <=
pag->pagf_freeblks + pag->pagf_flcount);
+#endif
out:
return error;
}
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 5050056..9f06a21 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -95,10 +95,7 @@
xfs_alloc_set_aside(
struct xfs_mount *mp)
{
- unsigned int blocks;
-
- blocks = 4 + (mp->m_sb.sb_agcount * XFS_ALLOC_AGFL_RESERVE);
- return blocks;
+ return mp->m_sb.sb_agcount * (XFS_ALLOC_AGFL_RESERVE + 4);
}
/*
@@ -365,36 +362,12 @@
return;
ASSERT(rlen >= args->minlen && rlen <= args->maxlen);
ASSERT(rlen % args->prod == args->mod);
+ ASSERT(args->pag->pagf_freeblks + args->pag->pagf_flcount >=
+ rlen + args->minleft);
args->len = rlen;
}
/*
- * Fix up length if there is too little space left in the a.g.
- * Return 1 if ok, 0 if too little, should give up.
- */
-STATIC int
-xfs_alloc_fix_minleft(
- xfs_alloc_arg_t *args) /* allocation argument structure */
-{
- xfs_agf_t *agf; /* a.g. freelist header */
- int diff; /* free space difference */
-
- if (args->minleft == 0)
- return 1;
- agf = XFS_BUF_TO_AGF(args->agbp);
- diff = be32_to_cpu(agf->agf_freeblks)
- - args->len - args->minleft;
- if (diff >= 0)
- return 1;
- args->len += diff; /* shrink the allocated space */
- /* casts to (int) catch length underflows */
- if ((int)args->len >= (int)args->minlen)
- return 1;
- args->agbno = NULLAGBLOCK;
- return 0;
-}
-
-/*
* Update the two btrees, logically removing from freespace the extent
* starting at rbno, rlen blocks. The extent is contained within the
* actual (current) free extent fbno for flen blocks.
@@ -689,8 +662,6 @@
xfs_alloc_arg_t *args) /* argument structure for allocation */
{
int error=0;
- xfs_extlen_t reservation;
- xfs_extlen_t oldmax;
ASSERT(args->minlen > 0);
ASSERT(args->maxlen > 0);
@@ -699,20 +670,6 @@
ASSERT(args->alignment > 0);
/*
- * Clamp maxlen to the amount of free space minus any reservations
- * that have been made.
- */
- oldmax = args->maxlen;
- reservation = xfs_ag_resv_needed(args->pag, args->resv);
- if (args->maxlen > args->pag->pagf_freeblks - reservation)
- args->maxlen = args->pag->pagf_freeblks - reservation;
- if (args->maxlen == 0) {
- args->agbno = NULLAGBLOCK;
- args->maxlen = oldmax;
- return 0;
- }
-
- /*
* Branch to correct routine based on the type.
*/
args->wasfromfl = 0;
@@ -731,8 +688,6 @@
/* NOTREACHED */
}
- args->maxlen = oldmax;
-
if (error || args->agbno == NULLAGBLOCK)
return error;
@@ -841,9 +796,6 @@
args->len = XFS_AGBLOCK_MIN(tend, args->agbno + args->maxlen)
- args->agbno;
xfs_alloc_fix_len(args);
- if (!xfs_alloc_fix_minleft(args))
- goto not_found;
-
ASSERT(args->agbno + args->len <= tend);
/*
@@ -1149,12 +1101,7 @@
XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0);
ASSERT(ltbno + ltlen <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length));
args->len = blen;
- if (!xfs_alloc_fix_minleft(args)) {
- xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
- trace_xfs_alloc_near_nominleft(args);
- return 0;
- }
- blen = args->len;
+
/*
* We are allocating starting at bnew for blen blocks.
*/
@@ -1346,12 +1293,6 @@
*/
args->len = XFS_EXTLEN_MIN(ltlena, args->maxlen);
xfs_alloc_fix_len(args);
- if (!xfs_alloc_fix_minleft(args)) {
- trace_xfs_alloc_near_nominleft(args);
- xfs_btree_del_cursor(bno_cur_lt, XFS_BTREE_NOERROR);
- xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
- return 0;
- }
rlen = args->len;
(void)xfs_alloc_compute_diff(args->agbno, rlen, args->alignment,
args->datatype, ltbnoa, ltlena, <new);
@@ -1553,8 +1494,6 @@
}
xfs_alloc_fix_len(args);
- if (!xfs_alloc_fix_minleft(args))
- goto out_nominleft;
rlen = args->len;
XFS_WANT_CORRUPTED_GOTO(args->mp, rlen <= flen, error0);
/*
@@ -2056,7 +1995,7 @@
int flags)
{
struct xfs_perag *pag = args->pag;
- xfs_extlen_t longest;
+ xfs_extlen_t alloc_len, longest;
xfs_extlen_t reservation; /* blocks that are still reserved */
int available;
@@ -2066,17 +2005,28 @@
reservation = xfs_ag_resv_needed(pag, args->resv);
/* do we have enough contiguous free space for the allocation? */
+ alloc_len = args->minlen + (args->alignment - 1) + args->minalignslop;
longest = xfs_alloc_longest_free_extent(args->mp, pag, min_free,
reservation);
- if ((args->minlen + args->alignment + args->minalignslop - 1) > longest)
+ if (longest < alloc_len)
return false;
/* do we have enough free space remaining for the allocation? */
available = (int)(pag->pagf_freeblks + pag->pagf_flcount -
- reservation - min_free - args->total);
- if (available < (int)args->minleft || available <= 0)
+ reservation - min_free - args->minleft);
+ if (available < (int)max(args->total, alloc_len))
return false;
+ /*
+ * Clamp maxlen to the amount of free space available for the actual
+ * extent allocation.
+ */
+ if (available < (int)args->maxlen && !(flags & XFS_ALLOC_FLAG_CHECK)) {
+ args->maxlen = available;
+ ASSERT(args->maxlen > 0);
+ ASSERT(args->maxlen >= args->minlen);
+ }
+
return true;
}
@@ -2122,7 +2072,8 @@
}
need = xfs_alloc_min_freelist(mp, pag);
- if (!xfs_alloc_space_available(args, need, flags))
+ if (!xfs_alloc_space_available(args, need, flags |
+ XFS_ALLOC_FLAG_CHECK))
goto out_agbp_relse;
/*
@@ -2638,12 +2589,10 @@
xfs_agblock_t agsize; /* allocation group size */
int error;
int flags; /* XFS_ALLOC_FLAG_... locking flags */
- xfs_extlen_t minleft;/* minimum left value, temp copy */
xfs_mount_t *mp; /* mount structure pointer */
xfs_agnumber_t sagno; /* starting allocation group number */
xfs_alloctype_t type; /* input allocation type */
int bump_rotor = 0;
- int no_min = 0;
xfs_agnumber_t rotorstep = xfs_rotorstep; /* inode32 agf stepper */
mp = args->mp;
@@ -2672,7 +2621,6 @@
trace_xfs_alloc_vextent_badargs(args);
return 0;
}
- minleft = args->minleft;
switch (type) {
case XFS_ALLOCTYPE_THIS_AG:
@@ -2683,9 +2631,7 @@
*/
args->agno = XFS_FSB_TO_AGNO(mp, args->fsbno);
args->pag = xfs_perag_get(mp, args->agno);
- args->minleft = 0;
error = xfs_alloc_fix_freelist(args, 0);
- args->minleft = minleft;
if (error) {
trace_xfs_alloc_vextent_nofix(args);
goto error0;
@@ -2750,9 +2696,7 @@
*/
for (;;) {
args->pag = xfs_perag_get(mp, args->agno);
- if (no_min) args->minleft = 0;
error = xfs_alloc_fix_freelist(args, flags);
- args->minleft = minleft;
if (error) {
trace_xfs_alloc_vextent_nofix(args);
goto error0;
@@ -2792,20 +2736,17 @@
* or switch to non-trylock mode.
*/
if (args->agno == sagno) {
- if (no_min == 1) {
+ if (flags == 0) {
args->agbno = NULLAGBLOCK;
trace_xfs_alloc_vextent_allfailed(args);
break;
}
- if (flags == 0) {
- no_min = 1;
- } else {
- flags = 0;
- if (type == XFS_ALLOCTYPE_START_BNO) {
- args->agbno = XFS_FSB_TO_AGBNO(mp,
- args->fsbno);
- args->type = XFS_ALLOCTYPE_NEAR_BNO;
- }
+
+ flags = 0;
+ if (type == XFS_ALLOCTYPE_START_BNO) {
+ args->agbno = XFS_FSB_TO_AGBNO(mp,
+ args->fsbno);
+ args->type = XFS_ALLOCTYPE_NEAR_BNO;
}
}
xfs_perag_put(args->pag);
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 7c404a6..1d0f48a 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -56,7 +56,7 @@
#define XFS_ALLOC_FLAG_FREEING 0x00000002 /* indicate caller is freeing extents*/
#define XFS_ALLOC_FLAG_NORMAP 0x00000004 /* don't modify the rmapbt */
#define XFS_ALLOC_FLAG_NOSHRINK 0x00000008 /* don't shrink the freelist */
-
+#define XFS_ALLOC_FLAG_CHECK 0x00000010 /* test only, don't modify args */
/*
* Argument structure for xfs_alloc routines.
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index af1ecb1..6622d46 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -131,9 +131,6 @@
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
- if (!xfs_inode_hasattr(ip))
- return -ENOATTR;
-
error = xfs_attr_args_init(&args, ip, name, flags);
if (error)
return error;
@@ -392,9 +389,6 @@
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
- if (!xfs_inode_hasattr(dp))
- return -ENOATTR;
-
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 2760bc3..bfc00de 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3629,7 +3629,7 @@
align = xfs_get_cowextsz_hint(ap->ip);
else if (xfs_alloc_is_userdata(ap->datatype))
align = xfs_get_extsz_hint(ap->ip);
- if (unlikely(align)) {
+ if (align) {
error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
align, 0, ap->eof, 0, ap->conv,
&ap->offset, &ap->length);
@@ -3701,7 +3701,7 @@
args.minlen = ap->minlen;
}
/* apply extent size hints if obtained earlier */
- if (unlikely(align)) {
+ if (align) {
args.prod = align;
if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod)))
args.mod = (xfs_extlen_t)(args.prod - args.mod);
@@ -3812,7 +3812,6 @@
args.fsbno = 0;
args.type = XFS_ALLOCTYPE_FIRST_AG;
args.total = ap->minlen;
- args.minleft = 0;
if ((error = xfs_alloc_vextent(&args)))
return error;
ap->dfops->dop_low = true;
@@ -4344,8 +4343,6 @@
if (error)
return error;
- if (bma->dfops->dop_low)
- bma->minleft = 0;
if (bma->cur)
bma->cur->bc_private.b.firstblock = *bma->firstblock;
if (bma->blkno == NULLFSBLOCK)
@@ -4517,8 +4514,6 @@
int n; /* current extent index */
xfs_fileoff_t obno; /* old block number (offset) */
int whichfork; /* data or attr fork */
- char inhole; /* current location is hole in file */
- char wasdelay; /* old extent was delayed */
#ifdef DEBUG
xfs_fileoff_t orig_bno; /* original block number value */
@@ -4606,22 +4601,44 @@
bma.firstblock = firstblock;
while (bno < end && n < *nmap) {
- inhole = eof || bma.got.br_startoff > bno;
- wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
+ bool need_alloc = false, wasdelay = false;
- /*
- * Make sure we only reflink into a hole.
- */
- if (flags & XFS_BMAPI_REMAP)
- ASSERT(inhole);
- if (flags & XFS_BMAPI_COWFORK)
- ASSERT(!inhole);
+ /* in hole or beyoned EOF? */
+ if (eof || bma.got.br_startoff > bno) {
+ if (flags & XFS_BMAPI_DELALLOC) {
+ /*
+ * For the COW fork we can reasonably get a
+ * request for converting an extent that races
+ * with other threads already having converted
+ * part of it, as there converting COW to
+ * regular blocks is not protected using the
+ * IOLOCK.
+ */
+ ASSERT(flags & XFS_BMAPI_COWFORK);
+ if (!(flags & XFS_BMAPI_COWFORK)) {
+ error = -EIO;
+ goto error0;
+ }
+
+ if (eof || bno >= end)
+ break;
+ } else {
+ need_alloc = true;
+ }
+ } else {
+ /*
+ * Make sure we only reflink into a hole.
+ */
+ ASSERT(!(flags & XFS_BMAPI_REMAP));
+ if (isnullstartblock(bma.got.br_startblock))
+ wasdelay = true;
+ }
/*
* First, deal with the hole before the allocated space
* that we found, if any.
*/
- if (inhole || wasdelay) {
+ if (need_alloc || wasdelay) {
bma.eof = eof;
bma.conv = !!(flags & XFS_BMAPI_CONVERT);
bma.wasdel = wasdelay;
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index cecd094..cdef87d 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -110,6 +110,9 @@
/* Map something in the CoW fork. */
#define XFS_BMAPI_COWFORK 0x200
+/* Only convert delalloc space, don't allocate entirely new extents */
+#define XFS_BMAPI_DELALLOC 0x400
+
#define XFS_BMAPI_FLAGS \
{ XFS_BMAPI_ENTIRE, "ENTIRE" }, \
{ XFS_BMAPI_METADATA, "METADATA" }, \
@@ -120,7 +123,8 @@
{ XFS_BMAPI_CONVERT, "CONVERT" }, \
{ XFS_BMAPI_ZERO, "ZERO" }, \
{ XFS_BMAPI_REMAP, "REMAP" }, \
- { XFS_BMAPI_COWFORK, "COWFORK" }
+ { XFS_BMAPI_COWFORK, "COWFORK" }, \
+ { XFS_BMAPI_DELALLOC, "DELALLOC" }
static inline int xfs_bmapi_aflag(int w)
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index d6330c2..d9be241 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -502,12 +502,11 @@
if (args.fsbno == NULLFSBLOCK && args.minleft) {
/*
* Could not find an AG with enough free space to satisfy
- * a full btree split. Try again without minleft and if
+ * a full btree split. Try again and if
* successful activate the lowspace algorithm.
*/
args.fsbno = 0;
args.type = XFS_ALLOCTYPE_FIRST_AG;
- args.minleft = 0;
error = xfs_alloc_vextent(&args);
if (error)
goto error0;
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index c58d72c..2f389d36 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -36,21 +36,29 @@
struct xfs_name xfs_name_dotdot = { (unsigned char *)"..", 2, XFS_DIR3_FT_DIR };
/*
- * @mode, if set, indicates that the type field needs to be set up.
- * This uses the transformation from file mode to DT_* as defined in linux/fs.h
- * for file type specification. This will be propagated into the directory
- * structure if appropriate for the given operation and filesystem config.
+ * Convert inode mode to directory entry filetype
*/
-const unsigned char xfs_mode_to_ftype[S_IFMT >> S_SHIFT] = {
- [0] = XFS_DIR3_FT_UNKNOWN,
- [S_IFREG >> S_SHIFT] = XFS_DIR3_FT_REG_FILE,
- [S_IFDIR >> S_SHIFT] = XFS_DIR3_FT_DIR,
- [S_IFCHR >> S_SHIFT] = XFS_DIR3_FT_CHRDEV,
- [S_IFBLK >> S_SHIFT] = XFS_DIR3_FT_BLKDEV,
- [S_IFIFO >> S_SHIFT] = XFS_DIR3_FT_FIFO,
- [S_IFSOCK >> S_SHIFT] = XFS_DIR3_FT_SOCK,
- [S_IFLNK >> S_SHIFT] = XFS_DIR3_FT_SYMLINK,
-};
+unsigned char xfs_mode_to_ftype(int mode)
+{
+ switch (mode & S_IFMT) {
+ case S_IFREG:
+ return XFS_DIR3_FT_REG_FILE;
+ case S_IFDIR:
+ return XFS_DIR3_FT_DIR;
+ case S_IFCHR:
+ return XFS_DIR3_FT_CHRDEV;
+ case S_IFBLK:
+ return XFS_DIR3_FT_BLKDEV;
+ case S_IFIFO:
+ return XFS_DIR3_FT_FIFO;
+ case S_IFSOCK:
+ return XFS_DIR3_FT_SOCK;
+ case S_IFLNK:
+ return XFS_DIR3_FT_SYMLINK;
+ default:
+ return XFS_DIR3_FT_UNKNOWN;
+ }
+}
/*
* ASCII case-insensitive (ie. A-Z) support for directories that was
@@ -631,7 +639,8 @@
if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
return rval;
rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize;
- ASSERT(rval == 0 || args->dp->i_d.di_size == args->geo->blksize);
+ if (rval != 0 && args->dp->i_d.di_size != args->geo->blksize)
+ return -EFSCORRUPTED;
*vp = rval;
return 0;
}
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 0197590..d6e6d9d 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -18,6 +18,9 @@
#ifndef __XFS_DIR2_H__
#define __XFS_DIR2_H__
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+
struct xfs_defer_ops;
struct xfs_da_args;
struct xfs_inode;
@@ -32,10 +35,9 @@
extern struct xfs_name xfs_name_dotdot;
/*
- * directory filetype conversion tables.
+ * Convert inode mode to directory entry filetype
*/
-#define S_SHIFT 12
-extern const unsigned char xfs_mode_to_ftype[];
+extern unsigned char xfs_mode_to_ftype(int mode);
/*
* directory operations vector for encode/decode routines
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 0fd086d..7c47188 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -82,11 +82,12 @@
}
STATIC int
-xfs_inobt_alloc_block(
+__xfs_inobt_alloc_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *start,
union xfs_btree_ptr *new,
- int *stat)
+ int *stat,
+ enum xfs_ag_resv_type resv)
{
xfs_alloc_arg_t args; /* block allocation args */
int error; /* error return value */
@@ -103,6 +104,7 @@
args.maxlen = 1;
args.prod = 1;
args.type = XFS_ALLOCTYPE_NEAR_BNO;
+ args.resv = resv;
error = xfs_alloc_vextent(&args);
if (error) {
@@ -123,6 +125,27 @@
}
STATIC int
+xfs_inobt_alloc_block(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *start,
+ union xfs_btree_ptr *new,
+ int *stat)
+{
+ return __xfs_inobt_alloc_block(cur, start, new, stat, XFS_AG_RESV_NONE);
+}
+
+STATIC int
+xfs_finobt_alloc_block(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *start,
+ union xfs_btree_ptr *new,
+ int *stat)
+{
+ return __xfs_inobt_alloc_block(cur, start, new, stat,
+ XFS_AG_RESV_METADATA);
+}
+
+STATIC int
xfs_inobt_free_block(
struct xfs_btree_cur *cur,
struct xfs_buf *bp)
@@ -328,7 +351,7 @@
.dup_cursor = xfs_inobt_dup_cursor,
.set_root = xfs_finobt_set_root,
- .alloc_block = xfs_inobt_alloc_block,
+ .alloc_block = xfs_finobt_alloc_block,
.free_block = xfs_inobt_free_block,
.get_minrecs = xfs_inobt_get_minrecs,
.get_maxrecs = xfs_inobt_get_maxrecs,
@@ -480,3 +503,64 @@
return 0;
}
#endif /* DEBUG */
+
+static xfs_extlen_t
+xfs_inobt_max_size(
+ struct xfs_mount *mp)
+{
+ /* Bail out if we're uninitialized, which can happen in mkfs. */
+ if (mp->m_inobt_mxr[0] == 0)
+ return 0;
+
+ return xfs_btree_calc_size(mp, mp->m_inobt_mnr,
+ (uint64_t)mp->m_sb.sb_agblocks * mp->m_sb.sb_inopblock /
+ XFS_INODES_PER_CHUNK);
+}
+
+static int
+xfs_inobt_count_blocks(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno,
+ xfs_btnum_t btnum,
+ xfs_extlen_t *tree_blocks)
+{
+ struct xfs_buf *agbp;
+ struct xfs_btree_cur *cur;
+ int error;
+
+ error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
+ if (error)
+ return error;
+
+ cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum);
+ error = xfs_btree_count_blocks(cur, tree_blocks);
+ xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+ xfs_buf_relse(agbp);
+
+ return error;
+}
+
+/*
+ * Figure out how many blocks to reserve and how many are used by this btree.
+ */
+int
+xfs_finobt_calc_reserves(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno,
+ xfs_extlen_t *ask,
+ xfs_extlen_t *used)
+{
+ xfs_extlen_t tree_len = 0;
+ int error;
+
+ if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+ return 0;
+
+ error = xfs_inobt_count_blocks(mp, agno, XFS_BTNUM_FINO, &tree_len);
+ if (error)
+ return error;
+
+ *ask += xfs_inobt_max_size(mp);
+ *used += tree_len;
+ return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index bd88453..aa81e2e 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -72,4 +72,7 @@
#define xfs_inobt_rec_check_count(mp, rec) 0
#endif /* DEBUG */
+int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_extlen_t *ask, xfs_extlen_t *used);
+
#endif /* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index dd483e2..d93f9d9 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -29,6 +29,7 @@
#include "xfs_icache.h"
#include "xfs_trans.h"
#include "xfs_ialloc.h"
+#include "xfs_dir2.h"
/*
* Check that none of the inode's in the buffer have a next
@@ -386,6 +387,7 @@
xfs_ino_t ino,
struct xfs_dinode *dip)
{
+ uint16_t mode;
uint16_t flags;
uint64_t flags2;
@@ -396,8 +398,12 @@
if (be64_to_cpu(dip->di_size) & (1ULL << 63))
return false;
- /* No zero-length symlinks. */
- if (S_ISLNK(be16_to_cpu(dip->di_mode)) && dip->di_size == 0)
+ mode = be16_to_cpu(dip->di_mode);
+ if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN)
+ return false;
+
+ /* No zero-length symlinks/dirs. */
+ if ((S_ISLNK(mode) || S_ISDIR(mode)) && dip->di_size == 0)
return false;
/* only version 3 or greater inodes are extensively verified here */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 2580262..584ec89 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -242,7 +242,7 @@
sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG ||
sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG ||
sbp->sb_blocksize != (1 << sbp->sb_blocklog) ||
- sbp->sb_dirblklog > XFS_MAX_BLOCKSIZE_LOG ||
+ sbp->sb_dirblklog + sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG ||
sbp->sb_inodesize < XFS_DINODE_MIN_SIZE ||
sbp->sb_inodesize > XFS_DINODE_MAX_SIZE ||
sbp->sb_inodelog < XFS_DINODE_MIN_LOG ||
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0f56fcd..631e7c0 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1152,19 +1152,22 @@
* block_invalidatepage() can send pages that are still marked dirty
* but otherwise have invalidated buffers.
*
- * We've historically freed buffers on the latter. Instead, quietly
- * filter out all dirty pages to avoid spurious buffer state warnings.
- * This can likely be removed once shrink_active_list() is fixed.
+ * We want to release the latter to avoid unnecessary buildup of the
+ * LRU, skip the former and warn if we've left any lingering
+ * delalloc/unwritten buffers on clean pages. Skip pages with delalloc
+ * or unwritten buffers and warn if the page is not dirty. Otherwise
+ * try to release the buffers.
*/
- if (PageDirty(page))
- return 0;
-
xfs_count_page_state(page, &delalloc, &unwritten);
- if (WARN_ON_ONCE(delalloc))
+ if (delalloc) {
+ WARN_ON_ONCE(!PageDirty(page));
return 0;
- if (WARN_ON_ONCE(unwritten))
+ }
+ if (unwritten) {
+ WARN_ON_ONCE(!PageDirty(page));
return 0;
+ }
return try_to_free_buffers(page);
}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index b9abce5..c141791 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -528,7 +528,6 @@
xfs_bmbt_irec_t *map; /* buffer for user's data */
xfs_mount_t *mp; /* file system mount point */
int nex; /* # of user extents can do */
- int nexleft; /* # of user extents left */
int subnex; /* # of bmapi's can do */
int nmap; /* number of map entries */
struct getbmapx *out; /* output structure */
@@ -686,10 +685,8 @@
goto out_free_map;
}
- nexleft = nex;
-
do {
- nmap = (nexleft > subnex) ? subnex : nexleft;
+ nmap = (nex> subnex) ? subnex : nex;
error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
XFS_BB_TO_FSB(mp, bmv->bmv_length),
map, &nmap, bmapi_flags);
@@ -697,8 +694,8 @@
goto out_free_map;
ASSERT(nmap <= subnex);
- for (i = 0; i < nmap && nexleft && bmv->bmv_length &&
- cur_ext < bmv->bmv_count; i++) {
+ for (i = 0; i < nmap && bmv->bmv_length &&
+ cur_ext < bmv->bmv_count - 1; i++) {
out[cur_ext].bmv_oflags = 0;
if (map[i].br_state == XFS_EXT_UNWRITTEN)
out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
@@ -760,16 +757,27 @@
continue;
}
+ /*
+ * In order to report shared extents accurately,
+ * we report each distinct shared/unshared part
+ * of a single bmbt record using multiple bmap
+ * extents. To make that happen, we iterate the
+ * same map array item multiple times, each
+ * time trimming out the subextent that we just
+ * reported.
+ *
+ * Because of this, we must check the out array
+ * index (cur_ext) directly against bmv_count-1
+ * to avoid overflows.
+ */
if (inject_map.br_startblock != NULLFSBLOCK) {
map[i] = inject_map;
i--;
- } else
- nexleft--;
+ }
bmv->bmv_entries++;
cur_ext++;
}
- } while (nmap && nexleft && bmv->bmv_length &&
- cur_ext < bmv->bmv_count);
+ } while (nmap && bmv->bmv_length && cur_ext < bmv->bmv_count - 1);
out_free_map:
kmem_free(map);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 7f0a01f..ac3b4db 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -422,6 +422,7 @@
out_free_pages:
for (i = 0; i < bp->b_page_count; i++)
__free_page(bp->b_pages[i]);
+ bp->b_flags &= ~_XBF_PAGES;
return error;
}
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 7a30b8f..9d06cc3 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -710,6 +710,10 @@
/* Simple advance */
next_id = *id + 1;
+ /* If we'd wrap past the max ID, stop */
+ if (next_id < *id)
+ return -ENOENT;
+
/* If new ID is within the current chunk, advancing it sufficed */
if (next_id % mp->m_quotainfo->qi_dqperchunk) {
*id = next_id;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b955779..de32f0f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1792,22 +1792,23 @@
int error;
/*
- * The ifree transaction might need to allocate blocks for record
- * insertion to the finobt. We don't want to fail here at ENOSPC, so
- * allow ifree to dip into the reserved block pool if necessary.
- *
- * Freeing large sets of inodes generally means freeing inode chunks,
- * directory and file data blocks, so this should be relatively safe.
- * Only under severe circumstances should it be possible to free enough
- * inodes to exhaust the reserve block pool via finobt expansion while
- * at the same time not creating free space in the filesystem.
+ * We try to use a per-AG reservation for any block needed by the finobt
+ * tree, but as the finobt feature predates the per-AG reservation
+ * support a degraded file system might not have enough space for the
+ * reservation at mount time. In that case try to dip into the reserved
+ * pool and pray.
*
* Send a warning if the reservation does happen to fail, as the inode
* now remains allocated and sits on the unlinked list until the fs is
* repaired.
*/
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
- XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+ if (unlikely(mp->m_inotbt_nores)) {
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
+ XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE,
+ &tp);
+ } else {
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, 0, 0, 0, &tp);
+ }
if (error) {
if (error == -ENOSPC) {
xfs_warn_ratelimited(mp,
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 0d14742..1aa3abd 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -681,7 +681,7 @@
xfs_trans_t *tp;
int nimaps;
int error = 0;
- int flags = 0;
+ int flags = XFS_BMAPI_DELALLOC;
int nres;
if (whichfork == XFS_COW_FORK)
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 308bebb..22c1615 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -98,12 +98,27 @@
static void
xfs_dentry_to_name(
struct xfs_name *namep,
+ struct dentry *dentry)
+{
+ namep->name = dentry->d_name.name;
+ namep->len = dentry->d_name.len;
+ namep->type = XFS_DIR3_FT_UNKNOWN;
+}
+
+static int
+xfs_dentry_mode_to_name(
+ struct xfs_name *namep,
struct dentry *dentry,
int mode)
{
namep->name = dentry->d_name.name;
namep->len = dentry->d_name.len;
- namep->type = xfs_mode_to_ftype[(mode & S_IFMT) >> S_SHIFT];
+ namep->type = xfs_mode_to_ftype(mode);
+
+ if (unlikely(namep->type == XFS_DIR3_FT_UNKNOWN))
+ return -EFSCORRUPTED;
+
+ return 0;
}
STATIC void
@@ -119,7 +134,7 @@
* xfs_init_security we must back out.
* ENOSPC can hit here, among other things.
*/
- xfs_dentry_to_name(&teardown, dentry, 0);
+ xfs_dentry_to_name(&teardown, dentry);
xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
}
@@ -154,8 +169,12 @@
if (error)
return error;
+ /* Verify mode is valid also for tmpfile case */
+ error = xfs_dentry_mode_to_name(&name, dentry, mode);
+ if (unlikely(error))
+ goto out_free_acl;
+
if (!tmpfile) {
- xfs_dentry_to_name(&name, dentry, mode);
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
} else {
error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
@@ -248,7 +267,7 @@
if (dentry->d_name.len >= MAXNAMELEN)
return ERR_PTR(-ENAMETOOLONG);
- xfs_dentry_to_name(&name, dentry, 0);
+ xfs_dentry_to_name(&name, dentry);
error = xfs_lookup(XFS_I(dir), &name, &cip, NULL);
if (unlikely(error)) {
if (unlikely(error != -ENOENT))
@@ -275,7 +294,7 @@
if (dentry->d_name.len >= MAXNAMELEN)
return ERR_PTR(-ENAMETOOLONG);
- xfs_dentry_to_name(&xname, dentry, 0);
+ xfs_dentry_to_name(&xname, dentry);
error = xfs_lookup(XFS_I(dir), &xname, &ip, &ci_name);
if (unlikely(error)) {
if (unlikely(error != -ENOENT))
@@ -310,7 +329,9 @@
struct xfs_name name;
int error;
- xfs_dentry_to_name(&name, dentry, inode->i_mode);
+ error = xfs_dentry_mode_to_name(&name, dentry, inode->i_mode);
+ if (unlikely(error))
+ return error;
error = xfs_link(XFS_I(dir), XFS_I(inode), &name);
if (unlikely(error))
@@ -329,7 +350,7 @@
struct xfs_name name;
int error;
- xfs_dentry_to_name(&name, dentry, 0);
+ xfs_dentry_to_name(&name, dentry);
error = xfs_remove(XFS_I(dir), &name, XFS_I(d_inode(dentry)));
if (error)
@@ -359,7 +380,9 @@
mode = S_IFLNK |
(irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO);
- xfs_dentry_to_name(&name, dentry, mode);
+ error = xfs_dentry_mode_to_name(&name, dentry, mode);
+ if (unlikely(error))
+ goto out;
error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip);
if (unlikely(error))
@@ -395,6 +418,7 @@
{
struct inode *new_inode = d_inode(ndentry);
int omode = 0;
+ int error;
struct xfs_name oname;
struct xfs_name nname;
@@ -405,8 +429,14 @@
if (flags & RENAME_EXCHANGE)
omode = d_inode(ndentry)->i_mode;
- xfs_dentry_to_name(&oname, odentry, omode);
- xfs_dentry_to_name(&nname, ndentry, d_inode(odentry)->i_mode);
+ error = xfs_dentry_mode_to_name(&oname, odentry, omode);
+ if (omode && unlikely(error))
+ return error;
+
+ error = xfs_dentry_mode_to_name(&nname, ndentry,
+ d_inode(odentry)->i_mode);
+ if (unlikely(error))
+ return error;
return xfs_rename(XFS_I(odir), &oname, XFS_I(d_inode(odentry)),
XFS_I(ndir), &nname,
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index e467218..7a989de 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -331,11 +331,11 @@
}
#define ASSERT_ALWAYS(expr) \
- (unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
+ (likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
#ifdef DEBUG
#define ASSERT(expr) \
- (unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
+ (likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
#ifndef STATIC
# define STATIC noinline
@@ -346,7 +346,7 @@
#ifdef XFS_WARN
#define ASSERT(expr) \
- (unlikely(expr) ? (void)0 : asswarn(#expr, __FILE__, __LINE__))
+ (likely(expr) ? (void)0 : asswarn(#expr, __FILE__, __LINE__))
#ifndef STATIC
# define STATIC static noinline
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index c39ac14..b1469f0 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -3317,12 +3317,8 @@
xfs_mount_t *mp,
uint flags)
{
- int error;
-
trace_xfs_log_force(mp, 0, _RET_IP_);
- error = _xfs_log_force(mp, flags, NULL);
- if (error)
- xfs_warn(mp, "%s: error %d returned.", __func__, error);
+ _xfs_log_force(mp, flags, NULL);
}
/*
@@ -3466,12 +3462,8 @@
xfs_lsn_t lsn,
uint flags)
{
- int error;
-
trace_xfs_log_force(mp, lsn, _RET_IP_);
- error = _xfs_log_force_lsn(mp, lsn, flags, NULL);
- if (error)
- xfs_warn(mp, "%s: error %d returned.", __func__, error);
+ _xfs_log_force_lsn(mp, lsn, flags, NULL);
}
/*
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 84f7852..7f351f7 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -140,6 +140,7 @@
int m_fixedfsid[2]; /* unchanged for life of FS */
uint m_dmevmask; /* DMI events for this FS */
__uint64_t m_flags; /* global mount flags */
+ bool m_inotbt_nores; /* no per-AG finobt resv. */
int m_ialloc_inos; /* inodes in inode allocation */
int m_ialloc_blks; /* blocks in inode allocation */
int m_ialloc_min_blks;/* min blocks in sparse inode
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 45e50ea..b669b12 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1177,7 +1177,8 @@
* the case in all other instances. It's OK that we do this because
* quotacheck is done only at mount time.
*/
- error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip);
+ error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, XFS_ILOCK_EXCL,
+ &ip);
if (error) {
*res = BULKSTAT_RV_NOTHING;
return error;
diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
deleted file mode 100644
index 5196943..0000000
--- a/include/asm-generic/cputime.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef _ASM_GENERIC_CPUTIME_H
-#define _ASM_GENERIC_CPUTIME_H
-
-#include <linux/time.h>
-#include <linux/jiffies.h>
-
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-# include <asm-generic/cputime_jiffies.h>
-#endif
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-# include <asm-generic/cputime_nsecs.h>
-#endif
-
-#endif
diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h
deleted file mode 100644
index 6bb8cd4..0000000
--- a/include/asm-generic/cputime_jiffies.h
+++ /dev/null
@@ -1,75 +0,0 @@
-#ifndef _ASM_GENERIC_CPUTIME_JIFFIES_H
-#define _ASM_GENERIC_CPUTIME_JIFFIES_H
-
-typedef unsigned long __nocast cputime_t;
-
-#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
-
-#define cputime_one_jiffy jiffies_to_cputime(1)
-#define cputime_to_jiffies(__ct) (__force unsigned long)(__ct)
-#define jiffies_to_cputime(__hz) (__force cputime_t)(__hz)
-
-typedef u64 __nocast cputime64_t;
-
-#define cputime64_to_jiffies64(__ct) (__force u64)(__ct)
-#define jiffies64_to_cputime64(__jif) (__force cputime64_t)(__jif)
-
-
-/*
- * Convert nanoseconds <-> cputime
- */
-#define cputime_to_nsecs(__ct) \
- jiffies_to_nsecs(cputime_to_jiffies(__ct))
-#define nsecs_to_cputime64(__nsec) \
- jiffies64_to_cputime64(nsecs_to_jiffies64(__nsec))
-#define nsecs_to_cputime(__nsec) \
- jiffies_to_cputime(nsecs_to_jiffies(__nsec))
-
-
-/*
- * Convert cputime to microseconds and back.
- */
-#define cputime_to_usecs(__ct) \
- jiffies_to_usecs(cputime_to_jiffies(__ct))
-#define usecs_to_cputime(__usec) \
- jiffies_to_cputime(usecs_to_jiffies(__usec))
-#define usecs_to_cputime64(__usec) \
- jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
-
-/*
- * Convert cputime to seconds and back.
- */
-#define cputime_to_secs(jif) (cputime_to_jiffies(jif) / HZ)
-#define secs_to_cputime(sec) jiffies_to_cputime((sec) * HZ)
-
-/*
- * Convert cputime to timespec and back.
- */
-#define timespec_to_cputime(__val) \
- jiffies_to_cputime(timespec_to_jiffies(__val))
-#define cputime_to_timespec(__ct,__val) \
- jiffies_to_timespec(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to timeval and back.
- */
-#define timeval_to_cputime(__val) \
- jiffies_to_cputime(timeval_to_jiffies(__val))
-#define cputime_to_timeval(__ct,__val) \
- jiffies_to_timeval(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to clock and back.
- */
-#define cputime_to_clock_t(__ct) \
- jiffies_to_clock_t(cputime_to_jiffies(__ct))
-#define clock_t_to_cputime(__x) \
- jiffies_to_cputime(clock_t_to_jiffies(__x))
-
-/*
- * Convert cputime64 to clock.
- */
-#define cputime64_to_clock_t(__ct) \
- jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct))
-
-#endif
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
deleted file mode 100644
index 4e3b18e..0000000
--- a/include/asm-generic/cputime_nsecs.h
+++ /dev/null
@@ -1,121 +0,0 @@
-/*
- * Definitions for measuring cputime in nsecs resolution.
- *
- * Based on <arch/ia64/include/asm/cputime.h>
- *
- * Copyright (C) 2007 FUJITSU LIMITED
- * Copyright (C) 2007 Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- */
-
-#ifndef _ASM_GENERIC_CPUTIME_NSECS_H
-#define _ASM_GENERIC_CPUTIME_NSECS_H
-
-#include <linux/math64.h>
-
-typedef u64 __nocast cputime_t;
-typedef u64 __nocast cputime64_t;
-
-#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
-
-#define cputime_one_jiffy jiffies_to_cputime(1)
-
-#define cputime_div(__ct, divisor) div_u64((__force u64)__ct, divisor)
-#define cputime_div_rem(__ct, divisor, remainder) \
- div_u64_rem((__force u64)__ct, divisor, remainder);
-
-/*
- * Convert cputime <-> jiffies (HZ)
- */
-#define cputime_to_jiffies(__ct) \
- cputime_div(__ct, NSEC_PER_SEC / HZ)
-#define jiffies_to_cputime(__jif) \
- (__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ))
-#define cputime64_to_jiffies64(__ct) \
- cputime_div(__ct, NSEC_PER_SEC / HZ)
-#define jiffies64_to_cputime64(__jif) \
- (__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ))
-
-
-/*
- * Convert cputime <-> nanoseconds
- */
-#define cputime_to_nsecs(__ct) \
- (__force u64)(__ct)
-#define nsecs_to_cputime(__nsecs) \
- (__force cputime_t)(__nsecs)
-#define nsecs_to_cputime64(__nsecs) \
- (__force cputime64_t)(__nsecs)
-
-
-/*
- * Convert cputime <-> microseconds
- */
-#define cputime_to_usecs(__ct) \
- cputime_div(__ct, NSEC_PER_USEC)
-#define usecs_to_cputime(__usecs) \
- (__force cputime_t)((__usecs) * NSEC_PER_USEC)
-#define usecs_to_cputime64(__usecs) \
- (__force cputime64_t)((__usecs) * NSEC_PER_USEC)
-
-/*
- * Convert cputime <-> seconds
- */
-#define cputime_to_secs(__ct) \
- cputime_div(__ct, NSEC_PER_SEC)
-#define secs_to_cputime(__secs) \
- (__force cputime_t)((__secs) * NSEC_PER_SEC)
-
-/*
- * Convert cputime <-> timespec (nsec)
- */
-static inline cputime_t timespec_to_cputime(const struct timespec *val)
-{
- u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
- return (__force cputime_t) ret;
-}
-static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
-{
- u32 rem;
-
- val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem);
- val->tv_nsec = rem;
-}
-
-/*
- * Convert cputime <-> timeval (msec)
- */
-static inline cputime_t timeval_to_cputime(const struct timeval *val)
-{
- u64 ret = (u64)val->tv_sec * NSEC_PER_SEC +
- val->tv_usec * NSEC_PER_USEC;
- return (__force cputime_t) ret;
-}
-static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
-{
- u32 rem;
-
- val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem);
- val->tv_usec = rem / NSEC_PER_USEC;
-}
-
-/*
- * Convert cputime <-> clock (USER_HZ)
- */
-#define cputime_to_clock_t(__ct) \
- cputime_div(__ct, (NSEC_PER_SEC / USER_HZ))
-#define clock_t_to_cputime(__x) \
- (__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ))
-
-/*
- * Convert cputime64 to clock.
- */
-#define cputime64_to_clock_t(__ct) \
- cputime_to_clock_t((__force cputime_t)__ct)
-
-#endif
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
index 63554e9..719db19 100644
--- a/include/asm-generic/export.h
+++ b/include/asm-generic/export.h
@@ -9,18 +9,15 @@
#ifndef KSYM_ALIGN
#define KSYM_ALIGN 8
#endif
-#ifndef KCRC_ALIGN
-#define KCRC_ALIGN 8
-#endif
#else
#define __put .long
#ifndef KSYM_ALIGN
#define KSYM_ALIGN 4
#endif
+#endif
#ifndef KCRC_ALIGN
#define KCRC_ALIGN 4
#endif
-#endif
#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
#define KSYM(name) _##name
@@ -52,7 +49,11 @@
.section ___kcrctab\sec+\name,"a"
.balign KCRC_ALIGN
KSYM(__kcrctab_\name):
- __put KSYM(__crc_\name)
+#if defined(CONFIG_MODULE_REL_CRCS)
+ .long KSYM(__crc_\name) - .
+#else
+ .long KSYM(__crc_\name)
+#endif
.weak KSYM(__crc_\name)
.previous
#endif
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 192016e..9c4ee14 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -517,6 +517,7 @@
struct drm_minor *control; /**< Control node */
struct drm_minor *primary; /**< Primary node */
struct drm_minor *render; /**< Render node */
+ bool registered;
/* currently active master for this device. Protected by master_mutex */
struct drm_master *master;
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index d6d241f..56814e8 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -144,7 +144,7 @@
struct drm_crtc *ptr;
struct drm_crtc_state *state;
struct drm_crtc_commit *commit;
- s64 __user *out_fence_ptr;
+ s32 __user *out_fence_ptr;
};
struct __drm_connnectors_state {
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index a9b9524..045a97c 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -381,6 +381,8 @@
* core drm connector interfaces. Everything added from this callback
* should be unregistered in the early_unregister callback.
*
+ * This is called while holding drm_connector->mutex.
+ *
* Returns:
*
* 0 on success, or a negative error code on failure.
@@ -395,6 +397,8 @@
* late_register(). It is called from drm_connector_unregister(),
* early in the driver unload sequence to disable userspace access
* before data structures are torndown.
+ *
+ * This is called while holding drm_connector->mutex.
*/
void (*early_unregister)(struct drm_connector *connector);
@@ -559,7 +563,6 @@
* @interlace_allowed: can this connector handle interlaced modes?
* @doublescan_allowed: can this connector handle doublescan?
* @stereo_allowed: can this connector handle stereo modes?
- * @registered: is this connector exposed (registered) with userspace?
* @modes: modes available on this connector (from fill_modes() + user)
* @status: one of the drm_connector_status enums (connected, not, or unknown)
* @probed_modes: list of modes derived directly from the display
@@ -608,6 +611,13 @@
char *name;
/**
+ * @mutex: Lock for general connector state, but currently only protects
+ * @registered. Most of the connector state is still protected by the
+ * mutex in &drm_mode_config.
+ */
+ struct mutex mutex;
+
+ /**
* @index: Compacted connector index, which matches the position inside
* the mode_config.list for drivers not supporting hot-add/removing. Can
* be used as an array index. It is invariant over the lifetime of the
@@ -620,6 +630,10 @@
bool interlace_allowed;
bool doublescan_allowed;
bool stereo_allowed;
+ /**
+ * @registered: Is this connector exposed (registered) with userspace?
+ * Protected by @mutex.
+ */
bool registered;
struct list_head modes; /* list of modes on this connector */
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index bf9991b..1374323 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -488,7 +488,7 @@
/**
* @prop_out_fence_ptr: Sync File fd pointer representing the
* outgoing fences for a CRTC. Userspace should provide a pointer to a
- * value of type s64, and then cast that pointer to u64.
+ * value of type s32, and then cast that pointer to u64.
*/
struct drm_property *prop_out_fence_ptr;
/**
diff --git a/include/dt-bindings/thermal/lm90.h b/include/dt-bindings/thermal/lm90.h
new file mode 100644
index 0000000..8c2e309
--- /dev/null
+++ b/include/dt-bindings/thermal/lm90.h
@@ -0,0 +1,12 @@
+/*
+ * This header provides constants for the LM90 thermal bindings.
+ */
+
+#ifndef _DT_BINDINGS_THERMAL_LM90_H_
+#define _DT_BINDINGS_THERMAL_LM90_H_
+
+#define LM90_LOCAL_TEMPERATURE 0
+#define LM90_REMOTE_TEMPERATURE 1
+#define LM90_REMOTE2_TEMPERATURE 2
+
+#endif
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index b717ed9..5c970ce 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -76,4 +76,5 @@
void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu);
+void kvm_timer_init_vhe(void);
#endif
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 5b36974..8e577c2 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1153,4 +1153,14 @@
static inline int parse_spcr(bool earlycon) { return 0; }
#endif
+#if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI)
+int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res);
+#else
+static inline
+int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res)
+{
+ return -EINVAL;
+}
+#endif
+
#endif /*_LINUX_ACPI_H*/
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index b20e3d5..2f1c690 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -593,9 +593,6 @@
u32 blocksize;
u16 numblocks;
u32 size;
-
- struct mtd_info *mtd;
- void *priv;
};
#endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8369564..1ca8e8f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -739,7 +739,7 @@
}
}
-static inline unsigned int blk_queue_zone_size(struct request_queue *q)
+static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
{
return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
}
@@ -1000,6 +1000,19 @@
return blk_rq_cur_bytes(rq) >> 9;
}
+/*
+ * Some commands like WRITE SAME have a payload or data transfer size which
+ * is different from the size of the request. Any driver that supports such
+ * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to
+ * calculate the data transfer size.
+ */
+static inline unsigned int blk_rq_payload_bytes(struct request *rq)
+{
+ if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+ return rq->special_vec.bv_len;
+ return blk_rq_bytes(rq);
+}
+
static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
int op)
{
@@ -1536,12 +1549,12 @@
return false;
}
-static inline unsigned int bdev_zone_size(struct block_device *bdev)
+static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q)
- return blk_queue_zone_size(q);
+ return blk_queue_zone_sectors(q);
return 0;
}
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 92bc89a..c970a25 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -21,20 +21,19 @@
*/
struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE];
struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE];
+ bool disallow_override[MAX_BPF_ATTACH_TYPE];
};
void cgroup_bpf_put(struct cgroup *cgrp);
void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent);
-void __cgroup_bpf_update(struct cgroup *cgrp,
- struct cgroup *parent,
- struct bpf_prog *prog,
- enum bpf_attach_type type);
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+ struct bpf_prog *prog, enum bpf_attach_type type,
+ bool overridable);
/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */
-void cgroup_bpf_update(struct cgroup *cgrp,
- struct bpf_prog *prog,
- enum bpf_attach_type type);
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, bool overridable);
int __cgroup_bpf_run_filter_skb(struct sock *sk,
struct sk_buff *skb,
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f74ae68..3ed1f3b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -216,7 +216,7 @@
u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
-int bpf_prog_calc_digest(struct bpf_prog *fp);
+int bpf_prog_calc_tag(struct bpf_prog *fp);
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
@@ -247,6 +247,8 @@
void bpf_map_put_with_uref(struct bpf_map *map);
void bpf_map_put(struct bpf_map *map);
int bpf_map_precharge_memlock(u32 pages);
+void *bpf_map_area_alloc(size_t size);
+void bpf_map_area_free(void *base);
extern int sysctl_unprivileged_bpf_disabled;
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index d67ab83..79591c3 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -243,12 +243,10 @@
{
if (err == 0)
return VM_FAULT_LOCKED;
- if (err == -EFAULT)
+ if (err == -EFAULT || err == -EAGAIN)
return VM_FAULT_NOPAGE;
if (err == -ENOMEM)
return VM_FAULT_OOM;
- if (err == -EAGAIN)
- return VM_FAULT_RETRY;
/* -ENOSPC, -EDQUOT, -EIO ... */
return VM_FAULT_SIGBUS;
}
diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index a087500..df08a41 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -45,10 +45,9 @@
extern int can_proto_register(const struct can_proto *cp);
extern void can_proto_unregister(const struct can_proto *cp);
-extern int can_rx_register(struct net_device *dev, canid_t can_id,
- canid_t mask,
- void (*func)(struct sk_buff *, void *),
- void *data, char *ident);
+int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+ void (*func)(struct sk_buff *, void *),
+ void *data, char *ident, struct sock *sk);
extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
canid_t mask,
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 0d442e3..5d3053c 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -224,4 +224,13 @@
#endif /* !CONFIG_GENERIC_CLOCKEVENTS */
+#define CLOCKEVENT_OF_DECLARE(name, compat, fn) \
+ OF_DECLARE_1_RET(clkevt, name, compat, fn)
+
+#ifdef CONFIG_CLKEVT_PROBE
+extern int clockevent_probe(void);
+#els
+static inline int clockevent_probe(void) { return 0; }
+#endif
+
#endif /* _LINUX_CLOCKCHIPS_H */
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index e315d04..cfc7584 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -62,6 +62,8 @@
* @archdata: arch-specific data
* @suspend: suspend function for the clocksource, if necessary
* @resume: resume function for the clocksource, if necessary
+ * @mark_unstable: Optional function to inform the clocksource driver that
+ * the watchdog marked the clocksource unstable
* @owner: module reference, must be set by clocksource in modules
*
* Note: This struct is not used in hotpathes of the timekeeping code
@@ -93,6 +95,7 @@
unsigned long flags;
void (*suspend)(struct clocksource *cs);
void (*resume)(struct clocksource *cs);
+ void (*mark_unstable)(struct clocksource *cs);
/* private: */
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 6360939..9e40be5 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -731,7 +731,25 @@
static inline bool in_compat_syscall(void) { return is_compat_task(); }
#endif
-#else
+/**
+ * ns_to_compat_timeval - Compat version of ns_to_timeval
+ * @nsec: the nanoseconds value to be converted
+ *
+ * Returns the compat_timeval representation of the nsec parameter.
+ */
+static inline struct compat_timeval ns_to_compat_timeval(s64 nsec)
+{
+ struct timeval tv;
+ struct compat_timeval ctv;
+
+ tv = ns_to_timeval(nsec);
+ ctv.tv_sec = tv.tv_sec;
+ ctv.tv_usec = tv.tv_usec;
+
+ return ctv;
+}
+
+#else /* !CONFIG_COMPAT */
#define is_compat_task() (0)
static inline bool in_compat_syscall(void) { return false; }
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index d016a12..28ffa94 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -14,6 +14,7 @@
extern int dump_skip(struct coredump_params *cprm, size_t nr);
extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
extern int dump_align(struct coredump_params *cprm, int align);
+extern void dump_truncate(struct coredump_params *cprm);
#ifdef CONFIG_COREDUMP
extern void do_coredump(const siginfo_t *siginfo);
#else
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 20bfefb..921acaa 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -8,9 +8,7 @@
CPUHP_CREATE_THREADS,
CPUHP_PERF_PREPARE,
CPUHP_PERF_X86_PREPARE,
- CPUHP_PERF_X86_UNCORE_PREP,
CPUHP_PERF_X86_AMD_UNCORE_PREP,
- CPUHP_PERF_X86_RAPL_PREP,
CPUHP_PERF_BFIN,
CPUHP_PERF_POWER,
CPUHP_PERF_SUPERH,
@@ -74,6 +72,8 @@
CPUHP_ZCOMP_PREPARE,
CPUHP_TIMERS_DEAD,
CPUHP_MIPS_SOC_PREPARE,
+ CPUHP_BP_PREPARE_DYN,
+ CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20,
CPUHP_BRINGUP_CPU,
CPUHP_AP_IDLE_DEAD,
CPUHP_AP_OFFLINE,
@@ -84,7 +84,6 @@
CPUHP_AP_IRQ_ARMADA_XP_STARTING,
CPUHP_AP_IRQ_BCM2836_STARTING,
CPUHP_AP_ARM_MVEBU_COHERENCY,
- CPUHP_AP_PERF_X86_UNCORE_STARTING,
CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
CPUHP_AP_PERF_X86_STARTING,
CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index c717f5e..96f1e88 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -560,7 +560,7 @@
static inline int cpumask_parse_user(const char __user *buf, int len,
struct cpumask *dstp)
{
- return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpu_ids);
+ return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
}
/**
@@ -575,7 +575,7 @@
struct cpumask *dstp)
{
return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
- nr_cpu_ids);
+ nr_cpumask_bits);
}
/**
@@ -590,7 +590,7 @@
char *nl = strchr(buf, '\n');
unsigned int len = nl ? (unsigned int)(nl - buf) : strlen(buf);
- return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpu_ids);
+ return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
}
/**
@@ -602,7 +602,7 @@
*/
static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
{
- return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpu_ids);
+ return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
}
/**
@@ -649,11 +649,15 @@
* used. Please use this_cpu_cpumask_var_t in those cases. The direct use
* of this_cpu_ptr() or this_cpu_read() will lead to failures when the
* other type of cpumask_var_t implementation is configured.
+ *
+ * Please also note that __cpumask_var_read_mostly can be used to declare
+ * a cpumask_var_t variable itself (not its content) as read mostly.
*/
#ifdef CONFIG_CPUMASK_OFFSTACK
typedef struct cpumask *cpumask_var_t;
-#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x)
+#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x)
+#define __cpumask_var_read_mostly __read_mostly
bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
@@ -667,6 +671,7 @@
typedef struct cpumask cpumask_var_t[1];
#define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
+#define __cpumask_var_read_mostly
static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
{
diff --git a/include/linux/cputime.h b/include/linux/cputime.h
index f2eb2ee..a691dc4 100644
--- a/include/linux/cputime.h
+++ b/include/linux/cputime.h
@@ -1,6 +1,7 @@
#ifndef __LINUX_CPUTIME_H
#define __LINUX_CPUTIME_H
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
#include <asm/cputime.h>
#ifndef cputime_to_nsecs
@@ -8,9 +9,5 @@
(cputime_to_usecs(__ct) * NSEC_PER_USEC)
#endif
-#ifndef nsecs_to_cputime
-# define nsecs_to_cputime(__nsecs) \
- usecs_to_cputime((__nsecs) / NSEC_PER_USEC)
-#endif
-
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
#endif /* __LINUX_CPUTIME_H */
diff --git a/include/linux/delay.h b/include/linux/delay.h
index a6ecb34..2ecb3c4 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -5,6 +5,17 @@
* Copyright (C) 1993 Linus Torvalds
*
* Delay routines, using a pre-computed "loops_per_jiffy" value.
+ *
+ * Please note that ndelay(), udelay() and mdelay() may return early for
+ * several reasons:
+ * 1. computed loops_per_jiffy too low (due to the time taken to
+ * execute the timer interrupt.)
+ * 2. cache behaviour affecting the time it takes to execute the
+ * loop function.
+ * 3. CPU clock rate changes.
+ *
+ * Please see this thread:
+ * http://lists.openwall.net/linux-kernel/2011/01/09/56
*/
#include <linux/kernel.h>
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 6cee17c..00e60f7 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -17,6 +17,7 @@
#ifndef _LINUX_DELAYACCT_H
#define _LINUX_DELAYACCT_H
+#include <uapi/linux/taskstats.h>
#include <linux/sched.h>
#include <linux/slab.h>
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 07c52c0..5b6adf9 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -190,8 +190,8 @@
* part of the memory details to the memory controller.
* @MEM_RMBS: Rambus DRAM, used on a few Pentium III/IV controllers.
* @MEM_DDR2: DDR2 RAM, as described at JEDEC JESD79-2F.
- * Those memories are labed as "PC2-" instead of "PC" to
- * differenciate from DDR.
+ * Those memories are labeled as "PC2-" instead of "PC" to
+ * differentiate from DDR.
* @MEM_FB_DDR2: Fully-Buffered DDR2, as described at JEDEC Std No. 205
* and JESD206.
* Those memories are accessed per DIMM slot, and not by
diff --git a/include/linux/efi-bgrt.h b/include/linux/efi-bgrt.h
index 051b21f..2fd3993 100644
--- a/include/linux/efi-bgrt.h
+++ b/include/linux/efi-bgrt.h
@@ -1,20 +1,19 @@
#ifndef _LINUX_EFI_BGRT_H
#define _LINUX_EFI_BGRT_H
-#ifdef CONFIG_ACPI_BGRT
-
#include <linux/acpi.h>
-void efi_bgrt_init(void);
+#ifdef CONFIG_ACPI_BGRT
+
+void efi_bgrt_init(struct acpi_table_header *table);
/* The BGRT data itself; only valid if bgrt_image != NULL. */
-extern void *bgrt_image;
extern size_t bgrt_image_size;
-extern struct acpi_table_bgrt *bgrt_tab;
+extern struct acpi_table_bgrt bgrt_tab;
#else /* !CONFIG_ACPI_BGRT */
-static inline void efi_bgrt_init(void) {}
+static inline void efi_bgrt_init(struct acpi_table_header *table) {}
#endif /* !CONFIG_ACPI_BGRT */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index a07a476..94d34e0 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -103,6 +103,7 @@
#define EFI_PAGE_SHIFT 12
#define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT)
+#define EFI_PAGES_MAX (U64_MAX >> EFI_PAGE_SHIFT)
typedef struct {
u32 type;
@@ -508,24 +509,6 @@
u64 query_variable_info;
} efi_runtime_services_64_t;
-typedef struct {
- efi_table_hdr_t hdr;
- void *get_time;
- void *set_time;
- void *get_wakeup_time;
- void *set_wakeup_time;
- void *set_virtual_address_map;
- void *convert_pointer;
- void *get_variable;
- void *get_next_variable;
- void *set_variable;
- void *get_next_high_mono_count;
- void *reset_system;
- void *update_capsule;
- void *query_capsule_caps;
- void *query_variable_info;
-} efi_runtime_services_t;
-
typedef efi_status_t efi_get_time_t (efi_time_t *tm, efi_time_cap_t *tc);
typedef efi_status_t efi_set_time_t (efi_time_t *tm);
typedef efi_status_t efi_get_wakeup_time_t (efi_bool_t *enabled, efi_bool_t *pending,
@@ -560,6 +543,24 @@
unsigned long size,
bool nonblocking);
+typedef struct {
+ efi_table_hdr_t hdr;
+ efi_get_time_t *get_time;
+ efi_set_time_t *set_time;
+ efi_get_wakeup_time_t *get_wakeup_time;
+ efi_set_wakeup_time_t *set_wakeup_time;
+ efi_set_virtual_address_map_t *set_virtual_address_map;
+ void *convert_pointer;
+ efi_get_variable_t *get_variable;
+ efi_get_next_variable_t *get_next_variable;
+ efi_set_variable_t *set_variable;
+ efi_get_next_high_mono_count_t *get_next_high_mono_count;
+ efi_reset_system_t *reset_system;
+ efi_update_capsule_t *update_capsule;
+ efi_query_capsule_caps_t *query_capsule_caps;
+ efi_query_variable_info_t *query_variable_info;
+} efi_runtime_services_t;
+
void efi_native_runtime_setup(void);
/*
@@ -610,6 +611,9 @@
#define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
#define APPLE_PROPERTIES_PROTOCOL_GUID EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb, 0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0)
+#define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f)
+#define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23)
+
/*
* This GUID is used to pass to the kernel proper the struct screen_info
* structure that was populated by the stub based on the GOP protocol instance
@@ -950,6 +954,7 @@
#endif
extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
+extern phys_addr_t __init efi_memmap_alloc(unsigned int num_entries);
extern int __init efi_memmap_init_early(struct efi_memory_map_data *data);
extern int __init efi_memmap_init_late(phys_addr_t addr, unsigned long size);
extern void __init efi_memmap_unmap(void);
@@ -1063,6 +1068,7 @@
#define EFI_ARCH_1 7 /* First arch-specific bit */
#define EFI_DBG 8 /* Print additional debug info at runtime */
#define EFI_NX_PE_DATA 9 /* Can runtime data regions be mapped non-executable? */
+#define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */
#ifdef CONFIG_EFI
/*
@@ -1238,17 +1244,17 @@
bool deleting;
};
-struct efi_simple_text_output_protocol_32 {
+typedef struct {
u32 reset;
u32 output_string;
u32 test_string;
-};
+} efi_simple_text_output_protocol_32_t;
-struct efi_simple_text_output_protocol_64 {
+typedef struct {
u64 reset;
u64 output_string;
u64 test_string;
-};
+} efi_simple_text_output_protocol_64_t;
struct efi_simple_text_output_protocol {
void *reset;
@@ -1474,6 +1480,14 @@
bool efi_runtime_disabled(void);
extern void efi_call_virt_check_flags(unsigned long flags, const char *call);
+enum efi_secureboot_mode {
+ efi_secureboot_mode_unset,
+ efi_secureboot_mode_unknown,
+ efi_secureboot_mode_disabled,
+ efi_secureboot_mode_enabled,
+};
+enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table);
+
/*
* Arch code can implement the following three template macros, avoiding
* reptition for the void/non-void return cases of {__,}efi_call_virt():
diff --git a/include/linux/export.h b/include/linux/export.h
index 2a0f61f..1a1dfdb 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -43,12 +43,19 @@
#ifdef CONFIG_MODVERSIONS
/* Mark the CRC weak since genksyms apparently decides not to
* generate a checksums for some symbols */
+#if defined(CONFIG_MODULE_REL_CRCS)
#define __CRC_SYMBOL(sym, sec) \
- extern __visible void *__crc_##sym __attribute__((weak)); \
- static const unsigned long __kcrctab_##sym \
- __used \
- __attribute__((section("___kcrctab" sec "+" #sym), used)) \
- = (unsigned long) &__crc_##sym;
+ asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \
+ " .weak " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \
+ " .long " VMLINUX_SYMBOL_STR(__crc_##sym) " - . \n" \
+ " .previous \n");
+#else
+#define __CRC_SYMBOL(sym, sec) \
+ asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \
+ " .weak " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \
+ " .long " VMLINUX_SYMBOL_STR(__crc_##sym) " \n" \
+ " .previous \n");
+#endif
#else
#define __CRC_SYMBOL(sym, sec)
#endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a0934e6..e4eb254 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -57,6 +57,8 @@
/* BPF program can access up to 512 bytes of stack space. */
#define MAX_BPF_STACK 512
+#define BPF_TAG_SIZE 8
+
/* Helper macros for filter block array initializers. */
/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
@@ -408,7 +410,7 @@
kmemcheck_bitfield_end(meta);
enum bpf_prog_type type; /* Type of BPF program */
u32 len; /* Number of filter blocks */
- u32 digest[SHA_DIGEST_WORDS]; /* Program digest */
+ u8 tag[BPF_TAG_SIZE];
struct bpf_prog_aux *aux; /* Auxiliary fields */
struct sock_fprog_kern *orig_prog; /* Original BPF program */
unsigned int (*bpf_func)(const void *ctx,
@@ -519,7 +521,7 @@
return prog->len * sizeof(struct bpf_insn);
}
-static inline u32 bpf_prog_digest_scratch_size(const struct bpf_prog *prog)
+static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog)
{
return round_up(bpf_prog_insn_size(prog) +
sizeof(__be64) + 1, SHA_MESSAGE_BYTES);
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 13ba552..4c467ef 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -360,6 +360,7 @@
#define FSCACHE_OBJECT_IS_AVAILABLE 5 /* T if object has become active */
#define FSCACHE_OBJECT_RETIRED 6 /* T if object was retired on relinquishment */
#define FSCACHE_OBJECT_KILLED_BY_CACHE 7 /* T if object was killed by the cache */
+#define FSCACHE_OBJECT_RUN_AFTER_DEAD 8 /* T if object has been dispatched after death */
struct list_head cache_link; /* link in cache->object_list */
struct hlist_node cookie_link; /* link in cookie->backing_objects */
diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h
index 3f9778c..c332f0a 100644
--- a/include/linux/fsl_ifc.h
+++ b/include/linux/fsl_ifc.h
@@ -733,8 +733,12 @@
__be32 nand_erattr1;
u32 res19[0x10];
__be32 nand_fsr;
- u32 res20[0x3];
- __be32 nand_eccstat[6];
+ u32 res20;
+ /* The V1 nand_eccstat is actually 4 words that overlaps the
+ * V2 nand_eccstat.
+ */
+ __be32 v1_nand_eccstat[2];
+ __be32 v2_nand_eccstat[6];
u32 res21[0x1c];
__be32 nanndcr;
u32 res22[0x2];
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index c2748ac..e973fab 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -274,37 +274,67 @@
struct irq_chip *irqchip,
int parent_irq);
-int _gpiochip_irqchip_add(struct gpio_chip *gpiochip,
- struct irq_chip *irqchip,
- unsigned int first_irq,
- irq_flow_handler_t handler,
- unsigned int type,
- bool nested,
- struct lock_class_key *lock_key);
+int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip,
+ struct irq_chip *irqchip,
+ unsigned int first_irq,
+ irq_flow_handler_t handler,
+ unsigned int type,
+ bool nested,
+ struct lock_class_key *lock_key);
-/* FIXME: I assume threaded IRQchips do not have the lockdep problem */
+#ifdef CONFIG_LOCKDEP
+
+/*
+ * Lockdep requires that each irqchip instance be created with a
+ * unique key so as to avoid unnecessary warnings. This upfront
+ * boilerplate static inlines provides such a key for each
+ * unique instance.
+ */
+static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
+ struct irq_chip *irqchip,
+ unsigned int first_irq,
+ irq_flow_handler_t handler,
+ unsigned int type)
+{
+ static struct lock_class_key key;
+
+ return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq,
+ handler, type, false, &key);
+}
+
static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip,
struct irq_chip *irqchip,
unsigned int first_irq,
irq_flow_handler_t handler,
unsigned int type)
{
- return _gpiochip_irqchip_add(gpiochip, irqchip, first_irq,
- handler, type, true, NULL);
+
+ static struct lock_class_key key;
+
+ return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq,
+ handler, type, true, &key);
+}
+#else
+static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
+ struct irq_chip *irqchip,
+ unsigned int first_irq,
+ irq_flow_handler_t handler,
+ unsigned int type)
+{
+ return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq,
+ handler, type, false, NULL);
}
-#ifdef CONFIG_LOCKDEP
-#define gpiochip_irqchip_add(...) \
-( \
- ({ \
- static struct lock_class_key _key; \
- _gpiochip_irqchip_add(__VA_ARGS__, false, &_key); \
- }) \
-)
-#else
-#define gpiochip_irqchip_add(...) \
- _gpiochip_irqchip_add(__VA_ARGS__, false, NULL)
-#endif
+static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip,
+ struct irq_chip *irqchip,
+ unsigned int first_irq,
+ irq_flow_handler_t handler,
+ unsigned int type)
+{
+ return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq,
+ handler, type, true, NULL);
+}
+#endif /* CONFIG_LOCKDEP */
#endif /* CONFIG_GPIOLIB_IRQCHIP */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index cdab81b..e52b427 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -88,12 +88,6 @@
* @base: pointer to the timer base (per cpu and per clock)
* @state: state information (See bit values above)
* @is_rel: Set if the timer was armed relative
- * @start_pid: timer statistics field to store the pid of the task which
- * started the timer
- * @start_site: timer statistics field to store the site where the timer
- * was started
- * @start_comm: timer statistics field to store the name of the process which
- * started the timer
*
* The hrtimer structure must be initialized by hrtimer_init()
*/
@@ -104,11 +98,6 @@
struct hrtimer_clock_base *base;
u8 state;
u8 is_rel;
-#ifdef CONFIG_TIMER_STATS
- int start_pid;
- void *start_site;
- char start_comm[16];
-#endif
};
/**
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 42fe43f..183efde 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -128,6 +128,7 @@
u32 ring_data_startoffset;
u32 priv_write_index;
u32 priv_read_index;
+ u32 cached_read_index;
};
/*
@@ -180,6 +181,19 @@
return write;
}
+static inline u32 hv_get_cached_bytes_to_write(
+ const struct hv_ring_buffer_info *rbi)
+{
+ u32 read_loc, write_loc, dsize, write;
+
+ dsize = rbi->ring_datasize;
+ read_loc = rbi->cached_read_index;
+ write_loc = rbi->ring_buffer->write_index;
+
+ write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
+ read_loc - write_loc;
+ return write;
+}
/*
* VMBUS version is 32 bit entity broken up into
* two 16 bit quantities: major_number. minor_number.
@@ -1488,7 +1502,7 @@
static inline void hv_signal_on_read(struct vmbus_channel *channel)
{
- u32 cur_write_sz;
+ u32 cur_write_sz, cached_write_sz;
u32 pending_sz;
struct hv_ring_buffer_info *rbi = &channel->inbound;
@@ -1512,12 +1526,24 @@
cur_write_sz = hv_get_bytes_to_write(rbi);
- if (cur_write_sz >= pending_sz)
+ if (cur_write_sz < pending_sz)
+ return;
+
+ cached_write_sz = hv_get_cached_bytes_to_write(rbi);
+ if (cached_write_sz < pending_sz)
vmbus_setevent(channel);
return;
}
+static inline void
+init_cached_read_index(struct vmbus_channel *channel)
+{
+ struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+ rbi->cached_read_index = rbi->ring_buffer->read_index;
+}
+
/*
* An API to support in-place processing of incoming VMBUS packets.
*/
@@ -1569,6 +1595,8 @@
* This call commits the read index and potentially signals the host.
* Here is the pattern for using the "in-place" consumption APIs:
*
+ * init_cached_read_index();
+ *
* while (get_next_pkt_raw() {
* process the packet "in-place";
* put_pkt_raw();
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index b2109c5..4b45ec4 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -665,6 +665,7 @@
#define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */
/* Must equal I2C_M_TEN below */
#define I2C_CLIENT_SLAVE 0x20 /* we are the slave */
+#define I2C_CLIENT_HOST_NOTIFY 0x40 /* We want to use I2C host notify */
#define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */
#define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */
/* Must match I2C_M_STOP|IGNORE_NAK */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 325f649..3a85d61 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -42,6 +42,27 @@
#define INIT_PREV_CPUTIME(x)
#endif
+#ifdef CONFIG_POSIX_TIMERS
+#define INIT_POSIX_TIMERS(s) \
+ .posix_timers = LIST_HEAD_INIT(s.posix_timers),
+#define INIT_CPU_TIMERS(s) \
+ .cpu_timers = { \
+ LIST_HEAD_INIT(s.cpu_timers[0]), \
+ LIST_HEAD_INIT(s.cpu_timers[1]), \
+ LIST_HEAD_INIT(s.cpu_timers[2]), \
+ },
+#define INIT_CPUTIMER(s) \
+ .cputimer = { \
+ .cputime_atomic = INIT_CPUTIME_ATOMIC, \
+ .running = false, \
+ .checking_timer = false, \
+ },
+#else
+#define INIT_POSIX_TIMERS(s)
+#define INIT_CPU_TIMERS(s)
+#define INIT_CPUTIMER(s)
+#endif
+
#define INIT_SIGNALS(sig) { \
.nr_threads = 1, \
.thread_head = LIST_HEAD_INIT(init_task.thread_node), \
@@ -49,14 +70,10 @@
.shared_pending = { \
.list = LIST_HEAD_INIT(sig.shared_pending.list), \
.signal = {{0}}}, \
- .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \
- .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \
+ INIT_POSIX_TIMERS(sig) \
+ INIT_CPU_TIMERS(sig) \
.rlim = INIT_RLIMITS, \
- .cputimer = { \
- .cputime_atomic = INIT_CPUTIME_ATOMIC, \
- .running = false, \
- .checking_timer = false, \
- }, \
+ INIT_CPUTIMER(sig) \
INIT_PREV_CPUTIME(sig) \
.cred_guard_mutex = \
__MUTEX_INITIALIZER(sig.cred_guard_mutex), \
@@ -247,7 +264,7 @@
.blocked = {{0}}, \
.alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \
.journal_info = NULL, \
- .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \
+ INIT_CPU_TIMERS(tsk) \
.pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \
.timer_slack_ns = 50000, /* 50 usec default slack */ \
.pids = { \
@@ -274,13 +291,6 @@
}
-#define INIT_CPU_TIMERS(cpu_timers) \
-{ \
- LIST_HEAD_INIT(cpu_timers[0]), \
- LIST_HEAD_INIT(cpu_timers[1]), \
- LIST_HEAD_INIT(cpu_timers[2]), \
-}
-
/* Attach to the init_task data structure for proper alignment */
#define __init_task_data __attribute__((__section__(".data..init_task")))
diff --git a/include/linux/irq.h b/include/linux/irq.h
index e798755..f887351 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -184,6 +184,7 @@
*
* IRQD_TRIGGER_MASK - Mask for the trigger type bits
* IRQD_SETAFFINITY_PENDING - Affinity setting is pending
+ * IRQD_ACTIVATED - Interrupt has already been activated
* IRQD_NO_BALANCING - Balancing disabled for this IRQ
* IRQD_PER_CPU - Interrupt is per cpu
* IRQD_AFFINITY_SET - Interrupt affinity was set
@@ -202,6 +203,7 @@
enum {
IRQD_TRIGGER_MASK = 0xf,
IRQD_SETAFFINITY_PENDING = (1 << 8),
+ IRQD_ACTIVATED = (1 << 9),
IRQD_NO_BALANCING = (1 << 10),
IRQD_PER_CPU = (1 << 11),
IRQD_AFFINITY_SET = (1 << 12),
@@ -312,6 +314,21 @@
return __irqd_to_state(d) & IRQD_AFFINITY_MANAGED;
}
+static inline bool irqd_is_activated(struct irq_data *d)
+{
+ return __irqd_to_state(d) & IRQD_ACTIVATED;
+}
+
+static inline void irqd_set_activated(struct irq_data *d)
+{
+ __irqd_to_state(d) |= IRQD_ACTIVATED;
+}
+
+static inline void irqd_clr_activated(struct irq_data *d)
+{
+ __irqd_to_state(d) &= ~IRQD_ACTIVATED;
+}
+
#undef __irqd_to_state
static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
@@ -715,6 +732,10 @@
int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
struct module *owner, const struct cpumask *affinity);
+int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from,
+ unsigned int cnt, int node, struct module *owner,
+ const struct cpumask *affinity);
+
/* use macros to avoid needing export.h for THIS_MODULE */
#define irq_alloc_descs(irq, from, cnt, node) \
__irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL)
@@ -731,6 +752,21 @@
#define irq_alloc_descs_from(from, cnt, node) \
irq_alloc_descs(-1, from, cnt, node)
+#define devm_irq_alloc_descs(dev, irq, from, cnt, node) \
+ __devm_irq_alloc_descs(dev, irq, from, cnt, node, THIS_MODULE, NULL)
+
+#define devm_irq_alloc_desc(dev, node) \
+ devm_irq_alloc_descs(dev, -1, 0, 1, node)
+
+#define devm_irq_alloc_desc_at(dev, at, node) \
+ devm_irq_alloc_descs(dev, at, at, 1, node)
+
+#define devm_irq_alloc_desc_from(dev, from, node) \
+ devm_irq_alloc_descs(dev, -1, from, 1, node)
+
+#define devm_irq_alloc_descs_from(dev, from, cnt, node) \
+ devm_irq_alloc_descs(dev, -1, from, cnt, node)
+
void irq_free_descs(unsigned int irq, unsigned int cnt);
static inline void irq_free_desc(unsigned int irq)
{
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index e808f8a..725e86b 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -73,7 +73,6 @@
#define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1)
#define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32)
-#define GICD_TYPER_LPIS (1U << 17)
#define GICD_IROUTER_SPI_MODE_ONE (0U << 31)
#define GICD_IROUTER_SPI_MODE_ANY (1U << 31)
@@ -306,7 +305,7 @@
#define GITS_BASER_TYPE_NONE 0
#define GITS_BASER_TYPE_DEVICE 1
#define GITS_BASER_TYPE_VCPU 2
-#define GITS_BASER_TYPE_CPU 3
+#define GITS_BASER_TYPE_RESERVED3 3
#define GITS_BASER_TYPE_COLLECTION 4
#define GITS_BASER_TYPE_RESERVED5 5
#define GITS_BASER_TYPE_RESERVED6 6
@@ -320,8 +319,6 @@
#define GITS_CMD_MAPD 0x08
#define GITS_CMD_MAPC 0x09
#define GITS_CMD_MAPTI 0x0a
-/* older GIC documentation used MAPVI for this command */
-#define GITS_CMD_MAPVI GITS_CMD_MAPTI
#define GITS_CMD_MAPI 0x0b
#define GITS_CMD_MOVI 0x01
#define GITS_CMD_DISCARD 0x0f
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 589d14e..624215c 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -293,6 +293,8 @@
return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC;
}
+extern u64 jiffies64_to_nsecs(u64 j);
+
extern unsigned long __msecs_to_jiffies(const unsigned int m);
#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
/*
diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h
index 089f70f..23da3af 100644
--- a/include/linux/jump_label_ratelimit.h
+++ b/include/linux/jump_label_ratelimit.h
@@ -14,6 +14,7 @@
#ifdef HAVE_JUMP_LABEL
extern void static_key_slow_dec_deferred(struct static_key_deferred *key);
+extern void static_key_deferred_flush(struct static_key_deferred *key);
extern void
jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl);
@@ -26,6 +27,10 @@
STATIC_KEY_CHECK_USE();
static_key_slow_dec(&key->key);
}
+static inline void static_key_deferred_flush(struct static_key_deferred *key)
+{
+ STATIC_KEY_CHECK_USE();
+}
static inline void
jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 56aec84..cb09238 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -514,8 +514,8 @@
#define TAINT_FLAGS_COUNT 16
struct taint_flag {
- char true; /* character printed when tainted */
- char false; /* character printed when not tainted */
+ char c_true; /* character printed when tainted */
+ char c_false; /* character printed when not tainted */
bool module; /* also show as a per-module taint flag */
};
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 00f7768..66be8b6 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -9,7 +9,6 @@
#include <linux/sched.h>
#include <linux/vtime.h>
#include <asm/irq.h>
-#include <linux/cputime.h>
/*
* 'kernel_stat.h' contains the definitions needed for doing
@@ -78,15 +77,18 @@
return kstat_cpu(cpu).irqs_sum;
}
-extern void account_user_time(struct task_struct *, cputime_t);
-extern void account_system_time(struct task_struct *, int, cputime_t);
-extern void account_steal_time(cputime_t);
-extern void account_idle_time(cputime_t);
+extern void account_user_time(struct task_struct *, u64);
+extern void account_guest_time(struct task_struct *, u64);
+extern void account_system_time(struct task_struct *, int, u64);
+extern void account_system_index_time(struct task_struct *, u64,
+ enum cpu_usage_stat);
+extern void account_steal_time(u64);
+extern void account_idle_time(u64);
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
static inline void account_process_tick(struct task_struct *tsk, int user)
{
- vtime_account_user(tsk);
+ vtime_flush(tsk);
}
#else
extern void account_process_tick(struct task_struct *, int user);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 8f68490..16ddfb8 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -278,9 +278,13 @@
int nr_garbage;
};
+#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c);
extern void __free_insn_slot(struct kprobe_insn_cache *c,
kprobe_opcode_t *slot, int dirty);
+/* sleep-less address checking routine */
+extern bool __is_insn_slot_addr(struct kprobe_insn_cache *c,
+ unsigned long addr);
#define DEFINE_INSN_CACHE_OPS(__name) \
extern struct kprobe_insn_cache kprobe_##__name##_slots; \
@@ -294,6 +298,18 @@
{ \
__free_insn_slot(&kprobe_##__name##_slots, slot, dirty); \
} \
+ \
+static inline bool is_kprobe_##__name##_slot(unsigned long addr) \
+{ \
+ return __is_insn_slot_addr(&kprobe_##__name##_slots, addr); \
+}
+#else /* __ARCH_WANT_KPROBES_INSN_SLOT */
+#define DEFINE_INSN_CACHE_OPS(__name) \
+static inline bool is_kprobe_##__name##_slot(unsigned long addr) \
+{ \
+ return 0; \
+}
+#endif
DEFINE_INSN_CACHE_OPS(insn);
@@ -330,7 +346,6 @@
int write, void __user *buffer,
size_t *length, loff_t *ppos);
#endif
-
#endif /* CONFIG_OPTPROBES */
#ifdef CONFIG_KPROBES_ON_FTRACE
extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
@@ -481,6 +496,19 @@
return enable_kprobe(&jp->kp);
}
+#ifndef CONFIG_KPROBES
+static inline bool is_kprobe_insn_slot(unsigned long addr)
+{
+ return false;
+}
+#endif
+#ifndef CONFIG_OPTPROBES
+static inline bool is_kprobe_optinsn_slot(unsigned long addr)
+{
+ return false;
+}
+#endif
+
#ifdef CONFIG_KPROBES
/*
* Blacklist ganerating macro. Specify functions which is not probed
diff --git a/include/linux/llist.h b/include/linux/llist.h
index fd4ca0b..171baa9 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -3,28 +3,33 @@
/*
* Lock-less NULL terminated single linked list
*
- * If there are multiple producers and multiple consumers, llist_add
- * can be used in producers and llist_del_all can be used in
- * consumers. They can work simultaneously without lock. But
- * llist_del_first can not be used here. Because llist_del_first
- * depends on list->first->next does not changed if list->first is not
- * changed during its operation, but llist_del_first, llist_add,
- * llist_add (or llist_del_all, llist_add, llist_add) sequence in
- * another consumer may violate that.
+ * Cases where locking is not needed:
+ * If there are multiple producers and multiple consumers, llist_add can be
+ * used in producers and llist_del_all can be used in consumers simultaneously
+ * without locking. Also a single consumer can use llist_del_first while
+ * multiple producers simultaneously use llist_add, without any locking.
*
- * If there are multiple producers and one consumer, llist_add can be
- * used in producers and llist_del_all or llist_del_first can be used
- * in the consumer.
+ * Cases where locking is needed:
+ * If we have multiple consumers with llist_del_first used in one consumer, and
+ * llist_del_first or llist_del_all used in other consumers, then a lock is
+ * needed. This is because llist_del_first depends on list->first->next not
+ * changing, but without lock protection, there's no way to be sure about that
+ * if a preemption happens in the middle of the delete operation and on being
+ * preempted back, the list->first is the same as before causing the cmpxchg in
+ * llist_del_first to succeed. For example, while a llist_del_first operation
+ * is in progress in one consumer, then a llist_del_first, llist_add,
+ * llist_add (or llist_del_all, llist_add, llist_add) sequence in another
+ * consumer may cause violations.
*
- * This can be summarized as follow:
+ * This can be summarized as follows:
*
* | add | del_first | del_all
* add | - | - | -
* del_first | | L | L
* del_all | | | -
*
- * Where "-" stands for no lock is needed, while "L" stands for lock
- * is needed.
+ * Where, a particular row's operation can happen concurrently with a column's
+ * operation, with "-" being no lock needed, while "L" being lock is needed.
*
* The list entries deleted via llist_del_all can be traversed with
* traversing function such as llist_for_each etc. But the list
diff --git a/include/linux/log2.h b/include/linux/log2.h
index fd7ff3d..ef3d4f6 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -203,6 +203,17 @@
* ... and so on.
*/
-#define order_base_2(n) ilog2(roundup_pow_of_two(n))
+static inline __attribute_const__
+int __order_base_2(unsigned long n)
+{
+ return n > 1 ? ilog2(n - 1) + 1 : 0;
+}
+#define order_base_2(n) \
+( \
+ __builtin_constant_p(n) ? ( \
+ ((n) == 0 || (n) == 1) ? 0 : \
+ ilog2((n) - 1) + 1) : \
+ __order_base_2(n) \
+)
#endif /* _LINUX_LOG2_H */
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 6e8b5b2..80690c9 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -133,6 +133,16 @@
return ret;
}
+#ifndef mul_u32_u32
+/*
+ * Many a GCC version messes this up and generates a 64x64 mult :-(
+ */
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+ return (u64)a * b;
+}
+#endif
+
#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
#ifndef mul_u64_u32_shr
@@ -160,9 +170,9 @@
al = a;
ah = a >> 32;
- ret = ((u64)al * mul) >> shift;
+ ret = mul_u32_u32(al, mul) >> shift;
if (ah)
- ret += ((u64)ah * mul) << (32 - shift);
+ ret += mul_u32_u32(ah, mul) << (32 - shift);
return ret;
}
@@ -186,10 +196,10 @@
a0.ll = a;
b0.ll = b;
- rl.ll = (u64)a0.l.low * b0.l.low;
- rm.ll = (u64)a0.l.low * b0.l.high;
- rn.ll = (u64)a0.l.high * b0.l.low;
- rh.ll = (u64)a0.l.high * b0.l.high;
+ rl.ll = mul_u32_u32(a0.l.low, b0.l.low);
+ rm.ll = mul_u32_u32(a0.l.low, b0.l.high);
+ rn.ll = mul_u32_u32(a0.l.high, b0.l.low);
+ rh.ll = mul_u32_u32(a0.l.high, b0.l.high);
/*
* Each of these lines computes a 64-bit intermediate result into "c",
@@ -229,8 +239,8 @@
} u, rl, rh;
u.ll = a;
- rl.ll = (u64)u.l.low * mul;
- rh.ll = (u64)u.l.high * mul + rl.l.high;
+ rl.ll = mul_u32_u32(u.l.low, mul);
+ rh.ll = mul_u32_u32(u.l.high, mul) + rl.l.high;
/* Bits 32-63 of the result will be in rh.l.low. */
rl.l.high = do_div(rh.ll, divisor);
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 01033fa..134a2f6 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -85,7 +85,8 @@
extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
/* VM interface that may be used by firmware interface */
extern int online_pages(unsigned long, unsigned long, int);
-extern int test_pages_in_a_zone(unsigned long, unsigned long);
+extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long *valid_start, unsigned long *valid_end);
extern void __offline_isolated_pages(unsigned long, unsigned long);
typedef void (*online_page_callback_t)(struct page *page);
@@ -284,7 +285,7 @@
unsigned long map_offset);
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
unsigned long pnum);
-extern int zone_can_shift(unsigned long pfn, unsigned long nr_pages,
- enum zone_type target);
+extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages,
+ enum zone_type target, int *zone_shift);
#endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h
index a4860bc..f848ee8 100644
--- a/include/linux/mfd/axp20x.h
+++ b/include/linux/mfd/axp20x.h
@@ -13,7 +13,7 @@
#include <linux/regmap.h>
-enum {
+enum axp20x_variants {
AXP152_ID = 0,
AXP202_ID,
AXP209_ID,
@@ -532,35 +532,6 @@
const struct regmap_irq_chip *regmap_irq_chip;
};
-#define BATTID_LEN 64
-#define OCV_CURVE_SIZE 32
-#define MAX_THERM_CURVE_SIZE 25
-#define PD_DEF_MIN_TEMP 0
-#define PD_DEF_MAX_TEMP 55
-
-struct axp20x_fg_pdata {
- char battid[BATTID_LEN + 1];
- int design_cap;
- int min_volt;
- int max_volt;
- int max_temp;
- int min_temp;
- int cap1;
- int cap0;
- int rdc1;
- int rdc0;
- int ocv_curve[OCV_CURVE_SIZE];
- int tcsz;
- int thermistor_curve[MAX_THERM_CURVE_SIZE][2];
-};
-
-struct axp20x_chrg_pdata {
- int max_cc;
- int max_cv;
- int def_cc;
- int def_cv;
-};
-
struct axp288_extcon_pdata {
/* GPIO pin control to switch D+/D- lines b/w PMIC and SOC */
struct gpio_desc *gpio_mux_cntl;
diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h
index 2b300b4..fba8fcb 100644
--- a/include/linux/mfd/lpc_ich.h
+++ b/include/linux/mfd/lpc_ich.h
@@ -20,6 +20,8 @@
#ifndef LPC_ICH_H
#define LPC_ICH_H
+#include <linux/platform_data/intel-spi.h>
+
/* GPIO resources */
#define ICH_RES_GPIO 0
#define ICH_RES_GPE0 1
@@ -40,6 +42,7 @@
char name[32];
unsigned int iTCO_version;
unsigned int gpio_version;
+ enum intel_spi_type spi_type;
u8 use_gpio;
};
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 257173e..f541da6 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -35,6 +35,8 @@
#define PHY_ID_KSZ886X 0x00221430
#define PHY_ID_KSZ8863 0x00221435
+#define PHY_ID_KSZ8795 0x00221550
+
/* struct phy_device dev_flags definitions */
#define MICREL_PHY_50MHZ_CLK 0x00000001
#define MICREL_PHY_FXEN 0x00000002
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 36d9896..f4aac87 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -972,12 +972,16 @@
* @zonelist - The zonelist to search for a suitable zone
* @highest_zoneidx - The zone index of the highest zone to return
* @nodes - An optional nodemask to filter the zonelist with
- * @zone - The first suitable zone found is returned via this parameter
+ * @return - Zoneref pointer for the first suitable zone found (see below)
*
* This function returns the first zone at or below a given zone index that is
* within the allowed nodemask. The zoneref returned is a cursor that can be
* used to iterate the zonelist with next_zones_zonelist by advancing it by
* one before calling.
+ *
+ * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is
+ * never NULL). This may happen either genuinely, or due to concurrent nodemask
+ * update due to cpuset modification.
*/
static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
enum zone_type highest_zoneidx,
diff --git a/include/linux/module.h b/include/linux/module.h
index 7c84273..cc7cba2 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -346,7 +346,7 @@
/* Exported symbols */
const struct kernel_symbol *syms;
- const unsigned long *crcs;
+ const s32 *crcs;
unsigned int num_syms;
/* Kernel parameters. */
@@ -359,18 +359,18 @@
/* GPL-only exported symbols. */
unsigned int num_gpl_syms;
const struct kernel_symbol *gpl_syms;
- const unsigned long *gpl_crcs;
+ const s32 *gpl_crcs;
#ifdef CONFIG_UNUSED_SYMBOLS
/* unused exported symbols. */
const struct kernel_symbol *unused_syms;
- const unsigned long *unused_crcs;
+ const s32 *unused_crcs;
unsigned int num_unused_syms;
/* GPL-only, unused exported symbols. */
unsigned int num_unused_gpl_syms;
const struct kernel_symbol *unused_gpl_syms;
- const unsigned long *unused_gpl_crcs;
+ const s32 *unused_gpl_crcs;
#endif
#ifdef CONFIG_MODULE_SIG
@@ -382,7 +382,7 @@
/* symbols that will be GPL-only in the near future. */
const struct kernel_symbol *gpl_future_syms;
- const unsigned long *gpl_future_crcs;
+ const s32 *gpl_future_crcs;
unsigned int num_gpl_future_syms;
/* Exception table */
@@ -523,7 +523,7 @@
struct symsearch {
const struct kernel_symbol *start, *stop;
- const unsigned long *crcs;
+ const s32 *crcs;
enum {
NOT_GPL_ONLY,
GPL_ONLY,
@@ -539,7 +539,7 @@
*/
const struct kernel_symbol *find_symbol(const char *name,
struct module **owner,
- const unsigned long **crc,
+ const s32 **crc,
bool gplok,
bool warn);
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 0db320b..a83b84f 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -17,7 +17,13 @@
struct pci_dev;
struct platform_msi_priv_data;
void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+#ifdef CONFIG_GENERIC_MSI_IRQ
void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
+#else
+static inline void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+}
+#endif
typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc,
struct msi_msg *msg);
@@ -116,11 +122,15 @@
struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc);
void *msi_desc_to_pci_sysdata(struct msi_desc *desc);
+void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg);
#else /* CONFIG_PCI_MSI */
static inline void *msi_desc_to_pci_sysdata(struct msi_desc *desc)
{
return NULL;
}
+static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+}
#endif /* CONFIG_PCI_MSI */
struct msi_desc *alloc_msi_entry(struct device *dev, int nvec,
@@ -128,7 +138,6 @@
void free_msi_entry(struct msi_desc *entry);
void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
-void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg);
u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag);
u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h
deleted file mode 100644
index ad3c348..0000000
--- a/include/linux/mtd/fsmc.h
+++ /dev/null
@@ -1,156 +0,0 @@
-/*
- * incude/mtd/fsmc.h
- *
- * ST Microelectronics
- * Flexible Static Memory Controller (FSMC)
- * platform data interface and header file
- *
- * Copyright © 2010 ST Microelectronics
- * Vipin Kumar <vipin.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __MTD_FSMC_H
-#define __MTD_FSMC_H
-
-#include <linux/io.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/physmap.h>
-#include <linux/types.h>
-#include <linux/mtd/partitions.h>
-#include <asm/param.h>
-
-#define FSMC_NAND_BW8 1
-#define FSMC_NAND_BW16 2
-
-#define FSMC_MAX_NOR_BANKS 4
-#define FSMC_MAX_NAND_BANKS 4
-
-#define FSMC_FLASH_WIDTH8 1
-#define FSMC_FLASH_WIDTH16 2
-
-/* fsmc controller registers for NOR flash */
-#define CTRL 0x0
- /* ctrl register definitions */
- #define BANK_ENABLE (1 << 0)
- #define MUXED (1 << 1)
- #define NOR_DEV (2 << 2)
- #define WIDTH_8 (0 << 4)
- #define WIDTH_16 (1 << 4)
- #define RSTPWRDWN (1 << 6)
- #define WPROT (1 << 7)
- #define WRT_ENABLE (1 << 12)
- #define WAIT_ENB (1 << 13)
-
-#define CTRL_TIM 0x4
- /* ctrl_tim register definitions */
-
-#define FSMC_NOR_BANK_SZ 0x8
-#define FSMC_NOR_REG_SIZE 0x40
-
-#define FSMC_NOR_REG(base, bank, reg) (base + \
- FSMC_NOR_BANK_SZ * (bank) + \
- reg)
-
-/* fsmc controller registers for NAND flash */
-#define PC 0x00
- /* pc register definitions */
- #define FSMC_RESET (1 << 0)
- #define FSMC_WAITON (1 << 1)
- #define FSMC_ENABLE (1 << 2)
- #define FSMC_DEVTYPE_NAND (1 << 3)
- #define FSMC_DEVWID_8 (0 << 4)
- #define FSMC_DEVWID_16 (1 << 4)
- #define FSMC_ECCEN (1 << 6)
- #define FSMC_ECCPLEN_512 (0 << 7)
- #define FSMC_ECCPLEN_256 (1 << 7)
- #define FSMC_TCLR_1 (1)
- #define FSMC_TCLR_SHIFT (9)
- #define FSMC_TCLR_MASK (0xF)
- #define FSMC_TAR_1 (1)
- #define FSMC_TAR_SHIFT (13)
- #define FSMC_TAR_MASK (0xF)
-#define STS 0x04
- /* sts register definitions */
- #define FSMC_CODE_RDY (1 << 15)
-#define COMM 0x08
- /* comm register definitions */
- #define FSMC_TSET_0 0
- #define FSMC_TSET_SHIFT 0
- #define FSMC_TSET_MASK 0xFF
- #define FSMC_TWAIT_6 6
- #define FSMC_TWAIT_SHIFT 8
- #define FSMC_TWAIT_MASK 0xFF
- #define FSMC_THOLD_4 4
- #define FSMC_THOLD_SHIFT 16
- #define FSMC_THOLD_MASK 0xFF
- #define FSMC_THIZ_1 1
- #define FSMC_THIZ_SHIFT 24
- #define FSMC_THIZ_MASK 0xFF
-#define ATTRIB 0x0C
-#define IOATA 0x10
-#define ECC1 0x14
-#define ECC2 0x18
-#define ECC3 0x1C
-#define FSMC_NAND_BANK_SZ 0x20
-
-#define FSMC_NAND_REG(base, bank, reg) (base + FSMC_NOR_REG_SIZE + \
- (FSMC_NAND_BANK_SZ * (bank)) + \
- reg)
-
-#define FSMC_BUSY_WAIT_TIMEOUT (1 * HZ)
-
-struct fsmc_nand_timings {
- uint8_t tclr;
- uint8_t tar;
- uint8_t thiz;
- uint8_t thold;
- uint8_t twait;
- uint8_t tset;
-};
-
-enum access_mode {
- USE_DMA_ACCESS = 1,
- USE_WORD_ACCESS,
-};
-
-/**
- * fsmc_nand_platform_data - platform specific NAND controller config
- * @nand_timings: timing setup for the physical NAND interface
- * @partitions: partition table for the platform, use a default fallback
- * if this is NULL
- * @nr_partitions: the number of partitions in the previous entry
- * @options: different options for the driver
- * @width: bus width
- * @bank: default bank
- * @select_bank: callback to select a certain bank, this is
- * platform-specific. If the controller only supports one bank
- * this may be set to NULL
- */
-struct fsmc_nand_platform_data {
- struct fsmc_nand_timings *nand_timings;
- struct mtd_partition *partitions;
- unsigned int nr_partitions;
- unsigned int options;
- unsigned int width;
- unsigned int bank;
-
- enum access_mode mode;
-
- void (*select_bank)(uint32_t bank, uint32_t busw);
-
- /* priv structures for dma accesses */
- void *read_dma_priv;
- void *write_dma_priv;
-};
-
-extern int __init fsmc_nor_init(struct platform_device *pdev,
- unsigned long base, uint32_t bank, uint32_t width);
-extern void __init fsmc_init_board_info(struct platform_device *pdev,
- struct mtd_partition *partitions, unsigned int nr_partitions,
- unsigned int width);
-
-#endif /* __MTD_FSMC_H */
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 13f8052..eebdc63 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -24,6 +24,7 @@
#include <linux/uio.h>
#include <linux/notifier.h>
#include <linux/device.h>
+#include <linux/of.h>
#include <mtd/mtd-abi.h>
@@ -322,6 +323,7 @@
int (*_block_isreserved) (struct mtd_info *mtd, loff_t ofs);
int (*_block_isbad) (struct mtd_info *mtd, loff_t ofs);
int (*_block_markbad) (struct mtd_info *mtd, loff_t ofs);
+ int (*_max_bad_blocks) (struct mtd_info *mtd, loff_t ofs, size_t len);
int (*_suspend) (struct mtd_info *mtd);
void (*_resume) (struct mtd_info *mtd);
void (*_reboot) (struct mtd_info *mtd);
@@ -385,6 +387,8 @@
struct device_node *np)
{
mtd->dev.of_node = np;
+ if (!mtd->name)
+ of_property_read_string(np, "label", &mtd->name);
}
static inline struct device_node *mtd_get_of_node(struct mtd_info *mtd)
@@ -397,6 +401,18 @@
return ops->mode == MTD_OPS_AUTO_OOB ? mtd->oobavail : mtd->oobsize;
}
+static inline int mtd_max_bad_blocks(struct mtd_info *mtd,
+ loff_t ofs, size_t len)
+{
+ if (!mtd->_max_bad_blocks)
+ return -ENOTSUPP;
+
+ if (mtd->size < (len + ofs) || ofs < 0)
+ return -EINVAL;
+
+ return mtd->_max_bad_blocks(mtd, ofs, len);
+}
+
int mtd_wunit_to_pairing_info(struct mtd_info *mtd, int wunit,
struct mtd_pairing_info *info);
int mtd_pairing_info_to_wunit(struct mtd_info *mtd,
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index c5f3a01..9591e0f 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -615,7 +615,7 @@
* @tALS_min: ALE setup time
* @tAR_min: ALE to RE# delay
* @tCEA_max: CE# access time
- * @tCEH_min:
+ * @tCEH_min: CE# high hold time
* @tCH_min: CE# hold time
* @tCHZ_max: CE# high to output hi-Z
* @tCLH_min: CLE hold time
@@ -801,6 +801,10 @@
* supported, 0 otherwise.
* @jedec_params: [INTERN] holds the JEDEC parameter page when JEDEC is
* supported, 0 otherwise.
+ * @max_bb_per_die: [INTERN] the max number of bad blocks each die of a
+ * this nand device will encounter their life times.
+ * @blocks_per_die: [INTERN] The number of PEBs in a die
+ * @data_interface: [INTERN] NAND interface timing information
* @read_retries: [INTERN] the number of read retry modes supported
* @onfi_set_features: [REPLACEABLE] set the features for ONFI nand
* @onfi_get_features: [REPLACEABLE] get the features for ONFI nand
@@ -883,6 +887,8 @@
struct nand_onfi_params onfi_params;
struct nand_jedec_params jedec_params;
};
+ u16 max_bb_per_die;
+ u32 blocks_per_die;
struct nand_data_interface *data_interface;
@@ -958,6 +964,7 @@
#define NAND_MFR_SANDISK 0x45
#define NAND_MFR_INTEL 0x89
#define NAND_MFR_ATO 0x9b
+#define NAND_MFR_WINBOND 0xef
/* The maximum expected count of bytes in the NAND ID sequence */
#define NAND_MAX_ID_LEN 8
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index 70736e1..06df1e0 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -41,6 +41,7 @@
uint64_t size; /* partition size */
uint64_t offset; /* offset within the master MTD space */
uint32_t mask_flags; /* master MTD flags to mask out for this partition */
+ struct device_node *of_node;
};
#define MTDPART_OFS_RETAIN (-3)
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index c425c7b..f2a7180 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -43,9 +43,13 @@
#define SPINOR_OP_WRSR 0x01 /* Write status register 1 byte */
#define SPINOR_OP_READ 0x03 /* Read data bytes (low frequency) */
#define SPINOR_OP_READ_FAST 0x0b /* Read data bytes (high frequency) */
-#define SPINOR_OP_READ_1_1_2 0x3b /* Read data bytes (Dual SPI) */
-#define SPINOR_OP_READ_1_1_4 0x6b /* Read data bytes (Quad SPI) */
+#define SPINOR_OP_READ_1_1_2 0x3b /* Read data bytes (Dual Output SPI) */
+#define SPINOR_OP_READ_1_2_2 0xbb /* Read data bytes (Dual I/O SPI) */
+#define SPINOR_OP_READ_1_1_4 0x6b /* Read data bytes (Quad Output SPI) */
+#define SPINOR_OP_READ_1_4_4 0xeb /* Read data bytes (Quad I/O SPI) */
#define SPINOR_OP_PP 0x02 /* Page program (up to 256 bytes) */
+#define SPINOR_OP_PP_1_1_4 0x32 /* Quad page program */
+#define SPINOR_OP_PP_1_4_4 0x38 /* Quad page program */
#define SPINOR_OP_BE_4K 0x20 /* Erase 4KiB block */
#define SPINOR_OP_BE_4K_PMC 0xd7 /* Erase 4KiB block on PMC chips */
#define SPINOR_OP_BE_32K 0x52 /* Erase 32KiB block */
@@ -56,11 +60,17 @@
#define SPINOR_OP_RDFSR 0x70 /* Read flag status register */
/* 4-byte address opcodes - used on Spansion and some Macronix flashes. */
-#define SPINOR_OP_READ4 0x13 /* Read data bytes (low frequency) */
-#define SPINOR_OP_READ4_FAST 0x0c /* Read data bytes (high frequency) */
-#define SPINOR_OP_READ4_1_1_2 0x3c /* Read data bytes (Dual SPI) */
-#define SPINOR_OP_READ4_1_1_4 0x6c /* Read data bytes (Quad SPI) */
+#define SPINOR_OP_READ_4B 0x13 /* Read data bytes (low frequency) */
+#define SPINOR_OP_READ_FAST_4B 0x0c /* Read data bytes (high frequency) */
+#define SPINOR_OP_READ_1_1_2_4B 0x3c /* Read data bytes (Dual Output SPI) */
+#define SPINOR_OP_READ_1_2_2_4B 0xbc /* Read data bytes (Dual I/O SPI) */
+#define SPINOR_OP_READ_1_1_4_4B 0x6c /* Read data bytes (Quad Output SPI) */
+#define SPINOR_OP_READ_1_4_4_4B 0xec /* Read data bytes (Quad I/O SPI) */
#define SPINOR_OP_PP_4B 0x12 /* Page program (up to 256 bytes) */
+#define SPINOR_OP_PP_1_1_4_4B 0x34 /* Quad page program */
+#define SPINOR_OP_PP_1_4_4_4B 0x3e /* Quad page program */
+#define SPINOR_OP_BE_4K_4B 0x21 /* Erase 4KiB block */
+#define SPINOR_OP_BE_32K_4B 0x5c /* Erase 32KiB block */
#define SPINOR_OP_SE_4B 0xdc /* Sector erase (usually 64KiB) */
/* Used for SST flashes only. */
@@ -68,6 +78,15 @@
#define SPINOR_OP_WRDI 0x04 /* Write disable */
#define SPINOR_OP_AAI_WP 0xad /* Auto address increment word program */
+/* Used for S3AN flashes only */
+#define SPINOR_OP_XSE 0x50 /* Sector erase */
+#define SPINOR_OP_XPP 0x82 /* Page program */
+#define SPINOR_OP_XRDSR 0xd7 /* Read status register */
+
+#define XSR_PAGESIZE BIT(0) /* Page size in Po2 or Linear */
+#define XSR_RDY BIT(7) /* Ready */
+
+
/* Used for Macronix and Winbond flashes. */
#define SPINOR_OP_EN4B 0xb7 /* Enter 4-byte mode */
#define SPINOR_OP_EX4B 0xe9 /* Exit 4-byte mode */
@@ -119,6 +138,9 @@
enum spi_nor_option_flags {
SNOR_F_USE_FSR = BIT(0),
SNOR_F_HAS_SR_TB = BIT(1),
+ SNOR_F_NO_OP_CHIP_ERASE = BIT(2),
+ SNOR_F_S3AN_ADDR_DEFAULT = BIT(3),
+ SNOR_F_READY_XSR_RDY = BIT(4),
};
/**
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index e17942f..1127fe3 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -159,10 +159,12 @@
unsigned int subclass);
extern int __must_check mutex_lock_killable_nested(struct mutex *lock,
unsigned int subclass);
+extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass);
#define mutex_lock(lock) mutex_lock_nested(lock, 0)
#define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0)
#define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0)
+#define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0)
#define mutex_lock_nest_lock(lock, nest_lock) \
do { \
@@ -174,11 +176,13 @@
extern void mutex_lock(struct mutex *lock);
extern int __must_check mutex_lock_interruptible(struct mutex *lock);
extern int __must_check mutex_lock_killable(struct mutex *lock);
+extern void mutex_lock_io(struct mutex *lock);
# define mutex_lock_nested(lock, subclass) mutex_lock(lock)
# define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
# define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
+# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock)
#endif
/*
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9bde955..2791467 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -866,11 +866,15 @@
* of useless work if you return NETDEV_TX_BUSY.
* Required; cannot be NULL.
*
- * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
- * netdev_features_t features);
- * Adjusts the requested feature flags according to device-specific
- * constraints, and returns the resulting flags. Must not modify
- * the device state.
+ * netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
+ * struct net_device *dev
+ * netdev_features_t features);
+ * Called by core transmit path to determine if device is capable of
+ * performing offload operations on a given packet. This is to give
+ * the device an opportunity to implement any restrictions that cannot
+ * be otherwise expressed by feature flags. The check is called with
+ * the set of features that the stack has calculated and it returns
+ * those the driver believes to be appropriate.
*
* u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
* void *accel_priv, select_queue_fallback_t fallback);
@@ -1028,6 +1032,12 @@
* Called to release previously enslaved netdev.
*
* Feature/offload setting functions.
+ * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
+ * netdev_features_t features);
+ * Adjusts the requested feature flags according to device-specific
+ * constraints, and returns the resulting flags. Must not modify
+ * the device state.
+ *
* int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);
* Called to update device configuration to new features. Passed
* feature set might be less than what was returned by ndo_fix_features()).
@@ -1100,15 +1110,6 @@
* Callback to use for xmit over the accelerated station. This
* is used in place of ndo_start_xmit on accelerated net
* devices.
- * netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
- * struct net_device *dev
- * netdev_features_t features);
- * Called by core transmit path to determine if device is capable of
- * performing offload operations on a given packet. This is to give
- * the device an opportunity to implement any restrictions that cannot
- * be otherwise expressed by feature flags. The check is called with
- * the set of features that the stack has calculated and it returns
- * those the driver believes to be appropriate.
* int (*ndo_set_tx_maxrate)(struct net_device *dev,
* int queue_index, u32 maxrate);
* Called when a user wants to set a max-rate limitation of specific
@@ -1510,6 +1511,7 @@
* @max_mtu: Interface Maximum MTU value
* @type: Interface hardware type
* @hard_header_len: Maximum hardware header length.
+ * @min_header_len: Minimum hardware header length
*
* @needed_headroom: Extra headroom the hardware may need, but not in all
* cases can this be guaranteed
@@ -1727,6 +1729,7 @@
unsigned int max_mtu;
unsigned short type;
unsigned short hard_header_len;
+ unsigned short min_header_len;
unsigned short needed_headroom;
unsigned short needed_tailroom;
@@ -2693,6 +2696,8 @@
{
if (likely(len >= dev->hard_header_len))
return true;
+ if (len < dev->min_header_len)
+ return false;
if (capable(CAP_SYS_RAWIO)) {
memset(ll_header + len, 0, dev->hard_header_len - len);
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index bca5363..1b1ca04 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -282,7 +282,7 @@
static inline bool seqid_mutating_err(u32 err)
{
- /* rfc 3530 section 8.1.5: */
+ /* See RFC 7530, section 9.1.7 */
switch (err) {
case NFS4ERR_STALE_CLIENTID:
case NFS4ERR_STALE_STATEID:
@@ -291,6 +291,7 @@
case NFS4ERR_BADXDR:
case NFS4ERR_RESOURCE:
case NFS4ERR_NOFILEHANDLE:
+ case NFS4ERR_MOVED:
return false;
};
return true;
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index aacca82..0a3fadc 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -110,6 +110,7 @@
extern int watchdog_thresh;
extern unsigned long watchdog_enabled;
extern unsigned long *watchdog_cpumask_bits;
+extern atomic_t watchdog_park_in_progress;
#ifdef CONFIG_SMP
extern int sysctl_softlockup_all_cpu_backtrace;
extern int sysctl_hardlockup_all_cpu_backtrace;
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 1c7eec0..3a481a4 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -204,7 +204,7 @@
static inline bool percpu_ref_tryget(struct percpu_ref *ref)
{
unsigned long __percpu *percpu_count;
- int ret;
+ bool ret;
rcu_read_lock_sched();
@@ -238,7 +238,7 @@
static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
{
unsigned long __percpu *percpu_count;
- int ret = false;
+ bool ret = false;
rcu_read_lock_sched();
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4741ecd..000fdb2 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -482,6 +482,7 @@
* @list: list of filters for this event
* @lock: spinlock that serializes accesses to the @list and event's
* (and its children's) filter generations.
+ * @nr_file_filters: number of file-based filters
*
* A child event will use parent's @list (and therefore @lock), so they are
* bundled together; see perf_event_addr_filters().
@@ -489,6 +490,7 @@
struct perf_addr_filters_head {
struct list_head list;
raw_spinlock_t lock;
+ unsigned int nr_file_filters;
};
/**
@@ -785,9 +787,9 @@
ktime_t hrtimer_interval;
unsigned int hrtimer_active;
- struct pmu *unique_pmu;
#ifdef CONFIG_CGROUP_PERF
struct perf_cgroup *cgrp;
+ struct list_head cgrp_cpuctx_entry;
#endif
struct list_head sched_cb_entry;
@@ -1259,6 +1261,7 @@
extern void perf_event_disable_local(struct perf_event *event);
extern void perf_event_disable_inatomic(struct perf_event *event);
extern void perf_event_task_tick(void);
+extern int perf_event_account_interrupt(struct perf_event *event);
#else /* !CONFIG_PERF_EVENTS: */
static inline void *
perf_aux_output_begin(struct perf_output_handle *handle,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index f7d95f6..7fc1105 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -25,7 +25,6 @@
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/mod_devicetable.h>
-#include <linux/phy_led_triggers.h>
#include <linux/atomic.h>
diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h
index a2daea0..b37b05b 100644
--- a/include/linux/phy_led_triggers.h
+++ b/include/linux/phy_led_triggers.h
@@ -18,11 +18,11 @@
#ifdef CONFIG_LED_TRIGGER_PHY
#include <linux/leds.h>
+#include <linux/phy.h>
#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 10
-#define PHY_MII_BUS_ID_SIZE (20 - 3)
-#define PHY_LINK_LED_TRIGGER_NAME_SIZE (PHY_MII_BUS_ID_SIZE + \
+#define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \
FIELD_SIZEOF(struct mdio_device, addr)+\
PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE)
diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h
new file mode 100644
index 0000000..942b0c3
--- /dev/null
+++ b/include/linux/platform_data/intel-spi.h
@@ -0,0 +1,31 @@
+/*
+ * Intel PCH/PCU SPI flash driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef INTEL_SPI_PDATA_H
+#define INTEL_SPI_PDATA_H
+
+enum intel_spi_type {
+ INTEL_SPI_BYT = 1,
+ INTEL_SPI_LPT,
+ INTEL_SPI_BXT,
+};
+
+/**
+ * struct intel_spi_boardinfo - Board specific data for Intel SPI driver
+ * @type: Type which this controller is compatible with
+ * @writeable: The chip is writeable
+ */
+struct intel_spi_boardinfo {
+ enum intel_spi_type type;
+ bool writeable;
+};
+
+#endif /* INTEL_SPI_PDATA_H */
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 62d44c1..64aa189 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -8,19 +8,9 @@
#include <linux/alarmtimer.h>
-static inline unsigned long long cputime_to_expires(cputime_t expires)
-{
- return (__force unsigned long long)expires;
-}
-
-static inline cputime_t expires_to_cputime(unsigned long long expires)
-{
- return (__force cputime_t)expires;
-}
-
struct cpu_timer_list {
struct list_head entry;
- unsigned long long expires, incr;
+ u64 expires, incr;
struct task_struct *task;
int firing;
};
@@ -129,7 +119,7 @@
void posix_cpu_timers_exit(struct task_struct *task);
void posix_cpu_timers_exit_group(struct task_struct *task);
void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
- cputime_t *newval, cputime_t *oldval);
+ u64 *newval, u64 *oldval);
long clock_nanosleep_restart(struct restart_block *restart_block);
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index bed9557..b312bce 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -4,8 +4,16 @@
enum bq27xxx_chip {
BQ27000 = 1, /* bq27000, bq27200 */
BQ27010, /* bq27010, bq27210 */
- BQ27500, /* bq27500 */
- BQ27510, /* bq27510, bq27520 */
+ BQ2750X, /* bq27500 deprecated alias */
+ BQ2751X, /* bq27510, bq27520 deprecated alias */
+ BQ27500, /* bq27500/1 */
+ BQ27510G1, /* bq27510G1 */
+ BQ27510G2, /* bq27510G2 */
+ BQ27510G3, /* bq27510G3 */
+ BQ27520G1, /* bq27520G1 */
+ BQ27520G2, /* bq27520G2 */
+ BQ27520G3, /* bq27520G3 */
+ BQ27520G4, /* bq27520G4 */
BQ27530, /* bq27530, bq27531 */
BQ27541, /* bq27541, bq27542, bq27546, bq27742 */
BQ27545, /* bq27545 */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 321f9ed..6ade6a5 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -444,6 +444,10 @@
#error "Unknown RCU implementation specified to kernel configuration"
#endif
+#define RCU_SCHEDULER_INACTIVE 0
+#define RCU_SCHEDULER_INIT 1
+#define RCU_SCHEDULER_RUNNING 2
+
/*
* init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
* initialization and destruction of rcu_head on the stack. rcu_head structures
@@ -1157,5 +1161,17 @@
ftrace_dump(oops_dump_mode); \
} while (0)
+/*
+ * Place this after a lock-acquisition primitive to guarantee that
+ * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies
+ * if the UNLOCK and LOCK are executed by the same CPU or if the
+ * UNLOCK and LOCK operate on the same lock variable.
+ */
+#ifdef CONFIG_PPC
+#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */
+#else /* #ifdef CONFIG_PPC */
+#define smp_mb__after_unlock_lock() do { } while (0)
+#endif /* #else #ifdef CONFIG_PPC */
+
#endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index ac81e40..4f9b2fa 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -27,6 +27,12 @@
#include <linux/cache.h>
+struct rcu_dynticks;
+static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
+{
+ return 0;
+}
+
static inline unsigned long get_state_synchronize_rcu(void)
{
return 0;
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index e2f3a32..8265d35 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -408,7 +408,8 @@
* @crash_comp: completion used to sync crash handler and the rproc reload
* @recovery_disabled: flag that state if recovery was disabled
* @max_notifyid: largest allocated notify id.
- * @table_ptr: our copy of the resource table
+ * @table_ptr: pointer to the resource table in effect
+ * @cached_table: copy of the resource table
* @has_iommu: flag to indicate if remote processor is behind an MMU
*/
struct rproc {
@@ -440,6 +441,7 @@
bool recovery_disabled;
int max_notifyid;
struct resource_table *table_ptr;
+ struct resource_table *cached_table;
bool has_iommu;
bool auto_boot;
};
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1cc0ded..c8e519d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -29,7 +29,6 @@
#include <asm/page.h>
#include <asm/ptrace.h>
-#include <linux/cputime.h>
#include <linux/smp.h>
#include <linux/sem.h>
@@ -436,12 +435,10 @@
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);
+extern int __must_check io_schedule_prepare(void);
+extern void io_schedule_finish(int token);
extern long io_schedule_timeout(long timeout);
-
-static inline void io_schedule(void)
-{
- io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
-}
+extern void io_schedule(void);
void __noreturn do_task_dead(void);
@@ -540,15 +537,13 @@
int ac_flag;
long ac_exitcode;
unsigned long ac_mem;
- cputime_t ac_utime, ac_stime;
+ u64 ac_utime, ac_stime;
unsigned long ac_minflt, ac_majflt;
};
struct cpu_itimer {
- cputime_t expires;
- cputime_t incr;
- u32 error;
- u32 incr_error;
+ u64 expires;
+ u64 incr;
};
/**
@@ -562,8 +557,8 @@
*/
struct prev_cputime {
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- cputime_t utime;
- cputime_t stime;
+ u64 utime;
+ u64 stime;
raw_spinlock_t lock;
#endif
};
@@ -578,8 +573,8 @@
/**
* struct task_cputime - collected CPU time counts
- * @utime: time spent in user mode, in &cputime_t units
- * @stime: time spent in kernel mode, in &cputime_t units
+ * @utime: time spent in user mode, in nanoseconds
+ * @stime: time spent in kernel mode, in nanoseconds
* @sum_exec_runtime: total time spent on the CPU, in nanoseconds
*
* This structure groups together three kinds of CPU time that are tracked for
@@ -587,8 +582,8 @@
* these counts together and treat all three of them in parallel.
*/
struct task_cputime {
- cputime_t utime;
- cputime_t stime;
+ u64 utime;
+ u64 stime;
unsigned long long sum_exec_runtime;
};
@@ -597,13 +592,6 @@
#define prof_exp stime
#define sched_exp sum_exec_runtime
-#define INIT_CPUTIME \
- (struct task_cputime) { \
- .utime = 0, \
- .stime = 0, \
- .sum_exec_runtime = 0, \
- }
-
/*
* This is the atomic variant of task_cputime, which can be used for
* storing and updating task_cputime statistics without locking.
@@ -709,13 +697,14 @@
unsigned int is_child_subreaper:1;
unsigned int has_child_subreaper:1;
+#ifdef CONFIG_POSIX_TIMERS
+
/* POSIX.1b Interval Timers */
int posix_timer_id;
struct list_head posix_timers;
/* ITIMER_REAL timer for the process */
struct hrtimer real_timer;
- struct pid *leader_pid;
ktime_t it_real_incr;
/*
@@ -734,12 +723,16 @@
/* Earliest-expiration cache. */
struct task_cputime cputime_expires;
+ struct list_head cpu_timers[3];
+
+#endif
+
+ struct pid *leader_pid;
+
#ifdef CONFIG_NO_HZ_FULL
atomic_t tick_dep_mask;
#endif
- struct list_head cpu_timers[3];
-
struct pid *tty_old_pgrp;
/* boolean value for session group leader */
@@ -757,9 +750,9 @@
* in __exit_signal, except for the group leader.
*/
seqlock_t stats_lock;
- cputime_t utime, stime, cutime, cstime;
- cputime_t gtime;
- cputime_t cgtime;
+ u64 utime, stime, cutime, cstime;
+ u64 gtime;
+ u64 cgtime;
struct prev_cputime prev_cputime;
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
@@ -1644,11 +1637,11 @@
int __user *set_child_tid; /* CLONE_CHILD_SETTID */
int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */
- cputime_t utime, stime;
+ u64 utime, stime;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
- cputime_t utimescaled, stimescaled;
+ u64 utimescaled, stimescaled;
#endif
- cputime_t gtime;
+ u64 gtime;
struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
seqcount_t vtime_seqcount;
@@ -1672,8 +1665,10 @@
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
unsigned long min_flt, maj_flt;
+#ifdef CONFIG_POSIX_TIMERS
struct task_cputime cputime_expires;
struct list_head cpu_timers[3];
+#endif
/* process credentials */
const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */
@@ -1798,7 +1793,7 @@
#if defined(CONFIG_TASK_XACCT)
u64 acct_rss_mem1; /* accumulated rss usage */
u64 acct_vm_mem1; /* accumulated virtual memory usage */
- cputime_t acct_timexpd; /* stime + utime since last update */
+ u64 acct_timexpd; /* stime + utime since last update */
#endif
#ifdef CONFIG_CPUSETS
nodemask_t mems_allowed; /* Protected by alloc_lock */
@@ -2243,17 +2238,17 @@
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
extern void task_cputime(struct task_struct *t,
- cputime_t *utime, cputime_t *stime);
-extern cputime_t task_gtime(struct task_struct *t);
+ u64 *utime, u64 *stime);
+extern u64 task_gtime(struct task_struct *t);
#else
static inline void task_cputime(struct task_struct *t,
- cputime_t *utime, cputime_t *stime)
+ u64 *utime, u64 *stime)
{
*utime = t->utime;
*stime = t->stime;
}
-static inline cputime_t task_gtime(struct task_struct *t)
+static inline u64 task_gtime(struct task_struct *t)
{
return t->gtime;
}
@@ -2261,23 +2256,23 @@
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
static inline void task_cputime_scaled(struct task_struct *t,
- cputime_t *utimescaled,
- cputime_t *stimescaled)
+ u64 *utimescaled,
+ u64 *stimescaled)
{
*utimescaled = t->utimescaled;
*stimescaled = t->stimescaled;
}
#else
static inline void task_cputime_scaled(struct task_struct *t,
- cputime_t *utimescaled,
- cputime_t *stimescaled)
+ u64 *utimescaled,
+ u64 *stimescaled)
{
task_cputime(t, utimescaled, stimescaled);
}
#endif
-extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
-extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
+extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
/*
* Per process flags
@@ -2496,10 +2491,18 @@
extern void sched_clock_init(void);
#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static inline void sched_clock_init_late(void)
+{
+}
+
static inline void sched_clock_tick(void)
{
}
+static inline void clear_sched_clock_stable(void)
+{
+}
+
static inline void sched_clock_idle_sleep_event(void)
{
}
@@ -2518,6 +2521,7 @@
return sched_clock();
}
#else
+extern void sched_clock_init_late(void);
/*
* Architectures can set this to 1 if they have specified
* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
@@ -2525,7 +2529,6 @@
* is reliable after all:
*/
extern int sched_clock_stable(void);
-extern void set_sched_clock_stable(void);
extern void clear_sched_clock_stable(void);
extern void sched_clock_tick(void);
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 4411453..49308e1 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -59,6 +59,7 @@
extern unsigned int sysctl_sched_autogroup_enabled;
#endif
+extern int sysctl_sched_rr_timeslice;
extern int sched_rr_timeslice;
extern int sched_rr_handler(struct ctl_table *table, int write,
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index dc8eb63..a598cf3 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -33,9 +33,9 @@
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
-struct srcu_struct_array {
- unsigned long c[2];
- unsigned long seq[2];
+struct srcu_array {
+ unsigned long lock_count[2];
+ unsigned long unlock_count[2];
};
struct rcu_batch {
@@ -46,7 +46,7 @@
struct srcu_struct {
unsigned long completed;
- struct srcu_struct_array __percpu *per_cpu_ref;
+ struct srcu_array __percpu *per_cpu_ref;
spinlock_t queue_lock; /* protect ->batch_queue, ->running */
bool running;
/* callbacks just queued */
@@ -118,7 +118,7 @@
* See include/linux/percpu-defs.h for the rules on per-CPU variables.
*/
#define __DEFINE_SRCU(name, is_static) \
- static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
+ static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 85cc819..333ad11 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -216,5 +216,6 @@
void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *);
bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt,
const struct sockaddr *sap);
+void rpc_cleanup_clids(void);
#endif /* __KERNEL__ */
#endif /* _LINUX_SUNRPC_CLNT_H */
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index e5d1934..7440290 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -66,6 +66,7 @@
#define XPT_LISTENER 10 /* listening endpoint */
#define XPT_CACHE_AUTH 11 /* cache auth info */
#define XPT_LOCAL 12 /* connection from loopback interface */
+#define XPT_KILL_TEMP 13 /* call xpo_kill_temp_xprt before closing */
struct svc_serv *xpt_server; /* service for transport */
atomic_t xpt_reserved; /* space on outq that is rsvd */
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 0c729c3..d971837 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -194,8 +194,6 @@
};
#ifdef CONFIG_SUSPEND
-extern suspend_state_t mem_sleep_default;
-
/**
* suspend_set_ops - set platform dependent suspend operations
* @ops: The new suspend operations to set.
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index fc5848d..c93f4b3 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -62,8 +62,13 @@
/* TCP Fast Open Cookie as stored in memory */
struct tcp_fastopen_cookie {
+ union {
+ u8 val[TCP_FASTOPEN_COOKIE_MAX];
+#if IS_ENABLED(CONFIG_IPV6)
+ struct in6_addr addr;
+#endif
+ };
s8 len;
- u8 val[TCP_FASTOPEN_COOKIE_MAX];
bool exp; /* In RFC6994 experimental option format */
};
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 51d601f..5a209b8 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -20,11 +20,6 @@
unsigned long data;
u32 flags;
-#ifdef CONFIG_TIMER_STATS
- int start_pid;
- void *start_site;
- char start_comm[16];
-#endif
#ifdef CONFIG_LOCKDEP
struct lockdep_map lockdep_map;
#endif
@@ -197,46 +192,6 @@
*/
#define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1)
-/*
- * Timer-statistics info:
- */
-#ifdef CONFIG_TIMER_STATS
-
-extern int timer_stats_active;
-
-extern void init_timer_stats(void);
-
-extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
- void *timerf, char *comm, u32 flags);
-
-extern void __timer_stats_timer_set_start_info(struct timer_list *timer,
- void *addr);
-
-static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
-{
- if (likely(!timer_stats_active))
- return;
- __timer_stats_timer_set_start_info(timer, __builtin_return_address(0));
-}
-
-static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
-{
- timer->start_site = NULL;
-}
-#else
-static inline void init_timer_stats(void)
-{
-}
-
-static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
-{
-}
-
-static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
-{
-}
-#endif
-
extern void add_timer(struct timer_list *timer);
extern int try_to_del_timer_sync(struct timer_list *timer);
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 6620400..5209b5e 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -56,7 +56,8 @@
static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
struct virtio_net_hdr *hdr,
- bool little_endian)
+ bool little_endian,
+ bool has_data_valid)
{
memset(hdr, 0, sizeof(*hdr)); /* no info leak */
@@ -91,7 +92,8 @@
skb_checksum_start_offset(skb));
hdr->csum_offset = __cpu_to_virtio16(little_endian,
skb->csum_offset);
- } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+ } else if (has_data_valid &&
+ skb->ip_summed == CHECKSUM_UNNECESSARY) {
hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
} /* else everything is zero */
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index aa9bfea..0681fe2 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -58,27 +58,28 @@
extern void vtime_account_system(struct task_struct *tsk);
extern void vtime_account_idle(struct task_struct *tsk);
-extern void vtime_account_user(struct task_struct *tsk);
#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
static inline void vtime_task_switch(struct task_struct *prev) { }
static inline void vtime_account_system(struct task_struct *tsk) { }
-static inline void vtime_account_user(struct task_struct *tsk) { }
#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
extern void arch_vtime_task_switch(struct task_struct *tsk);
+extern void vtime_account_user(struct task_struct *tsk);
extern void vtime_user_enter(struct task_struct *tsk);
static inline void vtime_user_exit(struct task_struct *tsk)
{
vtime_account_user(tsk);
}
+
extern void vtime_guest_enter(struct task_struct *tsk);
extern void vtime_guest_exit(struct task_struct *tsk);
extern void vtime_init_idle(struct task_struct *tsk, int cpu);
#else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */
+static inline void vtime_account_user(struct task_struct *tsk) { }
static inline void vtime_user_enter(struct task_struct *tsk) { }
static inline void vtime_user_exit(struct task_struct *tsk) { }
static inline void vtime_guest_enter(struct task_struct *tsk) { }
@@ -93,9 +94,11 @@
/* On hard|softirq exit we always account to hard|softirq cputime */
vtime_account_system(tsk);
}
+extern void vtime_flush(struct task_struct *tsk);
#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
static inline void vtime_account_irq_exit(struct task_struct *tsk) { }
+static inline void vtime_flush(struct task_struct *tsk) { }
#endif
diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index 3ebb168..a34b141 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -309,6 +309,10 @@
}
for (opt_iter = 6; opt_iter < opt_len;) {
+ if (opt_iter + 1 == opt_len) {
+ err_offset = opt_iter;
+ goto out;
+ }
tag_len = opt[opt_iter + 1];
if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) {
err_offset = opt_iter + 1;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 487e573..dbf0abb 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -776,6 +776,11 @@
{
u32 hash;
+ /* @flowlabel may include more than a flow label, eg, the traffic class.
+ * Here we want only the flow label value.
+ */
+ flowlabel &= IPV6_FLOWLABEL_MASK;
+
if (flowlabel ||
net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF ||
(!autolabel &&
@@ -871,7 +876,7 @@
* upper-layer output functions
*/
int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
- struct ipv6_txoptions *opt, int tclass);
+ __u32 mark, struct ipv6_txoptions *opt, int tclass);
int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr);
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index d4c1c75..0388b9c 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -44,6 +44,8 @@
int (*get_encap_size)(struct lwtunnel_state *lwtstate);
int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b);
int (*xmit)(struct sk_buff *skb);
+
+ struct module *owner;
};
#ifdef CONFIG_LWTUNNEL
@@ -105,6 +107,8 @@
unsigned int num);
int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
unsigned int num);
+int lwtunnel_valid_encap_type(u16 encap_type);
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len);
int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
struct nlattr *encap,
unsigned int family, const void *cfg,
@@ -168,6 +172,18 @@
return -EOPNOTSUPP;
}
+static inline int lwtunnel_valid_encap_type(u16 encap_type)
+{
+ return -EOPNOTSUPP;
+}
+static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len)
+{
+ /* return 0 since we are not walking attr looking for
+ * RTA_ENCAP_TYPE attribute on nexthops.
+ */
+ return 0;
+}
+
static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
struct nlattr *encap,
unsigned int family, const void *cfg,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 924325c..7dfdb51 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -207,9 +207,9 @@
unsigned int skip;
int err;
int (*fn)(const struct nft_ctx *ctx,
- const struct nft_set *set,
+ struct nft_set *set,
const struct nft_set_iter *iter,
- const struct nft_set_elem *elem);
+ struct nft_set_elem *elem);
};
/**
@@ -301,7 +301,7 @@
void (*remove)(const struct nft_set *set,
const struct nft_set_elem *elem);
void (*walk)(const struct nft_ctx *ctx,
- const struct nft_set *set,
+ struct nft_set *set,
struct nft_set_iter *iter);
unsigned int (*privsize)(const struct nlattr * const nla[]);
diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h
index cbedda0..5ceb220 100644
--- a/include/net/netfilter/nft_fib.h
+++ b/include/net/netfilter/nft_fib.h
@@ -9,6 +9,12 @@
extern const struct nla_policy nft_fib_policy[];
+static inline bool
+nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in)
+{
+ return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK;
+}
+
int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr);
int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
const struct nlattr * const tb[]);
diff --git a/include/net/sock.h b/include/net/sock.h
index f0e867f..c4f5e6f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2006,7 +2006,9 @@
void sk_stop_timer(struct sock *sk, struct timer_list *timer);
int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
- unsigned int flags);
+ unsigned int flags,
+ void (*destructor)(struct sock *sk,
+ struct sk_buff *skb));
int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 958a24d..b567e44 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -352,6 +352,20 @@
}
}
+static inline enum ib_mtu ib_mtu_int_to_enum(int mtu)
+{
+ if (mtu >= 4096)
+ return IB_MTU_4096;
+ else if (mtu >= 2048)
+ return IB_MTU_2048;
+ else if (mtu >= 1024)
+ return IB_MTU_1024;
+ else if (mtu >= 512)
+ return IB_MTU_512;
+ else
+ return IB_MTU_256;
+}
+
enum ib_port_state {
IB_PORT_NOP = 0,
IB_PORT_DOWN = 1,
diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h
index 96dd0b3..da5033d 100644
--- a/include/scsi/libfc.h
+++ b/include/scsi/libfc.h
@@ -809,11 +809,11 @@
/**
* fc_set_wwpn() - Set the World Wide Port Name of a local port
* @lport: The local port whose WWPN is to be set
- * @wwnn: The new WWPN
+ * @wwpn: The new WWPN
*/
-static inline void fc_set_wwpn(struct fc_lport *lport, u64 wwnn)
+static inline void fc_set_wwpn(struct fc_lport *lport, u64 wwpn)
{
- lport->wwpn = wwnn;
+ lport->wwpn = wwpn;
}
/**
diff --git a/include/soc/arc/mcip.h b/include/soc/arc/mcip.h
index 6902c2a..4b6b489 100644
--- a/include/soc/arc/mcip.h
+++ b/include/soc/arc/mcip.h
@@ -55,17 +55,17 @@
struct mcip_bcr {
#ifdef CONFIG_CPU_BIG_ENDIAN
- unsigned int pad3:8,
- idu:1, llm:1, num_cores:6,
- iocoh:1, gfrc:1, dbg:1, pad2:1,
- msg:1, sem:1, ipi:1, pad:1,
+ unsigned int pad4:6, pw_dom:1, pad3:1,
+ idu:1, pad2:1, num_cores:6,
+ pad:1, gfrc:1, dbg:1, pw:1,
+ msg:1, sem:1, ipi:1, slv:1,
ver:8;
#else
unsigned int ver:8,
- pad:1, ipi:1, sem:1, msg:1,
- pad2:1, dbg:1, gfrc:1, iocoh:1,
- num_cores:6, llm:1, idu:1,
- pad3:8;
+ slv:1, ipi:1, sem:1, msg:1,
+ pw:1, dbg:1, gfrc:1, pad:1,
+ num_cores:6, pad2:1, idu:1,
+ pad3:1, pw_dom:1, pad4:6;
#endif
};
diff --git a/include/soc/at91/at91sam9_ddrsdr.h b/include/soc/at91/at91sam9_ddrsdr.h
index dc10c52..393362b 100644
--- a/include/soc/at91/at91sam9_ddrsdr.h
+++ b/include/soc/at91/at91sam9_ddrsdr.h
@@ -81,6 +81,7 @@
#define AT91_DDRSDRC_LPCB_POWER_DOWN 2
#define AT91_DDRSDRC_LPCB_DEEP_POWER_DOWN 3
#define AT91_DDRSDRC_CLKFR (1 << 2) /* Clock Frozen */
+#define AT91_DDRSDRC_LPDDR2_PWOFF (1 << 3) /* LPDDR Power Off */
#define AT91_DDRSDRC_PASR (7 << 4) /* Partial Array Self Refresh */
#define AT91_DDRSDRC_TCSR (3 << 8) /* Temperature Compensated Self Refresh */
#define AT91_DDRSDRC_DS (3 << 10) /* Drive Strength */
@@ -96,7 +97,9 @@
#define AT91_DDRSDRC_MD_SDR 0
#define AT91_DDRSDRC_MD_LOW_POWER_SDR 1
#define AT91_DDRSDRC_MD_LOW_POWER_DDR 3
+#define AT91_DDRSDRC_MD_LPDDR3 5
#define AT91_DDRSDRC_MD_DDR2 6 /* [SAM9 Only] */
+#define AT91_DDRSDRC_MD_LPDDR2 7
#define AT91_DDRSDRC_DBW (1 << 4) /* Data Bus Width */
#define AT91_DDRSDRC_DBW_32BITS (0 << 4)
#define AT91_DDRSDRC_DBW_16BITS (1 << 4)
diff --git a/include/sound/hdmi-codec.h b/include/sound/hdmi-codec.h
index 530c57b..915c435 100644
--- a/include/sound/hdmi-codec.h
+++ b/include/sound/hdmi-codec.h
@@ -36,10 +36,10 @@
HDMI_AC97,
HDMI_SPDIF,
} fmt;
- int bit_clk_inv:1;
- int frame_clk_inv:1;
- int bit_clk_master:1;
- int frame_clk_master:1;
+ unsigned int bit_clk_inv:1;
+ unsigned int frame_clk_inv:1;
+ unsigned int bit_clk_master:1;
+ unsigned int frame_clk_master:1;
};
/*
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 2b502f6..b86168a 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -813,6 +813,7 @@
unsigned int suspended:1; /* is in suspend PM state */
struct list_head list;
+ struct list_head card_aux_list; /* for auxiliary bound components */
struct list_head card_list;
struct snd_soc_dai_driver *dai_drv;
@@ -1152,6 +1153,7 @@
*/
struct snd_soc_aux_dev *aux_dev;
int num_aux_devs;
+ struct list_head aux_comp_list;
const struct snd_kcontrol_new *controls;
int num_controls;
@@ -1547,6 +1549,7 @@
INIT_LIST_HEAD(&card->widgets);
INIT_LIST_HEAD(&card->paths);
INIT_LIST_HEAD(&card->dapm_list);
+ INIT_LIST_HEAD(&card->aux_comp_list);
INIT_LIST_HEAD(&card->component_dev_list);
}
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 29e6858..da854fb 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -174,6 +174,10 @@
TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED = R(0x16),
TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED = R(0x17),
TCM_COPY_TARGET_DEVICE_NOT_REACHABLE = R(0x18),
+ TCM_TOO_MANY_TARGET_DESCS = R(0x19),
+ TCM_UNSUPPORTED_TARGET_DESC_TYPE_CODE = R(0x1a),
+ TCM_TOO_MANY_SEGMENT_DESCS = R(0x1b),
+ TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE = R(0x1c),
#undef R
};
@@ -534,6 +538,7 @@
char initiatorname[TRANSPORT_IQN_LEN];
/* Used to signal demo mode created ACL, disabled by default */
bool dynamic_node_acl;
+ bool dynamic_stop;
u32 queue_depth;
u32 acl_index;
enum target_prot_type saved_prot_type;
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index c14bed4..88d18a8ce 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -130,8 +130,8 @@
BTRFS_I(inode)->root->root_key.objectid;
),
- TP_printk_btrfs("root = %llu(%s), gen = %llu, ino = %lu, blocks = %llu, "
- "disk_i_size = %llu, last_trans = %llu, logged_trans = %llu",
+ TP_printk_btrfs("root=%llu(%s) gen=%llu ino=%lu blocks=%llu "
+ "disk_i_size=%llu last_trans=%llu logged_trans=%llu",
show_root_type(__entry->root_objectid),
(unsigned long long)__entry->generation,
(unsigned long)__entry->ino,
@@ -184,14 +184,16 @@
TRACE_EVENT_CONDITION(btrfs_get_extent,
- TP_PROTO(struct btrfs_root *root, struct extent_map *map),
+ TP_PROTO(struct btrfs_root *root, struct inode *inode,
+ struct extent_map *map),
- TP_ARGS(root, map),
+ TP_ARGS(root, inode, map),
TP_CONDITION(map),
TP_STRUCT__entry_btrfs(
__field( u64, root_objectid )
+ __field( u64, ino )
__field( u64, start )
__field( u64, len )
__field( u64, orig_start )
@@ -204,7 +206,8 @@
TP_fast_assign_btrfs(root->fs_info,
__entry->root_objectid = root->root_key.objectid;
- __entry->start = map->start;
+ __entry->ino = btrfs_ino(inode);
+ __entry->start = map->start;
__entry->len = map->len;
__entry->orig_start = map->orig_start;
__entry->block_start = map->block_start;
@@ -214,11 +217,12 @@
__entry->compress_type = map->compress_type;
),
- TP_printk_btrfs("root = %llu(%s), start = %llu, len = %llu, "
- "orig_start = %llu, block_start = %llu(%s), "
- "block_len = %llu, flags = %s, refs = %u, "
- "compress_type = %u",
+ TP_printk_btrfs("root=%llu(%s) ino=%llu start=%llu len=%llu "
+ "orig_start=%llu block_start=%llu(%s) "
+ "block_len=%llu flags=%s refs=%u "
+ "compress_type=%u",
show_root_type(__entry->root_objectid),
+ (unsigned long long)__entry->ino,
(unsigned long long)__entry->start,
(unsigned long long)__entry->len,
(unsigned long long)__entry->orig_start,
@@ -259,6 +263,7 @@
__field( int, compress_type )
__field( int, refs )
__field( u64, root_objectid )
+ __field( u64, truncated_len )
),
TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
@@ -273,18 +278,21 @@
__entry->refs = atomic_read(&ordered->refs);
__entry->root_objectid =
BTRFS_I(inode)->root->root_key.objectid;
+ __entry->truncated_len = ordered->truncated_len;
),
- TP_printk_btrfs("root = %llu(%s), ino = %llu, file_offset = %llu, "
- "start = %llu, len = %llu, disk_len = %llu, "
- "bytes_left = %llu, flags = %s, compress_type = %d, "
- "refs = %d",
+ TP_printk_btrfs("root=%llu(%s) ino=%llu file_offset=%llu "
+ "start=%llu len=%llu disk_len=%llu "
+ "truncated_len=%llu "
+ "bytes_left=%llu flags=%s compress_type=%d "
+ "refs=%d",
show_root_type(__entry->root_objectid),
(unsigned long long)__entry->ino,
(unsigned long long)__entry->file_offset,
(unsigned long long)__entry->start,
(unsigned long long)__entry->len,
(unsigned long long)__entry->disk_len,
+ (unsigned long long)__entry->truncated_len,
(unsigned long long)__entry->bytes_left,
show_ordered_flags(__entry->flags),
__entry->compress_type, __entry->refs)
@@ -354,10 +362,10 @@
BTRFS_I(inode)->root->root_key.objectid;
),
- TP_printk_btrfs("root = %llu(%s), ino = %lu, page_index = %lu, "
- "nr_to_write = %ld, pages_skipped = %ld, range_start = %llu, "
- "range_end = %llu, for_kupdate = %d, "
- "for_reclaim = %d, range_cyclic = %d, writeback_index = %lu",
+ TP_printk_btrfs("root=%llu(%s) ino=%lu page_index=%lu "
+ "nr_to_write=%ld pages_skipped=%ld range_start=%llu "
+ "range_end=%llu for_kupdate=%d "
+ "for_reclaim=%d range_cyclic=%d writeback_index=%lu",
show_root_type(__entry->root_objectid),
(unsigned long)__entry->ino, __entry->index,
__entry->nr_to_write, __entry->pages_skipped,
@@ -400,8 +408,8 @@
BTRFS_I(page->mapping->host)->root->root_key.objectid;
),
- TP_printk_btrfs("root = %llu(%s), ino = %lu, page_index = %lu, start = %llu, "
- "end = %llu, uptodate = %d",
+ TP_printk_btrfs("root=%llu(%s) ino=%lu page_index=%lu start=%llu "
+ "end=%llu uptodate=%d",
show_root_type(__entry->root_objectid),
(unsigned long)__entry->ino, (unsigned long)__entry->index,
(unsigned long long)__entry->start,
@@ -433,7 +441,7 @@
BTRFS_I(inode)->root->root_key.objectid;
),
- TP_printk_btrfs("root = %llu(%s), ino = %ld, parent = %ld, datasync = %d",
+ TP_printk_btrfs("root=%llu(%s) ino=%ld parent=%ld datasync=%d",
show_root_type(__entry->root_objectid),
(unsigned long)__entry->ino, (unsigned long)__entry->parent,
__entry->datasync)
@@ -484,9 +492,9 @@
__entry->create = create;
),
- TP_printk("%pU: block_group offset = %llu, size = %llu, "
- "flags = %llu(%s), bytes_used = %llu, bytes_super = %llu, "
- "create = %d", __entry->fsid,
+ TP_printk("%pU: block_group offset=%llu size=%llu "
+ "flags=%llu(%s) bytes_used=%llu bytes_super=%llu "
+ "create=%d", __entry->fsid,
(unsigned long long)__entry->offset,
(unsigned long long)__entry->size,
(unsigned long long)__entry->flags,
@@ -535,9 +543,9 @@
__entry->seq = ref->seq;
),
- TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, "
- "parent = %llu(%s), ref_root = %llu(%s), level = %d, "
- "type = %s, seq = %llu",
+ TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s "
+ "parent=%llu(%s) ref_root=%llu(%s) level=%d "
+ "type=%s seq=%llu",
(unsigned long long)__entry->bytenr,
(unsigned long long)__entry->num_bytes,
show_ref_action(__entry->action),
@@ -600,9 +608,9 @@
__entry->seq = ref->seq;
),
- TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, "
- "parent = %llu(%s), ref_root = %llu(%s), owner = %llu, "
- "offset = %llu, type = %s, seq = %llu",
+ TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s "
+ "parent=%llu(%s) ref_root=%llu(%s) owner=%llu "
+ "offset=%llu type=%s seq=%llu",
(unsigned long long)__entry->bytenr,
(unsigned long long)__entry->num_bytes,
show_ref_action(__entry->action),
@@ -657,7 +665,7 @@
__entry->is_data = head_ref->is_data;
),
- TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, is_data = %d",
+ TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s is_data=%d",
(unsigned long long)__entry->bytenr,
(unsigned long long)__entry->num_bytes,
show_ref_action(__entry->action),
@@ -721,8 +729,8 @@
__entry->root_objectid = fs_info->chunk_root->root_key.objectid;
),
- TP_printk_btrfs("root = %llu(%s), offset = %llu, size = %llu, "
- "num_stripes = %d, sub_stripes = %d, type = %s",
+ TP_printk_btrfs("root=%llu(%s) offset=%llu size=%llu "
+ "num_stripes=%d sub_stripes=%d type=%s",
show_root_type(__entry->root_objectid),
(unsigned long long)__entry->offset,
(unsigned long long)__entry->size,
@@ -771,8 +779,8 @@
__entry->cow_level = btrfs_header_level(cow);
),
- TP_printk_btrfs("root = %llu(%s), refs = %d, orig_buf = %llu "
- "(orig_level = %d), cow_buf = %llu (cow_level = %d)",
+ TP_printk_btrfs("root=%llu(%s) refs=%d orig_buf=%llu "
+ "(orig_level=%d) cow_buf=%llu (cow_level=%d)",
show_root_type(__entry->root_objectid),
__entry->refs,
(unsigned long long)__entry->buf_start,
@@ -836,7 +844,7 @@
__assign_str(reason, reason)
),
- TP_printk("%pU: %s: flush = %d(%s), flags = %llu(%s), bytes = %llu",
+ TP_printk("%pU: %s: flush=%d(%s) flags=%llu(%s) bytes=%llu",
__entry->fsid, __get_str(reason), __entry->flush,
show_flush_action(__entry->flush),
(unsigned long long)__entry->flags,
@@ -879,8 +887,8 @@
__entry->ret = ret;
),
- TP_printk("%pU: state = %d(%s), flags = %llu(%s), num_bytes = %llu, "
- "orig_bytes = %llu, ret = %d", __entry->fsid, __entry->state,
+ TP_printk("%pU: state=%d(%s) flags=%llu(%s) num_bytes=%llu "
+ "orig_bytes=%llu ret=%d", __entry->fsid, __entry->state,
show_flush_state(__entry->state),
(unsigned long long)__entry->flags,
__print_flags((unsigned long)__entry->flags, "|",
@@ -905,7 +913,7 @@
__entry->len = len;
),
- TP_printk_btrfs("root = %llu(%s), start = %llu, len = %llu",
+ TP_printk_btrfs("root=%llu(%s) start=%llu len=%llu",
show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
(unsigned long long)__entry->start,
(unsigned long long)__entry->len)
@@ -944,7 +952,7 @@
__entry->data = data;
),
- TP_printk_btrfs("root = %Lu(%s), len = %Lu, empty_size = %Lu, flags = %Lu(%s)",
+ TP_printk_btrfs("root=%Lu(%s) len=%Lu empty_size=%Lu flags=%Lu(%s)",
show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
__entry->num_bytes, __entry->empty_size, __entry->data,
__print_flags((unsigned long)__entry->data, "|",
@@ -973,8 +981,8 @@
__entry->len = len;
),
- TP_printk_btrfs("root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), "
- "start = %Lu, len = %Lu",
+ TP_printk_btrfs("root=%Lu(%s) block_group=%Lu flags=%Lu(%s) "
+ "start=%Lu len=%Lu",
show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
__entry->bg_objectid,
__entry->flags, __print_flags((unsigned long)__entry->flags,
@@ -1025,8 +1033,8 @@
__entry->min_bytes = min_bytes;
),
- TP_printk_btrfs("block_group = %Lu, flags = %Lu(%s), start = %Lu, len = %Lu,"
- " empty_size = %Lu, min_bytes = %Lu", __entry->bg_objectid,
+ TP_printk_btrfs("block_group=%Lu flags=%Lu(%s) start=%Lu len=%Lu "
+ "empty_size=%Lu min_bytes=%Lu", __entry->bg_objectid,
__entry->flags,
__print_flags((unsigned long)__entry->flags, "|",
BTRFS_GROUP_FLAGS), __entry->start,
@@ -1047,7 +1055,7 @@
__entry->bg_objectid = block_group->key.objectid;
),
- TP_printk_btrfs("block_group = %Lu", __entry->bg_objectid)
+ TP_printk_btrfs("block_group=%Lu", __entry->bg_objectid)
);
TRACE_EVENT(btrfs_setup_cluster,
@@ -1075,8 +1083,8 @@
__entry->bitmap = bitmap;
),
- TP_printk_btrfs("block_group = %Lu, flags = %Lu(%s), window_start = %Lu, "
- "size = %Lu, max_size = %Lu, bitmap = %d",
+ TP_printk_btrfs("block_group=%Lu flags=%Lu(%s) window_start=%Lu "
+ "size=%Lu max_size=%Lu bitmap=%d",
__entry->bg_objectid,
__entry->flags,
__print_flags((unsigned long)__entry->flags, "|",
@@ -1103,7 +1111,7 @@
__entry->ip = IP
),
- TP_printk("state=%p; mask = %s; caller = %pS", __entry->state,
+ TP_printk("state=%p mask=%s caller=%pS", __entry->state,
show_gfp_flags(__entry->mask), (void *)__entry->ip)
);
@@ -1123,7 +1131,7 @@
__entry->ip = IP
),
- TP_printk(" state=%p; caller = %pS", __entry->state,
+ TP_printk("state=%p caller=%pS", __entry->state,
(void *)__entry->ip)
);
@@ -1151,28 +1159,32 @@
__entry->normal_work = &work->normal_work;
),
- TP_printk_btrfs("work=%p (normal_work=%p), wq=%p, func=%pf, ordered_func=%p,"
- " ordered_free=%p",
+ TP_printk_btrfs("work=%p (normal_work=%p) wq=%p func=%pf ordered_func=%p "
+ "ordered_free=%p",
__entry->work, __entry->normal_work, __entry->wq,
__entry->func, __entry->ordered_func, __entry->ordered_free)
);
-/* For situiations that the work is freed */
+/*
+ * For situiations when the work is freed, we pass fs_info and a tag that that
+ * matches address of the work structure so it can be paired with the
+ * scheduling event.
+ */
DECLARE_EVENT_CLASS(btrfs__work__done,
- TP_PROTO(struct btrfs_work *work),
+ TP_PROTO(struct btrfs_fs_info *fs_info, void *wtag),
- TP_ARGS(work),
+ TP_ARGS(fs_info, wtag),
TP_STRUCT__entry_btrfs(
- __field( void *, work )
+ __field( void *, wtag )
),
- TP_fast_assign_btrfs(btrfs_work_owner(work),
- __entry->work = work;
+ TP_fast_assign_btrfs(fs_info,
+ __entry->wtag = wtag;
),
- TP_printk_btrfs("work->%p", __entry->work)
+ TP_printk_btrfs("work->%p", __entry->wtag)
);
DEFINE_EVENT(btrfs__work, btrfs_work_queued,
@@ -1191,9 +1203,9 @@
DEFINE_EVENT(btrfs__work__done, btrfs_all_work_done,
- TP_PROTO(struct btrfs_work *work),
+ TP_PROTO(struct btrfs_fs_info *fs_info, void *wtag),
- TP_ARGS(work)
+ TP_ARGS(fs_info, wtag)
);
DEFINE_EVENT(btrfs__work, btrfs_ordered_sched,
@@ -1221,7 +1233,7 @@
__entry->high = high;
),
- TP_printk_btrfs("name=%s%s, wq=%p", __get_str(name),
+ TP_printk_btrfs("name=%s%s wq=%p", __get_str(name),
__print_flags(__entry->high, "",
{(WQ_HIGHPRI), "-high"}),
__entry->wq)
@@ -1276,7 +1288,7 @@
__entry->free_reserved = free_reserved;
),
- TP_printk_btrfs("rootid=%llu, ino=%lu, free_reserved=%llu",
+ TP_printk_btrfs("rootid=%llu ino=%lu free_reserved=%llu",
__entry->rootid, __entry->ino, __entry->free_reserved)
);
@@ -1323,7 +1335,7 @@
__entry->op = op;
),
- TP_printk_btrfs("root=%llu, ino=%lu, start=%llu, len=%llu, reserved=%llu, op=%s",
+ TP_printk_btrfs("root=%llu ino=%lu start=%llu len=%llu reserved=%llu op=%s",
__entry->rootid, __entry->ino, __entry->start, __entry->len,
__entry->reserved,
__print_flags((unsigned long)__entry->op, "",
@@ -1361,7 +1373,7 @@
__entry->reserved = reserved;
),
- TP_printk_btrfs("root=%llu, reserved=%llu, op=free",
+ TP_printk_btrfs("root=%llu reserved=%llu op=free",
__entry->ref_root, __entry->reserved)
);
@@ -1388,7 +1400,7 @@
__entry->num_bytes = rec->num_bytes;
),
- TP_printk_btrfs("bytenr = %llu, num_bytes = %llu",
+ TP_printk_btrfs("bytenr=%llu num_bytes=%llu",
(unsigned long long)__entry->bytenr,
(unsigned long long)__entry->num_bytes)
);
@@ -1430,8 +1442,8 @@
__entry->nr_new_roots = nr_new_roots;
),
- TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, nr_old_roots = %llu, "
- "nr_new_roots = %llu",
+ TP_printk_btrfs("bytenr=%llu num_bytes=%llu nr_old_roots=%llu "
+ "nr_new_roots=%llu",
__entry->bytenr,
__entry->num_bytes,
__entry->nr_old_roots,
@@ -1457,7 +1469,7 @@
__entry->cur_new_count = cur_new_count;
),
- TP_printk_btrfs("qgid = %llu, cur_old_count = %llu, cur_new_count = %llu",
+ TP_printk_btrfs("qgid=%llu cur_old_count=%llu cur_new_count=%llu",
__entry->qgid,
__entry->cur_old_count,
__entry->cur_new_count)
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 9d4f9b3..e3facb3 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -385,11 +385,11 @@
/*
* Tracepoint for quiescent states detected by force_quiescent_state().
- * These trace events include the type of RCU, the grace-period number
- * that was blocked by the CPU, the CPU itself, and the type of quiescent
- * state, which can be "dti" for dyntick-idle mode, "ofl" for CPU offline,
- * or "kick" when kicking a CPU that has been in dyntick-idle mode for
- * too long.
+ * These trace events include the type of RCU, the grace-period number that
+ * was blocked by the CPU, the CPU itself, and the type of quiescent state,
+ * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick"
+ * when kicking a CPU that has been in dyntick-idle mode for too long, or
+ * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr.
*/
TRACE_EVENT(rcu_fqs,
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 1448637..1bca99d 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -269,17 +269,17 @@
TRACE_EVENT(itimer_state,
TP_PROTO(int which, const struct itimerval *const value,
- cputime_t expires),
+ unsigned long long expires),
TP_ARGS(which, value, expires),
TP_STRUCT__entry(
- __field( int, which )
- __field( cputime_t, expires )
- __field( long, value_sec )
- __field( long, value_usec )
- __field( long, interval_sec )
- __field( long, interval_usec )
+ __field( int, which )
+ __field( unsigned long long, expires )
+ __field( long, value_sec )
+ __field( long, value_usec )
+ __field( long, interval_sec )
+ __field( long, interval_usec )
),
TP_fast_assign(
@@ -292,7 +292,7 @@
),
TP_printk("which=%d expires=%llu it_value=%ld.%ld it_interval=%ld.%ld",
- __entry->which, (unsigned long long)__entry->expires,
+ __entry->which, __entry->expires,
__entry->value_sec, __entry->value_usec,
__entry->interval_sec, __entry->interval_usec)
);
@@ -305,14 +305,14 @@
*/
TRACE_EVENT(itimer_expire,
- TP_PROTO(int which, struct pid *pid, cputime_t now),
+ TP_PROTO(int which, struct pid *pid, unsigned long long now),
TP_ARGS(which, pid, now),
TP_STRUCT__entry(
- __field( int , which )
- __field( pid_t, pid )
- __field( cputime_t, now )
+ __field( int , which )
+ __field( pid_t, pid )
+ __field( unsigned long long, now )
),
TP_fast_assign(
@@ -322,7 +322,7 @@
),
TP_printk("which=%d pid=%d now=%llu", __entry->which,
- (int) __entry->pid, (unsigned long long)__entry->now)
+ (int) __entry->pid, __entry->now)
);
#ifdef CONFIG_NO_HZ_COMMON
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0eb0e87..d2b0ac7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -116,6 +116,12 @@
#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
+ * to the given target_fd cgroup the descendent cgroup will be able to
+ * override effective bpf program that was inherited from this cgroup
+ */
+#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+
#define BPF_PSEUDO_MAP_FD 1
/* flags for BPF_MAP_UPDATE_ELEM command */
@@ -171,6 +177,7 @@
__u32 target_fd; /* container object to attach to */
__u32 attach_bpf_fd; /* eBPF program to attach */
__u32 attach_type;
+ __u32 attach_flags;
};
} __attribute__((aligned(8)));
diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h
index 3cbc327..c451eec 100644
--- a/include/uapi/linux/cec-funcs.h
+++ b/include/uapi/linux/cec-funcs.h
@@ -1665,14 +1665,15 @@
__u8 audio_out_compensated,
__u8 audio_out_delay)
{
- msg->len = 7;
+ msg->len = 6;
msg->msg[0] |= 0xf; /* broadcast */
msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY;
msg->msg[2] = phys_addr >> 8;
msg->msg[3] = phys_addr & 0xff;
msg->msg[4] = video_latency;
msg->msg[5] = (low_latency_mode << 2) | audio_out_compensated;
- msg->msg[6] = audio_out_delay;
+ if (audio_out_compensated == 3)
+ msg->msg[msg->len++] = audio_out_delay;
}
static inline void cec_ops_report_current_latency(const struct cec_msg *msg,
@@ -1686,7 +1687,10 @@
*video_latency = msg->msg[4];
*low_latency_mode = (msg->msg[5] >> 2) & 1;
*audio_out_compensated = msg->msg[5] & 3;
- *audio_out_delay = msg->msg[6];
+ if (*audio_out_compensated == 3 && msg->len >= 7)
+ *audio_out_delay = msg->msg[6];
+ else
+ *audio_out_delay = 0;
}
static inline void cec_msg_request_current_latency(struct cec_msg *msg,
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index f0db778..3dc91a4 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1384,6 +1384,8 @@
ETHTOOL_LINK_MODE_10000baseLR_Full_BIT = 44,
ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT = 45,
ETHTOOL_LINK_MODE_10000baseER_Full_BIT = 46,
+ ETHTOOL_LINK_MODE_2500baseT_Full_BIT = 47,
+ ETHTOOL_LINK_MODE_5000baseT_Full_BIT = 48,
/* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit
@@ -1393,7 +1395,7 @@
*/
__ETHTOOL_LINK_MODE_LAST
- = ETHTOOL_LINK_MODE_10000baseER_Full_BIT,
+ = ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
};
#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 85ddb74..b23c191 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -9,9 +9,8 @@
#include <linux/types.h>
#include <linux/socket.h>
-#ifndef __KERNEL__
-#include <netinet/in.h>
-#endif
+#include <linux/in.h>
+#include <linux/in6.h>
#define IPPROTO_L2TP 115
@@ -31,7 +30,7 @@
__u32 l2tp_conn_id; /* Connection ID of tunnel */
/* Pad to size of `struct sockaddr'. */
- unsigned char __pad[sizeof(struct sockaddr) -
+ unsigned char __pad[__SOCK_SIZE__ -
sizeof(__kernel_sa_family_t) -
sizeof(__be16) - sizeof(struct in_addr) -
sizeof(__u32)];
diff --git a/include/uapi/linux/netfilter/nf_log.h b/include/uapi/linux/netfilter/nf_log.h
index 8be21e0..d0b5fa9 100644
--- a/include/uapi/linux/netfilter/nf_log.h
+++ b/include/uapi/linux/netfilter/nf_log.h
@@ -9,4 +9,6 @@
#define NF_LOG_MACDECODE 0x20 /* Decode MAC header */
#define NF_LOG_MASK 0x2f
+#define NF_LOG_PREFIXLEN 128
+
#endif /* _NETFILTER_NF_LOG_H */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 881d49e..e3f27e0 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -235,7 +235,7 @@
/**
* enum nft_rule_compat_attributes - nf_tables rule compat attributes
*
- * @NFTA_RULE_COMPAT_PROTO: numerice value of handled protocol (NLA_U32)
+ * @NFTA_RULE_COMPAT_PROTO: numeric value of handled protocol (NLA_U32)
* @NFTA_RULE_COMPAT_FLAGS: bitmask of enum nft_rule_compat_flags (NLA_U32)
*/
enum nft_rule_compat_attributes {
@@ -499,7 +499,7 @@
* enum nft_byteorder_ops - nf_tables byteorder operators
*
* @NFT_BYTEORDER_NTOH: network to host operator
- * @NFT_BYTEORDER_HTON: host to network opertaor
+ * @NFT_BYTEORDER_HTON: host to network operator
*/
enum nft_byteorder_ops {
NFT_BYTEORDER_NTOH,
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 6b76e3b..bea982a 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1772,7 +1772,9 @@
*
* @NL80211_ATTR_OPMODE_NOTIF: Operating mode field from Operating Mode
* Notification Element based on association request when used with
- * %NL80211_CMD_NEW_STATION; u8 attribute.
+ * %NL80211_CMD_NEW_STATION or %NL80211_CMD_SET_STATION (only when
+ * %NL80211_FEATURE_FULL_AP_CLIENT_STATE is supported, or with TDLS);
+ * u8 attribute.
*
* @NL80211_ATTR_VENDOR_ID: The vendor ID, either a 24-bit OUI or, if
* %NL80211_VENDOR_ID_IS_LINUX is set, a special Linux ID (not used yet)
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index cb4bcdc..a4dcd88 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -397,7 +397,7 @@
TCA_BPF_NAME,
TCA_BPF_FLAGS,
TCA_BPF_FLAGS_GEN,
- TCA_BPF_DIGEST,
+ TCA_BPF_TAG,
__TCA_BPF_MAX,
};
diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h
index c396a80..052799e 100644
--- a/include/uapi/linux/seg6.h
+++ b/include/uapi/linux/seg6.h
@@ -23,14 +23,12 @@
__u8 type;
__u8 segments_left;
__u8 first_segment;
- __u8 flag_1;
- __u8 flag_2;
- __u8 reserved;
+ __u8 flags;
+ __u16 reserved;
struct in6_addr segments[0];
};
-#define SR6_FLAG1_CLEANUP (1 << 7)
#define SR6_FLAG1_PROTECTED (1 << 6)
#define SR6_FLAG1_OAM (1 << 5)
#define SR6_FLAG1_ALERT (1 << 4)
@@ -42,8 +40,7 @@
#define SR6_TLV_PADDING 4
#define SR6_TLV_HMAC 5
-#define sr_has_cleanup(srh) ((srh)->flag_1 & SR6_FLAG1_CLEANUP)
-#define sr_has_hmac(srh) ((srh)->flag_1 & SR6_FLAG1_HMAC)
+#define sr_has_hmac(srh) ((srh)->flags & SR6_FLAG1_HMAC)
struct sr6_tlv {
__u8 type;
diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h
index a6b88a6..975b50d 100644
--- a/include/uapi/linux/tc_act/tc_bpf.h
+++ b/include/uapi/linux/tc_act/tc_bpf.h
@@ -27,7 +27,7 @@
TCA_ACT_BPF_FD,
TCA_ACT_BPF_NAME,
TCA_ACT_BPF_PAD,
- TCA_ACT_BPF_DIGEST,
+ TCA_ACT_BPF_TAG,
__TCA_ACT_BPF_MAX,
};
#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 46e8a2e3..45184a2 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -362,8 +362,8 @@
/*
* The default for R'G'B' quantization is always full range, except
* for the BT2020 colorspace. For Y'CbCr the quantization is always
- * limited range, except for COLORSPACE_JPEG, SRGB, ADOBERGB,
- * XV601 or XV709: those are full range.
+ * limited range, except for COLORSPACE_JPEG, XV601 or XV709: those
+ * are full range.
*/
V4L2_QUANTIZATION_DEFAULT = 0,
V4L2_QUANTIZATION_FULL_RANGE = 1,
@@ -379,8 +379,7 @@
(((is_rgb_or_hsv) && (colsp) == V4L2_COLORSPACE_BT2020) ? \
V4L2_QUANTIZATION_LIM_RANGE : \
(((is_rgb_or_hsv) || (ycbcr_enc) == V4L2_YCBCR_ENC_XV601 || \
- (ycbcr_enc) == V4L2_YCBCR_ENC_XV709 || (colsp) == V4L2_COLORSPACE_JPEG) || \
- (colsp) == V4L2_COLORSPACE_ADOBERGB || (colsp) == V4L2_COLORSPACE_SRGB ? \
+ (ycbcr_enc) == V4L2_YCBCR_ENC_XV709 || (colsp) == V4L2_COLORSPACE_JPEG) ? \
V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE))
enum v4l2_priority {
diff --git a/include/uapi/rdma/Kbuild b/include/uapi/rdma/Kbuild
index 82bdf56..bb68cb1 100644
--- a/include/uapi/rdma/Kbuild
+++ b/include/uapi/rdma/Kbuild
@@ -16,3 +16,4 @@
header-y += ocrdma-abi.h
header-y += hns-abi.h
header-y += vmw_pvrdma-abi.h
+header-y += qedr-abi.h
diff --git a/include/uapi/rdma/cxgb3-abi.h b/include/uapi/rdma/cxgb3-abi.h
index 48a19bd..d24eee1 100644
--- a/include/uapi/rdma/cxgb3-abi.h
+++ b/include/uapi/rdma/cxgb3-abi.h
@@ -30,7 +30,7 @@
* SOFTWARE.
*/
#ifndef CXGB3_ABI_USER_H
-#define CXBG3_ABI_USER_H
+#define CXGB3_ABI_USER_H
#include <linux/types.h>
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index dfdfe4e..f4f87cf 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -37,7 +37,6 @@
#define IB_USER_VERBS_H
#include <linux/types.h>
-#include <rdma/ib_verbs.h>
/*
* Increment this value if any changes that break userspace ABI
@@ -548,11 +547,17 @@
};
enum {
- IB_USER_LEGACY_LAST_QP_ATTR_MASK = IB_QP_DEST_QPN
+ /*
+ * This value is equal to IB_QP_DEST_QPN.
+ */
+ IB_USER_LEGACY_LAST_QP_ATTR_MASK = 1ULL << 20,
};
enum {
- IB_USER_LAST_QP_ATTR_MASK = IB_QP_RATE_LIMIT
+ /*
+ * This value is equal to IB_QP_RATE_LIMIT.
+ */
+ IB_USER_LAST_QP_ATTR_MASK = 1ULL << 25,
};
struct ib_uverbs_ex_create_qp {
diff --git a/init/Kconfig b/init/Kconfig
index e1a93734..2655abb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -529,7 +529,6 @@
config TASKS_RCU
bool
default n
- depends on !UML
select SRCU
help
This option enables a task-based RCU implementation that uses
@@ -781,19 +780,6 @@
endchoice
-config RCU_EXPEDITE_BOOT
- bool
- default n
- help
- This option enables expedited grace periods at boot time,
- as if rcu_expedite_gp() had been invoked early in boot.
- The corresponding rcu_unexpedite_gp() is invoked from
- rcu_end_inkernel_boot(), which is intended to be invoked
- at the end of the kernel-only boot sequence, just before
- init is exec'ed.
-
- Accept the default if unsure.
-
endmenu # "RCU Subsystem"
config BUILD_BIN2C
@@ -1987,6 +1973,10 @@
make them incompatible with the kernel you are running. If
unsure, say N.
+config MODULE_REL_CRCS
+ bool
+ depends on MODVERSIONS
+
config MODULE_SRCVERSION_ALL
bool "Source checksum for all modules"
help
diff --git a/init/main.c b/init/main.c
index b0c9d6f..6ced14a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -625,7 +625,6 @@
numa_policy_init();
if (late_time_init)
late_time_init();
- sched_clock_init();
calibrate_delay();
pidmap_init();
anon_vma_init();
@@ -663,7 +662,6 @@
sfi_init_late();
if (efi_enabled(EFI_RUNTIME_SERVICES)) {
- efi_late_init();
efi_free_boot_services();
}
diff --git a/kernel/acct.c b/kernel/acct.c
index 74963d1..ca9cb55 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -453,8 +453,8 @@
spin_lock_irq(¤t->sighand->siglock);
tty = current->signal->tty; /* Safe as we hold the siglock */
ac->ac_tty = tty ? old_encode_dev(tty_devnum(tty)) : 0;
- ac->ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime)));
- ac->ac_stime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_stime)));
+ ac->ac_utime = encode_comp_t(nsec_to_AHZ(pacct->ac_utime));
+ ac->ac_stime = encode_comp_t(nsec_to_AHZ(pacct->ac_stime));
ac->ac_flag = pacct->ac_flag;
ac->ac_mem = encode_comp_t(pacct->ac_mem);
ac->ac_minflt = encode_comp_t(pacct->ac_minflt);
@@ -530,7 +530,7 @@
void acct_collect(long exitcode, int group_dead)
{
struct pacct_struct *pacct = ¤t->signal->pacct;
- cputime_t utime, stime;
+ u64 utime, stime;
unsigned long vsize = 0;
if (group_dead && current->mm) {
@@ -559,6 +559,7 @@
pacct->ac_flag |= ACORE;
if (current->flags & PF_SIGNALED)
pacct->ac_flag |= AXSIG;
+
task_cputime(current, &utime, &stime);
pacct->ac_utime += utime;
pacct->ac_stime += stime;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 229a5d5..3d55d95 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -11,7 +11,6 @@
*/
#include <linux/bpf.h>
#include <linux/err.h>
-#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/filter.h>
@@ -74,14 +73,10 @@
if (array_size >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-ENOMEM);
-
/* allocate all map elements and zero-initialize them */
- array = kzalloc(array_size, GFP_USER | __GFP_NOWARN);
- if (!array) {
- array = vzalloc(array_size);
- if (!array)
- return ERR_PTR(-ENOMEM);
- }
+ array = bpf_map_area_alloc(array_size);
+ if (!array)
+ return ERR_PTR(-ENOMEM);
/* copy mandatory map attributes */
array->map.map_type = attr->map_type;
@@ -97,7 +92,7 @@
if (array_size >= U32_MAX - PAGE_SIZE ||
elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
- kvfree(array);
+ bpf_map_area_free(array);
return ERR_PTR(-ENOMEM);
}
out:
@@ -262,7 +257,7 @@
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
bpf_array_free_percpu(array);
- kvfree(array);
+ bpf_map_area_free(array);
}
static const struct bpf_map_ops array_ops = {
@@ -319,7 +314,8 @@
/* make sure it's empty */
for (i = 0; i < array->map.max_entries; i++)
BUG_ON(array->ptrs[i] != NULL);
- kvfree(array);
+
+ bpf_map_area_free(array);
}
static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index a515f7b..da0f536 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -52,6 +52,7 @@
e = rcu_dereference_protected(parent->bpf.effective[type],
lockdep_is_held(&cgroup_mutex));
rcu_assign_pointer(cgrp->bpf.effective[type], e);
+ cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
}
}
@@ -82,30 +83,63 @@
*
* Must be called with cgroup_mutex held.
*/
-void __cgroup_bpf_update(struct cgroup *cgrp,
- struct cgroup *parent,
- struct bpf_prog *prog,
- enum bpf_attach_type type)
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+ struct bpf_prog *prog, enum bpf_attach_type type,
+ bool new_overridable)
{
- struct bpf_prog *old_prog, *effective;
+ struct bpf_prog *old_prog, *effective = NULL;
struct cgroup_subsys_state *pos;
+ bool overridable = true;
- old_prog = xchg(cgrp->bpf.prog + type, prog);
+ if (parent) {
+ overridable = !parent->bpf.disallow_override[type];
+ effective = rcu_dereference_protected(parent->bpf.effective[type],
+ lockdep_is_held(&cgroup_mutex));
+ }
- effective = (!prog && parent) ?
- rcu_dereference_protected(parent->bpf.effective[type],
- lockdep_is_held(&cgroup_mutex)) :
- prog;
+ if (prog && effective && !overridable)
+ /* if parent has non-overridable prog attached, disallow
+ * attaching new programs to descendent cgroup
+ */
+ return -EPERM;
+
+ if (prog && effective && overridable != new_overridable)
+ /* if parent has overridable prog attached, only
+ * allow overridable programs in descendent cgroup
+ */
+ return -EPERM;
+
+ old_prog = cgrp->bpf.prog[type];
+
+ if (prog) {
+ overridable = new_overridable;
+ effective = prog;
+ if (old_prog &&
+ cgrp->bpf.disallow_override[type] == new_overridable)
+ /* disallow attaching non-overridable on top
+ * of existing overridable in this cgroup
+ * and vice versa
+ */
+ return -EPERM;
+ }
+
+ if (!prog && !old_prog)
+ /* report error when trying to detach and nothing is attached */
+ return -ENOENT;
+
+ cgrp->bpf.prog[type] = prog;
css_for_each_descendant_pre(pos, &cgrp->self) {
struct cgroup *desc = container_of(pos, struct cgroup, self);
/* skip the subtree if the descendant has its own program */
- if (desc->bpf.prog[type] && desc != cgrp)
+ if (desc->bpf.prog[type] && desc != cgrp) {
pos = css_rightmost_descendant(pos);
- else
+ } else {
rcu_assign_pointer(desc->bpf.effective[type],
effective);
+ desc->bpf.disallow_override[type] = !overridable;
+ }
}
if (prog)
@@ -115,6 +149,7 @@
bpf_prog_put(old_prog);
static_branch_dec(&cgroup_bpf_enabled_key);
}
+ return 0;
}
/**
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1eb4f13..503d421 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -146,10 +146,11 @@
vfree(fp);
}
-int bpf_prog_calc_digest(struct bpf_prog *fp)
+int bpf_prog_calc_tag(struct bpf_prog *fp)
{
const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
- u32 raw_size = bpf_prog_digest_scratch_size(fp);
+ u32 raw_size = bpf_prog_tag_scratch_size(fp);
+ u32 digest[SHA_DIGEST_WORDS];
u32 ws[SHA_WORKSPACE_WORDS];
u32 i, bsize, psize, blocks;
struct bpf_insn *dst;
@@ -162,7 +163,7 @@
if (!raw)
return -ENOMEM;
- sha_init(fp->digest);
+ sha_init(digest);
memset(ws, 0, sizeof(ws));
/* We need to take out the map fd for the digest calculation
@@ -204,13 +205,14 @@
*bits = cpu_to_be64((psize - 1) << 3);
while (blocks--) {
- sha_transform(fp->digest, todo, ws);
+ sha_transform(digest, todo, ws);
todo += SHA_MESSAGE_BYTES;
}
- result = (__force __be32 *)fp->digest;
+ result = (__force __be32 *)digest;
for (i = 0; i < SHA_DIGEST_WORDS; i++)
- result[i] = cpu_to_be32(fp->digest[i]);
+ result[i] = cpu_to_be32(digest[i]);
+ memcpy(fp->tag, result, sizeof(fp->tag));
vfree(raw);
return 0;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3f2bb58..a753bbe 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -13,7 +13,6 @@
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
-#include <linux/vmalloc.h>
#include "percpu_freelist.h"
#include "bpf_lru_list.h"
@@ -103,7 +102,7 @@
free_percpu(pptr);
}
free_elems:
- vfree(htab->elems);
+ bpf_map_area_free(htab->elems);
}
static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
@@ -125,7 +124,8 @@
{
int err = -ENOMEM, i;
- htab->elems = vzalloc(htab->elem_size * htab->map.max_entries);
+ htab->elems = bpf_map_area_alloc(htab->elem_size *
+ htab->map.max_entries);
if (!htab->elems)
return -ENOMEM;
@@ -320,14 +320,10 @@
goto free_htab;
err = -ENOMEM;
- htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket),
- GFP_USER | __GFP_NOWARN);
-
- if (!htab->buckets) {
- htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket));
- if (!htab->buckets)
- goto free_htab;
- }
+ htab->buckets = bpf_map_area_alloc(htab->n_buckets *
+ sizeof(struct bucket));
+ if (!htab->buckets)
+ goto free_htab;
for (i = 0; i < htab->n_buckets; i++) {
INIT_HLIST_HEAD(&htab->buckets[i].head);
@@ -354,7 +350,7 @@
free_extra_elems:
free_percpu(htab->extra_elems);
free_buckets:
- kvfree(htab->buckets);
+ bpf_map_area_free(htab->buckets);
free_htab:
kfree(htab);
return ERR_PTR(err);
@@ -1014,7 +1010,7 @@
prealloc_destroy(htab);
free_percpu(htab->extra_elems);
- kvfree(htab->buckets);
+ bpf_map_area_free(htab->buckets);
kfree(htab);
}
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 732ae16..be85191 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -7,7 +7,6 @@
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
-#include <linux/vmalloc.h>
#include <linux/stacktrace.h>
#include <linux/perf_event.h>
#include "percpu_freelist.h"
@@ -32,7 +31,7 @@
u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
int err;
- smap->elems = vzalloc(elem_size * smap->map.max_entries);
+ smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries);
if (!smap->elems)
return -ENOMEM;
@@ -45,7 +44,7 @@
return 0;
free_elems:
- vfree(smap->elems);
+ bpf_map_area_free(smap->elems);
return err;
}
@@ -76,12 +75,9 @@
if (cost >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-E2BIG);
- smap = kzalloc(cost, GFP_USER | __GFP_NOWARN);
- if (!smap) {
- smap = vzalloc(cost);
- if (!smap)
- return ERR_PTR(-ENOMEM);
- }
+ smap = bpf_map_area_alloc(cost);
+ if (!smap)
+ return ERR_PTR(-ENOMEM);
err = -E2BIG;
cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
@@ -112,7 +108,7 @@
put_buffers:
put_callchain_buffers();
free_smap:
- kvfree(smap);
+ bpf_map_area_free(smap);
return ERR_PTR(err);
}
@@ -262,9 +258,9 @@
/* wait for bpf programs to complete before freeing stack map */
synchronize_rcu();
- vfree(smap->elems);
+ bpf_map_area_free(smap->elems);
pcpu_freelist_destroy(&smap->freelist);
- kvfree(smap);
+ bpf_map_area_free(smap);
put_callchain_buffers();
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e89acea..bbb016a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -12,6 +12,8 @@
#include <linux/bpf.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mmzone.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/license.h>
@@ -49,6 +51,30 @@
list_add(&tl->list_node, &bpf_map_types);
}
+void *bpf_map_area_alloc(size_t size)
+{
+ /* We definitely need __GFP_NORETRY, so OOM killer doesn't
+ * trigger under memory pressure as we really just want to
+ * fail instead.
+ */
+ const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
+ void *area;
+
+ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+ area = kmalloc(size, GFP_USER | flags);
+ if (area != NULL)
+ return area;
+ }
+
+ return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags,
+ PAGE_KERNEL);
+}
+
+void bpf_map_area_free(void *area)
+{
+ kvfree(area);
+}
+
int bpf_map_precharge_memlock(u32 pages)
{
struct user_struct *user = get_current_user();
@@ -688,17 +714,17 @@
static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_prog *prog = filp->private_data;
- char prog_digest[sizeof(prog->digest) * 2 + 1] = { };
+ char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
- bin2hex(prog_digest, prog->digest, sizeof(prog->digest));
+ bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
seq_printf(m,
"prog_type:\t%u\n"
"prog_jited:\t%u\n"
- "prog_digest:\t%s\n"
+ "prog_tag:\t%s\n"
"memlock:\t%llu\n",
prog->type,
prog->jited,
- prog_digest,
+ prog_tag,
prog->pages * 1ULL << PAGE_SHIFT);
}
#endif
@@ -894,13 +920,14 @@
#ifdef CONFIG_CGROUP_BPF
-#define BPF_PROG_ATTACH_LAST_FIELD attach_type
+#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
static int bpf_prog_attach(const union bpf_attr *attr)
{
+ enum bpf_prog_type ptype;
struct bpf_prog *prog;
struct cgroup *cgrp;
- enum bpf_prog_type ptype;
+ int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -908,6 +935,9 @@
if (CHECK_ATTR(BPF_PROG_ATTACH))
return -EINVAL;
+ if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
+ return -EINVAL;
+
switch (attr->attach_type) {
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
@@ -930,10 +960,13 @@
return PTR_ERR(cgrp);
}
- cgroup_bpf_update(cgrp, prog, attr->attach_type);
+ ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
+ attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+ if (ret)
+ bpf_prog_put(prog);
cgroup_put(cgrp);
- return 0;
+ return ret;
}
#define BPF_PROG_DETACH_LAST_FIELD attach_type
@@ -941,6 +974,7 @@
static int bpf_prog_detach(const union bpf_attr *attr)
{
struct cgroup *cgrp;
+ int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -956,7 +990,7 @@
if (IS_ERR(cgrp))
return PTR_ERR(cgrp);
- cgroup_bpf_update(cgrp, NULL, attr->attach_type);
+ ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
cgroup_put(cgrp);
break;
@@ -964,7 +998,7 @@
return -EINVAL;
}
- return 0;
+ return ret;
}
#endif /* CONFIG_CGROUP_BPF */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 83ed2f8..cdc43b8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2936,7 +2936,7 @@
int insn_cnt = env->prog->len;
int i, j, err;
- err = bpf_prog_calc_digest(env->prog);
+ err = bpf_prog_calc_tag(env->prog);
if (err)
return err;
diff --git a/kernel/capability.c b/kernel/capability.c
index a98e814..f97fe77 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -318,6 +318,7 @@
{
return has_ns_capability(t, &init_user_ns, cap);
}
+EXPORT_SYMBOL(has_capability);
/**
* has_ns_capability_noaudit - Does a task have a capability (unaudited)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2ee9ec3..53bbca7 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -5221,6 +5221,11 @@
return ERR_PTR(err);
}
+/*
+ * The returned cgroup is fully initialized including its control mask, but
+ * it isn't associated with its kernfs_node and doesn't have the control
+ * mask applied.
+ */
static struct cgroup *cgroup_create(struct cgroup *parent)
{
struct cgroup_root *root = parent->root;
@@ -5288,11 +5293,6 @@
cgroup_propagate_control(cgrp);
- /* @cgrp doesn't have dir yet so the following will only create csses */
- ret = cgroup_apply_control_enable(cgrp);
- if (ret)
- goto out_destroy;
-
return cgrp;
out_cancel_ref:
@@ -5300,9 +5300,6 @@
out_free_cgrp:
kfree(cgrp);
return ERR_PTR(ret);
-out_destroy:
- cgroup_destroy_locked(cgrp);
- return ERR_PTR(ret);
}
static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
@@ -6501,15 +6498,16 @@
subsys_initcall(cgroup_namespaces_init);
#ifdef CONFIG_CGROUP_BPF
-void cgroup_bpf_update(struct cgroup *cgrp,
- struct bpf_prog *prog,
- enum bpf_attach_type type)
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, bool overridable)
{
struct cgroup *parent = cgroup_parent(cgrp);
+ int ret;
mutex_lock(&cgroup_mutex);
- __cgroup_bpf_update(cgrp, parent, prog, type);
+ ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
mutex_unlock(&cgroup_mutex);
+ return ret;
}
#endif /* CONFIG_CGROUP_BPF */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f75c4d0..0a5f630 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -764,7 +764,6 @@
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int prev_state, ret = 0;
- bool hasdied = false;
if (num_online_cpus() == 1)
return -EBUSY;
@@ -809,7 +808,6 @@
cpuhp_kick_ap_work(cpu);
}
- hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
out:
cpu_hotplug_done();
return ret;
@@ -1302,10 +1300,24 @@
*/
static int cpuhp_reserve_state(enum cpuhp_state state)
{
- enum cpuhp_state i;
+ enum cpuhp_state i, end;
+ struct cpuhp_step *step;
- for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
- if (!cpuhp_ap_states[i].name)
+ switch (state) {
+ case CPUHP_AP_ONLINE_DYN:
+ step = cpuhp_ap_states + CPUHP_AP_ONLINE_DYN;
+ end = CPUHP_AP_ONLINE_DYN_END;
+ break;
+ case CPUHP_BP_PREPARE_DYN:
+ step = cpuhp_bp_states + CPUHP_BP_PREPARE_DYN;
+ end = CPUHP_BP_PREPARE_DYN_END;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ for (i = state; i <= end; i++, step++) {
+ if (!step->name)
return i;
}
WARN(1, "No more dynamic states available for CPU hotplug\n");
@@ -1323,7 +1335,7 @@
mutex_lock(&cpuhp_state_mutex);
- if (state == CPUHP_AP_ONLINE_DYN) {
+ if (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN) {
ret = cpuhp_reserve_state(state);
if (ret < 0)
goto out;
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 435c14a..6605496 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -82,19 +82,19 @@
int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
{
- cputime_t utime, stime, stimescaled, utimescaled;
+ u64 utime, stime, stimescaled, utimescaled;
unsigned long long t2, t3;
unsigned long flags, t1;
s64 tmp;
task_cputime(tsk, &utime, &stime);
tmp = (s64)d->cpu_run_real_total;
- tmp += cputime_to_nsecs(utime + stime);
+ tmp += utime + stime;
d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp;
task_cputime_scaled(tsk, &utimescaled, &stimescaled);
tmp = (s64)d->cpu_scaled_run_real_total;
- tmp += cputime_to_nsecs(utimescaled + stimescaled);
+ tmp += utimescaled + stimescaled;
d->cpu_scaled_run_real_total =
(tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ab15509..77a932b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -355,6 +355,8 @@
EVENT_FLEXIBLE = 0x1,
EVENT_PINNED = 0x2,
EVENT_TIME = 0x4,
+ /* see ctx_resched() for details */
+ EVENT_CPU = 0x8,
EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
};
@@ -678,6 +680,8 @@
info->timestamp = ctx->timestamp;
}
+static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
+
#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */
#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */
@@ -690,61 +694,46 @@
static void perf_cgroup_switch(struct task_struct *task, int mode)
{
struct perf_cpu_context *cpuctx;
- struct pmu *pmu;
+ struct list_head *list;
unsigned long flags;
/*
- * disable interrupts to avoid geting nr_cgroup
- * changes via __perf_event_disable(). Also
- * avoids preemption.
+ * Disable interrupts and preemption to avoid this CPU's
+ * cgrp_cpuctx_entry to change under us.
*/
local_irq_save(flags);
- /*
- * we reschedule only in the presence of cgroup
- * constrained events.
- */
+ list = this_cpu_ptr(&cgrp_cpuctx_list);
+ list_for_each_entry(cpuctx, list, cgrp_cpuctx_entry) {
+ WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
- list_for_each_entry_rcu(pmu, &pmus, entry) {
- cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
- if (cpuctx->unique_pmu != pmu)
- continue; /* ensure we process each cpuctx once */
+ perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+ perf_pmu_disable(cpuctx->ctx.pmu);
- /*
- * perf_cgroup_events says at least one
- * context on this CPU has cgroup events.
- *
- * ctx->nr_cgroups reports the number of cgroup
- * events for a context.
- */
- if (cpuctx->ctx.nr_cgroups > 0) {
- perf_ctx_lock(cpuctx, cpuctx->task_ctx);
- perf_pmu_disable(cpuctx->ctx.pmu);
-
- if (mode & PERF_CGROUP_SWOUT) {
- cpu_ctx_sched_out(cpuctx, EVENT_ALL);
- /*
- * must not be done before ctxswout due
- * to event_filter_match() in event_sched_out()
- */
- cpuctx->cgrp = NULL;
- }
-
- if (mode & PERF_CGROUP_SWIN) {
- WARN_ON_ONCE(cpuctx->cgrp);
- /*
- * set cgrp before ctxsw in to allow
- * event_filter_match() to not have to pass
- * task around
- * we pass the cpuctx->ctx to perf_cgroup_from_task()
- * because cgorup events are only per-cpu
- */
- cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx);
- cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
- }
- perf_pmu_enable(cpuctx->ctx.pmu);
- perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+ if (mode & PERF_CGROUP_SWOUT) {
+ cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+ /*
+ * must not be done before ctxswout due
+ * to event_filter_match() in event_sched_out()
+ */
+ cpuctx->cgrp = NULL;
}
+
+ if (mode & PERF_CGROUP_SWIN) {
+ WARN_ON_ONCE(cpuctx->cgrp);
+ /*
+ * set cgrp before ctxsw in to allow
+ * event_filter_match() to not have to pass
+ * task around
+ * we pass the cpuctx->ctx to perf_cgroup_from_task()
+ * because cgorup events are only per-cpu
+ */
+ cpuctx->cgrp = perf_cgroup_from_task(task,
+ &cpuctx->ctx);
+ cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
+ }
+ perf_pmu_enable(cpuctx->ctx.pmu);
+ perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
local_irq_restore(flags);
@@ -889,6 +878,7 @@
struct perf_event_context *ctx, bool add)
{
struct perf_cpu_context *cpuctx;
+ struct list_head *cpuctx_entry;
if (!is_cgroup_event(event))
return;
@@ -902,15 +892,16 @@
* this will always be called from the right CPU.
*/
cpuctx = __get_cpu_context(ctx);
-
- /*
- * cpuctx->cgrp is NULL until a cgroup event is sched in or
- * ctx->nr_cgroup == 0 .
- */
- if (add && perf_cgroup_from_task(current, ctx) == event->cgrp)
- cpuctx->cgrp = event->cgrp;
- else if (!add)
+ cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
+ /* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
+ if (add) {
+ list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
+ if (perf_cgroup_from_task(current, ctx) == event->cgrp)
+ cpuctx->cgrp = event->cgrp;
+ } else {
+ list_del(cpuctx_entry);
cpuctx->cgrp = NULL;
+ }
}
#else /* !CONFIG_CGROUP_PERF */
@@ -1453,6 +1444,20 @@
update_event_times(event);
}
+static enum event_type_t get_event_type(struct perf_event *event)
+{
+ struct perf_event_context *ctx = event->ctx;
+ enum event_type_t event_type;
+
+ lockdep_assert_held(&ctx->lock);
+
+ event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE;
+ if (!ctx->task)
+ event_type |= EVENT_CPU;
+
+ return event_type;
+}
+
static struct list_head *
ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
{
@@ -1469,7 +1474,6 @@
static void
list_add_event(struct perf_event *event, struct perf_event_context *ctx)
{
-
lockdep_assert_held(&ctx->lock);
WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
@@ -1624,6 +1628,8 @@
{
struct perf_event *group_leader = event->group_leader, *pos;
+ lockdep_assert_held(&event->ctx->lock);
+
/*
* We can have double attach due to group movement in perf_event_open.
*/
@@ -1697,6 +1703,8 @@
struct perf_event *sibling, *tmp;
struct list_head *list = NULL;
+ lockdep_assert_held(&event->ctx->lock);
+
/*
* We can have double detach due to exit/hot-unplug + close.
*/
@@ -1895,9 +1903,29 @@
*/
static void perf_remove_from_context(struct perf_event *event, unsigned long flags)
{
- lockdep_assert_held(&event->ctx->mutex);
+ struct perf_event_context *ctx = event->ctx;
+
+ lockdep_assert_held(&ctx->mutex);
event_function_call(event, __perf_remove_from_context, (void *)flags);
+
+ /*
+ * The above event_function_call() can NO-OP when it hits
+ * TASK_TOMBSTONE. In that case we must already have been detached
+ * from the context (by perf_event_exit_event()) but the grouping
+ * might still be in-tact.
+ */
+ WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
+ if ((flags & DETACH_GROUP) &&
+ (event->attach_state & PERF_ATTACH_GROUP)) {
+ /*
+ * Since in that case we cannot possibly be scheduled, simply
+ * detach now.
+ */
+ raw_spin_lock_irq(&ctx->lock);
+ perf_group_detach(event);
+ raw_spin_unlock_irq(&ctx->lock);
+ }
}
/*
@@ -2203,7 +2231,8 @@
struct task_struct *task);
static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
+ struct perf_event_context *ctx,
+ enum event_type_t event_type)
{
if (!cpuctx->task_ctx)
return;
@@ -2211,7 +2240,7 @@
if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
return;
- ctx_sched_out(ctx, cpuctx, EVENT_ALL);
+ ctx_sched_out(ctx, cpuctx, event_type);
}
static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
@@ -2226,13 +2255,51 @@
ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
}
+/*
+ * We want to maintain the following priority of scheduling:
+ * - CPU pinned (EVENT_CPU | EVENT_PINNED)
+ * - task pinned (EVENT_PINNED)
+ * - CPU flexible (EVENT_CPU | EVENT_FLEXIBLE)
+ * - task flexible (EVENT_FLEXIBLE).
+ *
+ * In order to avoid unscheduling and scheduling back in everything every
+ * time an event is added, only do it for the groups of equal priority and
+ * below.
+ *
+ * This can be called after a batch operation on task events, in which case
+ * event_type is a bit mask of the types of events involved. For CPU events,
+ * event_type is only either EVENT_PINNED or EVENT_FLEXIBLE.
+ */
static void ctx_resched(struct perf_cpu_context *cpuctx,
- struct perf_event_context *task_ctx)
+ struct perf_event_context *task_ctx,
+ enum event_type_t event_type)
{
+ enum event_type_t ctx_event_type = event_type & EVENT_ALL;
+ bool cpu_event = !!(event_type & EVENT_CPU);
+
+ /*
+ * If pinned groups are involved, flexible groups also need to be
+ * scheduled out.
+ */
+ if (event_type & EVENT_PINNED)
+ event_type |= EVENT_FLEXIBLE;
+
perf_pmu_disable(cpuctx->ctx.pmu);
if (task_ctx)
- task_ctx_sched_out(cpuctx, task_ctx);
- cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+ task_ctx_sched_out(cpuctx, task_ctx, event_type);
+
+ /*
+ * Decide which cpu ctx groups to schedule out based on the types
+ * of events that caused rescheduling:
+ * - EVENT_CPU: schedule out corresponding groups;
+ * - EVENT_PINNED task events: schedule out EVENT_FLEXIBLE groups;
+ * - otherwise, do nothing more.
+ */
+ if (cpu_event)
+ cpu_ctx_sched_out(cpuctx, ctx_event_type);
+ else if (ctx_event_type & EVENT_PINNED)
+ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+
perf_event_sched_in(cpuctx, task_ctx, current);
perf_pmu_enable(cpuctx->ctx.pmu);
}
@@ -2249,7 +2316,7 @@
struct perf_event_context *ctx = event->ctx;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
struct perf_event_context *task_ctx = cpuctx->task_ctx;
- bool activate = true;
+ bool reprogram = true;
int ret = 0;
raw_spin_lock(&cpuctx->ctx.lock);
@@ -2257,30 +2324,29 @@
raw_spin_lock(&ctx->lock);
task_ctx = ctx;
- /* If we're on the wrong CPU, try again */
- if (task_cpu(ctx->task) != smp_processor_id()) {
+ reprogram = (ctx->task == current);
+
+ /*
+ * If the task is running, it must be running on this CPU,
+ * otherwise we cannot reprogram things.
+ *
+ * If its not running, we don't care, ctx->lock will
+ * serialize against it becoming runnable.
+ */
+ if (task_curr(ctx->task) && !reprogram) {
ret = -ESRCH;
goto unlock;
}
- /*
- * If we're on the right CPU, see if the task we target is
- * current, if not we don't have to activate the ctx, a future
- * context switch will do that for us.
- */
- if (ctx->task != current)
- activate = false;
- else
- WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx);
-
+ WARN_ON_ONCE(reprogram && cpuctx->task_ctx && cpuctx->task_ctx != ctx);
} else if (task_ctx) {
raw_spin_lock(&task_ctx->lock);
}
- if (activate) {
+ if (reprogram) {
ctx_sched_out(ctx, cpuctx, EVENT_TIME);
add_event_to_ctx(event, ctx);
- ctx_resched(cpuctx, task_ctx);
+ ctx_resched(cpuctx, task_ctx, get_event_type(event));
} else {
add_event_to_ctx(event, ctx);
}
@@ -2328,13 +2394,36 @@
/*
* Installing events is tricky because we cannot rely on ctx->is_active
* to be set in case this is the nr_events 0 -> 1 transition.
+ *
+ * Instead we use task_curr(), which tells us if the task is running.
+ * However, since we use task_curr() outside of rq::lock, we can race
+ * against the actual state. This means the result can be wrong.
+ *
+ * If we get a false positive, we retry, this is harmless.
+ *
+ * If we get a false negative, things are complicated. If we are after
+ * perf_event_context_sched_in() ctx::lock will serialize us, and the
+ * value must be correct. If we're before, it doesn't matter since
+ * perf_event_context_sched_in() will program the counter.
+ *
+ * However, this hinges on the remote context switch having observed
+ * our task->perf_event_ctxp[] store, such that it will in fact take
+ * ctx::lock in perf_event_context_sched_in().
+ *
+ * We do this by task_function_call(), if the IPI fails to hit the task
+ * we know any future context switch of task must see the
+ * perf_event_ctpx[] store.
*/
-again:
+
/*
- * Cannot use task_function_call() because we need to run on the task's
- * CPU regardless of whether its current or not.
+ * This smp_mb() orders the task->perf_event_ctxp[] store with the
+ * task_cpu() load, such that if the IPI then does not find the task
+ * running, a future context switch of that task must observe the
+ * store.
*/
- if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event))
+ smp_mb();
+again:
+ if (!task_function_call(task, __perf_install_in_context, event))
return;
raw_spin_lock_irq(&ctx->lock);
@@ -2348,12 +2437,16 @@
raw_spin_unlock_irq(&ctx->lock);
return;
}
- raw_spin_unlock_irq(&ctx->lock);
/*
- * Since !ctx->is_active doesn't mean anything, we must IPI
- * unconditionally.
+ * If the task is not running, ctx->lock will avoid it becoming so,
+ * thus we can safely install the event.
*/
- goto again;
+ if (task_curr(task)) {
+ raw_spin_unlock_irq(&ctx->lock);
+ goto again;
+ }
+ add_event_to_ctx(event, ctx);
+ raw_spin_unlock_irq(&ctx->lock);
}
/*
@@ -2420,7 +2513,7 @@
if (ctx->task)
WARN_ON_ONCE(task_ctx != ctx);
- ctx_resched(cpuctx, task_ctx);
+ ctx_resched(cpuctx, task_ctx, get_event_type(event));
}
/*
@@ -2847,7 +2940,7 @@
if (do_switch) {
raw_spin_lock(&ctx->lock);
- task_ctx_sched_out(cpuctx, ctx);
+ task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
raw_spin_unlock(&ctx->lock);
}
}
@@ -2894,7 +2987,7 @@
return;
list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
- pmu = cpuctx->unique_pmu; /* software PMUs will not have sched_task */
+ pmu = cpuctx->ctx.pmu; /* software PMUs will not have sched_task */
if (WARN_ON_ONCE(!pmu->sched_task))
continue;
@@ -3084,8 +3177,12 @@
* We want to keep the following priority order:
* cpu pinned (that don't need to move), task pinned,
* cpu flexible, task flexible.
+ *
+ * However, if task's ctx is not carrying any pinned
+ * events, no need to flip the cpuctx's events around.
*/
- cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+ if (!list_empty(&ctx->pinned_groups))
+ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
perf_event_sched_in(cpuctx, ctx, task);
perf_pmu_enable(ctx->pmu);
perf_ctx_unlock(cpuctx, ctx);
@@ -3400,6 +3497,7 @@
static void perf_event_enable_on_exec(int ctxn)
{
struct perf_event_context *ctx, *clone_ctx = NULL;
+ enum event_type_t event_type = 0;
struct perf_cpu_context *cpuctx;
struct perf_event *event;
unsigned long flags;
@@ -3413,15 +3511,17 @@
cpuctx = __get_cpu_context(ctx);
perf_ctx_lock(cpuctx, ctx);
ctx_sched_out(ctx, cpuctx, EVENT_TIME);
- list_for_each_entry(event, &ctx->event_list, event_entry)
+ list_for_each_entry(event, &ctx->event_list, event_entry) {
enabled |= event_enable_on_exec(event, ctx);
+ event_type |= get_event_type(event);
+ }
/*
* Unclone and reschedule this context if we enabled any event.
*/
if (enabled) {
clone_ctx = unclone_ctx(ctx);
- ctx_resched(cpuctx, ctx);
+ ctx_resched(cpuctx, ctx, event_type);
}
perf_ctx_unlock(cpuctx, ctx);
@@ -3438,14 +3538,15 @@
int ret;
};
-static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
{
- int event_cpu = event->oncpu;
u16 local_pkg, event_pkg;
if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
- event_pkg = topology_physical_package_id(event_cpu);
- local_pkg = topology_physical_package_id(local_cpu);
+ int local_cpu = smp_processor_id();
+
+ event_pkg = topology_physical_package_id(event_cpu);
+ local_pkg = topology_physical_package_id(local_cpu);
if (event_pkg == local_pkg)
return local_cpu;
@@ -3575,7 +3676,7 @@
static int perf_event_read(struct perf_event *event, bool group)
{
- int ret = 0, cpu_to_read, local_cpu;
+ int event_cpu, ret = 0;
/*
* If event is enabled and currently active on a CPU, update the
@@ -3588,21 +3689,25 @@
.ret = 0,
};
- local_cpu = get_cpu();
- cpu_to_read = find_cpu_to_read(event, local_cpu);
- put_cpu();
+ event_cpu = READ_ONCE(event->oncpu);
+ if ((unsigned)event_cpu >= nr_cpu_ids)
+ return 0;
+
+ preempt_disable();
+ event_cpu = __perf_event_read_cpu(event, event_cpu);
/*
* Purposely ignore the smp_call_function_single() return
* value.
*
- * If event->oncpu isn't a valid CPU it means the event got
+ * If event_cpu isn't a valid CPU it means the event got
* scheduled out and that will have updated the event count.
*
* Therefore, either way, we'll have an up-to-date event count
* after this.
*/
- (void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
+ (void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1);
+ preempt_enable();
ret = data.ret;
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
@@ -6583,6 +6688,27 @@
char *buf = NULL;
char *name;
+ if (vma->vm_flags & VM_READ)
+ prot |= PROT_READ;
+ if (vma->vm_flags & VM_WRITE)
+ prot |= PROT_WRITE;
+ if (vma->vm_flags & VM_EXEC)
+ prot |= PROT_EXEC;
+
+ if (vma->vm_flags & VM_MAYSHARE)
+ flags = MAP_SHARED;
+ else
+ flags = MAP_PRIVATE;
+
+ if (vma->vm_flags & VM_DENYWRITE)
+ flags |= MAP_DENYWRITE;
+ if (vma->vm_flags & VM_MAYEXEC)
+ flags |= MAP_EXECUTABLE;
+ if (vma->vm_flags & VM_LOCKED)
+ flags |= MAP_LOCKED;
+ if (vma->vm_flags & VM_HUGETLB)
+ flags |= MAP_HUGETLB;
+
if (file) {
struct inode *inode;
dev_t dev;
@@ -6609,27 +6735,6 @@
maj = MAJOR(dev);
min = MINOR(dev);
- if (vma->vm_flags & VM_READ)
- prot |= PROT_READ;
- if (vma->vm_flags & VM_WRITE)
- prot |= PROT_WRITE;
- if (vma->vm_flags & VM_EXEC)
- prot |= PROT_EXEC;
-
- if (vma->vm_flags & VM_MAYSHARE)
- flags = MAP_SHARED;
- else
- flags = MAP_PRIVATE;
-
- if (vma->vm_flags & VM_DENYWRITE)
- flags |= MAP_DENYWRITE;
- if (vma->vm_flags & VM_MAYEXEC)
- flags |= MAP_EXECUTABLE;
- if (vma->vm_flags & VM_LOCKED)
- flags |= MAP_LOCKED;
- if (vma->vm_flags & VM_HUGETLB)
- flags |= MAP_HUGETLB;
-
goto got_name;
} else {
if (vma->vm_ops && vma->vm_ops->name) {
@@ -7034,25 +7139,12 @@
perf_output_end(&handle);
}
-/*
- * Generic event overflow handling, sampling.
- */
-
-static int __perf_event_overflow(struct perf_event *event,
- int throttle, struct perf_sample_data *data,
- struct pt_regs *regs)
+static int
+__perf_event_account_interrupt(struct perf_event *event, int throttle)
{
- int events = atomic_read(&event->event_limit);
struct hw_perf_event *hwc = &event->hw;
- u64 seq;
int ret = 0;
-
- /*
- * Non-sampling counters might still use the PMI to fold short
- * hardware counters, ignore those.
- */
- if (unlikely(!is_sampling_event(event)))
- return 0;
+ u64 seq;
seq = __this_cpu_read(perf_throttled_seq);
if (seq != hwc->interrupts_seq) {
@@ -7080,6 +7172,34 @@
perf_adjust_period(event, delta, hwc->last_period, true);
}
+ return ret;
+}
+
+int perf_event_account_interrupt(struct perf_event *event)
+{
+ return __perf_event_account_interrupt(event, 1);
+}
+
+/*
+ * Generic event overflow handling, sampling.
+ */
+
+static int __perf_event_overflow(struct perf_event *event,
+ int throttle, struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ int events = atomic_read(&event->event_limit);
+ int ret = 0;
+
+ /*
+ * Non-sampling counters might still use the PMI to fold short
+ * hardware counters, ignore those.
+ */
+ if (unlikely(!is_sampling_event(event)))
+ return 0;
+
+ ret = __perf_event_account_interrupt(event, throttle);
+
/*
* XXX event_limit might not quite work as expected on inherited
* events
@@ -7975,6 +8095,9 @@
if (task == TASK_TOMBSTONE)
return;
+ if (!ifh->nr_file_filters)
+ return;
+
mm = get_task_mm(event->ctx->task);
if (!mm)
goto restart;
@@ -8145,6 +8268,7 @@
* attribute.
*/
if (state == IF_STATE_END) {
+ ret = -EINVAL;
if (kernel && event->attr.exclude_kernel)
goto fail;
@@ -8152,6 +8276,18 @@
if (!filename)
goto fail;
+ /*
+ * For now, we only support file-based filters
+ * in per-task events; doing so for CPU-wide
+ * events requires additional context switching
+ * trickery, since same object code will be
+ * mapped at different virtual addresses in
+ * different processes.
+ */
+ ret = -EOPNOTSUPP;
+ if (!event->ctx->task)
+ goto fail_free_name;
+
/* look up the path and grab its inode */
ret = kern_path(filename, LOOKUP_FOLLOW, &path);
if (ret)
@@ -8167,6 +8303,8 @@
!S_ISREG(filter->inode->i_mode))
/* free_filters_list() will iput() */
goto fail;
+
+ event->addr_filters.nr_file_filters++;
}
/* ready to consume more filters */
@@ -8206,24 +8344,13 @@
if (WARN_ON_ONCE(event->parent))
return -EINVAL;
- /*
- * For now, we only support filtering in per-task events; doing so
- * for CPU-wide events requires additional context switching trickery,
- * since same object code will be mapped at different virtual
- * addresses in different processes.
- */
- if (!event->ctx->task)
- return -EOPNOTSUPP;
-
ret = perf_event_parse_addr_filter(event, filter_str, &filters);
if (ret)
- return ret;
+ goto fail_clear_files;
ret = event->pmu->addr_filters_validate(&filters);
- if (ret) {
- free_filters_list(&filters);
- return ret;
- }
+ if (ret)
+ goto fail_free_filters;
/* remove existing filters, if any */
perf_addr_filters_splice(event, &filters);
@@ -8232,6 +8359,14 @@
perf_event_for_each_child(event, perf_event_addr_filters_apply);
return ret;
+
+fail_free_filters:
+ free_filters_list(&filters);
+
+fail_clear_files:
+ event->addr_filters.nr_file_filters = 0;
+
+ return ret;
}
static int perf_event_set_filter(struct perf_event *event, void __user *arg)
@@ -8583,37 +8718,10 @@
return NULL;
}
-static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
-{
- int cpu;
-
- for_each_possible_cpu(cpu) {
- struct perf_cpu_context *cpuctx;
-
- cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
-
- if (cpuctx->unique_pmu == old_pmu)
- cpuctx->unique_pmu = pmu;
- }
-}
-
static void free_pmu_context(struct pmu *pmu)
{
- struct pmu *i;
-
mutex_lock(&pmus_lock);
- /*
- * Like a real lame refcount.
- */
- list_for_each_entry(i, &pmus, entry) {
- if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
- update_pmu_context(i, pmu);
- goto out;
- }
- }
-
free_percpu(pmu->pmu_cpu_context);
-out:
mutex_unlock(&pmus_lock);
}
@@ -8817,8 +8925,6 @@
cpuctx->ctx.pmu = pmu;
__perf_mux_hrtimer_init(cpuctx, cpu);
-
- cpuctx->unique_pmu = pmu;
}
got_cpu_context:
@@ -8936,6 +9042,14 @@
idx = srcu_read_lock(&pmus_srcu);
+ /* Try parent's PMU first: */
+ if (event->parent && event->parent->pmu) {
+ pmu = event->parent->pmu;
+ ret = perf_try_init_event(pmu, event);
+ if (!ret)
+ goto unlock;
+ }
+
rcu_read_lock();
pmu = idr_find(&pmu_idr, event->attr.type);
rcu_read_unlock();
@@ -9503,6 +9617,37 @@
return 0;
}
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+ struct perf_event_context *ctx)
+{
+ struct perf_event_context *gctx;
+
+again:
+ rcu_read_lock();
+ gctx = READ_ONCE(group_leader->ctx);
+ if (!atomic_inc_not_zero(&gctx->refcount)) {
+ rcu_read_unlock();
+ goto again;
+ }
+ rcu_read_unlock();
+
+ mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+ if (group_leader->ctx != gctx) {
+ mutex_unlock(&ctx->mutex);
+ mutex_unlock(&gctx->mutex);
+ put_ctx(gctx);
+ goto again;
+ }
+
+ return gctx;
+}
+
/**
* sys_perf_event_open - open a performance event, associate it to a task/cpu
*
@@ -9746,12 +9891,31 @@
}
if (move_group) {
- gctx = group_leader->ctx;
- mutex_lock_double(&gctx->mutex, &ctx->mutex);
+ gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
if (gctx->task == TASK_TOMBSTONE) {
err = -ESRCH;
goto err_locked;
}
+
+ /*
+ * Check if we raced against another sys_perf_event_open() call
+ * moving the software group underneath us.
+ */
+ if (!(group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
+ /*
+ * If someone moved the group out from under us, check
+ * if this new event wound up on the same ctx, if so
+ * its the regular !move_group case, otherwise fail.
+ */
+ if (gctx != ctx) {
+ err = -EINVAL;
+ goto err_locked;
+ } else {
+ perf_event_ctx_unlock(group_leader, gctx);
+ move_group = 0;
+ }
+ }
} else {
mutex_lock(&ctx->mutex);
}
@@ -9853,7 +10017,7 @@
perf_unpin_context(ctx);
if (move_group)
- mutex_unlock(&gctx->mutex);
+ perf_event_ctx_unlock(group_leader, gctx);
mutex_unlock(&ctx->mutex);
if (task) {
@@ -9879,7 +10043,7 @@
err_locked:
if (move_group)
- mutex_unlock(&gctx->mutex);
+ perf_event_ctx_unlock(group_leader, gctx);
mutex_unlock(&ctx->mutex);
/* err_file: */
fput(event_file);
@@ -10146,7 +10310,7 @@
* in.
*/
raw_spin_lock_irq(&child_ctx->lock);
- task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx);
+ task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx, EVENT_ALL);
/*
* Now that the context is inactive, destroy the task <-> ctx relation
@@ -10595,6 +10759,9 @@
INIT_LIST_HEAD(&per_cpu(pmu_sb_events.list, cpu));
raw_spin_lock_init(&per_cpu(pmu_sb_events.lock, cpu));
+#ifdef CONFIG_CGROUP_PERF
+ INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
+#endif
INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
}
}
diff --git a/kernel/exit.c b/kernel/exit.c
index a9441da..b67c57f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -87,7 +87,7 @@
bool group_dead = thread_group_leader(tsk);
struct sighand_struct *sighand;
struct tty_struct *uninitialized_var(tty);
- cputime_t utime, stime;
+ u64 utime, stime;
sighand = rcu_dereference_check(tsk->sighand,
lockdep_tasklist_lock_is_held());
@@ -1121,7 +1121,7 @@
struct signal_struct *sig = p->signal;
struct signal_struct *psig = current->signal;
unsigned long maxrss;
- cputime_t tgutime, tgstime;
+ u64 tgutime, tgstime;
/*
* The resource counters for the group leader are in its
diff --git a/kernel/extable.c b/kernel/extable.c
index e3beec4..e135947 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -20,6 +20,7 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/init.h>
+#include <linux/kprobes.h>
#include <asm/sections.h>
#include <linux/uaccess.h>
@@ -104,6 +105,8 @@
return 1;
if (is_ftrace_trampoline(addr))
return 1;
+ if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
+ return 1;
/*
* There might be init symbols in saved stacktraces.
* Give those symbols a chance to be printed in
@@ -123,7 +126,11 @@
return 1;
if (is_module_text_address(addr))
return 1;
- return is_ftrace_trampoline(addr);
+ if (is_ftrace_trampoline(addr))
+ return 1;
+ if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
+ return 1;
+ return 0;
}
/*
diff --git a/kernel/fork.c b/kernel/fork.c
index ea33f8a..ff82e24 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1306,6 +1306,7 @@
}
}
+#ifdef CONFIG_POSIX_TIMERS
/*
* Initialize POSIX timer handling for a thread group.
*/
@@ -1315,7 +1316,7 @@
cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
if (cpu_limit != RLIM_INFINITY) {
- sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
+ sig->cputime_expires.prof_exp = cpu_limit * NSEC_PER_SEC;
sig->cputimer.running = true;
}
@@ -1324,6 +1325,9 @@
INIT_LIST_HEAD(&sig->cpu_timers[1]);
INIT_LIST_HEAD(&sig->cpu_timers[2]);
}
+#else
+static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { }
+#endif
static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
{
@@ -1348,11 +1352,11 @@
init_waitqueue_head(&sig->wait_chldexit);
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
- INIT_LIST_HEAD(&sig->posix_timers);
seqlock_init(&sig->stats_lock);
prev_cputime_init(&sig->prev_cputime);
#ifdef CONFIG_POSIX_TIMERS
+ INIT_LIST_HEAD(&sig->posix_timers);
hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
sig->real_timer.function = it_real_fn;
#endif
@@ -1427,6 +1431,7 @@
#endif
}
+#ifdef CONFIG_POSIX_TIMERS
/*
* Initialize POSIX timer handling for a single task.
*/
@@ -1439,6 +1444,9 @@
INIT_LIST_HEAD(&tsk->cpu_timers[1]);
INIT_LIST_HEAD(&tsk->cpu_timers[2]);
}
+#else
+static inline void posix_cpu_timers_init(struct task_struct *tsk) { }
+#endif
static inline void
init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
diff --git a/kernel/futex.c b/kernel/futex.c
index 0842c8ca..cdf3650 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -3323,4 +3323,4 @@
return 0;
}
-__initcall(futex_init);
+core_initcall(futex_init);
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index 74d90a7..1613bfd 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -2,6 +2,7 @@
#include <linux/interrupt.h>
#include <linux/device.h>
#include <linux/gfp.h>
+#include <linux/irq.h>
/*
* Device resource management aware IRQ request/free implementation.
@@ -33,7 +34,7 @@
* @thread_fn: function to be called in a threaded interrupt context. NULL
* for devices which handle everything in @handler
* @irqflags: Interrupt type flags
- * @devname: An ascii name for the claiming device
+ * @devname: An ascii name for the claiming device, dev_name(dev) if NULL
* @dev_id: A cookie passed back to the handler function
*
* Except for the extra @dev argument, this function takes the
@@ -57,6 +58,9 @@
if (!dr)
return -ENOMEM;
+ if (!devname)
+ devname = dev_name(dev);
+
rc = request_threaded_irq(irq, handler, thread_fn, irqflags, devname,
dev_id);
if (rc) {
@@ -80,7 +84,7 @@
* @thread_fn: function to be called in a threaded interrupt context. NULL
* for devices which handle everything in @handler
* @irqflags: Interrupt type flags
- * @devname: An ascii name for the claiming device
+ * @devname: An ascii name for the claiming device, dev_name(dev) if NULL
* @dev_id: A cookie passed back to the handler function
*
* Except for the extra @dev argument, this function takes the
@@ -103,6 +107,9 @@
if (!dr)
return -ENOMEM;
+ if (!devname)
+ devname = dev_name(dev);
+
rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id);
if (rc < 0) {
devres_free(dr);
@@ -137,3 +144,57 @@
free_irq(irq, dev_id);
}
EXPORT_SYMBOL(devm_free_irq);
+
+struct irq_desc_devres {
+ unsigned int from;
+ unsigned int cnt;
+};
+
+static void devm_irq_desc_release(struct device *dev, void *res)
+{
+ struct irq_desc_devres *this = res;
+
+ irq_free_descs(this->from, this->cnt);
+}
+
+/**
+ * __devm_irq_alloc_descs - Allocate and initialize a range of irq descriptors
+ * for a managed device
+ * @dev: Device to allocate the descriptors for
+ * @irq: Allocate for specific irq number if irq >= 0
+ * @from: Start the search from this irq number
+ * @cnt: Number of consecutive irqs to allocate
+ * @node: Preferred node on which the irq descriptor should be allocated
+ * @owner: Owning module (can be NULL)
+ * @affinity: Optional pointer to an affinity mask array of size @cnt
+ * which hints where the irq descriptors should be allocated
+ * and which default affinities to use
+ *
+ * Returns the first irq number or error code.
+ *
+ * Note: Use the provided wrappers (devm_irq_alloc_desc*) for simplicity.
+ */
+int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from,
+ unsigned int cnt, int node, struct module *owner,
+ const struct cpumask *affinity)
+{
+ struct irq_desc_devres *dr;
+ int base;
+
+ dr = devres_alloc(devm_irq_desc_release, sizeof(*dr), GFP_KERNEL);
+ if (!dr)
+ return -ENOMEM;
+
+ base = __irq_alloc_descs(irq, from, cnt, node, owner, affinity);
+ if (base < 0) {
+ devres_free(dr);
+ return base;
+ }
+
+ dr->from = base;
+ dr->cnt = cnt;
+ devres_add(dev, dr);
+
+ return base;
+}
+EXPORT_SYMBOL_GPL(__devm_irq_alloc_descs);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 8c0a0ae..b59e676 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1346,6 +1346,30 @@
}
EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent);
+static void __irq_domain_activate_irq(struct irq_data *irq_data)
+{
+ if (irq_data && irq_data->domain) {
+ struct irq_domain *domain = irq_data->domain;
+
+ if (irq_data->parent_data)
+ __irq_domain_activate_irq(irq_data->parent_data);
+ if (domain->ops->activate)
+ domain->ops->activate(domain, irq_data);
+ }
+}
+
+static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
+{
+ if (irq_data && irq_data->domain) {
+ struct irq_domain *domain = irq_data->domain;
+
+ if (domain->ops->deactivate)
+ domain->ops->deactivate(domain, irq_data);
+ if (irq_data->parent_data)
+ __irq_domain_deactivate_irq(irq_data->parent_data);
+ }
+}
+
/**
* irq_domain_activate_irq - Call domain_ops->activate recursively to activate
* interrupt
@@ -1356,13 +1380,9 @@
*/
void irq_domain_activate_irq(struct irq_data *irq_data)
{
- if (irq_data && irq_data->domain) {
- struct irq_domain *domain = irq_data->domain;
-
- if (irq_data->parent_data)
- irq_domain_activate_irq(irq_data->parent_data);
- if (domain->ops->activate)
- domain->ops->activate(domain, irq_data);
+ if (!irqd_is_activated(irq_data)) {
+ __irq_domain_activate_irq(irq_data);
+ irqd_set_activated(irq_data);
}
}
@@ -1376,13 +1396,9 @@
*/
void irq_domain_deactivate_irq(struct irq_data *irq_data)
{
- if (irq_data && irq_data->domain) {
- struct irq_domain *domain = irq_data->domain;
-
- if (domain->ops->deactivate)
- domain->ops->deactivate(domain, irq_data);
- if (irq_data->parent_data)
- irq_domain_deactivate_irq(irq_data->parent_data);
+ if (irqd_is_activated(irq_data)) {
+ __irq_domain_deactivate_irq(irq_data);
+ irqd_clr_activated(irq_data);
}
}
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index feaa813..c53edad 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -487,6 +487,8 @@
}
if (desc->irq_data.domain)
seq_printf(p, " %*d", prec, (int) desc->irq_data.hwirq);
+ else
+ seq_printf(p, " %*s", prec, "");
#ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL
seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge");
#endif
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 5707f97..061ba7e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -175,7 +175,9 @@
static inline int bad_action_ret(irqreturn_t action_ret)
{
- if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD)))
+ unsigned int r = action_ret;
+
+ if (likely(r <= (IRQ_HANDLED | IRQ_WAKE_THREAD)))
return 0;
return 1;
}
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 93ad6c1..a9b8cf5 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -182,6 +182,13 @@
}
EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
+void static_key_deferred_flush(struct static_key_deferred *key)
+{
+ STATIC_KEY_CHECK_USE();
+ flush_delayed_work(&key->work);
+}
+EXPORT_SYMBOL_GPL(static_key_deferred_flush);
+
void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 4346010..ebb4dad 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -149,9 +149,11 @@
struct kprobe_insn_page *kip;
kprobe_opcode_t *slot = NULL;
+ /* Since the slot array is not protected by rcu, we need a mutex */
mutex_lock(&c->mutex);
retry:
- list_for_each_entry(kip, &c->pages, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(kip, &c->pages, list) {
if (kip->nused < slots_per_page(c)) {
int i;
for (i = 0; i < slots_per_page(c); i++) {
@@ -159,6 +161,7 @@
kip->slot_used[i] = SLOT_USED;
kip->nused++;
slot = kip->insns + (i * c->insn_size);
+ rcu_read_unlock();
goto out;
}
}
@@ -167,6 +170,7 @@
WARN_ON(1);
}
}
+ rcu_read_unlock();
/* If there are any garbage slots, collect it and try again. */
if (c->nr_garbage && collect_garbage_slots(c) == 0)
@@ -193,7 +197,7 @@
kip->nused = 1;
kip->ngarbage = 0;
kip->cache = c;
- list_add(&kip->list, &c->pages);
+ list_add_rcu(&kip->list, &c->pages);
slot = kip->insns;
out:
mutex_unlock(&c->mutex);
@@ -213,7 +217,8 @@
* next time somebody inserts a probe.
*/
if (!list_is_singular(&kip->list)) {
- list_del(&kip->list);
+ list_del_rcu(&kip->list);
+ synchronize_rcu();
kip->cache->free(kip->insns);
kfree(kip);
}
@@ -235,8 +240,7 @@
continue;
kip->ngarbage = 0; /* we will collect all garbages */
for (i = 0; i < slots_per_page(c); i++) {
- if (kip->slot_used[i] == SLOT_DIRTY &&
- collect_one_slot(kip, i))
+ if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i))
break;
}
}
@@ -248,29 +252,60 @@
kprobe_opcode_t *slot, int dirty)
{
struct kprobe_insn_page *kip;
+ long idx;
mutex_lock(&c->mutex);
- list_for_each_entry(kip, &c->pages, list) {
- long idx = ((long)slot - (long)kip->insns) /
- (c->insn_size * sizeof(kprobe_opcode_t));
- if (idx >= 0 && idx < slots_per_page(c)) {
- WARN_ON(kip->slot_used[idx] != SLOT_USED);
- if (dirty) {
- kip->slot_used[idx] = SLOT_DIRTY;
- kip->ngarbage++;
- if (++c->nr_garbage > slots_per_page(c))
- collect_garbage_slots(c);
- } else
- collect_one_slot(kip, idx);
+ rcu_read_lock();
+ list_for_each_entry_rcu(kip, &c->pages, list) {
+ idx = ((long)slot - (long)kip->insns) /
+ (c->insn_size * sizeof(kprobe_opcode_t));
+ if (idx >= 0 && idx < slots_per_page(c))
goto out;
+ }
+ /* Could not find this slot. */
+ WARN_ON(1);
+ kip = NULL;
+out:
+ rcu_read_unlock();
+ /* Mark and sweep: this may sleep */
+ if (kip) {
+ /* Check double free */
+ WARN_ON(kip->slot_used[idx] != SLOT_USED);
+ if (dirty) {
+ kip->slot_used[idx] = SLOT_DIRTY;
+ kip->ngarbage++;
+ if (++c->nr_garbage > slots_per_page(c))
+ collect_garbage_slots(c);
+ } else {
+ collect_one_slot(kip, idx);
}
}
- /* Could not free this slot. */
- WARN_ON(1);
-out:
mutex_unlock(&c->mutex);
}
+/*
+ * Check given address is on the page of kprobe instruction slots.
+ * This will be used for checking whether the address on a stack
+ * is on a text area or not.
+ */
+bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
+{
+ struct kprobe_insn_page *kip;
+ bool ret = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(kip, &c->pages, list) {
+ if (addr >= (unsigned long)kip->insns &&
+ addr < (unsigned long)kip->insns + PAGE_SIZE) {
+ ret = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
#ifdef CONFIG_OPTPROBES
/* For optimized_kprobe buffer */
struct kprobe_insn_cache kprobe_optinsn_slots = {
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 2318fba..8461a43 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -850,7 +850,6 @@
list_add(&work->node, &worker->delayed_work_list);
work->worker = worker;
- timer_stats_timer_set_start_info(&dwork->timer);
timer->expires = jiffies + delay;
add_timer(timer);
}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index bf60725..9812e5d 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4412,13 +4412,13 @@
#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
/* Note: the following can be executed concurrently, so be careful. */
printk("\n");
- printk("===============================\n");
- printk("[ INFO: suspicious RCU usage. ]\n");
+ pr_err("===============================\n");
+ pr_err("[ ERR: suspicious RCU usage. ]\n");
print_kernel_ident();
- printk("-------------------------------\n");
- printk("%s:%d %s!\n", file, line, s);
- printk("\nother info that might help us debug this:\n\n");
- printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
+ pr_err("-------------------------------\n");
+ pr_err("%s:%d %s!\n", file, line, s);
+ pr_err("\nother info that might help us debug this:\n\n");
+ pr_err("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
!rcu_lockdep_current_cpu_online()
? "RCU used illegally from offline CPU!\n"
: !rcu_is_watching()
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 9bffedd8..28350dc 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -852,6 +852,10 @@
else
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: SUCCESS");
+
+ kfree(cxt.lwsa);
+ kfree(cxt.lrsa);
+
end:
torture_cleanup_end();
}
@@ -997,6 +1001,8 @@
GFP_KERNEL);
if (reader_tasks == NULL) {
VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
+ kfree(writer_tasks);
+ writer_tasks = NULL;
firsterr = -ENOMEM;
goto unwind;
}
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 705e06f..ad2d9e2 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -929,6 +929,20 @@
}
EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
+void __sched
+mutex_lock_io_nested(struct mutex *lock, unsigned int subclass)
+{
+ int token;
+
+ might_sleep();
+
+ token = io_schedule_prepare();
+ __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
+ subclass, NULL, _RET_IP_, NULL, 0);
+ io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_io_nested);
+
static inline int
ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
@@ -1099,6 +1113,16 @@
}
EXPORT_SYMBOL(mutex_lock_killable);
+void __sched mutex_lock_io(struct mutex *lock)
+{
+ int token;
+
+ token = io_schedule_prepare();
+ mutex_lock(lock);
+ io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_io);
+
static noinline void __sched
__mutex_lock_slowpath(struct mutex *lock)
{
diff --git a/kernel/membarrier.c b/kernel/membarrier.c
index 536c727..9f9284f 100644
--- a/kernel/membarrier.c
+++ b/kernel/membarrier.c
@@ -16,6 +16,7 @@
#include <linux/syscalls.h>
#include <linux/membarrier.h>
+#include <linux/tick.h>
/*
* Bitmask made from a "or" of all commands within enum membarrier_cmd,
@@ -51,6 +52,9 @@
*/
SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
{
+ /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
+ if (tick_nohz_full_enabled())
+ return -ENOSYS;
if (unlikely(flags))
return -EINVAL;
switch (cmd) {
diff --git a/kernel/module.c b/kernel/module.c
index 5088784c..3d8f126 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -389,16 +389,16 @@
extern const struct kernel_symbol __stop___ksymtab_gpl[];
extern const struct kernel_symbol __start___ksymtab_gpl_future[];
extern const struct kernel_symbol __stop___ksymtab_gpl_future[];
-extern const unsigned long __start___kcrctab[];
-extern const unsigned long __start___kcrctab_gpl[];
-extern const unsigned long __start___kcrctab_gpl_future[];
+extern const s32 __start___kcrctab[];
+extern const s32 __start___kcrctab_gpl[];
+extern const s32 __start___kcrctab_gpl_future[];
#ifdef CONFIG_UNUSED_SYMBOLS
extern const struct kernel_symbol __start___ksymtab_unused[];
extern const struct kernel_symbol __stop___ksymtab_unused[];
extern const struct kernel_symbol __start___ksymtab_unused_gpl[];
extern const struct kernel_symbol __stop___ksymtab_unused_gpl[];
-extern const unsigned long __start___kcrctab_unused[];
-extern const unsigned long __start___kcrctab_unused_gpl[];
+extern const s32 __start___kcrctab_unused[];
+extern const s32 __start___kcrctab_unused_gpl[];
#endif
#ifndef CONFIG_MODVERSIONS
@@ -497,7 +497,7 @@
/* Output */
struct module *owner;
- const unsigned long *crc;
+ const s32 *crc;
const struct kernel_symbol *sym;
};
@@ -563,7 +563,7 @@
* (optional) module which owns it. Needs preempt disabled or module_mutex. */
const struct kernel_symbol *find_symbol(const char *name,
struct module **owner,
- const unsigned long **crc,
+ const s32 **crc,
bool gplok,
bool warn)
{
@@ -1145,7 +1145,7 @@
for (i = 0; i < TAINT_FLAGS_COUNT; i++) {
if (taint_flags[i].module && test_bit(i, &mod->taints))
- buf[l++] = taint_flags[i].true;
+ buf[l++] = taint_flags[i].c_true;
}
return l;
@@ -1249,23 +1249,17 @@
}
#ifdef CONFIG_MODVERSIONS
-/* If the arch applies (non-zero) relocations to kernel kcrctab, unapply it. */
-static unsigned long maybe_relocated(unsigned long crc,
- const struct module *crc_owner)
+
+static u32 resolve_rel_crc(const s32 *crc)
{
-#ifdef ARCH_RELOCATES_KCRCTAB
- if (crc_owner == NULL)
- return crc - (unsigned long)reloc_start;
-#endif
- return crc;
+ return *(u32 *)((void *)crc + *crc);
}
static int check_version(Elf_Shdr *sechdrs,
unsigned int versindex,
const char *symname,
struct module *mod,
- const unsigned long *crc,
- const struct module *crc_owner)
+ const s32 *crc)
{
unsigned int i, num_versions;
struct modversion_info *versions;
@@ -1283,13 +1277,19 @@
/ sizeof(struct modversion_info);
for (i = 0; i < num_versions; i++) {
+ u32 crcval;
+
if (strcmp(versions[i].name, symname) != 0)
continue;
- if (versions[i].crc == maybe_relocated(*crc, crc_owner))
+ if (IS_ENABLED(CONFIG_MODULE_REL_CRCS))
+ crcval = resolve_rel_crc(crc);
+ else
+ crcval = *crc;
+ if (versions[i].crc == crcval)
return 1;
- pr_debug("Found checksum %lX vs module %lX\n",
- maybe_relocated(*crc, crc_owner), versions[i].crc);
+ pr_debug("Found checksum %X vs module %lX\n",
+ crcval, versions[i].crc);
goto bad_version;
}
@@ -1307,7 +1307,7 @@
unsigned int versindex,
struct module *mod)
{
- const unsigned long *crc;
+ const s32 *crc;
/*
* Since this should be found in kernel (which can't be removed), no
@@ -1321,8 +1321,7 @@
}
preempt_enable();
return check_version(sechdrs, versindex,
- VMLINUX_SYMBOL_STR(module_layout), mod, crc,
- NULL);
+ VMLINUX_SYMBOL_STR(module_layout), mod, crc);
}
/* First part is kernel version, which we ignore if module has crcs. */
@@ -1340,8 +1339,7 @@
unsigned int versindex,
const char *symname,
struct module *mod,
- const unsigned long *crc,
- const struct module *crc_owner)
+ const s32 *crc)
{
return 1;
}
@@ -1368,7 +1366,7 @@
{
struct module *owner;
const struct kernel_symbol *sym;
- const unsigned long *crc;
+ const s32 *crc;
int err;
/*
@@ -1383,8 +1381,7 @@
if (!sym)
goto unlock;
- if (!check_version(info->sechdrs, info->index.vers, name, mod, crc,
- owner)) {
+ if (!check_version(info->sechdrs, info->index.vers, name, mod, crc)) {
sym = ERR_PTR(-EINVAL);
goto getname;
}
diff --git a/kernel/panic.c b/kernel/panic.c
index c51edaa..08aa88d 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -249,7 +249,7 @@
* Delay timeout seconds before rebooting the machine.
* We can't use the "normal" timers since we just panicked.
*/
- pr_emerg("Rebooting in %d seconds..", panic_timeout);
+ pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
touch_nmi_watchdog();
@@ -355,7 +355,7 @@
for (i = 0; i < TAINT_FLAGS_COUNT; i++) {
const struct taint_flag *t = &taint_flags[i];
*s++ = test_bit(i, &tainted_mask) ?
- t->true : t->false;
+ t->c_true : t->c_false;
}
*s = 0;
} else
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index df9e8e9..eef2ce9 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -151,8 +151,12 @@
static void delayed_free_pidns(struct rcu_head *p)
{
- kmem_cache_free(pid_ns_cachep,
- container_of(p, struct pid_namespace, rcu));
+ struct pid_namespace *ns = container_of(p, struct pid_namespace, rcu);
+
+ dec_pid_namespaces(ns->ucounts);
+ put_user_ns(ns->user_ns);
+
+ kmem_cache_free(pid_ns_cachep, ns);
}
static void destroy_pid_namespace(struct pid_namespace *ns)
@@ -162,8 +166,6 @@
ns_free_inum(&ns->ns);
for (i = 0; i < PIDMAP_ENTRIES; i++)
kfree(ns->pidmap[i].page);
- dec_pid_namespaces(ns->ucounts);
- put_user_ns(ns->user_ns);
call_rcu(&ns->rcu, delayed_free_pidns);
}
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f67ceb7..15e6bae 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -46,7 +46,7 @@
const char *mem_sleep_states[PM_SUSPEND_MAX];
suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE;
-suspend_state_t mem_sleep_default = PM_SUSPEND_MAX;
+static suspend_state_t mem_sleep_default = PM_SUSPEND_MEM;
unsigned int pm_suspend_global_flags;
EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
@@ -168,7 +168,7 @@
}
if (valid_state(PM_SUSPEND_MEM)) {
mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM];
- if (mem_sleep_default >= PM_SUSPEND_MEM)
+ if (mem_sleep_default == PM_SUSPEND_MEM)
mem_sleep_current = PM_SUSPEND_MEM;
}
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 8b26964..4ba3d34 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1516,7 +1516,7 @@
{
struct console *con;
- trace_console(text, len);
+ trace_console_rcuidle(text, len);
if (!console_drivers)
return;
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 80adef7..0d6ff3e 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -136,6 +136,7 @@
#define TPS(x) tracepoint_string(x)
void rcu_early_boot_tests(void);
+void rcu_test_sync_prims(void);
/*
* This function really isn't for public consumption, but RCU is special in
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 87c5122..d81345b 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -564,10 +564,25 @@
pr_alert("%s%s per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
+ unsigned long l0, l1;
+ unsigned long u0, u1;
long c0, c1;
+ struct srcu_array *counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
- c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx];
- c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx];
+ u0 = counts->unlock_count[!idx];
+ u1 = counts->unlock_count[idx];
+
+ /*
+ * Make sure that a lock is always counted if the corresponding
+ * unlock is counted.
+ */
+ smp_rmb();
+
+ l0 = counts->lock_count[!idx];
+ l1 = counts->lock_count[idx];
+
+ c0 = l0 - u0;
+ c1 = l1 - u1;
pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
}
pr_cont("\n");
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 9b9cdd5..e773129 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -106,7 +106,7 @@
rcu_batch_init(&sp->batch_check1);
rcu_batch_init(&sp->batch_done);
INIT_DELAYED_WORK(&sp->work, process_srcu);
- sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
+ sp->per_cpu_ref = alloc_percpu(struct srcu_array);
return sp->per_cpu_ref ? 0 : -ENOMEM;
}
@@ -141,114 +141,77 @@
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/*
- * Returns approximate total of the readers' ->seq[] values for the
+ * Returns approximate total of the readers' ->lock_count[] values for the
* rank of per-CPU counters specified by idx.
*/
-static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
{
int cpu;
unsigned long sum = 0;
- unsigned long t;
for_each_possible_cpu(cpu) {
- t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
- sum += t;
+ struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+
+ sum += READ_ONCE(cpuc->lock_count[idx]);
}
return sum;
}
/*
- * Returns approximate number of readers active on the specified rank
- * of the per-CPU ->c[] counters.
+ * Returns approximate total of the readers' ->unlock_count[] values for the
+ * rank of per-CPU counters specified by idx.
*/
-static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
{
int cpu;
unsigned long sum = 0;
- unsigned long t;
for_each_possible_cpu(cpu) {
- t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
- sum += t;
+ struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+
+ sum += READ_ONCE(cpuc->unlock_count[idx]);
}
return sum;
}
/*
* Return true if the number of pre-existing readers is determined to
- * be stably zero. An example unstable zero can occur if the call
- * to srcu_readers_active_idx() misses an __srcu_read_lock() increment,
- * but due to task migration, sees the corresponding __srcu_read_unlock()
- * decrement. This can happen because srcu_readers_active_idx() takes
- * time to sum the array, and might in fact be interrupted or preempted
- * partway through the summation.
+ * be zero.
*/
static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
{
- unsigned long seq;
+ unsigned long unlocks;
- seq = srcu_readers_seq_idx(sp, idx);
+ unlocks = srcu_readers_unlock_idx(sp, idx);
/*
- * The following smp_mb() A pairs with the smp_mb() B located in
- * __srcu_read_lock(). This pairing ensures that if an
- * __srcu_read_lock() increments its counter after the summation
- * in srcu_readers_active_idx(), then the corresponding SRCU read-side
- * critical section will see any changes made prior to the start
- * of the current SRCU grace period.
+ * Make sure that a lock is always counted if the corresponding unlock
+ * is counted. Needs to be a smp_mb() as the read side may contain a
+ * read from a variable that is written to before the synchronize_srcu()
+ * in the write side. In this case smp_mb()s A and B act like the store
+ * buffering pattern.
*
- * Also, if the above call to srcu_readers_seq_idx() saw the
- * increment of ->seq[], then the call to srcu_readers_active_idx()
- * must see the increment of ->c[].
+ * This smp_mb() also pairs with smp_mb() C to prevent accesses after the
+ * synchronize_srcu() from being executed before the grace period ends.
*/
smp_mb(); /* A */
/*
- * Note that srcu_readers_active_idx() can incorrectly return
- * zero even though there is a pre-existing reader throughout.
- * To see this, suppose that task A is in a very long SRCU
- * read-side critical section that started on CPU 0, and that
- * no other reader exists, so that the sum of the counters
- * is equal to one. Then suppose that task B starts executing
- * srcu_readers_active_idx(), summing up to CPU 1, and then that
- * task C starts reading on CPU 0, so that its increment is not
- * summed, but finishes reading on CPU 2, so that its decrement
- * -is- summed. Then when task B completes its sum, it will
- * incorrectly get zero, despite the fact that task A has been
- * in its SRCU read-side critical section the whole time.
+ * If the locks are the same as the unlocks, then there must have
+ * been no readers on this index at some time in between. This does not
+ * mean that there are no more readers, as one could have read the
+ * current index but not have incremented the lock counter yet.
*
- * We therefore do a validation step should srcu_readers_active_idx()
- * return zero.
+ * Possible bug: There is no guarantee that there haven't been ULONG_MAX
+ * increments of ->lock_count[] since the unlocks were counted, meaning
+ * that this could return true even if there are still active readers.
+ * Since there are no memory barriers around srcu_flip(), the CPU is not
+ * required to increment ->completed before running
+ * srcu_readers_unlock_idx(), which means that there could be an
+ * arbitrarily large number of critical sections that execute after
+ * srcu_readers_unlock_idx() but use the old value of ->completed.
*/
- if (srcu_readers_active_idx(sp, idx) != 0)
- return false;
-
- /*
- * The remainder of this function is the validation step.
- * The following smp_mb() D pairs with the smp_mb() C in
- * __srcu_read_unlock(). If the __srcu_read_unlock() was seen
- * by srcu_readers_active_idx() above, then any destructive
- * operation performed after the grace period will happen after
- * the corresponding SRCU read-side critical section.
- *
- * Note that there can be at most NR_CPUS worth of readers using
- * the old index, which is not enough to overflow even a 32-bit
- * integer. (Yes, this does mean that systems having more than
- * a billion or so CPUs need to be 64-bit systems.) Therefore,
- * the sum of the ->seq[] counters cannot possibly overflow.
- * Therefore, the only way that the return values of the two
- * calls to srcu_readers_seq_idx() can be equal is if there were
- * no increments of the corresponding rank of ->seq[] counts
- * in the interim. But the missed-increment scenario laid out
- * above includes an increment of the ->seq[] counter by
- * the corresponding __srcu_read_lock(). Therefore, if this
- * scenario occurs, the return values from the two calls to
- * srcu_readers_seq_idx() will differ, and thus the validation
- * step below suffices.
- */
- smp_mb(); /* D */
-
- return srcu_readers_seq_idx(sp, idx) == seq;
+ return srcu_readers_lock_idx(sp, idx) == unlocks;
}
/**
@@ -266,8 +229,12 @@
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
- sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
- sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
+ struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+
+ sum += READ_ONCE(cpuc->lock_count[0]);
+ sum += READ_ONCE(cpuc->lock_count[1]);
+ sum -= READ_ONCE(cpuc->unlock_count[0]);
+ sum -= READ_ONCE(cpuc->unlock_count[1]);
}
return sum;
}
@@ -298,9 +265,8 @@
int idx;
idx = READ_ONCE(sp->completed) & 0x1;
- __this_cpu_inc(sp->per_cpu_ref->c[idx]);
+ __this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
smp_mb(); /* B */ /* Avoid leaking the critical section. */
- __this_cpu_inc(sp->per_cpu_ref->seq[idx]);
return idx;
}
EXPORT_SYMBOL_GPL(__srcu_read_lock);
@@ -314,7 +280,7 @@
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
smp_mb(); /* C */ /* Avoid leaking the critical section. */
- this_cpu_dec(sp->per_cpu_ref->c[idx]);
+ this_cpu_inc(sp->per_cpu_ref->unlock_count[idx]);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
@@ -349,12 +315,21 @@
/*
* Increment the ->completed counter so that future SRCU readers will
- * use the other rank of the ->c[] and ->seq[] arrays. This allows
+ * use the other rank of the ->(un)lock_count[] arrays. This allows
* us to wait for pre-existing readers in a starvation-free manner.
*/
static void srcu_flip(struct srcu_struct *sp)
{
- sp->completed++;
+ WRITE_ONCE(sp->completed, sp->completed + 1);
+
+ /*
+ * Ensure that if the updater misses an __srcu_read_unlock()
+ * increment, that task's next __srcu_read_lock() will see the
+ * above counter update. Note that both this memory barrier
+ * and the one in srcu_readers_active_idx_check() provide the
+ * guarantee for __srcu_read_lock().
+ */
+ smp_mb(); /* D */ /* Pairs with C. */
}
/*
@@ -392,6 +367,7 @@
head->next = NULL;
head->func = func;
spin_lock_irqsave(&sp->queue_lock, flags);
+ smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
rcu_batch_queue(&sp->batch_queue, head);
if (!sp->running) {
sp->running = true;
@@ -425,6 +401,7 @@
head->next = NULL;
head->func = wakeme_after_rcu;
spin_lock_irq(&sp->queue_lock);
+ smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
if (!sp->running) {
/* steal the processing owner */
sp->running = true;
@@ -444,8 +421,11 @@
spin_unlock_irq(&sp->queue_lock);
}
- if (!done)
+ if (!done) {
wait_for_completion(&rcu.completion);
+ smp_mb(); /* Caller's later accesses after GP. */
+ }
+
}
/**
@@ -613,7 +593,8 @@
/*
* Invoke a limited number of SRCU callbacks that have passed through
* their grace period. If there are more to do, SRCU will reschedule
- * the workqueue.
+ * the workqueue. Note that needed memory barriers have been executed
+ * in this task's context by srcu_readers_active_idx_check().
*/
static void srcu_invoke_callbacks(struct srcu_struct *sp)
{
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 1898559..fa6a48d 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -41,8 +41,6 @@
/* Forward declarations for tiny_plugin.h. */
struct rcu_ctrlblk;
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
-static void rcu_process_callbacks(struct softirq_action *unused);
static void __call_rcu(struct rcu_head *head,
rcu_callback_t func,
struct rcu_ctrlblk *rcp);
@@ -185,9 +183,6 @@
* benefits of doing might_sleep() to reduce latency.)
*
* Cool, huh? (Due to Josh Triplett.)
- *
- * But we want to make this a static inline later. The cond_resched()
- * currently makes this problematic.
*/
void synchronize_sched(void)
{
@@ -195,7 +190,6 @@
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_sched() in RCU read-side critical section");
- cond_resched();
}
EXPORT_SYMBOL_GPL(synchronize_sched);
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index 196f030..c64b827 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -60,12 +60,17 @@
/*
* During boot, we forgive RCU lockdep issues. After this function is
- * invoked, we start taking RCU lockdep issues seriously.
+ * invoked, we start taking RCU lockdep issues seriously. Note that unlike
+ * Tree RCU, Tiny RCU transitions directly from RCU_SCHEDULER_INACTIVE
+ * to RCU_SCHEDULER_RUNNING, skipping the RCU_SCHEDULER_INIT stage.
+ * The reason for this is that Tiny RCU does not need kthreads, so does
+ * not have to care about the fact that the scheduler is half-initialized
+ * at a certain phase of the boot process.
*/
void __init rcu_scheduler_starting(void)
{
WARN_ON(nr_context_switches() > 0);
- rcu_scheduler_active = 1;
+ rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
}
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 96c52e4..d80e0d2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -127,13 +127,16 @@
int sysctl_panic_on_rcu_stall __read_mostly;
/*
- * The rcu_scheduler_active variable transitions from zero to one just
- * before the first task is spawned. So when this variable is zero, RCU
- * can assume that there is but one task, allowing RCU to (for example)
+ * The rcu_scheduler_active variable is initialized to the value
+ * RCU_SCHEDULER_INACTIVE and transitions RCU_SCHEDULER_INIT just before the
+ * first task is spawned. So when this variable is RCU_SCHEDULER_INACTIVE,
+ * RCU can assume that there is but one task, allowing RCU to (for example)
* optimize synchronize_rcu() to a simple barrier(). When this variable
- * is one, RCU must actually do all the hard work required to detect real
- * grace periods. This variable is also used to suppress boot-time false
- * positives from lockdep-RCU error checking.
+ * is RCU_SCHEDULER_INIT, RCU must actually do all the hard work required
+ * to detect real grace periods. This variable is also used to suppress
+ * boot-time false positives from lockdep-RCU error checking. Finally, it
+ * transitions from RCU_SCHEDULER_INIT to RCU_SCHEDULER_RUNNING after RCU
+ * is fully initialized, including all of its kthreads having been spawned.
*/
int rcu_scheduler_active __read_mostly;
EXPORT_SYMBOL_GPL(rcu_scheduler_active);
@@ -278,6 +281,116 @@
#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
};
+/*
+ * Record entry into an extended quiescent state. This is only to be
+ * called when not already in an extended quiescent state.
+ */
+static void rcu_dynticks_eqs_enter(void)
+{
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ int special;
+
+ /*
+ * CPUs seeing atomic_inc_return() must see prior RCU read-side
+ * critical sections, and we also must force ordering with the
+ * next idle sojourn.
+ */
+ special = atomic_inc_return(&rdtp->dynticks);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && special & 0x1);
+}
+
+/*
+ * Record exit from an extended quiescent state. This is only to be
+ * called from an extended quiescent state.
+ */
+static void rcu_dynticks_eqs_exit(void)
+{
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ int special;
+
+ /*
+ * CPUs seeing atomic_inc_return() must see prior idle sojourns,
+ * and we also must force ordering with the next RCU read-side
+ * critical section.
+ */
+ special = atomic_inc_return(&rdtp->dynticks);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(special & 0x1));
+}
+
+/*
+ * Reset the current CPU's ->dynticks counter to indicate that the
+ * newly onlined CPU is no longer in an extended quiescent state.
+ * This will either leave the counter unchanged, or increment it
+ * to the next non-quiescent value.
+ *
+ * The non-atomic test/increment sequence works because the upper bits
+ * of the ->dynticks counter are manipulated only by the corresponding CPU,
+ * or when the corresponding CPU is offline.
+ */
+static void rcu_dynticks_eqs_online(void)
+{
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+
+ if (atomic_read(&rdtp->dynticks) & 0x1)
+ return;
+ atomic_add(0x1, &rdtp->dynticks);
+}
+
+/*
+ * Is the current CPU in an extended quiescent state?
+ *
+ * No ordering, as we are sampling CPU-local information.
+ */
+bool rcu_dynticks_curr_cpu_in_eqs(void)
+{
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+
+ return !(atomic_read(&rdtp->dynticks) & 0x1);
+}
+
+/*
+ * Snapshot the ->dynticks counter with full ordering so as to allow
+ * stable comparison of this counter with past and future snapshots.
+ */
+int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
+{
+ int snap = atomic_add_return(0, &rdtp->dynticks);
+
+ return snap;
+}
+
+/*
+ * Return true if the snapshot returned from rcu_dynticks_snap()
+ * indicates that RCU is in an extended quiescent state.
+ */
+static bool rcu_dynticks_in_eqs(int snap)
+{
+ return !(snap & 0x1);
+}
+
+/*
+ * Return true if the CPU corresponding to the specified rcu_dynticks
+ * structure has spent some time in an extended quiescent state since
+ * rcu_dynticks_snap() returned the specified snapshot.
+ */
+static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap)
+{
+ return snap != rcu_dynticks_snap(rdtp);
+}
+
+/*
+ * Do a double-increment of the ->dynticks counter to emulate a
+ * momentary idle-CPU quiescent state.
+ */
+static void rcu_dynticks_momentary_idle(void)
+{
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ int special = atomic_add_return(2, &rdtp->dynticks);
+
+ /* It is illegal to call this from idle state. */
+ WARN_ON_ONCE(!(special & 0x1));
+}
+
DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
@@ -297,7 +410,6 @@
static void rcu_momentary_dyntick_idle(void)
{
struct rcu_data *rdp;
- struct rcu_dynticks *rdtp;
int resched_mask;
struct rcu_state *rsp;
@@ -324,10 +436,7 @@
* quiescent state, with no need for this CPU to do anything
* further.
*/
- rdtp = this_cpu_ptr(&rcu_dynticks);
- smp_mb__before_atomic(); /* Earlier stuff before QS. */
- atomic_add(2, &rdtp->dynticks); /* QS. */
- smp_mb__after_atomic(); /* Later stuff after QS. */
+ rcu_dynticks_momentary_idle();
break;
}
}
@@ -608,7 +717,7 @@
cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
{
return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
- rdp->nxttail[RCU_DONE_TAIL] != NULL;
+ rdp->nxttail[RCU_NEXT_TAIL] != NULL;
}
/*
@@ -670,7 +779,7 @@
{
struct rcu_state *rsp;
struct rcu_data *rdp;
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -689,12 +798,7 @@
do_nocb_deferred_wakeup(rdp);
}
rcu_prepare_for_idle();
- /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
- smp_mb__before_atomic(); /* See above. */
- atomic_inc(&rdtp->dynticks);
- smp_mb__after_atomic(); /* Force ordering with next sojourn. */
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
- atomic_read(&rdtp->dynticks) & 0x1);
+ rcu_dynticks_eqs_enter();
rcu_dynticks_task_enter();
/*
@@ -823,15 +927,10 @@
*/
static void rcu_eqs_exit_common(long long oldval, int user)
{
- struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
rcu_dynticks_task_exit();
- smp_mb__before_atomic(); /* Force ordering w/previous sojourn. */
- atomic_inc(&rdtp->dynticks);
- /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
- smp_mb__after_atomic(); /* See above. */
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
- !(atomic_read(&rdtp->dynticks) & 0x1));
+ rcu_dynticks_eqs_exit();
rcu_cleanup_after_idle();
trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -977,12 +1076,8 @@
* to be in the outermost NMI handler that interrupted an RCU-idle
* period (observation due to Andy Lutomirski).
*/
- if (!(atomic_read(&rdtp->dynticks) & 0x1)) {
- smp_mb__before_atomic(); /* Force delay from prior write. */
- atomic_inc(&rdtp->dynticks);
- /* atomic_inc() before later RCU read-side crit sects */
- smp_mb__after_atomic(); /* See above. */
- WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+ if (rcu_dynticks_curr_cpu_in_eqs()) {
+ rcu_dynticks_eqs_exit();
incby = 1;
}
rdtp->dynticks_nmi_nesting += incby;
@@ -1007,7 +1102,7 @@
* to us!)
*/
WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0);
- WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+ WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs());
/*
* If the nesting level is not 1, the CPU wasn't RCU-idle, so
@@ -1020,11 +1115,7 @@
/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
rdtp->dynticks_nmi_nesting = 0;
- /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
- smp_mb__before_atomic(); /* See above. */
- atomic_inc(&rdtp->dynticks);
- smp_mb__after_atomic(); /* Force delay to next write. */
- WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+ rcu_dynticks_eqs_enter();
}
/**
@@ -1037,7 +1128,7 @@
*/
bool notrace __rcu_is_watching(void)
{
- return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1;
+ return !rcu_dynticks_curr_cpu_in_eqs();
}
/**
@@ -1120,9 +1211,9 @@
static int dyntick_save_progress_counter(struct rcu_data *rdp,
bool *isidle, unsigned long *maxj)
{
- rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+ rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
rcu_sysidle_check_cpu(rdp, isidle, maxj);
- if ((rdp->dynticks_snap & 0x1) == 0) {
+ if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
rdp->mynode->gpnum))
@@ -1141,12 +1232,10 @@
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
bool *isidle, unsigned long *maxj)
{
- unsigned int curr;
+ unsigned long jtsq;
int *rcrmp;
- unsigned int snap;
-
- curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
- snap = (unsigned int)rdp->dynticks_snap;
+ unsigned long rjtsc;
+ struct rcu_node *rnp;
/*
* If the CPU passed through or entered a dynticks idle phase with
@@ -1156,27 +1245,39 @@
* read-side critical section that started before the beginning
* of the current RCU grace period.
*/
- if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) {
+ if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
rdp->dynticks_fqs++;
return 1;
}
+ /* Compute and saturate jiffies_till_sched_qs. */
+ jtsq = jiffies_till_sched_qs;
+ rjtsc = rcu_jiffies_till_stall_check();
+ if (jtsq > rjtsc / 2) {
+ WRITE_ONCE(jiffies_till_sched_qs, rjtsc);
+ jtsq = rjtsc / 2;
+ } else if (jtsq < 1) {
+ WRITE_ONCE(jiffies_till_sched_qs, 1);
+ jtsq = 1;
+ }
+
/*
- * Check for the CPU being offline, but only if the grace period
- * is old enough. We don't need to worry about the CPU changing
- * state: If we see it offline even once, it has been through a
- * quiescent state.
- *
- * The reason for insisting that the grace period be at least
- * one jiffy old is that CPUs that are not quite online and that
- * have just gone offline can still execute RCU read-side critical
- * sections.
+ * Has this CPU encountered a cond_resched_rcu_qs() since the
+ * beginning of the grace period? For this to be the case,
+ * the CPU has to have noticed the current grace period. This
+ * might not be the case for nohz_full CPUs looping in the kernel.
*/
- if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies))
- return 0; /* Grace period is not old enough. */
- barrier();
- if (cpu_is_offline(rdp->cpu)) {
+ rnp = rdp->mynode;
+ if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
+ READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_qs_ctr, rdp->cpu) &&
+ READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
+ trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
+ return 1;
+ }
+
+ /* Check for the CPU being offline. */
+ if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) {
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl"));
rdp->offline_fqs++;
return 1;
@@ -1204,9 +1305,8 @@
* warning delay.
*/
rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
- if (ULONG_CMP_GE(jiffies,
- rdp->rsp->gp_start + jiffies_till_sched_qs) ||
- ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
+ if (time_after(jiffies, rdp->rsp->gp_start + jtsq) ||
+ time_after(jiffies, rdp->rsp->jiffies_resched)) {
if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
WRITE_ONCE(rdp->cond_resched_completed,
READ_ONCE(rdp->mynode->completed));
@@ -1217,11 +1317,12 @@
rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
}
- /* And if it has been a really long time, kick the CPU as well. */
- if (ULONG_CMP_GE(jiffies,
- rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) ||
- ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs))
- resched_cpu(rdp->cpu); /* Force CPU into scheduler. */
+ /*
+ * If more than halfway to RCU CPU stall-warning time, do
+ * a resched_cpu() to try to loosen things up a bit.
+ */
+ if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2)
+ resched_cpu(rdp->cpu);
return 0;
}
@@ -1274,7 +1375,10 @@
}
/*
- * Dump stacks of all tasks running on stalled CPUs.
+ * Dump stacks of all tasks running on stalled CPUs. First try using
+ * NMIs, but fall back to manual remote stack tracing on architectures
+ * that don't support NMI-based stack dumps. The NMI-triggered stack
+ * traces are more accurate because they are printed by the target CPU.
*/
static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
{
@@ -1284,11 +1388,10 @@
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if (rnp->qsmask != 0) {
- for_each_leaf_node_possible_cpu(rnp, cpu)
- if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+ for_each_leaf_node_possible_cpu(rnp, cpu)
+ if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+ if (!trigger_single_cpu_backtrace(cpu))
dump_cpu_task(cpu);
- }
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
}
@@ -1376,6 +1479,9 @@
(long)rsp->gpnum, (long)rsp->completed, totqlen);
if (ndetected) {
rcu_dump_cpu_stacks(rsp);
+
+ /* Complain about tasks blocking the grace period. */
+ rcu_print_detail_task_stall(rsp);
} else {
if (READ_ONCE(rsp->gpnum) != gpnum ||
READ_ONCE(rsp->completed) == gpnum) {
@@ -1392,9 +1498,6 @@
}
}
- /* Complain about tasks blocking the grace period. */
- rcu_print_detail_task_stall(rsp);
-
rcu_check_gp_kthread_starvation(rsp);
panic_on_rcu_stall();
@@ -2464,10 +2567,8 @@
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if ((rdp->cpu_no_qs.b.norm &&
- rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
- rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
- rdp->gpwrap) {
+ if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum ||
+ rnp->completed == rnp->gpnum || rdp->gpwrap) {
/*
* The grace period in which this quiescent state was
@@ -2522,8 +2623,7 @@
* Was there a quiescent state since the beginning of the grace
* period? If no, then exit and wait for the next call.
*/
- if (rdp->cpu_no_qs.b.norm &&
- rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr))
+ if (rdp->cpu_no_qs.b.norm)
return;
/*
@@ -3477,9 +3577,7 @@
rdp->core_needs_qs && rdp->cpu_no_qs.b.norm &&
rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
rdp->n_rp_core_needs_qs++;
- } else if (rdp->core_needs_qs &&
- (!rdp->cpu_no_qs.b.norm ||
- rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) {
+ } else if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm) {
rdp->n_rp_report_qs++;
return 1;
}
@@ -3745,7 +3843,7 @@
rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
- WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
+ WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
rdp->cpu = cpu;
rdp->rsp = rsp;
rcu_boot_init_nocb_percpu_data(rdp);
@@ -3762,7 +3860,6 @@
rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
{
unsigned long flags;
- unsigned long mask;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rcu_get_root(rsp);
@@ -3775,8 +3872,7 @@
init_callback_list(rdp); /* Re-enable callbacks on this CPU. */
rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
rcu_sysidle_init_percpu_data(rdp->dynticks);
- atomic_set(&rdp->dynticks->dynticks,
- (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
+ rcu_dynticks_eqs_online();
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
/*
@@ -3785,7 +3881,6 @@
* of the next grace period.
*/
rnp = rdp->mynode;
- mask = rdp->grpmask;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
if (!rdp->beenonline)
WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1);
@@ -3869,7 +3964,7 @@
struct rcu_state *rsp;
for_each_rcu_flavor(rsp) {
- rdp = this_cpu_ptr(rsp->rda);
+ rdp = per_cpu_ptr(rsp->rda, cpu);
rnp = rdp->mynode;
mask = rdp->grpmask;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -3980,18 +4075,22 @@
early_initcall(rcu_spawn_gp_kthread);
/*
- * This function is invoked towards the end of the scheduler's initialization
- * process. Before this is called, the idle task might contain
- * RCU read-side critical sections (during which time, this idle
- * task is booting the system). After this function is called, the
- * idle tasks are prohibited from containing RCU read-side critical
- * sections. This function also enables RCU lockdep checking.
+ * This function is invoked towards the end of the scheduler's
+ * initialization process. Before this is called, the idle task might
+ * contain synchronous grace-period primitives (during which time, this idle
+ * task is booting the system, and such primitives are no-ops). After this
+ * function is called, any synchronous grace-period primitives are run as
+ * expedited, with the requesting task driving the grace period forward.
+ * A later core_initcall() rcu_exp_runtime_mode() will switch to full
+ * runtime RCU functionality.
*/
void rcu_scheduler_starting(void)
{
WARN_ON(num_online_cpus() != 1);
WARN_ON(nr_context_switches() > 0);
- rcu_scheduler_active = 1;
+ rcu_test_sync_prims();
+ rcu_scheduler_active = RCU_SCHEDULER_INIT;
+ rcu_test_sync_prims();
}
/*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index fe98dd2..b60f2b6 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -521,7 +521,6 @@
struct mutex exp_mutex; /* Serialize expedited GP. */
struct mutex exp_wake_mutex; /* Serialize wakeup. */
unsigned long expedited_sequence; /* Take a ticket. */
- atomic_long_t expedited_normal; /* # fallbacks to normal. */
atomic_t expedited_need_qs; /* # CPUs left to check in. */
struct swait_queue_head expedited_wq; /* Wait for check-ins. */
int ncpus_snap; /* # CPUs seen last time. */
@@ -595,6 +594,8 @@
extern struct rcu_state rcu_preempt_state;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
+int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
+
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
@@ -688,18 +689,6 @@
#endif /* #ifdef CONFIG_RCU_TRACE */
/*
- * Place this after a lock-acquisition primitive to guarantee that
- * an UNLOCK+LOCK pair act as a full barrier. This guarantee applies
- * if the UNLOCK and LOCK are executed by the same CPU or if the
- * UNLOCK and LOCK operate on the same lock variable.
- */
-#ifdef CONFIG_PPC
-#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */
-#else /* #ifdef CONFIG_PPC */
-#define smp_mb__after_unlock_lock() do { } while (0)
-#endif /* #else #ifdef CONFIG_PPC */
-
-/*
* Wrappers for the rcu_node::lock acquire and release.
*
* Because the rcu_nodes form a tree, the tree traversal locking will observe
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d3053e9..a7b639c 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -20,16 +20,26 @@
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
-/* Wrapper functions for expedited grace periods. */
+/*
+ * Record the start of an expedited grace period.
+ */
static void rcu_exp_gp_seq_start(struct rcu_state *rsp)
{
rcu_seq_start(&rsp->expedited_sequence);
}
+
+/*
+ * Record the end of an expedited grace period.
+ */
static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
{
rcu_seq_end(&rsp->expedited_sequence);
smp_mb(); /* Ensure that consecutive grace periods serialize. */
}
+
+/*
+ * Take a snapshot of the expedited-grace-period counter.
+ */
static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
{
unsigned long s;
@@ -39,6 +49,12 @@
trace_rcu_exp_grace_period(rsp->name, s, TPS("snap"));
return s;
}
+
+/*
+ * Given a counter snapshot from rcu_exp_gp_seq_snap(), return true
+ * if a full expedited grace period has elapsed since that snapshot
+ * was taken.
+ */
static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
{
return rcu_seq_done(&rsp->expedited_sequence, s);
@@ -356,12 +372,11 @@
mask_ofl_test = 0;
for_each_leaf_node_possible_cpu(rnp, cpu) {
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
- struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
rdp->exp_dynticks_snap =
- atomic_add_return(0, &rdtp->dynticks);
+ rcu_dynticks_snap(rdp->dynticks);
if (raw_smp_processor_id() == cpu ||
- !(rdp->exp_dynticks_snap & 0x1) ||
+ rcu_dynticks_in_eqs(rdp->exp_dynticks_snap) ||
!(rnp->qsmaskinitnext & rdp->grpmask))
mask_ofl_test |= rdp->grpmask;
}
@@ -380,13 +395,12 @@
for_each_leaf_node_possible_cpu(rnp, cpu) {
unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
- struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
if (!(mask_ofl_ipi & mask))
continue;
retry_ipi:
- if (atomic_add_return(0, &rdtp->dynticks) !=
- rdp->exp_dynticks_snap) {
+ if (rcu_dynticks_in_eqs_since(rdp->dynticks,
+ rdp->exp_dynticks_snap)) {
mask_ofl_test |= mask;
continue;
}
@@ -532,18 +546,28 @@
};
/*
+ * Common code to drive an expedited grace period forward, used by
+ * workqueues and mid-boot-time tasks.
+ */
+static void rcu_exp_sel_wait_wake(struct rcu_state *rsp,
+ smp_call_func_t func, unsigned long s)
+{
+ /* Initialize the rcu_node tree in preparation for the wait. */
+ sync_rcu_exp_select_cpus(rsp, func);
+
+ /* Wait and clean up, including waking everyone. */
+ rcu_exp_wait_wake(rsp, s);
+}
+
+/*
* Work-queue handler to drive an expedited grace period forward.
*/
static void wait_rcu_exp_gp(struct work_struct *wp)
{
struct rcu_exp_work *rewp;
- /* Initialize the rcu_node tree in preparation for the wait. */
rewp = container_of(wp, struct rcu_exp_work, rew_work);
- sync_rcu_exp_select_cpus(rewp->rew_rsp, rewp->rew_func);
-
- /* Wait and clean up, including waking everyone. */
- rcu_exp_wait_wake(rewp->rew_rsp, rewp->rew_s);
+ rcu_exp_sel_wait_wake(rewp->rew_rsp, rewp->rew_func, rewp->rew_s);
}
/*
@@ -569,12 +593,18 @@
if (exp_funnel_lock(rsp, s))
return; /* Someone else did our work for us. */
- /* Marshall arguments and schedule the expedited grace period. */
- rew.rew_func = func;
- rew.rew_rsp = rsp;
- rew.rew_s = s;
- INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
- schedule_work(&rew.rew_work);
+ /* Ensure that load happens before action based on it. */
+ if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
+ /* Direct call during scheduler init and early_initcalls(). */
+ rcu_exp_sel_wait_wake(rsp, func, s);
+ } else {
+ /* Marshall arguments & schedule the expedited grace period. */
+ rew.rew_func = func;
+ rew.rew_rsp = rsp;
+ rew.rew_s = s;
+ INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
+ schedule_work(&rew.rew_work);
+ }
/* Wait for expedited grace period to complete. */
rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
@@ -607,6 +637,11 @@
{
struct rcu_state *rsp = &rcu_sched_state;
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+ lock_is_held(&rcu_lock_map) ||
+ lock_is_held(&rcu_sched_lock_map),
+ "Illegal synchronize_sched_expedited() in RCU read-side critical section");
+
/* If only one CPU, this is automatically a grace period. */
if (rcu_blocking_is_gp())
return;
@@ -676,6 +711,13 @@
{
struct rcu_state *rsp = rcu_state_p;
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+ lock_is_held(&rcu_lock_map) ||
+ lock_is_held(&rcu_sched_lock_map),
+ "Illegal synchronize_rcu_expedited() in RCU read-side critical section");
+
+ if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
+ return;
_synchronize_rcu_expedited(rsp, sync_rcu_exp_handler);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
@@ -693,3 +735,15 @@
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
+/*
+ * Switch to run-time mode once Tree RCU has fully initialized.
+ */
+static int __init rcu_exp_runtime_mode(void)
+{
+ rcu_test_sync_prims();
+ rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+ rcu_test_sync_prims();
+ return 0;
+}
+core_initcall(rcu_exp_runtime_mode);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 85c5a88..a240f33 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -670,7 +670,7 @@
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu() in RCU read-side critical section");
- if (!rcu_scheduler_active)
+ if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return;
if (rcu_gp_is_expedited())
synchronize_rcu_expedited();
@@ -1643,7 +1643,7 @@
"o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
"N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
ticks_value, ticks_title,
- atomic_read(&rdtp->dynticks) & 0xfff,
+ rcu_dynticks_snap(rdtp) & 0xfff,
rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
@@ -2366,8 +2366,9 @@
}
/*
- * Each pass through this loop sets up one rcu_data structure and
- * spawns one rcu_nocb_kthread().
+ * Each pass through this loop sets up one rcu_data structure.
+ * Should the corresponding CPU come online in the future, then
+ * we will spawn the needed set of rcu_nocb_kthread() kthreads.
*/
for_each_cpu(cpu, rcu_nocb_mask) {
rdp = per_cpu_ptr(rsp->rda, cpu);
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index b1f2897..8751a74 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -124,7 +124,7 @@
rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
rdp->core_needs_qs);
seq_printf(m, " dt=%d/%llx/%d df=%lu",
- atomic_read(&rdp->dynticks->dynticks),
+ rcu_dynticks_snap(rdp->dynticks),
rdp->dynticks->dynticks_nesting,
rdp->dynticks->dynticks_nmi_nesting,
rdp->dynticks_fqs);
@@ -194,9 +194,8 @@
s2 += atomic_long_read(&rdp->exp_workdone2);
s3 += atomic_long_read(&rdp->exp_workdone3);
}
- seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n",
+ seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu enq=%d sc=%lu\n",
rsp->expedited_sequence, s0, s1, s2, s3,
- atomic_long_read(&rsp->expedited_normal),
atomic_read(&rsp->expedited_need_qs),
rsp->expedited_sequence / 2);
return 0;
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index f19271d..9e03db9 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -121,27 +121,30 @@
* Should expedited grace-period primitives always fall back to their
* non-expedited counterparts? Intended for use within RCU. Note
* that if the user specifies both rcu_expedited and rcu_normal, then
- * rcu_normal wins.
+ * rcu_normal wins. (Except during the time period during boot from
+ * when the first task is spawned until the rcu_exp_runtime_mode()
+ * core_initcall() is invoked, at which point everything is expedited.)
*/
bool rcu_gp_is_normal(void)
{
- return READ_ONCE(rcu_normal);
+ return READ_ONCE(rcu_normal) &&
+ rcu_scheduler_active != RCU_SCHEDULER_INIT;
}
EXPORT_SYMBOL_GPL(rcu_gp_is_normal);
-static atomic_t rcu_expedited_nesting =
- ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0);
+static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1);
/*
* Should normal grace-period primitives be expedited? Intended for
* use within RCU. Note that this function takes the rcu_expedited
- * sysfs/boot variable into account as well as the rcu_expedite_gp()
- * nesting. So looping on rcu_unexpedite_gp() until rcu_gp_is_expedited()
- * returns false is a -really- bad idea.
+ * sysfs/boot variable and rcu_scheduler_active into account as well
+ * as the rcu_expedite_gp() nesting. So looping on rcu_unexpedite_gp()
+ * until rcu_gp_is_expedited() returns false is a -really- bad idea.
*/
bool rcu_gp_is_expedited(void)
{
- return rcu_expedited || atomic_read(&rcu_expedited_nesting);
+ return rcu_expedited || atomic_read(&rcu_expedited_nesting) ||
+ rcu_scheduler_active == RCU_SCHEDULER_INIT;
}
EXPORT_SYMBOL_GPL(rcu_gp_is_expedited);
@@ -178,8 +181,7 @@
*/
void rcu_end_inkernel_boot(void)
{
- if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT))
- rcu_unexpedite_gp();
+ rcu_unexpedite_gp();
if (rcu_normal_after_boot)
WRITE_ONCE(rcu_normal, 1);
}
@@ -257,7 +259,7 @@
int notrace debug_lockdep_rcu_enabled(void)
{
- return rcu_scheduler_active && debug_locks &&
+ return rcu_scheduler_active != RCU_SCHEDULER_INACTIVE && debug_locks &&
current->lockdep_recursion == 0;
}
EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
@@ -591,7 +593,7 @@
void synchronize_rcu_tasks(void)
{
/* Complain if the scheduler has not started. */
- RCU_LOCKDEP_WARN(!rcu_scheduler_active,
+ RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
"synchronize_rcu_tasks called too soon");
/* Wait for the grace period. */
@@ -813,6 +815,23 @@
#endif /* #ifdef CONFIG_TASKS_RCU */
+/*
+ * Test each non-SRCU synchronous grace-period wait API. This is
+ * useful just after a change in mode for these primitives, and
+ * during early boot.
+ */
+void rcu_test_sync_prims(void)
+{
+ if (!IS_ENABLED(CONFIG_PROVE_RCU))
+ return;
+ synchronize_rcu();
+ synchronize_rcu_bh();
+ synchronize_sched();
+ synchronize_rcu_expedited();
+ synchronize_rcu_bh_expedited();
+ synchronize_sched_expedited();
+}
+
#ifdef CONFIG_PROVE_RCU
/*
@@ -865,6 +884,7 @@
early_boot_test_call_rcu_bh();
if (rcu_self_test_sched)
early_boot_test_call_rcu_sched();
+ rcu_test_sync_prims();
}
static int rcu_verify_early_boot_tests(void)
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 5e59b83..89ab675 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -18,8 +18,8 @@
obj-y += core.o loadavg.o clock.o cputime.o
obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
obj-y += wait.o swait.o completion.o idle.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
-obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o
+obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/autogroup.c
similarity index 100%
rename from kernel/sched/auto_group.c
rename to kernel/sched/autogroup.c
diff --git a/kernel/sched/auto_group.h b/kernel/sched/autogroup.h
similarity index 100%
rename from kernel/sched/auto_group.h
rename to kernel/sched/autogroup.h
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index e85a725..ad64efe 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -77,57 +77,27 @@
__read_mostly int sched_clock_running;
+void sched_clock_init(void)
+{
+ sched_clock_running = 1;
+}
+
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
-static int __sched_clock_stable_early;
+/*
+ * We must start with !__sched_clock_stable because the unstable -> stable
+ * transition is accurate, while the stable -> unstable transition is not.
+ *
+ * Similarly we start with __sched_clock_stable_early, thereby assuming we
+ * will become stable, such that there's only a single 1 -> 0 transition.
+ */
+static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
+static int __sched_clock_stable_early = 1;
-int sched_clock_stable(void)
-{
- return static_key_false(&__sched_clock_stable);
-}
-
-static void __set_sched_clock_stable(void)
-{
- if (!sched_clock_stable())
- static_key_slow_inc(&__sched_clock_stable);
-
- tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
-}
-
-void set_sched_clock_stable(void)
-{
- __sched_clock_stable_early = 1;
-
- smp_mb(); /* matches sched_clock_init() */
-
- if (!sched_clock_running)
- return;
-
- __set_sched_clock_stable();
-}
-
-static void __clear_sched_clock_stable(struct work_struct *work)
-{
- /* XXX worry about clock continuity */
- if (sched_clock_stable())
- static_key_slow_dec(&__sched_clock_stable);
-
- tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
-}
-
-static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
-
-void clear_sched_clock_stable(void)
-{
- __sched_clock_stable_early = 0;
-
- smp_mb(); /* matches sched_clock_init() */
-
- if (!sched_clock_running)
- return;
-
- schedule_work(&sched_clock_work);
-}
+/*
+ * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset
+ */
+static __read_mostly u64 raw_offset;
+static __read_mostly u64 gtod_offset;
struct sched_clock_data {
u64 tick_raw;
@@ -147,21 +117,66 @@
return &per_cpu(sched_clock_data, cpu);
}
-void sched_clock_init(void)
+int sched_clock_stable(void)
{
- u64 ktime_now = ktime_to_ns(ktime_get());
- int cpu;
+ return static_branch_likely(&__sched_clock_stable);
+}
- for_each_possible_cpu(cpu) {
- struct sched_clock_data *scd = cpu_sdc(cpu);
+static void __set_sched_clock_stable(void)
+{
+ struct sched_clock_data *scd = this_scd();
- scd->tick_raw = 0;
- scd->tick_gtod = ktime_now;
- scd->clock = ktime_now;
- }
+ /*
+ * Attempt to make the (initial) unstable->stable transition continuous.
+ */
+ raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw);
- sched_clock_running = 1;
+ printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
+ scd->tick_gtod, gtod_offset,
+ scd->tick_raw, raw_offset);
+ static_branch_enable(&__sched_clock_stable);
+ tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
+}
+
+static void __clear_sched_clock_stable(struct work_struct *work)
+{
+ struct sched_clock_data *scd = this_scd();
+
+ /*
+ * Attempt to make the stable->unstable transition continuous.
+ *
+ * Trouble is, this is typically called from the TSC watchdog
+ * timer, which is late per definition. This means the tick
+ * values can already be screwy.
+ *
+ * Still do what we can.
+ */
+ gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod);
+
+ printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
+ scd->tick_gtod, gtod_offset,
+ scd->tick_raw, raw_offset);
+
+ static_branch_disable(&__sched_clock_stable);
+ tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
+}
+
+static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+
+void clear_sched_clock_stable(void)
+{
+ __sched_clock_stable_early = 0;
+
+ smp_mb(); /* matches sched_clock_init_late() */
+
+ if (sched_clock_running == 2)
+ schedule_work(&sched_clock_work);
+}
+
+void sched_clock_init_late(void)
+{
+ sched_clock_running = 2;
/*
* Ensure that it is impossible to not do a static_key update.
*
@@ -173,8 +188,6 @@
if (__sched_clock_stable_early)
__set_sched_clock_stable();
- else
- __clear_sched_clock_stable(NULL);
}
/*
@@ -216,7 +229,7 @@
* scd->tick_gtod + TICK_NSEC);
*/
- clock = scd->tick_gtod + delta;
+ clock = scd->tick_gtod + gtod_offset + delta;
min_clock = wrap_max(scd->tick_gtod, old_clock);
max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
@@ -302,7 +315,7 @@
u64 clock;
if (sched_clock_stable())
- return sched_clock();
+ return sched_clock() + raw_offset;
if (unlikely(!sched_clock_running))
return 0ull;
@@ -323,23 +336,22 @@
void sched_clock_tick(void)
{
struct sched_clock_data *scd;
- u64 now, now_gtod;
-
- if (sched_clock_stable())
- return;
-
- if (unlikely(!sched_clock_running))
- return;
WARN_ON_ONCE(!irqs_disabled());
+ /*
+ * Update these values even if sched_clock_stable(), because it can
+ * become unstable at any point in time at which point we need some
+ * values to fall back on.
+ *
+ * XXX arguably we can skip this if we expose tsc_clocksource_reliable
+ */
scd = this_scd();
- now_gtod = ktime_to_ns(ktime_get());
- now = sched_clock();
+ scd->tick_raw = sched_clock();
+ scd->tick_gtod = ktime_get_ns();
- scd->tick_raw = now;
- scd->tick_gtod = now_gtod;
- sched_clock_local(scd);
+ if (!sched_clock_stable() && likely(sched_clock_running))
+ sched_clock_local(scd);
}
/*
@@ -366,11 +378,6 @@
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
-void sched_clock_init(void)
-{
- sched_clock_running = 1;
-}
-
u64 sched_clock_cpu(int cpu)
{
if (unlikely(!sched_clock_running))
@@ -378,6 +385,7 @@
return sched_clock();
}
+
#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
/*
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 8d0f35d..f063a25 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -31,7 +31,8 @@
unsigned long flags;
spin_lock_irqsave(&x->wait.lock, flags);
- x->done++;
+ if (x->done != UINT_MAX)
+ x->done++;
__wake_up_locked(&x->wait, TASK_NORMAL, 1);
spin_unlock_irqrestore(&x->wait.lock, flags);
}
@@ -51,7 +52,7 @@
unsigned long flags;
spin_lock_irqsave(&x->wait.lock, flags);
- x->done += UINT_MAX/2;
+ x->done = UINT_MAX;
__wake_up_locked(&x->wait, TASK_NORMAL, 0);
spin_unlock_irqrestore(&x->wait.lock, flags);
}
@@ -79,7 +80,8 @@
if (!x->done)
return timeout;
}
- x->done--;
+ if (x->done != UINT_MAX)
+ x->done--;
return timeout ?: 1;
}
@@ -280,7 +282,7 @@
spin_lock_irqsave(&x->wait.lock, flags);
if (!x->done)
ret = 0;
- else
+ else if (x->done != UINT_MAX)
x->done--;
spin_unlock_irqrestore(&x->wait.lock, flags);
return ret;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c56fb57..34e2291 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1,88 +1,28 @@
/*
* kernel/sched/core.c
*
- * Kernel scheduler and related syscalls
+ * Core kernel scheduler code and related syscalls
*
* Copyright (C) 1991-2002 Linus Torvalds
- *
- * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and
- * make semaphores SMP safe
- * 1998-11-19 Implemented schedule_timeout() and related stuff
- * by Andrea Arcangeli
- * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar:
- * hybrid priority-list and round-robin design with
- * an array-switch method of distributing timeslices
- * and per-CPU runqueues. Cleanups and useful suggestions
- * by Davide Libenzi, preemptible kernel bits by Robert Love.
- * 2003-09-03 Interactivity tuning by Con Kolivas.
- * 2004-04-02 Scheduler domains code by Nick Piggin
- * 2007-04-15 Work begun on replacing all interactivity tuning with a
- * fair scheduling design by Con Kolivas.
- * 2007-05-05 Load balancing (smp-nice) and other improvements
- * by Peter Williams
- * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith
- * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri
- * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins,
- * Thomas Gleixner, Mike Kravetz
*/
-
-#include <linux/kasan.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/nmi.h>
-#include <linux/init.h>
-#include <linux/uaccess.h>
-#include <linux/highmem.h>
-#include <linux/mmu_context.h>
-#include <linux/interrupt.h>
-#include <linux/capability.h>
-#include <linux/completion.h>
-#include <linux/kernel_stat.h>
-#include <linux/debug_locks.h>
-#include <linux/perf_event.h>
-#include <linux/security.h>
-#include <linux/notifier.h>
-#include <linux/profile.h>
-#include <linux/freezer.h>
-#include <linux/vmalloc.h>
-#include <linux/blkdev.h>
-#include <linux/delay.h>
-#include <linux/pid_namespace.h>
-#include <linux/smp.h>
-#include <linux/threads.h>
-#include <linux/timer.h>
-#include <linux/rcupdate.h>
-#include <linux/cpu.h>
+#include <linux/sched.h>
#include <linux/cpuset.h>
-#include <linux/percpu.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/sysctl.h>
-#include <linux/syscalls.h>
-#include <linux/times.h>
-#include <linux/tsacct_kern.h>
-#include <linux/kprobes.h>
#include <linux/delayacct.h>
-#include <linux/unistd.h>
-#include <linux/pagemap.h>
-#include <linux/hrtimer.h>
-#include <linux/tick.h>
-#include <linux/ctype.h>
-#include <linux/ftrace.h>
-#include <linux/slab.h>
#include <linux/init_task.h>
#include <linux/context_tracking.h>
-#include <linux/compiler.h>
-#include <linux/frame.h>
+
+#include <linux/blkdev.h>
+#include <linux/kprobes.h>
+#include <linux/mmu_context.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
#include <linux/prefetch.h>
-#include <linux/mutex.h>
+#include <linux/profile.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
-#include <asm/irq_regs.h>
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#endif
#include "sched.h"
#include "../workqueue_internal.h"
@@ -91,27 +31,8 @@
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
-DEFINE_MUTEX(sched_domains_mutex);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-static void update_rq_clock_task(struct rq *rq, s64 delta);
-
-void update_rq_clock(struct rq *rq)
-{
- s64 delta;
-
- lockdep_assert_held(&rq->lock);
-
- if (rq->clock_skip_update & RQCF_ACT_SKIP)
- return;
-
- delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
- if (delta < 0)
- return;
- rq->clock += delta;
- update_rq_clock_task(rq, delta);
-}
-
/*
* Debugging: various feature bits
*/
@@ -140,7 +61,7 @@
const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
/*
- * period over which we measure -rt task cpu usage in us.
+ * period over which we measure -rt task CPU usage in us.
* default: 1s
*/
unsigned int sysctl_sched_rt_period = 1000000;
@@ -153,7 +74,7 @@
*/
int sysctl_sched_rt_runtime = 950000;
-/* cpus with isolated domains */
+/* CPUs with isolated domains */
cpumask_var_t cpu_isolated_map;
/*
@@ -185,7 +106,7 @@
rq = task_rq(p);
raw_spin_lock(&rq->lock);
if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
- rf->cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
return rq;
}
raw_spin_unlock(&rq->lock);
@@ -221,11 +142,11 @@
* If we observe the old cpu in task_rq_lock, the acquire of
* the old rq->lock will fully serialize against the stores.
*
- * If we observe the new cpu in task_rq_lock, the acquire will
+ * If we observe the new CPU in task_rq_lock, the acquire will
* pair with the WMB to ensure we must then also see migrating.
*/
if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
- rf->cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
return rq;
}
raw_spin_unlock(&rq->lock);
@@ -236,6 +157,84 @@
}
}
+/*
+ * RQ-clock updating methods:
+ */
+
+static void update_rq_clock_task(struct rq *rq, s64 delta)
+{
+/*
+ * In theory, the compile should just see 0 here, and optimize out the call
+ * to sched_rt_avg_update. But I don't trust it...
+ */
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+ s64 steal = 0, irq_delta = 0;
+#endif
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+ /*
+ * Since irq_time is only updated on {soft,}irq_exit, we might run into
+ * this case when a previous update_rq_clock() happened inside a
+ * {soft,}irq region.
+ *
+ * When this happens, we stop ->clock_task and only update the
+ * prev_irq_time stamp to account for the part that fit, so that a next
+ * update will consume the rest. This ensures ->clock_task is
+ * monotonic.
+ *
+ * It does however cause some slight miss-attribution of {soft,}irq
+ * time, a more accurate solution would be to update the irq_time using
+ * the current rq->clock timestamp, except that would require using
+ * atomic ops.
+ */
+ if (irq_delta > delta)
+ irq_delta = delta;
+
+ rq->prev_irq_time += irq_delta;
+ delta -= irq_delta;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+ if (static_key_false((¶virt_steal_rq_enabled))) {
+ steal = paravirt_steal_clock(cpu_of(rq));
+ steal -= rq->prev_steal_time_rq;
+
+ if (unlikely(steal > delta))
+ steal = delta;
+
+ rq->prev_steal_time_rq += steal;
+ delta -= steal;
+ }
+#endif
+
+ rq->clock_task += delta;
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+ if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
+ sched_rt_avg_update(rq, irq_delta + steal);
+#endif
+}
+
+void update_rq_clock(struct rq *rq)
+{
+ s64 delta;
+
+ lockdep_assert_held(&rq->lock);
+
+ if (rq->clock_update_flags & RQCF_ACT_SKIP)
+ return;
+
+#ifdef CONFIG_SCHED_DEBUG
+ rq->clock_update_flags |= RQCF_UPDATED;
+#endif
+ delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+ if (delta < 0)
+ return;
+ rq->clock += delta;
+ update_rq_clock_task(rq, delta);
+}
+
+
#ifdef CONFIG_SCHED_HRTICK
/*
* Use HR-timers to deliver accurate preemption points.
@@ -458,7 +457,7 @@
task = container_of(node, struct task_struct, wake_q);
BUG_ON(!task);
- /* task can safely be re-inserted now */
+ /* Task can safely be re-inserted now: */
node = node->next;
task->wake_q.next = NULL;
@@ -516,12 +515,12 @@
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ_COMMON
/*
- * In the semi idle case, use the nearest busy cpu for migrating timers
- * from an idle cpu. This is good for power-savings.
+ * In the semi idle case, use the nearest busy CPU for migrating timers
+ * from an idle CPU. This is good for power-savings.
*
* We don't do similar optimization for completely idle system, as
- * selecting an idle cpu will add more delays to the timers than intended
- * (as that cpu's timer base may not be uptodate wrt jiffies etc).
+ * selecting an idle CPU will add more delays to the timers than intended
+ * (as that CPU's timer base may not be uptodate wrt jiffies etc).
*/
int get_nohz_timer_target(void)
{
@@ -550,6 +549,7 @@
rcu_read_unlock();
return cpu;
}
+
/*
* When add_timer_on() enqueues a timer into the timer wheel of an
* idle CPU then this timer might expire before the next timer event
@@ -784,60 +784,6 @@
dequeue_task(rq, p, flags);
}
-static void update_rq_clock_task(struct rq *rq, s64 delta)
-{
-/*
- * In theory, the compile should just see 0 here, and optimize out the call
- * to sched_rt_avg_update. But I don't trust it...
- */
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
- s64 steal = 0, irq_delta = 0;
-#endif
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
- irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
-
- /*
- * Since irq_time is only updated on {soft,}irq_exit, we might run into
- * this case when a previous update_rq_clock() happened inside a
- * {soft,}irq region.
- *
- * When this happens, we stop ->clock_task and only update the
- * prev_irq_time stamp to account for the part that fit, so that a next
- * update will consume the rest. This ensures ->clock_task is
- * monotonic.
- *
- * It does however cause some slight miss-attribution of {soft,}irq
- * time, a more accurate solution would be to update the irq_time using
- * the current rq->clock timestamp, except that would require using
- * atomic ops.
- */
- if (irq_delta > delta)
- irq_delta = delta;
-
- rq->prev_irq_time += irq_delta;
- delta -= irq_delta;
-#endif
-#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
- if (static_key_false((¶virt_steal_rq_enabled))) {
- steal = paravirt_steal_clock(cpu_of(rq));
- steal -= rq->prev_steal_time_rq;
-
- if (unlikely(steal > delta))
- steal = delta;
-
- rq->prev_steal_time_rq += steal;
- delta -= steal;
- }
-#endif
-
- rq->clock_task += delta;
-
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
- if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
- sched_rt_avg_update(rq, irq_delta + steal);
-#endif
-}
-
void sched_set_stop_task(int cpu, struct task_struct *stop)
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
@@ -1018,7 +964,7 @@
};
/*
- * Move (not current) task off this cpu, onto dest cpu. We're doing
+ * Move (not current) task off this CPU, onto the destination CPU. We're doing
* this because either it can't run here any more (set_cpus_allowed()
* away from this CPU, or CPU going down), or because we're
* attempting to rebalance this task on exec (sched_exec).
@@ -1052,8 +998,8 @@
struct rq *rq = this_rq();
/*
- * The original target cpu might have gone down and we might
- * be on another cpu but it doesn't matter.
+ * The original target CPU might have gone down and we might
+ * be on another CPU but it doesn't matter.
*/
local_irq_disable();
/*
@@ -1171,7 +1117,7 @@
if (p->flags & PF_KTHREAD) {
/*
* For kernel threads that do indeed end up on online &&
- * !active we want to ensure they are strict per-cpu threads.
+ * !active we want to ensure they are strict per-CPU threads.
*/
WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) &&
!cpumask_intersects(new_mask, cpu_active_mask) &&
@@ -1195,9 +1141,9 @@
* OK, since we're going to drop the lock immediately
* afterwards anyway.
*/
- lockdep_unpin_lock(&rq->lock, rf.cookie);
+ rq_unpin_lock(rq, &rf);
rq = move_queued_task(rq, p, dest_cpu);
- lockdep_repin_lock(&rq->lock, rf.cookie);
+ rq_repin_lock(rq, &rf);
}
out:
task_rq_unlock(rq, p, &rf);
@@ -1276,7 +1222,7 @@
/*
* Task isn't running anymore; make it appear like we migrated
* it before it went to sleep. This means on wakeup we make the
- * previous cpu our target instead of where it really is.
+ * previous CPU our target instead of where it really is.
*/
p->wake_cpu = cpu;
}
@@ -1508,12 +1454,12 @@
*
* - on cpu-up we allow per-cpu kthreads on the online && !active cpu,
* see __set_cpus_allowed_ptr(). At this point the newly online
- * cpu isn't yet part of the sched domains, and balancing will not
+ * CPU isn't yet part of the sched domains, and balancing will not
* see it.
*
- * - on cpu-down we clear cpu_active() to mask the sched domains and
+ * - on CPU-down we clear cpu_active() to mask the sched domains and
* avoid the load balancer to place new tasks on the to be removed
- * cpu. Existing tasks will remain running there and will be taken
+ * CPU. Existing tasks will remain running there and will be taken
* off.
*
* This means that fallback selection must not select !active CPUs.
@@ -1529,9 +1475,9 @@
int dest_cpu;
/*
- * If the node that the cpu is on has been offlined, cpu_to_node()
- * will return -1. There is no cpu on the node, and we should
- * select the cpu on the other node.
+ * If the node that the CPU is on has been offlined, cpu_to_node()
+ * will return -1. There is no CPU on the node, and we should
+ * select the CPU on the other node.
*/
if (nid != -1) {
nodemask = cpumask_of_node(nid);
@@ -1563,7 +1509,7 @@
state = possible;
break;
}
- /* fall-through */
+ /* Fall-through */
case possible:
do_set_cpus_allowed(p, cpu_possible_mask);
state = fail;
@@ -1607,7 +1553,7 @@
/*
* In order not to call set_task_cpu() on a blocking task we need
* to rely on ttwu() to place the task on a valid ->cpus_allowed
- * cpu.
+ * CPU.
*
* Since this is common to all placement strategies, this lives here.
*
@@ -1681,7 +1627,7 @@
activate_task(rq, p, en_flags);
p->on_rq = TASK_ON_RQ_QUEUED;
- /* if a worker is waking up, notify workqueue */
+ /* If a worker is waking up, notify the workqueue: */
if (p->flags & PF_WQ_WORKER)
wq_worker_waking_up(p, cpu_of(rq));
}
@@ -1690,7 +1636,7 @@
* Mark the task runnable and perform wakeup-preemption.
*/
static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
- struct pin_cookie cookie)
+ struct rq_flags *rf)
{
check_preempt_curr(rq, p, wake_flags);
p->state = TASK_RUNNING;
@@ -1702,9 +1648,9 @@
* Our task @p is fully woken up and running; so its safe to
* drop the rq->lock, hereafter rq is only used for statistics.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
p->sched_class->task_woken(rq, p);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
}
if (rq->idle_stamp) {
@@ -1723,7 +1669,7 @@
static void
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
- struct pin_cookie cookie)
+ struct rq_flags *rf)
{
int en_flags = ENQUEUE_WAKEUP;
@@ -1738,7 +1684,7 @@
#endif
ttwu_activate(rq, p, en_flags);
- ttwu_do_wakeup(rq, p, wake_flags, cookie);
+ ttwu_do_wakeup(rq, p, wake_flags, rf);
}
/*
@@ -1757,7 +1703,7 @@
if (task_on_rq_queued(p)) {
/* check_preempt_curr() may use rq clock */
update_rq_clock(rq);
- ttwu_do_wakeup(rq, p, wake_flags, rf.cookie);
+ ttwu_do_wakeup(rq, p, wake_flags, &rf);
ret = 1;
}
__task_rq_unlock(rq, &rf);
@@ -1770,15 +1716,15 @@
{
struct rq *rq = this_rq();
struct llist_node *llist = llist_del_all(&rq->wake_list);
- struct pin_cookie cookie;
struct task_struct *p;
unsigned long flags;
+ struct rq_flags rf;
if (!llist)
return;
raw_spin_lock_irqsave(&rq->lock, flags);
- cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, &rf);
while (llist) {
int wake_flags = 0;
@@ -1789,10 +1735,10 @@
if (p->sched_remote_wakeup)
wake_flags = WF_MIGRATED;
- ttwu_do_activate(rq, p, wake_flags, cookie);
+ ttwu_do_activate(rq, p, wake_flags, &rf);
}
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -1864,7 +1810,7 @@
raw_spin_lock_irqsave(&rq->lock, flags);
if (is_idle_task(rq->curr))
smp_send_reschedule(cpu);
- /* Else cpu is not in idle, do nothing here */
+ /* Else CPU is not idle, do nothing here: */
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -1881,20 +1827,20 @@
static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
{
struct rq *rq = cpu_rq(cpu);
- struct pin_cookie cookie;
+ struct rq_flags rf;
#if defined(CONFIG_SMP)
if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
- sched_clock_cpu(cpu); /* sync clocks x-cpu */
+ sched_clock_cpu(cpu); /* Sync clocks across CPUs */
ttwu_queue_remote(p, cpu, wake_flags);
return;
}
#endif
raw_spin_lock(&rq->lock);
- cookie = lockdep_pin_lock(&rq->lock);
- ttwu_do_activate(rq, p, wake_flags, cookie);
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_pin_lock(rq, &rf);
+ ttwu_do_activate(rq, p, wake_flags, &rf);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock(&rq->lock);
}
@@ -1904,8 +1850,8 @@
* MIGRATION
*
* The basic program-order guarantee on SMP systems is that when a task [t]
- * migrates, all its activity on its old cpu [c0] happens-before any subsequent
- * execution on its new cpu [c1].
+ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
+ * execution on its new CPU [c1].
*
* For migration (of runnable tasks) this is provided by the following means:
*
@@ -1916,7 +1862,7 @@
*
* Transitivity guarantees that B happens after A and C after B.
* Note: we only require RCpc transitivity.
- * Note: the cpu doing B need not be c0 or c1
+ * Note: the CPU doing B need not be c0 or c1
*
* Example:
*
@@ -2024,7 +1970,8 @@
trace_sched_waking(p);
- success = 1; /* we're going to change ->state */
+ /* We're going to change ->state: */
+ success = 1;
cpu = task_cpu(p);
/*
@@ -2073,7 +2020,7 @@
smp_rmb();
/*
- * If the owning (remote) cpu is still in the middle of schedule() with
+ * If the owning (remote) CPU is still in the middle of schedule() with
* this task as prev, wait until its done referencing the task.
*
* Pairs with the smp_store_release() in finish_lock_switch().
@@ -2086,11 +2033,24 @@
p->sched_contributes_to_load = !!task_contributes_to_load(p);
p->state = TASK_WAKING;
+ if (p->in_iowait) {
+ delayacct_blkio_end();
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
+
cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
if (task_cpu(p) != cpu) {
wake_flags |= WF_MIGRATED;
set_task_cpu(p, cpu);
}
+
+#else /* CONFIG_SMP */
+
+ if (p->in_iowait) {
+ delayacct_blkio_end();
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
+
#endif /* CONFIG_SMP */
ttwu_queue(p, cpu, wake_flags);
@@ -2111,7 +2071,7 @@
* ensure that this_rq() is locked, @p is bound to this_rq() and not
* the current task.
*/
-static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie)
+static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
{
struct rq *rq = task_rq(p);
@@ -2128,11 +2088,11 @@
* disabled avoiding further scheduler activity on it and we've
* not yet picked a replacement task.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
raw_spin_unlock(&rq->lock);
raw_spin_lock(&p->pi_lock);
raw_spin_lock(&rq->lock);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
}
if (!(p->state & TASK_NORMAL))
@@ -2140,10 +2100,15 @@
trace_sched_waking(p);
- if (!task_on_rq_queued(p))
+ if (!task_on_rq_queued(p)) {
+ if (p->in_iowait) {
+ delayacct_blkio_end();
+ atomic_dec(&rq->nr_iowait);
+ }
ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+ }
- ttwu_do_wakeup(rq, p, 0, cookie);
+ ttwu_do_wakeup(rq, p, 0, rf);
ttwu_stat(p, smp_processor_id(), 0);
out:
raw_spin_unlock(&p->pi_lock);
@@ -2427,7 +2392,7 @@
*/
raw_spin_lock_irqsave(&p->pi_lock, flags);
/*
- * We're setting the cpu for the first time, we don't migrate,
+ * We're setting the CPU for the first time, we don't migrate,
* so use __set_task_cpu().
*/
__set_task_cpu(p, cpu);
@@ -2570,7 +2535,7 @@
/*
* Fork balancing, do it here and not earlier because:
* - cpus_allowed can change in the fork path
- * - any previously selected cpu might disappear through hotplug
+ * - any previously selected CPU might disappear through hotplug
*
* Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
* as we're not fully set-up yet.
@@ -2578,6 +2543,7 @@
__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
rq = __task_rq_lock(p, &rf);
+ update_rq_clock(rq);
post_init_entity_util_avg(&p->se);
activate_task(rq, p, 0);
@@ -2590,9 +2556,9 @@
* Nothing relies on rq->lock after this, so its fine to
* drop it.
*/
- lockdep_unpin_lock(&rq->lock, rf.cookie);
+ rq_unpin_lock(rq, &rf);
p->sched_class->task_woken(rq, p);
- lockdep_repin_lock(&rq->lock, rf.cookie);
+ rq_repin_lock(rq, &rf);
}
#endif
task_rq_unlock(rq, p, &rf);
@@ -2861,7 +2827,7 @@
*/
static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
- struct task_struct *next, struct pin_cookie cookie)
+ struct task_struct *next, struct rq_flags *rf)
{
struct mm_struct *mm, *oldmm;
@@ -2887,13 +2853,16 @@
prev->active_mm = NULL;
rq->prev_mm = oldmm;
}
+
+ rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
+
/*
* Since the runqueue lock will be released by the next
* task (which is an invalid locking op but in the case
* of the scheduler it's an obvious special-case), so we
* do an early lockdep release here:
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
/* Here we just switch the register state and the stack. */
@@ -2920,7 +2889,7 @@
}
/*
- * Check if only the current task is running on the cpu.
+ * Check if only the current task is running on the CPU.
*
* Caution: this function does not check that the caller has disabled
* preemption, thus the result might have a time-of-check-to-time-of-use
@@ -2949,6 +2918,36 @@
return sum;
}
+/*
+ * IO-wait accounting, and how its mostly bollocks (on SMP).
+ *
+ * The idea behind IO-wait account is to account the idle time that we could
+ * have spend running if it were not for IO. That is, if we were to improve the
+ * storage performance, we'd have a proportional reduction in IO-wait time.
+ *
+ * This all works nicely on UP, where, when a task blocks on IO, we account
+ * idle time as IO-wait, because if the storage were faster, it could've been
+ * running and we'd not be idle.
+ *
+ * This has been extended to SMP, by doing the same for each CPU. This however
+ * is broken.
+ *
+ * Imagine for instance the case where two tasks block on one CPU, only the one
+ * CPU will have IO-wait accounted, while the other has regular idle. Even
+ * though, if the storage were faster, both could've ran at the same time,
+ * utilising both CPUs.
+ *
+ * This means, that when looking globally, the current IO-wait accounting on
+ * SMP is a lower bound, by reason of under accounting.
+ *
+ * Worse, since the numbers are provided per CPU, they are sometimes
+ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
+ * associated with any one particular CPU, it can wake to another CPU than it
+ * blocked on. This means the per CPU IO-wait number is meaningless.
+ *
+ * Task CPU affinities can make all that even more 'interesting'.
+ */
+
unsigned long nr_iowait(void)
{
unsigned long i, sum = 0;
@@ -2959,6 +2958,13 @@
return sum;
}
+/*
+ * Consumers of these two interfaces, like for example the cpufreq menu
+ * governor are using nonsensical data. Boosting frequency for a CPU that has
+ * IO-wait which might not even end up running the task when it does become
+ * runnable.
+ */
+
unsigned long nr_iowait_cpu(int cpu)
{
struct rq *this = cpu_rq(cpu);
@@ -3042,8 +3048,8 @@
* So we have a optimization chance when the task's delta_exec is 0.
* Reading ->on_cpu is racy, but this is ok.
*
- * If we race with it leaving cpu, we'll take a lock. So we're correct.
- * If we race with it entering cpu, unaccounted time is 0. This is
+ * If we race with it leaving CPU, we'll take a lock. So we're correct.
+ * If we race with it entering CPU, unaccounted time is 0. This is
* indistinguishable from the read occurring a few cycles earlier.
* If we see ->on_cpu without ->on_rq, the task is leaving, and has
* been accounted, so we're correct here as well.
@@ -3257,31 +3263,30 @@
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
- const struct sched_class *class = &fair_sched_class;
+ const struct sched_class *class;
struct task_struct *p;
/*
* Optimization: we know that if all tasks are in
* the fair class we can call that function directly:
*/
- if (likely(prev->sched_class == class &&
- rq->nr_running == rq->cfs.h_nr_running)) {
- p = fair_sched_class.pick_next_task(rq, prev, cookie);
+ if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+ p = fair_sched_class.pick_next_task(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
goto again;
- /* assumes fair_sched_class->next == idle_sched_class */
+ /* Assumes fair_sched_class->next == idle_sched_class */
if (unlikely(!p))
- p = idle_sched_class.pick_next_task(rq, prev, cookie);
+ p = idle_sched_class.pick_next_task(rq, prev, rf);
return p;
}
again:
for_each_class(class) {
- p = class->pick_next_task(rq, prev, cookie);
+ p = class->pick_next_task(rq, prev, rf);
if (p) {
if (unlikely(p == RETRY_TASK))
goto again;
@@ -3289,7 +3294,8 @@
}
}
- BUG(); /* the idle class will always have a runnable task */
+ /* The idle class should always have a runnable task: */
+ BUG();
}
/*
@@ -3335,7 +3341,7 @@
{
struct task_struct *prev, *next;
unsigned long *switch_count;
- struct pin_cookie cookie;
+ struct rq_flags rf;
struct rq *rq;
int cpu;
@@ -3358,9 +3364,10 @@
*/
smp_mb__before_spinlock();
raw_spin_lock(&rq->lock);
- cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, &rf);
- rq->clock_skip_update <<= 1; /* promote REQ to ACT */
+ /* Promote REQ to ACT */
+ rq->clock_update_flags <<= 1;
switch_count = &prev->nivcsw;
if (!preempt && prev->state) {
@@ -3370,6 +3377,11 @@
deactivate_task(rq, prev, DEQUEUE_SLEEP);
prev->on_rq = 0;
+ if (prev->in_iowait) {
+ atomic_inc(&rq->nr_iowait);
+ delayacct_blkio_start();
+ }
+
/*
* If a worker went to sleep, notify and ask workqueue
* whether it wants to wake up a task to maintain
@@ -3380,7 +3392,7 @@
to_wakeup = wq_worker_sleeping(prev);
if (to_wakeup)
- try_to_wake_up_local(to_wakeup, cookie);
+ try_to_wake_up_local(to_wakeup, &rf);
}
}
switch_count = &prev->nvcsw;
@@ -3389,10 +3401,9 @@
if (task_on_rq_queued(prev))
update_rq_clock(rq);
- next = pick_next_task(rq, prev, cookie);
+ next = pick_next_task(rq, prev, &rf);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
- rq->clock_skip_update = 0;
if (likely(prev != next)) {
rq->nr_switches++;
@@ -3400,9 +3411,12 @@
++*switch_count;
trace_sched_switch(preempt, prev, next);
- rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */
+
+ /* Also unlocks the rq: */
+ rq = context_switch(rq, prev, next, &rf);
} else {
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock_irq(&rq->lock);
}
@@ -3426,14 +3440,18 @@
smp_mb();
raw_spin_unlock_wait(¤t->pi_lock);
- /* causes final put_task_struct in finish_task_switch(). */
+ /* Causes final put_task_struct in finish_task_switch(): */
__set_current_state(TASK_DEAD);
- current->flags |= PF_NOFREEZE; /* tell freezer to ignore us */
+
+ /* Tell freezer to ignore us: */
+ current->flags |= PF_NOFREEZE;
+
__schedule(false);
BUG();
- /* Avoid "noreturn function does return". */
+
+ /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
for (;;)
- cpu_relax(); /* For when BUG is null */
+ cpu_relax();
}
static inline void sched_submit_work(struct task_struct *tsk)
@@ -3651,6 +3669,7 @@
BUG_ON(prio > MAX_PRIO);
rq = __task_rq_lock(p, &rf);
+ update_rq_clock(rq);
/*
* Idle task boosting is a nono in general. There is one
@@ -3725,7 +3744,8 @@
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
- preempt_disable(); /* avoid rq from going away on us */
+ /* Avoid rq from going away on us: */
+ preempt_disable();
__task_rq_unlock(rq, &rf);
balance_callback(rq);
@@ -3747,6 +3767,8 @@
* the task might be in the middle of scheduling on another CPU.
*/
rq = task_rq_lock(p, &rf);
+ update_rq_clock(rq);
+
/*
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
@@ -3793,7 +3815,7 @@
*/
int can_nice(const struct task_struct *p, const int nice)
{
- /* convert nice value [19,-20] to rlimit style value [1,40] */
+ /* Convert nice value [19,-20] to rlimit style value [1,40]: */
int nice_rlim = nice_to_rlimit(nice);
return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
@@ -3849,7 +3871,7 @@
}
/**
- * idle_cpu - is a given cpu idle currently?
+ * idle_cpu - is a given CPU idle currently?
* @cpu: the processor in question.
*
* Return: 1 if the CPU is currently idle. 0 otherwise.
@@ -3873,10 +3895,10 @@
}
/**
- * idle_task - return the idle task for a given cpu.
+ * idle_task - return the idle task for a given CPU.
* @cpu: the processor in question.
*
- * Return: The idle task for the cpu @cpu.
+ * Return: The idle task for the CPU @cpu.
*/
struct task_struct *idle_task(int cpu)
{
@@ -4042,7 +4064,7 @@
}
/*
- * check the target process has a UID that matches the current process's
+ * Check the target process has a UID that matches the current process's:
*/
static bool check_same_owner(struct task_struct *p)
{
@@ -4057,8 +4079,7 @@
return match;
}
-static bool dl_param_changed(struct task_struct *p,
- const struct sched_attr *attr)
+static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
{
struct sched_dl_entity *dl_se = &p->dl;
@@ -4085,10 +4106,10 @@
int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
struct rq *rq;
- /* may grab non-irq protected spin_locks */
+ /* May grab non-irq protected spin_locks: */
BUG_ON(in_interrupt());
recheck:
- /* double check policy once rq lock held */
+ /* Double check policy once rq lock held: */
if (policy < 0) {
reset_on_fork = p->sched_reset_on_fork;
policy = oldpolicy = p->policy;
@@ -4128,11 +4149,11 @@
unsigned long rlim_rtprio =
task_rlimit(p, RLIMIT_RTPRIO);
- /* can't set/change the rt policy */
+ /* Can't set/change the rt policy: */
if (policy != p->policy && !rlim_rtprio)
return -EPERM;
- /* can't increase priority */
+ /* Can't increase priority: */
if (attr->sched_priority > p->rt_priority &&
attr->sched_priority > rlim_rtprio)
return -EPERM;
@@ -4156,11 +4177,11 @@
return -EPERM;
}
- /* can't change other user's priorities */
+ /* Can't change other user's priorities: */
if (!check_same_owner(p))
return -EPERM;
- /* Normal users shall not reset the sched_reset_on_fork flag */
+ /* Normal users shall not reset the sched_reset_on_fork flag: */
if (p->sched_reset_on_fork && !reset_on_fork)
return -EPERM;
}
@@ -4172,16 +4193,17 @@
}
/*
- * make sure no PI-waiters arrive (or leave) while we are
+ * Make sure no PI-waiters arrive (or leave) while we are
* changing the priority of the task:
*
* To be able to change p->policy safely, the appropriate
* runqueue lock must be held.
*/
rq = task_rq_lock(p, &rf);
+ update_rq_clock(rq);
/*
- * Changing the policy of the stop threads its a very bad idea
+ * Changing the policy of the stop threads its a very bad idea:
*/
if (p == rq->stop) {
task_rq_unlock(rq, p, &rf);
@@ -4237,7 +4259,7 @@
#endif
}
- /* recheck policy now with rq lock held */
+ /* Re-check policy now with rq lock held: */
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
policy = oldpolicy = -1;
task_rq_unlock(rq, p, &rf);
@@ -4294,15 +4316,15 @@
set_curr_task(rq, p);
check_class_changed(rq, p, prev_class, oldprio);
- preempt_disable(); /* avoid rq from going away on us */
+
+ /* Avoid rq from going away on us: */
+ preempt_disable();
task_rq_unlock(rq, p, &rf);
if (pi)
rt_mutex_adjust_pi(p);
- /*
- * Run balance callbacks after we've adjusted the PI chain.
- */
+ /* Run balance callbacks after we've adjusted the PI chain: */
balance_callback(rq);
preempt_enable();
@@ -4395,8 +4417,7 @@
/*
* Mimics kernel/events/core.c perf_copy_attr().
*/
-static int sched_copy_attr(struct sched_attr __user *uattr,
- struct sched_attr *attr)
+static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
{
u32 size;
int ret;
@@ -4404,19 +4425,19 @@
if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
return -EFAULT;
- /*
- * zero the full structure, so that a short copy will be nice.
- */
+ /* Zero the full structure, so that a short copy will be nice: */
memset(attr, 0, sizeof(*attr));
ret = get_user(size, &uattr->size);
if (ret)
return ret;
- if (size > PAGE_SIZE) /* silly large */
+ /* Bail out on silly large: */
+ if (size > PAGE_SIZE)
goto err_size;
- if (!size) /* abi compat */
+ /* ABI compatibility quirk: */
+ if (!size)
size = SCHED_ATTR_SIZE_VER0;
if (size < SCHED_ATTR_SIZE_VER0)
@@ -4451,7 +4472,7 @@
return -EFAULT;
/*
- * XXX: do we want to be lenient like existing syscalls; or do we want
+ * XXX: Do we want to be lenient like existing syscalls; or do we want
* to be strict and return an error on out-of-bounds values?
*/
attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);
@@ -4471,10 +4492,8 @@
*
* Return: 0 on success. An error code otherwise.
*/
-SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
- struct sched_param __user *, param)
+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
{
- /* negative values for policy are not valid */
if (policy < 0)
return -EINVAL;
@@ -4784,10 +4803,10 @@
}
/**
- * sys_sched_setaffinity - set the cpu affinity of a process
+ * sys_sched_setaffinity - set the CPU affinity of a process
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
- * @user_mask_ptr: user-space pointer to the new cpu mask
+ * @user_mask_ptr: user-space pointer to the new CPU mask
*
* Return: 0 on success. An error code otherwise.
*/
@@ -4835,10 +4854,10 @@
}
/**
- * sys_sched_getaffinity - get the cpu affinity of a process
+ * sys_sched_getaffinity - get the CPU affinity of a process
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
- * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ * @user_mask_ptr: user-space pointer to hold the current CPU mask
*
* Return: size of CPU mask copied to user_mask_ptr on success. An
* error code otherwise.
@@ -4966,7 +4985,7 @@
* Typical broken usage is:
*
* while (!event)
- * yield();
+ * yield();
*
* where one assumes that yield() will let 'the other' process run that will
* make event true. If the current task is a SCHED_FIFO task that will never
@@ -5057,31 +5076,48 @@
}
EXPORT_SYMBOL_GPL(yield_to);
+int io_schedule_prepare(void)
+{
+ int old_iowait = current->in_iowait;
+
+ current->in_iowait = 1;
+ blk_schedule_flush_plug(current);
+
+ return old_iowait;
+}
+
+void io_schedule_finish(int token)
+{
+ current->in_iowait = token;
+}
+
/*
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
*/
long __sched io_schedule_timeout(long timeout)
{
- int old_iowait = current->in_iowait;
- struct rq *rq;
+ int token;
long ret;
- current->in_iowait = 1;
- blk_schedule_flush_plug(current);
-
- delayacct_blkio_start();
- rq = raw_rq();
- atomic_inc(&rq->nr_iowait);
+ token = io_schedule_prepare();
ret = schedule_timeout(timeout);
- current->in_iowait = old_iowait;
- atomic_dec(&rq->nr_iowait);
- delayacct_blkio_end();
+ io_schedule_finish(token);
return ret;
}
EXPORT_SYMBOL(io_schedule_timeout);
+void io_schedule(void)
+{
+ int token;
+
+ token = io_schedule_prepare();
+ schedule();
+ io_schedule_finish(token);
+}
+EXPORT_SYMBOL(io_schedule);
+
/**
* sys_sched_get_priority_max - return maximum RT priority.
* @policy: scheduling class.
@@ -5264,7 +5300,7 @@
/**
* init_idle - set up an idle thread for a given CPU
* @idle: task in question
- * @cpu: cpu the idle task belongs to
+ * @cpu: CPU the idle task belongs to
*
* NOTE: this function does not set the idle thread's NEED_RESCHED
* flag, to make booting more robust.
@@ -5295,7 +5331,7 @@
#endif
/*
* We're having a chicken and egg problem, even though we are
- * holding rq->lock, the cpu isn't yet set to this cpu so the
+ * holding rq->lock, the CPU isn't yet set to this CPU so the
* lockdep check in task_group() will fail.
*
* Similar case to sched_fork(). / Alternatively we could
@@ -5360,7 +5396,7 @@
/*
* Kthreads which disallow setaffinity shouldn't be moved
- * to a new cpuset; we don't want to change their cpu
+ * to a new cpuset; we don't want to change their CPU
* affinity and isolating such threads by their set of
* allowed nodes is unnecessary. Thus, cpusets are not
* applicable for such threads. This prevents checking for
@@ -5409,7 +5445,7 @@
#ifdef CONFIG_SMP
-static bool sched_smp_initialized __read_mostly;
+bool sched_smp_initialized __read_mostly;
#ifdef CONFIG_NUMA_BALANCING
/* Migrate current task p to target_cpu */
@@ -5461,7 +5497,7 @@
#ifdef CONFIG_HOTPLUG_CPU
/*
- * Ensures that the idle task is using init_mm right before its cpu goes
+ * Ensure that the idle task is using init_mm right before its CPU goes
* offline.
*/
void idle_task_exit(void)
@@ -5521,7 +5557,7 @@
{
struct rq *rq = dead_rq;
struct task_struct *next, *stop = rq->stop;
- struct pin_cookie cookie;
+ struct rq_flags rf, old_rf;
int dest_cpu;
/*
@@ -5545,16 +5581,16 @@
for (;;) {
/*
* There's this thread running, bail when that's the only
- * remaining thread.
+ * remaining thread:
*/
if (rq->nr_running == 1)
break;
/*
- * pick_next_task assumes pinned rq->lock.
+ * pick_next_task() assumes pinned rq->lock:
*/
- cookie = lockdep_pin_lock(&rq->lock);
- next = pick_next_task(rq, &fake_task, cookie);
+ rq_pin_lock(rq, &rf);
+ next = pick_next_task(rq, &fake_task, &rf);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);
@@ -5567,7 +5603,7 @@
* because !cpu_active at this point, which means load-balance
* will not interfere. Also, stop-machine.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock(&rq->lock);
raw_spin_lock(&next->pi_lock);
raw_spin_lock(&rq->lock);
@@ -5582,6 +5618,13 @@
continue;
}
+ /*
+ * __migrate_task() may return with a different
+ * rq->lock held and a new cookie in 'rf', but we need
+ * to preserve rf::clock_update_flags for 'dead_rq'.
+ */
+ old_rf = rf;
+
/* Find suitable destination for @next, with force if needed. */
dest_cpu = select_fallback_rq(dead_rq->cpu, next);
@@ -5590,6 +5633,7 @@
raw_spin_unlock(&rq->lock);
rq = dead_rq;
raw_spin_lock(&rq->lock);
+ rf = old_rf;
}
raw_spin_unlock(&next->pi_lock);
}
@@ -5598,7 +5642,7 @@
}
#endif /* CONFIG_HOTPLUG_CPU */
-static void set_rq_online(struct rq *rq)
+void set_rq_online(struct rq *rq)
{
if (!rq->online) {
const struct sched_class *class;
@@ -5613,7 +5657,7 @@
}
}
-static void set_rq_offline(struct rq *rq)
+void set_rq_offline(struct rq *rq)
{
if (rq->online) {
const struct sched_class *class;
@@ -5635,1647 +5679,10 @@
rq->age_stamp = sched_clock_cpu(cpu);
}
-static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
-
-#ifdef CONFIG_SCHED_DEBUG
-
-static __read_mostly int sched_debug_enabled;
-
-static int __init sched_debug_setup(char *str)
-{
- sched_debug_enabled = 1;
-
- return 0;
-}
-early_param("sched_debug", sched_debug_setup);
-
-static inline bool sched_debug(void)
-{
- return sched_debug_enabled;
-}
-
-static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
- struct cpumask *groupmask)
-{
- struct sched_group *group = sd->groups;
-
- cpumask_clear(groupmask);
-
- printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
-
- if (!(sd->flags & SD_LOAD_BALANCE)) {
- printk("does not load-balance\n");
- if (sd->parent)
- printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
- " has parent");
- return -1;
- }
-
- printk(KERN_CONT "span %*pbl level %s\n",
- cpumask_pr_args(sched_domain_span(sd)), sd->name);
-
- if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
- printk(KERN_ERR "ERROR: domain->span does not contain "
- "CPU%d\n", cpu);
- }
- if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
- printk(KERN_ERR "ERROR: domain->groups does not contain"
- " CPU%d\n", cpu);
- }
-
- printk(KERN_DEBUG "%*s groups:", level + 1, "");
- do {
- if (!group) {
- printk("\n");
- printk(KERN_ERR "ERROR: group is NULL\n");
- break;
- }
-
- if (!cpumask_weight(sched_group_cpus(group))) {
- printk(KERN_CONT "\n");
- printk(KERN_ERR "ERROR: empty group\n");
- break;
- }
-
- if (!(sd->flags & SD_OVERLAP) &&
- cpumask_intersects(groupmask, sched_group_cpus(group))) {
- printk(KERN_CONT "\n");
- printk(KERN_ERR "ERROR: repeated CPUs\n");
- break;
- }
-
- cpumask_or(groupmask, groupmask, sched_group_cpus(group));
-
- printk(KERN_CONT " %*pbl",
- cpumask_pr_args(sched_group_cpus(group)));
- if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
- printk(KERN_CONT " (cpu_capacity = %lu)",
- group->sgc->capacity);
- }
-
- group = group->next;
- } while (group != sd->groups);
- printk(KERN_CONT "\n");
-
- if (!cpumask_equal(sched_domain_span(sd), groupmask))
- printk(KERN_ERR "ERROR: groups don't span domain->span\n");
-
- if (sd->parent &&
- !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
- printk(KERN_ERR "ERROR: parent span is not a superset "
- "of domain->span\n");
- return 0;
-}
-
-static void sched_domain_debug(struct sched_domain *sd, int cpu)
-{
- int level = 0;
-
- if (!sched_debug_enabled)
- return;
-
- if (!sd) {
- printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
- return;
- }
-
- printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
-
- for (;;) {
- if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
- break;
- level++;
- sd = sd->parent;
- if (!sd)
- break;
- }
-}
-#else /* !CONFIG_SCHED_DEBUG */
-
-# define sched_debug_enabled 0
-# define sched_domain_debug(sd, cpu) do { } while (0)
-static inline bool sched_debug(void)
-{
- return false;
-}
-#endif /* CONFIG_SCHED_DEBUG */
-
-static int sd_degenerate(struct sched_domain *sd)
-{
- if (cpumask_weight(sched_domain_span(sd)) == 1)
- return 1;
-
- /* Following flags need at least 2 groups */
- if (sd->flags & (SD_LOAD_BALANCE |
- SD_BALANCE_NEWIDLE |
- SD_BALANCE_FORK |
- SD_BALANCE_EXEC |
- SD_SHARE_CPUCAPACITY |
- SD_ASYM_CPUCAPACITY |
- SD_SHARE_PKG_RESOURCES |
- SD_SHARE_POWERDOMAIN)) {
- if (sd->groups != sd->groups->next)
- return 0;
- }
-
- /* Following flags don't use groups */
- if (sd->flags & (SD_WAKE_AFFINE))
- return 0;
-
- return 1;
-}
-
-static int
-sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
-{
- unsigned long cflags = sd->flags, pflags = parent->flags;
-
- if (sd_degenerate(parent))
- return 1;
-
- if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
- return 0;
-
- /* Flags needing groups don't count if only 1 group in parent */
- if (parent->groups == parent->groups->next) {
- pflags &= ~(SD_LOAD_BALANCE |
- SD_BALANCE_NEWIDLE |
- SD_BALANCE_FORK |
- SD_BALANCE_EXEC |
- SD_ASYM_CPUCAPACITY |
- SD_SHARE_CPUCAPACITY |
- SD_SHARE_PKG_RESOURCES |
- SD_PREFER_SIBLING |
- SD_SHARE_POWERDOMAIN);
- if (nr_node_ids == 1)
- pflags &= ~SD_SERIALIZE;
- }
- if (~cflags & pflags)
- return 0;
-
- return 1;
-}
-
-static void free_rootdomain(struct rcu_head *rcu)
-{
- struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
-
- cpupri_cleanup(&rd->cpupri);
- cpudl_cleanup(&rd->cpudl);
- free_cpumask_var(rd->dlo_mask);
- free_cpumask_var(rd->rto_mask);
- free_cpumask_var(rd->online);
- free_cpumask_var(rd->span);
- kfree(rd);
-}
-
-static void rq_attach_root(struct rq *rq, struct root_domain *rd)
-{
- struct root_domain *old_rd = NULL;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&rq->lock, flags);
-
- if (rq->rd) {
- old_rd = rq->rd;
-
- if (cpumask_test_cpu(rq->cpu, old_rd->online))
- set_rq_offline(rq);
-
- cpumask_clear_cpu(rq->cpu, old_rd->span);
-
- /*
- * If we dont want to free the old_rd yet then
- * set old_rd to NULL to skip the freeing later
- * in this function:
- */
- if (!atomic_dec_and_test(&old_rd->refcount))
- old_rd = NULL;
- }
-
- atomic_inc(&rd->refcount);
- rq->rd = rd;
-
- cpumask_set_cpu(rq->cpu, rd->span);
- if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
- set_rq_online(rq);
-
- raw_spin_unlock_irqrestore(&rq->lock, flags);
-
- if (old_rd)
- call_rcu_sched(&old_rd->rcu, free_rootdomain);
-}
-
-static int init_rootdomain(struct root_domain *rd)
-{
- memset(rd, 0, sizeof(*rd));
-
- if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
- goto out;
- if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
- goto free_span;
- if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
- goto free_online;
- if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
- goto free_dlo_mask;
-
- init_dl_bw(&rd->dl_bw);
- if (cpudl_init(&rd->cpudl) != 0)
- goto free_dlo_mask;
-
- if (cpupri_init(&rd->cpupri) != 0)
- goto free_rto_mask;
- return 0;
-
-free_rto_mask:
- free_cpumask_var(rd->rto_mask);
-free_dlo_mask:
- free_cpumask_var(rd->dlo_mask);
-free_online:
- free_cpumask_var(rd->online);
-free_span:
- free_cpumask_var(rd->span);
-out:
- return -ENOMEM;
-}
-
/*
- * By default the system creates a single root-domain with all cpus as
- * members (mimicking the global state we have today).
+ * used to mark begin/end of suspend/resume:
*/
-struct root_domain def_root_domain;
-
-static void init_defrootdomain(void)
-{
- init_rootdomain(&def_root_domain);
-
- atomic_set(&def_root_domain.refcount, 1);
-}
-
-static struct root_domain *alloc_rootdomain(void)
-{
- struct root_domain *rd;
-
- rd = kmalloc(sizeof(*rd), GFP_KERNEL);
- if (!rd)
- return NULL;
-
- if (init_rootdomain(rd) != 0) {
- kfree(rd);
- return NULL;
- }
-
- return rd;
-}
-
-static void free_sched_groups(struct sched_group *sg, int free_sgc)
-{
- struct sched_group *tmp, *first;
-
- if (!sg)
- return;
-
- first = sg;
- do {
- tmp = sg->next;
-
- if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
- kfree(sg->sgc);
-
- kfree(sg);
- sg = tmp;
- } while (sg != first);
-}
-
-static void destroy_sched_domain(struct sched_domain *sd)
-{
- /*
- * If its an overlapping domain it has private groups, iterate and
- * nuke them all.
- */
- if (sd->flags & SD_OVERLAP) {
- free_sched_groups(sd->groups, 1);
- } else if (atomic_dec_and_test(&sd->groups->ref)) {
- kfree(sd->groups->sgc);
- kfree(sd->groups);
- }
- if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
- kfree(sd->shared);
- kfree(sd);
-}
-
-static void destroy_sched_domains_rcu(struct rcu_head *rcu)
-{
- struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
-
- while (sd) {
- struct sched_domain *parent = sd->parent;
- destroy_sched_domain(sd);
- sd = parent;
- }
-}
-
-static void destroy_sched_domains(struct sched_domain *sd)
-{
- if (sd)
- call_rcu(&sd->rcu, destroy_sched_domains_rcu);
-}
-
-/*
- * Keep a special pointer to the highest sched_domain that has
- * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
- * allows us to avoid some pointer chasing select_idle_sibling().
- *
- * Also keep a unique ID per domain (we use the first cpu number in
- * the cpumask of the domain), this allows us to quickly tell if
- * two cpus are in the same cache domain, see cpus_share_cache().
- */
-DEFINE_PER_CPU(struct sched_domain *, sd_llc);
-DEFINE_PER_CPU(int, sd_llc_size);
-DEFINE_PER_CPU(int, sd_llc_id);
-DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym);
-
-static void update_top_cache_domain(int cpu)
-{
- struct sched_domain_shared *sds = NULL;
- struct sched_domain *sd;
- int id = cpu;
- int size = 1;
-
- sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
- if (sd) {
- id = cpumask_first(sched_domain_span(sd));
- size = cpumask_weight(sched_domain_span(sd));
- sds = sd->shared;
- }
-
- rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
- per_cpu(sd_llc_size, cpu) = size;
- per_cpu(sd_llc_id, cpu) = id;
- rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
-
- sd = lowest_flag_domain(cpu, SD_NUMA);
- rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
-
- sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
- rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
-}
-
-/*
- * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
- * hold the hotplug lock.
- */
-static void
-cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
-{
- struct rq *rq = cpu_rq(cpu);
- struct sched_domain *tmp;
-
- /* Remove the sched domains which do not contribute to scheduling. */
- for (tmp = sd; tmp; ) {
- struct sched_domain *parent = tmp->parent;
- if (!parent)
- break;
-
- if (sd_parent_degenerate(tmp, parent)) {
- tmp->parent = parent->parent;
- if (parent->parent)
- parent->parent->child = tmp;
- /*
- * Transfer SD_PREFER_SIBLING down in case of a
- * degenerate parent; the spans match for this
- * so the property transfers.
- */
- if (parent->flags & SD_PREFER_SIBLING)
- tmp->flags |= SD_PREFER_SIBLING;
- destroy_sched_domain(parent);
- } else
- tmp = tmp->parent;
- }
-
- if (sd && sd_degenerate(sd)) {
- tmp = sd;
- sd = sd->parent;
- destroy_sched_domain(tmp);
- if (sd)
- sd->child = NULL;
- }
-
- sched_domain_debug(sd, cpu);
-
- rq_attach_root(rq, rd);
- tmp = rq->sd;
- rcu_assign_pointer(rq->sd, sd);
- destroy_sched_domains(tmp);
-
- update_top_cache_domain(cpu);
-}
-
-/* Setup the mask of cpus configured for isolated domains */
-static int __init isolated_cpu_setup(char *str)
-{
- int ret;
-
- alloc_bootmem_cpumask_var(&cpu_isolated_map);
- ret = cpulist_parse(str, cpu_isolated_map);
- if (ret) {
- pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids);
- return 0;
- }
- return 1;
-}
-__setup("isolcpus=", isolated_cpu_setup);
-
-struct s_data {
- struct sched_domain ** __percpu sd;
- struct root_domain *rd;
-};
-
-enum s_alloc {
- sa_rootdomain,
- sa_sd,
- sa_sd_storage,
- sa_none,
-};
-
-/*
- * Build an iteration mask that can exclude certain CPUs from the upwards
- * domain traversal.
- *
- * Asymmetric node setups can result in situations where the domain tree is of
- * unequal depth, make sure to skip domains that already cover the entire
- * range.
- *
- * In that case build_sched_domains() will have terminated the iteration early
- * and our sibling sd spans will be empty. Domains should always include the
- * cpu they're built on, so check that.
- *
- */
-static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
-{
- const struct cpumask *span = sched_domain_span(sd);
- struct sd_data *sdd = sd->private;
- struct sched_domain *sibling;
- int i;
-
- for_each_cpu(i, span) {
- sibling = *per_cpu_ptr(sdd->sd, i);
- if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
- continue;
-
- cpumask_set_cpu(i, sched_group_mask(sg));
- }
-}
-
-/*
- * Return the canonical balance cpu for this group, this is the first cpu
- * of this group that's also in the iteration mask.
- */
-int group_balance_cpu(struct sched_group *sg)
-{
- return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
-}
-
-static int
-build_overlap_sched_groups(struct sched_domain *sd, int cpu)
-{
- struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
- const struct cpumask *span = sched_domain_span(sd);
- struct cpumask *covered = sched_domains_tmpmask;
- struct sd_data *sdd = sd->private;
- struct sched_domain *sibling;
- int i;
-
- cpumask_clear(covered);
-
- for_each_cpu(i, span) {
- struct cpumask *sg_span;
-
- if (cpumask_test_cpu(i, covered))
- continue;
-
- sibling = *per_cpu_ptr(sdd->sd, i);
-
- /* See the comment near build_group_mask(). */
- if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
- continue;
-
- sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
- GFP_KERNEL, cpu_to_node(cpu));
-
- if (!sg)
- goto fail;
-
- sg_span = sched_group_cpus(sg);
- if (sibling->child)
- cpumask_copy(sg_span, sched_domain_span(sibling->child));
- else
- cpumask_set_cpu(i, sg_span);
-
- cpumask_or(covered, covered, sg_span);
-
- sg->sgc = *per_cpu_ptr(sdd->sgc, i);
- if (atomic_inc_return(&sg->sgc->ref) == 1)
- build_group_mask(sd, sg);
-
- /*
- * Initialize sgc->capacity such that even if we mess up the
- * domains and no possible iteration will get us here, we won't
- * die on a /0 trap.
- */
- sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
- sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
-
- /*
- * Make sure the first group of this domain contains the
- * canonical balance cpu. Otherwise the sched_domain iteration
- * breaks. See update_sg_lb_stats().
- */
- if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
- group_balance_cpu(sg) == cpu)
- groups = sg;
-
- if (!first)
- first = sg;
- if (last)
- last->next = sg;
- last = sg;
- last->next = first;
- }
- sd->groups = groups;
-
- return 0;
-
-fail:
- free_sched_groups(first, 0);
-
- return -ENOMEM;
-}
-
-static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
-{
- struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
- struct sched_domain *child = sd->child;
-
- if (child)
- cpu = cpumask_first(sched_domain_span(child));
-
- if (sg) {
- *sg = *per_cpu_ptr(sdd->sg, cpu);
- (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
- atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */
- }
-
- return cpu;
-}
-
-/*
- * build_sched_groups will build a circular linked list of the groups
- * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_capacity to 0.
- *
- * Assumes the sched_domain tree is fully constructed
- */
-static int
-build_sched_groups(struct sched_domain *sd, int cpu)
-{
- struct sched_group *first = NULL, *last = NULL;
- struct sd_data *sdd = sd->private;
- const struct cpumask *span = sched_domain_span(sd);
- struct cpumask *covered;
- int i;
-
- get_group(cpu, sdd, &sd->groups);
- atomic_inc(&sd->groups->ref);
-
- if (cpu != cpumask_first(span))
- return 0;
-
- lockdep_assert_held(&sched_domains_mutex);
- covered = sched_domains_tmpmask;
-
- cpumask_clear(covered);
-
- for_each_cpu(i, span) {
- struct sched_group *sg;
- int group, j;
-
- if (cpumask_test_cpu(i, covered))
- continue;
-
- group = get_group(i, sdd, &sg);
- cpumask_setall(sched_group_mask(sg));
-
- for_each_cpu(j, span) {
- if (get_group(j, sdd, NULL) != group)
- continue;
-
- cpumask_set_cpu(j, covered);
- cpumask_set_cpu(j, sched_group_cpus(sg));
- }
-
- if (!first)
- first = sg;
- if (last)
- last->next = sg;
- last = sg;
- }
- last->next = first;
-
- return 0;
-}
-
-/*
- * Initialize sched groups cpu_capacity.
- *
- * cpu_capacity indicates the capacity of sched group, which is used while
- * distributing the load between different sched groups in a sched domain.
- * Typically cpu_capacity for all the groups in a sched domain will be same
- * unless there are asymmetries in the topology. If there are asymmetries,
- * group having more cpu_capacity will pickup more load compared to the
- * group having less cpu_capacity.
- */
-static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
-{
- struct sched_group *sg = sd->groups;
-
- WARN_ON(!sg);
-
- do {
- int cpu, max_cpu = -1;
-
- sg->group_weight = cpumask_weight(sched_group_cpus(sg));
-
- if (!(sd->flags & SD_ASYM_PACKING))
- goto next;
-
- for_each_cpu(cpu, sched_group_cpus(sg)) {
- if (max_cpu < 0)
- max_cpu = cpu;
- else if (sched_asym_prefer(cpu, max_cpu))
- max_cpu = cpu;
- }
- sg->asym_prefer_cpu = max_cpu;
-
-next:
- sg = sg->next;
- } while (sg != sd->groups);
-
- if (cpu != group_balance_cpu(sg))
- return;
-
- update_group_capacity(sd, cpu);
-}
-
-/*
- * Initializers for schedule domains
- * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
- */
-
-static int default_relax_domain_level = -1;
-int sched_domain_level_max;
-
-static int __init setup_relax_domain_level(char *str)
-{
- if (kstrtoint(str, 0, &default_relax_domain_level))
- pr_warn("Unable to set relax_domain_level\n");
-
- return 1;
-}
-__setup("relax_domain_level=", setup_relax_domain_level);
-
-static void set_domain_attribute(struct sched_domain *sd,
- struct sched_domain_attr *attr)
-{
- int request;
-
- if (!attr || attr->relax_domain_level < 0) {
- if (default_relax_domain_level < 0)
- return;
- else
- request = default_relax_domain_level;
- } else
- request = attr->relax_domain_level;
- if (request < sd->level) {
- /* turn off idle balance on this domain */
- sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
- } else {
- /* turn on idle balance on this domain */
- sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
- }
-}
-
-static void __sdt_free(const struct cpumask *cpu_map);
-static int __sdt_alloc(const struct cpumask *cpu_map);
-
-static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
- const struct cpumask *cpu_map)
-{
- switch (what) {
- case sa_rootdomain:
- if (!atomic_read(&d->rd->refcount))
- free_rootdomain(&d->rd->rcu); /* fall through */
- case sa_sd:
- free_percpu(d->sd); /* fall through */
- case sa_sd_storage:
- __sdt_free(cpu_map); /* fall through */
- case sa_none:
- break;
- }
-}
-
-static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
- const struct cpumask *cpu_map)
-{
- memset(d, 0, sizeof(*d));
-
- if (__sdt_alloc(cpu_map))
- return sa_sd_storage;
- d->sd = alloc_percpu(struct sched_domain *);
- if (!d->sd)
- return sa_sd_storage;
- d->rd = alloc_rootdomain();
- if (!d->rd)
- return sa_sd;
- return sa_rootdomain;
-}
-
-/*
- * NULL the sd_data elements we've used to build the sched_domain and
- * sched_group structure so that the subsequent __free_domain_allocs()
- * will not free the data we're using.
- */
-static void claim_allocations(int cpu, struct sched_domain *sd)
-{
- struct sd_data *sdd = sd->private;
-
- WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
- *per_cpu_ptr(sdd->sd, cpu) = NULL;
-
- if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref))
- *per_cpu_ptr(sdd->sds, cpu) = NULL;
-
- if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
- *per_cpu_ptr(sdd->sg, cpu) = NULL;
-
- if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref))
- *per_cpu_ptr(sdd->sgc, cpu) = NULL;
-}
-
-#ifdef CONFIG_NUMA
-static int sched_domains_numa_levels;
-enum numa_topology_type sched_numa_topology_type;
-static int *sched_domains_numa_distance;
-int sched_max_numa_distance;
-static struct cpumask ***sched_domains_numa_masks;
-static int sched_domains_curr_level;
-#endif
-
-/*
- * SD_flags allowed in topology descriptions.
- *
- * These flags are purely descriptive of the topology and do not prescribe
- * behaviour. Behaviour is artificial and mapped in the below sd_init()
- * function:
- *
- * SD_SHARE_CPUCAPACITY - describes SMT topologies
- * SD_SHARE_PKG_RESOURCES - describes shared caches
- * SD_NUMA - describes NUMA topologies
- * SD_SHARE_POWERDOMAIN - describes shared power domain
- * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies
- *
- * Odd one out, which beside describing the topology has a quirk also
- * prescribes the desired behaviour that goes along with it:
- *
- * SD_ASYM_PACKING - describes SMT quirks
- */
-#define TOPOLOGY_SD_FLAGS \
- (SD_SHARE_CPUCAPACITY | \
- SD_SHARE_PKG_RESOURCES | \
- SD_NUMA | \
- SD_ASYM_PACKING | \
- SD_ASYM_CPUCAPACITY | \
- SD_SHARE_POWERDOMAIN)
-
-static struct sched_domain *
-sd_init(struct sched_domain_topology_level *tl,
- const struct cpumask *cpu_map,
- struct sched_domain *child, int cpu)
-{
- struct sd_data *sdd = &tl->data;
- struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
- int sd_id, sd_weight, sd_flags = 0;
-
-#ifdef CONFIG_NUMA
- /*
- * Ugly hack to pass state to sd_numa_mask()...
- */
- sched_domains_curr_level = tl->numa_level;
-#endif
-
- sd_weight = cpumask_weight(tl->mask(cpu));
-
- if (tl->sd_flags)
- sd_flags = (*tl->sd_flags)();
- if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
- "wrong sd_flags in topology description\n"))
- sd_flags &= ~TOPOLOGY_SD_FLAGS;
-
- *sd = (struct sched_domain){
- .min_interval = sd_weight,
- .max_interval = 2*sd_weight,
- .busy_factor = 32,
- .imbalance_pct = 125,
-
- .cache_nice_tries = 0,
- .busy_idx = 0,
- .idle_idx = 0,
- .newidle_idx = 0,
- .wake_idx = 0,
- .forkexec_idx = 0,
-
- .flags = 1*SD_LOAD_BALANCE
- | 1*SD_BALANCE_NEWIDLE
- | 1*SD_BALANCE_EXEC
- | 1*SD_BALANCE_FORK
- | 0*SD_BALANCE_WAKE
- | 1*SD_WAKE_AFFINE
- | 0*SD_SHARE_CPUCAPACITY
- | 0*SD_SHARE_PKG_RESOURCES
- | 0*SD_SERIALIZE
- | 0*SD_PREFER_SIBLING
- | 0*SD_NUMA
- | sd_flags
- ,
-
- .last_balance = jiffies,
- .balance_interval = sd_weight,
- .smt_gain = 0,
- .max_newidle_lb_cost = 0,
- .next_decay_max_lb_cost = jiffies,
- .child = child,
-#ifdef CONFIG_SCHED_DEBUG
- .name = tl->name,
-#endif
- };
-
- cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
- sd_id = cpumask_first(sched_domain_span(sd));
-
- /*
- * Convert topological properties into behaviour.
- */
-
- if (sd->flags & SD_ASYM_CPUCAPACITY) {
- struct sched_domain *t = sd;
-
- for_each_lower_domain(t)
- t->flags |= SD_BALANCE_WAKE;
- }
-
- if (sd->flags & SD_SHARE_CPUCAPACITY) {
- sd->flags |= SD_PREFER_SIBLING;
- sd->imbalance_pct = 110;
- sd->smt_gain = 1178; /* ~15% */
-
- } else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
- sd->imbalance_pct = 117;
- sd->cache_nice_tries = 1;
- sd->busy_idx = 2;
-
-#ifdef CONFIG_NUMA
- } else if (sd->flags & SD_NUMA) {
- sd->cache_nice_tries = 2;
- sd->busy_idx = 3;
- sd->idle_idx = 2;
-
- sd->flags |= SD_SERIALIZE;
- if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
- sd->flags &= ~(SD_BALANCE_EXEC |
- SD_BALANCE_FORK |
- SD_WAKE_AFFINE);
- }
-
-#endif
- } else {
- sd->flags |= SD_PREFER_SIBLING;
- sd->cache_nice_tries = 1;
- sd->busy_idx = 2;
- sd->idle_idx = 1;
- }
-
- /*
- * For all levels sharing cache; connect a sched_domain_shared
- * instance.
- */
- if (sd->flags & SD_SHARE_PKG_RESOURCES) {
- sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
- atomic_inc(&sd->shared->ref);
- atomic_set(&sd->shared->nr_busy_cpus, sd_weight);
- }
-
- sd->private = sdd;
-
- return sd;
-}
-
-/*
- * Topology list, bottom-up.
- */
-static struct sched_domain_topology_level default_topology[] = {
-#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-#ifdef CONFIG_SCHED_MC
- { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
-#endif
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
- { NULL, },
-};
-
-static struct sched_domain_topology_level *sched_domain_topology =
- default_topology;
-
-#define for_each_sd_topology(tl) \
- for (tl = sched_domain_topology; tl->mask; tl++)
-
-void set_sched_topology(struct sched_domain_topology_level *tl)
-{
- if (WARN_ON_ONCE(sched_smp_initialized))
- return;
-
- sched_domain_topology = tl;
-}
-
-#ifdef CONFIG_NUMA
-
-static const struct cpumask *sd_numa_mask(int cpu)
-{
- return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
-}
-
-static void sched_numa_warn(const char *str)
-{
- static int done = false;
- int i,j;
-
- if (done)
- return;
-
- done = true;
-
- printk(KERN_WARNING "ERROR: %s\n\n", str);
-
- for (i = 0; i < nr_node_ids; i++) {
- printk(KERN_WARNING " ");
- for (j = 0; j < nr_node_ids; j++)
- printk(KERN_CONT "%02d ", node_distance(i,j));
- printk(KERN_CONT "\n");
- }
- printk(KERN_WARNING "\n");
-}
-
-bool find_numa_distance(int distance)
-{
- int i;
-
- if (distance == node_distance(0, 0))
- return true;
-
- for (i = 0; i < sched_domains_numa_levels; i++) {
- if (sched_domains_numa_distance[i] == distance)
- return true;
- }
-
- return false;
-}
-
-/*
- * A system can have three types of NUMA topology:
- * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
- * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes
- * NUMA_BACKPLANE: nodes can reach other nodes through a backplane
- *
- * The difference between a glueless mesh topology and a backplane
- * topology lies in whether communication between not directly
- * connected nodes goes through intermediary nodes (where programs
- * could run), or through backplane controllers. This affects
- * placement of programs.
- *
- * The type of topology can be discerned with the following tests:
- * - If the maximum distance between any nodes is 1 hop, the system
- * is directly connected.
- * - If for two nodes A and B, located N > 1 hops away from each other,
- * there is an intermediary node C, which is < N hops away from both
- * nodes A and B, the system is a glueless mesh.
- */
-static void init_numa_topology_type(void)
-{
- int a, b, c, n;
-
- n = sched_max_numa_distance;
-
- if (sched_domains_numa_levels <= 1) {
- sched_numa_topology_type = NUMA_DIRECT;
- return;
- }
-
- for_each_online_node(a) {
- for_each_online_node(b) {
- /* Find two nodes furthest removed from each other. */
- if (node_distance(a, b) < n)
- continue;
-
- /* Is there an intermediary node between a and b? */
- for_each_online_node(c) {
- if (node_distance(a, c) < n &&
- node_distance(b, c) < n) {
- sched_numa_topology_type =
- NUMA_GLUELESS_MESH;
- return;
- }
- }
-
- sched_numa_topology_type = NUMA_BACKPLANE;
- return;
- }
- }
-}
-
-static void sched_init_numa(void)
-{
- int next_distance, curr_distance = node_distance(0, 0);
- struct sched_domain_topology_level *tl;
- int level = 0;
- int i, j, k;
-
- sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
- if (!sched_domains_numa_distance)
- return;
-
- /*
- * O(nr_nodes^2) deduplicating selection sort -- in order to find the
- * unique distances in the node_distance() table.
- *
- * Assumes node_distance(0,j) includes all distances in
- * node_distance(i,j) in order to avoid cubic time.
- */
- next_distance = curr_distance;
- for (i = 0; i < nr_node_ids; i++) {
- for (j = 0; j < nr_node_ids; j++) {
- for (k = 0; k < nr_node_ids; k++) {
- int distance = node_distance(i, k);
-
- if (distance > curr_distance &&
- (distance < next_distance ||
- next_distance == curr_distance))
- next_distance = distance;
-
- /*
- * While not a strong assumption it would be nice to know
- * about cases where if node A is connected to B, B is not
- * equally connected to A.
- */
- if (sched_debug() && node_distance(k, i) != distance)
- sched_numa_warn("Node-distance not symmetric");
-
- if (sched_debug() && i && !find_numa_distance(distance))
- sched_numa_warn("Node-0 not representative");
- }
- if (next_distance != curr_distance) {
- sched_domains_numa_distance[level++] = next_distance;
- sched_domains_numa_levels = level;
- curr_distance = next_distance;
- } else break;
- }
-
- /*
- * In case of sched_debug() we verify the above assumption.
- */
- if (!sched_debug())
- break;
- }
-
- if (!level)
- return;
-
- /*
- * 'level' contains the number of unique distances, excluding the
- * identity distance node_distance(i,i).
- *
- * The sched_domains_numa_distance[] array includes the actual distance
- * numbers.
- */
-
- /*
- * Here, we should temporarily reset sched_domains_numa_levels to 0.
- * If it fails to allocate memory for array sched_domains_numa_masks[][],
- * the array will contain less then 'level' members. This could be
- * dangerous when we use it to iterate array sched_domains_numa_masks[][]
- * in other functions.
- *
- * We reset it to 'level' at the end of this function.
- */
- sched_domains_numa_levels = 0;
-
- sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
- if (!sched_domains_numa_masks)
- return;
-
- /*
- * Now for each level, construct a mask per node which contains all
- * cpus of nodes that are that many hops away from us.
- */
- for (i = 0; i < level; i++) {
- sched_domains_numa_masks[i] =
- kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
- if (!sched_domains_numa_masks[i])
- return;
-
- for (j = 0; j < nr_node_ids; j++) {
- struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
- if (!mask)
- return;
-
- sched_domains_numa_masks[i][j] = mask;
-
- for_each_node(k) {
- if (node_distance(j, k) > sched_domains_numa_distance[i])
- continue;
-
- cpumask_or(mask, mask, cpumask_of_node(k));
- }
- }
- }
-
- /* Compute default topology size */
- for (i = 0; sched_domain_topology[i].mask; i++);
-
- tl = kzalloc((i + level + 1) *
- sizeof(struct sched_domain_topology_level), GFP_KERNEL);
- if (!tl)
- return;
-
- /*
- * Copy the default topology bits..
- */
- for (i = 0; sched_domain_topology[i].mask; i++)
- tl[i] = sched_domain_topology[i];
-
- /*
- * .. and append 'j' levels of NUMA goodness.
- */
- for (j = 0; j < level; i++, j++) {
- tl[i] = (struct sched_domain_topology_level){
- .mask = sd_numa_mask,
- .sd_flags = cpu_numa_flags,
- .flags = SDTL_OVERLAP,
- .numa_level = j,
- SD_INIT_NAME(NUMA)
- };
- }
-
- sched_domain_topology = tl;
-
- sched_domains_numa_levels = level;
- sched_max_numa_distance = sched_domains_numa_distance[level - 1];
-
- init_numa_topology_type();
-}
-
-static void sched_domains_numa_masks_set(unsigned int cpu)
-{
- int node = cpu_to_node(cpu);
- int i, j;
-
- for (i = 0; i < sched_domains_numa_levels; i++) {
- for (j = 0; j < nr_node_ids; j++) {
- if (node_distance(j, node) <= sched_domains_numa_distance[i])
- cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
- }
- }
-}
-
-static void sched_domains_numa_masks_clear(unsigned int cpu)
-{
- int i, j;
-
- for (i = 0; i < sched_domains_numa_levels; i++) {
- for (j = 0; j < nr_node_ids; j++)
- cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
- }
-}
-
-#else
-static inline void sched_init_numa(void) { }
-static void sched_domains_numa_masks_set(unsigned int cpu) { }
-static void sched_domains_numa_masks_clear(unsigned int cpu) { }
-#endif /* CONFIG_NUMA */
-
-static int __sdt_alloc(const struct cpumask *cpu_map)
-{
- struct sched_domain_topology_level *tl;
- int j;
-
- for_each_sd_topology(tl) {
- struct sd_data *sdd = &tl->data;
-
- sdd->sd = alloc_percpu(struct sched_domain *);
- if (!sdd->sd)
- return -ENOMEM;
-
- sdd->sds = alloc_percpu(struct sched_domain_shared *);
- if (!sdd->sds)
- return -ENOMEM;
-
- sdd->sg = alloc_percpu(struct sched_group *);
- if (!sdd->sg)
- return -ENOMEM;
-
- sdd->sgc = alloc_percpu(struct sched_group_capacity *);
- if (!sdd->sgc)
- return -ENOMEM;
-
- for_each_cpu(j, cpu_map) {
- struct sched_domain *sd;
- struct sched_domain_shared *sds;
- struct sched_group *sg;
- struct sched_group_capacity *sgc;
-
- sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
- GFP_KERNEL, cpu_to_node(j));
- if (!sd)
- return -ENOMEM;
-
- *per_cpu_ptr(sdd->sd, j) = sd;
-
- sds = kzalloc_node(sizeof(struct sched_domain_shared),
- GFP_KERNEL, cpu_to_node(j));
- if (!sds)
- return -ENOMEM;
-
- *per_cpu_ptr(sdd->sds, j) = sds;
-
- sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
- GFP_KERNEL, cpu_to_node(j));
- if (!sg)
- return -ENOMEM;
-
- sg->next = sg;
-
- *per_cpu_ptr(sdd->sg, j) = sg;
-
- sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(),
- GFP_KERNEL, cpu_to_node(j));
- if (!sgc)
- return -ENOMEM;
-
- *per_cpu_ptr(sdd->sgc, j) = sgc;
- }
- }
-
- return 0;
-}
-
-static void __sdt_free(const struct cpumask *cpu_map)
-{
- struct sched_domain_topology_level *tl;
- int j;
-
- for_each_sd_topology(tl) {
- struct sd_data *sdd = &tl->data;
-
- for_each_cpu(j, cpu_map) {
- struct sched_domain *sd;
-
- if (sdd->sd) {
- sd = *per_cpu_ptr(sdd->sd, j);
- if (sd && (sd->flags & SD_OVERLAP))
- free_sched_groups(sd->groups, 0);
- kfree(*per_cpu_ptr(sdd->sd, j));
- }
-
- if (sdd->sds)
- kfree(*per_cpu_ptr(sdd->sds, j));
- if (sdd->sg)
- kfree(*per_cpu_ptr(sdd->sg, j));
- if (sdd->sgc)
- kfree(*per_cpu_ptr(sdd->sgc, j));
- }
- free_percpu(sdd->sd);
- sdd->sd = NULL;
- free_percpu(sdd->sds);
- sdd->sds = NULL;
- free_percpu(sdd->sg);
- sdd->sg = NULL;
- free_percpu(sdd->sgc);
- sdd->sgc = NULL;
- }
-}
-
-struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
- const struct cpumask *cpu_map, struct sched_domain_attr *attr,
- struct sched_domain *child, int cpu)
-{
- struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);
-
- if (child) {
- sd->level = child->level + 1;
- sched_domain_level_max = max(sched_domain_level_max, sd->level);
- child->parent = sd;
-
- if (!cpumask_subset(sched_domain_span(child),
- sched_domain_span(sd))) {
- pr_err("BUG: arch topology borken\n");
-#ifdef CONFIG_SCHED_DEBUG
- pr_err(" the %s domain not a subset of the %s domain\n",
- child->name, sd->name);
-#endif
- /* Fixup, ensure @sd has at least @child cpus. */
- cpumask_or(sched_domain_span(sd),
- sched_domain_span(sd),
- sched_domain_span(child));
- }
-
- }
- set_domain_attribute(sd, attr);
-
- return sd;
-}
-
-/*
- * Build sched domains for a given set of cpus and attach the sched domains
- * to the individual cpus
- */
-static int build_sched_domains(const struct cpumask *cpu_map,
- struct sched_domain_attr *attr)
-{
- enum s_alloc alloc_state;
- struct sched_domain *sd;
- struct s_data d;
- struct rq *rq = NULL;
- int i, ret = -ENOMEM;
-
- alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
- if (alloc_state != sa_rootdomain)
- goto error;
-
- /* Set up domains for cpus specified by the cpu_map. */
- for_each_cpu(i, cpu_map) {
- struct sched_domain_topology_level *tl;
-
- sd = NULL;
- for_each_sd_topology(tl) {
- sd = build_sched_domain(tl, cpu_map, attr, sd, i);
- if (tl == sched_domain_topology)
- *per_cpu_ptr(d.sd, i) = sd;
- if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
- sd->flags |= SD_OVERLAP;
- if (cpumask_equal(cpu_map, sched_domain_span(sd)))
- break;
- }
- }
-
- /* Build the groups for the domains */
- for_each_cpu(i, cpu_map) {
- for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
- sd->span_weight = cpumask_weight(sched_domain_span(sd));
- if (sd->flags & SD_OVERLAP) {
- if (build_overlap_sched_groups(sd, i))
- goto error;
- } else {
- if (build_sched_groups(sd, i))
- goto error;
- }
- }
- }
-
- /* Calculate CPU capacity for physical packages and nodes */
- for (i = nr_cpumask_bits-1; i >= 0; i--) {
- if (!cpumask_test_cpu(i, cpu_map))
- continue;
-
- for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
- claim_allocations(i, sd);
- init_sched_groups_capacity(i, sd);
- }
- }
-
- /* Attach the domains */
- rcu_read_lock();
- for_each_cpu(i, cpu_map) {
- rq = cpu_rq(i);
- sd = *per_cpu_ptr(d.sd, i);
-
- /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
- if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
- WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
-
- cpu_attach_domain(sd, d.rd, i);
- }
- rcu_read_unlock();
-
- if (rq && sched_debug_enabled) {
- pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
- cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
- }
-
- ret = 0;
-error:
- __free_domain_allocs(&d, alloc_state, cpu_map);
- return ret;
-}
-
-static cpumask_var_t *doms_cur; /* current sched domains */
-static int ndoms_cur; /* number of sched domains in 'doms_cur' */
-static struct sched_domain_attr *dattr_cur;
- /* attribues of custom domains in 'doms_cur' */
-
-/*
- * Special case: If a kmalloc of a doms_cur partition (array of
- * cpumask) fails, then fallback to a single sched domain,
- * as determined by the single cpumask fallback_doms.
- */
-static cpumask_var_t fallback_doms;
-
-/*
- * arch_update_cpu_topology lets virtualized architectures update the
- * cpu core maps. It is supposed to return 1 if the topology changed
- * or 0 if it stayed the same.
- */
-int __weak arch_update_cpu_topology(void)
-{
- return 0;
-}
-
-cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
-{
- int i;
- cpumask_var_t *doms;
-
- doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
- if (!doms)
- return NULL;
- for (i = 0; i < ndoms; i++) {
- if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
- free_sched_domains(doms, i);
- return NULL;
- }
- }
- return doms;
-}
-
-void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
-{
- unsigned int i;
- for (i = 0; i < ndoms; i++)
- free_cpumask_var(doms[i]);
- kfree(doms);
-}
-
-/*
- * Set up scheduler domains and groups. Callers must hold the hotplug lock.
- * For now this just excludes isolated cpus, but could be used to
- * exclude other special cases in the future.
- */
-static int init_sched_domains(const struct cpumask *cpu_map)
-{
- int err;
-
- arch_update_cpu_topology();
- ndoms_cur = 1;
- doms_cur = alloc_sched_domains(ndoms_cur);
- if (!doms_cur)
- doms_cur = &fallback_doms;
- cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
- err = build_sched_domains(doms_cur[0], NULL);
- register_sched_domain_sysctl();
-
- return err;
-}
-
-/*
- * Detach sched domains from a group of cpus specified in cpu_map
- * These cpus will now be attached to the NULL domain
- */
-static void detach_destroy_domains(const struct cpumask *cpu_map)
-{
- int i;
-
- rcu_read_lock();
- for_each_cpu(i, cpu_map)
- cpu_attach_domain(NULL, &def_root_domain, i);
- rcu_read_unlock();
-}
-
-/* handle null as "default" */
-static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
- struct sched_domain_attr *new, int idx_new)
-{
- struct sched_domain_attr tmp;
-
- /* fast path */
- if (!new && !cur)
- return 1;
-
- tmp = SD_ATTR_INIT;
- return !memcmp(cur ? (cur + idx_cur) : &tmp,
- new ? (new + idx_new) : &tmp,
- sizeof(struct sched_domain_attr));
-}
-
-/*
- * Partition sched domains as specified by the 'ndoms_new'
- * cpumasks in the array doms_new[] of cpumasks. This compares
- * doms_new[] to the current sched domain partitioning, doms_cur[].
- * It destroys each deleted domain and builds each new domain.
- *
- * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
- * The masks don't intersect (don't overlap.) We should setup one
- * sched domain for each mask. CPUs not in any of the cpumasks will
- * not be load balanced. If the same cpumask appears both in the
- * current 'doms_cur' domains and in the new 'doms_new', we can leave
- * it as it is.
- *
- * The passed in 'doms_new' should be allocated using
- * alloc_sched_domains. This routine takes ownership of it and will
- * free_sched_domains it when done with it. If the caller failed the
- * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
- * and partition_sched_domains() will fallback to the single partition
- * 'fallback_doms', it also forces the domains to be rebuilt.
- *
- * If doms_new == NULL it will be replaced with cpu_online_mask.
- * ndoms_new == 0 is a special case for destroying existing domains,
- * and it will not create the default domain.
- *
- * Call with hotplug lock held
- */
-void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
- struct sched_domain_attr *dattr_new)
-{
- int i, j, n;
- int new_topology;
-
- mutex_lock(&sched_domains_mutex);
-
- /* always unregister in case we don't destroy any domains */
- unregister_sched_domain_sysctl();
-
- /* Let architecture update cpu core mappings. */
- new_topology = arch_update_cpu_topology();
-
- n = doms_new ? ndoms_new : 0;
-
- /* Destroy deleted domains */
- for (i = 0; i < ndoms_cur; i++) {
- for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(doms_cur[i], doms_new[j])
- && dattrs_equal(dattr_cur, i, dattr_new, j))
- goto match1;
- }
- /* no match - a current sched domain not in new doms_new[] */
- detach_destroy_domains(doms_cur[i]);
-match1:
- ;
- }
-
- n = ndoms_cur;
- if (doms_new == NULL) {
- n = 0;
- doms_new = &fallback_doms;
- cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
- WARN_ON_ONCE(dattr_new);
- }
-
- /* Build new domains */
- for (i = 0; i < ndoms_new; i++) {
- for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(doms_new[i], doms_cur[j])
- && dattrs_equal(dattr_new, i, dattr_cur, j))
- goto match2;
- }
- /* no match - add a new doms_new */
- build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
-match2:
- ;
- }
-
- /* Remember the new sched domains */
- if (doms_cur != &fallback_doms)
- free_sched_domains(doms_cur, ndoms_cur);
- kfree(dattr_cur); /* kfree(NULL) is safe */
- doms_cur = doms_new;
- dattr_cur = dattr_new;
- ndoms_cur = ndoms_new;
-
- register_sched_domain_sysctl();
-
- mutex_unlock(&sched_domains_mutex);
-}
-
-static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */
+static int num_cpus_frozen;
/*
* Update cpusets according to cpu_active mask. If cpusets are
@@ -7352,7 +5759,7 @@
* Put the rq online, if not already. This happens:
*
* 1) In the early boot process, because we build the real domains
- * after all cpus have been brought up.
+ * after all CPUs have been brought up.
*
* 2) At runtime, if cpuset_cpu_active() fails to rebuild the
* domains.
@@ -7467,7 +5874,7 @@
/*
* There's no userspace yet to cause hotplug operations; hence all the
- * cpu masks are stable and all blatant races in the below code cannot
+ * CPU masks are stable and all blatant races in the below code cannot
* happen.
*/
mutex_lock(&sched_domains_mutex);
@@ -7487,6 +5894,7 @@
init_sched_dl_class();
sched_init_smt();
+ sched_clock_init_late();
sched_smp_initialized = true;
}
@@ -7502,6 +5910,7 @@
void __init sched_init_smp(void)
{
sched_init_granularity();
+ sched_clock_init_late();
}
#endif /* CONFIG_SMP */
@@ -7545,6 +5954,8 @@
int i, j;
unsigned long alloc_size = 0, ptr;
+ sched_clock_init();
+
for (i = 0; i < WAIT_TABLE_SIZE; i++)
init_waitqueue_head(bit_wait_table + i);
@@ -7583,10 +5994,8 @@
}
#endif /* CONFIG_CPUMASK_OFFSTACK */
- init_rt_bandwidth(&def_rt_bandwidth,
- global_rt_period(), global_rt_runtime());
- init_dl_bandwidth(&def_dl_bandwidth,
- global_rt_period(), global_rt_runtime());
+ init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
+ init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime());
#ifdef CONFIG_SMP
init_defrootdomain();
@@ -7622,18 +6031,18 @@
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
/*
- * How much cpu bandwidth does root_task_group get?
+ * How much CPU bandwidth does root_task_group get?
*
* In case of task-groups formed thr' the cgroup filesystem, it
- * gets 100% of the cpu resources in the system. This overall
- * system cpu resource is divided among the tasks of
+ * gets 100% of the CPU resources in the system. This overall
+ * system CPU resource is divided among the tasks of
* root_task_group and its child task-groups in a fair manner,
* based on each entity's (task or task-group's) weight
* (se->load.weight).
*
* In other words, if root_task_group has 10 tasks of weight
* 1024) and two child groups A0 and A1 (of weight 1024 each),
- * then A0's share of the cpu resource is:
+ * then A0's share of the CPU resource is:
*
* A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
*
@@ -7742,10 +6151,14 @@
void ___might_sleep(const char *file, int line, int preempt_offset)
{
- static unsigned long prev_jiffy; /* ratelimiting */
+ /* Ratelimiting timestamp: */
+ static unsigned long prev_jiffy;
+
unsigned long preempt_disable_ip;
- rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
+ /* WARN_ON_ONCE() by default, no rate limit required: */
+ rcu_sleep_check();
+
if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
!is_idle_task(current)) ||
system_state != SYSTEM_RUNNING || oops_in_progress)
@@ -7754,7 +6167,7 @@
return;
prev_jiffy = jiffies;
- /* Save this before calling printk(), since that will clobber it */
+ /* Save this before calling printk(), since that will clobber it: */
preempt_disable_ip = get_preempt_disable_ip(current);
printk(KERN_ERR
@@ -7833,7 +6246,7 @@
*/
/**
- * curr_task - return the current task for a given cpu.
+ * curr_task - return the current task for a given CPU.
* @cpu: the processor in question.
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
@@ -7849,13 +6262,13 @@
#ifdef CONFIG_IA64
/**
- * set_curr_task - set the current task for a given cpu.
+ * set_curr_task - set the current task for a given CPU.
* @cpu: the processor in question.
* @p: the task pointer to set.
*
* Description: This function must only be used when non-maskable interrupts
* are serviced on a separate stack. It allows the architecture to switch the
- * notion of the current task on a cpu in a non-blocking manner. This function
+ * notion of the current task on a CPU in a non-blocking manner. This function
* must be called with all CPU's synchronized, and interrupts disabled, the
* and caller must save the original value of the current task (see
* curr_task() above) and restore that value before reenabling interrupts and
@@ -7911,7 +6324,8 @@
spin_lock_irqsave(&task_group_lock, flags);
list_add_rcu(&tg->list, &task_groups);
- WARN_ON(!parent); /* root should already exist */
+ /* Root should already exist: */
+ WARN_ON(!parent);
tg->parent = parent;
INIT_LIST_HEAD(&tg->children);
@@ -7924,13 +6338,13 @@
/* rcu callback to free various structures associated with a task group */
static void sched_free_group_rcu(struct rcu_head *rhp)
{
- /* now it should be safe to free those cfs_rqs */
+ /* Now it should be safe to free those cfs_rqs: */
sched_free_group(container_of(rhp, struct task_group, rcu));
}
void sched_destroy_group(struct task_group *tg)
{
- /* wait for possible concurrent references to cfs_rqs complete */
+ /* Wait for possible concurrent references to cfs_rqs complete: */
call_rcu(&tg->rcu, sched_free_group_rcu);
}
@@ -7938,7 +6352,7 @@
{
unsigned long flags;
- /* end participation in shares distribution */
+ /* End participation in shares distribution: */
unregister_fair_sched_group(tg);
spin_lock_irqsave(&task_group_lock, flags);
@@ -7983,20 +6397,21 @@
struct rq *rq;
rq = task_rq_lock(tsk, &rf);
+ update_rq_clock(rq);
running = task_current(rq, tsk);
queued = task_on_rq_queued(tsk);
if (queued)
dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
- if (unlikely(running))
+ if (running)
put_prev_task(rq, tsk);
sched_change_group(tsk, TASK_MOVE_GROUP);
if (queued)
enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE);
- if (unlikely(running))
+ if (running)
set_curr_task(rq, tsk);
task_rq_unlock(rq, tsk, &rf);
@@ -8366,11 +6781,14 @@
mutex_lock(&mutex);
ret = proc_dointvec(table, write, buffer, lenp, ppos);
- /* make sure that internally we keep jiffies */
- /* also, writing zero resets timeslice to default */
+ /*
+ * Make sure that internally we keep jiffies.
+ * Also, writing zero resets the timeslice to default:
+ */
if (!ret && write) {
- sched_rr_timeslice = sched_rr_timeslice <= 0 ?
- RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+ sched_rr_timeslice =
+ sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
+ msecs_to_jiffies(sysctl_sched_rr_timeslice);
}
mutex_unlock(&mutex);
return ret;
@@ -8431,6 +6849,7 @@
rq = task_rq_lock(task, &rf);
+ update_rq_clock(rq);
sched_change_group(task, TASK_SET_GROUP);
task_rq_unlock(rq, task, &rf);
@@ -8550,9 +6969,11 @@
cfs_b->quota = quota;
__refill_cfs_bandwidth_runtime(cfs_b);
- /* restart the period timer (if active) to handle new period expiry */
+
+ /* Restart the period timer (if active) to handle new period expiry: */
if (runtime_enabled)
start_cfs_bandwidth(cfs_b);
+
raw_spin_unlock_irq(&cfs_b->lock);
for_each_online_cpu(i) {
@@ -8690,8 +7111,8 @@
parent_quota = parent_b->hierarchical_quota;
/*
- * ensure max(child_quota) <= parent_quota, inherit when no
- * limit is set
+ * Ensure max(child_quota) <= parent_quota, inherit when no
+ * limit is set:
*/
if (quota == RUNTIME_INF)
quota = parent_quota;
@@ -8800,7 +7221,7 @@
.write_u64 = cpu_rt_period_write_uint,
},
#endif
- { } /* terminate */
+ { } /* Terminate */
};
struct cgroup_subsys cpu_cgrp_subsys = {
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 9add206..f95ab29 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -297,7 +297,7 @@
for (stat = 0; stat < CPUACCT_STAT_NSTATS; stat++) {
seq_printf(sf, "%s %lld\n",
cpuacct_stat_desc[stat],
- (long long)cputime64_to_clock_t(val[stat]));
+ (long long)nsec_to_clock_t(val[stat]));
}
return 0;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 7700a9c..2ecec3a 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -4,6 +4,7 @@
#include <linux/kernel_stat.h>
#include <linux/static_key.h>
#include <linux/context_tracking.h>
+#include <linux/cputime.h>
#include "sched.h"
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
@@ -44,6 +45,7 @@
void irqtime_account_irq(struct task_struct *curr)
{
struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
s64 delta;
int cpu;
@@ -61,49 +63,34 @@
* in that case, so as not to confuse scheduler with a special task
* that do not consume any time, but still wants to run.
*/
- if (hardirq_count())
- irqtime->hardirq_time += delta;
- else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
- irqtime->softirq_time += delta;
+ if (hardirq_count()) {
+ cpustat[CPUTIME_IRQ] += delta;
+ irqtime->tick_delta += delta;
+ } else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) {
+ cpustat[CPUTIME_SOFTIRQ] += delta;
+ irqtime->tick_delta += delta;
+ }
u64_stats_update_end(&irqtime->sync);
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
-static cputime_t irqtime_account_update(u64 irqtime, int idx, cputime_t maxtime)
+static u64 irqtime_tick_accounted(u64 maxtime)
{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
- cputime_t irq_cputime;
+ struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+ u64 delta;
- irq_cputime = nsecs_to_cputime64(irqtime) - cpustat[idx];
- irq_cputime = min(irq_cputime, maxtime);
- cpustat[idx] += irq_cputime;
+ delta = min(irqtime->tick_delta, maxtime);
+ irqtime->tick_delta -= delta;
- return irq_cputime;
-}
-
-static cputime_t irqtime_account_hi_update(cputime_t maxtime)
-{
- return irqtime_account_update(__this_cpu_read(cpu_irqtime.hardirq_time),
- CPUTIME_IRQ, maxtime);
-}
-
-static cputime_t irqtime_account_si_update(cputime_t maxtime)
-{
- return irqtime_account_update(__this_cpu_read(cpu_irqtime.softirq_time),
- CPUTIME_SOFTIRQ, maxtime);
+ return delta;
}
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
#define sched_clock_irqtime (0)
-static cputime_t irqtime_account_hi_update(cputime_t dummy)
-{
- return 0;
-}
-
-static cputime_t irqtime_account_si_update(cputime_t dummy)
+static u64 irqtime_tick_accounted(u64 dummy)
{
return 0;
}
@@ -129,7 +116,7 @@
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in user space since the last update
*/
-void account_user_time(struct task_struct *p, cputime_t cputime)
+void account_user_time(struct task_struct *p, u64 cputime)
{
int index;
@@ -140,7 +127,7 @@
index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
/* Add user time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
+ task_group_account_field(p, index, cputime);
/* Account for user time used */
acct_account_cputime(p);
@@ -151,7 +138,7 @@
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in virtual machine since the last update
*/
-static void account_guest_time(struct task_struct *p, cputime_t cputime)
+void account_guest_time(struct task_struct *p, u64 cputime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
@@ -162,11 +149,11 @@
/* Add guest time to cpustat. */
if (task_nice(p) > 0) {
- cpustat[CPUTIME_NICE] += (__force u64) cputime;
- cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
+ cpustat[CPUTIME_NICE] += cputime;
+ cpustat[CPUTIME_GUEST_NICE] += cputime;
} else {
- cpustat[CPUTIME_USER] += (__force u64) cputime;
- cpustat[CPUTIME_GUEST] += (__force u64) cputime;
+ cpustat[CPUTIME_USER] += cputime;
+ cpustat[CPUTIME_GUEST] += cputime;
}
}
@@ -176,15 +163,15 @@
* @cputime: the cpu time spent in kernel space since the last update
* @index: pointer to cpustat field that has to be updated
*/
-static inline
-void __account_system_time(struct task_struct *p, cputime_t cputime, int index)
+void account_system_index_time(struct task_struct *p,
+ u64 cputime, enum cpu_usage_stat index)
{
/* Add system time to process. */
p->stime += cputime;
account_group_system_time(p, cputime);
/* Add system time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
+ task_group_account_field(p, index, cputime);
/* Account for system time used */
acct_account_cputime(p);
@@ -196,8 +183,7 @@
* @hardirq_offset: the offset to subtract from hardirq_count()
* @cputime: the cpu time spent in kernel space since the last update
*/
-void account_system_time(struct task_struct *p, int hardirq_offset,
- cputime_t cputime)
+void account_system_time(struct task_struct *p, int hardirq_offset, u64 cputime)
{
int index;
@@ -213,33 +199,33 @@
else
index = CPUTIME_SYSTEM;
- __account_system_time(p, cputime, index);
+ account_system_index_time(p, cputime, index);
}
/*
* Account for involuntary wait time.
* @cputime: the cpu time spent in involuntary wait
*/
-void account_steal_time(cputime_t cputime)
+void account_steal_time(u64 cputime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
- cpustat[CPUTIME_STEAL] += (__force u64) cputime;
+ cpustat[CPUTIME_STEAL] += cputime;
}
/*
* Account for idle time.
* @cputime: the cpu time spent in idle wait
*/
-void account_idle_time(cputime_t cputime)
+void account_idle_time(u64 cputime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
struct rq *rq = this_rq();
if (atomic_read(&rq->nr_iowait) > 0)
- cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
+ cpustat[CPUTIME_IOWAIT] += cputime;
else
- cpustat[CPUTIME_IDLE] += (__force u64) cputime;
+ cpustat[CPUTIME_IDLE] += cputime;
}
/*
@@ -247,21 +233,19 @@
* ticks are not redelivered later. Due to that, this function may on
* occasion account more time than the calling functions think elapsed.
*/
-static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
+static __always_inline u64 steal_account_process_time(u64 maxtime)
{
#ifdef CONFIG_PARAVIRT
if (static_key_false(¶virt_steal_enabled)) {
- cputime_t steal_cputime;
u64 steal;
steal = paravirt_steal_clock(smp_processor_id());
steal -= this_rq()->prev_steal_time;
+ steal = min(steal, maxtime);
+ account_steal_time(steal);
+ this_rq()->prev_steal_time += steal;
- steal_cputime = min(nsecs_to_cputime(steal), maxtime);
- account_steal_time(steal_cputime);
- this_rq()->prev_steal_time += cputime_to_nsecs(steal_cputime);
-
- return steal_cputime;
+ return steal;
}
#endif
return 0;
@@ -270,9 +254,9 @@
/*
* Account how much elapsed time was spent in steal, irq, or softirq time.
*/
-static inline cputime_t account_other_time(cputime_t max)
+static inline u64 account_other_time(u64 max)
{
- cputime_t accounted;
+ u64 accounted;
/* Shall be converted to a lockdep-enabled lightweight check */
WARN_ON_ONCE(!irqs_disabled());
@@ -280,10 +264,7 @@
accounted = steal_account_process_time(max);
if (accounted < max)
- accounted += irqtime_account_hi_update(max - accounted);
-
- if (accounted < max)
- accounted += irqtime_account_si_update(max - accounted);
+ accounted += irqtime_tick_accounted(max - accounted);
return accounted;
}
@@ -315,7 +296,7 @@
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
{
struct signal_struct *sig = tsk->signal;
- cputime_t utime, stime;
+ u64 utime, stime;
struct task_struct *t;
unsigned int seq, nextseq;
unsigned long flags;
@@ -379,8 +360,7 @@
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
struct rq *rq, int ticks)
{
- u64 cputime = (__force u64) cputime_one_jiffy * ticks;
- cputime_t other;
+ u64 other, cputime = TICK_NSEC * ticks;
/*
* When returning from idle, many ticks can get accounted at
@@ -392,6 +372,7 @@
other = account_other_time(ULONG_MAX);
if (other >= cputime)
return;
+
cputime -= other;
if (this_cpu_ksoftirqd() == p) {
@@ -400,7 +381,7 @@
* So, we have to handle it separately here.
* Also, p->stime needs to be updated for ksoftirqd.
*/
- __account_system_time(p, cputime, CPUTIME_SOFTIRQ);
+ account_system_index_time(p, cputime, CPUTIME_SOFTIRQ);
} else if (user_tick) {
account_user_time(p, cputime);
} else if (p == rq->idle) {
@@ -408,7 +389,7 @@
} else if (p->flags & PF_VCPU) { /* System time or guest time */
account_guest_time(p, cputime);
} else {
- __account_system_time(p, cputime, CPUTIME_SYSTEM);
+ account_system_index_time(p, cputime, CPUTIME_SYSTEM);
}
}
@@ -437,9 +418,7 @@
else
vtime_account_system(prev);
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- vtime_account_user(prev);
-#endif
+ vtime_flush(prev);
arch_vtime_task_switch(prev);
}
#endif
@@ -467,14 +446,14 @@
EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
#endif /* __ARCH_HAS_VTIME_ACCOUNT */
-void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
{
*ut = p->utime;
*st = p->stime;
}
EXPORT_SYMBOL_GPL(task_cputime_adjusted);
-void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
{
struct task_cputime cputime;
@@ -491,7 +470,7 @@
*/
void account_process_tick(struct task_struct *p, int user_tick)
{
- cputime_t cputime, steal;
+ u64 cputime, steal;
struct rq *rq = this_rq();
if (vtime_accounting_cpu_enabled())
@@ -502,7 +481,7 @@
return;
}
- cputime = cputime_one_jiffy;
+ cputime = TICK_NSEC;
steal = steal_account_process_time(ULONG_MAX);
if (steal >= cputime)
@@ -524,14 +503,14 @@
*/
void account_idle_ticks(unsigned long ticks)
{
- cputime_t cputime, steal;
+ u64 cputime, steal;
if (sched_clock_irqtime) {
irqtime_account_idle_ticks(ticks);
return;
}
- cputime = jiffies_to_cputime(ticks);
+ cputime = ticks * TICK_NSEC;
steal = steal_account_process_time(ULONG_MAX);
if (steal >= cputime)
@@ -545,7 +524,7 @@
* Perform (stime * rtime) / total, but avoid multiplication overflow by
* loosing precision when the numbers are big.
*/
-static cputime_t scale_stime(u64 stime, u64 rtime, u64 total)
+static u64 scale_stime(u64 stime, u64 rtime, u64 total)
{
u64 scaled;
@@ -582,7 +561,7 @@
* followed by a 64/32->64 divide.
*/
scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
- return (__force cputime_t) scaled;
+ return scaled;
}
/*
@@ -607,14 +586,14 @@
*/
static void cputime_adjust(struct task_cputime *curr,
struct prev_cputime *prev,
- cputime_t *ut, cputime_t *st)
+ u64 *ut, u64 *st)
{
- cputime_t rtime, stime, utime;
+ u64 rtime, stime, utime;
unsigned long flags;
/* Serialize concurrent callers such that we can honour our guarantees */
raw_spin_lock_irqsave(&prev->lock, flags);
- rtime = nsecs_to_cputime(curr->sum_exec_runtime);
+ rtime = curr->sum_exec_runtime;
/*
* This is possible under two circumstances:
@@ -645,8 +624,7 @@
goto update;
}
- stime = scale_stime((__force u64)stime, (__force u64)rtime,
- (__force u64)(stime + utime));
+ stime = scale_stime(stime, rtime, stime + utime);
update:
/*
@@ -679,7 +657,7 @@
raw_spin_unlock_irqrestore(&prev->lock, flags);
}
-void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
{
struct task_cputime cputime = {
.sum_exec_runtime = p->se.sum_exec_runtime,
@@ -690,7 +668,7 @@
}
EXPORT_SYMBOL_GPL(task_cputime_adjusted);
-void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
{
struct task_cputime cputime;
@@ -700,20 +678,20 @@
#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-static cputime_t vtime_delta(struct task_struct *tsk)
+static u64 vtime_delta(struct task_struct *tsk)
{
unsigned long now = READ_ONCE(jiffies);
if (time_before(now, (unsigned long)tsk->vtime_snap))
return 0;
- return jiffies_to_cputime(now - tsk->vtime_snap);
+ return jiffies_to_nsecs(now - tsk->vtime_snap);
}
-static cputime_t get_vtime_delta(struct task_struct *tsk)
+static u64 get_vtime_delta(struct task_struct *tsk)
{
unsigned long now = READ_ONCE(jiffies);
- cputime_t delta, other;
+ u64 delta, other;
/*
* Unlike tick based timing, vtime based timing never has lost
@@ -722,7 +700,7 @@
* elapsed time. Limit account_other_time to prevent rounding
* errors from causing elapsed vtime to go negative.
*/
- delta = jiffies_to_cputime(now - tsk->vtime_snap);
+ delta = jiffies_to_nsecs(now - tsk->vtime_snap);
other = account_other_time(delta);
WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
tsk->vtime_snap = now;
@@ -732,9 +710,7 @@
static void __vtime_account_system(struct task_struct *tsk)
{
- cputime_t delta_cpu = get_vtime_delta(tsk);
-
- account_system_time(tsk, irq_count(), delta_cpu);
+ account_system_time(tsk, irq_count(), get_vtime_delta(tsk));
}
void vtime_account_system(struct task_struct *tsk)
@@ -749,14 +725,10 @@
void vtime_account_user(struct task_struct *tsk)
{
- cputime_t delta_cpu;
-
write_seqcount_begin(&tsk->vtime_seqcount);
tsk->vtime_snap_whence = VTIME_SYS;
- if (vtime_delta(tsk)) {
- delta_cpu = get_vtime_delta(tsk);
- account_user_time(tsk, delta_cpu);
- }
+ if (vtime_delta(tsk))
+ account_user_time(tsk, get_vtime_delta(tsk));
write_seqcount_end(&tsk->vtime_seqcount);
}
@@ -797,9 +769,7 @@
void vtime_account_idle(struct task_struct *tsk)
{
- cputime_t delta_cpu = get_vtime_delta(tsk);
-
- account_idle_time(delta_cpu);
+ account_idle_time(get_vtime_delta(tsk));
}
void arch_vtime_task_switch(struct task_struct *prev)
@@ -826,10 +796,10 @@
local_irq_restore(flags);
}
-cputime_t task_gtime(struct task_struct *t)
+u64 task_gtime(struct task_struct *t)
{
unsigned int seq;
- cputime_t gtime;
+ u64 gtime;
if (!vtime_accounting_enabled())
return t->gtime;
@@ -851,9 +821,9 @@
* add up the pending nohz execution time since the last
* cputime snapshot.
*/
-void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
+void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
{
- cputime_t delta;
+ u64 delta;
unsigned int seq;
if (!vtime_accounting_enabled()) {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 70ef2b1..27737f3 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -663,9 +663,9 @@
* Nothing relies on rq->lock after this, so its safe to drop
* rq->lock.
*/
- lockdep_unpin_lock(&rq->lock, rf.cookie);
+ rq_unpin_lock(rq, &rf);
push_dl_task(rq);
- lockdep_repin_lock(&rq->lock, rf.cookie);
+ rq_repin_lock(rq, &rf);
}
#endif
@@ -1118,7 +1118,7 @@
}
struct task_struct *
-pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct sched_dl_entity *dl_se;
struct task_struct *p;
@@ -1133,9 +1133,9 @@
* disabled avoiding further scheduler activity on it and we're
* being very careful to re-start the picking loop.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
pull_dl_task(rq);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
/*
* pull_dl_task() can drop (and re-acquire) rq->lock; this
* means a stop task can slip in, in which case we need to
@@ -1729,12 +1729,11 @@
#ifdef CONFIG_SMP
if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded)
queue_push_tasks(rq);
-#else
+#endif
if (dl_task(rq->curr))
check_preempt_curr_dl(rq, p, 0);
else
resched_curr(rq);
-#endif
}
}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index fa178b6..109adc0 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -953,6 +953,10 @@
#endif
P(policy);
P(prio);
+ if (p->policy == SCHED_DEADLINE) {
+ P(dl.runtime);
+ P(dl.deadline);
+ }
#undef PN_SCHEDSTAT
#undef PN
#undef __PN
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6559d19..274c747 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2657,6 +2657,18 @@
if (tg_weight)
shares /= tg_weight;
+ /*
+ * MIN_SHARES has to be unscaled here to support per-CPU partitioning
+ * of a group with small tg->shares value. It is a floor value which is
+ * assigned as a minimum load.weight to the sched_entity representing
+ * the group on a CPU.
+ *
+ * E.g. on 64-bit for a group with tg->shares of scale_load(15)=15*1024
+ * on an 8-core system with 8 tasks each runnable on one CPU shares has
+ * to be 15*1024*1/8=1920 instead of scale_load(MIN_SHARES)=2*1024. In
+ * case no task is runnable on a CPU MIN_SHARES=2 should be returned
+ * instead of 0.
+ */
if (shares < MIN_SHARES)
shares = MIN_SHARES;
if (shares > tg->shares)
@@ -2689,16 +2701,20 @@
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
-static void update_cfs_shares(struct cfs_rq *cfs_rq)
+static void update_cfs_shares(struct sched_entity *se)
{
+ struct cfs_rq *cfs_rq = group_cfs_rq(se);
struct task_group *tg;
- struct sched_entity *se;
long shares;
- tg = cfs_rq->tg;
- se = tg->se[cpu_of(rq_of(cfs_rq))];
- if (!se || throttled_hierarchy(cfs_rq))
+ if (!cfs_rq)
return;
+
+ if (throttled_hierarchy(cfs_rq))
+ return;
+
+ tg = cfs_rq->tg;
+
#ifndef CONFIG_SMP
if (likely(se->load.weight == tg->shares))
return;
@@ -2707,8 +2723,9 @@
reweight_entity(cfs_rq_of(se), se, shares);
}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
+static inline void update_cfs_shares(struct sched_entity *se)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -3424,7 +3441,7 @@
return cfs_rq->avg.load_avg;
}
-static int idle_balance(struct rq *this_rq);
+static int idle_balance(struct rq *this_rq, struct rq_flags *rf);
#else /* CONFIG_SMP */
@@ -3453,7 +3470,7 @@
static inline void
detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
-static inline int idle_balance(struct rq *rq)
+static inline int idle_balance(struct rq *rq, struct rq_flags *rf)
{
return 0;
}
@@ -3582,10 +3599,18 @@
if (renorm && !curr)
se->vruntime += cfs_rq->min_vruntime;
+ /*
+ * When enqueuing a sched_entity, we must:
+ * - Update loads to have both entity and cfs_rq synced with now.
+ * - Add its load to cfs_rq->runnable_avg
+ * - For group_entity, update its weight to reflect the new share of
+ * its group cfs_rq
+ * - Add its new weight to cfs_rq->load.weight
+ */
update_load_avg(se, UPDATE_TG);
enqueue_entity_load_avg(cfs_rq, se);
+ update_cfs_shares(se);
account_entity_enqueue(cfs_rq, se);
- update_cfs_shares(cfs_rq);
if (flags & ENQUEUE_WAKEUP)
place_entity(cfs_rq, se, 0);
@@ -3657,6 +3682,15 @@
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+
+ /*
+ * When dequeuing a sched_entity, we must:
+ * - Update loads to have both entity and cfs_rq synced with now.
+ * - Substract its load from the cfs_rq->runnable_avg.
+ * - Substract its previous weight from cfs_rq->load.weight.
+ * - For group entity, update its weight to reflect the new share
+ * of its group cfs_rq.
+ */
update_load_avg(se, UPDATE_TG);
dequeue_entity_load_avg(cfs_rq, se);
@@ -3681,7 +3715,7 @@
/* return excess runtime on last dequeue */
return_cfs_rq_runtime(cfs_rq);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(se);
/*
* Now advance min_vruntime if @se was the entity holding it back,
@@ -3864,7 +3898,7 @@
* Ensure that runnable average is periodically updated.
*/
update_load_avg(curr, UPDATE_TG);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(curr);
#ifdef CONFIG_SCHED_HRTICK
/*
@@ -4761,7 +4795,7 @@
break;
update_load_avg(se, UPDATE_TG);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(se);
}
if (!se)
@@ -4820,7 +4854,7 @@
break;
update_load_avg(se, UPDATE_TG);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(se);
}
if (!se)
@@ -6213,7 +6247,7 @@
}
static struct task_struct *
-pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
@@ -6320,15 +6354,8 @@
return p;
idle:
- /*
- * This is OK, because current is on_cpu, which avoids it being picked
- * for load-balance and preemption/IRQs are still disabled avoiding
- * further scheduler activity on it and we're being very careful to
- * re-start the picking loop.
- */
- lockdep_unpin_lock(&rq->lock, cookie);
- new_tasks = idle_balance(rq);
- lockdep_repin_lock(&rq->lock, cookie);
+ new_tasks = idle_balance(rq, rf);
+
/*
* Because idle_balance() releases (and re-acquires) rq->lock, it is
* possible for any higher priority task to appear. In that case we
@@ -8077,6 +8104,7 @@
more_balance:
raw_spin_lock_irqsave(&busiest->lock, flags);
+ update_rq_clock(busiest);
/*
* cur_ld_moved - load moved in current iteration
@@ -8297,7 +8325,7 @@
* idle_balance is called by schedule() if this_cpu is about to become
* idle. Attempts to pull tasks from other CPUs.
*/
-static int idle_balance(struct rq *this_rq)
+static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
{
unsigned long next_balance = jiffies + HZ;
int this_cpu = this_rq->cpu;
@@ -8311,6 +8339,14 @@
*/
this_rq->idle_stamp = rq_clock(this_rq);
+ /*
+ * This is OK, because current is on_cpu, which avoids it being picked
+ * for load-balance and preemption/IRQs are still disabled avoiding
+ * further scheduler activity on it and we're being very careful to
+ * re-start the picking loop.
+ */
+ rq_unpin_lock(this_rq, rf);
+
if (this_rq->avg_idle < sysctl_sched_migration_cost ||
!this_rq->rd->overload) {
rcu_read_lock();
@@ -8388,6 +8424,8 @@
if (pulled_task)
this_rq->idle_stamp = 0;
+ rq_repin_lock(this_rq, rf);
+
return pulled_task;
}
@@ -8443,6 +8481,7 @@
};
schedstat_inc(sd->alb_count);
+ update_rq_clock(busiest_rq);
p = detach_one_task(&env);
if (p) {
@@ -9264,6 +9303,7 @@
se = tg->se[i];
raw_spin_lock_irq(&rq->lock);
+ update_rq_clock(rq);
attach_entity_cfs_rq(se);
sync_throttle(tg, i);
raw_spin_unlock_irq(&rq->lock);
@@ -9356,8 +9396,10 @@
/* Possible calls to update_curr() need rq clock */
update_rq_clock(rq);
- for_each_sched_entity(se)
- update_cfs_shares(group_cfs_rq(se));
+ for_each_sched_entity(se) {
+ update_load_avg(se, UPDATE_TG);
+ update_cfs_shares(se);
+ }
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 5405d3f..0c00172 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -24,7 +24,7 @@
}
static struct task_struct *
-pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
put_prev_task(rq, prev);
update_idle_core(rq);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 2516b8d..e8836cf 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -9,6 +9,7 @@
#include <linux/irq_work.h>
int sched_rr_timeslice = RR_TIMESLICE;
+int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
@@ -1523,7 +1524,7 @@
}
static struct task_struct *
-pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *p;
struct rt_rq *rt_rq = &rq->rt;
@@ -1535,9 +1536,9 @@
* disabled avoiding further scheduler activity on it and we're
* being very careful to re-start the picking loop.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
pull_rt_task(rq);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
/*
* pull_rt_task() can drop (and re-acquire) rq->lock; this
* means a dl or stop task can slip in, in which case we need
@@ -2198,10 +2199,9 @@
#ifdef CONFIG_SMP
if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded)
queue_push_tasks(rq);
-#else
+#endif /* CONFIG_SMP */
if (p->prio < rq->curr->prio)
resched_curr(rq);
-#endif /* CONFIG_SMP */
}
}
@@ -2246,6 +2246,7 @@
}
}
+#ifdef CONFIG_POSIX_TIMERS
static void watchdog(struct rq *rq, struct task_struct *p)
{
unsigned long soft, hard;
@@ -2267,6 +2268,9 @@
p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
}
}
+#else
+static inline void watchdog(struct rq *rq, struct task_struct *p) { }
+#endif
static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7b34c78..71b10a9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -4,6 +4,7 @@
#include <linux/sched/rt.h>
#include <linux/u64_stats_sync.h>
#include <linux/sched/deadline.h>
+#include <linux/kernel_stat.h>
#include <linux/binfmts.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
@@ -222,7 +223,7 @@
dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
}
-extern struct mutex sched_domains_mutex;
+extern void init_dl_bw(struct dl_bw *dl_b);
#ifdef CONFIG_CGROUP_SCHED
@@ -583,6 +584,13 @@
};
extern struct root_domain def_root_domain;
+extern struct mutex sched_domains_mutex;
+extern cpumask_var_t fallback_doms;
+extern cpumask_var_t sched_domains_tmpmask;
+
+extern void init_defrootdomain(void);
+extern int init_sched_domains(const struct cpumask *cpu_map);
+extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
#endif /* CONFIG_SMP */
@@ -644,7 +652,7 @@
unsigned long next_balance;
struct mm_struct *prev_mm;
- unsigned int clock_skip_update;
+ unsigned int clock_update_flags;
u64 clock;
u64 clock_task;
@@ -768,28 +776,110 @@
return READ_ONCE(rq->clock);
}
+/*
+ * rq::clock_update_flags bits
+ *
+ * %RQCF_REQ_SKIP - will request skipping of clock update on the next
+ * call to __schedule(). This is an optimisation to avoid
+ * neighbouring rq clock updates.
+ *
+ * %RQCF_ACT_SKIP - is set from inside of __schedule() when skipping is
+ * in effect and calls to update_rq_clock() are being ignored.
+ *
+ * %RQCF_UPDATED - is a debug flag that indicates whether a call has been
+ * made to update_rq_clock() since the last time rq::lock was pinned.
+ *
+ * If inside of __schedule(), clock_update_flags will have been
+ * shifted left (a left shift is a cheap operation for the fast path
+ * to promote %RQCF_REQ_SKIP to %RQCF_ACT_SKIP), so you must use,
+ *
+ * if (rq-clock_update_flags >= RQCF_UPDATED)
+ *
+ * to check if %RQCF_UPADTED is set. It'll never be shifted more than
+ * one position though, because the next rq_unpin_lock() will shift it
+ * back.
+ */
+#define RQCF_REQ_SKIP 0x01
+#define RQCF_ACT_SKIP 0x02
+#define RQCF_UPDATED 0x04
+
+static inline void assert_clock_updated(struct rq *rq)
+{
+ /*
+ * The only reason for not seeing a clock update since the
+ * last rq_pin_lock() is if we're currently skipping updates.
+ */
+ SCHED_WARN_ON(rq->clock_update_flags < RQCF_ACT_SKIP);
+}
+
static inline u64 rq_clock(struct rq *rq)
{
lockdep_assert_held(&rq->lock);
+ assert_clock_updated(rq);
+
return rq->clock;
}
static inline u64 rq_clock_task(struct rq *rq)
{
lockdep_assert_held(&rq->lock);
+ assert_clock_updated(rq);
+
return rq->clock_task;
}
-#define RQCF_REQ_SKIP 0x01
-#define RQCF_ACT_SKIP 0x02
-
static inline void rq_clock_skip_update(struct rq *rq, bool skip)
{
lockdep_assert_held(&rq->lock);
if (skip)
- rq->clock_skip_update |= RQCF_REQ_SKIP;
+ rq->clock_update_flags |= RQCF_REQ_SKIP;
else
- rq->clock_skip_update &= ~RQCF_REQ_SKIP;
+ rq->clock_update_flags &= ~RQCF_REQ_SKIP;
+}
+
+struct rq_flags {
+ unsigned long flags;
+ struct pin_cookie cookie;
+#ifdef CONFIG_SCHED_DEBUG
+ /*
+ * A copy of (rq::clock_update_flags & RQCF_UPDATED) for the
+ * current pin context is stashed here in case it needs to be
+ * restored in rq_repin_lock().
+ */
+ unsigned int clock_update_flags;
+#endif
+};
+
+static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
+{
+ rf->cookie = lockdep_pin_lock(&rq->lock);
+
+#ifdef CONFIG_SCHED_DEBUG
+ rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+ rf->clock_update_flags = 0;
+#endif
+}
+
+static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
+{
+#ifdef CONFIG_SCHED_DEBUG
+ if (rq->clock_update_flags > RQCF_ACT_SKIP)
+ rf->clock_update_flags = RQCF_UPDATED;
+#endif
+
+ lockdep_unpin_lock(&rq->lock, rf->cookie);
+}
+
+static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
+{
+ lockdep_repin_lock(&rq->lock, rf->cookie);
+
+#ifdef CONFIG_SCHED_DEBUG
+ /*
+ * Restore the value we stashed in @rf for this pin context.
+ */
+ rq->clock_update_flags |= rf->clock_update_flags;
+#endif
}
#ifdef CONFIG_NUMA
@@ -803,6 +893,16 @@
extern bool find_numa_distance(int distance);
#endif
+#ifdef CONFIG_NUMA
+extern void sched_init_numa(void);
+extern void sched_domains_numa_masks_set(unsigned int cpu);
+extern void sched_domains_numa_masks_clear(unsigned int cpu);
+#else
+static inline void sched_init_numa(void) { }
+static inline void sched_domains_numa_masks_set(unsigned int cpu) { }
+static inline void sched_domains_numa_masks_clear(unsigned int cpu) { }
+#endif
+
#ifdef CONFIG_NUMA_BALANCING
/* The regions in numa_faults array from task_struct */
enum numa_faults_stats {
@@ -969,7 +1069,7 @@
#endif /* CONFIG_SMP */
#include "stats.h"
-#include "auto_group.h"
+#include "autogroup.h"
#ifdef CONFIG_CGROUP_SCHED
@@ -1245,7 +1345,7 @@
*/
struct task_struct * (*pick_next_task) (struct rq *rq,
struct task_struct *prev,
- struct pin_cookie cookie);
+ struct rq_flags *rf);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
@@ -1501,11 +1601,6 @@
static inline void sched_avg_update(struct rq *rq) { }
#endif
-struct rq_flags {
- unsigned long flags;
- struct pin_cookie cookie;
-};
-
struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
__acquires(rq->lock);
struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
@@ -1515,7 +1610,7 @@
static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
__releases(rq->lock)
{
- lockdep_unpin_lock(&rq->lock, rf->cookie);
+ rq_unpin_lock(rq, rf);
raw_spin_unlock(&rq->lock);
}
@@ -1524,7 +1619,7 @@
__releases(rq->lock)
__releases(p->pi_lock)
{
- lockdep_unpin_lock(&rq->lock, rf->cookie);
+ rq_unpin_lock(rq, rf);
raw_spin_unlock(&rq->lock);
raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
}
@@ -1674,6 +1769,10 @@
__release(rq2->lock);
}
+extern void set_rq_online (struct rq *rq);
+extern void set_rq_offline(struct rq *rq);
+extern bool sched_smp_initialized;
+
#else /* CONFIG_SMP */
/*
@@ -1750,8 +1849,7 @@
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
struct irqtime {
- u64 hardirq_time;
- u64 softirq_time;
+ u64 tick_delta;
u64 irq_start_time;
struct u64_stats_sync sync;
};
@@ -1761,12 +1859,13 @@
static inline u64 irq_time_read(int cpu)
{
struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
+ u64 *cpustat = kcpustat_cpu(cpu).cpustat;
unsigned int seq;
u64 total;
do {
seq = __u64_stats_fetch_begin(&irqtime->sync);
- total = irqtime->softirq_time + irqtime->hardirq_time;
+ total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ];
} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
return total;
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 34659a8..bf0da0a 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -172,18 +172,19 @@
*/
/**
- * cputimer_running - return true if cputimer is running
+ * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running
*
* @tsk: Pointer to target task.
*/
-static inline bool cputimer_running(struct task_struct *tsk)
-
+#ifdef CONFIG_POSIX_TIMERS
+static inline
+struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
{
struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
/* Check if cputimer isn't running. This is accessed without locking. */
if (!READ_ONCE(cputimer->running))
- return false;
+ return NULL;
/*
* After we flush the task's sum_exec_runtime to sig->sum_sched_runtime
@@ -200,10 +201,17 @@
* clock delta is behind the expiring timer value.
*/
if (unlikely(!tsk->sighand))
- return false;
+ return NULL;
- return true;
+ return cputimer;
}
+#else
+static inline
+struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
+{
+ return NULL;
+}
+#endif
/**
* account_group_user_time - Maintain utime for a thread group.
@@ -216,11 +224,11 @@
* running CPU and update the utime field there.
*/
static inline void account_group_user_time(struct task_struct *tsk,
- cputime_t cputime)
+ u64 cputime)
{
- struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+ struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
- if (!cputimer_running(tsk))
+ if (!cputimer)
return;
atomic64_add(cputime, &cputimer->cputime_atomic.utime);
@@ -237,11 +245,11 @@
* running CPU and update the stime field there.
*/
static inline void account_group_system_time(struct task_struct *tsk,
- cputime_t cputime)
+ u64 cputime)
{
- struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+ struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
- if (!cputimer_running(tsk))
+ if (!cputimer)
return;
atomic64_add(cputime, &cputimer->cputime_atomic.stime);
@@ -260,9 +268,9 @@
static inline void account_group_exec_runtime(struct task_struct *tsk,
unsigned long long ns)
{
- struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+ struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
- if (!cputimer_running(tsk))
+ if (!cputimer)
return;
atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 604297a..9f69fb6 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -24,7 +24,7 @@
}
static struct task_struct *
-pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *stop = rq->stop;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
new file mode 100644
index 0000000..1b0b4fb
--- /dev/null
+++ b/kernel/sched/topology.c
@@ -0,0 +1,1658 @@
+/*
+ * Scheduler topology setup/handling methods
+ */
+#include <linux/sched.h>
+#include <linux/mutex.h>
+
+#include "sched.h"
+
+DEFINE_MUTEX(sched_domains_mutex);
+
+/* Protected by sched_domains_mutex: */
+cpumask_var_t sched_domains_tmpmask;
+
+#ifdef CONFIG_SCHED_DEBUG
+
+static __read_mostly int sched_debug_enabled;
+
+static int __init sched_debug_setup(char *str)
+{
+ sched_debug_enabled = 1;
+
+ return 0;
+}
+early_param("sched_debug", sched_debug_setup);
+
+static inline bool sched_debug(void)
+{
+ return sched_debug_enabled;
+}
+
+static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
+ struct cpumask *groupmask)
+{
+ struct sched_group *group = sd->groups;
+
+ cpumask_clear(groupmask);
+
+ printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+
+ if (!(sd->flags & SD_LOAD_BALANCE)) {
+ printk("does not load-balance\n");
+ if (sd->parent)
+ printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
+ " has parent");
+ return -1;
+ }
+
+ printk(KERN_CONT "span %*pbl level %s\n",
+ cpumask_pr_args(sched_domain_span(sd)), sd->name);
+
+ if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+ printk(KERN_ERR "ERROR: domain->span does not contain "
+ "CPU%d\n", cpu);
+ }
+ if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
+ printk(KERN_ERR "ERROR: domain->groups does not contain"
+ " CPU%d\n", cpu);
+ }
+
+ printk(KERN_DEBUG "%*s groups:", level + 1, "");
+ do {
+ if (!group) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: group is NULL\n");
+ break;
+ }
+
+ if (!cpumask_weight(sched_group_cpus(group))) {
+ printk(KERN_CONT "\n");
+ printk(KERN_ERR "ERROR: empty group\n");
+ break;
+ }
+
+ if (!(sd->flags & SD_OVERLAP) &&
+ cpumask_intersects(groupmask, sched_group_cpus(group))) {
+ printk(KERN_CONT "\n");
+ printk(KERN_ERR "ERROR: repeated CPUs\n");
+ break;
+ }
+
+ cpumask_or(groupmask, groupmask, sched_group_cpus(group));
+
+ printk(KERN_CONT " %*pbl",
+ cpumask_pr_args(sched_group_cpus(group)));
+ if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
+ printk(KERN_CONT " (cpu_capacity = %lu)",
+ group->sgc->capacity);
+ }
+
+ group = group->next;
+ } while (group != sd->groups);
+ printk(KERN_CONT "\n");
+
+ if (!cpumask_equal(sched_domain_span(sd), groupmask))
+ printk(KERN_ERR "ERROR: groups don't span domain->span\n");
+
+ if (sd->parent &&
+ !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
+ printk(KERN_ERR "ERROR: parent span is not a superset "
+ "of domain->span\n");
+ return 0;
+}
+
+static void sched_domain_debug(struct sched_domain *sd, int cpu)
+{
+ int level = 0;
+
+ if (!sched_debug_enabled)
+ return;
+
+ if (!sd) {
+ printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+ return;
+ }
+
+ printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+
+ for (;;) {
+ if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
+ break;
+ level++;
+ sd = sd->parent;
+ if (!sd)
+ break;
+ }
+}
+#else /* !CONFIG_SCHED_DEBUG */
+
+# define sched_debug_enabled 0
+# define sched_domain_debug(sd, cpu) do { } while (0)
+static inline bool sched_debug(void)
+{
+ return false;
+}
+#endif /* CONFIG_SCHED_DEBUG */
+
+static int sd_degenerate(struct sched_domain *sd)
+{
+ if (cpumask_weight(sched_domain_span(sd)) == 1)
+ return 1;
+
+ /* Following flags need at least 2 groups */
+ if (sd->flags & (SD_LOAD_BALANCE |
+ SD_BALANCE_NEWIDLE |
+ SD_BALANCE_FORK |
+ SD_BALANCE_EXEC |
+ SD_SHARE_CPUCAPACITY |
+ SD_ASYM_CPUCAPACITY |
+ SD_SHARE_PKG_RESOURCES |
+ SD_SHARE_POWERDOMAIN)) {
+ if (sd->groups != sd->groups->next)
+ return 0;
+ }
+
+ /* Following flags don't use groups */
+ if (sd->flags & (SD_WAKE_AFFINE))
+ return 0;
+
+ return 1;
+}
+
+static int
+sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
+{
+ unsigned long cflags = sd->flags, pflags = parent->flags;
+
+ if (sd_degenerate(parent))
+ return 1;
+
+ if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
+ return 0;
+
+ /* Flags needing groups don't count if only 1 group in parent */
+ if (parent->groups == parent->groups->next) {
+ pflags &= ~(SD_LOAD_BALANCE |
+ SD_BALANCE_NEWIDLE |
+ SD_BALANCE_FORK |
+ SD_BALANCE_EXEC |
+ SD_ASYM_CPUCAPACITY |
+ SD_SHARE_CPUCAPACITY |
+ SD_SHARE_PKG_RESOURCES |
+ SD_PREFER_SIBLING |
+ SD_SHARE_POWERDOMAIN);
+ if (nr_node_ids == 1)
+ pflags &= ~SD_SERIALIZE;
+ }
+ if (~cflags & pflags)
+ return 0;
+
+ return 1;
+}
+
+static void free_rootdomain(struct rcu_head *rcu)
+{
+ struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
+
+ cpupri_cleanup(&rd->cpupri);
+ cpudl_cleanup(&rd->cpudl);
+ free_cpumask_var(rd->dlo_mask);
+ free_cpumask_var(rd->rto_mask);
+ free_cpumask_var(rd->online);
+ free_cpumask_var(rd->span);
+ kfree(rd);
+}
+
+void rq_attach_root(struct rq *rq, struct root_domain *rd)
+{
+ struct root_domain *old_rd = NULL;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+
+ if (rq->rd) {
+ old_rd = rq->rd;
+
+ if (cpumask_test_cpu(rq->cpu, old_rd->online))
+ set_rq_offline(rq);
+
+ cpumask_clear_cpu(rq->cpu, old_rd->span);
+
+ /*
+ * If we dont want to free the old_rd yet then
+ * set old_rd to NULL to skip the freeing later
+ * in this function:
+ */
+ if (!atomic_dec_and_test(&old_rd->refcount))
+ old_rd = NULL;
+ }
+
+ atomic_inc(&rd->refcount);
+ rq->rd = rd;
+
+ cpumask_set_cpu(rq->cpu, rd->span);
+ if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
+ set_rq_online(rq);
+
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+ if (old_rd)
+ call_rcu_sched(&old_rd->rcu, free_rootdomain);
+}
+
+static int init_rootdomain(struct root_domain *rd)
+{
+ memset(rd, 0, sizeof(*rd));
+
+ if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
+ goto out;
+ if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
+ goto free_span;
+ if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
+ goto free_online;
+ if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ goto free_dlo_mask;
+
+ init_dl_bw(&rd->dl_bw);
+ if (cpudl_init(&rd->cpudl) != 0)
+ goto free_rto_mask;
+
+ if (cpupri_init(&rd->cpupri) != 0)
+ goto free_cpudl;
+ return 0;
+
+free_cpudl:
+ cpudl_cleanup(&rd->cpudl);
+free_rto_mask:
+ free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+ free_cpumask_var(rd->dlo_mask);
+free_online:
+ free_cpumask_var(rd->online);
+free_span:
+ free_cpumask_var(rd->span);
+out:
+ return -ENOMEM;
+}
+
+/*
+ * By default the system creates a single root-domain with all CPUs as
+ * members (mimicking the global state we have today).
+ */
+struct root_domain def_root_domain;
+
+void init_defrootdomain(void)
+{
+ init_rootdomain(&def_root_domain);
+
+ atomic_set(&def_root_domain.refcount, 1);
+}
+
+static struct root_domain *alloc_rootdomain(void)
+{
+ struct root_domain *rd;
+
+ rd = kmalloc(sizeof(*rd), GFP_KERNEL);
+ if (!rd)
+ return NULL;
+
+ if (init_rootdomain(rd) != 0) {
+ kfree(rd);
+ return NULL;
+ }
+
+ return rd;
+}
+
+static void free_sched_groups(struct sched_group *sg, int free_sgc)
+{
+ struct sched_group *tmp, *first;
+
+ if (!sg)
+ return;
+
+ first = sg;
+ do {
+ tmp = sg->next;
+
+ if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
+ kfree(sg->sgc);
+
+ kfree(sg);
+ sg = tmp;
+ } while (sg != first);
+}
+
+static void destroy_sched_domain(struct sched_domain *sd)
+{
+ /*
+ * If its an overlapping domain it has private groups, iterate and
+ * nuke them all.
+ */
+ if (sd->flags & SD_OVERLAP) {
+ free_sched_groups(sd->groups, 1);
+ } else if (atomic_dec_and_test(&sd->groups->ref)) {
+ kfree(sd->groups->sgc);
+ kfree(sd->groups);
+ }
+ if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
+ kfree(sd->shared);
+ kfree(sd);
+}
+
+static void destroy_sched_domains_rcu(struct rcu_head *rcu)
+{
+ struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
+
+ while (sd) {
+ struct sched_domain *parent = sd->parent;
+ destroy_sched_domain(sd);
+ sd = parent;
+ }
+}
+
+static void destroy_sched_domains(struct sched_domain *sd)
+{
+ if (sd)
+ call_rcu(&sd->rcu, destroy_sched_domains_rcu);
+}
+
+/*
+ * Keep a special pointer to the highest sched_domain that has
+ * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
+ * allows us to avoid some pointer chasing select_idle_sibling().
+ *
+ * Also keep a unique ID per domain (we use the first CPU number in
+ * the cpumask of the domain), this allows us to quickly tell if
+ * two CPUs are in the same cache domain, see cpus_share_cache().
+ */
+DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(int, sd_llc_size);
+DEFINE_PER_CPU(int, sd_llc_id);
+DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
+DEFINE_PER_CPU(struct sched_domain *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+
+static void update_top_cache_domain(int cpu)
+{
+ struct sched_domain_shared *sds = NULL;
+ struct sched_domain *sd;
+ int id = cpu;
+ int size = 1;
+
+ sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
+ if (sd) {
+ id = cpumask_first(sched_domain_span(sd));
+ size = cpumask_weight(sched_domain_span(sd));
+ sds = sd->shared;
+ }
+
+ rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
+ per_cpu(sd_llc_size, cpu) = size;
+ per_cpu(sd_llc_id, cpu) = id;
+ rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
+
+ sd = lowest_flag_domain(cpu, SD_NUMA);
+ rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
+
+ sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
+ rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
+}
+
+/*
+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
+ * hold the hotplug lock.
+ */
+static void
+cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ struct sched_domain *tmp;
+
+ /* Remove the sched domains which do not contribute to scheduling. */
+ for (tmp = sd; tmp; ) {
+ struct sched_domain *parent = tmp->parent;
+ if (!parent)
+ break;
+
+ if (sd_parent_degenerate(tmp, parent)) {
+ tmp->parent = parent->parent;
+ if (parent->parent)
+ parent->parent->child = tmp;
+ /*
+ * Transfer SD_PREFER_SIBLING down in case of a
+ * degenerate parent; the spans match for this
+ * so the property transfers.
+ */
+ if (parent->flags & SD_PREFER_SIBLING)
+ tmp->flags |= SD_PREFER_SIBLING;
+ destroy_sched_domain(parent);
+ } else
+ tmp = tmp->parent;
+ }
+
+ if (sd && sd_degenerate(sd)) {
+ tmp = sd;
+ sd = sd->parent;
+ destroy_sched_domain(tmp);
+ if (sd)
+ sd->child = NULL;
+ }
+
+ sched_domain_debug(sd, cpu);
+
+ rq_attach_root(rq, rd);
+ tmp = rq->sd;
+ rcu_assign_pointer(rq->sd, sd);
+ destroy_sched_domains(tmp);
+
+ update_top_cache_domain(cpu);
+}
+
+/* Setup the mask of CPUs configured for isolated domains */
+static int __init isolated_cpu_setup(char *str)
+{
+ int ret;
+
+ alloc_bootmem_cpumask_var(&cpu_isolated_map);
+ ret = cpulist_parse(str, cpu_isolated_map);
+ if (ret) {
+ pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids);
+ return 0;
+ }
+ return 1;
+}
+__setup("isolcpus=", isolated_cpu_setup);
+
+struct s_data {
+ struct sched_domain ** __percpu sd;
+ struct root_domain *rd;
+};
+
+enum s_alloc {
+ sa_rootdomain,
+ sa_sd,
+ sa_sd_storage,
+ sa_none,
+};
+
+/*
+ * Build an iteration mask that can exclude certain CPUs from the upwards
+ * domain traversal.
+ *
+ * Asymmetric node setups can result in situations where the domain tree is of
+ * unequal depth, make sure to skip domains that already cover the entire
+ * range.
+ *
+ * In that case build_sched_domains() will have terminated the iteration early
+ * and our sibling sd spans will be empty. Domains should always include the
+ * CPU they're built on, so check that.
+ */
+static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+{
+ const struct cpumask *span = sched_domain_span(sd);
+ struct sd_data *sdd = sd->private;
+ struct sched_domain *sibling;
+ int i;
+
+ for_each_cpu(i, span) {
+ sibling = *per_cpu_ptr(sdd->sd, i);
+ if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+ continue;
+
+ cpumask_set_cpu(i, sched_group_mask(sg));
+ }
+}
+
+/*
+ * Return the canonical balance CPU for this group, this is the first CPU
+ * of this group that's also in the iteration mask.
+ */
+int group_balance_cpu(struct sched_group *sg)
+{
+ return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+}
+
+static int
+build_overlap_sched_groups(struct sched_domain *sd, int cpu)
+{
+ struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
+ const struct cpumask *span = sched_domain_span(sd);
+ struct cpumask *covered = sched_domains_tmpmask;
+ struct sd_data *sdd = sd->private;
+ struct sched_domain *sibling;
+ int i;
+
+ cpumask_clear(covered);
+
+ for_each_cpu(i, span) {
+ struct cpumask *sg_span;
+
+ if (cpumask_test_cpu(i, covered))
+ continue;
+
+ sibling = *per_cpu_ptr(sdd->sd, i);
+
+ /* See the comment near build_group_mask(). */
+ if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+ continue;
+
+ sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+ GFP_KERNEL, cpu_to_node(cpu));
+
+ if (!sg)
+ goto fail;
+
+ sg_span = sched_group_cpus(sg);
+ if (sibling->child)
+ cpumask_copy(sg_span, sched_domain_span(sibling->child));
+ else
+ cpumask_set_cpu(i, sg_span);
+
+ cpumask_or(covered, covered, sg_span);
+
+ sg->sgc = *per_cpu_ptr(sdd->sgc, i);
+ if (atomic_inc_return(&sg->sgc->ref) == 1)
+ build_group_mask(sd, sg);
+
+ /*
+ * Initialize sgc->capacity such that even if we mess up the
+ * domains and no possible iteration will get us here, we won't
+ * die on a /0 trap.
+ */
+ sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+ sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
+
+ /*
+ * Make sure the first group of this domain contains the
+ * canonical balance CPU. Otherwise the sched_domain iteration
+ * breaks. See update_sg_lb_stats().
+ */
+ if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
+ group_balance_cpu(sg) == cpu)
+ groups = sg;
+
+ if (!first)
+ first = sg;
+ if (last)
+ last->next = sg;
+ last = sg;
+ last->next = first;
+ }
+ sd->groups = groups;
+
+ return 0;
+
+fail:
+ free_sched_groups(first, 0);
+
+ return -ENOMEM;
+}
+
+static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
+{
+ struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
+ struct sched_domain *child = sd->child;
+
+ if (child)
+ cpu = cpumask_first(sched_domain_span(child));
+
+ if (sg) {
+ *sg = *per_cpu_ptr(sdd->sg, cpu);
+ (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+
+ /* For claim_allocations: */
+ atomic_set(&(*sg)->sgc->ref, 1);
+ }
+
+ return cpu;
+}
+
+/*
+ * build_sched_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_capacity to 0.
+ *
+ * Assumes the sched_domain tree is fully constructed
+ */
+static int
+build_sched_groups(struct sched_domain *sd, int cpu)
+{
+ struct sched_group *first = NULL, *last = NULL;
+ struct sd_data *sdd = sd->private;
+ const struct cpumask *span = sched_domain_span(sd);
+ struct cpumask *covered;
+ int i;
+
+ get_group(cpu, sdd, &sd->groups);
+ atomic_inc(&sd->groups->ref);
+
+ if (cpu != cpumask_first(span))
+ return 0;
+
+ lockdep_assert_held(&sched_domains_mutex);
+ covered = sched_domains_tmpmask;
+
+ cpumask_clear(covered);
+
+ for_each_cpu(i, span) {
+ struct sched_group *sg;
+ int group, j;
+
+ if (cpumask_test_cpu(i, covered))
+ continue;
+
+ group = get_group(i, sdd, &sg);
+ cpumask_setall(sched_group_mask(sg));
+
+ for_each_cpu(j, span) {
+ if (get_group(j, sdd, NULL) != group)
+ continue;
+
+ cpumask_set_cpu(j, covered);
+ cpumask_set_cpu(j, sched_group_cpus(sg));
+ }
+
+ if (!first)
+ first = sg;
+ if (last)
+ last->next = sg;
+ last = sg;
+ }
+ last->next = first;
+
+ return 0;
+}
+
+/*
+ * Initialize sched groups cpu_capacity.
+ *
+ * cpu_capacity indicates the capacity of sched group, which is used while
+ * distributing the load between different sched groups in a sched domain.
+ * Typically cpu_capacity for all the groups in a sched domain will be same
+ * unless there are asymmetries in the topology. If there are asymmetries,
+ * group having more cpu_capacity will pickup more load compared to the
+ * group having less cpu_capacity.
+ */
+static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
+{
+ struct sched_group *sg = sd->groups;
+
+ WARN_ON(!sg);
+
+ do {
+ int cpu, max_cpu = -1;
+
+ sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+
+ if (!(sd->flags & SD_ASYM_PACKING))
+ goto next;
+
+ for_each_cpu(cpu, sched_group_cpus(sg)) {
+ if (max_cpu < 0)
+ max_cpu = cpu;
+ else if (sched_asym_prefer(cpu, max_cpu))
+ max_cpu = cpu;
+ }
+ sg->asym_prefer_cpu = max_cpu;
+
+next:
+ sg = sg->next;
+ } while (sg != sd->groups);
+
+ if (cpu != group_balance_cpu(sg))
+ return;
+
+ update_group_capacity(sd, cpu);
+}
+
+/*
+ * Initializers for schedule domains
+ * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
+ */
+
+static int default_relax_domain_level = -1;
+int sched_domain_level_max;
+
+static int __init setup_relax_domain_level(char *str)
+{
+ if (kstrtoint(str, 0, &default_relax_domain_level))
+ pr_warn("Unable to set relax_domain_level\n");
+
+ return 1;
+}
+__setup("relax_domain_level=", setup_relax_domain_level);
+
+static void set_domain_attribute(struct sched_domain *sd,
+ struct sched_domain_attr *attr)
+{
+ int request;
+
+ if (!attr || attr->relax_domain_level < 0) {
+ if (default_relax_domain_level < 0)
+ return;
+ else
+ request = default_relax_domain_level;
+ } else
+ request = attr->relax_domain_level;
+ if (request < sd->level) {
+ /* Turn off idle balance on this domain: */
+ sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
+ } else {
+ /* Turn on idle balance on this domain: */
+ sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
+ }
+}
+
+static void __sdt_free(const struct cpumask *cpu_map);
+static int __sdt_alloc(const struct cpumask *cpu_map);
+
+static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
+ const struct cpumask *cpu_map)
+{
+ switch (what) {
+ case sa_rootdomain:
+ if (!atomic_read(&d->rd->refcount))
+ free_rootdomain(&d->rd->rcu);
+ /* Fall through */
+ case sa_sd:
+ free_percpu(d->sd);
+ /* Fall through */
+ case sa_sd_storage:
+ __sdt_free(cpu_map);
+ /* Fall through */
+ case sa_none:
+ break;
+ }
+}
+
+static enum s_alloc
+__visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map)
+{
+ memset(d, 0, sizeof(*d));
+
+ if (__sdt_alloc(cpu_map))
+ return sa_sd_storage;
+ d->sd = alloc_percpu(struct sched_domain *);
+ if (!d->sd)
+ return sa_sd_storage;
+ d->rd = alloc_rootdomain();
+ if (!d->rd)
+ return sa_sd;
+ return sa_rootdomain;
+}
+
+/*
+ * NULL the sd_data elements we've used to build the sched_domain and
+ * sched_group structure so that the subsequent __free_domain_allocs()
+ * will not free the data we're using.
+ */
+static void claim_allocations(int cpu, struct sched_domain *sd)
+{
+ struct sd_data *sdd = sd->private;
+
+ WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
+ *per_cpu_ptr(sdd->sd, cpu) = NULL;
+
+ if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref))
+ *per_cpu_ptr(sdd->sds, cpu) = NULL;
+
+ if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
+ *per_cpu_ptr(sdd->sg, cpu) = NULL;
+
+ if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref))
+ *per_cpu_ptr(sdd->sgc, cpu) = NULL;
+}
+
+#ifdef CONFIG_NUMA
+static int sched_domains_numa_levels;
+enum numa_topology_type sched_numa_topology_type;
+static int *sched_domains_numa_distance;
+int sched_max_numa_distance;
+static struct cpumask ***sched_domains_numa_masks;
+static int sched_domains_curr_level;
+#endif
+
+/*
+ * SD_flags allowed in topology descriptions.
+ *
+ * These flags are purely descriptive of the topology and do not prescribe
+ * behaviour. Behaviour is artificial and mapped in the below sd_init()
+ * function:
+ *
+ * SD_SHARE_CPUCAPACITY - describes SMT topologies
+ * SD_SHARE_PKG_RESOURCES - describes shared caches
+ * SD_NUMA - describes NUMA topologies
+ * SD_SHARE_POWERDOMAIN - describes shared power domain
+ * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies
+ *
+ * Odd one out, which beside describing the topology has a quirk also
+ * prescribes the desired behaviour that goes along with it:
+ *
+ * SD_ASYM_PACKING - describes SMT quirks
+ */
+#define TOPOLOGY_SD_FLAGS \
+ (SD_SHARE_CPUCAPACITY | \
+ SD_SHARE_PKG_RESOURCES | \
+ SD_NUMA | \
+ SD_ASYM_PACKING | \
+ SD_ASYM_CPUCAPACITY | \
+ SD_SHARE_POWERDOMAIN)
+
+static struct sched_domain *
+sd_init(struct sched_domain_topology_level *tl,
+ const struct cpumask *cpu_map,
+ struct sched_domain *child, int cpu)
+{
+ struct sd_data *sdd = &tl->data;
+ struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
+ int sd_id, sd_weight, sd_flags = 0;
+
+#ifdef CONFIG_NUMA
+ /*
+ * Ugly hack to pass state to sd_numa_mask()...
+ */
+ sched_domains_curr_level = tl->numa_level;
+#endif
+
+ sd_weight = cpumask_weight(tl->mask(cpu));
+
+ if (tl->sd_flags)
+ sd_flags = (*tl->sd_flags)();
+ if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
+ "wrong sd_flags in topology description\n"))
+ sd_flags &= ~TOPOLOGY_SD_FLAGS;
+
+ *sd = (struct sched_domain){
+ .min_interval = sd_weight,
+ .max_interval = 2*sd_weight,
+ .busy_factor = 32,
+ .imbalance_pct = 125,
+
+ .cache_nice_tries = 0,
+ .busy_idx = 0,
+ .idle_idx = 0,
+ .newidle_idx = 0,
+ .wake_idx = 0,
+ .forkexec_idx = 0,
+
+ .flags = 1*SD_LOAD_BALANCE
+ | 1*SD_BALANCE_NEWIDLE
+ | 1*SD_BALANCE_EXEC
+ | 1*SD_BALANCE_FORK
+ | 0*SD_BALANCE_WAKE
+ | 1*SD_WAKE_AFFINE
+ | 0*SD_SHARE_CPUCAPACITY
+ | 0*SD_SHARE_PKG_RESOURCES
+ | 0*SD_SERIALIZE
+ | 0*SD_PREFER_SIBLING
+ | 0*SD_NUMA
+ | sd_flags
+ ,
+
+ .last_balance = jiffies,
+ .balance_interval = sd_weight,
+ .smt_gain = 0,
+ .max_newidle_lb_cost = 0,
+ .next_decay_max_lb_cost = jiffies,
+ .child = child,
+#ifdef CONFIG_SCHED_DEBUG
+ .name = tl->name,
+#endif
+ };
+
+ cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
+ sd_id = cpumask_first(sched_domain_span(sd));
+
+ /*
+ * Convert topological properties into behaviour.
+ */
+
+ if (sd->flags & SD_ASYM_CPUCAPACITY) {
+ struct sched_domain *t = sd;
+
+ for_each_lower_domain(t)
+ t->flags |= SD_BALANCE_WAKE;
+ }
+
+ if (sd->flags & SD_SHARE_CPUCAPACITY) {
+ sd->flags |= SD_PREFER_SIBLING;
+ sd->imbalance_pct = 110;
+ sd->smt_gain = 1178; /* ~15% */
+
+ } else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+ sd->imbalance_pct = 117;
+ sd->cache_nice_tries = 1;
+ sd->busy_idx = 2;
+
+#ifdef CONFIG_NUMA
+ } else if (sd->flags & SD_NUMA) {
+ sd->cache_nice_tries = 2;
+ sd->busy_idx = 3;
+ sd->idle_idx = 2;
+
+ sd->flags |= SD_SERIALIZE;
+ if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
+ sd->flags &= ~(SD_BALANCE_EXEC |
+ SD_BALANCE_FORK |
+ SD_WAKE_AFFINE);
+ }
+
+#endif
+ } else {
+ sd->flags |= SD_PREFER_SIBLING;
+ sd->cache_nice_tries = 1;
+ sd->busy_idx = 2;
+ sd->idle_idx = 1;
+ }
+
+ /*
+ * For all levels sharing cache; connect a sched_domain_shared
+ * instance.
+ */
+ if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+ sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
+ atomic_inc(&sd->shared->ref);
+ atomic_set(&sd->shared->nr_busy_cpus, sd_weight);
+ }
+
+ sd->private = sdd;
+
+ return sd;
+}
+
+/*
+ * Topology list, bottom-up.
+ */
+static struct sched_domain_topology_level default_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+ { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+ { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+ { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { NULL, },
+};
+
+static struct sched_domain_topology_level *sched_domain_topology =
+ default_topology;
+
+#define for_each_sd_topology(tl) \
+ for (tl = sched_domain_topology; tl->mask; tl++)
+
+void set_sched_topology(struct sched_domain_topology_level *tl)
+{
+ if (WARN_ON_ONCE(sched_smp_initialized))
+ return;
+
+ sched_domain_topology = tl;
+}
+
+#ifdef CONFIG_NUMA
+
+static const struct cpumask *sd_numa_mask(int cpu)
+{
+ return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
+}
+
+static void sched_numa_warn(const char *str)
+{
+ static int done = false;
+ int i,j;
+
+ if (done)
+ return;
+
+ done = true;
+
+ printk(KERN_WARNING "ERROR: %s\n\n", str);
+
+ for (i = 0; i < nr_node_ids; i++) {
+ printk(KERN_WARNING " ");
+ for (j = 0; j < nr_node_ids; j++)
+ printk(KERN_CONT "%02d ", node_distance(i,j));
+ printk(KERN_CONT "\n");
+ }
+ printk(KERN_WARNING "\n");
+}
+
+bool find_numa_distance(int distance)
+{
+ int i;
+
+ if (distance == node_distance(0, 0))
+ return true;
+
+ for (i = 0; i < sched_domains_numa_levels; i++) {
+ if (sched_domains_numa_distance[i] == distance)
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * A system can have three types of NUMA topology:
+ * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
+ * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes
+ * NUMA_BACKPLANE: nodes can reach other nodes through a backplane
+ *
+ * The difference between a glueless mesh topology and a backplane
+ * topology lies in whether communication between not directly
+ * connected nodes goes through intermediary nodes (where programs
+ * could run), or through backplane controllers. This affects
+ * placement of programs.
+ *
+ * The type of topology can be discerned with the following tests:
+ * - If the maximum distance between any nodes is 1 hop, the system
+ * is directly connected.
+ * - If for two nodes A and B, located N > 1 hops away from each other,
+ * there is an intermediary node C, which is < N hops away from both
+ * nodes A and B, the system is a glueless mesh.
+ */
+static void init_numa_topology_type(void)
+{
+ int a, b, c, n;
+
+ n = sched_max_numa_distance;
+
+ if (sched_domains_numa_levels <= 1) {
+ sched_numa_topology_type = NUMA_DIRECT;
+ return;
+ }
+
+ for_each_online_node(a) {
+ for_each_online_node(b) {
+ /* Find two nodes furthest removed from each other. */
+ if (node_distance(a, b) < n)
+ continue;
+
+ /* Is there an intermediary node between a and b? */
+ for_each_online_node(c) {
+ if (node_distance(a, c) < n &&
+ node_distance(b, c) < n) {
+ sched_numa_topology_type =
+ NUMA_GLUELESS_MESH;
+ return;
+ }
+ }
+
+ sched_numa_topology_type = NUMA_BACKPLANE;
+ return;
+ }
+ }
+}
+
+void sched_init_numa(void)
+{
+ int next_distance, curr_distance = node_distance(0, 0);
+ struct sched_domain_topology_level *tl;
+ int level = 0;
+ int i, j, k;
+
+ sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
+ if (!sched_domains_numa_distance)
+ return;
+
+ /*
+ * O(nr_nodes^2) deduplicating selection sort -- in order to find the
+ * unique distances in the node_distance() table.
+ *
+ * Assumes node_distance(0,j) includes all distances in
+ * node_distance(i,j) in order to avoid cubic time.
+ */
+ next_distance = curr_distance;
+ for (i = 0; i < nr_node_ids; i++) {
+ for (j = 0; j < nr_node_ids; j++) {
+ for (k = 0; k < nr_node_ids; k++) {
+ int distance = node_distance(i, k);
+
+ if (distance > curr_distance &&
+ (distance < next_distance ||
+ next_distance == curr_distance))
+ next_distance = distance;
+
+ /*
+ * While not a strong assumption it would be nice to know
+ * about cases where if node A is connected to B, B is not
+ * equally connected to A.
+ */
+ if (sched_debug() && node_distance(k, i) != distance)
+ sched_numa_warn("Node-distance not symmetric");
+
+ if (sched_debug() && i && !find_numa_distance(distance))
+ sched_numa_warn("Node-0 not representative");
+ }
+ if (next_distance != curr_distance) {
+ sched_domains_numa_distance[level++] = next_distance;
+ sched_domains_numa_levels = level;
+ curr_distance = next_distance;
+ } else break;
+ }
+
+ /*
+ * In case of sched_debug() we verify the above assumption.
+ */
+ if (!sched_debug())
+ break;
+ }
+
+ if (!level)
+ return;
+
+ /*
+ * 'level' contains the number of unique distances, excluding the
+ * identity distance node_distance(i,i).
+ *
+ * The sched_domains_numa_distance[] array includes the actual distance
+ * numbers.
+ */
+
+ /*
+ * Here, we should temporarily reset sched_domains_numa_levels to 0.
+ * If it fails to allocate memory for array sched_domains_numa_masks[][],
+ * the array will contain less then 'level' members. This could be
+ * dangerous when we use it to iterate array sched_domains_numa_masks[][]
+ * in other functions.
+ *
+ * We reset it to 'level' at the end of this function.
+ */
+ sched_domains_numa_levels = 0;
+
+ sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
+ if (!sched_domains_numa_masks)
+ return;
+
+ /*
+ * Now for each level, construct a mask per node which contains all
+ * CPUs of nodes that are that many hops away from us.
+ */
+ for (i = 0; i < level; i++) {
+ sched_domains_numa_masks[i] =
+ kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
+ if (!sched_domains_numa_masks[i])
+ return;
+
+ for (j = 0; j < nr_node_ids; j++) {
+ struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
+ if (!mask)
+ return;
+
+ sched_domains_numa_masks[i][j] = mask;
+
+ for_each_node(k) {
+ if (node_distance(j, k) > sched_domains_numa_distance[i])
+ continue;
+
+ cpumask_or(mask, mask, cpumask_of_node(k));
+ }
+ }
+ }
+
+ /* Compute default topology size */
+ for (i = 0; sched_domain_topology[i].mask; i++);
+
+ tl = kzalloc((i + level + 1) *
+ sizeof(struct sched_domain_topology_level), GFP_KERNEL);
+ if (!tl)
+ return;
+
+ /*
+ * Copy the default topology bits..
+ */
+ for (i = 0; sched_domain_topology[i].mask; i++)
+ tl[i] = sched_domain_topology[i];
+
+ /*
+ * .. and append 'j' levels of NUMA goodness.
+ */
+ for (j = 0; j < level; i++, j++) {
+ tl[i] = (struct sched_domain_topology_level){
+ .mask = sd_numa_mask,
+ .sd_flags = cpu_numa_flags,
+ .flags = SDTL_OVERLAP,
+ .numa_level = j,
+ SD_INIT_NAME(NUMA)
+ };
+ }
+
+ sched_domain_topology = tl;
+
+ sched_domains_numa_levels = level;
+ sched_max_numa_distance = sched_domains_numa_distance[level - 1];
+
+ init_numa_topology_type();
+}
+
+void sched_domains_numa_masks_set(unsigned int cpu)
+{
+ int node = cpu_to_node(cpu);
+ int i, j;
+
+ for (i = 0; i < sched_domains_numa_levels; i++) {
+ for (j = 0; j < nr_node_ids; j++) {
+ if (node_distance(j, node) <= sched_domains_numa_distance[i])
+ cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
+ }
+ }
+}
+
+void sched_domains_numa_masks_clear(unsigned int cpu)
+{
+ int i, j;
+
+ for (i = 0; i < sched_domains_numa_levels; i++) {
+ for (j = 0; j < nr_node_ids; j++)
+ cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
+ }
+}
+
+#endif /* CONFIG_NUMA */
+
+static int __sdt_alloc(const struct cpumask *cpu_map)
+{
+ struct sched_domain_topology_level *tl;
+ int j;
+
+ for_each_sd_topology(tl) {
+ struct sd_data *sdd = &tl->data;
+
+ sdd->sd = alloc_percpu(struct sched_domain *);
+ if (!sdd->sd)
+ return -ENOMEM;
+
+ sdd->sds = alloc_percpu(struct sched_domain_shared *);
+ if (!sdd->sds)
+ return -ENOMEM;
+
+ sdd->sg = alloc_percpu(struct sched_group *);
+ if (!sdd->sg)
+ return -ENOMEM;
+
+ sdd->sgc = alloc_percpu(struct sched_group_capacity *);
+ if (!sdd->sgc)
+ return -ENOMEM;
+
+ for_each_cpu(j, cpu_map) {
+ struct sched_domain *sd;
+ struct sched_domain_shared *sds;
+ struct sched_group *sg;
+ struct sched_group_capacity *sgc;
+
+ sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
+ GFP_KERNEL, cpu_to_node(j));
+ if (!sd)
+ return -ENOMEM;
+
+ *per_cpu_ptr(sdd->sd, j) = sd;
+
+ sds = kzalloc_node(sizeof(struct sched_domain_shared),
+ GFP_KERNEL, cpu_to_node(j));
+ if (!sds)
+ return -ENOMEM;
+
+ *per_cpu_ptr(sdd->sds, j) = sds;
+
+ sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+ GFP_KERNEL, cpu_to_node(j));
+ if (!sg)
+ return -ENOMEM;
+
+ sg->next = sg;
+
+ *per_cpu_ptr(sdd->sg, j) = sg;
+
+ sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(),
+ GFP_KERNEL, cpu_to_node(j));
+ if (!sgc)
+ return -ENOMEM;
+
+ *per_cpu_ptr(sdd->sgc, j) = sgc;
+ }
+ }
+
+ return 0;
+}
+
+static void __sdt_free(const struct cpumask *cpu_map)
+{
+ struct sched_domain_topology_level *tl;
+ int j;
+
+ for_each_sd_topology(tl) {
+ struct sd_data *sdd = &tl->data;
+
+ for_each_cpu(j, cpu_map) {
+ struct sched_domain *sd;
+
+ if (sdd->sd) {
+ sd = *per_cpu_ptr(sdd->sd, j);
+ if (sd && (sd->flags & SD_OVERLAP))
+ free_sched_groups(sd->groups, 0);
+ kfree(*per_cpu_ptr(sdd->sd, j));
+ }
+
+ if (sdd->sds)
+ kfree(*per_cpu_ptr(sdd->sds, j));
+ if (sdd->sg)
+ kfree(*per_cpu_ptr(sdd->sg, j));
+ if (sdd->sgc)
+ kfree(*per_cpu_ptr(sdd->sgc, j));
+ }
+ free_percpu(sdd->sd);
+ sdd->sd = NULL;
+ free_percpu(sdd->sds);
+ sdd->sds = NULL;
+ free_percpu(sdd->sg);
+ sdd->sg = NULL;
+ free_percpu(sdd->sgc);
+ sdd->sgc = NULL;
+ }
+}
+
+struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+ struct sched_domain *child, int cpu)
+{
+ struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);
+
+ if (child) {
+ sd->level = child->level + 1;
+ sched_domain_level_max = max(sched_domain_level_max, sd->level);
+ child->parent = sd;
+
+ if (!cpumask_subset(sched_domain_span(child),
+ sched_domain_span(sd))) {
+ pr_err("BUG: arch topology borken\n");
+#ifdef CONFIG_SCHED_DEBUG
+ pr_err(" the %s domain not a subset of the %s domain\n",
+ child->name, sd->name);
+#endif
+ /* Fixup, ensure @sd has at least @child cpus. */
+ cpumask_or(sched_domain_span(sd),
+ sched_domain_span(sd),
+ sched_domain_span(child));
+ }
+
+ }
+ set_domain_attribute(sd, attr);
+
+ return sd;
+}
+
+/*
+ * Build sched domains for a given set of CPUs and attach the sched domains
+ * to the individual CPUs
+ */
+static int
+build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr)
+{
+ enum s_alloc alloc_state;
+ struct sched_domain *sd;
+ struct s_data d;
+ struct rq *rq = NULL;
+ int i, ret = -ENOMEM;
+
+ alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
+ if (alloc_state != sa_rootdomain)
+ goto error;
+
+ /* Set up domains for CPUs specified by the cpu_map: */
+ for_each_cpu(i, cpu_map) {
+ struct sched_domain_topology_level *tl;
+
+ sd = NULL;
+ for_each_sd_topology(tl) {
+ sd = build_sched_domain(tl, cpu_map, attr, sd, i);
+ if (tl == sched_domain_topology)
+ *per_cpu_ptr(d.sd, i) = sd;
+ if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
+ sd->flags |= SD_OVERLAP;
+ if (cpumask_equal(cpu_map, sched_domain_span(sd)))
+ break;
+ }
+ }
+
+ /* Build the groups for the domains */
+ for_each_cpu(i, cpu_map) {
+ for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+ sd->span_weight = cpumask_weight(sched_domain_span(sd));
+ if (sd->flags & SD_OVERLAP) {
+ if (build_overlap_sched_groups(sd, i))
+ goto error;
+ } else {
+ if (build_sched_groups(sd, i))
+ goto error;
+ }
+ }
+ }
+
+ /* Calculate CPU capacity for physical packages and nodes */
+ for (i = nr_cpumask_bits-1; i >= 0; i--) {
+ if (!cpumask_test_cpu(i, cpu_map))
+ continue;
+
+ for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+ claim_allocations(i, sd);
+ init_sched_groups_capacity(i, sd);
+ }
+ }
+
+ /* Attach the domains */
+ rcu_read_lock();
+ for_each_cpu(i, cpu_map) {
+ rq = cpu_rq(i);
+ sd = *per_cpu_ptr(d.sd, i);
+
+ /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
+ if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
+ WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
+
+ cpu_attach_domain(sd, d.rd, i);
+ }
+ rcu_read_unlock();
+
+ if (rq && sched_debug_enabled) {
+ pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
+ cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
+ }
+
+ ret = 0;
+error:
+ __free_domain_allocs(&d, alloc_state, cpu_map);
+ return ret;
+}
+
+/* Current sched domains: */
+static cpumask_var_t *doms_cur;
+
+/* Number of sched domains in 'doms_cur': */
+static int ndoms_cur;
+
+/* Attribues of custom domains in 'doms_cur' */
+static struct sched_domain_attr *dattr_cur;
+
+/*
+ * Special case: If a kmalloc() of a doms_cur partition (array of
+ * cpumask) fails, then fallback to a single sched domain,
+ * as determined by the single cpumask fallback_doms.
+ */
+cpumask_var_t fallback_doms;
+
+/*
+ * arch_update_cpu_topology lets virtualized architectures update the
+ * CPU core maps. It is supposed to return 1 if the topology changed
+ * or 0 if it stayed the same.
+ */
+int __weak arch_update_cpu_topology(void)
+{
+ return 0;
+}
+
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
+{
+ int i;
+ cpumask_var_t *doms;
+
+ doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
+ if (!doms)
+ return NULL;
+ for (i = 0; i < ndoms; i++) {
+ if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
+ free_sched_domains(doms, i);
+ return NULL;
+ }
+ }
+ return doms;
+}
+
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
+{
+ unsigned int i;
+ for (i = 0; i < ndoms; i++)
+ free_cpumask_var(doms[i]);
+ kfree(doms);
+}
+
+/*
+ * Set up scheduler domains and groups. Callers must hold the hotplug lock.
+ * For now this just excludes isolated CPUs, but could be used to
+ * exclude other special cases in the future.
+ */
+int init_sched_domains(const struct cpumask *cpu_map)
+{
+ int err;
+
+ arch_update_cpu_topology();
+ ndoms_cur = 1;
+ doms_cur = alloc_sched_domains(ndoms_cur);
+ if (!doms_cur)
+ doms_cur = &fallback_doms;
+ cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
+ err = build_sched_domains(doms_cur[0], NULL);
+ register_sched_domain_sysctl();
+
+ return err;
+}
+
+/*
+ * Detach sched domains from a group of CPUs specified in cpu_map
+ * These CPUs will now be attached to the NULL domain
+ */
+static void detach_destroy_domains(const struct cpumask *cpu_map)
+{
+ int i;
+
+ rcu_read_lock();
+ for_each_cpu(i, cpu_map)
+ cpu_attach_domain(NULL, &def_root_domain, i);
+ rcu_read_unlock();
+}
+
+/* handle null as "default" */
+static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
+ struct sched_domain_attr *new, int idx_new)
+{
+ struct sched_domain_attr tmp;
+
+ /* Fast path: */
+ if (!new && !cur)
+ return 1;
+
+ tmp = SD_ATTR_INIT;
+ return !memcmp(cur ? (cur + idx_cur) : &tmp,
+ new ? (new + idx_new) : &tmp,
+ sizeof(struct sched_domain_attr));
+}
+
+/*
+ * Partition sched domains as specified by the 'ndoms_new'
+ * cpumasks in the array doms_new[] of cpumasks. This compares
+ * doms_new[] to the current sched domain partitioning, doms_cur[].
+ * It destroys each deleted domain and builds each new domain.
+ *
+ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
+ * The masks don't intersect (don't overlap.) We should setup one
+ * sched domain for each mask. CPUs not in any of the cpumasks will
+ * not be load balanced. If the same cpumask appears both in the
+ * current 'doms_cur' domains and in the new 'doms_new', we can leave
+ * it as it is.
+ *
+ * The passed in 'doms_new' should be allocated using
+ * alloc_sched_domains. This routine takes ownership of it and will
+ * free_sched_domains it when done with it. If the caller failed the
+ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms', it also forces the domains to be rebuilt.
+ *
+ * If doms_new == NULL it will be replaced with cpu_online_mask.
+ * ndoms_new == 0 is a special case for destroying existing domains,
+ * and it will not create the default domain.
+ *
+ * Call with hotplug lock held
+ */
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+ struct sched_domain_attr *dattr_new)
+{
+ int i, j, n;
+ int new_topology;
+
+ mutex_lock(&sched_domains_mutex);
+
+ /* Always unregister in case we don't destroy any domains: */
+ unregister_sched_domain_sysctl();
+
+ /* Let the architecture update CPU core mappings: */
+ new_topology = arch_update_cpu_topology();
+
+ n = doms_new ? ndoms_new : 0;
+
+ /* Destroy deleted domains: */
+ for (i = 0; i < ndoms_cur; i++) {
+ for (j = 0; j < n && !new_topology; j++) {
+ if (cpumask_equal(doms_cur[i], doms_new[j])
+ && dattrs_equal(dattr_cur, i, dattr_new, j))
+ goto match1;
+ }
+ /* No match - a current sched domain not in new doms_new[] */
+ detach_destroy_domains(doms_cur[i]);
+match1:
+ ;
+ }
+
+ n = ndoms_cur;
+ if (doms_new == NULL) {
+ n = 0;
+ doms_new = &fallback_doms;
+ cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
+ WARN_ON_ONCE(dattr_new);
+ }
+
+ /* Build new domains: */
+ for (i = 0; i < ndoms_new; i++) {
+ for (j = 0; j < n && !new_topology; j++) {
+ if (cpumask_equal(doms_new[i], doms_cur[j])
+ && dattrs_equal(dattr_new, i, dattr_cur, j))
+ goto match2;
+ }
+ /* No match - add a new doms_new */
+ build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
+match2:
+ ;
+ }
+
+ /* Remember the new sched domains: */
+ if (doms_cur != &fallback_doms)
+ free_sched_domains(doms_cur, ndoms_cur);
+
+ kfree(dattr_cur);
+ doms_cur = doms_new;
+ dattr_cur = dattr_new;
+ ndoms_cur = ndoms_new;
+
+ register_sched_domain_sysctl();
+
+ mutex_unlock(&sched_domains_mutex);
+}
+
diff --git a/kernel/signal.c b/kernel/signal.c
index 3603d93..13f9def 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1581,7 +1581,7 @@
unsigned long flags;
struct sighand_struct *psig;
bool autoreap = false;
- cputime_t utime, stime;
+ u64 utime, stime;
BUG_ON(sig == -1);
@@ -1620,8 +1620,8 @@
rcu_read_unlock();
task_cputime(tsk, &utime, &stime);
- info.si_utime = cputime_to_clock_t(utime + tsk->signal->utime);
- info.si_stime = cputime_to_clock_t(stime + tsk->signal->stime);
+ info.si_utime = nsec_to_clock_t(utime + tsk->signal->utime);
+ info.si_stime = nsec_to_clock_t(stime + tsk->signal->stime);
info.si_status = tsk->exit_code & 0x7f;
if (tsk->exit_code & 0x80)
@@ -1685,7 +1685,7 @@
unsigned long flags;
struct task_struct *parent;
struct sighand_struct *sighand;
- cputime_t utime, stime;
+ u64 utime, stime;
if (for_ptracer) {
parent = tsk->parent;
@@ -1705,8 +1705,8 @@
rcu_read_unlock();
task_cputime(tsk, &utime, &stime);
- info.si_utime = cputime_to_clock_t(utime);
- info.si_stime = cputime_to_clock_t(stime);
+ info.si_utime = nsec_to_clock_t(utime);
+ info.si_stime = nsec_to_clock_t(stime);
info.si_code = why;
switch (why) {
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index b6e4c16..9c15a91 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -18,10 +18,8 @@
if (WARN_ON(!trace->entries))
return;
- for (i = 0; i < trace->nr_entries; i++) {
- printk("%*c", 1 + spaces, ' ');
- print_ip_sym(trace->entries[i]);
- }
+ for (i = 0; i < trace->nr_entries; i++)
+ printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);
}
EXPORT_SYMBOL_GPL(print_stack_trace);
@@ -29,7 +27,6 @@
struct stack_trace *trace, int spaces)
{
int i;
- unsigned long ip;
int generated;
int total = 0;
@@ -37,9 +34,8 @@
return 0;
for (i = 0; i < trace->nr_entries; i++) {
- ip = trace->entries[i];
- generated = snprintf(buf, size, "%*c[<%p>] %pS\n",
- 1 + spaces, ' ', (void *) ip, (void *) ip);
+ generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ',
+ (void *)trace->entries[i]);
total += generated;
diff --git a/kernel/sys.c b/kernel/sys.c
index 842914e..7d4a9a6 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -881,15 +881,15 @@
void do_sys_times(struct tms *tms)
{
- cputime_t tgutime, tgstime, cutime, cstime;
+ u64 tgutime, tgstime, cutime, cstime;
thread_group_cputime_adjusted(current, &tgutime, &tgstime);
cutime = current->signal->cutime;
cstime = current->signal->cstime;
- tms->tms_utime = cputime_to_clock_t(tgutime);
- tms->tms_stime = cputime_to_clock_t(tgstime);
- tms->tms_cutime = cputime_to_clock_t(cutime);
- tms->tms_cstime = cputime_to_clock_t(cstime);
+ tms->tms_utime = nsec_to_clock_t(tgutime);
+ tms->tms_stime = nsec_to_clock_t(tgstime);
+ tms->tms_cutime = nsec_to_clock_t(cutime);
+ tms->tms_cstime = nsec_to_clock_t(cstime);
}
SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
@@ -1544,7 +1544,7 @@
{
struct task_struct *t;
unsigned long flags;
- cputime_t tgutime, tgstime, utime, stime;
+ u64 tgutime, tgstime, utime, stime;
unsigned long maxrss = 0;
memset((char *)r, 0, sizeof (*r));
@@ -1600,8 +1600,8 @@
unlock_task_sighand(p, &flags);
out:
- cputime_to_timeval(utime, &r->ru_utime);
- cputime_to_timeval(stime, &r->ru_stime);
+ r->ru_utime = ns_to_timeval(utime);
+ r->ru_stime = ns_to_timeval(stime);
if (who != RUSAGE_CHILDREN) {
struct mm_struct *mm = get_task_mm(p);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8dbaec0..bb260ce 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -416,7 +416,7 @@
},
{
.procname = "sched_rr_timeslice_ms",
- .data = &sched_rr_timeslice,
+ .data = &sysctl_sched_rr_timeslice,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = sched_rr_handler,
@@ -2475,6 +2475,7 @@
break;
if (neg)
continue;
+ val = convmul * val / convdiv;
if ((min && val < *min) || (max && val > *max))
continue;
*i = val;
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 976840d..938dbf3 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -15,6 +15,5 @@
endif
obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o
obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o
-obj-$(CONFIG_TIMER_STATS) += timer_stats.o
obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o
obj-$(CONFIG_TEST_UDELAY) += test_udelay.o
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 665985b..93621ae 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -141,6 +141,10 @@
{
cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
cs->flags |= CLOCK_SOURCE_UNSTABLE;
+
+ if (cs->mark_unstable)
+ cs->mark_unstable(cs);
+
if (finished_booting)
schedule_work(&watchdog_work);
}
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index c6ecedd..8e11d8d 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -94,17 +94,15 @@
};
static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+ /* Make sure we catch unsupported clockids */
+ [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES,
+
[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME,
[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC,
[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME,
[CLOCK_TAI] = HRTIMER_BASE_TAI,
};
-static inline int hrtimer_clockid_to_base(clockid_t clock_id)
-{
- return hrtimer_clock_to_base_table[clock_id];
-}
-
/*
* Functions and macros which are different for UP/SMP systems are kept in a
* single place
@@ -766,34 +764,6 @@
clock_was_set_delayed();
}
-static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
-{
-#ifdef CONFIG_TIMER_STATS
- if (timer->start_site)
- return;
- timer->start_site = __builtin_return_address(0);
- memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
- timer->start_pid = current->pid;
-#endif
-}
-
-static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer)
-{
-#ifdef CONFIG_TIMER_STATS
- timer->start_site = NULL;
-#endif
-}
-
-static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
-{
-#ifdef CONFIG_TIMER_STATS
- if (likely(!timer_stats_active))
- return;
- timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
- timer->function, timer->start_comm, 0);
-#endif
-}
-
/*
* Counterpart to lock_hrtimer_base above:
*/
@@ -932,7 +902,6 @@
* rare case and less expensive than a smp call.
*/
debug_deactivate(timer);
- timer_stats_hrtimer_clear_start_info(timer);
reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
if (!restart)
@@ -990,8 +959,6 @@
/* Switch the timer base, if necessary: */
new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
- timer_stats_hrtimer_set_start_info(timer);
-
leftmost = enqueue_hrtimer(timer, new_base);
if (!leftmost)
goto unlock;
@@ -1112,6 +1079,18 @@
}
#endif
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+ if (likely(clock_id < MAX_CLOCKS)) {
+ int base = hrtimer_clock_to_base_table[clock_id];
+
+ if (likely(base != HRTIMER_MAX_CLOCK_BASES))
+ return base;
+ }
+ WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id);
+ return HRTIMER_BASE_MONOTONIC;
+}
+
static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
enum hrtimer_mode mode)
{
@@ -1128,12 +1107,6 @@
base = hrtimer_clockid_to_base(clock_id);
timer->base = &cpu_base->clock_base[base];
timerqueue_init(&timer->node);
-
-#ifdef CONFIG_TIMER_STATS
- timer->start_site = NULL;
- timer->start_pid = -1;
- memset(timer->start_comm, 0, TASK_COMM_LEN);
-#endif
}
/**
@@ -1217,7 +1190,6 @@
raw_write_seqcount_barrier(&cpu_base->seq);
__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
- timer_stats_account_hrtimer(timer);
fn = timer->function;
/*
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 8c89143..a95f13c 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -45,16 +45,16 @@
static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
struct itimerval *const value)
{
- cputime_t cval, cinterval;
+ u64 val, interval;
struct cpu_itimer *it = &tsk->signal->it[clock_id];
spin_lock_irq(&tsk->sighand->siglock);
- cval = it->expires;
- cinterval = it->incr;
- if (cval) {
+ val = it->expires;
+ interval = it->incr;
+ if (val) {
struct task_cputime cputime;
- cputime_t t;
+ u64 t;
thread_group_cputimer(tsk, &cputime);
if (clock_id == CPUCLOCK_PROF)
@@ -63,17 +63,17 @@
/* CPUCLOCK_VIRT */
t = cputime.utime;
- if (cval < t)
+ if (val < t)
/* about to fire */
- cval = cputime_one_jiffy;
+ val = TICK_NSEC;
else
- cval = cval - t;
+ val -= t;
}
spin_unlock_irq(&tsk->sighand->siglock);
- cputime_to_timeval(cval, &value->it_value);
- cputime_to_timeval(cinterval, &value->it_interval);
+ value->it_value = ns_to_timeval(val);
+ value->it_interval = ns_to_timeval(interval);
}
int do_getitimer(int which, struct itimerval *value)
@@ -129,55 +129,35 @@
return HRTIMER_NORESTART;
}
-static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns)
-{
- struct timespec ts;
- s64 cpu_ns;
-
- cputime_to_timespec(ct, &ts);
- cpu_ns = timespec_to_ns(&ts);
-
- return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns;
-}
-
static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
const struct itimerval *const value,
struct itimerval *const ovalue)
{
- cputime_t cval, nval, cinterval, ninterval;
- s64 ns_ninterval, ns_nval;
- u32 error, incr_error;
+ u64 oval, nval, ointerval, ninterval;
struct cpu_itimer *it = &tsk->signal->it[clock_id];
- nval = timeval_to_cputime(&value->it_value);
- ns_nval = timeval_to_ns(&value->it_value);
- ninterval = timeval_to_cputime(&value->it_interval);
- ns_ninterval = timeval_to_ns(&value->it_interval);
-
- error = cputime_sub_ns(nval, ns_nval);
- incr_error = cputime_sub_ns(ninterval, ns_ninterval);
+ nval = timeval_to_ns(&value->it_value);
+ ninterval = timeval_to_ns(&value->it_interval);
spin_lock_irq(&tsk->sighand->siglock);
- cval = it->expires;
- cinterval = it->incr;
- if (cval || nval) {
+ oval = it->expires;
+ ointerval = it->incr;
+ if (oval || nval) {
if (nval > 0)
- nval += cputime_one_jiffy;
- set_process_cpu_timer(tsk, clock_id, &nval, &cval);
+ nval += TICK_NSEC;
+ set_process_cpu_timer(tsk, clock_id, &nval, &oval);
}
it->expires = nval;
it->incr = ninterval;
- it->error = error;
- it->incr_error = incr_error;
trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
spin_unlock_irq(&tsk->sighand->siglock);
if (ovalue) {
- cputime_to_timeval(cval, &ovalue->it_value);
- cputime_to_timeval(cinterval, &ovalue->it_interval);
+ ovalue->it_value = ns_to_timeval(oval);
+ ovalue->it_interval = ns_to_timeval(ointerval);
}
}
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index a4a0e47..7906b3f 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -27,19 +27,8 @@
#include "timekeeping.h"
-/* The Jiffies based clocksource is the lowest common
- * denominator clock source which should function on
- * all systems. It has the same coarse resolution as
- * the timer interrupt frequency HZ and it suffers
- * inaccuracies caused by missed or lost timer
- * interrupts and the inability for the timer
- * interrupt hardware to accuratly tick at the
- * requested HZ value. It is also not recommended
- * for "tick-less" systems.
- */
-#define NSEC_PER_JIFFY ((NSEC_PER_SEC+HZ/2)/HZ)
-/* Since jiffies uses a simple NSEC_PER_JIFFY multiplier
+/* Since jiffies uses a simple TICK_NSEC multiplier
* conversion, the .shift value could be zero. However
* this would make NTP adjustments impossible as they are
* in units of 1/2^.shift. Thus we use JIFFIES_SHIFT to
@@ -47,8 +36,8 @@
* amount, and give ntp adjustments in units of 1/2^8
*
* The value 8 is somewhat carefully chosen, as anything
- * larger can result in overflows. NSEC_PER_JIFFY grows as
- * HZ shrinks, so values greater than 8 overflow 32bits when
+ * larger can result in overflows. TICK_NSEC grows as HZ
+ * shrinks, so values greater than 8 overflow 32bits when
* HZ=100.
*/
#if HZ < 34
@@ -64,12 +53,23 @@
return (u64) jiffies;
}
+/*
+ * The Jiffies based clocksource is the lowest common
+ * denominator clock source which should function on
+ * all systems. It has the same coarse resolution as
+ * the timer interrupt frequency HZ and it suffers
+ * inaccuracies caused by missed or lost timer
+ * interrupts and the inability for the timer
+ * interrupt hardware to accuratly tick at the
+ * requested HZ value. It is also not recommended
+ * for "tick-less" systems.
+ */
static struct clocksource clocksource_jiffies = {
.name = "jiffies",
.rating = 1, /* lowest valid rating*/
.read = jiffies_read,
.mask = CLOCKSOURCE_MASK(32),
- .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
+ .mult = TICK_NSEC << JIFFIES_SHIFT, /* details above */
.shift = JIFFIES_SHIFT,
.max_cycles = 10,
};
@@ -125,7 +125,7 @@
shift_hz += cycles_per_tick/2;
do_div(shift_hz, cycles_per_tick);
/* Calculate nsec_per_tick using shift_hz */
- nsec_per_tick = (u64)NSEC_PER_SEC << 8;
+ nsec_per_tick = (u64)TICK_NSEC << 8;
nsec_per_tick += (u32)shift_hz/2;
do_div(nsec_per_tick, (u32)shift_hz);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index e9e8c10..b4377a5 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -20,10 +20,10 @@
*/
void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
{
- cputime_t cputime = secs_to_cputime(rlim_new);
+ u64 nsecs = rlim_new * NSEC_PER_SEC;
spin_lock_irq(&task->sighand->siglock);
- set_process_cpu_timer(task, CPUCLOCK_PROF, &cputime, NULL);
+ set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL);
spin_unlock_irq(&task->sighand->siglock);
}
@@ -50,39 +50,14 @@
return error;
}
-static inline unsigned long long
-timespec_to_sample(const clockid_t which_clock, const struct timespec *tp)
-{
- unsigned long long ret;
-
- ret = 0; /* high half always zero when .cpu used */
- if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
- ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
- } else {
- ret = cputime_to_expires(timespec_to_cputime(tp));
- }
- return ret;
-}
-
-static void sample_to_timespec(const clockid_t which_clock,
- unsigned long long expires,
- struct timespec *tp)
-{
- if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
- *tp = ns_to_timespec(expires);
- else
- cputime_to_timespec((__force cputime_t)expires, tp);
-}
-
/*
* Update expiry time from increment, and increase overrun count,
* given the current clock sample.
*/
-static void bump_cpu_timer(struct k_itimer *timer,
- unsigned long long now)
+static void bump_cpu_timer(struct k_itimer *timer, u64 now)
{
int i;
- unsigned long long delta, incr;
+ u64 delta, incr;
if (timer->it.cpu.incr == 0)
return;
@@ -122,21 +97,21 @@
return 0;
}
-static inline unsigned long long prof_ticks(struct task_struct *p)
+static inline u64 prof_ticks(struct task_struct *p)
{
- cputime_t utime, stime;
+ u64 utime, stime;
task_cputime(p, &utime, &stime);
- return cputime_to_expires(utime + stime);
+ return utime + stime;
}
-static inline unsigned long long virt_ticks(struct task_struct *p)
+static inline u64 virt_ticks(struct task_struct *p)
{
- cputime_t utime, stime;
+ u64 utime, stime;
task_cputime(p, &utime, &stime);
- return cputime_to_expires(utime);
+ return utime;
}
static int
@@ -176,8 +151,8 @@
/*
* Sample a per-thread clock for the given task.
*/
-static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
- unsigned long long *sample)
+static int cpu_clock_sample(const clockid_t which_clock,
+ struct task_struct *p, u64 *sample)
{
switch (CPUCLOCK_WHICH(which_clock)) {
default:
@@ -260,7 +235,7 @@
*/
static int cpu_clock_sample_group(const clockid_t which_clock,
struct task_struct *p,
- unsigned long long *sample)
+ u64 *sample)
{
struct task_cputime cputime;
@@ -269,11 +244,11 @@
return -EINVAL;
case CPUCLOCK_PROF:
thread_group_cputime(p, &cputime);
- *sample = cputime_to_expires(cputime.utime + cputime.stime);
+ *sample = cputime.utime + cputime.stime;
break;
case CPUCLOCK_VIRT:
thread_group_cputime(p, &cputime);
- *sample = cputime_to_expires(cputime.utime);
+ *sample = cputime.utime;
break;
case CPUCLOCK_SCHED:
thread_group_cputime(p, &cputime);
@@ -288,7 +263,7 @@
struct timespec *tp)
{
int err = -EINVAL;
- unsigned long long rtn;
+ u64 rtn;
if (CPUCLOCK_PERTHREAD(which_clock)) {
if (same_thread_group(tsk, current))
@@ -299,7 +274,7 @@
}
if (!err)
- sample_to_timespec(which_clock, rtn, tp);
+ *tp = ns_to_timespec(rtn);
return err;
}
@@ -453,7 +428,7 @@
cleanup_timers(tsk->signal->cpu_timers);
}
-static inline int expires_gt(cputime_t expires, cputime_t new_exp)
+static inline int expires_gt(u64 expires, u64 new_exp)
{
return expires == 0 || expires > new_exp;
}
@@ -488,7 +463,7 @@
list_add(&nt->entry, listpos);
if (listpos == head) {
- unsigned long long exp = nt->expires;
+ u64 exp = nt->expires;
/*
* We are the new earliest-expiring POSIX 1.b timer, hence
@@ -499,16 +474,15 @@
switch (CPUCLOCK_WHICH(timer->it_clock)) {
case CPUCLOCK_PROF:
- if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp)))
- cputime_expires->prof_exp = expires_to_cputime(exp);
+ if (expires_gt(cputime_expires->prof_exp, exp))
+ cputime_expires->prof_exp = exp;
break;
case CPUCLOCK_VIRT:
- if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp)))
- cputime_expires->virt_exp = expires_to_cputime(exp);
+ if (expires_gt(cputime_expires->virt_exp, exp))
+ cputime_expires->virt_exp = exp;
break;
case CPUCLOCK_SCHED:
- if (cputime_expires->sched_exp == 0 ||
- cputime_expires->sched_exp > exp)
+ if (expires_gt(cputime_expires->sched_exp, exp))
cputime_expires->sched_exp = exp;
break;
}
@@ -559,8 +533,7 @@
* traversal.
*/
static int cpu_timer_sample_group(const clockid_t which_clock,
- struct task_struct *p,
- unsigned long long *sample)
+ struct task_struct *p, u64 *sample)
{
struct task_cputime cputime;
@@ -569,10 +542,10 @@
default:
return -EINVAL;
case CPUCLOCK_PROF:
- *sample = cputime_to_expires(cputime.utime + cputime.stime);
+ *sample = cputime.utime + cputime.stime;
break;
case CPUCLOCK_VIRT:
- *sample = cputime_to_expires(cputime.utime);
+ *sample = cputime.utime;
break;
case CPUCLOCK_SCHED:
*sample = cputime.sum_exec_runtime;
@@ -593,12 +566,12 @@
unsigned long flags;
struct sighand_struct *sighand;
struct task_struct *p = timer->it.cpu.task;
- unsigned long long old_expires, new_expires, old_incr, val;
+ u64 old_expires, new_expires, old_incr, val;
int ret;
WARN_ON_ONCE(p == NULL);
- new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
+ new_expires = timespec_to_ns(&new->it_value);
/*
* Protect against sighand release/switch in exit/exec and p->cpu_timers
@@ -659,9 +632,7 @@
bump_cpu_timer(timer, val);
if (val < timer->it.cpu.expires) {
old_expires = timer->it.cpu.expires - val;
- sample_to_timespec(timer->it_clock,
- old_expires,
- &old->it_value);
+ old->it_value = ns_to_timespec(old_expires);
} else {
old->it_value.tv_nsec = 1;
old->it_value.tv_sec = 0;
@@ -699,8 +670,7 @@
* Install the new reload setting, and
* set up the signal and overrun bookkeeping.
*/
- timer->it.cpu.incr = timespec_to_sample(timer->it_clock,
- &new->it_interval);
+ timer->it.cpu.incr = timespec_to_ns(&new->it_interval);
/*
* This acts as a modification timestamp for the timer,
@@ -723,17 +693,15 @@
ret = 0;
out:
- if (old) {
- sample_to_timespec(timer->it_clock,
- old_incr, &old->it_interval);
- }
+ if (old)
+ old->it_interval = ns_to_timespec(old_incr);
return ret;
}
static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
{
- unsigned long long now;
+ u64 now;
struct task_struct *p = timer->it.cpu.task;
WARN_ON_ONCE(p == NULL);
@@ -741,8 +709,7 @@
/*
* Easy part: convert the reload time.
*/
- sample_to_timespec(timer->it_clock,
- timer->it.cpu.incr, &itp->it_interval);
+ itp->it_interval = ns_to_timespec(timer->it.cpu.incr);
if (timer->it.cpu.expires == 0) { /* Timer not armed at all. */
itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
@@ -771,8 +738,7 @@
* Call the timer disarmed, nothing else to do.
*/
timer->it.cpu.expires = 0;
- sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
- &itp->it_value);
+ itp->it_value = ns_to_timespec(timer->it.cpu.expires);
return;
} else {
cpu_timer_sample_group(timer->it_clock, p, &now);
@@ -781,9 +747,7 @@
}
if (now < timer->it.cpu.expires) {
- sample_to_timespec(timer->it_clock,
- timer->it.cpu.expires - now,
- &itp->it_value);
+ itp->it_value = ns_to_timespec(timer->it.cpu.expires - now);
} else {
/*
* The timer should have expired already, but the firing
@@ -827,7 +791,7 @@
struct list_head *timers = tsk->cpu_timers;
struct signal_struct *const sig = tsk->signal;
struct task_cputime *tsk_expires = &tsk->cputime_expires;
- unsigned long long expires;
+ u64 expires;
unsigned long soft;
/*
@@ -838,10 +802,10 @@
return;
expires = check_timers_list(timers, firing, prof_ticks(tsk));
- tsk_expires->prof_exp = expires_to_cputime(expires);
+ tsk_expires->prof_exp = expires;
expires = check_timers_list(++timers, firing, virt_ticks(tsk));
- tsk_expires->virt_exp = expires_to_cputime(expires);
+ tsk_expires->virt_exp = expires;
tsk_expires->sched_exp = check_timers_list(++timers, firing,
tsk->se.sum_exec_runtime);
@@ -890,26 +854,17 @@
tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER);
}
-static u32 onecputick;
-
static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
- unsigned long long *expires,
- unsigned long long cur_time, int signo)
+ u64 *expires, u64 cur_time, int signo)
{
if (!it->expires)
return;
if (cur_time >= it->expires) {
- if (it->incr) {
+ if (it->incr)
it->expires += it->incr;
- it->error += it->incr_error;
- if (it->error >= onecputick) {
- it->expires -= cputime_one_jiffy;
- it->error -= onecputick;
- }
- } else {
+ else
it->expires = 0;
- }
trace_itimer_expire(signo == SIGPROF ?
ITIMER_PROF : ITIMER_VIRTUAL,
@@ -917,9 +872,8 @@
__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
}
- if (it->expires && (!*expires || it->expires < *expires)) {
+ if (it->expires && (!*expires || it->expires < *expires))
*expires = it->expires;
- }
}
/*
@@ -931,8 +885,8 @@
struct list_head *firing)
{
struct signal_struct *const sig = tsk->signal;
- unsigned long long utime, ptime, virt_expires, prof_expires;
- unsigned long long sum_sched_runtime, sched_expires;
+ u64 utime, ptime, virt_expires, prof_expires;
+ u64 sum_sched_runtime, sched_expires;
struct list_head *timers = sig->cpu_timers;
struct task_cputime cputime;
unsigned long soft;
@@ -954,8 +908,8 @@
* Collect the current process totals.
*/
thread_group_cputimer(tsk, &cputime);
- utime = cputime_to_expires(cputime.utime);
- ptime = utime + cputime_to_expires(cputime.stime);
+ utime = cputime.utime;
+ ptime = utime + cputime.stime;
sum_sched_runtime = cputime.sum_exec_runtime;
prof_expires = check_timers_list(timers, firing, ptime);
@@ -971,10 +925,10 @@
SIGVTALRM);
soft = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
if (soft != RLIM_INFINITY) {
- unsigned long psecs = cputime_to_secs(ptime);
+ unsigned long psecs = div_u64(ptime, NSEC_PER_SEC);
unsigned long hard =
READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
- cputime_t x;
+ u64 x;
if (psecs >= hard) {
/*
* At the hard limit, we just die.
@@ -993,14 +947,13 @@
sig->rlim[RLIMIT_CPU].rlim_cur = soft;
}
}
- x = secs_to_cputime(soft);
- if (!prof_expires || x < prof_expires) {
+ x = soft * NSEC_PER_SEC;
+ if (!prof_expires || x < prof_expires)
prof_expires = x;
- }
}
- sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires);
- sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires);
+ sig->cputime_expires.prof_exp = prof_expires;
+ sig->cputime_expires.virt_exp = virt_expires;
sig->cputime_expires.sched_exp = sched_expires;
if (task_cputime_zero(&sig->cputime_expires))
stop_process_timers(sig);
@@ -1017,7 +970,7 @@
struct sighand_struct *sighand;
unsigned long flags;
struct task_struct *p = timer->it.cpu.task;
- unsigned long long now;
+ u64 now;
WARN_ON_ONCE(p == NULL);
@@ -1214,9 +1167,9 @@
* The tsk->sighand->siglock must be held by the caller.
*/
void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
- cputime_t *newval, cputime_t *oldval)
+ u64 *newval, u64 *oldval)
{
- unsigned long long now;
+ u64 now;
WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
cpu_timer_sample_group(clock_idx, tsk, &now);
@@ -1230,7 +1183,7 @@
if (*oldval) {
if (*oldval <= now) {
/* Just about to fire. */
- *oldval = cputime_one_jiffy;
+ *oldval = TICK_NSEC;
} else {
*oldval -= now;
}
@@ -1310,7 +1263,7 @@
/*
* We were interrupted by a signal.
*/
- sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
+ *rqtp = ns_to_timespec(timer.it.cpu.expires);
error = posix_cpu_timer_set(&timer, 0, &zero_it, it);
if (!error) {
/*
@@ -1476,15 +1429,10 @@
.clock_get = thread_cpu_clock_get,
.timer_create = thread_cpu_timer_create,
};
- struct timespec ts;
posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
- cputime_to_timespec(cputime_one_jiffy, &ts);
- onecputick = ts.tv_nsec;
- WARN_ON(ts.tv_sec != 0);
-
return 0;
}
__initcall(init_posix_cpu_timers);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 3109204..987e496 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -29,12 +29,13 @@
*/
static struct tick_device tick_broadcast_device;
-static cpumask_var_t tick_broadcast_mask;
-static cpumask_var_t tick_broadcast_on;
-static cpumask_var_t tmpmask;
-static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
+static cpumask_var_t tick_broadcast_mask __cpumask_var_read_mostly;
+static cpumask_var_t tick_broadcast_on __cpumask_var_read_mostly;
+static cpumask_var_t tmpmask __cpumask_var_read_mostly;
static int tick_broadcast_forced;
+static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
+
#ifdef CONFIG_TICK_ONESHOT
static void tick_broadcast_clear_oneshot(int cpu);
static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
@@ -347,17 +348,16 @@
*
* Called when the system enters a state where affected tick devices
* might stop. Note: TICK_BROADCAST_FORCE cannot be undone.
- *
- * Called with interrupts disabled, so clockevents_lock is not
- * required here because the local clock event device cannot go away
- * under us.
*/
void tick_broadcast_control(enum tick_broadcast_mode mode)
{
struct clock_event_device *bc, *dev;
struct tick_device *td;
int cpu, bc_stopped;
+ unsigned long flags;
+ /* Protects also the local clockevent device. */
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
td = this_cpu_ptr(&tick_cpu_device);
dev = td->evtdev;
@@ -365,12 +365,11 @@
* Is the device not affected by the powerstate ?
*/
if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP))
- return;
+ goto out;
if (!tick_device_is_functional(dev))
- return;
+ goto out;
- raw_spin_lock(&tick_broadcast_lock);
cpu = smp_processor_id();
bc = tick_broadcast_device.evtdev;
bc_stopped = cpumask_empty(tick_broadcast_mask);
@@ -420,7 +419,8 @@
tick_broadcast_setup_oneshot(bc);
}
}
- raw_spin_unlock(&tick_broadcast_lock);
+out:
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
EXPORT_SYMBOL_GPL(tick_broadcast_control);
@@ -517,9 +517,9 @@
#ifdef CONFIG_TICK_ONESHOT
-static cpumask_var_t tick_broadcast_oneshot_mask;
-static cpumask_var_t tick_broadcast_pending_mask;
-static cpumask_var_t tick_broadcast_force_mask;
+static cpumask_var_t tick_broadcast_oneshot_mask __cpumask_var_read_mostly;
+static cpumask_var_t tick_broadcast_pending_mask __cpumask_var_read_mostly;
+static cpumask_var_t tick_broadcast_force_mask __cpumask_var_read_mostly;
/*
* Exposed for debugging: see timer_list.c
diff --git a/kernel/time/time.c b/kernel/time/time.c
index a3a9a8a..25bdd25 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -702,6 +702,16 @@
#endif
}
+u64 jiffies64_to_nsecs(u64 j)
+{
+#if !(NSEC_PER_SEC % HZ)
+ return (NSEC_PER_SEC / HZ) * j;
+# else
+ return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN);
+#endif
+}
+EXPORT_SYMBOL(jiffies64_to_nsecs);
+
/**
* nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
*
diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc
index c486889..f83bbb8 100644
--- a/kernel/time/timeconst.bc
+++ b/kernel/time/timeconst.bc
@@ -98,6 +98,12 @@
print "#define HZ_TO_USEC_DEN\t\t", hz/cd, "\n"
print "#define USEC_TO_HZ_NUM\t\t", hz/cd, "\n"
print "#define USEC_TO_HZ_DEN\t\t", 1000000/cd, "\n"
+
+ cd=gcd(hz,1000000000)
+ print "#define HZ_TO_NSEC_NUM\t\t", 1000000000/cd, "\n"
+ print "#define HZ_TO_NSEC_DEN\t\t", hz/cd, "\n"
+ print "#define NSEC_TO_HZ_NUM\t\t", hz/cd, "\n"
+ print "#define NSEC_TO_HZ_DEN\t\t", 1000000000/cd, "\n"
print "\n"
print "#endif /* KERNEL_TIMECONST_H */\n"
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index db087d7e1..95b258d 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1275,27 +1275,8 @@
}
EXPORT_SYMBOL(timekeeping_inject_offset);
-
/**
- * timekeeping_get_tai_offset - Returns current TAI offset from UTC
- *
- */
-s32 timekeeping_get_tai_offset(void)
-{
- struct timekeeper *tk = &tk_core.timekeeper;
- unsigned int seq;
- s32 ret;
-
- do {
- seq = read_seqcount_begin(&tk_core.seq);
- ret = tk->tai_offset;
- } while (read_seqcount_retry(&tk_core.seq, seq));
-
- return ret;
-}
-
-/**
- * __timekeeping_set_tai_offset - Lock free worker function
+ * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic
*
*/
static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
@@ -1305,24 +1286,6 @@
}
/**
- * timekeeping_set_tai_offset - Sets the current TAI offset from UTC
- *
- */
-void timekeeping_set_tai_offset(s32 tai_offset)
-{
- struct timekeeper *tk = &tk_core.timekeeper;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&timekeeper_lock, flags);
- write_seqcount_begin(&tk_core.seq);
- __timekeeping_set_tai_offset(tk, tai_offset);
- timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
- write_seqcount_end(&tk_core.seq);
- raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
- clock_was_set();
-}
-
-/**
* change_clocksource - Swaps clocksources if a new one is available
*
* Accumulates current time interval and initializes new clocksource
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 704f595..d091467 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -11,8 +11,6 @@
extern int timekeeping_valid_for_hres(void);
extern u64 timekeeping_max_deferment(void);
extern int timekeeping_inject_offset(struct timespec *ts);
-extern s32 timekeeping_get_tai_offset(void);
-extern void timekeeping_set_tai_offset(s32 tai_offset);
extern int timekeeping_suspend(void);
extern void timekeeping_resume(void);
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index ca9fb80..38bc4d2 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -75,7 +75,7 @@
int bin = min(fls(t->tv_sec), NUM_BINS-1);
sleep_time_bin[bin]++;
- pr_info("Suspended for %lld.%03lu seconds\n", (s64)t->tv_sec,
- t->tv_nsec / NSEC_PER_MSEC);
+ printk_deferred(KERN_INFO "Suspended for %lld.%03lu seconds\n",
+ (s64)t->tv_sec, t->tv_nsec / NSEC_PER_MSEC);
}
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index ec33a69..82a6bfa 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -571,38 +571,6 @@
trigger_dyntick_cpu(base, timer);
}
-#ifdef CONFIG_TIMER_STATS
-void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
-{
- if (timer->start_site)
- return;
-
- timer->start_site = addr;
- memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
- timer->start_pid = current->pid;
-}
-
-static void timer_stats_account_timer(struct timer_list *timer)
-{
- void *site;
-
- /*
- * start_site can be concurrently reset by
- * timer_stats_timer_clear_start_info()
- */
- site = READ_ONCE(timer->start_site);
- if (likely(!site))
- return;
-
- timer_stats_update_stats(timer, timer->start_pid, site,
- timer->function, timer->start_comm,
- timer->flags);
-}
-
-#else
-static void timer_stats_account_timer(struct timer_list *timer) {}
-#endif
-
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
static struct debug_obj_descr timer_debug_descr;
@@ -789,11 +757,6 @@
{
timer->entry.pprev = NULL;
timer->flags = flags | raw_smp_processor_id();
-#ifdef CONFIG_TIMER_STATS
- timer->start_site = NULL;
- timer->start_pid = -1;
- memset(timer->start_comm, 0, TASK_COMM_LEN);
-#endif
lockdep_init_map(&timer->lockdep_map, name, key, 0);
}
@@ -1001,8 +964,6 @@
base = lock_timer_base(timer, &flags);
}
- timer_stats_timer_set_start_info(timer);
-
ret = detach_if_pending(timer, base, false);
if (!ret && pending_only)
goto out_unlock;
@@ -1130,7 +1091,6 @@
struct timer_base *new_base, *base;
unsigned long flags;
- timer_stats_timer_set_start_info(timer);
BUG_ON(timer_pending(timer) || !timer->function);
new_base = get_timer_cpu_base(timer->flags, cpu);
@@ -1176,7 +1136,6 @@
debug_assert_init(timer);
- timer_stats_timer_clear_start_info(timer);
if (timer_pending(timer)) {
base = lock_timer_base(timer, &flags);
ret = detach_if_pending(timer, base, true);
@@ -1204,10 +1163,9 @@
base = lock_timer_base(timer, &flags);
- if (base->running_timer != timer) {
- timer_stats_timer_clear_start_info(timer);
+ if (base->running_timer != timer)
ret = detach_if_pending(timer, base, true);
- }
+
spin_unlock_irqrestore(&base->lock, flags);
return ret;
@@ -1331,7 +1289,6 @@
unsigned long data;
timer = hlist_entry(head->first, struct timer_list, entry);
- timer_stats_account_timer(timer);
base->running_timer = timer;
detach_timer(timer, true);
@@ -1868,7 +1825,6 @@
void __init init_timers(void)
{
init_timer_cpus();
- init_timer_stats();
open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
}
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index afe6cd1..ff8d5c1 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -62,21 +62,11 @@
print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
int idx, u64 now)
{
-#ifdef CONFIG_TIMER_STATS
- char tmp[TASK_COMM_LEN + 1];
-#endif
SEQ_printf(m, " #%d: ", idx);
print_name_offset(m, taddr);
SEQ_printf(m, ", ");
print_name_offset(m, timer->function);
SEQ_printf(m, ", S:%02x", timer->state);
-#ifdef CONFIG_TIMER_STATS
- SEQ_printf(m, ", ");
- print_name_offset(m, timer->start_site);
- memcpy(tmp, timer->start_comm, TASK_COMM_LEN);
- tmp[TASK_COMM_LEN] = 0;
- SEQ_printf(m, ", %s/%d", tmp, timer->start_pid);
-#endif
SEQ_printf(m, "\n");
SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n",
(unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)),
@@ -127,7 +117,7 @@
SEQ_printf(m, " .base: %pK\n", base);
SEQ_printf(m, " .index: %d\n", base->index);
- SEQ_printf(m, " .resolution: %u nsecs\n", (unsigned) hrtimer_resolution);
+ SEQ_printf(m, " .resolution: %u nsecs\n", hrtimer_resolution);
SEQ_printf(m, " .get_time: ");
print_name_offset(m, base->get_time);
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
deleted file mode 100644
index afddded..0000000
--- a/kernel/time/timer_stats.c
+++ /dev/null
@@ -1,425 +0,0 @@
-/*
- * kernel/time/timer_stats.c
- *
- * Collect timer usage statistics.
- *
- * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
- * Copyright(C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
- *
- * timer_stats is based on timer_top, a similar functionality which was part of
- * Con Kolivas dyntick patch set. It was developed by Daniel Petrini at the
- * Instituto Nokia de Tecnologia - INdT - Manaus. timer_top's design was based
- * on dynamic allocation of the statistics entries and linear search based
- * lookup combined with a global lock, rather than the static array, hash
- * and per-CPU locking which is used by timer_stats. It was written for the
- * pre hrtimer kernel code and therefore did not take hrtimers into account.
- * Nevertheless it provided the base for the timer_stats implementation and
- * was a helpful source of inspiration. Kudos to Daniel and the Nokia folks
- * for this effort.
- *
- * timer_top.c is
- * Copyright (C) 2005 Instituto Nokia de Tecnologia - INdT - Manaus
- * Written by Daniel Petrini <d.pensator@gmail.com>
- * timer_top.c was released under the GNU General Public License version 2
- *
- * We export the addresses and counting of timer functions being called,
- * the pid and cmdline from the owner process if applicable.
- *
- * Start/stop data collection:
- * # echo [1|0] >/proc/timer_stats
- *
- * Display the information collected so far:
- * # cat /proc/timer_stats
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/proc_fs.h>
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/sched.h>
-#include <linux/seq_file.h>
-#include <linux/kallsyms.h>
-
-#include <linux/uaccess.h>
-
-/*
- * This is our basic unit of interest: a timer expiry event identified
- * by the timer, its start/expire functions and the PID of the task that
- * started the timer. We count the number of times an event happens:
- */
-struct entry {
- /*
- * Hash list:
- */
- struct entry *next;
-
- /*
- * Hash keys:
- */
- void *timer;
- void *start_func;
- void *expire_func;
- pid_t pid;
-
- /*
- * Number of timeout events:
- */
- unsigned long count;
- u32 flags;
-
- /*
- * We save the command-line string to preserve
- * this information past task exit:
- */
- char comm[TASK_COMM_LEN + 1];
-
-} ____cacheline_aligned_in_smp;
-
-/*
- * Spinlock protecting the tables - not taken during lookup:
- */
-static DEFINE_RAW_SPINLOCK(table_lock);
-
-/*
- * Per-CPU lookup locks for fast hash lookup:
- */
-static DEFINE_PER_CPU(raw_spinlock_t, tstats_lookup_lock);
-
-/*
- * Mutex to serialize state changes with show-stats activities:
- */
-static DEFINE_MUTEX(show_mutex);
-
-/*
- * Collection status, active/inactive:
- */
-int __read_mostly timer_stats_active;
-
-/*
- * Beginning/end timestamps of measurement:
- */
-static ktime_t time_start, time_stop;
-
-/*
- * tstat entry structs only get allocated while collection is
- * active and never freed during that time - this simplifies
- * things quite a bit.
- *
- * They get freed when a new collection period is started.
- */
-#define MAX_ENTRIES_BITS 10
-#define MAX_ENTRIES (1UL << MAX_ENTRIES_BITS)
-
-static unsigned long nr_entries;
-static struct entry entries[MAX_ENTRIES];
-
-static atomic_t overflow_count;
-
-/*
- * The entries are in a hash-table, for fast lookup:
- */
-#define TSTAT_HASH_BITS (MAX_ENTRIES_BITS - 1)
-#define TSTAT_HASH_SIZE (1UL << TSTAT_HASH_BITS)
-#define TSTAT_HASH_MASK (TSTAT_HASH_SIZE - 1)
-
-#define __tstat_hashfn(entry) \
- (((unsigned long)(entry)->timer ^ \
- (unsigned long)(entry)->start_func ^ \
- (unsigned long)(entry)->expire_func ^ \
- (unsigned long)(entry)->pid ) & TSTAT_HASH_MASK)
-
-#define tstat_hashentry(entry) (tstat_hash_table + __tstat_hashfn(entry))
-
-static struct entry *tstat_hash_table[TSTAT_HASH_SIZE] __read_mostly;
-
-static void reset_entries(void)
-{
- nr_entries = 0;
- memset(entries, 0, sizeof(entries));
- memset(tstat_hash_table, 0, sizeof(tstat_hash_table));
- atomic_set(&overflow_count, 0);
-}
-
-static struct entry *alloc_entry(void)
-{
- if (nr_entries >= MAX_ENTRIES)
- return NULL;
-
- return entries + nr_entries++;
-}
-
-static int match_entries(struct entry *entry1, struct entry *entry2)
-{
- return entry1->timer == entry2->timer &&
- entry1->start_func == entry2->start_func &&
- entry1->expire_func == entry2->expire_func &&
- entry1->pid == entry2->pid;
-}
-
-/*
- * Look up whether an entry matching this item is present
- * in the hash already. Must be called with irqs off and the
- * lookup lock held:
- */
-static struct entry *tstat_lookup(struct entry *entry, char *comm)
-{
- struct entry **head, *curr, *prev;
-
- head = tstat_hashentry(entry);
- curr = *head;
-
- /*
- * The fastpath is when the entry is already hashed,
- * we do this with the lookup lock held, but with the
- * table lock not held:
- */
- while (curr) {
- if (match_entries(curr, entry))
- return curr;
-
- curr = curr->next;
- }
- /*
- * Slowpath: allocate, set up and link a new hash entry:
- */
- prev = NULL;
- curr = *head;
-
- raw_spin_lock(&table_lock);
- /*
- * Make sure we have not raced with another CPU:
- */
- while (curr) {
- if (match_entries(curr, entry))
- goto out_unlock;
-
- prev = curr;
- curr = curr->next;
- }
-
- curr = alloc_entry();
- if (curr) {
- *curr = *entry;
- curr->count = 0;
- curr->next = NULL;
- memcpy(curr->comm, comm, TASK_COMM_LEN);
-
- smp_mb(); /* Ensure that curr is initialized before insert */
-
- if (prev)
- prev->next = curr;
- else
- *head = curr;
- }
- out_unlock:
- raw_spin_unlock(&table_lock);
-
- return curr;
-}
-
-/**
- * timer_stats_update_stats - Update the statistics for a timer.
- * @timer: pointer to either a timer_list or a hrtimer
- * @pid: the pid of the task which set up the timer
- * @startf: pointer to the function which did the timer setup
- * @timerf: pointer to the timer callback function of the timer
- * @comm: name of the process which set up the timer
- * @tflags: The flags field of the timer
- *
- * When the timer is already registered, then the event counter is
- * incremented. Otherwise the timer is registered in a free slot.
- */
-void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
- void *timerf, char *comm, u32 tflags)
-{
- /*
- * It doesn't matter which lock we take:
- */
- raw_spinlock_t *lock;
- struct entry *entry, input;
- unsigned long flags;
-
- if (likely(!timer_stats_active))
- return;
-
- lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id());
-
- input.timer = timer;
- input.start_func = startf;
- input.expire_func = timerf;
- input.pid = pid;
- input.flags = tflags;
-
- raw_spin_lock_irqsave(lock, flags);
- if (!timer_stats_active)
- goto out_unlock;
-
- entry = tstat_lookup(&input, comm);
- if (likely(entry))
- entry->count++;
- else
- atomic_inc(&overflow_count);
-
- out_unlock:
- raw_spin_unlock_irqrestore(lock, flags);
-}
-
-static void print_name_offset(struct seq_file *m, unsigned long addr)
-{
- char symname[KSYM_NAME_LEN];
-
- if (lookup_symbol_name(addr, symname) < 0)
- seq_printf(m, "<%p>", (void *)addr);
- else
- seq_printf(m, "%s", symname);
-}
-
-static int tstats_show(struct seq_file *m, void *v)
-{
- struct timespec64 period;
- struct entry *entry;
- unsigned long ms;
- long events = 0;
- ktime_t time;
- int i;
-
- mutex_lock(&show_mutex);
- /*
- * If still active then calculate up to now:
- */
- if (timer_stats_active)
- time_stop = ktime_get();
-
- time = ktime_sub(time_stop, time_start);
-
- period = ktime_to_timespec64(time);
- ms = period.tv_nsec / 1000000;
-
- seq_puts(m, "Timer Stats Version: v0.3\n");
- seq_printf(m, "Sample period: %ld.%03ld s\n", (long)period.tv_sec, ms);
- if (atomic_read(&overflow_count))
- seq_printf(m, "Overflow: %d entries\n", atomic_read(&overflow_count));
- seq_printf(m, "Collection: %s\n", timer_stats_active ? "active" : "inactive");
-
- for (i = 0; i < nr_entries; i++) {
- entry = entries + i;
- if (entry->flags & TIMER_DEFERRABLE) {
- seq_printf(m, "%4luD, %5d %-16s ",
- entry->count, entry->pid, entry->comm);
- } else {
- seq_printf(m, " %4lu, %5d %-16s ",
- entry->count, entry->pid, entry->comm);
- }
-
- print_name_offset(m, (unsigned long)entry->start_func);
- seq_puts(m, " (");
- print_name_offset(m, (unsigned long)entry->expire_func);
- seq_puts(m, ")\n");
-
- events += entry->count;
- }
-
- ms += period.tv_sec * 1000;
- if (!ms)
- ms = 1;
-
- if (events && period.tv_sec)
- seq_printf(m, "%ld total events, %ld.%03ld events/sec\n",
- events, events * 1000 / ms,
- (events * 1000000 / ms) % 1000);
- else
- seq_printf(m, "%ld total events\n", events);
-
- mutex_unlock(&show_mutex);
-
- return 0;
-}
-
-/*
- * After a state change, make sure all concurrent lookup/update
- * activities have stopped:
- */
-static void sync_access(void)
-{
- unsigned long flags;
- int cpu;
-
- for_each_online_cpu(cpu) {
- raw_spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu);
-
- raw_spin_lock_irqsave(lock, flags);
- /* nothing */
- raw_spin_unlock_irqrestore(lock, flags);
- }
-}
-
-static ssize_t tstats_write(struct file *file, const char __user *buf,
- size_t count, loff_t *offs)
-{
- char ctl[2];
-
- if (count != 2 || *offs)
- return -EINVAL;
-
- if (copy_from_user(ctl, buf, count))
- return -EFAULT;
-
- mutex_lock(&show_mutex);
- switch (ctl[0]) {
- case '0':
- if (timer_stats_active) {
- timer_stats_active = 0;
- time_stop = ktime_get();
- sync_access();
- }
- break;
- case '1':
- if (!timer_stats_active) {
- reset_entries();
- time_start = ktime_get();
- smp_mb();
- timer_stats_active = 1;
- }
- break;
- default:
- count = -EINVAL;
- }
- mutex_unlock(&show_mutex);
-
- return count;
-}
-
-static int tstats_open(struct inode *inode, struct file *filp)
-{
- return single_open(filp, tstats_show, NULL);
-}
-
-static const struct file_operations tstats_fops = {
- .open = tstats_open,
- .read = seq_read,
- .write = tstats_write,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-void __init init_timer_stats(void)
-{
- int cpu;
-
- for_each_possible_cpu(cpu)
- raw_spin_lock_init(&per_cpu(tstats_lookup_lock, cpu));
-}
-
-static int __init init_tstats_procfs(void)
-{
- struct proc_dir_entry *pe;
-
- pe = proc_create("timer_stats", 0644, NULL, &tstats_fops);
- if (!pe)
- return -ENOMEM;
- return 0;
-}
-__initcall(init_tstats_procfs);
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 775569e..af344a1b 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -266,7 +266,7 @@
static struct cpumask save_cpumask;
static bool disable_migrate;
-static void move_to_next_cpu(void)
+static void move_to_next_cpu(bool initmask)
{
static struct cpumask *current_mask;
int next_cpu;
@@ -275,7 +275,7 @@
return;
/* Just pick the first CPU on first iteration */
- if (!current_mask) {
+ if (initmask) {
current_mask = &save_cpumask;
get_online_cpus();
cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
@@ -330,10 +330,12 @@
static int kthread_fn(void *data)
{
u64 interval;
+ bool initmask = true;
while (!kthread_should_stop()) {
- move_to_next_cpu();
+ move_to_next_cpu(initmask);
+ initmask = false;
local_irq_disable();
get_sample();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index a133ecd..7ad9e53 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1372,7 +1372,7 @@
return a1 + a2 + a3 + a4 + a5 + a6;
}
-static struct __init trace_event_file *
+static __init struct trace_event_file *
find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr)
{
struct trace_event_file *file;
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index f8e26ab..5c21f05 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -31,7 +31,7 @@
struct taskstats *stats, struct task_struct *tsk)
{
const struct cred *tcred;
- cputime_t utime, stime, utimescaled, stimescaled;
+ u64 utime, stime, utimescaled, stimescaled;
u64 delta;
BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN);
@@ -67,12 +67,12 @@
rcu_read_unlock();
task_cputime(tsk, &utime, &stime);
- stats->ac_utime = cputime_to_usecs(utime);
- stats->ac_stime = cputime_to_usecs(stime);
+ stats->ac_utime = div_u64(utime, NSEC_PER_USEC);
+ stats->ac_stime = div_u64(stime, NSEC_PER_USEC);
task_cputime_scaled(tsk, &utimescaled, &stimescaled);
- stats->ac_utimescaled = cputime_to_usecs(utimescaled);
- stats->ac_stimescaled = cputime_to_usecs(stimescaled);
+ stats->ac_utimescaled = div_u64(utimescaled, NSEC_PER_USEC);
+ stats->ac_stimescaled = div_u64(stimescaled, NSEC_PER_USEC);
stats->ac_minflt = tsk->min_flt;
stats->ac_majflt = tsk->maj_flt;
@@ -123,18 +123,15 @@
#undef MB
static void __acct_update_integrals(struct task_struct *tsk,
- cputime_t utime, cputime_t stime)
+ u64 utime, u64 stime)
{
- cputime_t time, dtime;
- u64 delta;
+ u64 time, delta;
if (!likely(tsk->mm))
return;
time = stime + utime;
- dtime = time - tsk->acct_timexpd;
- /* Avoid division: cputime_t is often in nanoseconds already. */
- delta = cputime_to_nsecs(dtime);
+ delta = time - tsk->acct_timexpd;
if (delta < TICK_NSEC)
return;
@@ -155,7 +152,7 @@
*/
void acct_update_integrals(struct task_struct *tsk)
{
- cputime_t utime, stime;
+ u64 utime, stime;
unsigned long flags;
local_irq_save(flags);
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 9d20d5d..95c6336 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -128,10 +128,10 @@
struct hlist_head *hashent = ucounts_hashentry(ns, uid);
struct ucounts *ucounts, *new;
- spin_lock(&ucounts_lock);
+ spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
if (!ucounts) {
- spin_unlock(&ucounts_lock);
+ spin_unlock_irq(&ucounts_lock);
new = kzalloc(sizeof(*new), GFP_KERNEL);
if (!new)
@@ -141,7 +141,7 @@
new->uid = uid;
atomic_set(&new->count, 0);
- spin_lock(&ucounts_lock);
+ spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
if (ucounts) {
kfree(new);
@@ -152,16 +152,18 @@
}
if (!atomic_add_unless(&ucounts->count, 1, INT_MAX))
ucounts = NULL;
- spin_unlock(&ucounts_lock);
+ spin_unlock_irq(&ucounts_lock);
return ucounts;
}
static void put_ucounts(struct ucounts *ucounts)
{
+ unsigned long flags;
+
if (atomic_dec_and_test(&ucounts->count)) {
- spin_lock(&ucounts_lock);
+ spin_lock_irqsave(&ucounts_lock, flags);
hlist_del_init(&ucounts->node);
- spin_unlock(&ucounts_lock);
+ spin_unlock_irqrestore(&ucounts_lock, flags);
kfree(ucounts);
}
@@ -225,11 +227,10 @@
* properly.
*/
user_header = register_sysctl("user", empty);
+ kmemleak_ignore(user_header);
BUG_ON(!user_header);
BUG_ON(!setup_userns_sysctls(&init_user_ns));
#endif
return 0;
}
subsys_initcall(user_namespace_sysctl_init);
-
-
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index d4b0fa0..63177be 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -49,6 +49,8 @@
#define for_each_watchdog_cpu(cpu) \
for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
+atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
+
/*
* The 'watchdog_running' variable is set to 1 when the watchdog threads
* are registered/started and is set to 0 when the watchdog threads are
@@ -260,6 +262,9 @@
int duration;
int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
+ if (atomic_read(&watchdog_park_in_progress) != 0)
+ return HRTIMER_NORESTART;
+
/* kick the hardlockup detector */
watchdog_interrupt_count();
@@ -467,12 +472,16 @@
{
int cpu, ret = 0;
+ atomic_set(&watchdog_park_in_progress, 1);
+
for_each_watchdog_cpu(cpu) {
ret = kthread_park(per_cpu(softlockup_watchdog, cpu));
if (ret)
break;
}
+ atomic_set(&watchdog_park_in_progress, 0);
+
return ret;
}
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 84016c8..12b8dd6 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -84,6 +84,9 @@
/* Ensure the watchdog never gets throttled */
event->hw.interrupts = 0;
+ if (atomic_read(&watchdog_park_in_progress) != 0)
+ return;
+
if (__this_cpu_read(watchdog_nmi_touch) == true) {
__this_cpu_write(watchdog_nmi_touch, false);
return;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1d9fb65..072cbc9 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1523,8 +1523,6 @@
return;
}
- timer_stats_timer_set_start_info(&dwork->timer);
-
dwork->wq = wq;
dwork->cpu = cpu;
timer->expires = jiffies + delay;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8f1f0e6..acedbe6 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -993,20 +993,6 @@
If unsure, say N.
-config TIMER_STATS
- bool "Collect kernel timers statistics"
- depends on DEBUG_KERNEL && PROC_FS
- help
- If you say Y here, additional code will be inserted into the
- timer routines to collect statistics about kernel timers being
- reprogrammed. The statistics can be read from /proc/timer_stats.
- The statistics collection is started by writing 1 to /proc/timer_stats,
- writing 0 stops it. This feature is useful to collect information
- about timer usage patterns in kernel and userspace. This feature
- is lightweight if enabled in the kernel config but not activated
- (it defaults to deactivated on bootup and will only be activated
- if some application like powertop activates it explicitly).
-
config DEBUG_PREEMPT
bool "Debug preemptible kernel"
depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT
@@ -1475,6 +1461,7 @@
config RCU_TRACE
bool "Enable tracing for RCU"
depends on DEBUG_KERNEL
+ default y if TREE_RCU
select TRACE_CLOCK
help
This option provides tracing in RCU which presents stats
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 04c1ef7..8c28cbd 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -52,9 +52,18 @@
static int debug_objects_warnings __read_mostly;
static int debug_objects_enabled __read_mostly
= CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT;
-
+static int debug_objects_pool_size __read_mostly
+ = ODEBUG_POOL_SIZE;
+static int debug_objects_pool_min_level __read_mostly
+ = ODEBUG_POOL_MIN_LEVEL;
static struct debug_obj_descr *descr_test __read_mostly;
+/*
+ * Track numbers of kmem_cache_alloc()/free() calls done.
+ */
+static int debug_objects_allocated;
+static int debug_objects_freed;
+
static void free_obj_work(struct work_struct *work);
static DECLARE_WORK(debug_obj_work, free_obj_work);
@@ -88,13 +97,13 @@
struct debug_obj *new;
unsigned long flags;
- if (likely(obj_pool_free >= ODEBUG_POOL_MIN_LEVEL))
+ if (likely(obj_pool_free >= debug_objects_pool_min_level))
return;
if (unlikely(!obj_cache))
return;
- while (obj_pool_free < ODEBUG_POOL_MIN_LEVEL) {
+ while (obj_pool_free < debug_objects_pool_min_level) {
new = kmem_cache_zalloc(obj_cache, gfp);
if (!new)
@@ -102,6 +111,7 @@
raw_spin_lock_irqsave(&pool_lock, flags);
hlist_add_head(&new->node, &obj_pool);
+ debug_objects_allocated++;
obj_pool_free++;
raw_spin_unlock_irqrestore(&pool_lock, flags);
}
@@ -162,24 +172,39 @@
/*
* workqueue function to free objects.
+ *
+ * To reduce contention on the global pool_lock, the actual freeing of
+ * debug objects will be delayed if the pool_lock is busy. We also free
+ * the objects in a batch of 4 for each lock/unlock cycle.
*/
+#define ODEBUG_FREE_BATCH 4
+
static void free_obj_work(struct work_struct *work)
{
- struct debug_obj *obj;
+ struct debug_obj *objs[ODEBUG_FREE_BATCH];
unsigned long flags;
+ int i;
- raw_spin_lock_irqsave(&pool_lock, flags);
- while (obj_pool_free > ODEBUG_POOL_SIZE) {
- obj = hlist_entry(obj_pool.first, typeof(*obj), node);
- hlist_del(&obj->node);
- obj_pool_free--;
+ if (!raw_spin_trylock_irqsave(&pool_lock, flags))
+ return;
+ while (obj_pool_free >= debug_objects_pool_size + ODEBUG_FREE_BATCH) {
+ for (i = 0; i < ODEBUG_FREE_BATCH; i++) {
+ objs[i] = hlist_entry(obj_pool.first,
+ typeof(*objs[0]), node);
+ hlist_del(&objs[i]->node);
+ }
+
+ obj_pool_free -= ODEBUG_FREE_BATCH;
+ debug_objects_freed += ODEBUG_FREE_BATCH;
/*
* We release pool_lock across kmem_cache_free() to
* avoid contention on pool_lock.
*/
raw_spin_unlock_irqrestore(&pool_lock, flags);
- kmem_cache_free(obj_cache, obj);
- raw_spin_lock_irqsave(&pool_lock, flags);
+ for (i = 0; i < ODEBUG_FREE_BATCH; i++)
+ kmem_cache_free(obj_cache, objs[i]);
+ if (!raw_spin_trylock_irqsave(&pool_lock, flags))
+ return;
}
raw_spin_unlock_irqrestore(&pool_lock, flags);
}
@@ -198,7 +223,7 @@
* schedule work when the pool is filled and the cache is
* initialized:
*/
- if (obj_pool_free > ODEBUG_POOL_SIZE && obj_cache)
+ if (obj_pool_free > debug_objects_pool_size && obj_cache)
sched = 1;
hlist_add_head(&obj->node, &obj_pool);
obj_pool_free++;
@@ -758,6 +783,8 @@
seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free);
seq_printf(m, "pool_used :%d\n", obj_pool_used);
seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used);
+ seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated);
+ seq_printf(m, "objs_freed :%d\n", debug_objects_freed);
return 0;
}
@@ -1116,4 +1143,11 @@
pr_warn("out of memory.\n");
} else
debug_objects_selftest();
+
+ /*
+ * Increase the thresholds for allocating and freeing objects
+ * according to the number of possible CPUs available in the system.
+ */
+ debug_objects_pool_size += num_possible_cpus() * 32;
+ debug_objects_pool_min_level += num_possible_cpus() * 4;
}
diff --git a/lib/ioremap.c b/lib/ioremap.c
index 86c8911..a3e14ce 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -144,4 +144,3 @@
return err;
}
-EXPORT_SYMBOL_GPL(ioremap_page_range);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 25f5723..e68604a 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -730,43 +730,50 @@
}
EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
-static void pipe_advance(struct iov_iter *i, size_t size)
+static inline void pipe_truncate(struct iov_iter *i)
{
struct pipe_inode_info *pipe = i->pipe;
- struct pipe_buffer *buf;
- int idx = i->idx;
- size_t off = i->iov_offset, orig_sz;
-
- if (unlikely(i->count < size))
- size = i->count;
- orig_sz = size;
-
- if (size) {
- if (off) /* make it relative to the beginning of buffer */
- size += off - pipe->bufs[idx].offset;
- while (1) {
- buf = &pipe->bufs[idx];
- if (size <= buf->len)
- break;
- size -= buf->len;
- idx = next_idx(idx, pipe);
- }
- buf->len = size;
- i->idx = idx;
- off = i->iov_offset = buf->offset + size;
- }
- if (off)
- idx = next_idx(idx, pipe);
if (pipe->nrbufs) {
- int unused = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
- /* [curbuf,unused) is in use. Free [idx,unused) */
- while (idx != unused) {
+ size_t off = i->iov_offset;
+ int idx = i->idx;
+ int nrbufs = (idx - pipe->curbuf) & (pipe->buffers - 1);
+ if (off) {
+ pipe->bufs[idx].len = off - pipe->bufs[idx].offset;
+ idx = next_idx(idx, pipe);
+ nrbufs++;
+ }
+ while (pipe->nrbufs > nrbufs) {
pipe_buf_release(pipe, &pipe->bufs[idx]);
idx = next_idx(idx, pipe);
pipe->nrbufs--;
}
}
- i->count -= orig_sz;
+}
+
+static void pipe_advance(struct iov_iter *i, size_t size)
+{
+ struct pipe_inode_info *pipe = i->pipe;
+ if (unlikely(i->count < size))
+ size = i->count;
+ if (size) {
+ struct pipe_buffer *buf;
+ size_t off = i->iov_offset, left = size;
+ int idx = i->idx;
+ if (off) /* make it relative to the beginning of buffer */
+ left += off - pipe->bufs[idx].offset;
+ while (1) {
+ buf = &pipe->bufs[idx];
+ if (left <= buf->len)
+ break;
+ left -= buf->len;
+ idx = next_idx(idx, pipe);
+ }
+ i->idx = idx;
+ i->iov_offset = buf->offset + left;
+ }
+ i->count -= size;
+ /* ... and discard everything past that point */
+ pipe_truncate(i);
}
void iov_iter_advance(struct iov_iter *i, size_t size)
@@ -826,6 +833,7 @@
size_t count)
{
BUG_ON(direction != ITER_PIPE);
+ WARN_ON(pipe->nrbufs == pipe->buffers);
i->type = direction;
i->pipe = pipe;
i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 0b92d60..84812a9 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -769,7 +769,7 @@
struct radix_tree_node *old = child;
offset = child->offset + 1;
child = child->parent;
- WARN_ON_ONCE(!list_empty(&node->private_list));
+ WARN_ON_ONCE(!list_empty(&old->private_list));
radix_tree_node_free(old);
if (old == entry_to_node(node))
return;
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 975b8fc..a8d74a7 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -483,11 +483,11 @@
: 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
/*
- * For mappings greater than a page, we limit the stride (and
- * hence alignment) to a page size.
+ * For mappings greater than or equal to a page, we limit the stride
+ * (and hence alignment) to a page size.
*/
nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
- if (size > PAGE_SIZE)
+ if (size >= PAGE_SIZE)
stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
else
stride = 1;
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index adc6ee0..4a720ed 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -80,8 +80,7 @@
if (head->next == node) {
struct rb_node *rbn = rb_next(&node->node);
- head->next = rbn ?
- rb_entry(rbn, struct timerqueue_node, node) : NULL;
+ head->next = rb_entry_safe(rbn, struct timerqueue_node, node);
}
rb_erase(&node->node, &head->head);
RB_CLEAR_NODE(&node->node);
diff --git a/mm/filemap.c b/mm/filemap.c
index b772a33..3f9afde 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1791,6 +1791,11 @@
cond_resched();
find_page:
+ if (fatal_signal_pending(current)) {
+ error = -EINTR;
+ goto out;
+ }
+
page = find_get_page(mapping, index);
if (!page) {
page_cache_sync_readahead(mapping,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9a6bd6c..5f3ad65c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -783,6 +783,12 @@
assert_spin_locked(pmd_lockptr(mm, pmd));
+ /*
+ * When we COW a devmap PMD entry, we split it into PTEs, so we should
+ * not be in this function with `flags & FOLL_COW` set.
+ */
+ WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
+
if (flags & FOLL_WRITE && !pmd_write(*pmd))
return NULL;
@@ -1128,6 +1134,16 @@
return ret;
}
+/*
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
+{
+ return pmd_write(pmd) ||
+ ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+}
+
struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
unsigned long addr,
pmd_t *pmd,
@@ -1138,7 +1154,7 @@
assert_spin_locked(pmd_lockptr(mm, pmd));
- if (flags & FOLL_WRITE && !pmd_write(*pmd))
+ if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags))
goto out;
/* Avoid dumping huge zero page */
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index b82b3e2..f479365 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -13,6 +13,7 @@
*
*/
+#include <linux/ftrace.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/printk.h>
@@ -300,6 +301,8 @@
if (likely(!kasan_report_enabled()))
return;
+ disable_trace_on_warning();
+
info.access_addr = (void *)addr;
info.access_size = size;
info.is_write = is_write;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a63a8f8..b822e15 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4353,9 +4353,9 @@
return ret;
}
- /* Try charges one by one with reclaim */
+ /* Try charges one by one with reclaim, but do not retry */
while (count--) {
- ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
+ ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1);
if (ret)
return ret;
mc.precharge++;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e43142c1..b8c11e0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1033,36 +1033,39 @@
node_set_state(node, N_MEMORY);
}
-int zone_can_shift(unsigned long pfn, unsigned long nr_pages,
- enum zone_type target)
+bool zone_can_shift(unsigned long pfn, unsigned long nr_pages,
+ enum zone_type target, int *zone_shift)
{
struct zone *zone = page_zone(pfn_to_page(pfn));
enum zone_type idx = zone_idx(zone);
int i;
+ *zone_shift = 0;
+
if (idx < target) {
/* pages must be at end of current zone */
if (pfn + nr_pages != zone_end_pfn(zone))
- return 0;
+ return false;
/* no zones in use between current zone and target */
for (i = idx + 1; i < target; i++)
if (zone_is_initialized(zone - idx + i))
- return 0;
+ return false;
}
if (target < idx) {
/* pages must be at beginning of current zone */
if (pfn != zone->zone_start_pfn)
- return 0;
+ return false;
/* no zones in use between current zone and target */
for (i = target + 1; i < idx; i++)
if (zone_is_initialized(zone - idx + i))
- return 0;
+ return false;
}
- return target - idx;
+ *zone_shift = target - idx;
+ return true;
}
/* Must be protected by mem_hotplug_begin() */
@@ -1089,10 +1092,13 @@
!can_online_high_movable(zone))
return -EINVAL;
- if (online_type == MMOP_ONLINE_KERNEL)
- zone_shift = zone_can_shift(pfn, nr_pages, ZONE_NORMAL);
- else if (online_type == MMOP_ONLINE_MOVABLE)
- zone_shift = zone_can_shift(pfn, nr_pages, ZONE_MOVABLE);
+ if (online_type == MMOP_ONLINE_KERNEL) {
+ if (!zone_can_shift(pfn, nr_pages, ZONE_NORMAL, &zone_shift))
+ return -EINVAL;
+ } else if (online_type == MMOP_ONLINE_MOVABLE) {
+ if (!zone_can_shift(pfn, nr_pages, ZONE_MOVABLE, &zone_shift))
+ return -EINVAL;
+ }
zone = move_pfn_range(zone_shift, pfn, pfn + nr_pages);
if (!zone)
@@ -1477,17 +1483,20 @@
}
/*
- * Confirm all pages in a range [start, end) is belongs to the same zone.
+ * Confirm all pages in a range [start, end) belong to the same zone.
+ * When true, return its valid [start, end).
*/
-int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
+int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long *valid_start, unsigned long *valid_end)
{
unsigned long pfn, sec_end_pfn;
+ unsigned long start, end;
struct zone *zone = NULL;
struct page *page;
int i;
- for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn);
+ for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1);
pfn < end_pfn;
- pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) {
+ pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) {
/* Make sure the memory section is present first */
if (!present_section_nr(pfn_to_section_nr(pfn)))
continue;
@@ -1503,10 +1512,20 @@
page = pfn_to_page(pfn + i);
if (zone && page_zone(page) != zone)
return 0;
+ if (!zone)
+ start = pfn + i;
zone = page_zone(page);
+ end = pfn + MAX_ORDER_NR_PAGES;
}
}
- return 1;
+
+ if (zone) {
+ *valid_start = start;
+ *valid_end = end;
+ return 1;
+ } else {
+ return 0;
+ }
}
/*
@@ -1833,6 +1852,7 @@
long offlined_pages;
int ret, drain, retry_max, node;
unsigned long flags;
+ unsigned long valid_start, valid_end;
struct zone *zone;
struct memory_notify arg;
@@ -1843,10 +1863,10 @@
return -EINVAL;
/* This makes hotplug much easier...and readable.
we assume this for now. .*/
- if (!test_pages_in_a_zone(start_pfn, end_pfn))
+ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
return -EINVAL;
- zone = page_zone(pfn_to_page(start_pfn));
+ zone = page_zone(pfn_to_page(valid_start));
node = zone_to_nid(zone);
nr_pages = end_pfn - start_pfn;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2e34664..1e7873e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2017,8 +2017,8 @@
nmask = policy_nodemask(gfp, pol);
zl = policy_zonelist(gfp, pol, node);
- mpol_cond_put(pol);
page = __alloc_pages_nodemask(gfp, order, zl, nmask);
+ mpol_cond_put(pol);
out:
if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
goto retry_cpuset;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d604d25..f3e0c69 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3523,12 +3523,13 @@
struct page *page = NULL;
unsigned int alloc_flags;
unsigned long did_some_progress;
- enum compact_priority compact_priority = DEF_COMPACT_PRIORITY;
+ enum compact_priority compact_priority;
enum compact_result compact_result;
- int compaction_retries = 0;
- int no_progress_loops = 0;
+ int compaction_retries;
+ int no_progress_loops;
unsigned long alloc_start = jiffies;
unsigned int stall_timeout = 10 * HZ;
+ unsigned int cpuset_mems_cookie;
/*
* In the slowpath, we sanity check order to avoid ever trying to
@@ -3549,6 +3550,23 @@
(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
gfp_mask &= ~__GFP_ATOMIC;
+retry_cpuset:
+ compaction_retries = 0;
+ no_progress_loops = 0;
+ compact_priority = DEF_COMPACT_PRIORITY;
+ cpuset_mems_cookie = read_mems_allowed_begin();
+ /*
+ * We need to recalculate the starting point for the zonelist iterator
+ * because we might have used different nodemask in the fast path, or
+ * there was a cpuset modification and we are retrying - otherwise we
+ * could end up iterating over non-eligible zones endlessly.
+ */
+ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+ ac->high_zoneidx, ac->nodemask);
+ if (!ac->preferred_zoneref->zone)
+ goto nopage;
+
+
/*
* The fast path uses conservative alloc_flags to succeed only until
* kswapd needs to be woken up, and to avoid the cost of setting up
@@ -3708,6 +3726,13 @@
&compaction_retries))
goto retry;
+ /*
+ * It's possible we raced with cpuset update so the OOM would be
+ * premature (see below the nopage: label for full explanation).
+ */
+ if (read_mems_allowed_retry(cpuset_mems_cookie))
+ goto retry_cpuset;
+
/* Reclaim has failed us, start killing things */
page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
if (page)
@@ -3720,6 +3745,16 @@
}
nopage:
+ /*
+ * When updating a task's mems_allowed or mempolicy nodemask, it is
+ * possible to race with parallel threads in such a way that our
+ * allocation can fail while the mask is being updated. If we are about
+ * to fail, check if the cpuset changed during allocation and if so,
+ * retry.
+ */
+ if (read_mems_allowed_retry(cpuset_mems_cookie))
+ goto retry_cpuset;
+
warn_alloc(gfp_mask,
"page allocation failure: order:%u", order);
got_pg:
@@ -3734,7 +3769,6 @@
struct zonelist *zonelist, nodemask_t *nodemask)
{
struct page *page;
- unsigned int cpuset_mems_cookie;
unsigned int alloc_flags = ALLOC_WMARK_LOW;
gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
struct alloc_context ac = {
@@ -3771,9 +3805,6 @@
if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
-retry_cpuset:
- cpuset_mems_cookie = read_mems_allowed_begin();
-
/* Dirty zone balancing only done in the fast path */
ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
@@ -3784,8 +3815,13 @@
*/
ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
ac.high_zoneidx, ac.nodemask);
- if (!ac.preferred_zoneref) {
+ if (!ac.preferred_zoneref->zone) {
page = NULL;
+ /*
+ * This might be due to race with cpuset_current_mems_allowed
+ * update, so make sure we retry with original nodemask in the
+ * slow path.
+ */
goto no_zone;
}
@@ -3794,6 +3830,7 @@
if (likely(page))
goto out;
+no_zone:
/*
* Runtime PM, block IO and its error handling path can deadlock
* because I/O on the device might not complete.
@@ -3805,21 +3842,10 @@
* Restore the original nodemask if it was potentially replaced with
* &cpuset_current_mems_allowed to optimize the fast-path attempt.
*/
- if (cpusets_enabled())
+ if (unlikely(ac.nodemask != nodemask))
ac.nodemask = nodemask;
- page = __alloc_pages_slowpath(alloc_mask, order, &ac);
-no_zone:
- /*
- * When updating a task's mems_allowed, it is possible to race with
- * parallel threads in such a way that an allocation can fail while
- * the mask is being updated. If a page allocation is about to fail,
- * check if the cpuset changed during allocation and if so, retry.
- */
- if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) {
- alloc_mask = gfp_mask;
- goto retry_cpuset;
- }
+ page = __alloc_pages_slowpath(alloc_mask, order, &ac);
out:
if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
@@ -7248,6 +7274,7 @@
.zone = page_zone(pfn_to_page(start)),
.mode = MIGRATE_SYNC,
.ignore_skip_hint = true,
+ .gfp_mask = GFP_KERNEL,
};
INIT_LIST_HEAD(&cc.migratepages);
diff --git a/mm/shmem.c b/mm/shmem.c
index bb53285..3a7587a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -415,6 +415,7 @@
struct shrink_control *sc, unsigned long nr_to_split)
{
LIST_HEAD(list), *pos, *next;
+ LIST_HEAD(to_remove);
struct inode *inode;
struct shmem_inode_info *info;
struct page *page;
@@ -441,9 +442,8 @@
/* Check if there's anything to gain */
if (round_up(inode->i_size, PAGE_SIZE) ==
round_up(inode->i_size, HPAGE_PMD_SIZE)) {
- list_del_init(&info->shrinklist);
+ list_move(&info->shrinklist, &to_remove);
removed++;
- iput(inode);
goto next;
}
@@ -454,6 +454,13 @@
}
spin_unlock(&sbinfo->shrinklist_lock);
+ list_for_each_safe(pos, next, &to_remove) {
+ info = list_entry(pos, struct shmem_inode_info, shrinklist);
+ inode = &info->vfs_inode;
+ list_del_init(&info->shrinklist);
+ iput(inode);
+ }
+
list_for_each_safe(pos, next, &list) {
int ret;
diff --git a/mm/slub.c b/mm/slub.c
index 067598a..7ec0a96 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -496,10 +496,11 @@
return 1;
}
-static void print_section(char *text, u8 *addr, unsigned int length)
+static void print_section(char *level, char *text, u8 *addr,
+ unsigned int length)
{
metadata_access_enable();
- print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
+ print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
length, 1);
metadata_access_disable();
}
@@ -636,14 +637,15 @@
p, p - addr, get_freepointer(s, p));
if (s->flags & SLAB_RED_ZONE)
- print_section("Redzone ", p - s->red_left_pad, s->red_left_pad);
+ print_section(KERN_ERR, "Redzone ", p - s->red_left_pad,
+ s->red_left_pad);
else if (p > addr + 16)
- print_section("Bytes b4 ", p - 16, 16);
+ print_section(KERN_ERR, "Bytes b4 ", p - 16, 16);
- print_section("Object ", p, min_t(unsigned long, s->object_size,
- PAGE_SIZE));
+ print_section(KERN_ERR, "Object ", p,
+ min_t(unsigned long, s->object_size, PAGE_SIZE));
if (s->flags & SLAB_RED_ZONE)
- print_section("Redzone ", p + s->object_size,
+ print_section(KERN_ERR, "Redzone ", p + s->object_size,
s->inuse - s->object_size);
if (s->offset)
@@ -658,7 +660,8 @@
if (off != size_from_object(s))
/* Beginning of the filler is the free pointer */
- print_section("Padding ", p + off, size_from_object(s) - off);
+ print_section(KERN_ERR, "Padding ", p + off,
+ size_from_object(s) - off);
dump_stack();
}
@@ -820,7 +823,7 @@
end--;
slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
- print_section("Padding ", end - remainder, remainder);
+ print_section(KERN_ERR, "Padding ", end - remainder, remainder);
restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end);
return 0;
@@ -973,7 +976,7 @@
page->freelist);
if (!alloc)
- print_section("Object ", (void *)object,
+ print_section(KERN_INFO, "Object ", (void *)object,
s->object_size);
dump_stack();
@@ -1419,6 +1422,10 @@
int err;
unsigned long i, count = oo_objects(s->oo);
+ /* Bailout if already initialised */
+ if (s->random_seq)
+ return 0;
+
err = cache_random_seq_create(s, count, GFP_KERNEL);
if (err) {
pr_err("SLUB: Unable to initialize free list for %s\n",
diff --git a/mm/zswap.c b/mm/zswap.c
index 067a0d6..cabf09e 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -78,7 +78,13 @@
/* Enable/disable zswap (disabled by default) */
static bool zswap_enabled;
-module_param_named(enabled, zswap_enabled, bool, 0644);
+static int zswap_enabled_param_set(const char *,
+ const struct kernel_param *);
+static struct kernel_param_ops zswap_enabled_param_ops = {
+ .set = zswap_enabled_param_set,
+ .get = param_get_bool,
+};
+module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644);
/* Crypto compressor to use */
#define ZSWAP_COMPRESSOR_DEFAULT "lzo"
@@ -176,6 +182,9 @@
/* used by param callback function */
static bool zswap_init_started;
+/* fatal error during init */
+static bool zswap_init_failed;
+
/*********************************
* helpers and fwd declarations
**********************************/
@@ -624,6 +633,11 @@
char *s = strstrip((char *)val);
int ret;
+ if (zswap_init_failed) {
+ pr_err("can't set param, initialization failed\n");
+ return -ENODEV;
+ }
+
/* no change required */
if (!strcmp(s, *(char **)kp->arg))
return 0;
@@ -703,6 +717,17 @@
return __zswap_param_set(val, kp, NULL, zswap_compressor);
}
+static int zswap_enabled_param_set(const char *val,
+ const struct kernel_param *kp)
+{
+ if (zswap_init_failed) {
+ pr_err("can't enable, initialization failed\n");
+ return -ENODEV;
+ }
+
+ return param_set_bool(val, kp);
+}
+
/*********************************
* writeback code
**********************************/
@@ -1201,6 +1226,9 @@
dstmem_fail:
zswap_entry_cache_destroy();
cache_fail:
+ /* if built-in, we aren't unloaded on failure; don't allow use */
+ zswap_init_failed = true;
+ zswap_enabled = false;
return -ENOMEM;
}
/* must be late so crypto has time to come up */
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 4855d18..038b109 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -264,7 +264,7 @@
{
ax25_clear_queues(ax25);
- if (!sock_flag(ax25->sk, SOCK_DESTROY))
+ if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY))
ax25_stop_heartbeat(ax25);
ax25_stop_t1timer(ax25);
ax25_stop_t2timer(ax25);
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 9c561e6..0854ebd 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -474,7 +474,7 @@
primary_if = batadv_primary_if_get_selected(bat_priv);
if (!primary_if) {
ret = -EINVAL;
- goto put_primary_if;
+ goto free_skb;
}
/* Create one header to be copied to all fragments */
@@ -502,7 +502,7 @@
skb_fragment = batadv_frag_create(skb, &frag_header, mtu);
if (!skb_fragment) {
ret = -ENOMEM;
- goto free_skb;
+ goto put_primary_if;
}
batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_TX);
@@ -511,7 +511,7 @@
ret = batadv_send_unicast_skb(skb_fragment, neigh_node);
if (ret != NET_XMIT_SUCCESS) {
ret = NET_XMIT_DROP;
- goto free_skb;
+ goto put_primary_if;
}
frag_header.no++;
@@ -519,7 +519,7 @@
/* The initial check in this function should cover this case */
if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1) {
ret = -EINVAL;
- goto free_skb;
+ goto put_primary_if;
}
}
@@ -527,7 +527,7 @@
if (batadv_skb_head_push(skb, header_size) < 0 ||
pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0) {
ret = -ENOMEM;
- goto free_skb;
+ goto put_primary_if;
}
memcpy(skb->data, &frag_header, header_size);
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 71c7453..7109b38 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -781,20 +781,6 @@
return 0;
}
-static int br_dev_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[])
-{
- struct net_bridge *br = netdev_priv(dev);
-
- if (tb[IFLA_ADDRESS]) {
- spin_lock_bh(&br->lock);
- br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
- spin_unlock_bh(&br->lock);
- }
-
- return register_netdevice(dev);
-}
-
static int br_port_slave_changelink(struct net_device *brdev,
struct net_device *dev,
struct nlattr *tb[],
@@ -1115,6 +1101,25 @@
return 0;
}
+static int br_dev_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ struct net_bridge *br = netdev_priv(dev);
+ int err;
+
+ if (tb[IFLA_ADDRESS]) {
+ spin_lock_bh(&br->lock);
+ br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
+ spin_unlock_bh(&br->lock);
+ }
+
+ err = br_changelink(dev, tb, data);
+ if (err)
+ return err;
+
+ return register_netdevice(dev);
+}
+
static size_t br_get_size(const struct net_device *brdev)
{
return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 1108079..5488e4a 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -445,6 +445,7 @@
* @func: callback function on filter match
* @data: returned parameter for callback function
* @ident: string for calling module identification
+ * @sk: socket pointer (might be NULL)
*
* Description:
* Invokes the callback function with the received sk_buff and the given
@@ -468,7 +469,7 @@
*/
int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
void (*func)(struct sk_buff *, void *), void *data,
- char *ident)
+ char *ident, struct sock *sk)
{
struct receiver *r;
struct hlist_head *rl;
@@ -496,6 +497,7 @@
r->func = func;
r->data = data;
r->ident = ident;
+ r->sk = sk;
hlist_add_head_rcu(&r->list, rl);
d->entries++;
@@ -520,8 +522,11 @@
static void can_rx_delete_receiver(struct rcu_head *rp)
{
struct receiver *r = container_of(rp, struct receiver, rcu);
+ struct sock *sk = r->sk;
kmem_cache_free(rcv_cache, r);
+ if (sk)
+ sock_put(sk);
}
/**
@@ -596,8 +601,11 @@
spin_unlock(&can_rcvlists_lock);
/* schedule the receiver item for deletion */
- if (r)
+ if (r) {
+ if (r->sk)
+ sock_hold(r->sk);
call_rcu(&r->rcu, can_rx_delete_receiver);
+ }
}
EXPORT_SYMBOL(can_rx_unregister);
diff --git a/net/can/af_can.h b/net/can/af_can.h
index fca0fe9..b86f512 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -50,13 +50,14 @@
struct receiver {
struct hlist_node list;
- struct rcu_head rcu;
canid_t can_id;
canid_t mask;
unsigned long matches;
void (*func)(struct sk_buff *, void *);
void *data;
char *ident;
+ struct sock *sk;
+ struct rcu_head rcu;
};
#define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS)
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 21ac753..95d13b2 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -734,14 +734,23 @@
static void bcm_remove_op(struct bcm_op *op)
{
- hrtimer_cancel(&op->timer);
- hrtimer_cancel(&op->thrtimer);
+ if (op->tsklet.func) {
+ while (test_bit(TASKLET_STATE_SCHED, &op->tsklet.state) ||
+ test_bit(TASKLET_STATE_RUN, &op->tsklet.state) ||
+ hrtimer_active(&op->timer)) {
+ hrtimer_cancel(&op->timer);
+ tasklet_kill(&op->tsklet);
+ }
+ }
- if (op->tsklet.func)
- tasklet_kill(&op->tsklet);
-
- if (op->thrtsklet.func)
- tasklet_kill(&op->thrtsklet);
+ if (op->thrtsklet.func) {
+ while (test_bit(TASKLET_STATE_SCHED, &op->thrtsklet.state) ||
+ test_bit(TASKLET_STATE_RUN, &op->thrtsklet.state) ||
+ hrtimer_active(&op->thrtimer)) {
+ hrtimer_cancel(&op->thrtimer);
+ tasklet_kill(&op->thrtsklet);
+ }
+ }
if ((op->frames) && (op->frames != &op->sframe))
kfree(op->frames);
@@ -1216,7 +1225,7 @@
err = can_rx_register(dev, op->can_id,
REGMASK(op->can_id),
bcm_rx_handler, op,
- "bcm");
+ "bcm", sk);
op->rx_reg_dev = dev;
dev_put(dev);
@@ -1225,7 +1234,7 @@
} else
err = can_rx_register(NULL, op->can_id,
REGMASK(op->can_id),
- bcm_rx_handler, op, "bcm");
+ bcm_rx_handler, op, "bcm", sk);
if (err) {
/* this bcm rx op is broken -> remove it */
list_del(&op->list);
diff --git a/net/can/gw.c b/net/can/gw.c
index a54ab0c..7056a1a 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -442,7 +442,7 @@
{
return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id,
gwj->ccgw.filter.can_mask, can_can_gw_rcv,
- gwj, "gw");
+ gwj, "gw", NULL);
}
static inline void cgw_unregister_filter(struct cgw_job *gwj)
diff --git a/net/can/raw.c b/net/can/raw.c
index b075f02..6dc546a 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -190,7 +190,7 @@
for (i = 0; i < count; i++) {
err = can_rx_register(dev, filter[i].can_id,
filter[i].can_mask,
- raw_rcv, sk, "raw");
+ raw_rcv, sk, "raw", sk);
if (err) {
/* clean up successfully registered filters */
while (--i >= 0)
@@ -211,7 +211,7 @@
if (err_mask)
err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
- raw_rcv, sk, "raw");
+ raw_rcv, sk, "raw", sk);
return err;
}
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 3949ce7..292e33b 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -214,7 +214,7 @@
SKCIPHER_REQUEST_ON_STACK(req, key->tfm);
struct sg_table sgt;
struct scatterlist prealloc_sg;
- char iv[AES_BLOCK_SIZE];
+ char iv[AES_BLOCK_SIZE] __aligned(8);
int pad_byte = AES_BLOCK_SIZE - (in_len & (AES_BLOCK_SIZE - 1));
int crypt_len = encrypt ? in_len + pad_byte : in_len;
int ret;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 662bea5..ea63334 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -332,7 +332,9 @@
EXPORT_SYMBOL(__skb_free_datagram_locked);
int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
- unsigned int flags)
+ unsigned int flags,
+ void (*destructor)(struct sock *sk,
+ struct sk_buff *skb))
{
int err = 0;
@@ -342,6 +344,8 @@
if (skb == skb_peek(&sk->sk_receive_queue)) {
__skb_unlink(skb, &sk->sk_receive_queue);
atomic_dec(&skb->users);
+ if (destructor)
+ destructor(sk, skb);
err = 0;
}
spin_unlock_bh(&sk->sk_receive_queue.lock);
@@ -375,7 +379,7 @@
int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
{
- int err = __sk_queue_drop_skb(sk, skb, flags);
+ int err = __sk_queue_drop_skb(sk, skb, flags, NULL);
kfree_skb(skb);
sk_mem_reclaim_partial(sk);
diff --git a/net/core/dev.c b/net/core/dev.c
index 07b307b..29101c9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1695,24 +1695,19 @@
static struct static_key netstamp_needed __read_mostly;
#ifdef HAVE_JUMP_LABEL
-/* We are not allowed to call static_key_slow_dec() from irq context
- * If net_disable_timestamp() is called from irq context, defer the
- * static_key_slow_dec() calls.
- */
static atomic_t netstamp_needed_deferred;
+static void netstamp_clear(struct work_struct *work)
+{
+ int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+
+ while (deferred--)
+ static_key_slow_dec(&netstamp_needed);
+}
+static DECLARE_WORK(netstamp_work, netstamp_clear);
#endif
void net_enable_timestamp(void)
{
-#ifdef HAVE_JUMP_LABEL
- int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
-
- if (deferred) {
- while (--deferred)
- static_key_slow_dec(&netstamp_needed);
- return;
- }
-#endif
static_key_slow_inc(&netstamp_needed);
}
EXPORT_SYMBOL(net_enable_timestamp);
@@ -1720,12 +1715,12 @@
void net_disable_timestamp(void)
{
#ifdef HAVE_JUMP_LABEL
- if (in_interrupt()) {
- atomic_inc(&netstamp_needed_deferred);
- return;
- }
-#endif
+ /* net_disable_timestamp() can be called from non process context */
+ atomic_inc(&netstamp_needed_deferred);
+ schedule_work(&netstamp_work);
+#else
static_key_slow_dec(&netstamp_needed);
+#endif
}
EXPORT_SYMBOL(net_disable_timestamp);
@@ -2795,9 +2790,9 @@
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, type)) {
features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
- } else if (illegal_highdma(skb->dev, skb)) {
- features &= ~NETIF_F_SG;
}
+ if (illegal_highdma(skb->dev, skb))
+ features &= ~NETIF_F_SG;
return features;
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index e23766c..d92de0a 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1405,9 +1405,12 @@
if (regs.len > reglen)
regs.len = reglen;
- regbuf = vzalloc(reglen);
- if (reglen && !regbuf)
- return -ENOMEM;
+ regbuf = NULL;
+ if (reglen) {
+ regbuf = vzalloc(reglen);
+ if (!regbuf)
+ return -ENOMEM;
+ }
ops->get_regs(dev, ®s, regbuf);
@@ -1712,7 +1715,7 @@
static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
void __user *useraddr)
{
- struct ethtool_channels channels, max;
+ struct ethtool_channels channels, max = { .cmd = ETHTOOL_GCHANNELS };
u32 max_rx_in_use = 0;
if (!dev->ethtool_ops->set_channels || !dev->ethtool_ops->get_channels)
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 71bb3e2..b3eef90 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -386,6 +386,7 @@
.fill_encap = bpf_fill_encap_info,
.get_encap_size = bpf_encap_nlsize,
.cmp_encap = bpf_encap_cmp,
+ .owner = THIS_MODULE,
};
static int __init bpf_lwt_init(void)
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index a5d4e86..c234650 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -26,6 +26,7 @@
#include <net/lwtunnel.h>
#include <net/rtnetlink.h>
#include <net/ip6_fib.h>
+#include <net/nexthop.h>
#ifdef CONFIG_MODULES
@@ -114,26 +115,78 @@
ret = -EOPNOTSUPP;
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[encap_type]);
-#ifdef CONFIG_MODULES
- if (!ops) {
- const char *encap_type_str = lwtunnel_encap_str(encap_type);
-
- if (encap_type_str) {
- rcu_read_unlock();
- request_module("rtnl-lwt-%s", encap_type_str);
- rcu_read_lock();
- ops = rcu_dereference(lwtun_encaps[encap_type]);
- }
- }
-#endif
- if (likely(ops && ops->build_state))
+ if (likely(ops && ops->build_state && try_module_get(ops->owner))) {
ret = ops->build_state(dev, encap, family, cfg, lws);
+ if (ret)
+ module_put(ops->owner);
+ }
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(lwtunnel_build_state);
+int lwtunnel_valid_encap_type(u16 encap_type)
+{
+ const struct lwtunnel_encap_ops *ops;
+ int ret = -EINVAL;
+
+ if (encap_type == LWTUNNEL_ENCAP_NONE ||
+ encap_type > LWTUNNEL_ENCAP_MAX)
+ return ret;
+
+ rcu_read_lock();
+ ops = rcu_dereference(lwtun_encaps[encap_type]);
+ rcu_read_unlock();
+#ifdef CONFIG_MODULES
+ if (!ops) {
+ const char *encap_type_str = lwtunnel_encap_str(encap_type);
+
+ if (encap_type_str) {
+ __rtnl_unlock();
+ request_module("rtnl-lwt-%s", encap_type_str);
+ rtnl_lock();
+
+ rcu_read_lock();
+ ops = rcu_dereference(lwtun_encaps[encap_type]);
+ rcu_read_unlock();
+ }
+ }
+#endif
+ return ops ? 0 : -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(lwtunnel_valid_encap_type);
+
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
+{
+ struct rtnexthop *rtnh = (struct rtnexthop *)attr;
+ struct nlattr *nla_entype;
+ struct nlattr *attrs;
+ struct nlattr *nla;
+ u16 encap_type;
+ int attrlen;
+
+ while (rtnh_ok(rtnh, remaining)) {
+ attrlen = rtnh_attrlen(rtnh);
+ if (attrlen > 0) {
+ attrs = rtnh_attrs(rtnh);
+ nla = nla_find(attrs, attrlen, RTA_ENCAP);
+ nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
+
+ if (nla_entype) {
+ encap_type = nla_get_u16(nla_entype);
+
+ if (lwtunnel_valid_encap_type(encap_type) != 0)
+ return -EOPNOTSUPP;
+ }
+ }
+ rtnh = rtnh_next(rtnh, &remaining);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(lwtunnel_valid_encap_type_attr);
+
void lwtstate_free(struct lwtunnel_state *lws)
{
const struct lwtunnel_encap_ops *ops = lwtun_encaps[lws->type];
@@ -144,6 +197,7 @@
} else {
kfree(lws);
}
+ module_put(ops->owner);
}
EXPORT_SYMBOL(lwtstate_free);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7bb12e0..e7c12ca 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2923,7 +2923,8 @@
return;
set_bit(index, p->data_state);
- call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
+ if (index == NEIGH_VAR_DELAY_PROBE_TIME)
+ call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
if (!dev) /* NULL dev means this is default value */
neigh_copy_dflt_parms(net, p, index);
}
diff --git a/net/dccp/input.c b/net/dccp/input.c
index ba34718..8fedc2d 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -606,7 +606,8 @@
if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
skb) < 0)
return 1;
- goto discard;
+ consume_skb(skb);
+ return 0;
}
if (dh->dccph_type == DCCP_PKT_RESET)
goto discard;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index adfc790..c4e879c 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -227,7 +227,7 @@
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
+ err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -281,7 +281,7 @@
dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
if (!IS_ERR(dst)) {
skb_dst_set(skb, dst);
- ip6_xmit(ctl_sk, skb, &fl6, NULL, 0);
+ ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
DCCP_INC_STATS(DCCP_MIB_OUTRSTS);
return;
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index da38621..0f99297 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -273,6 +273,7 @@
if (err) {
dev_warn(ds->dev, "Failed to create slave %d: %d\n",
index, err);
+ ds->ports[index].netdev = NULL;
return err;
}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 68c9eea..7d45961 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1105,10 +1105,8 @@
/* Use already configured phy mode */
if (p->phy_interface == PHY_INTERFACE_MODE_NA)
p->phy_interface = p->phy->interface;
- phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
- p->phy_interface);
-
- return 0;
+ return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
+ p->phy_interface);
}
static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
@@ -1203,6 +1201,8 @@
{
struct dsa_slave_priv *p = netdev_priv(slave_dev);
+ netif_device_detach(slave_dev);
+
if (p->phy) {
phy_stop(p->phy);
p->old_pause = -1;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 8c5a479..516c87e 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -356,6 +356,7 @@
dev->header_ops = ð_header_ops;
dev->type = ARPHRD_ETHER;
dev->hard_header_len = ETH_HLEN;
+ dev->min_header_len = ETH_HLEN;
dev->mtu = ETH_DATA_LEN;
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = ETH_DATA_LEN;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 89a8cac4..51b27ae 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1263,7 +1263,7 @@
/*
* ax25 -> ASCII conversion
*/
-static char *ax2asc2(ax25_address *a, char *buf)
+static void ax2asc2(ax25_address *a, char *buf)
{
char c, *s;
int n;
@@ -1285,10 +1285,10 @@
*s++ = n + '0';
*s++ = '\0';
- if (*buf == '\0' || *buf == '-')
- return "*";
-
- return buf;
+ if (*buf == '\0' || *buf == '-') {
+ buf[0] = '*';
+ buf[1] = '\0';
+ }
}
#endif /* CONFIG_AX25 */
@@ -1322,7 +1322,7 @@
}
#endif
sprintf(tbuf, "%pI4", n->primary_key);
- seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n",
+ seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s * %s\n",
tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name);
read_unlock(&n->lock);
}
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 72d6f05..ae20616 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1587,6 +1587,10 @@
goto validate_return_locked;
}
+ if (opt_iter + 1 == opt_len) {
+ err_offset = opt_iter;
+ goto validate_return_locked;
+ }
tag_len = tag[1];
if (tag_len > (opt_len - opt_iter)) {
err_offset = opt_iter + 1;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index eae0332..7db2ad2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -46,6 +46,7 @@
#include <net/rtnetlink.h>
#include <net/xfrm.h>
#include <net/l3mdev.h>
+#include <net/lwtunnel.h>
#include <trace/events/fib.h>
#ifndef CONFIG_IP_MULTIPLE_TABLES
@@ -677,6 +678,10 @@
cfg->fc_mx_len = nla_len(attr);
break;
case RTA_MULTIPATH:
+ err = lwtunnel_valid_encap_type_attr(nla_data(attr),
+ nla_len(attr));
+ if (err < 0)
+ goto errout;
cfg->fc_mp = nla_data(attr);
cfg->fc_mp_len = nla_len(attr);
break;
@@ -691,6 +696,9 @@
break;
case RTA_ENCAP_TYPE:
cfg->fc_encap_type = nla_get_u16(attr);
+ err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+ if (err < 0)
+ goto errout;
break;
}
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index eba1546..9a375b9 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1279,8 +1279,9 @@
nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
goto nla_put_failure;
#endif
- if (fi->fib_nh->nh_lwtstate)
- lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate);
+ if (fi->fib_nh->nh_lwtstate &&
+ lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0)
+ goto nla_put_failure;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (fi->fib_nhs > 1) {
@@ -1316,8 +1317,10 @@
nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
goto nla_put_failure;
#endif
- if (nh->nh_lwtstate)
- lwtunnel_fill_encap(skb, nh->nh_lwtstate);
+ if (nh->nh_lwtstate &&
+ lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0)
+ goto nla_put_failure;
+
/* length of rtnetlink header + attributes */
rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
} endfor_nexthops(fi);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 5b15459..44fd86d 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1172,6 +1172,7 @@
psf->sf_crcount = im->crcount;
}
in_dev_put(pmc->interface);
+ kfree(pmc);
}
spin_unlock_bh(&im->lock);
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index fac275c4..b67719f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1629,6 +1629,7 @@
sk->sk_protocol = ip_hdr(skb)->protocol;
sk->sk_bound_dev_if = arg->bound_dev_if;
sk->sk_sndbuf = sysctl_wmem_default;
+ sk->sk_mark = fl4.flowi4_mark;
err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
len, 0, &ipc, &rt, MSG_DONTWAIT);
if (unlikely(err)) {
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 53ae0c6..9000117 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1238,7 +1238,14 @@
pktinfo->ipi_ifindex = 0;
pktinfo->ipi_spec_dst.s_addr = 0;
}
- skb_dst_drop(skb);
+ /* We need to keep the dst for __ip_options_echo()
+ * We could restrict the test to opt.ts_needtime || opt.srr,
+ * but the following is good enough as IP options are not often used.
+ */
+ if (unlikely(IPCB(skb)->opt.optlen))
+ skb_dst_force(skb);
+ else
+ skb_dst_drop(skb);
}
int ip_setsockopt(struct sock *sk, int level,
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index fed3d29..0fd1976 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -313,6 +313,7 @@
.fill_encap = ip_tun_fill_encap_info,
.get_encap_size = ip_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
+ .owner = THIS_MODULE,
};
static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
@@ -403,6 +404,7 @@
.fill_encap = ip6_tun_fill_encap_info,
.get_encap_size = ip6_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
+ .owner = THIS_MODULE,
};
void __init ip_tunnel_core_init(void)
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index a6b8c1a..0a783cd 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -144,7 +144,12 @@
rcu_read_lock_bh();
c = __clusterip_config_find(net, clusterip);
if (c) {
- if (!c->pde || unlikely(!atomic_inc_not_zero(&c->refcount)))
+#ifdef CONFIG_PROC_FS
+ if (!c->pde)
+ c = NULL;
+ else
+#endif
+ if (unlikely(!atomic_inc_not_zero(&c->refcount)))
c = NULL;
else if (entry)
atomic_inc(&c->entries);
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index f273098..37fb955 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -63,10 +63,10 @@
return dev_match || flags & XT_RPFILTER_LOOSE;
}
-static bool rpfilter_is_local(const struct sk_buff *skb)
+static bool
+rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in)
{
- const struct rtable *rt = skb_rtable(skb);
- return rt && (rt->rt_flags & RTCF_LOCAL);
+ return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK;
}
static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
@@ -79,7 +79,7 @@
info = par->matchinfo;
invert = info->flags & XT_RPFILTER_INVERT;
- if (rpfilter_is_local(skb))
+ if (rpfilter_is_loopback(skb, xt_in(par)))
return true ^ invert;
iph = ip_hdr(skb);
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index fd82202..146d861 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -126,6 +126,8 @@
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
+ nskb->mark = IP4_REPLY_MARK(net, oldskb->mark);
+
skb_reserve(nskb, LL_MAX_HEADER);
niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
ip4_dst_hoplimit(skb_dst(nskb)));
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 965b1a1..29812919 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -26,13 +26,6 @@
return addr;
}
-static bool fib4_is_local(const struct sk_buff *skb)
-{
- const struct rtable *rt = skb_rtable(skb);
-
- return rt && (rt->rt_flags & RTCF_LOCAL);
-}
-
#define DSCP_BITS 0xfc
void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
@@ -95,8 +88,10 @@
else
oif = NULL;
- if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib4_is_local(pkt->skb)) {
- nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX);
+ if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
+ nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
+ nft_fib_store_result(dest, priv->result, pkt,
+ nft_in(pkt)->ifindex);
return;
}
@@ -131,7 +126,7 @@
switch (res.type) {
case RTN_UNICAST:
break;
- case RTN_LOCAL: /* should not appear here, see fib4_is_local() above */
+ case RTN_LOCAL: /* Should not see RTN_LOCAL here */
return;
default:
break;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 86cca61..68d77b1 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -642,6 +642,8 @@
{
struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
+ if (!skb)
+ return 0;
pfh->wcheck = csum_partial((char *)&pfh->icmph,
sizeof(struct icmphdr), pfh->wcheck);
pfh->icmph.checksum = csum_fold(pfh->wcheck);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0fcac8e..709ffe6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2472,7 +2472,7 @@
r->rtm_dst_len = 32;
r->rtm_src_len = 0;
r->rtm_tos = fl4->flowi4_tos;
- r->rtm_table = table_id;
+ r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT;
if (nla_put_u32(skb, RTA_TABLE, table_id))
goto nla_put_failure;
r->rtm_type = rt->rt_type;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4a04496..0efb4c7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -770,6 +770,12 @@
ret = -EAGAIN;
break;
}
+ /* if __tcp_splice_read() got nothing while we have
+ * an skb in receive queue, we do not want to loop.
+ * This might happen with URG data.
+ */
+ if (!skb_queue_empty(&sk->sk_receive_queue))
+ break;
sk_wait_data(sk, &timeo, NULL);
if (signal_pending(current)) {
ret = sock_intr_errno(timeo);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 4e777a3..dd2560c 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -113,7 +113,7 @@
struct tcp_fastopen_cookie tmp;
if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
- struct in6_addr *buf = (struct in6_addr *) tmp.val;
+ struct in6_addr *buf = &tmp.addr;
int i;
for (i = 0; i < 4; i++)
@@ -205,6 +205,7 @@
* scaled. So correct it appropriately.
*/
tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+ tp->max_window = tp->snd_wnd;
/* Activate the retrans timer so that SYNACK can be retransmitted.
* The request socket is not added to the ehash
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6c79075..41dcbd5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5078,7 +5078,7 @@
if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
/* pairs with tcp_poll() */
- smp_mb__after_atomic();
+ smp_mb();
if (sk->sk_socket &&
test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
tcp_new_space(sk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1d5331a..8ce50dc3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2518,9 +2518,11 @@
int full_space = min_t(int, tp->window_clamp, allowed_space);
int window;
- if (mss > full_space)
+ if (unlikely(mss > full_space)) {
mss = full_space;
-
+ if (mss <= 0)
+ return 0;
+ }
if (free_space < (full_space >> 1)) {
icsk->icsk_ack.quick = 0;
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index f6c50af..3d063eb 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -117,7 +117,7 @@
(fwmark > 0 && skb->mark == fwmark)) &&
(full || tp->snd_cwnd != tcp_probe.lastcwnd)) {
- spin_lock(&tcp_probe.lock);
+ spin_lock_bh(&tcp_probe.lock);
/* If log fills, just silently drop */
if (tcp_probe_avail() > 1) {
struct tcp_log *p = tcp_probe.log + tcp_probe.head;
@@ -157,7 +157,7 @@
tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
}
tcp_probe.lastcwnd = tp->snd_cwnd;
- spin_unlock(&tcp_probe.lock);
+ spin_unlock_bh(&tcp_probe.lock);
wake_up(&tcp_probe.wait);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1307a7c..8aab7d7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1501,7 +1501,7 @@
return err;
csum_copy_err:
- if (!__sk_queue_drop_skb(sk, skb, flags)) {
+ if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) {
UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c1e124b..a7bcc0a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3386,9 +3386,15 @@
}
if (idev) {
- if (idev->if_flags & IF_READY)
- /* device is already configured. */
+ if (idev->if_flags & IF_READY) {
+ /* device is already configured -
+ * but resend MLD reports, we might
+ * have roamed and need to update
+ * multicast snooping switches
+ */
+ ipv6_mc_up(idev);
break;
+ }
idev->if_flags |= IF_READY;
}
@@ -4009,6 +4015,12 @@
if (bump_id)
rt_genid_bump_ipv6(dev_net(dev));
+
+ /* Make sure that a new temporary address will be created
+ * before this temporary address becomes deprecated.
+ */
+ if (ifp->flags & IFA_F_TEMPORARY)
+ addrconf_verify_rtnl();
}
static void addrconf_dad_run(struct inet6_dev *idev)
@@ -5540,8 +5552,7 @@
struct net_device *dev;
struct inet6_dev *idev;
- rcu_read_lock();
- for_each_netdev_rcu(net, dev) {
+ for_each_netdev(net, dev) {
idev = __in6_dev_get(dev);
if (idev) {
int changed = (!idev->cnf.disable_ipv6) ^ (!newf);
@@ -5550,7 +5561,6 @@
dev_disable_change(idev);
}
}
- rcu_read_unlock();
}
static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index a3eaafd..eec27f8 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,18 +167,22 @@
if (np->sndflow)
fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
- addr_type = ipv6_addr_type(&usin->sin6_addr);
-
- if (addr_type == IPV6_ADDR_ANY) {
+ if (ipv6_addr_any(&usin->sin6_addr)) {
/*
* connect to self
*/
- usin->sin6_addr.s6_addr[15] = 0x01;
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+ ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+ &usin->sin6_addr);
+ else
+ usin->sin6_addr = in6addr_loopback;
}
+ addr_type = ipv6_addr_type(&usin->sin6_addr);
+
daddr = &usin->sin6_addr;
- if (addr_type == IPV6_ADDR_MAPPED) {
+ if (addr_type & IPV6_ADDR_MAPPED) {
struct sockaddr_in sin;
if (__ipv6_only_sock(sk)) {
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index e419850..275cac6 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -327,7 +327,6 @@
struct ipv6_sr_hdr *hdr;
struct inet6_dev *idev;
struct in6_addr *addr;
- bool cleanup = false;
int accept_seg6;
hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
@@ -351,11 +350,7 @@
#endif
looped_back:
- if (hdr->segments_left > 0) {
- if (hdr->nexthdr != NEXTHDR_IPV6 && hdr->segments_left == 1 &&
- sr_has_cleanup(hdr))
- cleanup = true;
- } else {
+ if (hdr->segments_left == 0) {
if (hdr->nexthdr == NEXTHDR_IPV6) {
int offset = (hdr->hdrlen + 1) << 3;
@@ -418,21 +413,6 @@
ipv6_hdr(skb)->daddr = *addr;
- if (cleanup) {
- int srhlen = (hdr->hdrlen + 1) << 3;
- int nh = hdr->nexthdr;
-
- skb_pull_rcsum(skb, sizeof(struct ipv6hdr) + srhlen);
- memmove(skb_network_header(skb) + srhlen,
- skb_network_header(skb),
- (unsigned char *)hdr - skb_network_header(skb));
- skb->network_header += srhlen;
- ipv6_hdr(skb)->nexthdr = nh;
- ipv6_hdr(skb)->payload_len = htons(skb->len -
- sizeof(struct ipv6hdr));
- skb_push_rcsum(skb, sizeof(struct ipv6hdr));
- }
-
skb_dst_drop(skb);
ip6_route_input(skb);
@@ -453,13 +433,8 @@
}
ipv6_hdr(skb)->hop_limit--;
- /* be sure that srh is still present before reinjecting */
- if (!cleanup) {
- skb_pull(skb, sizeof(struct ipv6hdr));
- goto looped_back;
- }
- skb_set_transport_header(skb, sizeof(struct ipv6hdr));
- IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
+ skb_pull(skb, sizeof(struct ipv6hdr));
+ goto looped_back;
}
dst_input(skb);
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index a7bc54a..13b5e85 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -238,6 +238,7 @@
.fill_encap = ila_fill_encap_info,
.get_encap_size = ila_encap_nlsize,
.cmp_encap = ila_encap_cmp,
+ .owner = THIS_MODULE,
};
int ila_lwt_init(void)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 7396e75..75c3082 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -176,7 +176,7 @@
/* Restore final destination back after routing done */
fl6.daddr = sk->sk_v6_daddr;
- res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+ res = ip6_xmit(sk, skb, &fl6, sk->sk_mark, rcu_dereference(np->opt),
np->tclass);
rcu_read_unlock();
return res;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 75b6108..630b73b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -367,35 +367,37 @@
static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, __be32 info)
+ u8 type, u8 code, int offset, __be32 info)
{
- const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data;
- __be16 *p = (__be16 *)(skb->data + offset);
- int grehlen = offset + 4;
+ const struct gre_base_hdr *greh;
+ const struct ipv6hdr *ipv6h;
+ int grehlen = sizeof(*greh);
struct ip6_tnl *t;
+ int key_off = 0;
__be16 flags;
+ __be32 key;
- flags = p[0];
- if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
- if (flags&(GRE_VERSION|GRE_ROUTING))
- return;
- if (flags&GRE_KEY) {
- grehlen += 4;
- if (flags&GRE_CSUM)
- grehlen += 4;
- }
+ if (!pskb_may_pull(skb, offset + grehlen))
+ return;
+ greh = (const struct gre_base_hdr *)(skb->data + offset);
+ flags = greh->flags;
+ if (flags & (GRE_VERSION | GRE_ROUTING))
+ return;
+ if (flags & GRE_CSUM)
+ grehlen += 4;
+ if (flags & GRE_KEY) {
+ key_off = grehlen + offset;
+ grehlen += 4;
}
- /* If only 8 bytes returned, keyed message will be dropped here */
- if (!pskb_may_pull(skb, grehlen))
+ if (!pskb_may_pull(skb, offset + grehlen))
return;
ipv6h = (const struct ipv6hdr *)skb->data;
- p = (__be16 *)(skb->data + offset);
+ greh = (const struct gre_base_hdr *)(skb->data + offset);
+ key = key_off ? *(__be32 *)(skb->data + key_off) : 0;
t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
- flags & GRE_KEY ?
- *(((__be32 *)p) + (grehlen / 4) - 1) : 0,
- p[1]);
+ key, greh->protocol);
if (!t)
return;
@@ -582,6 +584,9 @@
return -1;
offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+ /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+ ipv6h = ipv6_hdr(skb);
+
if (offset > 0) {
struct ipv6_tlv_tnl_enc_lim *tel;
tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 38122d0..7cebee5 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -172,7 +172,7 @@
* which are using proper atomic operations or spinlocks.
*/
int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
- struct ipv6_txoptions *opt, int tclass)
+ __u32 mark, struct ipv6_txoptions *opt, int tclass)
{
struct net *net = sock_net(sk);
const struct ipv6_pinfo *np = inet6_sk(sk);
@@ -240,7 +240,7 @@
skb->protocol = htons(ETH_P_IPV6);
skb->priority = sk->sk_priority;
- skb->mark = sk->sk_mark;
+ skb->mark = mark;
mtu = dst_mtu(dst);
if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
@@ -1021,6 +1021,11 @@
}
}
#endif
+ if (ipv6_addr_v4mapped(&fl6->saddr) &&
+ !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) {
+ err = -EAFNOSUPPORT;
+ goto out_err_release;
+ }
return 0;
@@ -1344,7 +1349,7 @@
*/
if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
headersize == sizeof(struct ipv6hdr) &&
- length < mtu - headersize &&
+ length <= mtu - headersize &&
!(flags & MSG_MORE) &&
rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
csummode = CHECKSUM_PARTIAL;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 36d2921..75fac93 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -400,18 +400,19 @@
__u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
{
- const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
- __u8 nexthdr = ipv6h->nexthdr;
- __u16 off = sizeof(*ipv6h);
+ const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw;
+ unsigned int nhoff = raw - skb->data;
+ unsigned int off = nhoff + sizeof(*ipv6h);
+ u8 next, nexthdr = ipv6h->nexthdr;
while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
- __u16 optlen = 0;
struct ipv6_opt_hdr *hdr;
- if (raw + off + sizeof(*hdr) > skb->data &&
- !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
+ u16 optlen;
+
+ if (!pskb_may_pull(skb, off + sizeof(*hdr)))
break;
- hdr = (struct ipv6_opt_hdr *) (raw + off);
+ hdr = (struct ipv6_opt_hdr *)(skb->data + off);
if (nexthdr == NEXTHDR_FRAGMENT) {
struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
if (frag_hdr->frag_off)
@@ -422,20 +423,29 @@
} else {
optlen = ipv6_optlen(hdr);
}
+ /* cache hdr->nexthdr, since pskb_may_pull() might
+ * invalidate hdr
+ */
+ next = hdr->nexthdr;
if (nexthdr == NEXTHDR_DEST) {
- __u16 i = off + 2;
+ u16 i = 2;
+
+ /* Remember : hdr is no longer valid at this point. */
+ if (!pskb_may_pull(skb, off + optlen))
+ break;
+
while (1) {
struct ipv6_tlv_tnl_enc_lim *tel;
/* No more room for encapsulation limit */
- if (i + sizeof (*tel) > off + optlen)
+ if (i + sizeof(*tel) > optlen)
break;
- tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i];
+ tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i);
/* return index of option if found and valid */
if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
tel->length == 1)
- return i;
+ return i + off - nhoff;
/* else jump to next option */
if (tel->type)
i += tel->length + 2;
@@ -443,7 +453,7 @@
i++;
}
}
- nexthdr = hdr->nexthdr;
+ nexthdr = next;
off += optlen;
}
return 0;
@@ -1108,7 +1118,7 @@
t->parms.name);
goto tx_err_dst_release;
}
- mtu = dst_mtu(dst) - psh_hlen;
+ mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen;
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
@@ -1117,7 +1127,7 @@
mtu = IPV6_MIN_MTU;
if (skb_dst(skb) && !t->parms.collect_md)
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
- if (skb->len > mtu && !skb_is_gso(skb)) {
+ if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) {
*pmtu = mtu;
err = -EMSGSIZE;
goto tx_err_dst_release;
@@ -1303,6 +1313,8 @@
fl6.flowlabel = key->label;
} else {
offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+ /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+ ipv6h = ipv6_hdr(skb);
if (offset > 0) {
struct ipv6_tlv_tnl_enc_lim *tel;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 14a3903..1bdc703 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -81,7 +81,7 @@
static void mld_ifc_timer_expire(unsigned long data);
static void mld_ifc_event(struct inet6_dev *idev);
static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc);
-static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *addr);
+static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc);
static void mld_clear_delrec(struct inet6_dev *idev);
static bool mld_in_v1_mode(const struct inet6_dev *idev);
static int sf_setstate(struct ifmcaddr6 *pmc);
@@ -692,9 +692,9 @@
dev_mc_del(dev, buf);
}
- if (mc->mca_flags & MAF_NOREPORT)
- goto done;
spin_unlock_bh(&mc->mca_lock);
+ if (mc->mca_flags & MAF_NOREPORT)
+ return;
if (!mc->idev->dead)
igmp6_leave_group(mc);
@@ -702,8 +702,6 @@
spin_lock_bh(&mc->mca_lock);
if (del_timer(&mc->mca_timer))
atomic_dec(&mc->mca_refcnt);
-done:
- ip6_mc_clear_src(mc);
spin_unlock_bh(&mc->mca_lock);
}
@@ -748,10 +746,11 @@
spin_unlock_bh(&idev->mc_lock);
}
-static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
+static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
{
struct ifmcaddr6 *pmc, *pmc_prev;
- struct ip6_sf_list *psf, *psf_next;
+ struct ip6_sf_list *psf;
+ struct in6_addr *pmca = &im->mca_addr;
spin_lock_bh(&idev->mc_lock);
pmc_prev = NULL;
@@ -768,14 +767,21 @@
}
spin_unlock_bh(&idev->mc_lock);
+ spin_lock_bh(&im->mca_lock);
if (pmc) {
- for (psf = pmc->mca_tomb; psf; psf = psf_next) {
- psf_next = psf->sf_next;
- kfree(psf);
+ im->idev = pmc->idev;
+ im->mca_crcount = idev->mc_qrv;
+ im->mca_sfmode = pmc->mca_sfmode;
+ if (pmc->mca_sfmode == MCAST_INCLUDE) {
+ im->mca_tomb = pmc->mca_tomb;
+ im->mca_sources = pmc->mca_sources;
+ for (psf = im->mca_sources; psf; psf = psf->sf_next)
+ psf->sf_crcount = im->mca_crcount;
}
in6_dev_put(pmc->idev);
kfree(pmc);
}
+ spin_unlock_bh(&im->mca_lock);
}
static void mld_clear_delrec(struct inet6_dev *idev)
@@ -904,7 +910,7 @@
mca_get(mc);
write_unlock_bh(&idev->lock);
- mld_del_delrec(idev, &mc->mca_addr);
+ mld_del_delrec(idev, mc);
igmp6_group_added(mc);
ma_put(mc);
return 0;
@@ -927,6 +933,7 @@
write_unlock_bh(&idev->lock);
igmp6_group_dropped(ma);
+ ip6_mc_clear_src(ma);
ma_put(ma);
return 0;
@@ -2501,15 +2508,17 @@
/* Withdraw multicast list */
read_lock_bh(&idev->lock);
- mld_ifc_stop_timer(idev);
- mld_gq_stop_timer(idev);
- mld_dad_stop_timer(idev);
for (i = idev->mc_list; i; i = i->next)
igmp6_group_dropped(i);
- read_unlock_bh(&idev->lock);
- mld_clear_delrec(idev);
+ /* Should stop timer after group drop. or we will
+ * start timer again in mld_ifc_event()
+ */
+ mld_ifc_stop_timer(idev);
+ mld_gq_stop_timer(idev);
+ mld_dad_stop_timer(idev);
+ read_unlock_bh(&idev->lock);
}
static void ipv6_mc_reset(struct inet6_dev *idev)
@@ -2531,8 +2540,10 @@
read_lock_bh(&idev->lock);
ipv6_mc_reset(idev);
- for (i = idev->mc_list; i; i = i->next)
+ for (i = idev->mc_list; i; i = i->next) {
+ mld_del_delrec(idev, i);
igmp6_group_added(i);
+ }
read_unlock_bh(&idev->lock);
}
@@ -2565,6 +2576,7 @@
/* Deactivate timers */
ipv6_mc_down(idev);
+ mld_clear_delrec(idev);
/* Delete all-nodes address. */
/* We cannot call ipv6_dev_mc_dec() directly, our caller in
@@ -2579,11 +2591,9 @@
write_lock_bh(&idev->lock);
while ((i = idev->mc_list) != NULL) {
idev->mc_list = i->next;
+
write_unlock_bh(&idev->lock);
-
- igmp6_group_dropped(i);
ma_put(i);
-
write_lock_bh(&idev->lock);
}
write_unlock_bh(&idev->lock);
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index d5263dc..b12e61b 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -72,10 +72,10 @@
return ret;
}
-static bool rpfilter_is_local(const struct sk_buff *skb)
+static bool
+rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in)
{
- const struct rt6_info *rt = (const void *) skb_dst(skb);
- return rt && (rt->rt6i_flags & RTF_LOCAL);
+ return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK;
}
static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
@@ -85,7 +85,7 @@
struct ipv6hdr *iph;
bool invert = info->flags & XT_RPFILTER_INVERT;
- if (rpfilter_is_local(skb))
+ if (rpfilter_is_loopback(skb, xt_in(par)))
return true ^ invert;
iph = ipv6_hdr(skb);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 1009040..eedee5d 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -157,6 +157,7 @@
fl6.fl6_sport = otcph->dest;
fl6.fl6_dport = otcph->source;
fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev);
+ fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark);
security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
@@ -180,6 +181,8 @@
skb_dst_set(nskb, dst);
+ nskb->mark = fl6.flowi6_mark;
+
skb_reserve(nskb, hh_len + dst->header_len);
ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
ip6_dst_hoplimit(dst));
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index c947aad..765facf 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -18,13 +18,6 @@
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
-static bool fib6_is_local(const struct sk_buff *skb)
-{
- const struct rt6_info *rt = (const void *)skb_dst(skb);
-
- return rt && (rt->rt6i_flags & RTF_LOCAL);
-}
-
static int get_ifindex(const struct net_device *dev)
{
return dev ? dev->ifindex : 0;
@@ -164,8 +157,10 @@
lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif);
- if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib6_is_local(pkt->skb)) {
- nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX);
+ if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
+ nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
+ nft_fib_store_result(dest, priv->result, pkt,
+ nft_in(pkt)->ifindex);
return;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ce5aaf4..7ea8537 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2896,6 +2896,11 @@
if (tb[RTA_MULTIPATH]) {
cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
+
+ err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
+ cfg->fc_mp_len);
+ if (err < 0)
+ goto errout;
}
if (tb[RTA_PREF]) {
@@ -2909,9 +2914,14 @@
if (tb[RTA_ENCAP])
cfg->fc_encap = tb[RTA_ENCAP];
- if (tb[RTA_ENCAP_TYPE])
+ if (tb[RTA_ENCAP_TYPE]) {
cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
+ err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+ if (err < 0)
+ goto errout;
+ }
+
if (tb[RTA_EXPIRES]) {
unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ);
@@ -3317,7 +3327,8 @@
if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
goto nla_put_failure;
- lwtunnel_fill_encap(skb, rt->dst.lwtstate);
+ if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
+ goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index b172d85..a855eb3 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -176,6 +176,8 @@
val = nla_data(info->attrs[SEG6_ATTR_DST]);
t_new = kmemdup(val, sizeof(*val), GFP_KERNEL);
+ if (!t_new)
+ return -ENOMEM;
mutex_lock(&sdata->lock);
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index ef1c8a4..6ef3dfb 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -174,7 +174,7 @@
* hash function (RadioGatun) with up to 1216 bits
*/
- /* saddr(16) + first_seg(1) + cleanup(1) + keyid(4) + seglist(16n) */
+ /* saddr(16) + first_seg(1) + flags(1) + keyid(4) + seglist(16n) */
plen = 16 + 1 + 1 + 4 + (hdr->first_segment + 1) * 16;
/* this limit allows for 14 segments */
@@ -186,7 +186,7 @@
*
* 1. Source IPv6 address (128 bits)
* 2. first_segment value (8 bits)
- * 3. cleanup flag (8 bits: highest bit is cleanup value, others are 0)
+ * 3. Flags (8 bits)
* 4. HMAC Key ID (32 bits)
* 5. All segments in the segments list (n * 128 bits)
*/
@@ -202,8 +202,8 @@
/* first_segment value */
*off++ = hdr->first_segment;
- /* cleanup flag */
- *off++ = !!(sr_has_cleanup(hdr)) << 7;
+ /* flags */
+ *off++ = hdr->flags;
/* HMAC Key ID */
memcpy(off, &hmackeyid, 4);
@@ -400,7 +400,7 @@
*p_tfm = tfm;
}
- p_tfm = this_cpu_ptr(algo->tfms);
+ p_tfm = raw_cpu_ptr(algo->tfms);
tfm = *p_tfm;
shsize = sizeof(*shash) + crypto_shash_descsize(tfm);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index bbfca22..c46f8cb 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -265,7 +265,9 @@
slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
#ifdef CONFIG_DST_CACHE
+ preempt_disable();
dst = dst_cache_get(&slwt->cache);
+ preempt_enable();
#endif
if (unlikely(!dst)) {
@@ -286,7 +288,9 @@
}
#ifdef CONFIG_DST_CACHE
+ preempt_disable();
dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
+ preempt_enable();
#endif
}
@@ -418,6 +422,7 @@
.fill_encap = seg6_fill_encap_info,
.get_encap_size = seg6_encap_nlsize,
.cmp_encap = seg6_encap_cmp,
+ .owner = THIS_MODULE,
};
int __init seg6_iptunnel_init(void)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index fad992a..99853c6 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1380,6 +1380,7 @@
err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
if (err) {
free_percpu(dev->tstats);
+ dev->tstats = NULL;
return err;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 73bc8fc6..4c60c6f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -148,8 +148,13 @@
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
- if (ipv6_addr_any(&usin->sin6_addr))
- usin->sin6_addr.s6_addr[15] = 0x1;
+ if (ipv6_addr_any(&usin->sin6_addr)) {
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+ ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+ &usin->sin6_addr);
+ else
+ usin->sin6_addr = in6addr_loopback;
+ }
addr_type = ipv6_addr_type(&usin->sin6_addr);
@@ -188,7 +193,7 @@
* TCP over IPv4
*/
- if (addr_type == IPV6_ADDR_MAPPED) {
+ if (addr_type & IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
@@ -469,7 +474,7 @@
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, fl6, opt, np->tclass);
+ err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -840,7 +845,7 @@
dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
if (!IS_ERR(dst)) {
skb_dst_set(buff, dst);
- ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass);
+ ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass);
TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
if (rst)
TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -991,6 +996,16 @@
return 0; /* don't send reset */
}
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+ /* We need to move header back to the beginning if xfrm6_policy_check()
+ * and tcp_v6_fill_cb() are going to be called again.
+ * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
+ */
+ memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+ sizeof(struct inet6_skb_parm));
+}
+
static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
@@ -1182,8 +1197,10 @@
sk_gfp_mask(sk, GFP_ATOMIC));
consume_skb(ireq->pktopts);
ireq->pktopts = NULL;
- if (newnp->pktoptions)
+ if (newnp->pktoptions) {
+ tcp_v6_restore_cb(newnp->pktoptions);
skb_set_owner_r(newnp->pktoptions, newsk);
+ }
}
}
@@ -1198,16 +1215,6 @@
return NULL;
}
-static void tcp_v6_restore_cb(struct sk_buff *skb)
-{
- /* We need to move header back to the beginning if xfrm6_policy_check()
- * and tcp_v6_fill_cb() are going to be called again.
- * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
- */
- memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
- sizeof(struct inet6_skb_parm));
-}
-
/* The socket must have it's spinlock held when we get
* here, unless it is a TCP_LISTEN socket.
*
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4d5c4ee..221825a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -441,7 +441,7 @@
return err;
csum_copy_err:
- if (!__sk_queue_drop_skb(sk, skb, flags)) {
+ if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) {
if (is_udp4) {
UDP_INC_STATS(sock_net(sk),
UDP_MIB_CSUMERRORS, is_udplite);
@@ -1033,6 +1033,10 @@
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
daddr = &sin6->sin6_addr;
+ if (ipv6_addr_any(daddr) &&
+ ipv6_addr_v4mapped(&np->saddr))
+ ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+ daddr);
break;
case AF_INET:
goto do_udp_sendmsg;
diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c
index acbe61c..160dc89 100644
--- a/net/irda/irqueue.c
+++ b/net/irda/irqueue.c
@@ -383,9 +383,6 @@
* for deallocating this structure if it's complex. If not the user can
* just supply kfree, which should take care of the job.
*/
-#ifdef CONFIG_LOCKDEP
-static int hashbin_lock_depth = 0;
-#endif
int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
{
irda_queue_t* queue;
@@ -396,22 +393,27 @@
IRDA_ASSERT(hashbin->magic == HB_MAGIC, return -1;);
/* Synchronize */
- if ( hashbin->hb_type & HB_LOCK ) {
- spin_lock_irqsave_nested(&hashbin->hb_spinlock, flags,
- hashbin_lock_depth++);
- }
+ if (hashbin->hb_type & HB_LOCK)
+ spin_lock_irqsave(&hashbin->hb_spinlock, flags);
/*
* Free the entries in the hashbin, TODO: use hashbin_clear when
* it has been shown to work
*/
for (i = 0; i < HASHBIN_SIZE; i ++ ) {
- queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
- while (queue ) {
- if (free_func)
- (*free_func)(queue);
- queue = dequeue_first(
- (irda_queue_t**) &hashbin->hb_queue[i]);
+ while (1) {
+ queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
+
+ if (!queue)
+ break;
+
+ if (free_func) {
+ if (hashbin->hb_type & HB_LOCK)
+ spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
+ free_func(queue);
+ if (hashbin->hb_type & HB_LOCK)
+ spin_lock_irqsave(&hashbin->hb_spinlock, flags);
+ }
}
}
@@ -420,12 +422,8 @@
hashbin->magic = ~HB_MAGIC;
/* Release lock */
- if ( hashbin->hb_type & HB_LOCK) {
+ if (hashbin->hb_type & HB_LOCK)
spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
-#ifdef CONFIG_LOCKDEP
- hashbin_lock_depth--;
-#endif
- }
/*
* Free the hashbin structure
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 7e08a4d..a646f34 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -929,24 +929,26 @@
goto out_error;
}
- /* New message, alloc head skb */
- head = alloc_skb(0, sk->sk_allocation);
- while (!head) {
- kcm_push(kcm);
- err = sk_stream_wait_memory(sk, &timeo);
- if (err)
- goto out_error;
-
+ if (msg_data_left(msg)) {
+ /* New message, alloc head skb */
head = alloc_skb(0, sk->sk_allocation);
+ while (!head) {
+ kcm_push(kcm);
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err)
+ goto out_error;
+
+ head = alloc_skb(0, sk->sk_allocation);
+ }
+
+ skb = head;
+
+ /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling
+ * csum_and_copy_from_iter from skb_do_copy_data_nocache.
+ */
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
}
- skb = head;
-
- /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling
- * csum_and_copy_from_iter from skb_do_copy_data_nocache.
- */
- skb->ip_summed = CHECKSUM_UNNECESSARY;
-
start:
while (msg_data_left(msg)) {
bool merge = true;
@@ -1018,10 +1020,12 @@
if (eor) {
bool not_busy = skb_queue_empty(&sk->sk_write_queue);
- /* Message complete, queue it on send buffer */
- __skb_queue_tail(&sk->sk_write_queue, head);
- kcm->seq_skb = NULL;
- KCM_STATS_INCR(kcm->stats.tx_msgs);
+ if (head) {
+ /* Message complete, queue it on send buffer */
+ __skb_queue_tail(&sk->sk_write_queue, head);
+ kcm->seq_skb = NULL;
+ KCM_STATS_INCR(kcm->stats.tx_msgs);
+ }
if (msg->msg_flags & MSG_BATCH) {
kcm->tx_wait_more = true;
@@ -1040,8 +1044,10 @@
} else {
/* Message not complete, save state */
partial_message:
- kcm->seq_skb = head;
- kcm_tx_msg(head)->last_skb = skb;
+ if (head) {
+ kcm->seq_skb = head;
+ kcm_tx_msg(head)->last_skb = skb;
+ }
}
KCM_STATS_ADD(kcm->stats.tx_bytes, copied);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 8f560f7..aebf281 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -263,6 +263,7 @@
int l2tp_nl_register_ops(enum l2tp_pwtype pw_type,
const struct l2tp_nl_cmd_ops *ops);
void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
/* Session reference counts. Incremented when code obtains a reference
* to a session.
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 3d73278..28c2154 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -11,6 +11,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <asm/ioctls.h>
#include <linux/icmp.h>
#include <linux/module.h>
#include <linux/skbuff.h>
@@ -553,6 +554,30 @@
return err ? err : copied;
}
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+{
+ struct sk_buff *skb;
+ int amount;
+
+ switch (cmd) {
+ case SIOCOUTQ:
+ amount = sk_wmem_alloc_get(sk);
+ break;
+ case SIOCINQ:
+ spin_lock_bh(&sk->sk_receive_queue.lock);
+ skb = skb_peek(&sk->sk_receive_queue);
+ amount = skb ? skb->len : 0;
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
+ break;
+
+ default:
+ return -ENOIOCTLCMD;
+ }
+
+ return put_user(amount, (int __user *)arg);
+}
+EXPORT_SYMBOL(l2tp_ioctl);
+
static struct proto l2tp_ip_prot = {
.name = "L2TP/IP",
.owner = THIS_MODULE,
@@ -561,7 +586,7 @@
.bind = l2tp_ip_bind,
.connect = l2tp_ip_connect,
.disconnect = l2tp_ip_disconnect,
- .ioctl = udp_ioctl,
+ .ioctl = l2tp_ioctl,
.destroy = l2tp_ip_destroy_sock,
.setsockopt = ip_setsockopt,
.getsockopt = ip_getsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 331ccf5..f47c452 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -722,7 +722,7 @@
.bind = l2tp_ip6_bind,
.connect = l2tp_ip6_connect,
.disconnect = l2tp_ip6_disconnect,
- .ioctl = udp_ioctl,
+ .ioctl = l2tp_ioctl,
.destroy = l2tp_ip6_destroy_sock,
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 3e821da..8bc5a1b 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -821,7 +821,10 @@
* another trick required to cope with how the PROCOM state
* machine works. -acme
*/
+ skb_orphan(skb);
+ sock_hold(sk);
skb->sk = sk;
+ skb->destructor = sock_efree;
}
if (!sock_owned_by_user(sk))
llc_conn_rcv(sk, skb);
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index d0e1e80..5404d0d 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -290,7 +290,10 @@
ev->type = LLC_SAP_EV_TYPE_PDU;
ev->reason = 0;
+ skb_orphan(skb);
+ sock_hold(sk);
skb->sk = sk;
+ skb->destructor = sock_efree;
llc_sap_state_process(sap, skb);
}
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index e75cbf6..a0d901d 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -231,9 +231,6 @@
!(sta->sdata->bss && sta->sdata->bss == sdata->bss))
continue;
- if (!sta->uploaded || !test_sta_flag(sta, WLAN_STA_ASSOC))
- continue;
-
max_bw = max(max_bw, ieee80211_get_sta_bw(&sta->sta));
}
rcu_read_unlock();
diff --git a/net/mac80211/fils_aead.c b/net/mac80211/fils_aead.c
index ecfdd97..5c3af5e 100644
--- a/net/mac80211/fils_aead.c
+++ b/net/mac80211/fils_aead.c
@@ -124,7 +124,7 @@
/* CTR */
- tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, 0);
+ tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(tfm2)) {
kfree(tmp);
return PTR_ERR(tfm2);
@@ -183,7 +183,7 @@
/* CTR */
- tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, 0);
+ tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(tfm2))
return PTR_ERR(tfm2);
/* K2 for CTR */
@@ -272,7 +272,7 @@
crypt_len = skb->data + skb->len - encr;
skb_put(skb, AES_BLOCK_SIZE);
return aes_siv_encrypt(assoc_data->fils_kek, assoc_data->fils_kek_len,
- encr, crypt_len, 1, addr, len, encr);
+ encr, crypt_len, 5, addr, len, encr);
}
int fils_decrypt_assoc_resp(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 41497b6..d37ae7d 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -6,6 +6,7 @@
* Copyright (c) 2006 Jiri Benc <jbenc@suse.cz>
* Copyright 2008, Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 Intel Deutschland GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -1295,6 +1296,26 @@
} else if (ieee80211_is_action(mgmt->frame_control) &&
mgmt->u.action.category == WLAN_CATEGORY_VHT) {
switch (mgmt->u.action.u.vht_group_notif.action_code) {
+ case WLAN_VHT_ACTION_OPMODE_NOTIF: {
+ struct ieee80211_rx_status *status;
+ enum nl80211_band band;
+ u8 opmode;
+
+ status = IEEE80211_SKB_RXCB(skb);
+ band = status->band;
+ opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode;
+
+ mutex_lock(&local->sta_mtx);
+ sta = sta_info_get_bss(sdata, mgmt->sa);
+
+ if (sta)
+ ieee80211_vht_handle_opmode(sdata, sta,
+ opmode,
+ band);
+
+ mutex_unlock(&local->sta_mtx);
+ break;
+ }
case WLAN_VHT_ACTION_GROUPID_MGMT:
ieee80211_process_mu_groups(sdata, mgmt);
break;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 1822c77..56fb479 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -913,12 +913,17 @@
supp_ht = supp_ht || sband->ht_cap.ht_supported;
supp_vht = supp_vht || sband->vht_cap.vht_supported;
- if (sband->ht_cap.ht_supported)
- local->rx_chains =
- max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs),
- local->rx_chains);
+ if (!sband->ht_cap.ht_supported)
+ continue;
/* TODO: consider VHT for RX chains, hopefully it's the same */
+ local->rx_chains =
+ max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs),
+ local->rx_chains);
+
+ /* no need to mask, SM_PS_DISABLED has all bits set */
+ sband->ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED <<
+ IEEE80211_HT_CAP_SM_PS_SHIFT;
}
/* if low-level driver supports AP, we also support VLAN */
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 42120d9..50e1b7f 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -339,7 +339,7 @@
/* fast-forward to vendor IEs */
offset = ieee80211_ie_split_vendor(ifmsh->ie, ifmsh->ie_len, 0);
- if (offset) {
+ if (offset < ifmsh->ie_len) {
len = ifmsh->ie_len - offset;
data = ifmsh->ie + offset;
if (skb_tailroom(skb) < len)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3e289a6..3090dd4 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2472,7 +2472,8 @@
if (!ifmsh->mshcfg.dot11MeshForwarding)
goto out;
- fwd_skb = skb_copy_expand(skb, local->tx_headroom, 0, GFP_ATOMIC);
+ fwd_skb = skb_copy_expand(skb, local->tx_headroom +
+ sdata->encrypt_headroom, 0, GFP_ATOMIC);
if (!fwd_skb) {
net_info_ratelimited("%s: failed to clone mesh frame\n",
sdata->name);
@@ -2880,17 +2881,10 @@
switch (mgmt->u.action.u.vht_opmode_notif.action_code) {
case WLAN_VHT_ACTION_OPMODE_NOTIF: {
- u8 opmode;
-
/* verify opmode is present */
if (len < IEEE80211_MIN_ACTION_SIZE + 2)
goto invalid;
-
- opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode;
-
- ieee80211_vht_handle_opmode(rx->sdata, rx->sta,
- opmode, status->band);
- goto handled;
+ goto queue;
}
case WLAN_VHT_ACTION_GROUPID_MGMT: {
if (len < IEEE80211_MIN_ACTION_SIZE + 25)
@@ -3942,21 +3936,31 @@
u64_stats_update_end(&stats->syncp);
if (fast_rx->internal_forward) {
- struct sta_info *dsta = sta_info_get(rx->sdata, skb->data);
+ struct sk_buff *xmit_skb = NULL;
+ bool multicast = is_multicast_ether_addr(skb->data);
- if (dsta) {
+ if (multicast) {
+ xmit_skb = skb_copy(skb, GFP_ATOMIC);
+ } else if (sta_info_get(rx->sdata, skb->data)) {
+ xmit_skb = skb;
+ skb = NULL;
+ }
+
+ if (xmit_skb) {
/*
* Send to wireless media and increase priority by 256
* to keep the received priority instead of
* reclassifying the frame (see cfg80211_classify8021d).
*/
- skb->priority += 256;
- skb->protocol = htons(ETH_P_802_3);
- skb_reset_network_header(skb);
- skb_reset_mac_header(skb);
- dev_queue_xmit(skb);
- return true;
+ xmit_skb->priority += 256;
+ xmit_skb->protocol = htons(ETH_P_802_3);
+ skb_reset_network_header(xmit_skb);
+ skb_reset_mac_header(xmit_skb);
+ dev_queue_xmit(xmit_skb);
}
+
+ if (!skb)
+ return true;
}
/* deliver to local stack */
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index b6cfcf0..50c3090 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1501,8 +1501,8 @@
/* This will evaluate to 1, 3, 5 or 7. */
for (ac = IEEE80211_AC_VO; ac < IEEE80211_NUM_ACS; ac++)
- if (ignored_acs & BIT(ac))
- continue;
+ if (!(ignored_acs & ieee80211_ac_to_qos_mask[ac]))
+ break;
tid = 7 - 2 * ac;
ieee80211_send_null_response(sta, tid, reason, true, false);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 0d8b716..797e847 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1243,7 +1243,7 @@
static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
struct ieee80211_vif *vif,
- struct ieee80211_sta *pubsta,
+ struct sta_info *sta,
struct sk_buff *skb)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
@@ -1257,10 +1257,13 @@
if (!ieee80211_is_data(hdr->frame_control))
return NULL;
- if (pubsta) {
+ if (sta) {
u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
- txq = pubsta->txq[tid];
+ if (!sta->uploaded)
+ return NULL;
+
+ txq = sta->sta.txq[tid];
} else if (vif) {
txq = vif->txq;
}
@@ -1503,23 +1506,17 @@
struct fq *fq = &local->fq;
struct ieee80211_vif *vif;
struct txq_info *txqi;
- struct ieee80211_sta *pubsta;
if (!local->ops->wake_tx_queue ||
sdata->vif.type == NL80211_IFTYPE_MONITOR)
return false;
- if (sta && sta->uploaded)
- pubsta = &sta->sta;
- else
- pubsta = NULL;
-
if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
sdata = container_of(sdata->bss,
struct ieee80211_sub_if_data, u.ap);
vif = &sdata->vif;
- txqi = ieee80211_get_txq(local, vif, pubsta, skb);
+ txqi = ieee80211_get_txq(local, vif, sta, skb);
if (!txqi)
return false;
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index 6832bf6..43e45bb 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -527,8 +527,10 @@
u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode, band);
- if (changed > 0)
+ if (changed > 0) {
+ ieee80211_recalc_min_chandef(sdata);
rate_control_rate_update(local, sband, sta, changed);
+ }
}
void ieee80211_get_vht_mask_from_cap(__le16 vht_cap,
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 15fe976..5b77377 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -98,18 +98,19 @@
}
EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
-static u32 mpls_multipath_hash(struct mpls_route *rt,
- struct sk_buff *skb, bool bos)
+static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb)
{
struct mpls_entry_decoded dec;
+ unsigned int mpls_hdr_len = 0;
struct mpls_shim_hdr *hdr;
bool eli_seen = false;
int label_index;
u32 hash = 0;
- for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos;
+ for (label_index = 0; label_index < MAX_MP_SELECT_LABELS;
label_index++) {
- if (!pskb_may_pull(skb, sizeof(*hdr) * label_index))
+ mpls_hdr_len += sizeof(*hdr);
+ if (!pskb_may_pull(skb, mpls_hdr_len))
break;
/* Read and decode the current label */
@@ -134,37 +135,38 @@
eli_seen = true;
}
- bos = dec.bos;
- if (bos && pskb_may_pull(skb, sizeof(*hdr) * label_index +
- sizeof(struct iphdr))) {
+ if (!dec.bos)
+ continue;
+
+ /* found bottom label; does skb have room for a header? */
+ if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) {
const struct iphdr *v4hdr;
- v4hdr = (const struct iphdr *)(mpls_hdr(skb) +
- label_index);
+ v4hdr = (const struct iphdr *)(hdr + 1);
if (v4hdr->version == 4) {
hash = jhash_3words(ntohl(v4hdr->saddr),
ntohl(v4hdr->daddr),
v4hdr->protocol, hash);
} else if (v4hdr->version == 6 &&
- pskb_may_pull(skb, sizeof(*hdr) * label_index +
- sizeof(struct ipv6hdr))) {
+ pskb_may_pull(skb, mpls_hdr_len +
+ sizeof(struct ipv6hdr))) {
const struct ipv6hdr *v6hdr;
- v6hdr = (const struct ipv6hdr *)(mpls_hdr(skb) +
- label_index);
-
+ v6hdr = (const struct ipv6hdr *)(hdr + 1);
hash = __ipv6_addr_jhash(&v6hdr->saddr, hash);
hash = __ipv6_addr_jhash(&v6hdr->daddr, hash);
hash = jhash_1word(v6hdr->nexthdr, hash);
}
}
+
+ break;
}
return hash;
}
static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
- struct sk_buff *skb, bool bos)
+ struct sk_buff *skb)
{
int alive = ACCESS_ONCE(rt->rt_nhn_alive);
u32 hash = 0;
@@ -180,7 +182,7 @@
if (alive <= 0)
return NULL;
- hash = mpls_multipath_hash(rt, skb, bos);
+ hash = mpls_multipath_hash(rt, skb);
nh_index = hash % alive;
if (alive == rt->rt_nhn)
goto out;
@@ -278,17 +280,11 @@
hdr = mpls_hdr(skb);
dec = mpls_entry_decode(hdr);
- /* Pop the label */
- skb_pull(skb, sizeof(*hdr));
- skb_reset_network_header(skb);
-
- skb_orphan(skb);
-
rt = mpls_route_input_rcu(net, dec.label);
if (!rt)
goto drop;
- nh = mpls_select_multipath(rt, skb, dec.bos);
+ nh = mpls_select_multipath(rt, skb);
if (!nh)
goto drop;
@@ -297,6 +293,12 @@
if (!mpls_output_possible(out_dev))
goto drop;
+ /* Pop the label */
+ skb_pull(skb, sizeof(*hdr));
+ skb_reset_network_header(skb);
+
+ skb_orphan(skb);
+
if (skb_warn_if_lro(skb))
goto drop;
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 2f7ccd9..1d281c1 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -215,6 +215,7 @@
.fill_encap = mpls_fill_encap_info,
.get_encap_size = mpls_encap_nlsize,
.cmp_encap = mpls_encap_cmp,
+ .owner = THIS_MODULE,
};
static int __init mpls_iptunnel_init(void)
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 63729b4..bbc45f8 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -494,7 +494,7 @@
depends on NF_CONNTRACK
tristate "Netfilter nf_tables conntrack module"
help
- This option adds the "meta" expression that you can use to match
+ This option adds the "ct" expression that you can use to match
connection tracking information such as the flow state.
config NFT_SET_RBTREE
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3a073cd..4e8083c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -85,11 +85,11 @@
static __read_mostly bool nf_conntrack_locks_all;
/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */
-#define GC_MAX_BUCKETS_DIV 64u
-/* upper bound of scan intervals */
-#define GC_INTERVAL_MAX (2 * HZ)
-/* maximum conntracks to evict per gc run */
-#define GC_MAX_EVICTS 256u
+#define GC_MAX_BUCKETS_DIV 128u
+/* upper bound of full table scan */
+#define GC_MAX_SCAN_JIFFIES (16u * HZ)
+/* desired ratio of entries found to be expired */
+#define GC_EVICT_RATIO 50u
static struct conntrack_gc_work conntrack_gc_work;
@@ -938,6 +938,7 @@
static void gc_worker(struct work_struct *work)
{
+ unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);
unsigned int i, goal, buckets = 0, expired_count = 0;
struct conntrack_gc_work *gc_work;
unsigned int ratio, scanned = 0;
@@ -979,8 +980,7 @@
*/
rcu_read_unlock();
cond_resched_rcu_qs();
- } while (++buckets < goal &&
- expired_count < GC_MAX_EVICTS);
+ } while (++buckets < goal);
if (gc_work->exiting)
return;
@@ -997,27 +997,25 @@
* 1. Minimize time until we notice a stale entry
* 2. Maximize scan intervals to not waste cycles
*
- * Normally, expired_count will be 0, this increases the next_run time
- * to priorize 2) above.
+ * Normally, expire ratio will be close to 0.
*
- * As soon as a timed-out entry is found, move towards 1) and increase
- * the scan frequency.
- * In case we have lots of evictions next scan is done immediately.
+ * As soon as a sizeable fraction of the entries have expired
+ * increase scan frequency.
*/
ratio = scanned ? expired_count * 100 / scanned : 0;
- if (ratio >= 90 || expired_count == GC_MAX_EVICTS) {
- gc_work->next_gc_run = 0;
- next_run = 0;
- } else if (expired_count) {
- gc_work->next_gc_run /= 2U;
- next_run = msecs_to_jiffies(1);
+ if (ratio > GC_EVICT_RATIO) {
+ gc_work->next_gc_run = min_interval;
} else {
- if (gc_work->next_gc_run < GC_INTERVAL_MAX)
- gc_work->next_gc_run += msecs_to_jiffies(1);
+ unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV;
- next_run = gc_work->next_gc_run;
+ BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0);
+
+ gc_work->next_gc_run += min_interval;
+ if (gc_work->next_gc_run > max)
+ gc_work->next_gc_run = max;
}
+ next_run = gc_work->next_gc_run;
gc_work->last_bucket = i;
queue_delayed_work(system_long_wq, &gc_work->dwork, next_run);
}
@@ -1025,7 +1023,7 @@
static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
{
INIT_DELAYED_WORK(&gc_work->dwork, gc_worker);
- gc_work->next_gc_run = GC_INTERVAL_MAX;
+ gc_work->next_gc_run = HZ;
gc_work->exiting = false;
}
@@ -1917,7 +1915,7 @@
nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
conntrack_gc_work_init(&conntrack_gc_work);
- queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, GC_INTERVAL_MAX);
+ queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, HZ);
return 0;
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 3dca90d..ffb9e8a 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -13,7 +13,6 @@
/* Internal logging interface, which relies on the real
LOG target modules */
-#define NF_LOG_PREFIXLEN 128
#define NFLOGGER_NAME_LEN 64
static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0db5f97..1b91376 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -928,7 +928,8 @@
}
static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
- [NFTA_CHAIN_TABLE] = { .type = NLA_STRING },
+ [NFTA_CHAIN_TABLE] = { .type = NLA_STRING,
+ .len = NFT_TABLE_MAXNAMELEN - 1 },
[NFTA_CHAIN_HANDLE] = { .type = NLA_U64 },
[NFTA_CHAIN_NAME] = { .type = NLA_STRING,
.len = NFT_CHAIN_MAXNAMELEN - 1 },
@@ -1854,7 +1855,8 @@
}
static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
- [NFTA_RULE_TABLE] = { .type = NLA_STRING },
+ [NFTA_RULE_TABLE] = { .type = NLA_STRING,
+ .len = NFT_TABLE_MAXNAMELEN - 1 },
[NFTA_RULE_CHAIN] = { .type = NLA_STRING,
.len = NFT_CHAIN_MAXNAMELEN - 1 },
[NFTA_RULE_HANDLE] = { .type = NLA_U64 },
@@ -2443,7 +2445,8 @@
}
static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
- [NFTA_SET_TABLE] = { .type = NLA_STRING },
+ [NFTA_SET_TABLE] = { .type = NLA_STRING,
+ .len = NFT_TABLE_MAXNAMELEN - 1 },
[NFTA_SET_NAME] = { .type = NLA_STRING,
.len = NFT_SET_MAXNAMELEN - 1 },
[NFTA_SET_FLAGS] = { .type = NLA_U32 },
@@ -3084,9 +3087,9 @@
}
static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
- const struct nft_set *set,
+ struct nft_set *set,
const struct nft_set_iter *iter,
- const struct nft_set_elem *elem)
+ struct nft_set_elem *elem)
{
const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
enum nft_registers dreg;
@@ -3192,8 +3195,10 @@
};
static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = {
- [NFTA_SET_ELEM_LIST_TABLE] = { .type = NLA_STRING },
- [NFTA_SET_ELEM_LIST_SET] = { .type = NLA_STRING },
+ [NFTA_SET_ELEM_LIST_TABLE] = { .type = NLA_STRING,
+ .len = NFT_TABLE_MAXNAMELEN - 1 },
+ [NFTA_SET_ELEM_LIST_SET] = { .type = NLA_STRING,
+ .len = NFT_SET_MAXNAMELEN - 1 },
[NFTA_SET_ELEM_LIST_ELEMENTS] = { .type = NLA_NESTED },
[NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 },
};
@@ -3303,9 +3308,9 @@
};
static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
- const struct nft_set *set,
+ struct nft_set *set,
const struct nft_set_iter *iter,
- const struct nft_set_elem *elem)
+ struct nft_set_elem *elem)
{
struct nft_set_dump_args *args;
@@ -3317,7 +3322,7 @@
{
struct net *net = sock_net(skb->sk);
u8 genmask = nft_genmask_cur(net);
- const struct nft_set *set;
+ struct nft_set *set;
struct nft_set_dump_args args;
struct nft_ctx ctx;
struct nlattr *nla[NFTA_SET_ELEM_LIST_MAX + 1];
@@ -3740,10 +3745,18 @@
goto err5;
}
+ if (set->size &&
+ !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) {
+ err = -ENFILE;
+ goto err6;
+ }
+
nft_trans_elem(trans) = elem;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
+err6:
+ set->ops->remove(set, &elem);
err5:
kfree(trans);
err4:
@@ -3790,15 +3803,9 @@
return -EBUSY;
nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
- if (set->size &&
- !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact))
- return -ENFILE;
-
err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags);
- if (err < 0) {
- atomic_dec(&set->nelems);
+ if (err < 0)
break;
- }
}
return err;
}
@@ -3883,9 +3890,9 @@
}
static int nft_flush_set(const struct nft_ctx *ctx,
- const struct nft_set *set,
+ struct nft_set *set,
const struct nft_set_iter *iter,
- const struct nft_set_elem *elem)
+ struct nft_set_elem *elem)
{
struct nft_trans *trans;
int err;
@@ -3899,9 +3906,10 @@
err = -ENOENT;
goto err1;
}
+ set->ndeact++;
- nft_trans_elem_set(trans) = (struct nft_set *)set;
- nft_trans_elem(trans) = *((struct nft_set_elem *)elem);
+ nft_trans_elem_set(trans) = set;
+ nft_trans_elem(trans) = *elem;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
@@ -4032,8 +4040,10 @@
EXPORT_SYMBOL_GPL(nf_tables_obj_lookup);
static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
- [NFTA_OBJ_TABLE] = { .type = NLA_STRING },
- [NFTA_OBJ_NAME] = { .type = NLA_STRING },
+ [NFTA_OBJ_TABLE] = { .type = NLA_STRING,
+ .len = NFT_TABLE_MAXNAMELEN - 1 },
+ [NFTA_OBJ_NAME] = { .type = NLA_STRING,
+ .len = NFT_OBJ_MAXNAMELEN - 1 },
[NFTA_OBJ_TYPE] = { .type = NLA_U32 },
[NFTA_OBJ_DATA] = { .type = NLA_NESTED },
};
@@ -4262,10 +4272,11 @@
if (idx > s_idx)
memset(&cb->args[1], 0,
sizeof(cb->args) - sizeof(cb->args[0]));
- if (filter->table[0] &&
+ if (filter && filter->table[0] &&
strcmp(filter->table, table->name))
goto cont;
- if (filter->type != NFT_OBJECT_UNSPEC &&
+ if (filter &&
+ filter->type != NFT_OBJECT_UNSPEC &&
obj->type->type != filter->type)
goto cont;
@@ -5009,9 +5020,9 @@
const struct nft_chain *chain);
static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
- const struct nft_set *set,
+ struct nft_set *set,
const struct nft_set_iter *iter,
- const struct nft_set_elem *elem)
+ struct nft_set_elem *elem)
{
const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
const struct nft_data *data;
@@ -5035,7 +5046,7 @@
{
const struct nft_rule *rule;
const struct nft_expr *expr, *last;
- const struct nft_set *set;
+ struct nft_set *set;
struct nft_set_binding *binding;
struct nft_set_iter iter;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 7de2f46..049ad2d 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -98,7 +98,8 @@
}
static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = {
- [NFTA_DYNSET_SET_NAME] = { .type = NLA_STRING },
+ [NFTA_DYNSET_SET_NAME] = { .type = NLA_STRING,
+ .len = NFT_SET_MAXNAMELEN - 1 },
[NFTA_DYNSET_SET_ID] = { .type = NLA_U32 },
[NFTA_DYNSET_OP] = { .type = NLA_U32 },
[NFTA_DYNSET_SREG_KEY] = { .type = NLA_U32 },
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 6271e40..6f6e644 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -39,7 +39,8 @@
static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = {
[NFTA_LOG_GROUP] = { .type = NLA_U16 },
- [NFTA_LOG_PREFIX] = { .type = NLA_STRING },
+ [NFTA_LOG_PREFIX] = { .type = NLA_STRING,
+ .len = NF_LOG_PREFIXLEN - 1 },
[NFTA_LOG_SNAPLEN] = { .type = NLA_U32 },
[NFTA_LOG_QTHRESHOLD] = { .type = NLA_U16 },
[NFTA_LOG_LEVEL] = { .type = NLA_U32 },
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index d4f97fa..e21aea7 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -49,7 +49,8 @@
}
static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = {
- [NFTA_LOOKUP_SET] = { .type = NLA_STRING },
+ [NFTA_LOOKUP_SET] = { .type = NLA_STRING,
+ .len = NFT_SET_MAXNAMELEN - 1 },
[NFTA_LOOKUP_SET_ID] = { .type = NLA_U32 },
[NFTA_LOOKUP_SREG] = { .type = NLA_U32 },
[NFTA_LOOKUP_DREG] = { .type = NLA_U32 },
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 415a65b..1ae8c49 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -193,10 +193,12 @@
}
static const struct nla_policy nft_objref_policy[NFTA_OBJREF_MAX + 1] = {
- [NFTA_OBJREF_IMM_NAME] = { .type = NLA_STRING },
+ [NFTA_OBJREF_IMM_NAME] = { .type = NLA_STRING,
+ .len = NFT_OBJ_MAXNAMELEN - 1 },
[NFTA_OBJREF_IMM_TYPE] = { .type = NLA_U32 },
[NFTA_OBJREF_SET_SREG] = { .type = NLA_U32 },
- [NFTA_OBJREF_SET_NAME] = { .type = NLA_STRING },
+ [NFTA_OBJREF_SET_NAME] = { .type = NLA_STRING,
+ .len = NFT_SET_MAXNAMELEN - 1 },
[NFTA_OBJREF_SET_ID] = { .type = NLA_U32 },
};
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 1e20e2b..e36069f 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -212,7 +212,7 @@
rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params);
}
-static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
+static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set,
struct nft_set_iter *iter)
{
struct nft_hash *priv = nft_set_priv(set);
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 08376e5..f06f55e 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -221,7 +221,7 @@
}
static void nft_rbtree_walk(const struct nft_ctx *ctx,
- const struct nft_set *set,
+ struct nft_set *set,
struct nft_set_iter *iter)
{
const struct nft_rbtree *priv = nft_set_priv(set);
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 6b78bab..54253ea 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -514,7 +514,7 @@
int hooknum, nh_off, err = NF_ACCEPT;
nh_off = skb_network_offset(skb);
- skb_pull(skb, nh_off);
+ skb_pull_rcsum(skb, nh_off);
/* See HOOK2MANIP(). */
if (maniptype == NF_NAT_MANIP_SRC)
@@ -579,6 +579,7 @@
err = nf_nat_packet(ct, ctinfo, hooknum, skb);
push:
skb_push(skb, nh_off);
+ skb_postpush_rcsum(skb, skb->data, nh_off);
return err;
}
@@ -886,7 +887,7 @@
/* The conntrack module expects to be working at L3. */
nh_ofs = skb_network_offset(skb);
- skb_pull(skb, nh_ofs);
+ skb_pull_rcsum(skb, nh_ofs);
if (key->ip.frag != OVS_FRAG_TYPE_NONE) {
err = handle_fragments(net, key, info->zone.id, skb);
@@ -900,6 +901,7 @@
err = ovs_ct_lookup(net, key, info, skb);
skb_push(skb, nh_ofs);
+ skb_postpush_rcsum(skb, skb->data, nh_ofs);
if (err)
kfree_skb(skb);
return err;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b9e1a13..70f5b6a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1497,6 +1497,8 @@
f->arr[f->num_members] = sk;
smp_wmb();
f->num_members++;
+ if (f->num_members == 1)
+ dev_add_pack(&f->prot_hook);
spin_unlock(&f->lock);
}
@@ -1513,6 +1515,8 @@
BUG_ON(i >= f->num_members);
f->arr[i] = f->arr[f->num_members - 1];
f->num_members--;
+ if (f->num_members == 0)
+ __dev_remove_pack(&f->prot_hook);
spin_unlock(&f->lock);
}
@@ -1619,6 +1623,7 @@
static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
{
+ struct packet_rollover *rollover = NULL;
struct packet_sock *po = pkt_sk(sk);
struct packet_fanout *f, *match;
u8 type = type_flags & 0xff;
@@ -1641,23 +1646,28 @@
return -EINVAL;
}
- if (!po->running)
- return -EINVAL;
+ mutex_lock(&fanout_mutex);
+ err = -EINVAL;
+ if (!po->running)
+ goto out;
+
+ err = -EALREADY;
if (po->fanout)
- return -EALREADY;
+ goto out;
if (type == PACKET_FANOUT_ROLLOVER ||
(type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
- po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL);
- if (!po->rollover)
- return -ENOMEM;
- atomic_long_set(&po->rollover->num, 0);
- atomic_long_set(&po->rollover->num_huge, 0);
- atomic_long_set(&po->rollover->num_failed, 0);
+ err = -ENOMEM;
+ rollover = kzalloc(sizeof(*rollover), GFP_KERNEL);
+ if (!rollover)
+ goto out;
+ atomic_long_set(&rollover->num, 0);
+ atomic_long_set(&rollover->num_huge, 0);
+ atomic_long_set(&rollover->num_failed, 0);
+ po->rollover = rollover;
}
- mutex_lock(&fanout_mutex);
match = NULL;
list_for_each_entry(f, &fanout_list, list) {
if (f->id == id &&
@@ -1687,7 +1697,6 @@
match->prot_hook.func = packet_rcv_fanout;
match->prot_hook.af_packet_priv = match;
match->prot_hook.id_match = match_fanout_group;
- dev_add_pack(&match->prot_hook);
list_add(&match->list, &fanout_list);
}
err = -EINVAL;
@@ -1704,36 +1713,40 @@
}
}
out:
- mutex_unlock(&fanout_mutex);
- if (err) {
- kfree(po->rollover);
+ if (err && rollover) {
+ kfree(rollover);
po->rollover = NULL;
}
+ mutex_unlock(&fanout_mutex);
return err;
}
-static void fanout_release(struct sock *sk)
+/* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes
+ * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout.
+ * It is the responsibility of the caller to call fanout_release_data() and
+ * free the returned packet_fanout (after synchronize_net())
+ */
+static struct packet_fanout *fanout_release(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
struct packet_fanout *f;
- f = po->fanout;
- if (!f)
- return;
-
mutex_lock(&fanout_mutex);
- po->fanout = NULL;
+ f = po->fanout;
+ if (f) {
+ po->fanout = NULL;
- if (atomic_dec_and_test(&f->sk_ref)) {
- list_del(&f->list);
- dev_remove_pack(&f->prot_hook);
- fanout_release_data(f);
- kfree(f);
+ if (atomic_dec_and_test(&f->sk_ref))
+ list_del(&f->list);
+ else
+ f = NULL;
+
+ if (po->rollover)
+ kfree_rcu(po->rollover, rcu);
}
mutex_unlock(&fanout_mutex);
- if (po->rollover)
- kfree_rcu(po->rollover, rcu);
+ return f;
}
static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
@@ -1976,7 +1989,7 @@
return -EINVAL;
*len -= sizeof(vnet_hdr);
- if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le()))
+ if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true))
return -EINVAL;
return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr));
@@ -2237,7 +2250,7 @@
if (po->has_vnet_hdr) {
if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
sizeof(struct virtio_net_hdr),
- vio_le())) {
+ vio_le(), true)) {
spin_lock(&sk->sk_receive_queue.lock);
goto drop_n_account;
}
@@ -2755,7 +2768,7 @@
struct virtio_net_hdr vnet_hdr = { 0 };
int offset = 0;
struct packet_sock *po = pkt_sk(sk);
- int hlen, tlen;
+ int hlen, tlen, linear;
int extra_len = 0;
/*
@@ -2816,8 +2829,9 @@
err = -ENOBUFS;
hlen = LL_RESERVED_SPACE(dev);
tlen = dev->needed_tailroom;
- skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
- __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len),
+ linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len);
+ linear = max(linear, min_t(int, len, dev->hard_header_len));
+ skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear,
msg->msg_flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto out_unlock;
@@ -2906,6 +2920,7 @@
{
struct sock *sk = sock->sk;
struct packet_sock *po;
+ struct packet_fanout *f;
struct net *net;
union tpacket_req_u req_u;
@@ -2945,9 +2960,14 @@
packet_set_ring(sk, &req_u, 1, 1);
}
- fanout_release(sk);
+ f = fanout_release(sk);
synchronize_net();
+
+ if (f) {
+ fanout_release_data(f);
+ kfree(f);
+ }
/*
* Now the socket is dead. No more input will appear.
*/
@@ -3899,7 +3919,6 @@
}
if (msg == NETDEV_UNREGISTER) {
packet_cached_dev_reset(po);
- fanout_release(sk);
po->ifindex = -1;
if (po->prot_hook.dev)
dev_put(po->prot_hook.dev);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 2095c83..e10456ef6f 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -900,8 +900,6 @@
goto err;
}
act->order = i;
- if (event == RTM_GETACTION)
- act->tcfa_refcnt++;
list_add_tail(&act->list, &actions);
}
@@ -914,7 +912,8 @@
return ret;
}
err:
- tcf_action_destroy(&actions, 0);
+ if (event != RTM_GETACTION)
+ tcf_action_destroy(&actions, 0);
return ret;
}
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 1c60317..520baa41 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -123,12 +123,11 @@
nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name))
return -EMSGSIZE;
- nla = nla_reserve(skb, TCA_ACT_BPF_DIGEST,
- sizeof(prog->filter->digest));
+ nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag));
if (nla == NULL)
return -EMSGSIZE;
- memcpy(nla_data(nla), prog->filter->digest, nla_len(nla));
+ memcpy(nla_data(nla), prog->filter->tag, nla_len(nla));
return 0;
}
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index adc7760..d9c9701 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -555,11 +555,11 @@
nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name))
return -EMSGSIZE;
- nla = nla_reserve(skb, TCA_BPF_DIGEST, sizeof(prog->filter->digest));
+ nla = nla_reserve(skb, TCA_BPF_TAG, sizeof(prog->filter->tag));
if (nla == NULL)
return -EMSGSIZE;
- memcpy(nla_data(nla), prog->filter->digest, nla_len(nla));
+ memcpy(nla_data(nla), prog->filter->tag, nla_len(nla));
return 0;
}
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 970db7a..5752789 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -568,9 +568,9 @@
&mask->icmp.type,
TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,
sizeof(key->icmp.type));
- fl_set_key_val(tb, &key->icmp.code, TCA_FLOWER_KEY_ICMPV4_CODE,
+ fl_set_key_val(tb, &key->icmp.code, TCA_FLOWER_KEY_ICMPV6_CODE,
&mask->icmp.code,
- TCA_FLOWER_KEY_ICMPV4_CODE_MASK,
+ TCA_FLOWER_KEY_ICMPV6_CODE_MASK,
sizeof(key->icmp.code));
}
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index f935429..b12bc2a 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -16,16 +16,11 @@
#include <net/sch_generic.h>
#include <net/pkt_cls.h>
-struct cls_mall_filter {
+struct cls_mall_head {
struct tcf_exts exts;
struct tcf_result res;
u32 handle;
- struct rcu_head rcu;
u32 flags;
-};
-
-struct cls_mall_head {
- struct cls_mall_filter *filter;
struct rcu_head rcu;
};
@@ -33,38 +28,29 @@
struct tcf_result *res)
{
struct cls_mall_head *head = rcu_dereference_bh(tp->root);
- struct cls_mall_filter *f = head->filter;
- if (tc_skip_sw(f->flags))
+ if (tc_skip_sw(head->flags))
return -1;
- return tcf_exts_exec(skb, &f->exts, res);
+ return tcf_exts_exec(skb, &head->exts, res);
}
static int mall_init(struct tcf_proto *tp)
{
- struct cls_mall_head *head;
-
- head = kzalloc(sizeof(*head), GFP_KERNEL);
- if (!head)
- return -ENOBUFS;
-
- rcu_assign_pointer(tp->root, head);
-
return 0;
}
-static void mall_destroy_filter(struct rcu_head *head)
+static void mall_destroy_rcu(struct rcu_head *rcu)
{
- struct cls_mall_filter *f = container_of(head, struct cls_mall_filter, rcu);
+ struct cls_mall_head *head = container_of(rcu, struct cls_mall_head,
+ rcu);
- tcf_exts_destroy(&f->exts);
-
- kfree(f);
+ tcf_exts_destroy(&head->exts);
+ kfree(head);
}
static int mall_replace_hw_filter(struct tcf_proto *tp,
- struct cls_mall_filter *f,
+ struct cls_mall_head *head,
unsigned long cookie)
{
struct net_device *dev = tp->q->dev_queue->dev;
@@ -74,7 +60,7 @@
offload.type = TC_SETUP_MATCHALL;
offload.cls_mall = &mall_offload;
offload.cls_mall->command = TC_CLSMATCHALL_REPLACE;
- offload.cls_mall->exts = &f->exts;
+ offload.cls_mall->exts = &head->exts;
offload.cls_mall->cookie = cookie;
return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol,
@@ -82,7 +68,7 @@
}
static void mall_destroy_hw_filter(struct tcf_proto *tp,
- struct cls_mall_filter *f,
+ struct cls_mall_head *head,
unsigned long cookie)
{
struct net_device *dev = tp->q->dev_queue->dev;
@@ -103,29 +89,20 @@
{
struct cls_mall_head *head = rtnl_dereference(tp->root);
struct net_device *dev = tp->q->dev_queue->dev;
- struct cls_mall_filter *f = head->filter;
- if (!force && f)
- return false;
+ if (!head)
+ return true;
- if (f) {
- if (tc_should_offload(dev, tp, f->flags))
- mall_destroy_hw_filter(tp, f, (unsigned long) f);
+ if (tc_should_offload(dev, tp, head->flags))
+ mall_destroy_hw_filter(tp, head, (unsigned long) head);
- call_rcu(&f->rcu, mall_destroy_filter);
- }
- kfree_rcu(head, rcu);
+ call_rcu(&head->rcu, mall_destroy_rcu);
return true;
}
static unsigned long mall_get(struct tcf_proto *tp, u32 handle)
{
- struct cls_mall_head *head = rtnl_dereference(tp->root);
- struct cls_mall_filter *f = head->filter;
-
- if (f && f->handle == handle)
- return (unsigned long) f;
- return 0;
+ return 0UL;
}
static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
@@ -134,7 +111,7 @@
};
static int mall_set_parms(struct net *net, struct tcf_proto *tp,
- struct cls_mall_filter *f,
+ struct cls_mall_head *head,
unsigned long base, struct nlattr **tb,
struct nlattr *est, bool ovr)
{
@@ -147,11 +124,11 @@
return err;
if (tb[TCA_MATCHALL_CLASSID]) {
- f->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]);
- tcf_bind_filter(tp, &f->res, base);
+ head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]);
+ tcf_bind_filter(tp, &head->res, base);
}
- tcf_exts_change(tp, &f->exts, &e);
+ tcf_exts_change(tp, &head->exts, &e);
return 0;
}
@@ -162,21 +139,17 @@
unsigned long *arg, bool ovr)
{
struct cls_mall_head *head = rtnl_dereference(tp->root);
- struct cls_mall_filter *fold = (struct cls_mall_filter *) *arg;
struct net_device *dev = tp->q->dev_queue->dev;
- struct cls_mall_filter *f;
struct nlattr *tb[TCA_MATCHALL_MAX + 1];
+ struct cls_mall_head *new;
u32 flags = 0;
int err;
if (!tca[TCA_OPTIONS])
return -EINVAL;
- if (head->filter)
- return -EBUSY;
-
- if (fold)
- return -EINVAL;
+ if (head)
+ return -EEXIST;
err = nla_parse_nested(tb, TCA_MATCHALL_MAX,
tca[TCA_OPTIONS], mall_policy);
@@ -189,23 +162,23 @@
return -EINVAL;
}
- f = kzalloc(sizeof(*f), GFP_KERNEL);
- if (!f)
+ new = kzalloc(sizeof(*new), GFP_KERNEL);
+ if (!new)
return -ENOBUFS;
- tcf_exts_init(&f->exts, TCA_MATCHALL_ACT, 0);
+ tcf_exts_init(&new->exts, TCA_MATCHALL_ACT, 0);
if (!handle)
handle = 1;
- f->handle = handle;
- f->flags = flags;
+ new->handle = handle;
+ new->flags = flags;
- err = mall_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr);
+ err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr);
if (err)
goto errout;
if (tc_should_offload(dev, tp, flags)) {
- err = mall_replace_hw_filter(tp, f, (unsigned long) f);
+ err = mall_replace_hw_filter(tp, new, (unsigned long) new);
if (err) {
if (tc_skip_sw(flags))
goto errout;
@@ -214,39 +187,29 @@
}
}
- *arg = (unsigned long) f;
- rcu_assign_pointer(head->filter, f);
-
+ *arg = (unsigned long) head;
+ rcu_assign_pointer(tp->root, new);
+ if (head)
+ call_rcu(&head->rcu, mall_destroy_rcu);
return 0;
errout:
- kfree(f);
+ kfree(new);
return err;
}
static int mall_delete(struct tcf_proto *tp, unsigned long arg)
{
- struct cls_mall_head *head = rtnl_dereference(tp->root);
- struct cls_mall_filter *f = (struct cls_mall_filter *) arg;
- struct net_device *dev = tp->q->dev_queue->dev;
-
- if (tc_should_offload(dev, tp, f->flags))
- mall_destroy_hw_filter(tp, f, (unsigned long) f);
-
- RCU_INIT_POINTER(head->filter, NULL);
- tcf_unbind_filter(tp, &f->res);
- call_rcu(&f->rcu, mall_destroy_filter);
- return 0;
+ return -EOPNOTSUPP;
}
static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
struct cls_mall_head *head = rtnl_dereference(tp->root);
- struct cls_mall_filter *f = head->filter;
if (arg->count < arg->skip)
goto skip;
- if (arg->fn(tp, (unsigned long) f, arg) < 0)
+ if (arg->fn(tp, (unsigned long) head, arg) < 0)
arg->stop = 1;
skip:
arg->count++;
@@ -255,28 +218,28 @@
static int mall_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
struct sk_buff *skb, struct tcmsg *t)
{
- struct cls_mall_filter *f = (struct cls_mall_filter *) fh;
+ struct cls_mall_head *head = (struct cls_mall_head *) fh;
struct nlattr *nest;
- if (!f)
+ if (!head)
return skb->len;
- t->tcm_handle = f->handle;
+ t->tcm_handle = head->handle;
nest = nla_nest_start(skb, TCA_OPTIONS);
if (!nest)
goto nla_put_failure;
- if (f->res.classid &&
- nla_put_u32(skb, TCA_MATCHALL_CLASSID, f->res.classid))
+ if (head->res.classid &&
+ nla_put_u32(skb, TCA_MATCHALL_CLASSID, head->res.classid))
goto nla_put_failure;
- if (tcf_exts_dump(skb, &f->exts))
+ if (tcf_exts_dump(skb, &head->exts))
goto nla_put_failure;
nla_nest_end(skb, nest);
- if (tcf_exts_dump_stats(skb, &f->exts) < 0)
+ if (tcf_exts_dump_stats(skb, &head->exts) < 0)
goto nla_put_failure;
return skb->len;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 5ed8e79..64dfd35 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -222,7 +222,8 @@
SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
rcu_read_lock();
- res = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass);
+ res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
+ np->tclass);
rcu_read_unlock();
return res;
}
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 7e869d0..4f5a2b5 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -68,7 +68,7 @@
goto out;
}
- segs = skb_segment(skb, features | NETIF_F_HW_CSUM);
+ segs = skb_segment(skb, features | NETIF_F_HW_CSUM | NETIF_F_SG);
if (IS_ERR(segs))
goto out;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 318c678..1b5d669 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -235,8 +235,12 @@
sctp_assoc_t id)
{
struct sctp_association *addr_asoc = NULL, *id_asoc = NULL;
- struct sctp_transport *transport;
+ struct sctp_af *af = sctp_get_af_specific(addr->ss_family);
union sctp_addr *laddr = (union sctp_addr *)addr;
+ struct sctp_transport *transport;
+
+ if (!af || sctp_verify_addr(sk, laddr, af->sockaddr_len))
+ return NULL;
addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep,
laddr,
@@ -7422,7 +7426,8 @@
*/
release_sock(sk);
current_timeo = schedule_timeout(current_timeo);
- BUG_ON(sk != asoc->base.sk);
+ if (sk != asoc->base.sk)
+ goto do_error;
lock_sock(sk);
*timeo_p = current_timeo;
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index dc6fb79..25d9a9c 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -260,7 +260,7 @@
if (!oa->data)
return -ENOMEM;
- creds = kmalloc(sizeof(struct svc_cred), GFP_KERNEL);
+ creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL);
if (!creds) {
kfree(oa->data);
return -ENOMEM;
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 886e9d38..1530825 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1489,7 +1489,7 @@
case RPC_GSS_PROC_DESTROY:
if (gss_write_verf(rqstp, rsci->mechctx, gc->gc_seq))
goto auth_err;
- rsci->h.expiry_time = get_seconds();
+ rsci->h.expiry_time = seconds_since_boot();
set_bit(CACHE_NEGATIVE, &rsci->h.flags);
if (resv->iov_len + 4 > PAGE_SIZE)
goto drop;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 1efbe48..1dc9f3b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -336,6 +336,11 @@
static DEFINE_IDA(rpc_clids);
+void rpc_cleanup_clids(void)
+{
+ ida_destroy(&rpc_clids);
+}
+
static int rpc_alloc_clid(struct rpc_clnt *clnt)
{
int clid;
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index d1c330a..c73de18 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -119,6 +119,7 @@
static void __exit
cleanup_sunrpc(void)
{
+ rpc_cleanup_clids();
rpcauth_remove_module();
cleanup_socket_xprt();
svc_cleanup_xprt_sock();
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 04e7f87..7bfe1fb 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -799,6 +799,8 @@
if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
dprintk("svc_recv: found XPT_CLOSE\n");
+ if (test_and_clear_bit(XPT_KILL_TEMP, &xprt->xpt_flags))
+ xprt->xpt_ops->xpo_kill_temp_xprt(xprt);
svc_delete_xprt(xprt);
/* Leave XPT_BUSY set on the dead xprt: */
goto out;
@@ -1020,9 +1022,11 @@
le = to_be_closed.next;
list_del_init(le);
xprt = list_entry(le, struct svc_xprt, xpt_list);
- dprintk("svc_age_temp_xprts_now: closing %p\n", xprt);
- xprt->xpt_ops->xpo_kill_temp_xprt(xprt);
- svc_close_xprt(xprt);
+ set_bit(XPT_CLOSE, &xprt->xpt_flags);
+ set_bit(XPT_KILL_TEMP, &xprt->xpt_flags);
+ dprintk("svc_age_temp_xprts_now: queuing xprt %p for closing\n",
+ xprt);
+ svc_xprt_enqueue(xprt);
}
}
EXPORT_SYMBOL_GPL(svc_age_temp_xprts_now);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 57d35fb..172b537 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -347,8 +347,6 @@
atomic_inc(&rdma_stat_read);
return ret;
err:
- ib_dma_unmap_sg(xprt->sc_cm_id->device,
- frmr->sg, frmr->sg_nents, frmr->direction);
svc_rdma_put_context(ctxt, 0);
svc_rdma_put_frmr(xprt, frmr);
return ret;
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 6b109a8..02462d6 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -169,7 +169,7 @@
/* Send response, if necessary */
if (respond && (mtyp == DSC_REQ_MSG)) {
- rskb = tipc_buf_acquire(MAX_H_SIZE);
+ rskb = tipc_buf_acquire(MAX_H_SIZE, GFP_ATOMIC);
if (!rskb)
return;
tipc_disc_init_msg(net, rskb, DSC_RESP_MSG, bearer);
@@ -278,7 +278,7 @@
req = kmalloc(sizeof(*req), GFP_ATOMIC);
if (!req)
return -ENOMEM;
- req->buf = tipc_buf_acquire(MAX_H_SIZE);
+ req->buf = tipc_buf_acquire(MAX_H_SIZE, GFP_ATOMIC);
if (!req->buf) {
kfree(req);
return -ENOMEM;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index bda89bf..4e8647a 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1395,7 +1395,7 @@
msg_set_seqno(hdr, seqno++);
pktlen = msg_size(hdr);
msg_set_size(&tnlhdr, pktlen + INT_H_SIZE);
- tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE);
+ tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC);
if (!tnlskb) {
pr_warn("%sunable to send packet\n", link_co_err);
return;
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index a22be50..ab02d07 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -58,12 +58,12 @@
* NOTE: Headroom is reserved to allow prepending of a data link header.
* There may also be unrequested tailroom present at the buffer's end.
*/
-struct sk_buff *tipc_buf_acquire(u32 size)
+struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp)
{
struct sk_buff *skb;
unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u;
- skb = alloc_skb_fclone(buf_size, GFP_ATOMIC);
+ skb = alloc_skb_fclone(buf_size, gfp);
if (skb) {
skb_reserve(skb, BUF_HEADROOM);
skb_put(skb, size);
@@ -95,7 +95,7 @@
struct tipc_msg *msg;
struct sk_buff *buf;
- buf = tipc_buf_acquire(hdr_sz + data_sz);
+ buf = tipc_buf_acquire(hdr_sz + data_sz, GFP_ATOMIC);
if (unlikely(!buf))
return NULL;
@@ -261,7 +261,7 @@
/* No fragmentation needed? */
if (likely(msz <= pktmax)) {
- skb = tipc_buf_acquire(msz);
+ skb = tipc_buf_acquire(msz, GFP_KERNEL);
if (unlikely(!skb))
return -ENOMEM;
skb_orphan(skb);
@@ -282,7 +282,7 @@
msg_set_importance(&pkthdr, msg_importance(mhdr));
/* Prepare first fragment */
- skb = tipc_buf_acquire(pktmax);
+ skb = tipc_buf_acquire(pktmax, GFP_KERNEL);
if (!skb)
return -ENOMEM;
skb_orphan(skb);
@@ -313,7 +313,7 @@
pktsz = drem + INT_H_SIZE;
else
pktsz = pktmax;
- skb = tipc_buf_acquire(pktsz);
+ skb = tipc_buf_acquire(pktsz, GFP_KERNEL);
if (!skb) {
rc = -ENOMEM;
goto error;
@@ -448,7 +448,7 @@
if (msz > (max / 2))
return false;
- _skb = tipc_buf_acquire(max);
+ _skb = tipc_buf_acquire(max, GFP_ATOMIC);
if (!_skb)
return false;
@@ -496,7 +496,7 @@
/* Never return SHORT header; expand by replacing buffer if necessary */
if (msg_short(hdr)) {
- *skb = tipc_buf_acquire(BASIC_H_SIZE + dlen);
+ *skb = tipc_buf_acquire(BASIC_H_SIZE + dlen, GFP_ATOMIC);
if (!*skb)
goto exit;
memcpy((*skb)->data + BASIC_H_SIZE, msg_data(hdr), dlen);
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 8d40861..2c3dc38 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -820,7 +820,7 @@
return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG);
}
-struct sk_buff *tipc_buf_acquire(u32 size);
+struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp);
bool tipc_msg_validate(struct sk_buff *skb);
bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err);
void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type,
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index c1cfd92..23f8899 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -69,7 +69,7 @@
u32 dest)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
- struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size);
+ struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size, GFP_ATOMIC);
struct tipc_msg *msg;
if (buf != NULL) {
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 9d2f4c2..2775332 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -263,6 +263,11 @@
write_lock_bh(&n->lock);
}
+static void tipc_node_write_unlock_fast(struct tipc_node *n)
+{
+ write_unlock_bh(&n->lock);
+}
+
static void tipc_node_write_unlock(struct tipc_node *n)
{
struct net *net = n->net;
@@ -417,7 +422,7 @@
}
tipc_node_write_lock(n);
list_add_tail(subscr, &n->publ_list);
- tipc_node_write_unlock(n);
+ tipc_node_write_unlock_fast(n);
tipc_node_put(n);
}
@@ -435,7 +440,7 @@
}
tipc_node_write_lock(n);
list_del_init(subscr);
- tipc_node_write_unlock(n);
+ tipc_node_write_unlock_fast(n);
tipc_node_put(n);
}
diff --git a/net/tipc/server.c b/net/tipc/server.c
index 215849c..3cd6402 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -86,12 +86,12 @@
static void tipc_recv_work(struct work_struct *work);
static void tipc_send_work(struct work_struct *work);
static void tipc_clean_outqueues(struct tipc_conn *con);
-static void tipc_sock_release(struct tipc_conn *con);
static void tipc_conn_kref_release(struct kref *kref)
{
struct tipc_conn *con = container_of(kref, struct tipc_conn, kref);
- struct sockaddr_tipc *saddr = con->server->saddr;
+ struct tipc_server *s = con->server;
+ struct sockaddr_tipc *saddr = s->saddr;
struct socket *sock = con->sock;
struct sock *sk;
@@ -103,9 +103,13 @@
}
saddr->scope = -TIPC_NODE_SCOPE;
kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr));
- tipc_sock_release(con);
sock_release(sock);
con->sock = NULL;
+
+ spin_lock_bh(&s->idr_lock);
+ idr_remove(&s->conn_idr, con->conid);
+ s->idr_in_use--;
+ spin_unlock_bh(&s->idr_lock);
}
tipc_clean_outqueues(con);
@@ -128,8 +132,10 @@
spin_lock_bh(&s->idr_lock);
con = idr_find(&s->conn_idr, conid);
- if (con)
+ if (con && test_bit(CF_CONNECTED, &con->flags))
conn_get(con);
+ else
+ con = NULL;
spin_unlock_bh(&s->idr_lock);
return con;
}
@@ -186,26 +192,15 @@
write_unlock_bh(&sk->sk_callback_lock);
}
-static void tipc_sock_release(struct tipc_conn *con)
-{
- struct tipc_server *s = con->server;
-
- if (con->conid)
- s->tipc_conn_release(con->conid, con->usr_data);
-
- tipc_unregister_callbacks(con);
-}
-
static void tipc_close_conn(struct tipc_conn *con)
{
struct tipc_server *s = con->server;
if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
+ tipc_unregister_callbacks(con);
- spin_lock_bh(&s->idr_lock);
- idr_remove(&s->conn_idr, con->conid);
- s->idr_in_use--;
- spin_unlock_bh(&s->idr_lock);
+ if (con->conid)
+ s->tipc_conn_release(con->conid, con->usr_data);
/* We shouldn't flush pending works as we may be in the
* thread. In fact the races with pending rx/tx work structs
@@ -458,6 +453,11 @@
if (!con)
return -EINVAL;
+ if (!test_bit(CF_CONNECTED, &con->flags)) {
+ conn_put(con);
+ return 0;
+ }
+
e = tipc_alloc_entry(data, len);
if (!e) {
conn_put(con);
@@ -471,12 +471,8 @@
list_add_tail(&e->list, &con->outqueue);
spin_unlock_bh(&con->outqueue_lock);
- if (test_bit(CF_CONNECTED, &con->flags)) {
- if (!queue_work(s->send_wq, &con->swork))
- conn_put(con);
- } else {
+ if (!queue_work(s->send_wq, &con->swork))
conn_put(con);
- }
return 0;
}
@@ -500,7 +496,7 @@
int ret;
spin_lock_bh(&con->outqueue_lock);
- while (1) {
+ while (test_bit(CF_CONNECTED, &con->flags)) {
e = list_entry(con->outqueue.next, struct outqueue_entry,
list);
if ((struct list_head *) e == &con->outqueue)
@@ -623,14 +619,12 @@
void tipc_server_stop(struct tipc_server *s)
{
struct tipc_conn *con;
- int total = 0;
int id;
spin_lock_bh(&s->idr_lock);
- for (id = 0; total < s->idr_in_use; id++) {
+ for (id = 0; s->idr_in_use; id++) {
con = idr_find(&s->conn_idr, id);
if (con) {
- total++;
spin_unlock_bh(&s->idr_lock);
tipc_close_conn(con);
spin_lock_bh(&s->idr_lock);
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 0dd0224..9d94e65 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -54,6 +54,8 @@
static void tipc_subscrp_delete(struct tipc_subscription *sub);
static void tipc_subscrb_put(struct tipc_subscriber *subscriber);
+static void tipc_subscrp_put(struct tipc_subscription *subscription);
+static void tipc_subscrp_get(struct tipc_subscription *subscription);
/**
* htohl - convert value to endianness used by destination
@@ -123,6 +125,7 @@
{
struct tipc_name_seq seq;
+ tipc_subscrp_get(sub);
tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq);
if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper))
return;
@@ -132,30 +135,23 @@
tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref,
node);
+ tipc_subscrp_put(sub);
}
static void tipc_subscrp_timeout(unsigned long data)
{
struct tipc_subscription *sub = (struct tipc_subscription *)data;
- struct tipc_subscriber *subscriber = sub->subscriber;
/* Notify subscriber of timeout */
tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper,
TIPC_SUBSCR_TIMEOUT, 0, 0);
- spin_lock_bh(&subscriber->lock);
- tipc_subscrp_delete(sub);
- spin_unlock_bh(&subscriber->lock);
-
- tipc_subscrb_put(subscriber);
+ tipc_subscrp_put(sub);
}
static void tipc_subscrb_kref_release(struct kref *kref)
{
- struct tipc_subscriber *subcriber = container_of(kref,
- struct tipc_subscriber, kref);
-
- kfree(subcriber);
+ kfree(container_of(kref,struct tipc_subscriber, kref));
}
static void tipc_subscrb_put(struct tipc_subscriber *subscriber)
@@ -168,6 +164,59 @@
kref_get(&subscriber->kref);
}
+static void tipc_subscrp_kref_release(struct kref *kref)
+{
+ struct tipc_subscription *sub = container_of(kref,
+ struct tipc_subscription,
+ kref);
+ struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
+ struct tipc_subscriber *subscriber = sub->subscriber;
+
+ spin_lock_bh(&subscriber->lock);
+ tipc_nametbl_unsubscribe(sub);
+ list_del(&sub->subscrp_list);
+ atomic_dec(&tn->subscription_count);
+ spin_unlock_bh(&subscriber->lock);
+ kfree(sub);
+ tipc_subscrb_put(subscriber);
+}
+
+static void tipc_subscrp_put(struct tipc_subscription *subscription)
+{
+ kref_put(&subscription->kref, tipc_subscrp_kref_release);
+}
+
+static void tipc_subscrp_get(struct tipc_subscription *subscription)
+{
+ kref_get(&subscription->kref);
+}
+
+/* tipc_subscrb_subscrp_delete - delete a specific subscription or all
+ * subscriptions for a given subscriber.
+ */
+static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber,
+ struct tipc_subscr *s)
+{
+ struct list_head *subscription_list = &subscriber->subscrp_list;
+ struct tipc_subscription *sub, *temp;
+
+ spin_lock_bh(&subscriber->lock);
+ list_for_each_entry_safe(sub, temp, subscription_list, subscrp_list) {
+ if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr)))
+ continue;
+
+ tipc_subscrp_get(sub);
+ spin_unlock_bh(&subscriber->lock);
+ tipc_subscrp_delete(sub);
+ tipc_subscrp_put(sub);
+ spin_lock_bh(&subscriber->lock);
+
+ if (s)
+ break;
+ }
+ spin_unlock_bh(&subscriber->lock);
+}
+
static struct tipc_subscriber *tipc_subscrb_create(int conid)
{
struct tipc_subscriber *subscriber;
@@ -177,8 +226,8 @@
pr_warn("Subscriber rejected, no memory\n");
return NULL;
}
- kref_init(&subscriber->kref);
INIT_LIST_HEAD(&subscriber->subscrp_list);
+ kref_init(&subscriber->kref);
subscriber->conid = conid;
spin_lock_init(&subscriber->lock);
@@ -187,55 +236,22 @@
static void tipc_subscrb_delete(struct tipc_subscriber *subscriber)
{
- struct tipc_subscription *sub, *temp;
- u32 timeout;
-
- spin_lock_bh(&subscriber->lock);
- /* Destroy any existing subscriptions for subscriber */
- list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list,
- subscrp_list) {
- timeout = htohl(sub->evt.s.timeout, sub->swap);
- if ((timeout == TIPC_WAIT_FOREVER) || del_timer(&sub->timer)) {
- tipc_subscrp_delete(sub);
- tipc_subscrb_put(subscriber);
- }
- }
- spin_unlock_bh(&subscriber->lock);
-
+ tipc_subscrb_subscrp_delete(subscriber, NULL);
tipc_subscrb_put(subscriber);
}
static void tipc_subscrp_delete(struct tipc_subscription *sub)
{
- struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
+ u32 timeout = htohl(sub->evt.s.timeout, sub->swap);
- tipc_nametbl_unsubscribe(sub);
- list_del(&sub->subscrp_list);
- kfree(sub);
- atomic_dec(&tn->subscription_count);
+ if (timeout == TIPC_WAIT_FOREVER || del_timer(&sub->timer))
+ tipc_subscrp_put(sub);
}
static void tipc_subscrp_cancel(struct tipc_subscr *s,
struct tipc_subscriber *subscriber)
{
- struct tipc_subscription *sub, *temp;
- u32 timeout;
-
- spin_lock_bh(&subscriber->lock);
- /* Find first matching subscription, exit if not found */
- list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list,
- subscrp_list) {
- if (!memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) {
- timeout = htohl(sub->evt.s.timeout, sub->swap);
- if ((timeout == TIPC_WAIT_FOREVER) ||
- del_timer(&sub->timer)) {
- tipc_subscrp_delete(sub);
- tipc_subscrb_put(subscriber);
- }
- break;
- }
- }
- spin_unlock_bh(&subscriber->lock);
+ tipc_subscrb_subscrp_delete(subscriber, s);
}
static struct tipc_subscription *tipc_subscrp_create(struct net *net,
@@ -272,6 +288,7 @@
sub->swap = swap;
memcpy(&sub->evt.s, s, sizeof(*s));
atomic_inc(&tn->subscription_count);
+ kref_init(&sub->kref);
return sub;
}
@@ -288,17 +305,16 @@
spin_lock_bh(&subscriber->lock);
list_add(&sub->subscrp_list, &subscriber->subscrp_list);
- tipc_subscrb_get(subscriber);
sub->subscriber = subscriber;
tipc_nametbl_subscribe(sub);
+ tipc_subscrb_get(subscriber);
spin_unlock_bh(&subscriber->lock);
- timeout = htohl(sub->evt.s.timeout, swap);
- if (timeout == TIPC_WAIT_FOREVER)
- return;
-
setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub);
- mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout));
+ timeout = htohl(sub->evt.s.timeout, swap);
+
+ if (timeout != TIPC_WAIT_FOREVER)
+ mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout));
}
/* Handle one termination request for the subscriber */
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index be60103..ffdc214 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -57,6 +57,7 @@
* @evt: template for events generated by subscription
*/
struct tipc_subscription {
+ struct kref kref;
struct tipc_subscriber *subscriber;
struct net *net;
struct timer_list timer;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 127656e..cef7987 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -995,6 +995,7 @@
unsigned int hash;
struct unix_address *addr;
struct hlist_head *list;
+ struct path path = { NULL, NULL };
err = -EINVAL;
if (sunaddr->sun_family != AF_UNIX)
@@ -1010,9 +1011,20 @@
goto out;
addr_len = err;
+ if (sun_path[0]) {
+ umode_t mode = S_IFSOCK |
+ (SOCK_INODE(sock)->i_mode & ~current_umask());
+ err = unix_mknod(sun_path, mode, &path);
+ if (err) {
+ if (err == -EEXIST)
+ err = -EADDRINUSE;
+ goto out;
+ }
+ }
+
err = mutex_lock_interruptible(&u->bindlock);
if (err)
- goto out;
+ goto out_put;
err = -EINVAL;
if (u->addr)
@@ -1029,16 +1041,6 @@
atomic_set(&addr->refcnt, 1);
if (sun_path[0]) {
- struct path path;
- umode_t mode = S_IFSOCK |
- (SOCK_INODE(sock)->i_mode & ~current_umask());
- err = unix_mknod(sun_path, mode, &path);
- if (err) {
- if (err == -EEXIST)
- err = -EADDRINUSE;
- unix_release_addr(addr);
- goto out_up;
- }
addr->hash = UNIX_HASH_SIZE;
hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
spin_lock(&unix_table_lock);
@@ -1065,6 +1067,9 @@
spin_unlock(&unix_table_lock);
out_up:
mutex_unlock(&u->bindlock);
+out_put:
+ if (err)
+ path_put(&path);
out:
return err;
}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ef5eff93..aee396b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4615,6 +4615,15 @@
break;
}
+ /*
+ * Older kernel versions ignored this attribute entirely, so don't
+ * reject attempts to update it but mark it as unused instead so the
+ * driver won't look at the data.
+ */
+ if (statype != CFG80211_STA_AP_CLIENT_UNASSOC &&
+ statype != CFG80211_STA_TDLS_PEER_SETUP)
+ params->opmode_notif_used = false;
+
return 0;
}
EXPORT_SYMBOL(cfg80211_check_station_change);
@@ -4854,6 +4863,12 @@
params.local_pm = pm;
}
+ if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) {
+ params.opmode_notif_used = true;
+ params.opmode_notif =
+ nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]);
+ }
+
/* Include parameters for TDLS peer (will check later) */
err = nl80211_set_station_tdls(info, ¶ms);
if (err)
@@ -5901,6 +5916,7 @@
break;
}
cfg->ht_opmode = ht_opmode;
+ mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1));
}
FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout,
1, 65535, mask,
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 396e204..b86ee54 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -277,6 +277,11 @@
Elf_Data *data, *data_prog, *symbols = NULL;
char *shname, *shname_prog;
+ /* reset global variables */
+ kern_version = 0;
+ memset(license, 0, sizeof(license));
+ memset(processed_sec, 0, sizeof(processed_sec));
+
if (elf_version(EV_CURRENT) == EV_NONE)
return 1;
@@ -328,6 +333,8 @@
/* load programs that need map fixup (relocations) */
for (i = 1; i < ehdr.e_shnum; i++) {
+ if (processed_sec[i])
+ continue;
if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
continue;
diff --git a/samples/bpf/sock_example.h b/samples/bpf/sock_example.h
index 09f7fe7..d801406 100644
--- a/samples/bpf/sock_example.h
+++ b/samples/bpf/sock_example.h
@@ -4,7 +4,7 @@
#include <unistd.h>
#include <string.h>
#include <errno.h>
-#include <net/ethernet.h>
+#include <linux/if_ether.h>
#include <net/if.h>
#include <linux/if_packet.h>
#include <arpa/inet.h>
diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c
index 92a4472..7ef2a12 100644
--- a/samples/bpf/tc_l2_redirect_kern.c
+++ b/samples/bpf/tc_l2_redirect_kern.c
@@ -4,6 +4,7 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
+#define KBUILD_MODNAME "foo"
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c
index 5040586..4bfcaf9 100644
--- a/samples/bpf/test_cgrp2_attach.c
+++ b/samples/bpf/test_cgrp2_attach.c
@@ -104,7 +104,7 @@
return EXIT_FAILURE;
}
- ret = bpf_prog_attach(prog_fd, cg_fd, type);
+ ret = bpf_prog_attach(prog_fd, cg_fd, type, 0);
if (ret < 0) {
printf("Failed to attach prog to cgroup: '%s'\n",
strerror(errno));
diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c
index 6e69be3..3049b1f2 100644
--- a/samples/bpf/test_cgrp2_attach2.c
+++ b/samples/bpf/test_cgrp2_attach2.c
@@ -79,11 +79,12 @@
if (join_cgroup(FOO))
goto err;
- if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS)) {
+ if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 1)) {
log_err("Attaching prog to /foo");
goto err;
}
+ printf("Attached DROP prog. This ping in cgroup /foo should fail...\n");
assert(system(PING_CMD) != 0);
/* Create cgroup /foo/bar, get fd, and join it */
@@ -94,24 +95,27 @@
if (join_cgroup(BAR))
goto err;
+ printf("Attached DROP prog. This ping in cgroup /foo/bar should fail...\n");
assert(system(PING_CMD) != 0);
- if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS)) {
+ if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
log_err("Attaching prog to /foo/bar");
goto err;
}
+ printf("Attached PASS prog. This ping in cgroup /foo/bar should pass...\n");
assert(system(PING_CMD) == 0);
-
if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
log_err("Detaching program from /foo/bar");
goto err;
}
+ printf("Detached PASS from /foo/bar while DROP is attached to /foo.\n"
+ "This ping in cgroup /foo/bar should fail...\n");
assert(system(PING_CMD) != 0);
- if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS)) {
+ if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
log_err("Attaching prog to /foo/bar");
goto err;
}
@@ -121,8 +125,60 @@
goto err;
}
+ printf("Attached PASS from /foo/bar and detached DROP from /foo.\n"
+ "This ping in cgroup /foo/bar should pass...\n");
assert(system(PING_CMD) == 0);
+ if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
+ log_err("Attaching prog to /foo/bar");
+ goto err;
+ }
+
+ if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
+ errno = 0;
+ log_err("Unexpected success attaching prog to /foo/bar");
+ goto err;
+ }
+
+ if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
+ log_err("Detaching program from /foo/bar");
+ goto err;
+ }
+
+ if (!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) {
+ errno = 0;
+ log_err("Unexpected success in double detach from /foo");
+ goto err;
+ }
+
+ if (bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
+ log_err("Attaching non-overridable prog to /foo");
+ goto err;
+ }
+
+ if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
+ errno = 0;
+ log_err("Unexpected success attaching non-overridable prog to /foo/bar");
+ goto err;
+ }
+
+ if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
+ errno = 0;
+ log_err("Unexpected success attaching overridable prog to /foo/bar");
+ goto err;
+ }
+
+ if (!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 1)) {
+ errno = 0;
+ log_err("Unexpected success attaching overridable prog to /foo");
+ goto err;
+ }
+
+ if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
+ log_err("Attaching different non-overridable prog to /foo");
+ goto err;
+ }
+
goto out;
err:
@@ -132,5 +188,9 @@
close(foo);
close(bar);
cleanup_cgroup_environment();
+ if (!rc)
+ printf("PASS\n");
+ else
+ printf("FAIL\n");
return rc;
}
diff --git a/samples/bpf/test_cgrp2_sock.c b/samples/bpf/test_cgrp2_sock.c
index 0791b94..c3cfb23e 100644
--- a/samples/bpf/test_cgrp2_sock.c
+++ b/samples/bpf/test_cgrp2_sock.c
@@ -75,7 +75,7 @@
return EXIT_FAILURE;
}
- ret = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE);
+ ret = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE, 0);
if (ret < 0) {
printf("Failed to attach prog to cgroup: '%s'\n",
strerror(errno));
diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c
index 455ef0d..db03607 100644
--- a/samples/bpf/test_cgrp2_sock2.c
+++ b/samples/bpf/test_cgrp2_sock2.c
@@ -55,7 +55,7 @@
}
ret = bpf_prog_attach(prog_fd[filter_id], cg_fd,
- BPF_CGROUP_INET_SOCK_CREATE);
+ BPF_CGROUP_INET_SOCK_CREATE, 0);
if (ret < 0) {
printf("Failed to attach prog to cgroup: '%s'\n",
strerror(errno));
diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c
index f4fa6af..ccca1e3 100644
--- a/samples/bpf/trace_output_user.c
+++ b/samples/bpf/trace_output_user.c
@@ -9,7 +9,6 @@
#include <string.h>
#include <fcntl.h>
#include <poll.h>
-#include <sys/ioctl.h>
#include <linux/perf_event.h>
#include <linux/bpf.h>
#include <errno.h>
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c
index fd12d71..7e4cf74 100644
--- a/samples/bpf/tracex5_kern.c
+++ b/samples/bpf/tracex5_kern.c
@@ -8,6 +8,7 @@
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/seccomp.h>
+#include <uapi/linux/unistd.h>
#include "bpf_helpers.h"
#define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F
diff --git a/samples/bpf/xdp_tx_iptunnel_kern.c b/samples/bpf/xdp_tx_iptunnel_kern.c
index 85c38ec..0f4f6e8 100644
--- a/samples/bpf/xdp_tx_iptunnel_kern.c
+++ b/samples/bpf/xdp_tx_iptunnel_kern.c
@@ -8,6 +8,7 @@
* encapsulating the incoming packet in an IPv4/v6 header
* and then XDP_TX it out.
*/
+#define KBUILD_MODNAME "foo"
#include <uapi/linux/bpf.h>
#include <linux/in.h>
#include <linux/if_ether.h>
diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c
index 1fc57a5..ca49568 100644
--- a/samples/vfio-mdev/mtty.c
+++ b/samples/vfio-mdev/mtty.c
@@ -1073,7 +1073,7 @@
{
unsigned int size = 0;
struct mdev_state *mdev_state;
- int bar_index;
+ u32 bar_index;
if (!mdev)
return -EINVAL;
@@ -1082,8 +1082,11 @@
if (!mdev_state)
return -EINVAL;
- mutex_lock(&mdev_state->ops_lock);
bar_index = region_info->index;
+ if (bar_index >= VFIO_PCI_NUM_REGIONS)
+ return -EINVAL;
+
+ mutex_lock(&mdev_state->ops_lock);
switch (bar_index) {
case VFIO_PCI_CONFIG_REGION_INDEX:
@@ -1180,7 +1183,10 @@
memcpy(&mdev_state->dev_info, &info, sizeof(info));
- return copy_to_user((void __user *)arg, &info, minsz);
+ if (copy_to_user((void __user *)arg, &info, minsz))
+ return -EFAULT;
+
+ return 0;
}
case VFIO_DEVICE_GET_REGION_INFO:
{
@@ -1201,7 +1207,10 @@
if (ret)
return ret;
- return copy_to_user((void __user *)arg, &info, minsz);
+ if (copy_to_user((void __user *)arg, &info, minsz))
+ return -EFAULT;
+
+ return 0;
}
case VFIO_DEVICE_GET_IRQ_INFO:
@@ -1221,10 +1230,10 @@
if (ret)
return ret;
- if (info.count == -1)
- return -EINVAL;
+ if (copy_to_user((void __user *)arg, &info, minsz))
+ return -EFAULT;
- return copy_to_user((void __user *)arg, &info, minsz);
+ return 0;
}
case VFIO_DEVICE_SET_IRQS:
{
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index eadcd4d..d883116 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -164,6 +164,7 @@
$(CPP) -D__GENKSYMS__ $(c_flags) $< | \
$(GENKSYMS) $(if $(1), -T $(2)) \
$(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \
+ $(patsubst y,-R,$(CONFIG_MODULE_REL_CRCS)) \
$(if $(KBUILD_PRESERVE),-p) \
-r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null))
@@ -337,6 +338,7 @@
$(CPP) -D__GENKSYMS__ $(c_flags) -xc - | \
$(GENKSYMS) $(if $(1), -T $(2)) \
$(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \
+ $(patsubst y,-R,$(CONFIG_MODULE_REL_CRCS)) \
$(if $(KBUILD_PRESERVE),-p) \
-r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null))
diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index 06121ce..c9235d8 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -44,7 +44,7 @@
int in_source_file;
static int flag_debug, flag_dump_defs, flag_reference, flag_dump_types,
- flag_preserve, flag_warnings;
+ flag_preserve, flag_warnings, flag_rel_crcs;
static const char *mod_prefix = "";
static int errors;
@@ -693,7 +693,10 @@
fputs(">\n", debugfile);
/* Used as a linker script. */
- printf("%s__crc_%s = 0x%08lx ;\n", mod_prefix, name, crc);
+ printf(!flag_rel_crcs ? "%s__crc_%s = 0x%08lx;\n" :
+ "SECTIONS { .rodata : ALIGN(4) { "
+ "%s__crc_%s = .; LONG(0x%08lx); } }\n",
+ mod_prefix, name, crc);
}
}
@@ -730,7 +733,7 @@
static void genksyms_usage(void)
{
- fputs("Usage:\n" "genksyms [-adDTwqhV] > /path/to/.tmp_obj.ver\n" "\n"
+ fputs("Usage:\n" "genksyms [-adDTwqhVR] > /path/to/.tmp_obj.ver\n" "\n"
#ifdef __GNU_LIBRARY__
" -s, --symbol-prefix Select symbol prefix\n"
" -d, --debug Increment the debug level (repeatable)\n"
@@ -742,6 +745,7 @@
" -q, --quiet Disable warnings (default)\n"
" -h, --help Print this message\n"
" -V, --version Print the release version\n"
+ " -R, --relative-crc Emit section relative symbol CRCs\n"
#else /* __GNU_LIBRARY__ */
" -s Select symbol prefix\n"
" -d Increment the debug level (repeatable)\n"
@@ -753,6 +757,7 @@
" -q Disable warnings (default)\n"
" -h Print this message\n"
" -V Print the release version\n"
+ " -R Emit section relative symbol CRCs\n"
#endif /* __GNU_LIBRARY__ */
, stderr);
}
@@ -774,13 +779,14 @@
{"preserve", 0, 0, 'p'},
{"version", 0, 0, 'V'},
{"help", 0, 0, 'h'},
+ {"relative-crc", 0, 0, 'R'},
{0, 0, 0, 0}
};
- while ((o = getopt_long(argc, argv, "s:dwqVDr:T:ph",
+ while ((o = getopt_long(argc, argv, "s:dwqVDr:T:phR",
&long_opts[0], NULL)) != EOF)
#else /* __GNU_LIBRARY__ */
- while ((o = getopt(argc, argv, "s:dwqVDr:T:ph")) != EOF)
+ while ((o = getopt(argc, argv, "s:dwqVDr:T:phR")) != EOF)
#endif /* __GNU_LIBRARY__ */
switch (o) {
case 's':
@@ -823,6 +829,9 @@
case 'h':
genksyms_usage();
return 0;
+ case 'R':
+ flag_rel_crcs = 1;
+ break;
default:
genksyms_usage();
return 1;
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 299b92c..5d55441 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -219,6 +219,10 @@
"_SDA2_BASE_", /* ppc */
NULL };
+ static char *special_prefixes[] = {
+ "__crc_", /* modversions */
+ NULL };
+
static char *special_suffixes[] = {
"_veneer", /* arm */
"_from_arm", /* arm */
@@ -259,6 +263,14 @@
if (strcmp(sym_name, special_symbols[i]) == 0)
return 0;
+ for (i = 0; special_prefixes[i]; i++) {
+ int l = strlen(special_prefixes[i]);
+
+ if (l <= strlen(sym_name) &&
+ strncmp(sym_name, special_prefixes[i], l) == 0)
+ return 0;
+ }
+
for (i = 0; special_suffixes[i]; i++) {
int l = strlen(sym_name) - strlen(special_suffixes[i]);
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 29c89a6..4dedd0d 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -621,6 +621,16 @@
if (strncmp(symname, CRC_PFX, strlen(CRC_PFX)) == 0) {
is_crc = true;
crc = (unsigned int) sym->st_value;
+ if (sym->st_shndx != SHN_UNDEF && sym->st_shndx != SHN_ABS) {
+ unsigned int *crcp;
+
+ /* symbol points to the CRC in the ELF object */
+ crcp = (void *)info->hdr + sym->st_value +
+ info->sechdrs[sym->st_shndx].sh_offset -
+ (info->hdr->e_type != ET_REL ?
+ info->sechdrs[sym->st_shndx].sh_addr : 0);
+ crc = *crcp;
+ }
sym_update_crc(symname + strlen(CRC_PFX), mod, crc,
export);
}
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index c7c6619..d98550a 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5887,7 +5887,7 @@
return error;
/* Obtain a SID for the context, if one was specified. */
- if (size && str[1] && str[1] != '\n') {
+ if (size && str[0] && str[0] != '\n') {
if (str[size-1] == '\n') {
str[size-1] = 0;
size--;
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index c850345..dfa5156 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -419,7 +419,6 @@
{
unsigned long flags;
struct snd_seq_event_cell *ptr;
- int max_count = 5 * HZ;
if (snd_BUG_ON(!pool))
return -EINVAL;
@@ -432,14 +431,8 @@
if (waitqueue_active(&pool->output_sleep))
wake_up(&pool->output_sleep);
- while (atomic_read(&pool->counter) > 0) {
- if (max_count == 0) {
- pr_warn("ALSA: snd_seq_pool_done timeout: %d cells remain\n", atomic_read(&pool->counter));
- break;
- }
+ while (atomic_read(&pool->counter) > 0)
schedule_timeout_uninterruptible(1);
- max_count--;
- }
/* release all resources */
spin_lock_irqsave(&pool->lock, flags);
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index 0bec02e..450c518 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -181,6 +181,8 @@
}
}
+static void queue_use(struct snd_seq_queue *queue, int client, int use);
+
/* allocate a new queue -
* return queue index value or negative value for error
*/
@@ -192,11 +194,11 @@
if (q == NULL)
return -ENOMEM;
q->info_flags = info_flags;
+ queue_use(q, client, 1);
if (queue_list_add(q) < 0) {
queue_delete(q);
return -ENOMEM;
}
- snd_seq_queue_use(q->queue, client, 1); /* use this queue */
return q->queue;
}
@@ -502,19 +504,9 @@
return result;
}
-
-/* use or unuse this queue -
- * if it is the first client, starts the timer.
- * if it is not longer used by any clients, stop the timer.
- */
-int snd_seq_queue_use(int queueid, int client, int use)
+/* use or unuse this queue */
+static void queue_use(struct snd_seq_queue *queue, int client, int use)
{
- struct snd_seq_queue *queue;
-
- queue = queueptr(queueid);
- if (queue == NULL)
- return -EINVAL;
- mutex_lock(&queue->timer_mutex);
if (use) {
if (!test_and_set_bit(client, queue->clients_bitmap))
queue->clients++;
@@ -529,6 +521,21 @@
} else {
snd_seq_timer_close(queue);
}
+}
+
+/* use or unuse this queue -
+ * if it is the first client, starts the timer.
+ * if it is not longer used by any clients, stop the timer.
+ */
+int snd_seq_queue_use(int queueid, int client, int use)
+{
+ struct snd_seq_queue *queue;
+
+ queue = queueptr(queueid);
+ if (queue == NULL)
+ return -EINVAL;
+ mutex_lock(&queue->timer_mutex);
+ queue_use(queue, client, use);
mutex_unlock(&queue->timer_mutex);
queuefree(queue);
return 0;
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index cf9bc042..3fc201c 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -3639,6 +3639,7 @@
HDA_CODEC_ENTRY(0x10de0071, "GPU 71 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de0072, "GPU 72 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de007d, "GPU 7d HDMI/DP", patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de0080, "GPU 80 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de0082, "GPU 82 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de0083, "GPU 83 HDMI/DP", patch_nvhdmi),
HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch),
diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c
index efe3a44..4576f98 100644
--- a/sound/soc/codecs/nau8825.c
+++ b/sound/soc/codecs/nau8825.c
@@ -561,9 +561,9 @@
nau8825_xtalk_backup(nau8825);
/* Config IIS as master to output signal by codec */
regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2,
- NAU8825_I2S_MS_MASK | NAU8825_I2S_DRV_MASK |
+ NAU8825_I2S_MS_MASK | NAU8825_I2S_LRC_DIV_MASK |
NAU8825_I2S_BLK_DIV_MASK, NAU8825_I2S_MS_MASTER |
- (0x2 << NAU8825_I2S_DRV_SFT) | 0x1);
+ (0x2 << NAU8825_I2S_LRC_DIV_SFT) | 0x1);
/* Ramp up headphone volume to 0dB to get better performance and
* avoid pop noise in headphone.
*/
@@ -657,7 +657,7 @@
NAU8825_IRQ_RMS_EN, NAU8825_IRQ_RMS_EN);
/* Recover default value for IIS */
regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2,
- NAU8825_I2S_MS_MASK | NAU8825_I2S_DRV_MASK |
+ NAU8825_I2S_MS_MASK | NAU8825_I2S_LRC_DIV_MASK |
NAU8825_I2S_BLK_DIV_MASK, NAU8825_I2S_MS_SLAVE);
/* Restore value of specific register for cross talk */
nau8825_xtalk_restore(nau8825);
@@ -2006,7 +2006,8 @@
NAU8825_FLL_INTEGER_MASK, fll_param->fll_int);
/* FLL pre-scaler */
regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL4,
- NAU8825_FLL_REF_DIV_MASK, fll_param->clk_ref_div);
+ NAU8825_FLL_REF_DIV_MASK,
+ fll_param->clk_ref_div << NAU8825_FLL_REF_DIV_SFT);
/* select divided VCO input */
regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL5,
NAU8825_FLL_CLK_SW_MASK, NAU8825_FLL_CLK_SW_REF);
diff --git a/sound/soc/codecs/nau8825.h b/sound/soc/codecs/nau8825.h
index 5d1704e..514fd13 100644
--- a/sound/soc/codecs/nau8825.h
+++ b/sound/soc/codecs/nau8825.h
@@ -137,7 +137,8 @@
#define NAU8825_FLL_CLK_SRC_FS (0x3 << NAU8825_FLL_CLK_SRC_SFT)
/* FLL4 (0x07) */
-#define NAU8825_FLL_REF_DIV_MASK (0x3 << 10)
+#define NAU8825_FLL_REF_DIV_SFT 10
+#define NAU8825_FLL_REF_DIV_MASK (0x3 << NAU8825_FLL_REF_DIV_SFT)
/* FLL5 (0x08) */
#define NAU8825_FLL_PDB_DAC_EN (0x1 << 15)
@@ -247,8 +248,8 @@
/* I2S_PCM_CTRL2 (0x1d) */
#define NAU8825_I2S_TRISTATE (1 << 15) /* 0 - normal mode, 1 - Hi-Z output */
-#define NAU8825_I2S_DRV_SFT 12
-#define NAU8825_I2S_DRV_MASK (0x3 << NAU8825_I2S_DRV_SFT)
+#define NAU8825_I2S_LRC_DIV_SFT 12
+#define NAU8825_I2S_LRC_DIV_MASK (0x3 << NAU8825_I2S_LRC_DIV_SFT)
#define NAU8825_I2S_MS_SFT 3
#define NAU8825_I2S_MS_MASK (1 << NAU8825_I2S_MS_SFT)
#define NAU8825_I2S_MS_MASTER (1 << NAU8825_I2S_MS_SFT)
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 10c2a564..1ac96ef 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3833,6 +3833,9 @@
}
}
+ regmap_update_bits(rt5645->regmap, RT5645_ADDA_CLK1,
+ RT5645_I2S_PD1_MASK, RT5645_I2S_PD1_2);
+
if (rt5645->pdata.jd_invert) {
regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2,
RT5645_JD_1_1_MASK, RT5645_JD_1_1_INV);
diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c
index 8877b74..bb94d50 100644
--- a/sound/soc/codecs/tlv320aic3x.c
+++ b/sound/soc/codecs/tlv320aic3x.c
@@ -126,6 +126,16 @@
{ 108, 0x00 }, { 109, 0x00 },
};
+static bool aic3x_volatile_reg(struct device *dev, unsigned int reg)
+{
+ switch (reg) {
+ case AIC3X_RESET:
+ return true;
+ default:
+ return false;
+ }
+}
+
static const struct regmap_config aic3x_regmap = {
.reg_bits = 8,
.val_bits = 8,
@@ -133,6 +143,9 @@
.max_register = DAC_ICC_ADJ,
.reg_defaults = aic3x_reg,
.num_reg_defaults = ARRAY_SIZE(aic3x_reg),
+
+ .volatile_reg = aic3x_volatile_reg,
+
.cache_type = REGCACHE_RBTREE,
};
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 593b7d1..d72ccef 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1551,7 +1551,7 @@
const struct wmfw_region *region;
const struct wm_adsp_region *mem;
const char *region_name;
- char *file, *text;
+ char *file, *text = NULL;
struct wm_adsp_buf *buf;
unsigned int reg;
int regions = 0;
@@ -1700,10 +1700,21 @@
regions, le32_to_cpu(region->len), offset,
region_name);
+ if ((pos + le32_to_cpu(region->len) + sizeof(*region)) >
+ firmware->size) {
+ adsp_err(dsp,
+ "%s.%d: %s region len %d bytes exceeds file length %zu\n",
+ file, regions, region_name,
+ le32_to_cpu(region->len), firmware->size);
+ ret = -EINVAL;
+ goto out_fw;
+ }
+
if (text) {
memcpy(text, region->data, le32_to_cpu(region->len));
adsp_info(dsp, "%s: %s\n", file, text);
kfree(text);
+ text = NULL;
}
if (reg) {
@@ -1748,6 +1759,7 @@
regmap_async_complete(regmap);
wm_adsp_buf_free(&buf_list);
release_firmware(firmware);
+ kfree(text);
out:
kfree(file);
@@ -2233,6 +2245,17 @@
}
if (reg) {
+ if ((pos + le32_to_cpu(blk->len) + sizeof(*blk)) >
+ firmware->size) {
+ adsp_err(dsp,
+ "%s.%d: %s region len %d bytes exceeds file length %zu\n",
+ file, blocks, region_name,
+ le32_to_cpu(blk->len),
+ firmware->size);
+ ret = -EINVAL;
+ goto out_fw;
+ }
+
buf = wm_adsp_buf_alloc(blk->data,
le32_to_cpu(blk->len),
&buf_list);
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index 2998954a..bdf8398 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -681,22 +681,19 @@
}
if (!pdata) {
- ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
- if (ret == -EPROBE_DEFER) {
- dev_err(&pdev->dev,
- "failed to register PCM, deferring probe\n");
- return ret;
- } else if (ret) {
- dev_err(&pdev->dev,
- "Could not register DMA PCM: %d\n"
- "falling back to PIO mode\n", ret);
+ if (irq >= 0) {
ret = dw_pcm_register(pdev);
- if (ret) {
- dev_err(&pdev->dev,
- "Could not register PIO PCM: %d\n",
+ dev->use_pio = true;
+ } else {
+ ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL,
+ 0);
+ dev->use_pio = false;
+ }
+
+ if (ret) {
+ dev_err(&pdev->dev, "could not register pcm: %d\n",
ret);
- goto err_clk_disable;
- }
+ goto err_clk_disable;
}
}
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 5034943..fde08660 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -224,6 +224,12 @@
* @dbg_stats: Debugging statistics
*
* @soc: SoC specific data
+ *
+ * @fifo_watermark: the FIFO watermark setting. Notifies DMA when
+ * there are @fifo_watermark or fewer words in TX fifo or
+ * @fifo_watermark or more empty words in RX fifo.
+ * @dma_maxburst: max number of words to transfer in one go. So far,
+ * this is always the same as fifo_watermark.
*/
struct fsl_ssi_private {
struct regmap *regs;
@@ -263,6 +269,9 @@
const struct fsl_ssi_soc_data *soc;
struct device *dev;
+
+ u32 fifo_watermark;
+ u32 dma_maxburst;
};
/*
@@ -1051,21 +1060,7 @@
regmap_write(regs, CCSR_SSI_SRCR, srcr);
regmap_write(regs, CCSR_SSI_SCR, scr);
- /*
- * Set the watermark for transmit FIFI 0 and receive FIFO 0. We don't
- * use FIFO 1. We program the transmit water to signal a DMA transfer
- * if there are only two (or fewer) elements left in the FIFO. Two
- * elements equals one frame (left channel, right channel). This value,
- * however, depends on the depth of the transmit buffer.
- *
- * We set the watermark on the same level as the DMA burstsize. For
- * fiq it is probably better to use the biggest possible watermark
- * size.
- */
- if (ssi_private->use_dma)
- wm = ssi_private->fifo_depth - 2;
- else
- wm = ssi_private->fifo_depth;
+ wm = ssi_private->fifo_watermark;
regmap_write(regs, CCSR_SSI_SFCSR,
CCSR_SSI_SFCSR_TFWM0(wm) | CCSR_SSI_SFCSR_RFWM0(wm) |
@@ -1373,12 +1368,8 @@
dev_dbg(&pdev->dev, "could not get baud clock: %ld\n",
PTR_ERR(ssi_private->baudclk));
- /*
- * We have burstsize be "fifo_depth - 2" to match the SSI
- * watermark setting in fsl_ssi_startup().
- */
- ssi_private->dma_params_tx.maxburst = ssi_private->fifo_depth - 2;
- ssi_private->dma_params_rx.maxburst = ssi_private->fifo_depth - 2;
+ ssi_private->dma_params_tx.maxburst = ssi_private->dma_maxburst;
+ ssi_private->dma_params_rx.maxburst = ssi_private->dma_maxburst;
ssi_private->dma_params_tx.addr = ssi_private->ssi_phys + CCSR_SSI_STX0;
ssi_private->dma_params_rx.addr = ssi_private->ssi_phys + CCSR_SSI_SRX0;
@@ -1543,6 +1534,47 @@
/* Older 8610 DTs didn't have the fifo-depth property */
ssi_private->fifo_depth = 8;
+ /*
+ * Set the watermark for transmit FIFO 0 and receive FIFO 0. We don't
+ * use FIFO 1 but set the watermark appropriately nontheless.
+ * We program the transmit water to signal a DMA transfer
+ * if there are N elements left in the FIFO. For chips with 15-deep
+ * FIFOs, set watermark to 8. This allows the SSI to operate at a
+ * high data rate without channel slipping. Behavior is unchanged
+ * for the older chips with a fifo depth of only 8. A value of 4
+ * might be appropriate for the older chips, but is left at
+ * fifo_depth-2 until sombody has a chance to test.
+ *
+ * We set the watermark on the same level as the DMA burstsize. For
+ * fiq it is probably better to use the biggest possible watermark
+ * size.
+ */
+ switch (ssi_private->fifo_depth) {
+ case 15:
+ /*
+ * 2 samples is not enough when running at high data
+ * rates (like 48kHz @ 16 bits/channel, 16 channels)
+ * 8 seems to split things evenly and leave enough time
+ * for the DMA to fill the FIFO before it's over/under
+ * run.
+ */
+ ssi_private->fifo_watermark = 8;
+ ssi_private->dma_maxburst = 8;
+ break;
+ case 8:
+ default:
+ /*
+ * maintain old behavior for older chips.
+ * Keeping it the same because I don't have an older
+ * board to test with.
+ * I suspect this could be changed to be something to
+ * leave some more space in the fifo.
+ */
+ ssi_private->fifo_watermark = ssi_private->fifo_depth - 2;
+ ssi_private->dma_maxburst = ssi_private->fifo_depth - 2;
+ break;
+ }
+
dev_set_drvdata(&pdev->dev, ssi_private);
if (ssi_private->soc->imx) {
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 507a86a..8d2fb2d 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -142,7 +142,7 @@
* for Jack detection and button press
*/
ret = snd_soc_dai_set_sysclk(codec_dai, RT5640_SCLK_S_RCCLK,
- 0,
+ 48000 * 512,
SND_SOC_CLOCK_IN);
if (!ret) {
if ((byt_rt5640_quirk & BYT_RT5640_MCLK_EN) && priv->mclk)
@@ -825,10 +825,20 @@
if ((byt_rt5640_quirk & BYT_RT5640_MCLK_EN) && (is_valleyview())) {
priv->mclk = devm_clk_get(&pdev->dev, "pmc_plt_clk_3");
if (IS_ERR(priv->mclk)) {
+ ret_val = PTR_ERR(priv->mclk);
+
dev_err(&pdev->dev,
- "Failed to get MCLK from pmc_plt_clk_3: %ld\n",
- PTR_ERR(priv->mclk));
- return PTR_ERR(priv->mclk);
+ "Failed to get MCLK from pmc_plt_clk_3: %d\n",
+ ret_val);
+
+ /*
+ * Fall back to bit clock usage for -ENOENT (clock not
+ * available likely due to missing dependencies), bail
+ * for all other errors, including -EPROBE_DEFER
+ */
+ if (ret_val != -ENOENT)
+ return ret_val;
+ byt_rt5640_quirk &= ~BYT_RT5640_MCLK_EN;
}
}
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index 84b5101..6c6b63a 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -180,6 +180,9 @@
snd_pcm_set_sync(substream);
mconfig = skl_tplg_fe_get_cpr_module(dai, substream->stream);
+ if (!mconfig)
+ return -EINVAL;
+
skl_tplg_d0i3_get(skl, mconfig->d0i3_caps);
return 0;
diff --git a/sound/soc/intel/skylake/skl-sst.c b/sound/soc/intel/skylake/skl-sst.c
index 8fc3178..b30bd38 100644
--- a/sound/soc/intel/skylake/skl-sst.c
+++ b/sound/soc/intel/skylake/skl-sst.c
@@ -515,6 +515,9 @@
void skl_sst_dsp_cleanup(struct device *dev, struct skl_sst *ctx)
{
+
+ if (ctx->dsp->fw)
+ release_firmware(ctx->dsp->fw);
skl_clear_module_table(ctx->dsp);
skl_freeup_uuid_list(ctx);
skl_ipc_free(&ctx->ipc);
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 4bd68de..99b5b08 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -1030,10 +1030,8 @@
return -ENOMEM;
ret = snd_ctl_add(card, kctrl);
- if (ret < 0) {
- snd_ctl_free_one(kctrl);
+ if (ret < 0)
return ret;
- }
cfg->update = update;
cfg->card = card;
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index f1901bb..baa1afa 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1748,6 +1748,7 @@
component->init = aux_dev->init;
component->auxiliary = 1;
+ list_add(&component->card_aux_list, &card->aux_comp_list);
return 0;
@@ -1758,16 +1759,14 @@
static int soc_probe_aux_devices(struct snd_soc_card *card)
{
- struct snd_soc_component *comp;
+ struct snd_soc_component *comp, *tmp;
int order;
int ret;
for (order = SND_SOC_COMP_ORDER_FIRST; order <= SND_SOC_COMP_ORDER_LAST;
order++) {
- list_for_each_entry(comp, &card->component_dev_list, card_list) {
- if (!comp->auxiliary)
- continue;
-
+ list_for_each_entry_safe(comp, tmp, &card->aux_comp_list,
+ card_aux_list) {
if (comp->driver->probe_order == order) {
ret = soc_probe_component(card, comp);
if (ret < 0) {
@@ -1776,6 +1775,7 @@
comp->name, ret);
return ret;
}
+ list_del(&comp->card_aux_list);
}
}
}
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index e7a1eaa..6aba140 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -2184,9 +2184,11 @@
break;
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_SUSPEND:
- case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
fe->dpcm[stream].state = SND_SOC_DPCM_STATE_STOP;
break;
+ case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+ fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PAUSED;
+ break;
}
out:
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 65670b2..fbfb1fa 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -514,13 +514,12 @@
== SND_SOC_TPLG_TYPE_MIXER)
kfree(kcontrol->tlv.p);
- snd_ctl_remove(card, kcontrol);
-
/* Private value is used as struct soc_mixer_control
* for volume mixers or soc_bytes_ext for bytes
* controls.
*/
kfree((void *)kcontrol->private_value);
+ snd_ctl_remove(card, kcontrol);
}
kfree(w->kcontrol_news);
}
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index 90009c0..ab3c280 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -754,8 +754,9 @@
goto error;
}
+ line6_get_interval(line6);
+
if (properties->capabilities & LINE6_CAP_CONTROL) {
- line6_get_interval(line6);
ret = line6_init_cap_control(line6);
if (ret < 0)
goto error;
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index b3fd2382..eb4b9f7 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1135,6 +1135,7 @@
case USB_ID(0x045E, 0x076F): /* MS Lifecam HD-6000 */
case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */
case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */
+ case USB_ID(0x047F, 0x02F7): /* Plantronics BT-600 */
case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */
case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */
case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index a2b3eb3..af05f8e 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -84,6 +84,15 @@
#define KVM_VGIC_V2_DIST_SIZE 0x1000
#define KVM_VGIC_V2_CPU_SIZE 0x2000
+/* Supported VGICv3 address types */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
+#define KVM_VGIC_ITS_ADDR_TYPE 4
+
+#define KVM_VGIC_V3_DIST_SIZE SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K)
+
#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
#define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index c93cf35..3603b6f 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -573,6 +573,10 @@
#define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
#define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
+/* POWER9 registers */
+#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
+#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
@@ -596,6 +600,7 @@
#define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
#define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
#define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a)
/* PPC64 eXternal Interrupt Controller Specification */
#define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index cddd5d0..eafee31 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -105,6 +105,7 @@
#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */
#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */
#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */
@@ -188,10 +189,14 @@
#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
@@ -220,11 +225,13 @@
#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */
#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */
#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
@@ -278,8 +285,10 @@
#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
@@ -310,4 +319,6 @@
#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 37fee27..1445865 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,8 @@
#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
#define EXIT_REASON_APIC_ACCESS 44
#define EXIT_REASON_EOI_INDUCED 45
+#define EXIT_REASON_GDTR_IDTR 46
+#define EXIT_REASON_LDTR_TR 47
#define EXIT_REASON_EPT_VIOLATION 48
#define EXIT_REASON_EPT_MISCONFIG 49
#define EXIT_REASON_INVEPT 50
@@ -113,6 +115,8 @@
{ EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
{ EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \
{ EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
+ { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \
+ { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \
{ EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
{ EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
{ EXIT_REASON_INVEPT, "INVEPT" }, \
@@ -129,6 +133,7 @@
{ EXIT_REASON_XRSTORS, "XRSTORS" }
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
+#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 99c0ccd..e279a71 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -19,6 +19,16 @@
Q=@
endif
+ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4
+ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
+ quiet=silent_
+endif
+else # make-3.8x
+ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
+ quiet=silent_
+endif
+endif
+
build-dir := $(srctree)/tools/build
# Define $(fixdep) for dep-cmd function
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
new file mode 100644
index 0000000..48af2f1
--- /dev/null
+++ b/tools/include/linux/compiler-gcc.h
@@ -0,0 +1,14 @@
+#ifndef _TOOLS_LINUX_COMPILER_H_
+#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
+#endif
+
+/*
+ * Common definitions for all gcc versions go here.
+ */
+#define GCC_VERSION (__GNUC__ * 10000 \
+ + __GNUC_MINOR__ * 100 \
+ + __GNUC_PATCHLEVEL__)
+
+#if GCC_VERSION >= 70000 && !defined(__CHECKER__)
+# define __fallthrough __attribute__ ((fallthrough))
+#endif
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index e33fc1d..6326ede 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -1,6 +1,10 @@
#ifndef _TOOLS_LINUX_COMPILER_H_
#define _TOOLS_LINUX_COMPILER_H_
+#ifdef __GNUC__
+#include <linux/compiler-gcc.h>
+#endif
+
/* Optimization barrier */
/* The "volatile" is due to gcc bugs */
#define barrier() __asm__ __volatile__("": : :"memory")
@@ -126,4 +130,9 @@
#define WRITE_ONCE(x, val) \
({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+#ifndef __fallthrough
+# define __fallthrough
+#endif
+
#endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0eb0e87..d2b0ac7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -116,6 +116,12 @@
#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
+ * to the given target_fd cgroup the descendent cgroup will be able to
+ * override effective bpf program that was inherited from this cgroup
+ */
+#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+
#define BPF_PSEUDO_MAP_FD 1
/* flags for BPF_MAP_UPDATE_ELEM command */
@@ -171,6 +177,7 @@
__u32 target_fd; /* container object to attach to */
__u32 attach_bpf_fd; /* eBPF program to attach */
__u32 attach_type;
+ __u32 attach_flags;
};
} __attribute__((aligned(8)));
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index adba83b..eb6e0b3 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -17,7 +17,13 @@
LIBFILE = $(OUTPUT)libapi.a
CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+
+ifeq ($(CC), clang)
+ CFLAGS += -O3
+else
+ CFLAGS += -O6
+endif
# Treat warnings as errors unless directed not to
ifneq ($(WERROR),0)
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index f99f49e4..4b6bfc4 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -38,6 +38,10 @@
#define HUGETLBFS_MAGIC 0x958458f6
#endif
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC 0xcafe4a11
+#endif
+
static const char * const sysfs__fs_known_mountpoints[] = {
"/sys",
0,
@@ -75,6 +79,11 @@
0,
};
+static const char * const bpf_fs__known_mountpoints[] = {
+ "/sys/fs/bpf",
+ 0,
+};
+
struct fs {
const char *name;
const char * const *mounts;
@@ -89,6 +98,7 @@
FS__DEBUGFS = 2,
FS__TRACEFS = 3,
FS__HUGETLBFS = 4,
+ FS__BPF_FS = 5,
};
#ifndef TRACEFS_MAGIC
@@ -121,6 +131,11 @@
.mounts = hugetlbfs__known_mountpoints,
.magic = HUGETLBFS_MAGIC,
},
+ [FS__BPF_FS] = {
+ .name = "bpf",
+ .mounts = bpf_fs__known_mountpoints,
+ .magic = BPF_FS_MAGIC,
+ },
};
static bool fs__read_mounts(struct fs *fs)
@@ -280,6 +295,7 @@
FS(debugfs, FS__DEBUGFS);
FS(tracefs, FS__TRACEFS);
FS(hugetlbfs, FS__HUGETLBFS);
+FS(bpf_fs, FS__BPF_FS);
int filename__read_int(const char *filename, int *value)
{
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index a63269f..6b332dc 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -22,6 +22,7 @@
FS(debugfs)
FS(tracefs)
FS(hugetlbfs)
+FS(bpf_fs)
#undef FS
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 251b7c3..3e606b9 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -86,9 +86,13 @@
free(file);
}
-static int strerror_open(int err, char *buf, size_t size, const char *filename)
+int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
+ const char *sys, const char *name)
{
char sbuf[128];
+ char filename[PATH_MAX];
+
+ snprintf(filename, PATH_MAX, "%s/%s", sys, name ?: "*");
switch (err) {
case ENOENT:
@@ -99,10 +103,19 @@
* - jirka
*/
if (debugfs__configured() || tracefs__configured()) {
- snprintf(buf, size,
- "Error:\tFile %s/%s not found.\n"
- "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
- tracing_events_path, filename);
+ /* sdt markers */
+ if (!strncmp(filename, "sdt_", 4)) {
+ snprintf(buf, size,
+ "Error:\tFile %s/%s not found.\n"
+ "Hint:\tSDT event cannot be directly recorded on.\n"
+ "\tPlease first use 'perf probe %s:%s' before recording it.\n",
+ tracing_events_path, filename, sys, name);
+ } else {
+ snprintf(buf, size,
+ "Error:\tFile %s/%s not found.\n"
+ "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
+ tracing_events_path, filename);
+ }
break;
}
snprintf(buf, size, "%s",
@@ -125,12 +138,3 @@
return 0;
}
-
-int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name)
-{
- char path[PATH_MAX];
-
- snprintf(path, PATH_MAX, "%s/%s", sys, name ?: "*");
-
- return strerror_open(err, buf, size, path);
-}
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 3ddb58a..ae752fa 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -168,7 +168,8 @@
return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
}
-int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
+ unsigned int flags)
{
union bpf_attr attr;
@@ -176,6 +177,7 @@
attr.target_fd = target_fd;
attr.attach_bpf_fd = prog_fd;
attr.attach_type = type;
+ attr.attach_flags = flags;
return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index a2f9853..44fb7c5 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -22,6 +22,7 @@
#define __BPF_BPF_H
#include <linux/bpf.h>
+#include <stddef.h>
int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
int max_entries, __u32 map_flags);
@@ -41,7 +42,8 @@
int bpf_map_get_next_key(int fd, void *key, void *next_key);
int bpf_obj_pin(int fd, const char *pathname);
int bpf_obj_get(const char *pathname);
-int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
+ unsigned int flags);
int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 84e6b35..ac6eb86 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4,6 +4,7 @@
* Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
@@ -22,15 +23,21 @@
#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
+#include <libgen.h>
#include <inttypes.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <errno.h>
#include <asm/unistd.h>
+#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/bpf.h>
#include <linux/list.h>
+#include <linux/limits.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
#include <libelf.h>
#include <gelf.h>
@@ -41,6 +48,10 @@
#define EM_BPF 247
#endif
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC 0xcafe4a11
+#endif
+
#define __printf(a, b) __attribute__((format(printf, a, b)))
__printf(1, 2)
@@ -779,7 +790,7 @@
bpf_program__collect_reloc(struct bpf_program *prog,
size_t nr_maps, GElf_Shdr *shdr,
Elf_Data *data, Elf_Data *symbols,
- int maps_shndx)
+ int maps_shndx, struct bpf_map *maps)
{
int i, nrels;
@@ -829,7 +840,15 @@
return -LIBBPF_ERRNO__RELOC;
}
- map_idx = sym.st_value / sizeof(struct bpf_map_def);
+ /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
+ for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+ if (maps[map_idx].offset == sym.st_value) {
+ pr_debug("relocation: find map %zd (%s) for insn %u\n",
+ map_idx, maps[map_idx].name, insn_idx);
+ break;
+ }
+ }
+
if (map_idx >= nr_maps) {
pr_warning("bpf relocation: map_idx %d large than %d\n",
(int)map_idx, (int)nr_maps - 1);
@@ -953,7 +972,8 @@
err = bpf_program__collect_reloc(prog, nr_maps,
shdr, data,
obj->efile.symbols,
- obj->efile.maps_shndx);
+ obj->efile.maps_shndx,
+ obj->maps);
if (err)
return err;
}
@@ -1227,6 +1247,191 @@
return err;
}
+static int check_path(const char *path)
+{
+ struct statfs st_fs;
+ char *dname, *dir;
+ int err = 0;
+
+ if (path == NULL)
+ return -EINVAL;
+
+ dname = strdup(path);
+ if (dname == NULL)
+ return -ENOMEM;
+
+ dir = dirname(dname);
+ if (statfs(dir, &st_fs)) {
+ pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
+ err = -errno;
+ }
+ free(dname);
+
+ if (!err && st_fs.f_type != BPF_FS_MAGIC) {
+ pr_warning("specified path %s is not on BPF FS\n", path);
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+ int instance)
+{
+ int err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (prog == NULL) {
+ pr_warning("invalid program pointer\n");
+ return -EINVAL;
+ }
+
+ if (instance < 0 || instance >= prog->instances.nr) {
+ pr_warning("invalid prog instance %d of prog %s (max %d)\n",
+ instance, prog->section_name, prog->instances.nr);
+ return -EINVAL;
+ }
+
+ if (bpf_obj_pin(prog->instances.fds[instance], path)) {
+ pr_warning("failed to pin program: %s\n", strerror(errno));
+ return -errno;
+ }
+ pr_debug("pinned program '%s'\n", path);
+
+ return 0;
+}
+
+static int make_dir(const char *path)
+{
+ int err = 0;
+
+ if (mkdir(path, 0700) && errno != EEXIST)
+ err = -errno;
+
+ if (err)
+ pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
+ return err;
+}
+
+int bpf_program__pin(struct bpf_program *prog, const char *path)
+{
+ int i, err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (prog == NULL) {
+ pr_warning("invalid program pointer\n");
+ return -EINVAL;
+ }
+
+ if (prog->instances.nr <= 0) {
+ pr_warning("no instances of prog %s to pin\n",
+ prog->section_name);
+ return -EINVAL;
+ }
+
+ err = make_dir(path);
+ if (err)
+ return err;
+
+ for (i = 0; i < prog->instances.nr; i++) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_program__pin_instance(prog, buf, i);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+int bpf_map__pin(struct bpf_map *map, const char *path)
+{
+ int err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (map == NULL) {
+ pr_warning("invalid map pointer\n");
+ return -EINVAL;
+ }
+
+ if (bpf_obj_pin(map->fd, path)) {
+ pr_warning("failed to pin map: %s\n", strerror(errno));
+ return -errno;
+ }
+
+ pr_debug("pinned map '%s'\n", path);
+ return 0;
+}
+
+int bpf_object__pin(struct bpf_object *obj, const char *path)
+{
+ struct bpf_program *prog;
+ struct bpf_map *map;
+ int err;
+
+ if (!obj)
+ return -ENOENT;
+
+ if (!obj->loaded) {
+ pr_warning("object not yet loaded; load it first\n");
+ return -ENOENT;
+ }
+
+ err = make_dir(path);
+ if (err)
+ return err;
+
+ bpf_map__for_each(map, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_map__pin(map, buf);
+ if (err)
+ return err;
+ }
+
+ bpf_object__for_each_program(prog, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ prog->section_name);
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_program__pin(prog, buf);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
void bpf_object__close(struct bpf_object *obj)
{
size_t i;
@@ -1419,37 +1624,33 @@
prog->type = type;
}
-int bpf_program__set_tracepoint(struct bpf_program *prog)
-{
- if (!prog)
- return -EINVAL;
- bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
- return 0;
-}
-
-int bpf_program__set_kprobe(struct bpf_program *prog)
-{
- if (!prog)
- return -EINVAL;
- bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
- return 0;
-}
-
static bool bpf_program__is_type(struct bpf_program *prog,
enum bpf_prog_type type)
{
return prog ? (prog->type == type) : false;
}
-bool bpf_program__is_tracepoint(struct bpf_program *prog)
-{
- return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-}
+#define BPF_PROG_TYPE_FNS(NAME, TYPE) \
+int bpf_program__set_##NAME(struct bpf_program *prog) \
+{ \
+ if (!prog) \
+ return -EINVAL; \
+ bpf_program__set_type(prog, TYPE); \
+ return 0; \
+} \
+ \
+bool bpf_program__is_##NAME(struct bpf_program *prog) \
+{ \
+ return bpf_program__is_type(prog, TYPE); \
+} \
-bool bpf_program__is_kprobe(struct bpf_program *prog)
-{
- return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE);
-}
+BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
+BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
+BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
+BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
+BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
+BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
+BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
int bpf_map__fd(struct bpf_map *map)
{
@@ -1537,3 +1738,10 @@
}
return ERR_PTR(-ENOENT);
}
+
+long libbpf_get_error(const void *ptr)
+{
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+ return 0;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index a5a8b86..b30394f 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -22,8 +22,8 @@
#define __BPF_LIBBPF_H
#include <stdio.h>
+#include <stdint.h>
#include <stdbool.h>
-#include <linux/err.h>
#include <sys/types.h> // for size_t
enum libbpf_errno {
@@ -65,6 +65,7 @@
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
size_t obj_buf_sz,
const char *name);
+int bpf_object__pin(struct bpf_object *object, const char *path);
void bpf_object__close(struct bpf_object *object);
/* Load/unload object into/from kernel */
@@ -106,6 +107,9 @@
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
int bpf_program__fd(struct bpf_program *prog);
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+ int instance);
+int bpf_program__pin(struct bpf_program *prog, const char *path);
struct bpf_insn;
@@ -174,11 +178,21 @@
/*
* Adjust type of bpf program. Default is kprobe.
*/
+int bpf_program__set_socket_filter(struct bpf_program *prog);
int bpf_program__set_tracepoint(struct bpf_program *prog);
int bpf_program__set_kprobe(struct bpf_program *prog);
+int bpf_program__set_sched_cls(struct bpf_program *prog);
+int bpf_program__set_sched_act(struct bpf_program *prog);
+int bpf_program__set_xdp(struct bpf_program *prog);
+int bpf_program__set_perf_event(struct bpf_program *prog);
+bool bpf_program__is_socket_filter(struct bpf_program *prog);
bool bpf_program__is_tracepoint(struct bpf_program *prog);
bool bpf_program__is_kprobe(struct bpf_program *prog);
+bool bpf_program__is_sched_cls(struct bpf_program *prog);
+bool bpf_program__is_sched_act(struct bpf_program *prog);
+bool bpf_program__is_xdp(struct bpf_program *prog);
+bool bpf_program__is_perf_event(struct bpf_program *prog);
/*
* We don't need __attribute__((packed)) now since it is
@@ -223,5 +237,8 @@
int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv);
void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__pin(struct bpf_map *map, const char *path);
+
+long libbpf_get_error(const void *ptr);
#endif
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index 3f8cc44..3d1c3b5 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -19,7 +19,13 @@
LIBFILE = $(OUTPUT)libsubcmd.a
CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+
+ifeq ($(CC), clang)
+ CFLAGS += -O3
+else
+ CFLAGS += -O6
+endif
# Treat warnings as errors unless directed not to
ifneq ($(WERROR),0)
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index 3284bb1..6bc2402 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -213,6 +213,9 @@
else
err = get_arg(p, opt, flags, (const char **)opt->value);
+ if (opt->set)
+ *(bool *)opt->set = true;
+
/* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */
if (opt->flags & PARSE_OPT_NOEMPTY) {
const char *val = *(const char **)opt->value;
@@ -267,6 +270,8 @@
}
if (get_arg(p, opt, flags, &arg))
return -1;
+ if (arg[0] == '-')
+ return opterror(opt, "expects an unsigned numerical value", flags);
*(unsigned int *)opt->value = strtol(arg, (char **)&s, 10);
if (*s)
return opterror(opt, "expects a numerical value", flags);
@@ -299,6 +304,8 @@
}
if (get_arg(p, opt, flags, &arg))
return -1;
+ if (arg[0] == '-')
+ return opterror(opt, "expects an unsigned numerical value", flags);
*(u64 *)opt->value = strtoull(arg, (char **)&s, 10);
if (*s)
return opterror(opt, "expects a numerical value", flags);
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 8866ac4..f054ca1 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -1,6 +1,7 @@
#ifndef __SUBCMD_PARSE_OPTIONS_H
#define __SUBCMD_PARSE_OPTIONS_H
+#include <linux/kernel.h>
#include <stdbool.h>
#include <stdint.h>
@@ -132,27 +133,32 @@
#define OPT_UINTEGER(s, l, v, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
-#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
- .value = check_vtype(v, const char **), (a), .help = (h), \
+ .value = check_vtype(v, const char **), .argh =(a), .help = (h), \
.flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
-#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
+#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
+ { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
+ .value = check_vtype(v, const char **), .argh = (a), .help = (h), \
+ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
+ .set = check_vtype(os, bool *)}
+#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
#define OPT_DATE(s, l, v, h) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
#define OPT_CALLBACK(s, l, v, a, h, f) \
- { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) }
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) }
#define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \
- { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
#define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
- { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
- .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
+ .value = (v), .arg = (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
- .value = (v), (a), .help = (h), .callback = (f), \
+ .value = (v), .argh = (a), .help = (h), .callback = (f), \
.flags = PARSE_OPT_OPTARG, .data = (d) }
/* parse_options() will filter out the processed options and leave the
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 2616c66..47076b1 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -257,10 +257,16 @@
endef
define do_generate_dynamic_list_file
- (echo '{'; \
- $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u; \
- echo '};'; \
- ) > $2
+ symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
+ xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\
+ if [ "$$symbol_type" = "U W w" ];then \
+ (echo '{'; \
+ $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
+ echo '};'; \
+ ) > $2; \
+ else \
+ (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\
+ fi
endef
install_lib: all_cmd install_plugins
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index 65984f1..c94e364 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -315,6 +315,7 @@
extend += delta;
delta = extend;
ptr += 4;
+ length = 0;
break;
case OLD_RINGBUF_TYPE_TIME_STAMP:
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index a00ec19..42dbf73 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -130,7 +130,7 @@
unsigned long long pfunction;
const char *func;
const char *parent;
- int index;
+ int index = 0;
if (pevent_get_field_val(s, event, "ip", record, &function, 1))
return trace_seq_putc(s, '!');
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index f1ce600..ec30c2f 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -111,7 +111,7 @@
trace_seq_printf(s, "%lld ", val);
if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
- trace_seq_printf(s, "[%lld] ", val);
+ trace_seq_printf(s, "[%d] ", (int) val);
if (pevent_get_field_val(s, event, "prev_state", record, &val, 0) == 0)
write_state(s, val);
@@ -129,7 +129,7 @@
trace_seq_printf(s, "%lld", val);
if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
- trace_seq_printf(s, " [%lld]", val);
+ trace_seq_printf(s, " [%d]", (int) val);
return 0;
}
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 5e0dea2..039636f 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -150,9 +150,9 @@
*type = INSN_RETURN;
break;
- case 0xc5: /* iret */
case 0xca: /* retf */
case 0xcb: /* retf */
+ case 0xcf: /* iret */
*type = INSN_CONTEXT_SWITCH;
break;
diff --git a/tools/perf/Build b/tools/perf/Build
index b12d5d1..9b79f8d 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -3,10 +3,12 @@
perf-y += builtin-config.o
perf-y += builtin-diff.o
perf-y += builtin-evlist.o
+perf-y += builtin-ftrace.o
perf-y += builtin-help.o
perf-y += builtin-sched.o
perf-y += builtin-buildid-list.o
perf-y += builtin-buildid-cache.o
+perf-y += builtin-kallsyms.o
perf-y += builtin-list.o
perf-y += builtin-record.o
perf-y += builtin-report.o
@@ -39,8 +41,7 @@
CFLAGS_builtin-timechart.o += $(paths)
CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \
-DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" \
- -DPREFIX="BUILD_STR($(prefix_SQ))" \
- -include $(OUTPUT)PERF-VERSION-FILE
+ -DPREFIX="BUILD_STR($(prefix_SQ))"
CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
CFLAGS_builtin-report.o += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 3f06730..2da07e5 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -248,7 +248,7 @@
Code address, Code symbol, Shared Object, Source line
dso - coalesced by shared object
-By default the coalescing is setup with 'pid,tid,iaddr'.
+By default the coalescing is setup with 'pid,iaddr'.
STDIO OUTPUT
------------
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 9365b75..5b4fff3 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -498,6 +498,18 @@
But if this option is 'no-cache', it will not update the build-id cache.
'skip' skips post-processing and does not update the cache.
+diff.*::
+ diff.order::
+ This option sets the number of columns to sort the result.
+ The default is 0, which means sorting by baseline.
+ Setting it to 1 will sort the result by delta (or other
+ compute method selected).
+
+ diff.compute::
+ This options sets the method for computing the diff result.
+ Possible values are 'delta', 'delta-abs', 'ratio' and
+ 'wdiff'. Default is 'delta'.
+
SEE ALSO
--------
linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 3e9490b..66dbe3de 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -86,8 +86,9 @@
-c::
--compute::
- Differential computation selection - delta,ratio,wdiff (default is delta).
- See COMPARISON METHODS section for more info.
+ Differential computation selection - delta, ratio, wdiff, delta-abs
+ (default is delta-abs). Default can be changed using diff.compute
+ config option. See COMPARISON METHODS section for more info.
-p::
--period::
@@ -99,7 +100,11 @@
-o::
--order::
- Specify compute sorting column number.
+ Specify compute sorting column number. 0 means sorting by baseline
+ overhead and 1 (default) means sorting by computed value of column 1
+ (data from the first file other base baseline). Values more than 1
+ can be used only if enough data files are provided.
+ The default value can be set using the diff.order config option.
--percentage::
Determine how to display the overhead percentage of filtered entries.
@@ -181,6 +186,10 @@
relative to how entries are filtered. Use --percentage=absolute to
prevent such fluctuation.
+delta-abs
+~~~~~~~~~
+Same as 'delta` method, but sort the result with the absolute values.
+
ratio
~~~~~
If specified the 'Ratio' column is displayed with value 'r' computed as:
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
new file mode 100644
index 0000000..2d96de6
--- /dev/null
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -0,0 +1,36 @@
+perf-ftrace(1)
+=============
+
+NAME
+----
+perf-ftrace - simple wrapper for kernel's ftrace functionality
+
+
+SYNOPSIS
+--------
+[verse]
+'perf ftrace' <command>
+
+DESCRIPTION
+-----------
+The 'perf ftrace' command is a simple wrapper of kernel's ftrace
+functionality. It only supports single thread tracing currently and
+just reads trace_pipe in text and then write it to stdout.
+
+The following options apply to perf ftrace.
+
+OPTIONS
+-------
+
+-t::
+--tracer=::
+ Tracer to use: function_graph or function.
+
+-v::
+--verbose=::
+ Verbosity level.
+
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-trace[1]
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
new file mode 100644
index 0000000..954ea9e
--- /dev/null
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -0,0 +1,24 @@
+perf-kallsyms(1)
+==============
+
+NAME
+----
+perf-kallsyms - Searches running kernel for symbols
+
+SYNOPSIS
+--------
+[verse]
+'perf kallsyms <options> symbol_name[,symbol_name...]'
+
+DESCRIPTION
+-----------
+This command searches the running kernel kallsyms file for the given symbol(s)
+and prints information about it, including the DSO, the kallsyms begin/end
+addresses and the addresses in the ELF kallsyms symbol table (for symbols in
+modules).
+
+OPTIONS
+-------
+-v::
+--verbose=::
+ Increase verbosity level, showing details about symbol table loading, etc.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 27fc361..27256bc 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -421,15 +421,29 @@
--timestamp-filename
Append timestamp to output file name.
---switch-output::
+--switch-output[=mode]::
Generate multiple perf.data files, timestamp prefixed, switching to a new one
-when receiving a SIGUSR2.
+based on 'mode' value:
+ "signal" - when receiving a SIGUSR2 (default value) or
+ <size> - when reaching the size threshold, size is expected to
+ be a number with appended unit character - B/K/M/G
+ <time> - when reaching the time threshold, size is expected to
+ be a number with appended unit character - s/m/h/d
+
+ Note: the precision of the size threshold hugely depends
+ on your configuration - the number and size of your ring
+ buffers (-m). It is generally more precise for higher sizes
+ (like >5M), for lower values expect different sizes.
A possible use case is to, given an external event, slice the perf.data file
that gets then processed, possibly via a perf script, to decide if that
particular perf.data snapshot should be kept or not.
Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
+The reason for the latter two is to reduce the data file switching
+overhead. You can still switch them on with:
+
+ --switch-output --no-no-buildid --no-no-buildid-cache
--dry-run::
Parse options then exit. --dry-run can be used to detect errors in cmdline
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 7617396..d33dedd 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -143,6 +143,8 @@
stop time is not given (i.e, time string is 'x.y,') then analysis goes
to end of file.
+--state::
+ Show task state when it switched out.
SEE ALSO
--------
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5dc5c6a..4ed5f23 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -36,7 +36,7 @@
'perf script report <script> [args]' to run and display the results
of <script>. <script> is the name displayed in the output of 'perf
- trace --list' i.e. the actual script name minus any language
+ script --list' i.e. the actual script name minus any language
extension. The perf.data output from a previous run of 'perf script
record <script>' is used and should be present for this command to
succeed. [args] refers to the (mainly optional) args expected by
@@ -76,7 +76,7 @@
Any command you can specify in a shell.
-D::
---dump-raw-script=::
+--dump-raw-trace=::
Display verbose dump of the trace data.
-L::
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 781b019..afd7286 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -35,7 +35,10 @@
-e::
--expr::
- List of syscalls to show, currently only syscall names.
+--event::
+ List of syscalls and other perf events (tracepoints, HW cache events,
+ etc) to show.
+ See 'perf list' for a complete list of events.
Prefixing with ! shows all syscalls but the ones specified. You may
need to escape it.
@@ -135,9 +138,6 @@
--kernel-syscall-graph::
Show the kernel callchains on the syscall exit path.
---event::
- Trace other events, see 'perf list' for a complete list.
-
--max-stack::
Set the stack depth limit when parsing the callchain, anything
beyond the specified depth will be ignored. Note that at this point
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index a511e5f..8672f83 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -61,6 +61,7 @@
tools/include/linux/atomic.h
tools/include/linux/bitops.h
tools/include/linux/compiler.h
+tools/include/linux/compiler-gcc.h
tools/include/linux/coresight-pmu.h
tools/include/linux/filter.h
tools/include/linux/hash.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 76c84f0..2b941ef 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -144,8 +144,12 @@
endif
ifeq ($(DEBUG),0)
+ifeq ($(CC), clang)
+ CFLAGS += -O3
+else
CFLAGS += -O6
endif
+endif
ifdef PARSER_DEBUG
PARSER_DEBUG_BISON := -t
@@ -291,8 +295,10 @@
endif
endif
ifneq ($(feature-dwarf), 1)
- msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
- NO_DWARF := 1
+ ifndef NO_DWARF
+ msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+ NO_DWARF := 1
+ endif
else
ifneq ($(feature-dwarf_getlocations), 1)
msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8fc2482..4da19b6 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -661,6 +661,7 @@
endif
ifndef NO_JVMTI
$(call QUIET_INSTALL, $(LIBJVMTI)) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
$(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)';
endif
$(call QUIET_INSTALL, libexec) \
@@ -704,9 +705,9 @@
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
-install-bin: install-tools install-tests
+install-bin: install-tools install-tests install-traceevent-plugins
-install: install-bin try-install-man install-traceevent-plugins
+install: install-bin try-install-man
install-python_ext:
$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 18b1351..eebe1ec 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -2,3 +2,4 @@
PERF_HAVE_DWARF_REGS := 1
endif
PERF_HAVE_JITDUMP := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h
index 2675936..36e375f 100644
--- a/tools/perf/arch/arm64/include/dwarf-regs-table.h
+++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h
@@ -2,12 +2,12 @@
/* This is included in perf/util/dwarf-regs.c */
static const char * const aarch64_regstr_tbl[] = {
- "%r0", "%r1", "%r2", "%r3", "%r4",
- "%r5", "%r6", "%r7", "%r8", "%r9",
- "%r10", "%r11", "%r12", "%r13", "%r14",
- "%r15", "%r16", "%r17", "%r18", "%r19",
- "%r20", "%r21", "%r22", "%r23", "%r24",
- "%r25", "%r26", "%r27", "%r28", "%r29",
+ "%x0", "%x1", "%x2", "%x3", "%x4",
+ "%x5", "%x6", "%x7", "%x8", "%x9",
+ "%x10", "%x11", "%x12", "%x13", "%x14",
+ "%x15", "%x16", "%x17", "%x18", "%x19",
+ "%x20", "%x21", "%x22", "%x23", "%x24",
+ "%x25", "%x26", "%x27", "%x28", "%x29",
"%lr", "%sp",
};
#endif
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
index d49efeb..068b618 100644
--- a/tools/perf/arch/arm64/util/dwarf-regs.c
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -10,17 +10,20 @@
#include <stddef.h>
#include <dwarf-regs.h>
+#include <linux/ptrace.h> /* for struct user_pt_regs */
+#include "util.h"
struct pt_regs_dwarfnum {
const char *name;
unsigned int dwarfnum;
};
-#define STR(s) #s
#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
#define GPR_DWARFNUM_NAME(num) \
{.name = STR(%x##num), .dwarfnum = num}
#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+#define DWARFNUM2OFFSET(index) \
+ (index * sizeof((struct user_pt_regs *)0)->regs[0])
/*
* Reference:
@@ -78,3 +81,13 @@
return roff->name;
return NULL;
}
+
+int regs_query_register_offset(const char *name)
+{
+ const struct pt_regs_dwarfnum *roff;
+
+ for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+ if (!strcmp(roff->name, name))
+ return DWARFNUM2OFFSET(roff->dwarfnum);
+ return -EINVAL;
+}
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index bfbb6b5..da04b8c 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -130,8 +130,6 @@
}
ncpus = sysconf(_SC_NPROCESSORS_ONLN);
- nsecs = futexbench_sanitize_numeric(nsecs);
- nfutexes = futexbench_sanitize_numeric(nfutexes);
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
@@ -139,8 +137,6 @@
if (!nthreads) /* default to the number of CPUs */
nthreads = ncpus;
- else
- nthreads = futexbench_sanitize_numeric(nthreads);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 6d9d6c4..9187777 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -152,7 +152,6 @@
goto err;
ncpus = sysconf(_SC_NPROCESSORS_ONLN);
- nsecs = futexbench_sanitize_numeric(nsecs);
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
@@ -160,8 +159,6 @@
if (!nthreads)
nthreads = ncpus;
- else
- nthreads = futexbench_sanitize_numeric(nthreads);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index fd4ee95..2b9705a 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -128,8 +128,6 @@
if (!nthreads)
nthreads = ncpus;
- else
- nthreads = futexbench_sanitize_numeric(nthreads);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index beaa6c1..2c8fa67 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -217,12 +217,8 @@
sigaction(SIGINT, &act, NULL);
ncpus = sysconf(_SC_NPROCESSORS_ONLN);
- nwaking_threads = futexbench_sanitize_numeric(nwaking_threads);
-
if (!nblocked_threads)
nblocked_threads = ncpus;
- else
- nblocked_threads = futexbench_sanitize_numeric(nblocked_threads);
/* some sanity checks */
if (nwaking_threads > nblocked_threads || !nwaking_threads)
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 46efcb9..e246b1b 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -129,7 +129,6 @@
}
ncpus = sysconf(_SC_NPROCESSORS_ONLN);
- nwakes = futexbench_sanitize_numeric(nwakes);
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
@@ -137,8 +136,6 @@
if (!nthreads)
nthreads = ncpus;
- else
- nthreads = futexbench_sanitize_numeric(nthreads);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index ba7c735..b2e06d1 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -7,7 +7,6 @@
#ifndef _FUTEX_H
#define _FUTEX_H
-#include <stdlib.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/types.h>
@@ -100,7 +99,4 @@
}
#endif
-/* User input sanitation */
-#define futexbench_sanitize_numeric(__n) abs((__n))
-
#endif /* _FUTEX_H */
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 8efe904..3083fc3 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -43,6 +43,7 @@
/*
* Debug printf:
*/
+#undef dprintf
#define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0)
struct thread_data {
@@ -1573,13 +1574,13 @@
"GB/sec,", "total-speed", "GB/sec total speed");
if (g->p.show_details >= 2) {
- char tname[32];
+ char tname[14 + 2 * 10 + 1];
struct thread_data *td;
for (p = 0; p < g->p.nr_proc; p++) {
for (t = 0; t < g->p.nr_threads; t++) {
- memset(tname, 0, 32);
+ memset(tname, 0, sizeof(tname));
td = g->threads + p*g->p.nr_threads + t;
- snprintf(tname, 32, "process%d:thread%d", p, t);
+ snprintf(tname, sizeof(tname), "process%d:thread%d", p, t);
print_res(tname, td->speed_gbs,
"GB/sec", "thread-speed", "GB/sec/thread speed");
print_res(tname, td->system_time_ns / NSEC_PER_SEC,
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index f8ca7a4..e2b2172 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -58,7 +58,7 @@
struct hist_entry he;
};
-static char const *coalesce_default = "pid,tid,iaddr";
+static char const *coalesce_default = "pid,iaddr";
struct perf_c2c {
struct perf_tool tool;
@@ -2476,6 +2476,7 @@
"mean_rmt,"
"mean_lcl,"
"mean_load,"
+ "tot_recs,"
"cpucnt,",
add_sym ? "symbol," : "",
add_dso ? "dso," : "",
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9ff0db4..70a2893 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -17,6 +17,7 @@
#include "util/symbol.h"
#include "util/util.h"
#include "util/data.h"
+#include "util/config.h"
#include <stdlib.h>
#include <math.h>
@@ -30,6 +31,7 @@
PERF_HPP_DIFF__RATIO,
PERF_HPP_DIFF__WEIGHTED_DIFF,
PERF_HPP_DIFF__FORMULA,
+ PERF_HPP_DIFF__DELTA_ABS,
PERF_HPP_DIFF__MAX_INDEX
};
@@ -64,7 +66,7 @@
static bool show_period;
static bool show_formula;
static bool show_baseline_only;
-static unsigned int sort_compute;
+static unsigned int sort_compute = 1;
static s64 compute_wdiff_w1;
static s64 compute_wdiff_w2;
@@ -73,19 +75,22 @@
COMPUTE_DELTA,
COMPUTE_RATIO,
COMPUTE_WEIGHTED_DIFF,
+ COMPUTE_DELTA_ABS,
COMPUTE_MAX,
};
const char *compute_names[COMPUTE_MAX] = {
[COMPUTE_DELTA] = "delta",
+ [COMPUTE_DELTA_ABS] = "delta-abs",
[COMPUTE_RATIO] = "ratio",
[COMPUTE_WEIGHTED_DIFF] = "wdiff",
};
-static int compute;
+static int compute = COMPUTE_DELTA_ABS;
static int compute_2_hpp[COMPUTE_MAX] = {
[COMPUTE_DELTA] = PERF_HPP_DIFF__DELTA,
+ [COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS,
[COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO,
[COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF,
};
@@ -111,6 +116,10 @@
.name = "Delta",
.width = 7,
},
+ [PERF_HPP_DIFF__DELTA_ABS] = {
+ .name = "Delta Abs",
+ .width = 7,
+ },
[PERF_HPP_DIFF__RATIO] = {
.name = "Ratio",
.width = 14,
@@ -298,6 +307,7 @@
{
switch (compute) {
case COMPUTE_DELTA:
+ case COMPUTE_DELTA_ABS:
return formula_delta(he, pair, buf, size);
case COMPUTE_RATIO:
return formula_ratio(he, pair, buf, size);
@@ -461,6 +471,7 @@
switch (compute) {
case COMPUTE_DELTA:
+ case COMPUTE_DELTA_ABS:
compute_delta(he, pair);
break;
case COMPUTE_RATIO:
@@ -498,6 +509,13 @@
return cmp_doubles(l, r);
}
+ case COMPUTE_DELTA_ABS:
+ {
+ double l = fabs(left->diff.period_ratio_delta);
+ double r = fabs(right->diff.period_ratio_delta);
+
+ return cmp_doubles(l, r);
+ }
case COMPUTE_RATIO:
{
double l = left->diff.period_ratio;
@@ -564,7 +582,7 @@
if (!p_left || !p_right)
return p_left ? -1 : 1;
- if (c != COMPUTE_DELTA) {
+ if (c != COMPUTE_DELTA && c != COMPUTE_DELTA_ABS) {
/*
* The delta can be computed without the baseline, but
* others are not. Put those entries which have no
@@ -607,6 +625,15 @@
}
static int64_t
+hist_entry__cmp_delta_abs(struct perf_hpp_fmt *fmt,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ struct data__file *d = fmt_to_data_file(fmt);
+
+ return hist_entry__cmp_compute(right, left, COMPUTE_DELTA_ABS, d->idx);
+}
+
+static int64_t
hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt,
struct hist_entry *left, struct hist_entry *right)
{
@@ -633,6 +660,14 @@
}
static int64_t
+hist_entry__cmp_delta_abs_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+ struct hist_entry *left, struct hist_entry *right)
+{
+ return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA_ABS,
+ sort_compute);
+}
+
+static int64_t
hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
@@ -775,7 +810,7 @@
OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
"Show only items with match in baseline"),
OPT_CALLBACK('c', "compute", &compute,
- "delta,ratio,wdiff:w1,w2 (default delta)",
+ "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)",
"Entries differential computation selection",
setup_compute),
OPT_BOOLEAN('p', "period", &show_period,
@@ -945,6 +980,7 @@
switch (idx) {
case PERF_HPP_DIFF__DELTA:
+ case PERF_HPP_DIFF__DELTA_ABS:
if (pair->diff.computed)
diff = pair->diff.period_ratio_delta;
else
@@ -1118,6 +1154,10 @@
fmt->color = hpp__color_wdiff;
fmt->sort = hist_entry__cmp_wdiff;
break;
+ case PERF_HPP_DIFF__DELTA_ABS:
+ fmt->color = hpp__color_delta;
+ fmt->sort = hist_entry__cmp_delta_abs;
+ break;
default:
fmt->sort = hist_entry__cmp_nop;
break;
@@ -1195,11 +1235,14 @@
case COMPUTE_WEIGHTED_DIFF:
fmt->sort = hist_entry__cmp_wdiff_idx;
break;
+ case COMPUTE_DELTA_ABS:
+ fmt->sort = hist_entry__cmp_delta_abs_idx;
+ break;
default:
BUG_ON(1);
}
- perf_hpp__register_sort_field(fmt);
+ perf_hpp__prepend_sort_field(fmt);
return 0;
}
@@ -1249,6 +1292,31 @@
return 0;
}
+static int diff__config(const char *var, const char *value,
+ void *cb __maybe_unused)
+{
+ if (!strcmp(var, "diff.order")) {
+ sort_compute = perf_config_int(var, value);
+ return 0;
+ }
+ if (!strcmp(var, "diff.compute")) {
+ if (!strcmp(value, "delta")) {
+ compute = COMPUTE_DELTA;
+ } else if (!strcmp(value, "delta-abs")) {
+ compute = COMPUTE_DELTA_ABS;
+ } else if (!strcmp(value, "ratio")) {
+ compute = COMPUTE_RATIO;
+ } else if (!strcmp(value, "wdiff")) {
+ compute = COMPUTE_WEIGHTED_DIFF;
+ } else {
+ pr_err("Invalid compute method: %s\n", value);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
{
int ret = hists__init();
@@ -1256,6 +1324,8 @@
if (ret < 0)
return ret;
+ perf_config(diff__config, NULL);
+
argc = parse_options(argc, argv, options, diff_usage, 0);
if (symbol__init(NULL) < 0)
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
new file mode 100644
index 0000000..c3e6436
--- /dev/null
+++ b/tools/perf/builtin-ftrace.c
@@ -0,0 +1,265 @@
+/*
+ * builtin-ftrace.c
+ *
+ * Copyright (c) 2013 LG Electronics, Namhyung Kim <namhyung@kernel.org>
+ *
+ * Released under the GPL v2.
+ */
+
+#include "builtin.h"
+#include "perf.h"
+
+#include <unistd.h>
+#include <signal.h>
+
+#include "debug.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "target.h"
+#include "thread_map.h"
+#include "util/config.h"
+
+
+#define DEFAULT_TRACER "function_graph"
+
+struct perf_ftrace {
+ struct perf_evlist *evlist;
+ struct target target;
+ const char *tracer;
+};
+
+static bool done;
+
+static void sig_handler(int sig __maybe_unused)
+{
+ done = true;
+}
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to the function below,
+ * ftrace__workload_exec_failed_signal.
+ *
+ * XXX We need to handle this more appropriately, emitting an error, etc.
+ */
+static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
+ siginfo_t *info __maybe_unused,
+ void *ucontext __maybe_unused)
+{
+ /* workload_exec_errno = info->si_value.sival_int; */
+ done = true;
+}
+
+static int write_tracing_file(const char *name, const char *val)
+{
+ char *file;
+ int fd, ret = -1;
+ ssize_t size = strlen(val);
+
+ file = get_tracing_file(name);
+ if (!file) {
+ pr_debug("cannot get tracing file: %s\n", name);
+ return -1;
+ }
+
+ fd = open(file, O_WRONLY);
+ if (fd < 0) {
+ pr_debug("cannot open tracing file: %s\n", name);
+ goto out;
+ }
+
+ if (write(fd, val, size) == size)
+ ret = 0;
+ else
+ pr_debug("write '%s' to tracing/%s failed\n", val, name);
+
+ close(fd);
+out:
+ put_tracing_file(file);
+ return ret;
+}
+
+static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
+{
+ if (write_tracing_file("tracing_on", "0") < 0)
+ return -1;
+
+ if (write_tracing_file("current_tracer", "nop") < 0)
+ return -1;
+
+ if (write_tracing_file("set_ftrace_pid", " ") < 0)
+ return -1;
+
+ return 0;
+}
+
+static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+{
+ char *trace_file;
+ int trace_fd;
+ char *trace_pid;
+ char buf[4096];
+ struct pollfd pollfd = {
+ .events = POLLIN,
+ };
+
+ if (geteuid() != 0) {
+ pr_err("ftrace only works for root!\n");
+ return -1;
+ }
+
+ if (argc < 1)
+ return -1;
+
+ signal(SIGINT, sig_handler);
+ signal(SIGUSR1, sig_handler);
+ signal(SIGCHLD, sig_handler);
+
+ reset_tracing_files(ftrace);
+
+ /* reset ftrace buffer */
+ if (write_tracing_file("trace", "0") < 0)
+ goto out;
+
+ if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
+ argv, false, ftrace__workload_exec_failed_signal) < 0)
+ goto out;
+
+ if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+ pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+ goto out;
+ }
+
+ if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
+ pr_err("failed to allocate pid string\n");
+ goto out;
+ }
+
+ if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
+ pr_err("failed to set pid: %s\n", trace_pid);
+ goto out_free_pid;
+ }
+
+ trace_file = get_tracing_file("trace_pipe");
+ if (!trace_file) {
+ pr_err("failed to open trace_pipe\n");
+ goto out_free_pid;
+ }
+
+ trace_fd = open(trace_file, O_RDONLY);
+
+ put_tracing_file(trace_file);
+
+ if (trace_fd < 0) {
+ pr_err("failed to open trace_pipe\n");
+ goto out_free_pid;
+ }
+
+ fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+ pollfd.fd = trace_fd;
+
+ if (write_tracing_file("tracing_on", "1") < 0) {
+ pr_err("can't enable tracing\n");
+ goto out_close_fd;
+ }
+
+ perf_evlist__start_workload(ftrace->evlist);
+
+ while (!done) {
+ if (poll(&pollfd, 1, -1) < 0)
+ break;
+
+ if (pollfd.revents & POLLIN) {
+ int n = read(trace_fd, buf, sizeof(buf));
+ if (n < 0)
+ break;
+ if (fwrite(buf, n, 1, stdout) != 1)
+ break;
+ }
+ }
+
+ write_tracing_file("tracing_on", "0");
+
+ /* read remaining buffer contents */
+ while (true) {
+ int n = read(trace_fd, buf, sizeof(buf));
+ if (n <= 0)
+ break;
+ if (fwrite(buf, n, 1, stdout) != 1)
+ break;
+ }
+
+out_close_fd:
+ close(trace_fd);
+out_free_pid:
+ free(trace_pid);
+out:
+ reset_tracing_files(ftrace);
+
+ return done ? 0 : -1;
+}
+
+static int perf_ftrace_config(const char *var, const char *value, void *cb)
+{
+ struct perf_ftrace *ftrace = cb;
+
+ if (prefixcmp(var, "ftrace."))
+ return 0;
+
+ if (strcmp(var, "ftrace.tracer"))
+ return -1;
+
+ if (!strcmp(value, "function_graph") ||
+ !strcmp(value, "function")) {
+ ftrace->tracer = value;
+ return 0;
+ }
+
+ pr_err("Please select \"function_graph\" (default) or \"function\"\n");
+ return -1;
+}
+
+int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ int ret;
+ struct perf_ftrace ftrace = {
+ .tracer = DEFAULT_TRACER,
+ .target = { .uid = UINT_MAX, },
+ };
+ const char * const ftrace_usage[] = {
+ "perf ftrace [<options>] <command>",
+ "perf ftrace [<options>] -- <command> [<options>]",
+ NULL
+ };
+ const struct option ftrace_options[] = {
+ OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+ "tracer to use: function_graph(default) or function"),
+ OPT_INCR('v', "verbose", &verbose,
+ "be more verbose"),
+ OPT_END()
+ };
+
+ ret = perf_config(perf_ftrace_config, &ftrace);
+ if (ret < 0)
+ return -1;
+
+ argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (!argc)
+ usage_with_options(ftrace_usage, ftrace_options);
+
+ ftrace.evlist = perf_evlist__new();
+ if (ftrace.evlist == NULL)
+ return -ENOMEM;
+
+ ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
+ if (ret < 0)
+ goto out_delete_evlist;
+
+ ret = __cmd_ftrace(&ftrace, argc, argv);
+
+out_delete_evlist:
+ perf_evlist__delete(ftrace.evlist);
+
+ return ret;
+}
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 3bdb2c7..aed0d84 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -434,7 +434,7 @@
const char * const builtin_help_subcommands[] = {
"buildid-cache", "buildid-list", "diff", "evlist", "help", "list",
"record", "report", "bench", "stat", "timechart", "top", "annotate",
- "script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
+ "script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
#ifdef HAVE_LIBELF_SUPPORT
"probe",
#endif
@@ -447,11 +447,13 @@
NULL
};
const char *alias;
- int rc = 0;
+ int rc;
load_command_list("perf-", &main_cmds, &other_cmds);
- perf_config(perf_help_config, &help_format);
+ rc = perf_config(perf_help_config, &help_format);
+ if (rc)
+ return rc;
argc = parse_options_subcommand(argc, argv, builtin_help_options,
builtin_help_subcommands, builtin_help_usage, 0);
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
new file mode 100644
index 0000000..224bfc4
--- /dev/null
+++ b/tools/perf/builtin-kallsyms.c
@@ -0,0 +1,67 @@
+/*
+ * builtin-kallsyms.c
+ *
+ * Builtin command: Look for a symbol in the running kernel and its modules
+ *
+ * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "builtin.h"
+#include <linux/compiler.h>
+#include <subcmd/parse-options.h>
+#include "debug.h"
+#include "machine.h"
+#include "symbol.h"
+
+static int __cmd_kallsyms(int argc, const char **argv)
+{
+ int i;
+ struct machine *machine = machine__new_kallsyms();
+
+ if (machine == NULL) {
+ pr_err("Couldn't read /proc/kallsyms\n");
+ return -1;
+ }
+
+ for (i = 0; i < argc; ++i) {
+ struct map *map;
+ struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
+
+ if (symbol == NULL) {
+ printf("%s: not found\n", argv[i]);
+ continue;
+ }
+
+ printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n",
+ symbol->name, map->dso->short_name, map->dso->long_name,
+ map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end),
+ symbol->start, symbol->end);
+ }
+
+ machine__delete(machine);
+ return 0;
+}
+
+int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ const struct option options[] = {
+ OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
+ OPT_END()
+ };
+ const char * const kallsyms_usage[] = {
+ "perf kallsyms [<options>] symbol_name",
+ NULL
+ };
+
+ argc = parse_options(argc, argv, options, kallsyms_usage, 0);
+ if (argc < 1)
+ usage_with_options(kallsyms_usage, options);
+
+ symbol_conf.sort_by_name = true;
+ symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+ if (symbol__init(NULL) < 0)
+ return -1;
+
+ return __cmd_kallsyms(argc, argv);
+}
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 915869e..6da8d08 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1065,7 +1065,7 @@
data = rb_entry(next, struct page_stat, node);
sym = machine__find_kernel_function(machine, data->callsite, &map);
- if (sym && sym->name)
+ if (sym)
caller = sym->name;
else
scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@@ -1107,7 +1107,7 @@
data = rb_entry(next, struct page_stat, node);
sym = machine__find_kernel_function(machine, data->callsite, &map);
- if (sym && sym->name)
+ if (sym)
caller = sym->name;
else
scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@@ -1920,10 +1920,12 @@
NULL
};
struct perf_session *session;
- int ret = -1;
const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n";
+ int ret = perf_config(kmem_config, NULL);
- perf_config(kmem_config, NULL);
+ if (ret)
+ return ret;
+
argc = parse_options_subcommand(argc, argv, kmem_options,
kmem_subcommands, kmem_usage, 0);
@@ -1948,6 +1950,8 @@
if (session == NULL)
return -1;
+ ret = -1;
+
if (kmem_slab) {
if (!perf_evlist__find_tracepoint_by_name(session->evlist,
"kmem:kmalloc")) {
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index ba9322f..3b9d98b 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -14,6 +14,7 @@
#include "util/parse-events.h"
#include "util/cache.h"
#include "util/pmu.h"
+#include "util/debug.h"
#include <subcmd/parse-options.h>
static bool desc_flag = true;
@@ -29,6 +30,8 @@
"Print extra event descriptions. --no-desc to not print."),
OPT_BOOLEAN('v', "long-desc", &long_desc_flag,
"Print longer event descriptions."),
+ OPT_INCR(0, "debug", &verbose,
+ "Enable debugging output"),
OPT_END()
};
const char * const list_usage[] = {
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index f87996b..1fcebc3 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -552,6 +552,8 @@
OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
"Enable kernel symbol demangling"),
OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
+ OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+ "Look for files with symbols relative to this directory"),
OPT_END()
};
int ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 74d6a03..6cd6776 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -46,6 +46,15 @@
#include <asm/bug.h>
#include <linux/time64.h>
+struct switch_output {
+ bool enabled;
+ bool signal;
+ unsigned long size;
+ unsigned long time;
+ const char *str;
+ bool set;
+};
+
struct record {
struct perf_tool tool;
struct record_opts opts;
@@ -62,10 +71,33 @@
bool no_buildid_cache_set;
bool buildid_all;
bool timestamp_filename;
- bool switch_output;
+ struct switch_output switch_output;
unsigned long long samples;
};
+static volatile int auxtrace_record__snapshot_started;
+static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
+static DEFINE_TRIGGER(switch_output_trigger);
+
+static bool switch_output_signal(struct record *rec)
+{
+ return rec->switch_output.signal &&
+ trigger_is_ready(&switch_output_trigger);
+}
+
+static bool switch_output_size(struct record *rec)
+{
+ return rec->switch_output.size &&
+ trigger_is_ready(&switch_output_trigger) &&
+ (rec->bytes_written >= rec->switch_output.size);
+}
+
+static bool switch_output_time(struct record *rec)
+{
+ return rec->switch_output.time &&
+ trigger_is_ready(&switch_output_trigger);
+}
+
static int record__write(struct record *rec, void *bf, size_t size)
{
if (perf_data_file__write(rec->session->file, bf, size) < 0) {
@@ -74,6 +106,10 @@
}
rec->bytes_written += size;
+
+ if (switch_output_size(rec))
+ trigger_hit(&switch_output_trigger);
+
return 0;
}
@@ -193,10 +229,6 @@
static volatile int signr = -1;
static volatile int child_finished;
-static volatile int auxtrace_record__snapshot_started;
-static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
-static DEFINE_TRIGGER(switch_output_trigger);
-
static void sig_handler(int sig)
{
if (sig == SIGCHLD)
@@ -386,7 +418,7 @@
static int record__open(struct record *rec)
{
- char msg[512];
+ char msg[BUFSIZ];
struct perf_evsel *pos;
struct perf_evlist *evlist = rec->evlist;
struct perf_session *session = rec->session;
@@ -623,22 +655,23 @@
static int record__synthesize_workload(struct record *rec, bool tail)
{
- struct {
- struct thread_map map;
- struct thread_map_data map_data;
- } thread_map;
+ int err;
+ struct thread_map *thread_map;
if (rec->opts.tail_synthesize != tail)
return 0;
- thread_map.map.nr = 1;
- thread_map.map.map[0].pid = rec->evlist->workload.pid;
- thread_map.map.map[0].comm = NULL;
- return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map,
+ thread_map = thread_map__new_by_tid(rec->evlist->workload.pid);
+ if (thread_map == NULL)
+ return -1;
+
+ err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
process_synthesized_event,
&rec->session->machines.host,
rec->opts.sample_address,
rec->opts.proc_map_timeout);
+ thread_map__put(thread_map);
+ return err;
}
static int record__synthesize(struct record *rec, bool tail);
@@ -712,6 +745,7 @@
}
static void snapshot_sig_handler(int sig);
+static void alarm_sig_handler(int sig);
int __weak
perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
@@ -842,11 +876,11 @@
signal(SIGTERM, sig_handler);
signal(SIGSEGV, sigsegv_handler);
- if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) {
+ if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
signal(SIGUSR2, snapshot_sig_handler);
if (rec->opts.auxtrace_snapshot_mode)
trigger_on(&auxtrace_snapshot_trigger);
- if (rec->switch_output)
+ if (rec->switch_output.enabled)
trigger_on(&switch_output_trigger);
} else {
signal(SIGUSR2, SIG_IGN);
@@ -1043,6 +1077,10 @@
err = fd;
goto out_child;
}
+
+ /* re-arm the alarm */
+ if (rec->switch_output.time)
+ alarm(rec->switch_output.time);
}
if (hits == rec->samples) {
@@ -1352,6 +1390,78 @@
return ret;
}
+static void switch_output_size_warn(struct record *rec)
+{
+ u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages);
+ struct switch_output *s = &rec->switch_output;
+
+ wakeup_size /= 2;
+
+ if (s->size < wakeup_size) {
+ char buf[100];
+
+ unit_number__scnprintf(buf, sizeof(buf), wakeup_size);
+ pr_warning("WARNING: switch-output data size lower than "
+ "wakeup kernel buffer size (%s) "
+ "expect bigger perf.data sizes\n", buf);
+ }
+}
+
+static int switch_output_setup(struct record *rec)
+{
+ struct switch_output *s = &rec->switch_output;
+ static struct parse_tag tags_size[] = {
+ { .tag = 'B', .mult = 1 },
+ { .tag = 'K', .mult = 1 << 10 },
+ { .tag = 'M', .mult = 1 << 20 },
+ { .tag = 'G', .mult = 1 << 30 },
+ { .tag = 0 },
+ };
+ static struct parse_tag tags_time[] = {
+ { .tag = 's', .mult = 1 },
+ { .tag = 'm', .mult = 60 },
+ { .tag = 'h', .mult = 60*60 },
+ { .tag = 'd', .mult = 60*60*24 },
+ { .tag = 0 },
+ };
+ unsigned long val;
+
+ if (!s->set)
+ return 0;
+
+ if (!strcmp(s->str, "signal")) {
+ s->signal = true;
+ pr_debug("switch-output with SIGUSR2 signal\n");
+ goto enabled;
+ }
+
+ val = parse_tag_value(s->str, tags_size);
+ if (val != (unsigned long) -1) {
+ s->size = val;
+ pr_debug("switch-output with %s size threshold\n", s->str);
+ goto enabled;
+ }
+
+ val = parse_tag_value(s->str, tags_time);
+ if (val != (unsigned long) -1) {
+ s->time = val;
+ pr_debug("switch-output with %s time threshold (%lu seconds)\n",
+ s->str, s->time);
+ goto enabled;
+ }
+
+ return -1;
+
+enabled:
+ rec->timestamp_filename = true;
+ s->enabled = true;
+
+ if (s->size && !rec->opts.no_buffering)
+ switch_output_size_warn(rec);
+
+ return 0;
+}
+
static const char * const __record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@@ -1405,7 +1515,7 @@
* perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
* using pipes, etc.
*/
-struct option __record_options[] = {
+static struct option __record_options[] = {
OPT_CALLBACK('e', "event", &record.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
@@ -1519,8 +1629,10 @@
"Record build-id of all DSOs regardless of hits"),
OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
"append timestamp to output filename"),
- OPT_BOOLEAN(0, "switch-output", &record.switch_output,
- "Switch output when receive SIGUSR2"),
+ OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
+ &record.switch_output.set, "signal,size,time",
+ "Switch output when receive SIGUSR2 or cross size,time threshold",
+ "signal"),
OPT_BOOLEAN(0, "dry-run", &dry_run,
"Parse options then exit"),
OPT_END()
@@ -1559,7 +1671,9 @@
if (rec->evlist == NULL)
return -ENOMEM;
- perf_config(perf_record_config, rec);
+ err = perf_config(perf_record_config, rec);
+ if (err)
+ return err;
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
@@ -1578,8 +1692,15 @@
return -EINVAL;
}
- if (rec->switch_output)
- rec->timestamp_filename = true;
+ if (switch_output_setup(rec)) {
+ parse_options_usage(record_usage, record_options, "switch-output", 0);
+ return -EINVAL;
+ }
+
+ if (rec->switch_output.time) {
+ signal(SIGALRM, alarm_sig_handler);
+ alarm(rec->switch_output.time);
+ }
if (!rec->itr) {
rec->itr = auxtrace_record__init(rec->evlist, &err);
@@ -1629,14 +1750,14 @@
if (rec->no_buildid_cache || rec->no_buildid) {
disable_buildid_cache();
- } else if (rec->switch_output) {
+ } else if (rec->switch_output.enabled) {
/*
* In 'perf record --switch-output', disable buildid
* generation by default to reduce data file switching
* overhead. Still generate buildid if they are required
* explicitly using
*
- * perf record --signal-trigger --no-no-buildid \
+ * perf record --switch-output --no-no-buildid \
* --no-no-buildid-cache
*
* Following code equals to:
@@ -1721,6 +1842,8 @@
static void snapshot_sig_handler(int sig __maybe_unused)
{
+ struct record *rec = &record;
+
if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
trigger_hit(&auxtrace_snapshot_trigger);
auxtrace_record__snapshot_started = 1;
@@ -1728,6 +1851,14 @@
trigger_error(&auxtrace_snapshot_trigger);
}
- if (trigger_is_ready(&switch_output_trigger))
+ if (switch_output_signal(rec))
+ trigger_hit(&switch_output_trigger);
+}
+
+static void alarm_sig_handler(int sig __maybe_unused)
+{
+ struct record *rec = &record;
+
+ if (switch_output_time(rec))
trigger_hit(&switch_output_trigger);
}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 06cc759..dbd7fa0 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -847,7 +847,9 @@
if (ret < 0)
return ret;
- perf_config(report__config, &report);
+ ret = perf_config(report__config, &report);
+ if (ret)
+ return ret;
argc = parse_options(argc, argv, options, report_usage, 0);
if (argc) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index d53e706..270eb2d 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -77,6 +77,22 @@
#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
+/* task state bitmask, copied from include/linux/sched.h */
+#define TASK_RUNNING 0
+#define TASK_INTERRUPTIBLE 1
+#define TASK_UNINTERRUPTIBLE 2
+#define __TASK_STOPPED 4
+#define __TASK_TRACED 8
+/* in tsk->exit_state */
+#define EXIT_DEAD 16
+#define EXIT_ZOMBIE 32
+#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD)
+/* in tsk->state again */
+#define TASK_DEAD 64
+#define TASK_WAKEKILL 128
+#define TASK_WAKING 256
+#define TASK_PARKED 512
+
enum thread_state {
THREAD_SLEEPING = 0,
THREAD_WAIT_CPU,
@@ -206,22 +222,31 @@
bool show_cpu_visual;
bool show_wakeups;
bool show_migrations;
+ bool show_state;
u64 skipped_samples;
const char *time_str;
struct perf_time_interval ptime;
+ struct perf_time_interval hist_time;
};
/* per thread run time data */
struct thread_runtime {
u64 last_time; /* time of previous sched in/out event */
u64 dt_run; /* run time */
- u64 dt_wait; /* time between CPU access (off cpu) */
+ u64 dt_sleep; /* time between CPU access by sleep (off cpu) */
+ u64 dt_iowait; /* time between CPU access by iowait (off cpu) */
+ u64 dt_preempt; /* time between CPU access by preempt (off cpu) */
u64 dt_delay; /* time between wakeup and sched-in */
u64 ready_to_run; /* time of wakeup */
struct stats run_stats;
u64 total_run_time;
+ u64 total_sleep_time;
+ u64 total_iowait_time;
+ u64 total_preempt_time;
+ u64 total_delay_time;
+ int last_state;
u64 migrations;
};
@@ -1820,6 +1845,9 @@
printf(" %-*s %9s %9s %9s", comm_width,
"task name", "wait time", "sch delay", "run time");
+ if (sched->show_state)
+ printf(" %s", "state");
+
printf("\n");
/*
@@ -1830,9 +1858,14 @@
if (sched->show_cpu_visual)
printf(" %*s ", ncpus, "");
- printf(" %-*s %9s %9s %9s\n", comm_width,
+ printf(" %-*s %9s %9s %9s", comm_width,
"[tid/pid]", "(msec)", "(msec)", "(msec)");
+ if (sched->show_state)
+ printf(" %5s", "");
+
+ printf("\n");
+
/*
* separator
*/
@@ -1845,18 +1878,34 @@
graph_dotted_line, graph_dotted_line, graph_dotted_line,
graph_dotted_line);
+ if (sched->show_state)
+ printf(" %.5s", graph_dotted_line);
+
printf("\n");
}
+static char task_state_char(struct thread *thread, int state)
+{
+ static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
+ unsigned bit = state ? ffs(state) : 0;
+
+ /* 'I' for idle */
+ if (thread->tid == 0)
+ return 'I';
+
+ return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
+}
+
static void timehist_print_sample(struct perf_sched *sched,
struct perf_sample *sample,
struct addr_location *al,
struct thread *thread,
- u64 t)
+ u64 t, int state)
{
struct thread_runtime *tr = thread__priv(thread);
u32 max_cpus = sched->max_cpu + 1;
char tstr[64];
+ u64 wait_time;
timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
printf("%15s [%04d] ", tstr, sample->cpu);
@@ -1879,10 +1928,15 @@
printf(" %-*s ", comm_width, timehist_get_commstr(thread));
- print_sched_time(tr->dt_wait, 6);
+ wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt;
+ print_sched_time(wait_time, 6);
+
print_sched_time(tr->dt_delay, 6);
print_sched_time(tr->dt_run, 6);
+ if (sched->show_state)
+ printf(" %5c ", task_state_char(thread, state));
+
if (sched->show_wakeups)
printf(" %-*s", comm_width, "");
@@ -1929,8 +1983,11 @@
u64 t, u64 tprev)
{
r->dt_delay = 0;
- r->dt_wait = 0;
+ r->dt_sleep = 0;
+ r->dt_iowait = 0;
+ r->dt_preempt = 0;
r->dt_run = 0;
+
if (tprev) {
r->dt_run = t - tprev;
if (r->ready_to_run) {
@@ -1942,12 +1999,25 @@
if (r->last_time > tprev)
pr_debug("time travel: last sched out time for task > previous sched_switch event\n");
- else if (r->last_time)
- r->dt_wait = tprev - r->last_time;
+ else if (r->last_time) {
+ u64 dt_wait = tprev - r->last_time;
+
+ if (r->last_state == TASK_RUNNING)
+ r->dt_preempt = dt_wait;
+ else if (r->last_state == TASK_UNINTERRUPTIBLE)
+ r->dt_iowait = dt_wait;
+ else
+ r->dt_sleep = dt_wait;
+ }
}
update_stats(&r->run_stats, r->dt_run);
- r->total_run_time += r->dt_run;
+
+ r->total_run_time += r->dt_run;
+ r->total_delay_time += r->dt_delay;
+ r->total_sleep_time += r->dt_sleep;
+ r->total_iowait_time += r->dt_iowait;
+ r->total_preempt_time += r->dt_preempt;
}
static bool is_idle_sample(struct perf_sample *sample,
@@ -1997,7 +2067,7 @@
break;
sym = node->sym;
- if (sym && sym->name) {
+ if (sym) {
if (!strcmp(sym->name, "schedule") ||
!strcmp(sym->name, "__schedule") ||
!strcmp(sym->name, "preempt_schedule"))
@@ -2372,6 +2442,8 @@
struct thread_runtime *tr = NULL;
u64 tprev, t = sample->time;
int rc = 0;
+ int state = perf_evsel__intval(evsel, sample, "prev_state");
+
if (machine__resolve(machine, &al, sample) < 0) {
pr_err("problem processing %d event. skipping it\n",
@@ -2446,8 +2518,10 @@
* time. we only care total run time and run stat.
*/
last_tr->dt_run = 0;
- last_tr->dt_wait = 0;
last_tr->dt_delay = 0;
+ last_tr->dt_sleep = 0;
+ last_tr->dt_iowait = 0;
+ last_tr->dt_preempt = 0;
if (itr->cursor.nr)
callchain_append(&itr->callchain, &itr->cursor, t - tprev);
@@ -2457,13 +2531,21 @@
}
if (!sched->summary_only)
- timehist_print_sample(sched, sample, &al, thread, t);
+ timehist_print_sample(sched, sample, &al, thread, t, state);
out:
+ if (sched->hist_time.start == 0 && t >= ptime->start)
+ sched->hist_time.start = t;
+ if (ptime->end == 0 || t <= ptime->end)
+ sched->hist_time.end = t;
+
if (tr) {
/* time of this sched_switch event becomes last time task seen */
tr->last_time = sample->time;
+ /* last state is used to determine where to account wait time */
+ tr->last_state = state;
+
/* sched out event for task so reset ready to run time */
tr->ready_to_run = 0;
}
@@ -2520,7 +2602,26 @@
printf("\n");
}
+static void print_thread_waittime(struct thread *t,
+ struct thread_runtime *r)
+{
+ printf("%*s %5d %9" PRIu64 " ",
+ comm_width, timehist_get_commstr(t), t->ppid,
+ (u64) r->run_stats.n);
+
+ print_sched_time(r->total_run_time, 8);
+ print_sched_time(r->total_sleep_time, 6);
+ printf(" ");
+ print_sched_time(r->total_iowait_time, 6);
+ printf(" ");
+ print_sched_time(r->total_preempt_time, 6);
+ printf(" ");
+ print_sched_time(r->total_delay_time, 6);
+ printf("\n");
+}
+
struct total_run_stats {
+ struct perf_sched *sched;
u64 sched_count;
u64 task_count;
u64 total_run_time;
@@ -2539,7 +2640,11 @@
stats->task_count++;
stats->sched_count += r->run_stats.n;
stats->total_run_time += r->total_run_time;
- print_thread_runtime(t, r);
+
+ if (stats->sched->show_state)
+ print_thread_waittime(t, r);
+ else
+ print_thread_runtime(t, r);
}
return 0;
@@ -2624,20 +2729,27 @@
struct thread *t;
struct thread_runtime *r;
int i;
+ u64 hist_time = sched->hist_time.end - sched->hist_time.start;
memset(&totals, 0, sizeof(totals));
+ totals.sched = sched;
if (sched->idle_hist) {
printf("\nIdle-time summary\n");
printf("%*s parent sched-out ", comm_width, "comm");
printf(" idle-time min-idle avg-idle max-idle stddev migrations\n");
+ } else if (sched->show_state) {
+ printf("\nWait-time summary\n");
+ printf("%*s parent sched-in ", comm_width, "comm");
+ printf(" run-time sleep iowait preempt delay\n");
} else {
printf("\nRuntime summary\n");
printf("%*s parent sched-in ", comm_width, "comm");
printf(" run-time min-run avg-run max-run stddev migrations\n");
}
printf("%*s (count) ", comm_width, "");
- printf(" (msec) (msec) (msec) (msec) %%\n");
+ printf(" (msec) (msec) (msec) (msec) %s\n",
+ sched->show_state ? "(msec)" : "%");
printf("%.117s\n", graph_dotted_line);
machine__for_each_thread(m, show_thread_runtime, &totals);
@@ -2665,7 +2777,7 @@
totals.sched_count += r->run_stats.n;
printf(" CPU %2d idle for ", i);
print_sched_time(r->total_run_time, 6);
- printf(" msec\n");
+ printf(" msec (%6.2f%%)\n", 100.0 * r->total_run_time / hist_time);
} else
printf(" CPU %2d idle entire time window\n", i);
}
@@ -2701,12 +2813,16 @@
printf("\n"
" Total number of unique tasks: %" PRIu64 "\n"
- "Total number of context switches: %" PRIu64 "\n"
- " Total run time (msec): ",
+ "Total number of context switches: %" PRIu64 "\n",
totals.task_count, totals.sched_count);
+ printf(" Total run time (msec): ");
print_sched_time(totals.total_run_time, 2);
printf("\n");
+
+ printf(" Total scheduling time (msec): ");
+ print_sched_time(hist_time, 2);
+ printf(" (x %d)\n", sched->max_cpu);
}
typedef int (*sched_handler)(struct perf_tool *tool,
@@ -3229,6 +3345,7 @@
OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
OPT_STRING(0, "time", &sched.time_str, "str",
"Time span for analysis (start,stop)"),
+ OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
OPT_PARENT(sched_options)
};
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2f3ff69..c0783b4 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2180,7 +2180,7 @@
"Show the mmap events"),
OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
"Show context switch events (if recorded)"),
- OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
OPT_BOOLEAN(0, "ns", &nanosecs,
"Use 9 decimal places when displaying time"),
OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
@@ -2212,6 +2212,7 @@
PARSE_OPT_STOP_AT_NON_OPTION);
file.path = input_name;
+ file.force = symbol_conf.force;
if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a02f2e9..f287191 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -533,7 +533,7 @@
static int __run_perf_stat(int argc, const char **argv)
{
int interval = stat_config.interval;
- char msg[512];
+ char msg[BUFSIZ];
unsigned long long t0, t1;
struct perf_evsel *counter;
struct timespec ts;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 3df4178..5a7fd7a 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -643,7 +643,7 @@
case -1:
if (errno == EINTR)
continue;
- /* Fall trhu */
+ __fallthrough;
default:
c = getc(stdin);
tcsetattr(0, TCSAFLUSH, &save);
@@ -859,7 +859,7 @@
static int perf_top__start_counters(struct perf_top *top)
{
- char msg[512];
+ char msg[BUFSIZ];
struct perf_evsel *counter;
struct perf_evlist *evlist = top->evlist;
struct record_opts *opts = &top->record_opts;
@@ -1216,7 +1216,9 @@
if (top.evlist == NULL)
return -ENOMEM;
- perf_config(perf_top_config, &top);
+ status = perf_config(perf_top_config, &top);
+ if (status)
+ return status;
argc = parse_options(argc, argv, options, top_usage, 0);
if (argc)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 206bf72..40ef9b2 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -40,6 +40,7 @@
#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
#include <stdlib.h>
+#include <string.h>
#include <linux/err.h>
#include <linux/filter.h>
#include <linux/audit.h>
@@ -2699,6 +2700,91 @@
evsel->handler = handler;
}
+/*
+ * XXX: Hackish, just splitting the combined -e+--event (syscalls
+ * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
+ * existing facilities unchanged (trace->ev_qualifier + parse_options()).
+ *
+ * It'd be better to introduce a parse_options() variant that would return a
+ * list with the terms it didn't match to an event...
+ */
+static int trace__parse_events_option(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ struct trace *trace = (struct trace *)opt->value;
+ const char *s = str;
+ char *sep = NULL, *lists[2] = { NULL, NULL, };
+ int len = strlen(str), err = -1, list;
+ char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
+ char group_name[PATH_MAX];
+
+ if (strace_groups_dir == NULL)
+ return -1;
+
+ if (*s == '!') {
+ ++s;
+ trace->not_ev_qualifier = true;
+ }
+
+ while (1) {
+ if ((sep = strchr(s, ',')) != NULL)
+ *sep = '\0';
+
+ list = 0;
+ if (syscalltbl__id(trace->sctbl, s) >= 0) {
+ list = 1;
+ } else {
+ path__join(group_name, sizeof(group_name), strace_groups_dir, s);
+ if (access(group_name, R_OK) == 0)
+ list = 1;
+ }
+
+ if (lists[list]) {
+ sprintf(lists[list] + strlen(lists[list]), ",%s", s);
+ } else {
+ lists[list] = malloc(len);
+ if (lists[list] == NULL)
+ goto out;
+ strcpy(lists[list], s);
+ }
+
+ if (!sep)
+ break;
+
+ *sep = ',';
+ s = sep + 1;
+ }
+
+ if (lists[1] != NULL) {
+ struct strlist_config slist_config = {
+ .dirname = strace_groups_dir,
+ };
+
+ trace->ev_qualifier = strlist__new(lists[1], &slist_config);
+ if (trace->ev_qualifier == NULL) {
+ fputs("Not enough memory to parse event qualifier", trace->output);
+ goto out;
+ }
+
+ if (trace__validate_ev_qualifier(trace))
+ goto out;
+ }
+
+ err = 0;
+
+ if (lists[0]) {
+ struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
+ "event selector. use 'perf list' to list available events",
+ parse_events_option);
+ err = parse_events_option(&o, lists[0], 0);
+ }
+out:
+ if (sep)
+ *sep = ',';
+
+ return err;
+}
+
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
const char *trace_usage[] = {
@@ -2730,15 +2816,15 @@
.max_stack = UINT_MAX,
};
const char *output_name = NULL;
- const char *ev_qualifier_str = NULL;
const struct option trace_options[] = {
- OPT_CALLBACK(0, "event", &trace.evlist, "event",
- "event selector. use 'perf list' to list available events",
- parse_events_option),
+ OPT_CALLBACK('e', "event", &trace, "event",
+ "event/syscall selector. use 'perf list' to list available events",
+ trace__parse_events_option),
OPT_BOOLEAN(0, "comm", &trace.show_comm,
"show the thread COMM next to its id"),
OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
- OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
+ OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
+ trace__parse_events_option),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
@@ -2863,7 +2949,7 @@
return -1;
}
- if (!trace.trace_syscalls && ev_qualifier_str) {
+ if (!trace.trace_syscalls && trace.ev_qualifier) {
pr_err("The -e option can't be used with --no-syscalls.\n");
goto out;
}
@@ -2878,28 +2964,6 @@
trace.open_id = syscalltbl__id(trace.sctbl, "open");
- if (ev_qualifier_str != NULL) {
- const char *s = ev_qualifier_str;
- struct strlist_config slist_config = {
- .dirname = system_path(STRACE_GROUPS_DIR),
- };
-
- trace.not_ev_qualifier = *s == '!';
- if (trace.not_ev_qualifier)
- ++s;
- trace.ev_qualifier = strlist__new(s, &slist_config);
- if (trace.ev_qualifier == NULL) {
- fputs("Not enough memory to parse event qualifier",
- trace.output);
- err = -ENOMEM;
- goto out_close;
- }
-
- err = trace__validate_ev_qualifier(&trace);
- if (err)
- goto out_close;
- }
-
err = target__validate(&trace.opts.target);
if (err) {
target__strerror(&trace.opts.target, err, bf, sizeof(bf));
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 0bcf68e..036e1e3 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -23,6 +23,7 @@
int cmd_evlist(int argc, const char **argv, const char *prefix);
int cmd_help(int argc, const char **argv, const char *prefix);
int cmd_sched(int argc, const char **argv, const char *prefix);
+int cmd_kallsyms(int argc, const char **argv, const char *prefix);
int cmd_list(int argc, const char **argv, const char *prefix);
int cmd_record(int argc, const char **argv, const char *prefix);
int cmd_report(int argc, const char **argv, const char *prefix);
@@ -40,6 +41,7 @@
int cmd_inject(int argc, const char **argv, const char *prefix);
int cmd_mem(int argc, const char **argv, const char *prefix);
int cmd_data(int argc, const char **argv, const char *prefix);
+int cmd_ftrace(int argc, const char **argv, const char *prefix);
int find_scripts(char **scripts_array, char **scripts_path_array);
#endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index ab5cbaa..ac3efd3 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -11,7 +11,9 @@
perf-diff mainporcelain common
perf-config mainporcelain common
perf-evlist mainporcelain common
+perf-ftrace mainporcelain common
perf-inject mainporcelain common
+perf-kallsyms mainporcelain common
perf-kmem mainporcelain common
perf-kvm mainporcelain common
perf-list mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index aa23b33..6d5479e 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -29,7 +29,6 @@
const char perf_more_info_string[] =
"See 'perf help COMMAND' for more information on a specific command.";
-int use_browser = -1;
static int use_pager = -1;
const char *input_name;
@@ -47,6 +46,7 @@
{ "diff", cmd_diff, 0 },
{ "evlist", cmd_evlist, 0 },
{ "help", cmd_help, 0 },
+ { "kallsyms", cmd_kallsyms, 0 },
{ "list", cmd_list, 0 },
{ "record", cmd_record, 0 },
{ "report", cmd_report, 0 },
@@ -71,6 +71,7 @@
{ "inject", cmd_inject, 0 },
{ "mem", cmd_mem, 0 },
{ "data", cmd_data, 0 },
+ { "ftrace", cmd_ftrace, 0 },
};
struct pager_config {
@@ -89,11 +90,12 @@
/* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */
int check_pager_config(const char *cmd)
{
+ int err;
struct pager_config c;
c.cmd = cmd;
c.val = -1;
- perf_config(pager_command_config, &c);
- return c.val;
+ err = perf_config(pager_command_config, &c);
+ return err ?: c.val;
}
static int browser_command_config(const char *var, const char *value, void *data)
@@ -112,11 +114,12 @@
*/
static int check_browser_config(const char *cmd)
{
+ int err;
struct pager_config c;
c.cmd = cmd;
c.val = -1;
- perf_config(browser_command_config, &c);
- return c.val;
+ err = perf_config(browser_command_config, &c);
+ return err ?: c.val;
}
static void commit_pager_choice(void)
@@ -329,8 +332,6 @@
return ret;
}
-const char perf_version_string[] = PERF_VERSION;
-
#define RUN_SETUP (1<<0)
#define USE_PAGER (1<<1)
@@ -510,6 +511,7 @@
int main(int argc, const char **argv)
{
+ int err;
const char *cmd;
char sbuf[STRERR_BUFSIZE];
int value;
@@ -535,7 +537,9 @@
srandom(time(NULL));
perf_config__init();
- perf_config(perf_default_config, NULL);
+ err = perf_config(perf_default_config, NULL);
+ if (err)
+ return err;
set_buildid_dir(NULL);
/* get debugfs/tracefs mount point from /proc/mounts */
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
new file mode 100644
index 0000000..076459c
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+ {
+ "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_C_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x34",
+ "EventName": "UNC_C_LLC_LOOKUP.ANY",
+ "Filter": "filter_state=0x1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x11",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x37",
+ "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.UNCACHEABLE",
+ "Filter": "filter_opc=0x187",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_READ",
+ "Filter": "filter_opc=0x187,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_WRITE",
+ "Filter": "filter_opc=0x18f,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+ "Filter": "filter_opc=0x190",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x191",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+ "Filter": "filter_opc=0x192",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+ "Filter": "filter_opc=0x180,filter_tid=0x3e",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x181",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_FULL",
+ "Filter": "filter_opc=0x18c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+ "Filter": "filter_opc=0x18d",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES",
+ "PerPkg": "1",
+ "UMask": "0xC",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+ "PerPkg": "1",
+ "UMask": "0x40",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x20",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPS",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x8",
+ "Unit": "HA"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
new file mode 100644
index 0000000..d17dc23
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+ {
+ "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0xC",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_M_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x85",
+ "EventName": "UNC_M_POWER_CHANNEL_PPD",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x86",
+ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x43",
+ "EventName": "UNC_M_POWER_SELF_REFRESH",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.RD",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.WR",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
new file mode 100644
index 0000000..b44d430
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
@@ -0,0 +1,84 @@
+[
+ {
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+ "Filter": "occ_sel=1",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+ "Filter": "occ_sel=2",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+ "Filter": "occ_sel=3",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xA",
+ "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+ "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x6",
+ "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x5",
+ "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x74",
+ "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
new file mode 100644
index 0000000..076459c
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+ {
+ "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_C_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x34",
+ "EventName": "UNC_C_LLC_LOOKUP.ANY",
+ "Filter": "filter_state=0x1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x11",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x37",
+ "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.UNCACHEABLE",
+ "Filter": "filter_opc=0x187",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_READ",
+ "Filter": "filter_opc=0x187,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_WRITE",
+ "Filter": "filter_opc=0x18f,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+ "Filter": "filter_opc=0x190",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x191",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+ "Filter": "filter_opc=0x192",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+ "Filter": "filter_opc=0x180,filter_tid=0x3e",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x181",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_FULL",
+ "Filter": "filter_opc=0x18c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+ "Filter": "filter_opc=0x18d",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES",
+ "PerPkg": "1",
+ "UMask": "0xC",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+ "PerPkg": "1",
+ "UMask": "0x40",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x20",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPS",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x8",
+ "Unit": "HA"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
new file mode 100644
index 0000000..39387f7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
@@ -0,0 +1,28 @@
+[
+ {
+ "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x14",
+ "EventName": "UNC_Q_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x2",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x4",
+ "Unit": "QPI LL"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
new file mode 100644
index 0000000..d17dc23
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+ {
+ "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0xC",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_M_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x85",
+ "EventName": "UNC_M_POWER_CHANNEL_PPD",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x86",
+ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x43",
+ "EventName": "UNC_M_POWER_SELF_REFRESH",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.RD",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.WR",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
new file mode 100644
index 0000000..b44d430
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
@@ -0,0 +1,84 @@
+[
+ {
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+ "Filter": "occ_sel=1",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+ "Filter": "occ_sel=2",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+ "Filter": "occ_sel=3",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xA",
+ "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+ "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x6",
+ "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x5",
+ "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x74",
+ "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
new file mode 100644
index 0000000..076459c
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+ {
+ "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_C_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x34",
+ "EventName": "UNC_C_LLC_LOOKUP.ANY",
+ "Filter": "filter_state=0x1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x11",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x37",
+ "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.UNCACHEABLE",
+ "Filter": "filter_opc=0x187",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_READ",
+ "Filter": "filter_opc=0x187,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_WRITE",
+ "Filter": "filter_opc=0x18f,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+ "Filter": "filter_opc=0x190",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x191",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+ "Filter": "filter_opc=0x192",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+ "Filter": "filter_opc=0x180,filter_tid=0x3e",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x181",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_FULL",
+ "Filter": "filter_opc=0x18c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+ "Filter": "filter_opc=0x18d",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES",
+ "PerPkg": "1",
+ "UMask": "0xC",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+ "PerPkg": "1",
+ "UMask": "0x40",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x20",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPS",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x8",
+ "Unit": "HA"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
new file mode 100644
index 0000000..39387f7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
@@ -0,0 +1,28 @@
+[
+ {
+ "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x14",
+ "EventName": "UNC_Q_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x2",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x4",
+ "Unit": "QPI LL"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
new file mode 100644
index 0000000..d17dc23
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+ {
+ "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0xC",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_M_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x85",
+ "EventName": "UNC_M_POWER_CHANNEL_PPD",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x86",
+ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x43",
+ "EventName": "UNC_M_POWER_SELF_REFRESH",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.RD",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.WR",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
new file mode 100644
index 0000000..b44d430
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
@@ -0,0 +1,84 @@
+[
+ {
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+ "Filter": "occ_sel=1",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+ "Filter": "occ_sel=2",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+ "Filter": "occ_sel=3",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xA",
+ "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+ "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x6",
+ "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x5",
+ "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x74",
+ "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
new file mode 100644
index 0000000..2efdc67
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
@@ -0,0 +1,322 @@
+[
+ {
+ "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_C_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_C_LLC_LOOKUP.ANY",
+ "Filter": "filter_state=0x1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x11",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "Counter": "0,1",
+ "EventCode": "0x37",
+ "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.UNCACHEABLE",
+ "Filter": "filter_opc=0x187",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode.rfo_prefetch",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+ "Filter": "filter_opc=0x190",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode.code",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x191",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode.data_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+ "Filter": "filter_opc=0x192",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_WRITE",
+ "Filter": "filter_opc=0x19c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.ITOM_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe non-snoop reads. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_READ",
+ "Filter": "filter_opc=0x1e4",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.miss_opcode.pcie_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+ "Filter": "filter_opc=0x1e6",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_FULL",
+ "Filter": "filter_opc=0x18c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+ "Filter": "filter_opc=0x18d",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
+ "Filter": "filter_opc=0x195",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_WRITE",
+ "Filter": "filter_opc=0x19c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.ITOM_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_READ",
+ "Filter": "filter_opc=0x1e4",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+ "Filter": "filter_opc=0x1e5",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
+ "Filter": "filter_opc=0x1e6",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory. Derived from unc_c_tor_occupancy.miss_local",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x2A",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory. Derived from unc_c_tor_occupancy.miss_remote",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x8A",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Read requests to home agent. Derived from unc_h_requests.reads",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Write requests to home agent. Derived from unc_h_requests.writes",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES",
+ "PerPkg": "1",
+ "UMask": "0xC",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x20",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPS",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x8",
+ "Unit": "HA"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
new file mode 100644
index 0000000..d7e2fda
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
@@ -0,0 +1,46 @@
+[
+ {
+ "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events. Derived from unc_q_clockticks",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x14",
+ "EventName": "UNC_Q_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x10",
+ "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
+ "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
+ "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x2",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x4",
+ "Unit": "QPI LL"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
new file mode 100644
index 0000000..ac4ad4d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
@@ -0,0 +1,75 @@
+[
+ {
+ "BriefDescription": "Memory page activates for reads and writes. Derived from unc_m_act_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_M_ACT_COUNT.RD",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Umask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0xC",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events. Derived from unc_m_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_M_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x85",
+ "EventName": "UNC_M_POWER_CHANNEL_PPD",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x86",
+ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x43",
+ "EventName": "UNC_M_POWER_SELF_REFRESH",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
new file mode 100644
index 0000000..dc2586d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
@@ -0,0 +1,249 @@
+[
+ {
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_BAND0_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_BAND1_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_BAND2_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_BAND3_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+ "Filter": "occ_sel=1",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+ "Filter": "occ_sel=2",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c6",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+ "Filter": "occ_sel=3",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xa",
+ "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+ "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency. This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature. This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x6",
+ "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x5",
+ "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x7",
+ "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system. Derived from unc_p_freq_trans_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x60",
+ "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
+ "Filter": "filter_band0=1200",
+ "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
+ "Filter": "filter_band1=2000",
+ "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
+ "Filter": "filter_band2=3000",
+ "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
+ "Filter": "filter_band3=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band0=1200",
+ "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band1=2000",
+ "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band2=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band3=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
new file mode 100644
index 0000000..2f23cf0
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
@@ -0,0 +1,209 @@
+[
+ {
+ "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_C_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_C_LLC_LOOKUP.ANY",
+ "Filter": "filter_state=0x1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x11",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "Counter": "0,1",
+ "EventCode": "0x37",
+ "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.UNCACHEABLE",
+ "Filter": "filter_opc=0x187",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_WRITE",
+ "Filter": "filter_opc=0x19c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.ITOM_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_FULL",
+ "Filter": "filter_opc=0x18c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+ "Filter": "filter_opc=0x18d",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
+ "Filter": "filter_opc=0x195",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_WRITE",
+ "Filter": "filter_opc=0x19c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.ITOM_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_READ",
+ "Filter": "filter_opc=0x1e4",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+ "Filter": "filter_opc=0x1e5",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
+ "Filter": "filter_opc=0x1e6",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth. Derived from unc_c_tor_occupancy.miss_all",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL",
+ "Filter": "filter_opc=0x182",
+ "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "UMask": "0xa",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES",
+ "PerPkg": "1",
+ "UMask": "0xc",
+ "Unit": "HA"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
new file mode 100644
index 0000000..6335187
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
@@ -0,0 +1,46 @@
+[
+ {
+ "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events. Derived from unc_q_clockticks",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x14",
+ "EventName": "UNC_Q_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x10",
+ "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
+ "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
+ "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x2",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x4",
+ "Unit": "QPI LL"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
new file mode 100644
index 0000000..e2cf6da
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
@@ -0,0 +1,79 @@
+[
+ {
+ "BriefDescription": "Memory page activates. Derived from unc_m_act_count",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_M_ACT_COUNT",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "UMask": "0xc",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events. Derived from unc_m_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_M_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x85",
+ "EventName": "UNC_M_POWER_CHANNEL_PPD",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x86",
+ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x43",
+ "EventName": "UNC_M_POWER_SELF_REFRESH",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Occupancy counter for memory read queue. Derived from unc_m_rpq_occupancy",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_M_RPQ_OCCUPANCY",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
new file mode 100644
index 0000000..bbe36d5
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
@@ -0,0 +1,248 @@
+[
+ {
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_BAND0_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_BAND1_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_BAND2_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_BAND3_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transistioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+ "Filter": "occ_sel=1",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+ "Filter": "occ_sel=2",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events . Derived from unc_p_power_state_occupancy.cores_c6",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+ "Filter": "occ_sel=3",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xa",
+ "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+ "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x6",
+ "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x5",
+ "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x7",
+ "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
+ "Filter": "filter_band0=1200",
+ "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
+ "Filter": "filter_band1=2000",
+ "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
+ "Filter": "filter_band2=3000",
+ "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
+ "Filter": "filter_band3=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band0=1200",
+ "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band1=2000",
+ "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band2=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band3=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json
new file mode 100644
index 0000000..e3bcd86
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json
@@ -0,0 +1,42 @@
+[
+ {
+ "BriefDescription": "ddr bandwidth read (CPU traffic only) (MB/sec). ",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x03",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "ScaleUnit": "6.4e-05MiB",
+ "UMask": "0x01",
+ "Unit": "imc"
+ },
+ {
+ "BriefDescription": "ddr bandwidth write (CPU traffic only) (MB/sec). ",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x03",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "ScaleUnit": "6.4e-05MiB",
+ "UMask": "0x02",
+ "Unit": "imc"
+ },
+ {
+ "BriefDescription": "mcdram bandwidth read (CPU traffic only) (MB/sec). ",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x01",
+ "EventName": "UNC_E_RPQ_INSERTS",
+ "PerPkg": "1",
+ "ScaleUnit": "6.4e-05MiB",
+ "UMask": "0x01",
+ "Unit": "edc_eclk"
+ },
+ {
+ "BriefDescription": "mcdram bandwidth write (CPU traffic only) (MB/sec). ",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x02",
+ "EventName": "UNC_E_WPQ_INSERTS",
+ "PerPkg": "1",
+ "ScaleUnit": "6.4e-05MiB",
+ "UMask": "0x01",
+ "Unit": "edc_eclk"
+ }
+]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 41611d7..eed0934 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -135,7 +135,6 @@
const char *field;
const char *kernel;
} fields[] = {
- { "EventCode", "event=" },
{ "UMask", "umask=" },
{ "CounterMask", "cmask=" },
{ "Invert", "inv=" },
@@ -189,6 +188,27 @@
return NULL;
}
+static struct map {
+ const char *json;
+ const char *perf;
+} unit_to_pmu[] = {
+ { "CBO", "uncore_cbox" },
+ { "QPI LL", "uncore_qpi" },
+ { "SBO", "uncore_sbox" },
+ {}
+};
+
+static const char *field_to_perf(struct map *table, char *map, jsmntok_t *val)
+{
+ int i;
+
+ for (i = 0; table[i].json; i++) {
+ if (json_streq(map, val, table[i].json))
+ return table[i].perf;
+ }
+ return NULL;
+}
+
#define EXPECT(e, t, m) do { if (!(e)) { \
jsmntok_t *loc = (t); \
if (!(t)->start && (t) > tokens) \
@@ -270,7 +290,8 @@
}
static int print_events_table_entry(void *data, char *name, char *event,
- char *desc, char *long_desc)
+ char *desc, char *long_desc,
+ char *pmu, char *unit, char *perpkg)
{
struct perf_entry_data *pd = data;
FILE *outfp = pd->outfp;
@@ -288,7 +309,12 @@
fprintf(outfp, "\t.topic = \"%s\",\n", topic);
if (long_desc && long_desc[0])
fprintf(outfp, "\t.long_desc = \"%s\",\n", long_desc);
-
+ if (pmu)
+ fprintf(outfp, "\t.pmu = \"%s\",\n", pmu);
+ if (unit)
+ fprintf(outfp, "\t.unit = \"%s\",\n", unit);
+ if (perpkg)
+ fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg);
fprintf(outfp, "},\n");
return 0;
@@ -335,7 +361,8 @@
/* Call func with each event in the json file */
int json_events(const char *fn,
int (*func)(void *data, char *name, char *event, char *desc,
- char *long_desc),
+ char *long_desc,
+ char *pmu, char *unit, char *perpkg),
void *data)
{
int err = -EIO;
@@ -343,6 +370,7 @@
jsmntok_t *tokens, *tok;
int i, j, len;
char *map;
+ char buf[128];
if (!fn)
return -ENOENT;
@@ -356,6 +384,11 @@
char *event = NULL, *desc = NULL, *name = NULL;
char *long_desc = NULL;
char *extra_desc = NULL;
+ char *pmu = NULL;
+ char *filter = NULL;
+ char *perpkg = NULL;
+ char *unit = NULL;
+ unsigned long long eventcode = 0;
struct msrmap *msr = NULL;
jsmntok_t *msrval = NULL;
jsmntok_t *precise = NULL;
@@ -376,6 +409,16 @@
nz = !json_streq(map, val, "0");
if (match_field(map, field, nz, &event, val)) {
/* ok */
+ } else if (json_streq(map, field, "EventCode")) {
+ char *code = NULL;
+ addfield(map, &code, "", "", val);
+ eventcode |= strtoul(code, NULL, 0);
+ free(code);
+ } else if (json_streq(map, field, "ExtSel")) {
+ char *code = NULL;
+ addfield(map, &code, "", "", val);
+ eventcode |= strtoul(code, NULL, 0) << 21;
+ free(code);
} else if (json_streq(map, field, "EventName")) {
addfield(map, &name, "", "", val);
} else if (json_streq(map, field, "BriefDescription")) {
@@ -399,6 +442,28 @@
addfield(map, &extra_desc, ". ",
" Supports address when precise",
NULL);
+ } else if (json_streq(map, field, "Unit")) {
+ const char *ppmu;
+ char *s;
+
+ ppmu = field_to_perf(unit_to_pmu, map, val);
+ if (ppmu) {
+ pmu = strdup(ppmu);
+ } else {
+ if (!pmu)
+ pmu = strdup("uncore_");
+ addfield(map, &pmu, "", "", val);
+ for (s = pmu; *s; s++)
+ *s = tolower(*s);
+ }
+ addfield(map, &desc, ". ", "Unit: ", NULL);
+ addfield(map, &desc, "", pmu, NULL);
+ } else if (json_streq(map, field, "Filter")) {
+ addfield(map, &filter, "", "", val);
+ } else if (json_streq(map, field, "ScaleUnit")) {
+ addfield(map, &unit, "", "", val);
+ } else if (json_streq(map, field, "PerPkg")) {
+ addfield(map, &perpkg, "", "", val);
}
/* ignore unknown fields */
}
@@ -410,20 +475,29 @@
addfield(map, &extra_desc, " ",
"(Precise event)", NULL);
}
+ snprintf(buf, sizeof buf, "event=%#llx", eventcode);
+ addfield(map, &event, ",", buf, NULL);
if (desc && extra_desc)
addfield(map, &desc, " ", extra_desc, NULL);
if (long_desc && extra_desc)
addfield(map, &long_desc, " ", extra_desc, NULL);
+ if (filter)
+ addfield(map, &event, ",", filter, NULL);
if (msr != NULL)
addfield(map, &event, ",", msr->pname, msrval);
fixname(name);
- err = func(data, name, real_event(name, event), desc, long_desc);
+ err = func(data, name, real_event(name, event), desc, long_desc,
+ pmu, unit, perpkg);
free(event);
free(desc);
free(name);
free(long_desc);
free(extra_desc);
+ free(pmu);
+ free(filter);
+ free(perpkg);
+ free(unit);
if (err)
break;
tok += j;
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index b0eb274..71e13de 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -3,7 +3,9 @@
int json_events(const char *fn,
int (*func)(void *data, char *name, char *event, char *desc,
- char *long_desc),
+ char *long_desc,
+ char *pmu,
+ char *unit, char *perpkg),
void *data);
char *get_cpu_str(void);
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 2eaef59..c669a3c 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -10,6 +10,9 @@
const char *desc;
const char *topic;
const char *long_desc;
+ const char *pmu;
+ const char *unit;
+ const char *perpkg;
};
/*
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6676c2d..1cb3d9b 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -44,6 +44,7 @@
perf-y += bitmap.o
perf-y += perf-hooks.o
perf-y += clang.o
+perf-y += unit_number__scnprintf.o
$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
$(call rule_mkdir)
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 92343f4..1a04fe7 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -5,11 +5,13 @@
#include <util/evlist.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <api/fs/fs.h>
#include <bpf/bpf.h>
#include "tests.h"
#include "llvm.h"
#include "debug.h"
#define NR_ITERS 111
+#define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test"
#ifdef HAVE_LIBBPF_SUPPORT
@@ -54,6 +56,7 @@
const char *msg_load_fail;
int (*target_func)(void);
int expect_result;
+ bool pin;
} bpf_testcase_table[] = {
{
LLVM_TESTCASE_BASE,
@@ -63,6 +66,17 @@
"load bpf object failed",
&epoll_wait_loop,
(NR_ITERS + 1) / 2,
+ false,
+ },
+ {
+ LLVM_TESTCASE_BASE,
+ "BPF pinning",
+ "[bpf_pinning]",
+ "fix kbuild first",
+ "check your vmlinux setting?",
+ &epoll_wait_loop,
+ (NR_ITERS + 1) / 2,
+ true,
},
#ifdef HAVE_BPF_PROLOGUE
{
@@ -73,6 +87,7 @@
"check your vmlinux setting?",
&llseek_loop,
(NR_ITERS + 1) / 4,
+ false,
},
#endif
{
@@ -83,6 +98,7 @@
"libbpf error when dealing with relocation",
NULL,
0,
+ false,
},
};
@@ -226,10 +242,34 @@
goto out;
}
- if (obj)
+ if (obj) {
ret = do_test(obj,
bpf_testcase_table[idx].target_func,
bpf_testcase_table[idx].expect_result);
+ if (ret != TEST_OK)
+ goto out;
+ if (bpf_testcase_table[idx].pin) {
+ int err;
+
+ if (!bpf_fs__mount()) {
+ pr_debug("BPF filesystem not mounted\n");
+ ret = TEST_FAIL;
+ goto out;
+ }
+ err = mkdir(PERF_TEST_BPF_PATH, 0777);
+ if (err && errno != EEXIST) {
+ pr_debug("Failed to make perf_test dir: %s\n",
+ strerror(errno));
+ ret = TEST_FAIL;
+ goto out;
+ }
+ if (bpf_object__pin(obj, PERF_TEST_BPF_PATH))
+ ret = TEST_FAIL;
+ if (rm_rf(PERF_TEST_BPF_PATH))
+ ret = TEST_FAIL;
+ }
+ }
+
out:
bpf__clear();
return ret;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index a77dcc0..37e326b 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -247,6 +247,10 @@
}
},
{
+ .desc = "unit_number__scnprintf",
+ .func = test__unit_number__scnprint,
+ },
+ {
.func = NULL,
},
};
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 02a33eb..d357dab 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -13,7 +13,7 @@
struct bpf_object *obj;
obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL);
- if (IS_ERR(obj))
+ if (libbpf_get_error(obj))
return TEST_FAIL;
bpf_object__close(obj);
return TEST_OK;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 20c2e64..aa9276b 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1779,15 +1779,14 @@
}
while (!ret && (ent = readdir(dir))) {
-#define MAX_NAME 100
struct evlist_test e;
- char name[MAX_NAME];
+ char name[2 * NAME_MAX + 1 + 12 + 3];
/* Names containing . are special and cannot be used directly */
if (strchr(ent->d_name, '.'))
continue;
- snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name);
+ snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name);
e.name = name;
e.check = test__checkevent_pmu_events;
@@ -1795,11 +1794,10 @@
ret = test_event(&e);
if (ret)
break;
- snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
+ snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
e.name = name;
e.check = test__checkevent_pmu_events_mix;
ret = test_event(&e);
-#undef MAX_NAME
}
closedir(dir);
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 81c6eea..65dcf48 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -50,7 +50,8 @@
}
struct test_attr_event {
- struct attr_event attr;
+ struct perf_event_header header;
+ struct perf_event_attr attr;
u64 id;
};
@@ -71,20 +72,16 @@
int err;
struct test_attr_event event1 = {
- .attr = {
- .header = {
- .type = PERF_RECORD_HEADER_ATTR,
- .size = sizeof(struct test_attr_event),
- },
+ .header = {
+ .type = PERF_RECORD_HEADER_ATTR,
+ .size = sizeof(struct test_attr_event),
},
.id = 1,
};
struct test_attr_event event2 = {
- .attr = {
- .header = {
- .type = PERF_RECORD_HEADER_ATTR,
- .size = sizeof(struct test_attr_event),
- },
+ .header = {
+ .type = PERF_RECORD_HEADER_ATTR,
+ .size = sizeof(struct test_attr_event),
},
.id = 2,
};
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 8f2e1de..541da7a 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -66,7 +66,7 @@
if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */
evlist = perf_evlist__new_default();
- if (evlist == NULL || argv == NULL) {
+ if (evlist == NULL) {
pr_debug("Not enough memory to create evlist\n");
goto out;
}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a512f0c..1fa9b9d 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -96,6 +96,7 @@
int test__clang(int subtest);
const char *test__clang_subtest_get_desc(int subtest);
int test__clang_subtest_get_nr(void);
+int test__unit_number__scnprint(int subtest);
#if defined(__arm__) || defined(__aarch64__)
#ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
new file mode 100644
index 0000000..623c2aa
--- /dev/null
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -0,0 +1,37 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include "tests.h"
+#include "util.h"
+#include "debug.h"
+
+int test__unit_number__scnprint(int subtest __maybe_unused)
+{
+ struct {
+ u64 n;
+ const char *str;
+ } test[] = {
+ { 1, "1B" },
+ { 10*1024, "10K" },
+ { 20*1024*1024, "20M" },
+ { 30*1024*1024*1024ULL, "30G" },
+ { 0, "0B" },
+ { 0, NULL },
+ };
+ unsigned i = 0;
+
+ while (test[i].str) {
+ char buf[100];
+
+ unit_number__scnprintf(buf, sizeof(buf), test[i].n);
+
+ pr_debug("n %" PRIu64 ", str '%s', buf '%s'\n",
+ test[i].n, test[i].str, buf);
+
+ if (strcmp(test[i].str, buf))
+ return TEST_FAIL;
+
+ i++;
+ }
+
+ return TEST_OK;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 641b402..fc4fb66 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -501,8 +501,8 @@
return n;
}
-static void hist_entry__set_folding(struct hist_entry *he,
- struct hist_browser *hb, bool unfold)
+static void __hist_entry__set_folding(struct hist_entry *he,
+ struct hist_browser *hb, bool unfold)
{
hist_entry__init_have_children(he);
he->unfolded = unfold ? he->has_children : false;
@@ -520,12 +520,34 @@
he->nr_rows = 0;
}
+static void hist_entry__set_folding(struct hist_entry *he,
+ struct hist_browser *browser, bool unfold)
+{
+ double percent;
+
+ percent = hist_entry__get_percent_limit(he);
+ if (he->filtered || percent < browser->min_pcnt)
+ return;
+
+ __hist_entry__set_folding(he, browser, unfold);
+
+ if (!he->depth || unfold)
+ browser->nr_hierarchy_entries++;
+ if (he->leaf)
+ browser->nr_callchain_rows += he->nr_rows;
+ else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+ browser->nr_hierarchy_entries++;
+ he->has_no_entry = true;
+ he->nr_rows = 1;
+ } else
+ he->has_no_entry = false;
+}
+
static void
__hist_browser__set_folding(struct hist_browser *browser, bool unfold)
{
struct rb_node *nd;
struct hist_entry *he;
- double percent;
nd = rb_first(&browser->hists->entries);
while (nd) {
@@ -535,21 +557,6 @@
nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
hist_entry__set_folding(he, browser, unfold);
-
- percent = hist_entry__get_percent_limit(he);
- if (he->filtered || percent < browser->min_pcnt)
- continue;
-
- if (!he->depth || unfold)
- browser->nr_hierarchy_entries++;
- if (he->leaf)
- browser->nr_callchain_rows += he->nr_rows;
- else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
- browser->nr_hierarchy_entries++;
- he->has_no_entry = true;
- he->nr_rows = 1;
- } else
- he->has_no_entry = false;
}
}
@@ -564,6 +571,15 @@
ui_browser__reset_index(&browser->b);
}
+static void hist_browser__set_folding_selected(struct hist_browser *browser, bool unfold)
+{
+ if (!browser->he_selection)
+ return;
+
+ hist_entry__set_folding(browser->he_selection, browser, unfold);
+ browser->b.nr_entries = hist_browser__nr_entries(browser);
+}
+
static void ui_browser__warn_lost_events(struct ui_browser *browser)
{
ui_browser__warning(browser, 4,
@@ -637,10 +653,18 @@
/* Collapse the whole world. */
hist_browser__set_folding(browser, false);
break;
+ case 'c':
+ /* Collapse the selected entry. */
+ hist_browser__set_folding_selected(browser, false);
+ break;
case 'E':
/* Expand the whole world. */
hist_browser__set_folding(browser, true);
break;
+ case 'e':
+ /* Expand the selected entry. */
+ hist_browser__set_folding_selected(browser, true);
+ break;
case 'H':
browser->show_headers = !browser->show_headers;
hist_browser__update_rows(browser);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 3738839..18cfcdc9 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -521,6 +521,12 @@
list_add_tail(&format->sort_list, &list->sorts);
}
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+ struct perf_hpp_fmt *format)
+{
+ list_add(&format->sort_list, &list->sorts);
+}
+
void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
{
list_del(&format->list);
@@ -560,6 +566,10 @@
perf_hpp_list__for_each_sort_list(list, fmt) {
struct perf_hpp_fmt *pos;
+ /* skip sort-only fields ("sort_compute" in perf diff) */
+ if (!fmt->entry && !fmt->color)
+ continue;
+
perf_hpp_list__for_each_format(list, pos) {
if (fmt_equal(fmt, pos))
goto next;
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 1f6b099..50d13e58 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -7,6 +7,7 @@
pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
void *perf_gtk_handle;
+int use_browser = -1;
#ifdef HAVE_GTK2_SUPPORT
static int setup_gtk_browser(void)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 3840e3a..5da376b 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -162,6 +162,7 @@
CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_parse-events.o += -Wno-redundant-decls
+CFLAGS_header.o += -include $(OUTPUT)PERF-VERSION-FILE
$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
$(call rule_mkdir)
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 36c8611..bc6bc70 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -670,13 +670,13 @@
err = convert_perf_probe_events(pev, 1);
if (err < 0) {
- pr_debug("bpf_probe: failed to convert perf probe events");
+ pr_debug("bpf_probe: failed to convert perf probe events\n");
goto out;
}
err = apply_perf_probe_events(pev, 1);
if (err < 0) {
- pr_debug("bpf_probe: failed to apply perf probe events");
+ pr_debug("bpf_probe: failed to apply perf probe events\n");
goto out;
}
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 4292251..aba9534 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -48,6 +48,8 @@
callchain_param.mode = CHAIN_FOLDED;
return 0;
}
+
+ pr_err("Invalid callchain mode: %s\n", value);
return -1;
}
@@ -63,6 +65,8 @@
callchain_param.order_set = true;
return 0;
}
+
+ pr_err("Invalid callchain order: %s\n", value);
return -1;
}
@@ -80,6 +84,8 @@
callchain_param.branch_callstack = 1;
return 0;
}
+
+ pr_err("Invalid callchain sort key: %s\n", value);
return -1;
}
@@ -97,6 +103,8 @@
callchain_param.value = CCVAL_COUNT;
return 0;
}
+
+ pr_err("Invalid callchain config key: %s\n", value);
return -1;
}
@@ -210,13 +218,17 @@
return parse_callchain_sort_key(value);
if (!strcmp(var, "threshold")) {
callchain_param.min_percent = strtod(value, &endptr);
- if (value == endptr)
+ if (value == endptr) {
+ pr_err("Invalid callchain threshold: %s\n", value);
return -1;
+ }
}
if (!strcmp(var, "print-limit")) {
callchain_param.print_limit = strtod(value, &endptr);
- if (value == endptr)
+ if (value == endptr) {
+ pr_err("Invalid callchain print limit: %s\n", value);
return -1;
+ }
}
return 0;
@@ -437,7 +449,7 @@
}
call->ip = cursor_node->ip;
call->ms.sym = cursor_node->sym;
- call->ms.map = cursor_node->map;
+ call->ms.map = map__get(cursor_node->map);
if (cursor_node->branch) {
call->branch_count = 1;
@@ -477,6 +489,7 @@
list_for_each_entry_safe(call, tmp, &new->val, list) {
list_del(&call->list);
+ map__zput(call->ms.map);
free(call);
}
free(new);
@@ -761,6 +774,7 @@
list->ms.map, list->ms.sym,
false, NULL, 0, 0);
list_del(&list->list);
+ map__zput(list->ms.map);
free(list);
}
@@ -811,7 +825,8 @@
}
node->ip = ip;
- node->map = map;
+ map__zput(node->map);
+ node->map = map__get(map);
node->sym = sym;
node->branch = branch;
node->nr_loop_iter = nr_loop_iter;
@@ -1142,11 +1157,13 @@
list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
list_del(&list->list);
+ map__zput(list->ms.map);
free(list);
}
list_for_each_entry_safe(list, tmp, &node->val, list) {
list_del(&list->list);
+ map__zput(list->ms.map);
free(list);
}
@@ -1210,6 +1227,7 @@
goto out;
*new = *chain;
new->has_children = false;
+ map__get(new->ms.map);
list_add_tail(&new->list, &head);
}
parent = parent->parent;
@@ -1230,6 +1248,7 @@
out:
list_for_each_entry_safe(chain, new, &head, list) {
list_del(&chain->list);
+ map__zput(chain->ms.map);
free(chain);
}
return -ENOMEM;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 35c8e37..4f4b60f 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -5,6 +5,7 @@
#include <linux/list.h>
#include <linux/rbtree.h>
#include "event.h"
+#include "map.h"
#include "symbol.h"
#define HELP_PAD "\t\t\t\t"
@@ -184,8 +185,13 @@
*/
static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
{
+ struct callchain_cursor_node *node;
+
cursor->nr = 0;
cursor->last = &cursor->first;
+
+ for (node = cursor->first; node != NULL; node = node->next)
+ map__zput(node->map);
}
int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 3d906db..0c7d5a4 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -386,8 +386,10 @@
if (!strcmp(var, "buildid.dir")) {
const char *dir = perf_config_dirname(var, value);
- if (!dir)
+ if (!dir) {
+ pr_err("Invalid buildid directory!\n");
return -1;
+ }
strncpy(buildid_dir, dir, MAXPATHLEN-1);
buildid_dir[MAXPATHLEN-1] = '\0';
}
@@ -405,10 +407,9 @@
static int perf_ui_config(const char *var, const char *value)
{
/* Add other config variables here. */
- if (!strcmp(var, "ui.show-headers")) {
+ if (!strcmp(var, "ui.show-headers"))
symbol_conf.show_hist_headers = perf_config_bool(var, value);
- return 0;
- }
+
return 0;
}
@@ -646,8 +647,13 @@
goto out;
}
- if (stat(user_config, &st) < 0)
+ if (stat(user_config, &st) < 0) {
+ if (errno == ENOENT)
+ ret = 0;
goto out_free;
+ }
+
+ ret = 0;
if (st.st_uid && (st.st_uid != geteuid())) {
warning("File %s not owned by current user or root, "
@@ -655,11 +661,8 @@
goto out_free;
}
- if (!st.st_size)
- goto out_free;
-
- ret = perf_config_from_file(collect_config, user_config, set);
-
+ if (st.st_size)
+ ret = perf_config_from_file(collect_config, user_config, set);
out_free:
free(user_config);
}
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 7123f4d..4e6cbc9 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1473,7 +1473,7 @@
},
};
struct ctf_writer *cw = &c.writer;
- int err = -1;
+ int err;
if (opts->all) {
c.tool.comm = process_comm_event;
@@ -1481,12 +1481,15 @@
c.tool.fork = process_fork_event;
}
- perf_config(convert__config, &c);
+ err = perf_config(convert__config, &c);
+ if (err)
+ return err;
/* CTF writer */
if (ctf_writer__init(cw, path))
return -1;
+ err = -1;
/* perf.data session */
session = perf_session__new(&file, 0, &c.tool);
if (!session)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d2c6cdd..28d41e7 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -9,6 +9,13 @@
#include "debug.h"
#include "vdso.h"
+static const char * const debuglink_paths[] = {
+ "%.0s%s",
+ "%s/%s",
+ "%s/.debug/%s",
+ "/usr/lib/debug%s/%s"
+};
+
char dso__symtab_origin(const struct dso *dso)
{
static const char origin[] = {
@@ -44,24 +51,43 @@
size_t len;
switch (type) {
- case DSO_BINARY_TYPE__DEBUGLINK: {
- char *debuglink;
+ case DSO_BINARY_TYPE__DEBUGLINK:
+ {
+ const char *last_slash;
+ char dso_dir[PATH_MAX];
+ char symfile[PATH_MAX];
+ unsigned int i;
len = __symbol__join_symfs(filename, size, dso->long_name);
- debuglink = filename + len;
- while (debuglink != filename && *debuglink != '/')
- debuglink--;
- if (*debuglink == '/')
- debuglink++;
+ last_slash = filename + len;
+ while (last_slash != filename && *last_slash != '/')
+ last_slash--;
- ret = -1;
- if (!is_regular_file(filename))
+ strncpy(dso_dir, filename, last_slash - filename);
+ dso_dir[last_slash-filename] = '\0';
+
+ if (!is_regular_file(filename)) {
+ ret = -1;
+ break;
+ }
+
+ ret = filename__read_debuglink(filename, symfile, PATH_MAX);
+ if (ret)
break;
- ret = filename__read_debuglink(filename, debuglink,
- size - (debuglink - filename));
+ /* Check predefined locations where debug file might reside */
+ ret = -1;
+ for (i = 0; i < ARRAY_SIZE(debuglink_paths); i++) {
+ snprintf(filename, size,
+ debuglink_paths[i], dso_dir, symfile);
+ if (is_regular_file(filename)) {
+ ret = 0;
+ break;
+ }
}
+
break;
+ }
case DSO_BINARY_TYPE__BUILD_ID_CACHE:
if (dso__build_id_filename(dso, filename, size) == NULL)
ret = -1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8ab0d7d..4ea7ce7 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,5 +1,5 @@
#include <linux/types.h>
-#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include <linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
#include <api/fs/fs.h>
#include "event.h"
#include "debug.h"
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d92e020..b601f28 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1184,7 +1184,7 @@
return pages;
}
-static size_t perf_evlist__mmap_size(unsigned long pages)
+size_t perf_evlist__mmap_size(unsigned long pages)
{
if (pages == UINT_MAX)
pages = perf_event_mlock_kb_in_pages();
@@ -1224,12 +1224,16 @@
if (pages == 0 && min == 0) {
/* leave number of pages at 0 */
} else if (!is_power_of_2(pages)) {
+ char buf[100];
+
/* round pages up to next power of 2 */
pages = roundup_pow_of_two(pages);
if (!pages)
return -EINVAL;
- pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
- pages * page_size, pages);
+
+ unit_number__scnprintf(buf, sizeof(buf), pages * page_size);
+ pr_info("rounding mmap pages size to %s (%lu pages)\n",
+ buf, pages);
}
if (pages > max)
@@ -1797,7 +1801,7 @@
*/
ret = write(evlist->workload.cork_fd, &bf, 1);
if (ret < 0)
- perror("enable to write to pipe");
+ perror("unable to write to pipe");
close(evlist->workload.cork_fd);
return ret;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 4fd034f..389b9cc 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -218,6 +218,8 @@
bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
+size_t perf_evlist__mmap_size(unsigned long pages);
+
void perf_evlist__disable(struct perf_evlist *evlist);
void perf_evlist__enable(struct perf_evlist *evlist);
void perf_evlist__toggle_enable(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 04e536a..ac59710 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1448,8 +1448,8 @@
return true;
}
-static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
- struct thread_map *threads)
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+ struct thread_map *threads)
{
int cpu, thread, nthreads;
unsigned long flags = PERF_FLAG_FD_CLOEXEC;
@@ -1459,6 +1459,30 @@
if (perf_missing_features.write_backward && evsel->attr.write_backward)
return -EINVAL;
+ if (cpus == NULL) {
+ static struct cpu_map *empty_cpu_map;
+
+ if (empty_cpu_map == NULL) {
+ empty_cpu_map = cpu_map__dummy_new();
+ if (empty_cpu_map == NULL)
+ return -ENOMEM;
+ }
+
+ cpus = empty_cpu_map;
+ }
+
+ if (threads == NULL) {
+ static struct thread_map *empty_thread_map;
+
+ if (empty_thread_map == NULL) {
+ empty_thread_map = thread_map__new_by_tid(-1);
+ if (empty_thread_map == NULL)
+ return -ENOMEM;
+ }
+
+ threads = empty_thread_map;
+ }
+
if (evsel->system_wide)
nthreads = 1;
else
@@ -1655,46 +1679,16 @@
perf_evsel__free_fd(evsel);
}
-static struct {
- struct cpu_map map;
- int cpus[1];
-} empty_cpu_map = {
- .map.nr = 1,
- .cpus = { -1, },
-};
-
-static struct {
- struct thread_map map;
- int threads[1];
-} empty_thread_map = {
- .map.nr = 1,
- .threads = { -1, },
-};
-
-int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
- struct thread_map *threads)
-{
- if (cpus == NULL) {
- /* Work around old compiler warnings about strict aliasing */
- cpus = &empty_cpu_map.map;
- }
-
- if (threads == NULL)
- threads = &empty_thread_map.map;
-
- return __perf_evsel__open(evsel, cpus, threads);
-}
-
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
struct cpu_map *cpus)
{
- return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
+ return perf_evsel__open(evsel, cpus, NULL);
}
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
struct thread_map *threads)
{
- return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
+ return perf_evsel__open(evsel, NULL, threads);
}
static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
@@ -2469,7 +2463,9 @@
" -1: Allow use of (almost) all events by all users\n"
">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
- ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
+ ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n"
+ "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n"
+ " kernel.perf_event_paranoid = -1\n" ,
target->system_wide ? "system-wide " : "",
perf_event_paranoid());
case ENOENT:
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 6b29255..4ef5184 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -168,7 +168,6 @@
if (symbol_conf.bt_stop_list &&
node->sym &&
- node->sym->name &&
strlist__has_entry(symbol_conf.bt_stop_list,
node->sym->name)) {
break;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d89c9c7..3d12c16 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -41,6 +41,8 @@
#define PERF_MAGIC __perf_magic2
+const char perf_version_string[] = PERF_VERSION;
+
struct perf_file_attr {
struct perf_event_attr attr;
struct perf_file_section ids;
@@ -2801,8 +2803,10 @@
}
event = pevent_find_event(pevent, evsel->attr.config);
- if (event == NULL)
+ if (event == NULL) {
+ pr_debug("cannot find event format for %d\n", (int)evsel->attr.config);
return -1;
+ }
if (!evsel->name) {
snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
@@ -3201,6 +3205,7 @@
case PERF_EVENT_UPDATE__SCALE:
ev_scale = (struct event_update_event_scale *) ev->data;
evsel->scale = ev_scale->scale;
+ break;
case PERF_EVENT_UPDATE__CPUS:
ev_cpus = (struct event_update_event_cpus *) ev->data;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6770a96..32c6a93 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,6 +1,7 @@
#include "util.h"
#include "build-id.h"
#include "hist.h"
+#include "map.h"
#include "session.h"
#include "sort.h"
#include "evlist.h"
@@ -1019,6 +1020,10 @@
int max_stack_depth, void *arg)
{
int err, err2;
+ struct map *alm = NULL;
+
+ if (al && al->map)
+ alm = map__get(al->map);
err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
iter->evsel, al, max_stack_depth);
@@ -1058,6 +1063,8 @@
if (!err)
err = err2;
+ map__put(alm);
+
return err;
}
@@ -2439,8 +2446,10 @@
symbol_conf.filter_relative = true;
else if (!strcmp(arg, "absolute"))
symbol_conf.filter_relative = false;
- else
+ else {
+ pr_debug("Invalud percentage: %s\n", arg);
return -1;
+ }
return 0;
}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d4b6514..28c216e 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -283,6 +283,8 @@
struct perf_hpp_fmt *format);
void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
struct perf_hpp_fmt *format);
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+ struct perf_hpp_fmt *format);
static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
{
@@ -294,6 +296,11 @@
perf_hpp_list__register_sort_field(&perf_hpp_list, format);
}
+static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
+{
+ perf_hpp_list__prepend_sort_field(&perf_hpp_list, format);
+}
+
#define perf_hpp_list__for_each_format(_list, format) \
list_for_each_entry(format, &(_list)->fields, list)
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 9b742ea..7aca5d6 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -23,4 +23,8 @@
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
-CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init
+CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder
+
+ifneq ($(CC), clang)
+ CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init
+endif
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index e4e7dc7..7cf7f7a 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -22,6 +22,7 @@
#include <errno.h>
#include <stdint.h>
#include <inttypes.h>
+#include <linux/compiler.h>
#include "../cache.h"
#include "../util.h"
@@ -1746,6 +1747,7 @@
switch (decoder->packet.type) {
case INTEL_PT_TIP_PGD:
decoder->continuous_period = false;
+ __fallthrough;
case INTEL_PT_TIP_PGE:
case INTEL_PT_TIP:
intel_pt_log("ERROR: Unexpected packet\n");
@@ -1799,6 +1801,8 @@
decoder->pge = false;
decoder->continuous_period = false;
intel_pt_clear_tx_flags(decoder);
+ __fallthrough;
+
case INTEL_PT_TNT:
decoder->have_tma = false;
intel_pt_log("ERROR: Unexpected packet\n");
@@ -1839,6 +1843,7 @@
switch (decoder->packet.type) {
case INTEL_PT_TIP_PGD:
decoder->continuous_period = false;
+ __fallthrough;
case INTEL_PT_TIP_PGE:
case INTEL_PT_TIP:
decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index 4f7b320..7528ae4 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -17,6 +17,7 @@
#include <string.h>
#include <endian.h>
#include <byteswap.h>
+#include <linux/compiler.h>
#include "intel-pt-pkt-decoder.h"
@@ -498,6 +499,7 @@
case INTEL_PT_FUP:
if (!(packet->count))
return snprintf(buf, buf_len, "%s no ip", name);
+ __fallthrough;
case INTEL_PT_CYC:
case INTEL_PT_VMCS:
case INTEL_PT_MTC:
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 85d5eeb..da20cd5 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2159,7 +2159,9 @@
addr_filters__init(&pt->filts);
- perf_config(intel_pt_perf_config, pt);
+ err = perf_config(intel_pt_perf_config, pt);
+ if (err)
+ goto err_free;
err = auxtrace_queues__init(&pt->queues);
if (err)
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index b23ff44..8243564 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -48,8 +48,10 @@
llvm_param.kbuild_opts = strdup(value);
else if (!strcmp(var, "dump-obj"))
llvm_param.dump_obj = !!perf_config_bool(var, value);
- else
+ else {
+ pr_debug("Invalid LLVM config option: %s\n", value);
return -1;
+ }
llvm_param.user_set_param = true;
return 0;
}
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9b33bef..71c9720 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -87,6 +87,25 @@
return NULL;
}
+struct machine *machine__new_kallsyms(void)
+{
+ struct machine *machine = machine__new_host();
+ /*
+ * FIXME:
+ * 1) MAP__FUNCTION will go away when we stop loading separate maps for
+ * functions and data objects.
+ * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely
+ * ask for not using the kcore parsing code, once this one is fixed
+ * to create a map per module.
+ */
+ if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) {
+ machine__delete(machine);
+ machine = NULL;
+ }
+
+ return machine;
+}
+
static void dsos__purge(struct dsos *dsos)
{
struct dso *pos, *n;
@@ -763,7 +782,7 @@
int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
{
- enum map_type type;
+ int type;
u64 start = machine__get_running_kernel_start(machine, NULL);
/* In case of renewal the kernel map, destroy previous one */
@@ -794,7 +813,7 @@
void machine__destroy_kernel_maps(struct machine *machine)
{
- enum map_type type;
+ int type;
for (type = 0; type < MAP__NR_TYPES; ++type) {
struct kmap *kmap;
@@ -1546,7 +1565,7 @@
static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
{
- if (sym->name && !regexec(regex, sym->name, 0, NULL, 0))
+ if (!regexec(regex, sym->name, 0, NULL, 0))
return 1;
return 0;
}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 354de6e..a283050 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -129,6 +129,7 @@
void machines__set_comm_exec(struct machines *machines, bool comm_exec);
struct machine *machine__new_host(void);
+struct machine *machine__new_kallsyms(void);
int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
void machine__exit(struct machine *machine);
void machine__delete_threads(struct machine *machine);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4f9a71c..0a943e7 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -387,10 +387,10 @@
{
const char *dsoname = "[unknown]";
- if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+ if (map && map->dso) {
if (symbol_conf.show_kernel_path && map->dso->long_name)
dsoname = map->dso->long_name;
- else if (map->dso->name)
+ else
dsoname = map->dso->name;
}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 3c876b8..281e44a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -211,6 +211,8 @@
closedir(evt_dir);
closedir(sys_dir);
path = zalloc(sizeof(*path));
+ if (!path)
+ return NULL;
path->system = malloc(MAX_EVENT_LENGTH);
if (!path->system) {
free(path);
@@ -252,8 +254,7 @@
if (path->system == NULL || path->name == NULL) {
zfree(&path->system);
zfree(&path->name);
- free(path);
- path = NULL;
+ zfree(&path);
}
return path;
@@ -310,10 +311,11 @@
event_attr_init(attr);
- evsel = perf_evsel__new_idx(attr, (*idx)++);
+ evsel = perf_evsel__new_idx(attr, *idx);
if (!evsel)
return NULL;
+ (*idx)++;
evsel->cpus = cpu_map__get(cpus);
evsel->own_cpus = cpu_map__get(cpus);
@@ -1477,10 +1479,9 @@
for (i = 0; i < perf_pmu_events_list_num; i++) {
p = perf_pmu_events_list + i;
- free(p->symbol);
+ zfree(&p->symbol);
}
- free(perf_pmu_events_list);
- perf_pmu_events_list = NULL;
+ zfree(&perf_pmu_events_list);
perf_pmu_events_list_num = 0;
}
}
@@ -1504,35 +1505,41 @@
struct perf_pmu_alias *alias;
int len = 0;
- pmu = perf_pmu__find("cpu");
- if ((pmu == NULL) || list_empty(&pmu->aliases)) {
+ pmu = NULL;
+ while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+ list_for_each_entry(alias, &pmu->aliases, list) {
+ if (strchr(alias->name, '-'))
+ len++;
+ len++;
+ }
+ }
+
+ if (len == 0) {
perf_pmu_events_list_num = -1;
return;
}
- list_for_each_entry(alias, &pmu->aliases, list) {
- if (strchr(alias->name, '-'))
- len++;
- len++;
- }
perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len);
if (!perf_pmu_events_list)
return;
perf_pmu_events_list_num = len;
len = 0;
- list_for_each_entry(alias, &pmu->aliases, list) {
- struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
- char *tmp = strchr(alias->name, '-');
+ pmu = NULL;
+ while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+ list_for_each_entry(alias, &pmu->aliases, list) {
+ struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
+ char *tmp = strchr(alias->name, '-');
- if (tmp != NULL) {
- SET_SYMBOL(strndup(alias->name, tmp - alias->name),
- PMU_EVENT_SYMBOL_PREFIX);
- p++;
- SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
- len += 2;
- } else {
- SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
- len++;
+ if (tmp != NULL) {
+ SET_SYMBOL(strndup(alias->name, tmp - alias->name),
+ PMU_EVENT_SYMBOL_PREFIX);
+ p++;
+ SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
+ len += 2;
+ } else {
+ SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
+ len++;
+ }
}
}
qsort(perf_pmu_events_list, len,
@@ -1563,7 +1570,7 @@
r = bsearch(&p, perf_pmu_events_list,
(size_t) perf_pmu_events_list_num,
sizeof(struct perf_pmu_event_symbol), comp_pmu);
- free(p.symbol);
+ zfree(&p.symbol);
return r ? r->type : PMU_EVENT_SYMBOL_ERR;
}
@@ -1710,8 +1717,8 @@
fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str);
if (err->help)
fprintf(stderr, "\n%s\n", err->help);
- free(err->str);
- free(err->help);
+ zfree(&err->str);
+ zfree(&err->help);
}
fprintf(stderr, "Run 'perf list' for a list of valid events\n");
@@ -2013,17 +2020,14 @@
.config = config,
.disabled = 1,
};
- struct {
- struct thread_map map;
- int threads[1];
- } tmap = {
- .map.nr = 1,
- .threads = { 0 },
- };
+ struct thread_map *tmap = thread_map__new_by_tid(0);
+
+ if (tmap == NULL)
+ return false;
evsel = perf_evsel__new(&attr);
if (evsel) {
- open_return = perf_evsel__open(evsel, NULL, &tmap.map);
+ open_return = perf_evsel__open(evsel, NULL, tmap);
ret = open_return >= 0;
if (open_return == -EACCES) {
@@ -2035,7 +2039,7 @@
*
*/
evsel->attr.exclude_kernel = 1;
- ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+ ret = perf_evsel__open(evsel, NULL, tmap) >= 0;
}
perf_evsel__delete(evsel);
}
@@ -2406,7 +2410,7 @@
list_for_each_entry_safe(term, h, terms, list) {
if (term->array.nr_ranges)
- free(term->array.ranges);
+ zfree(&term->array.ranges);
list_del_init(&term->list);
free(term);
}
@@ -2422,7 +2426,7 @@
void parse_events__clear_array(struct parse_events_array *a)
{
- free(a->ranges);
+ zfree(&a->ranges);
}
void parse_events_evlist_error(struct parse_events_evlist *data,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 879115f..a14b47a 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -12,9 +12,13 @@
#include <linux/list.h>
#include <linux/types.h>
#include "util.h"
+#include "pmu.h"
+#include "debug.h"
#include "parse-events.h"
#include "parse-events-bison.h"
+void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg);
+
#define ABORT_ON(val) \
do { \
if (val) \
@@ -236,15 +240,34 @@
struct list_head *head;
struct parse_events_term *term;
struct list_head *list;
+ struct perf_pmu *pmu = NULL;
+ int ok = 0;
- ALLOC_LIST(head);
- ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, 1, &@1, NULL));
- list_add_tail(&term->list, head);
-
+ /* Add it for all PMUs that support the alias */
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
- parse_events_terms__delete(head);
+ while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+ struct perf_pmu_alias *alias;
+
+ list_for_each_entry(alias, &pmu->aliases, list) {
+ if (!strcasecmp(alias->name, $1)) {
+ ALLOC_LIST(head);
+ ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+ $1, 1, &@1, NULL));
+ list_add_tail(&term->list, head);
+
+ if (!parse_events_add_pmu(data, list,
+ pmu->name, head)) {
+ pr_debug("%s -> %s/%s/\n", $1,
+ pmu->name, alias->str);
+ ok++;
+ }
+
+ parse_events_terms__delete(head);
+ }
+ }
+ }
+ if (!ok)
+ YYABORT;
$$ = list;
}
|
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index dc6ccaa..49bfee0 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -94,6 +94,43 @@
return 0;
}
+static int convert_scale(const char *scale, char **end, double *sval)
+{
+ char *lc;
+ int ret = 0;
+
+ /*
+ * save current locale
+ */
+ lc = setlocale(LC_NUMERIC, NULL);
+
+ /*
+ * The lc string may be allocated in static storage,
+ * so get a dynamic copy to make it survive setlocale
+ * call below.
+ */
+ lc = strdup(lc);
+ if (!lc) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * force to C locale to ensure kernel
+ * scale string is converted correctly.
+ * kernel uses default C locale.
+ */
+ setlocale(LC_NUMERIC, "C");
+
+ *sval = strtod(scale, end);
+
+out:
+ /* restore locale */
+ setlocale(LC_NUMERIC, lc);
+ free(lc);
+ return ret;
+}
+
static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
{
struct stat st;
@@ -101,7 +138,6 @@
char scale[128];
int fd, ret = -1;
char path[PATH_MAX];
- char *lc;
snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
@@ -121,37 +157,7 @@
else
scale[sret] = '\0';
- /*
- * save current locale
- */
- lc = setlocale(LC_NUMERIC, NULL);
-
- /*
- * The lc string may be allocated in static storage,
- * so get a dynamic copy to make it survive setlocale
- * call below.
- */
- lc = strdup(lc);
- if (!lc) {
- ret = -ENOMEM;
- goto error;
- }
-
- /*
- * force to C locale to ensure kernel
- * scale string is converted correctly.
- * kernel uses default C locale.
- */
- setlocale(LC_NUMERIC, "C");
-
- alias->scale = strtod(scale, NULL);
-
- /* restore locale */
- setlocale(LC_NUMERIC, lc);
-
- free(lc);
-
- ret = 0;
+ ret = convert_scale(scale, NULL, &alias->scale);
error:
close(fd);
return ret;
@@ -223,11 +229,13 @@
}
static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
- char *desc, char *val, char *long_desc,
- char *topic)
+ char *desc, char *val,
+ char *long_desc, char *topic,
+ char *unit, char *perpkg)
{
struct perf_pmu_alias *alias;
int ret;
+ int num;
alias = malloc(sizeof(*alias));
if (!alias)
@@ -261,6 +269,13 @@
alias->long_desc = long_desc ? strdup(long_desc) :
desc ? strdup(desc) : NULL;
alias->topic = topic ? strdup(topic) : NULL;
+ if (unit) {
+ if (convert_scale(unit, &unit, &alias->scale) < 0)
+ return -1;
+ snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
+ }
+ alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
+ alias->str = strdup(val);
list_add_tail(&alias->list, list);
@@ -278,7 +293,8 @@
buf[ret] = 0;
- return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL);
+ return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
+ NULL);
}
static inline bool pmu_alias_info_file(char *name)
@@ -498,7 +514,7 @@
* to the current running CPU. Then, add all PMU events from that table
* as aliases.
*/
-static void pmu_add_cpu_aliases(struct list_head *head)
+static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
{
int i;
struct pmu_events_map *map;
@@ -534,14 +550,21 @@
*/
i = 0;
while (1) {
+ const char *pname;
+
pe = &map->table[i++];
if (!pe->name)
break;
+ pname = pe->pmu ? pe->pmu : "cpu";
+ if (strncmp(pname, name, strlen(pname)))
+ continue;
+
/* need type casts to override 'const' */
__perf_pmu__new_alias(head, NULL, (char *)pe->name,
(char *)pe->desc, (char *)pe->event,
- (char *)pe->long_desc, (char *)pe->topic);
+ (char *)pe->long_desc, (char *)pe->topic,
+ (char *)pe->unit, (char *)pe->perpkg);
}
out:
@@ -569,15 +592,16 @@
if (pmu_format(name, &format))
return NULL;
- if (pmu_aliases(name, &aliases))
- return NULL;
-
- if (!strcmp(name, "cpu"))
- pmu_add_cpu_aliases(&aliases);
-
+ /*
+ * Check the type first to avoid unnecessary work.
+ */
if (pmu_type(name, &type))
return NULL;
+ if (pmu_aliases(name, &aliases))
+ return NULL;
+
+ pmu_add_cpu_aliases(&aliases, name);
pmu = zalloc(sizeof(*pmu));
if (!pmu)
return NULL;
@@ -921,12 +945,12 @@
* define unit, scale and snapshot, fail
* if there's more than one.
*/
- if ((info->unit && alias->unit) ||
+ if ((info->unit && alias->unit[0]) ||
(info->scale && alias->scale) ||
(info->snapshot && alias->snapshot))
return -EINVAL;
- if (alias->unit)
+ if (alias->unit[0])
info->unit = alias->unit;
if (alias->scale)
@@ -1065,6 +1089,8 @@
char *name;
char *desc;
char *topic;
+ char *str;
+ char *pmu;
};
static int cmp_sevent(const void *a, const void *b)
@@ -1161,6 +1187,8 @@
aliases[j].desc = long_desc ? alias->long_desc :
alias->desc;
aliases[j].topic = alias->topic;
+ aliases[j].str = alias->str;
+ aliases[j].pmu = pmu->name;
j++;
}
if (pmu->selectable &&
@@ -1175,6 +1203,9 @@
len = j;
qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
for (j = 0; j < len; j++) {
+ /* Skip duplicates */
+ if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name))
+ continue;
if (name_only) {
printf("%s ", aliases[j].name);
continue;
@@ -1192,6 +1223,8 @@
printf("%*s", 8, "[");
wordwrap(aliases[j].desc, 8, columns, 0);
printf("]\n");
+ if (verbose)
+ printf("%*s%s/%s/\n", 8, "", aliases[j].pmu, aliases[j].str);
} else
printf(" %-50s [Kernel PMU event]\n", aliases[j].name);
printed++;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 2571203..00852dd 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -43,6 +43,7 @@
char *desc;
char *long_desc;
char *topic;
+ char *str;
struct list_head terms; /* HEAD struct parse_events_term -> list */
struct list_head list; /* ELEM */
char unit[UNIT_MAX_LEN+1];
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d281ae2..35f5b7b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -163,7 +163,7 @@
/* A file path -- this is an offline module */
if (module && strchr(module, '/'))
- return machine__findnew_module_map(host_machine, 0, module);
+ return dso__new_map(module);
if (!module)
module = "kernel";
@@ -173,6 +173,7 @@
if (strncmp(pos->dso->short_name + 1, module,
pos->dso->short_name_len - 2) == 0 &&
module[pos->dso->short_name_len - 2] == '\0') {
+ map__get(pos);
return pos;
}
}
@@ -188,15 +189,6 @@
return kernel_get_module_map(target);
}
-static void put_target_map(struct map *map, bool user)
-{
- if (map && user) {
- /* Only the user map needs to be released */
- map__put(map);
- }
-}
-
-
static int convert_exec_to_group(const char *exec, char **result)
{
char *ptr1, *ptr2, *exec_copy;
@@ -268,21 +260,6 @@
}
/*
- * NOTE:
- * '.gnu.linkonce.this_module' section of kernel module elf directly
- * maps to 'struct module' from linux/module.h. This section contains
- * actual module name which will be used by kernel after loading it.
- * But, we cannot use 'struct module' here since linux/module.h is not
- * exposed to user-space. Offset of 'name' has remained same from long
- * time, so hardcoding it here.
- */
-#ifdef __LP64__
-#define MOD_NAME_OFFSET 24
-#else
-#define MOD_NAME_OFFSET 12
-#endif
-
-/*
* @module can be module name of module file path. In case of path,
* inspect elf and find out what is actual module name.
* Caller has to free mod_name after using it.
@@ -296,6 +273,7 @@
Elf_Data *data;
Elf_Scn *sec;
char *mod_name = NULL;
+ int name_offset;
fd = open(module, O_RDONLY);
if (fd < 0)
@@ -317,7 +295,21 @@
if (!data || !data->d_buf)
goto ret_err;
- mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET);
+ /*
+ * NOTE:
+ * '.gnu.linkonce.this_module' section of kernel module elf directly
+ * maps to 'struct module' from linux/module.h. This section contains
+ * actual module name which will be used by kernel after loading it.
+ * But, we cannot use 'struct module' here since linux/module.h is not
+ * exposed to user-space. Offset of 'name' has remained same from long
+ * time, so hardcoding it here.
+ */
+ if (ehdr.e_ident[EI_CLASS] == ELFCLASS32)
+ name_offset = 12;
+ else /* expect ELFCLASS64 by default */
+ name_offset = 24;
+
+ mod_name = strdup((char *)data->d_buf + name_offset);
ret_err:
elf_end(elf);
@@ -412,7 +404,7 @@
}
out:
- put_target_map(map, uprobes);
+ map__put(map);
return ret;
}
@@ -618,6 +610,67 @@
return ret ? : -ENOENT;
}
+/* Adjust symbol name and address */
+static int post_process_probe_trace_point(struct probe_trace_point *tp,
+ struct map *map, unsigned long offs)
+{
+ struct symbol *sym;
+ u64 addr = tp->address + tp->offset - offs;
+
+ sym = map__find_symbol(map, addr);
+ if (!sym)
+ return -ENOENT;
+
+ if (strcmp(sym->name, tp->symbol)) {
+ /* If we have no realname, use symbol for it */
+ if (!tp->realname)
+ tp->realname = tp->symbol;
+ else
+ free(tp->symbol);
+ tp->symbol = strdup(sym->name);
+ if (!tp->symbol)
+ return -ENOMEM;
+ }
+ tp->offset = addr - sym->start;
+ tp->address -= offs;
+
+ return 0;
+}
+
+/*
+ * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions
+ * and generate new symbols with suffixes such as .constprop.N or .isra.N
+ * etc. Since those symbols are not recorded in DWARF, we have to find
+ * correct generated symbols from offline ELF binary.
+ * For online kernel or uprobes we don't need this because those are
+ * rebased on _text, or already a section relative address.
+ */
+static int
+post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
+ int ntevs, const char *pathname)
+{
+ struct map *map;
+ unsigned long stext = 0;
+ int i, ret = 0;
+
+ /* Prepare a map for offline binary */
+ map = dso__new_map(pathname);
+ if (!map || get_text_start_address(pathname, &stext) < 0) {
+ pr_warning("Failed to get ELF symbols for %s\n", pathname);
+ return -EINVAL;
+ }
+
+ for (i = 0; i < ntevs; i++) {
+ ret = post_process_probe_trace_point(&tevs[i].point,
+ map, stext);
+ if (ret < 0)
+ break;
+ }
+ map__put(map);
+
+ return ret;
+}
+
static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
int ntevs, const char *exec)
{
@@ -645,18 +698,31 @@
return ret;
}
-static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
- int ntevs, const char *module)
+static int
+post_process_module_probe_trace_events(struct probe_trace_event *tevs,
+ int ntevs, const char *module,
+ struct debuginfo *dinfo)
{
+ Dwarf_Addr text_offs = 0;
int i, ret = 0;
char *mod_name = NULL;
+ struct map *map;
if (!module)
return 0;
- mod_name = find_module_name(module);
+ map = get_target_map(module, false);
+ if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) {
+ pr_warning("Failed to get ELF symbols for %s\n", module);
+ return -EINVAL;
+ }
+ mod_name = find_module_name(module);
for (i = 0; i < ntevs; i++) {
+ ret = post_process_probe_trace_point(&tevs[i].point,
+ map, (unsigned long)text_offs);
+ if (ret < 0)
+ break;
tevs[i].point.module =
strdup(mod_name ? mod_name : module);
if (!tevs[i].point.module) {
@@ -666,6 +732,8 @@
}
free(mod_name);
+ map__put(map);
+
return ret;
}
@@ -679,7 +747,8 @@
/* Skip post process if the target is an offline kernel */
if (symbol_conf.ignore_vmlinux_buildid)
- return 0;
+ return post_process_offline_probe_trace_events(tevs, ntevs,
+ symbol_conf.vmlinux_name);
reloc_sym = kernel_get_ref_reloc_sym();
if (!reloc_sym) {
@@ -722,7 +791,7 @@
static int post_process_probe_trace_events(struct perf_probe_event *pev,
struct probe_trace_event *tevs,
int ntevs, const char *module,
- bool uprobe)
+ bool uprobe, struct debuginfo *dinfo)
{
int ret;
@@ -730,7 +799,8 @@
ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
else if (module)
/* Currently ref_reloc_sym based probe is not for drivers */
- ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+ ret = post_process_module_probe_trace_events(tevs, ntevs,
+ module, dinfo);
else
ret = post_process_kernel_probe_trace_events(tevs, ntevs);
@@ -774,30 +844,27 @@
}
}
- debuginfo__delete(dinfo);
-
if (ntevs > 0) { /* Succeeded to find trace events */
pr_debug("Found %d probe_trace_events.\n", ntevs);
ret = post_process_probe_trace_events(pev, *tevs, ntevs,
- pev->target, pev->uprobes);
+ pev->target, pev->uprobes, dinfo);
if (ret < 0 || ret == ntevs) {
+ pr_debug("Post processing failed or all events are skipped. (%d)\n", ret);
clear_probe_trace_events(*tevs, ntevs);
zfree(tevs);
+ ntevs = 0;
}
- if (ret != ntevs)
- return ret < 0 ? ret : ntevs;
- ntevs = 0;
- /* Fall through */
}
+ debuginfo__delete(dinfo);
+
if (ntevs == 0) { /* No error but failed to find probe point. */
pr_warning("Probe point '%s' not found.\n",
synthesize_perf_probe_point(&pev->point));
return -ENOENT;
- }
- /* Error path : ntevs < 0 */
- pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
- if (ntevs < 0) {
+ } else if (ntevs < 0) {
+ /* Error path : ntevs < 0 */
+ pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
if (ntevs == -EBADF)
pr_warning("Warning: No dwarf info found in the vmlinux - "
"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
@@ -1994,7 +2061,7 @@
bool is_kprobe)
{
struct symbol *sym = NULL;
- struct map *map;
+ struct map *map = NULL;
u64 addr = tp->address;
int ret = -ENOENT;
@@ -2869,7 +2936,7 @@
}
out:
- put_target_map(map, pev->uprobes);
+ map__put(map);
free(syms);
return ret;
@@ -2956,20 +3023,17 @@
tev->nargs = pev->nargs;
tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
- if (!tev->args) {
- err = -ENOMEM;
+ if (!tev->args)
goto errout;
- }
+
for (i = 0; i < tev->nargs; i++)
copy_to_probe_trace_arg(&tev->args[i], &pev->args[i]);
return 1;
errout:
- if (*tevs) {
- clear_probe_trace_events(*tevs, 1);
- *tevs = NULL;
- }
+ clear_probe_trace_events(*tevs, 1);
+ *tevs = NULL;
return err;
}
@@ -3362,10 +3426,7 @@
return ret;
/* Get a symbol map */
- if (user)
- map = dso__new_map(target);
- else
- map = kernel_get_module_map(target);
+ map = get_target_map(target, user);
if (!map) {
pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
return -EINVAL;
@@ -3397,9 +3458,7 @@
}
end:
- if (user) {
- map__put(map);
- }
+ map__put(map);
exit_probe_symbol_maps();
return ret;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index df4debe..0d9d6e0 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1501,7 +1501,8 @@
}
/* For the kernel module, we need a special code to get a DIE */
-static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+ bool adjust_offset)
{
int n, i;
Elf32_Word shndx;
@@ -1530,6 +1531,8 @@
if (!shdr)
return -ENOENT;
*offs = shdr->sh_addr;
+ if (adjust_offset)
+ *offs -= shdr->sh_offset;
}
}
return 0;
@@ -1543,16 +1546,12 @@
Dwarf_Addr _addr = 0, baseaddr = 0;
const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
int baseline = 0, lineno = 0, ret = 0;
- bool reloc = false;
-retry:
+ /* We always need to relocate the address for aranges */
+ if (debuginfo__get_text_offset(dbg, &baseaddr, false) == 0)
+ addr += baseaddr;
/* Find cu die */
if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
- if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) {
- addr += baseaddr;
- reloc = true;
- goto retry;
- }
pr_warning("Failed to find debug information for address %lx\n",
addr);
ret = -EINVAL;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index f1d8558..2956c51 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -46,6 +46,9 @@
int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
struct perf_probe_point *ppt);
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+ bool adjust_offset);
+
/* Find a line range */
int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index 6516e22..82d28c6 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -1,6 +1,6 @@
libperf-$(CONFIG_LIBPERL) += trace-event-perl.o
libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o
-CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default
+CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default
CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e55a132..c1555fd 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -309,10 +309,10 @@
if (node->map) {
struct map *map = node->map;
const char *dsoname = "[unknown]";
- if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+ if (map && map->dso) {
if (symbol_conf.show_kernel_path && map->dso->long_name)
dsoname = map->dso->long_name;
- else if (map->dso->name)
+ else
dsoname = map->dso->name;
}
if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) {
@@ -350,8 +350,10 @@
if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
return;
- if (!event)
- die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+ if (!event) {
+ pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+ return;
+ }
pid = raw_field_value(event, "common_pid", data);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f268201..4cdbc8f 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1191,7 +1191,7 @@
u64 sample_type = evsel->attr.sample_type;
u64 read_format = evsel->attr.read_format;
- /* Standard sample delievery. */
+ /* Standard sample delivery. */
if (!(sample_type & PERF_SAMPLE_READ))
return tool->sample(tool, event, sample, evsel, machine);
@@ -1901,7 +1901,7 @@
const char *symbol_name, u64 addr)
{
char *bracket;
- enum map_type i;
+ int i;
struct ref_reloc_sym *ref;
ref = zalloc(sizeof(struct ref_reloc_sym));
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index bcae659..efb5377 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -269,6 +269,7 @@
len = strfilter_node__sprint_pt(node->l, buf);
if (len < 0)
return len;
+ __fallthrough;
case '!':
if (buf) {
*(buf + len++) = *node->p;
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index d8dfaf6..bddca51 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -21,6 +21,8 @@
case 'b': case 'B':
if (*p)
goto out_err;
+
+ __fallthrough;
case '\0':
return length;
default:
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 99400b0..adbc6c0 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -537,6 +537,12 @@
break;
} else {
int n = namesz + descsz;
+
+ if (n > (int)sizeof(bf)) {
+ n = sizeof(bf);
+ pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n",
+ __func__, filename, nhdr.n_namesz, nhdr.n_descsz);
+ }
if (read(fd, bf, n) != n)
break;
}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index dc93940..70e389b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1460,9 +1460,11 @@
* DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
*/
if (!dso->has_build_id &&
- is_regular_file(dso->long_name) &&
- filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
+ is_regular_file(dso->long_name)) {
+ __symbol__join_symfs(name, PATH_MAX, dso->long_name);
+ if (filename__read_build_id(name, build_id, BUILD_ID_SIZE) > 0)
dso__set_build_id(dso, build_id);
+ }
/*
* Iterate over candidate debug images.
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index 7c6b33e..63694e1 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -21,7 +21,7 @@
unsigned long offset;
size_t length;
- if (sym && sym->name) {
+ if (sym) {
length = fprintf(fp, "%s", sym->name);
if (al && print_offsets) {
if (al->addr < sym->end)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index f9eab20..7c3fcc5 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -93,7 +93,7 @@
{
DIR *proc;
int max_threads = 32, items, i;
- char path[256];
+ char path[NAME_MAX + 1 + 6];
struct dirent *dirent, **namelist = NULL;
struct thread_map *threads = thread_map__alloc(max_threads);
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d995743..e7d60d0 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -42,7 +42,7 @@
#include "evsel.h"
#include "debug.h"
-#define VERSION "0.5"
+#define VERSION "0.6"
static int output_fd;
@@ -170,6 +170,12 @@
return false;
}
+#define for_each_event(dir, dent, tps) \
+ while ((dent = readdir(dir))) \
+ if (dent->d_type == DT_DIR && \
+ (strcmp(dent->d_name, ".")) && \
+ (strcmp(dent->d_name, ".."))) \
+
static int copy_event_system(const char *sys, struct tracepoint_path *tps)
{
struct dirent *dent;
@@ -186,12 +192,10 @@
return -errno;
}
- while ((dent = readdir(dir))) {
- if (dent->d_type != DT_DIR ||
- strcmp(dent->d_name, ".") == 0 ||
- strcmp(dent->d_name, "..") == 0 ||
- !name_in_tp_list(dent->d_name, tps))
+ for_each_event(dir, dent, tps) {
+ if (!name_in_tp_list(dent->d_name, tps))
continue;
+
if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
err = -ENOMEM;
goto out;
@@ -210,12 +214,10 @@
}
rewinddir(dir);
- while ((dent = readdir(dir))) {
- if (dent->d_type != DT_DIR ||
- strcmp(dent->d_name, ".") == 0 ||
- strcmp(dent->d_name, "..") == 0 ||
- !name_in_tp_list(dent->d_name, tps))
+ for_each_event(dir, dent, tps) {
+ if (!name_in_tp_list(dent->d_name, tps))
continue;
+
if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
err = -ENOMEM;
goto out;
@@ -290,13 +292,11 @@
goto out;
}
- while ((dent = readdir(dir))) {
- if (dent->d_type != DT_DIR ||
- strcmp(dent->d_name, ".") == 0 ||
- strcmp(dent->d_name, "..") == 0 ||
- strcmp(dent->d_name, "ftrace") == 0 ||
+ for_each_event(dir, dent, tps) {
+ if (strcmp(dent->d_name, "ftrace") == 0 ||
!system_in_tp_list(dent->d_name, tps))
continue;
+
count++;
}
@@ -307,13 +307,11 @@
}
rewinddir(dir);
- while ((dent = readdir(dir))) {
- if (dent->d_type != DT_DIR ||
- strcmp(dent->d_name, ".") == 0 ||
- strcmp(dent->d_name, "..") == 0 ||
- strcmp(dent->d_name, "ftrace") == 0 ||
+ for_each_event(dir, dent, tps) {
+ if (strcmp(dent->d_name, "ftrace") == 0 ||
!system_in_tp_list(dent->d_name, tps))
continue;
+
if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) {
err = -ENOMEM;
goto out;
@@ -379,6 +377,34 @@
return err;
}
+static int record_saved_cmdline(void)
+{
+ unsigned int size;
+ char *path;
+ struct stat st;
+ int ret, err = 0;
+
+ path = get_tracing_file("saved_cmdlines");
+ if (!path) {
+ pr_debug("can't get tracing/saved_cmdline");
+ return -ENOMEM;
+ }
+
+ ret = stat(path, &st);
+ if (ret < 0) {
+ /* not found */
+ size = 0;
+ if (write(output_fd, &size, 8) != 8)
+ err = -EIO;
+ goto out;
+ }
+ err = record_file(path, 8);
+
+out:
+ put_tracing_file(path);
+ return err;
+}
+
static void
put_tracepoints_path(struct tracepoint_path *tps)
{
@@ -539,6 +565,9 @@
if (err)
goto out;
err = record_ftrace_printk();
+ if (err)
+ goto out;
+ err = record_saved_cmdline();
out:
/*
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 33b52ea..de0078e 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -160,6 +160,23 @@
}
}
+void parse_saved_cmdline(struct pevent *pevent,
+ char *file, unsigned int size __maybe_unused)
+{
+ char *comm;
+ char *line;
+ char *next = NULL;
+ int pid;
+
+ line = strtok_r(file, "\n", &next);
+ while (line) {
+ sscanf(line, "%d %ms", &pid, &comm);
+ pevent_register_comm(pevent, comm, pid);
+ free(comm);
+ line = strtok_r(NULL, "\n", &next);
+ }
+}
+
int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size)
{
return pevent_parse_event(pevent, buf, size, "ftrace");
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index b67a0cc..2742015 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -260,39 +260,53 @@
static int read_ftrace_file(struct pevent *pevent, unsigned long long size)
{
+ int ret;
char *buf;
buf = malloc(size);
- if (buf == NULL)
- return -1;
-
- if (do_read(buf, size) < 0) {
- free(buf);
+ if (buf == NULL) {
+ pr_debug("memory allocation failure\n");
return -1;
}
- parse_ftrace_file(pevent, buf, size);
+ ret = do_read(buf, size);
+ if (ret < 0) {
+ pr_debug("error reading ftrace file.\n");
+ goto out;
+ }
+
+ ret = parse_ftrace_file(pevent, buf, size);
+ if (ret < 0)
+ pr_debug("error parsing ftrace file.\n");
+out:
free(buf);
- return 0;
+ return ret;
}
static int read_event_file(struct pevent *pevent, char *sys,
unsigned long long size)
{
+ int ret;
char *buf;
buf = malloc(size);
- if (buf == NULL)
- return -1;
-
- if (do_read(buf, size) < 0) {
- free(buf);
+ if (buf == NULL) {
+ pr_debug("memory allocation failure\n");
return -1;
}
- parse_event_file(pevent, buf, size, sys);
+ ret = do_read(buf, size);
+ if (ret < 0) {
+ free(buf);
+ goto out;
+ }
+
+ ret = parse_event_file(pevent, buf, size, sys);
+ if (ret < 0)
+ pr_debug("error parsing event file.\n");
+out:
free(buf);
- return 0;
+ return ret;
}
static int read_ftrace_files(struct pevent *pevent)
@@ -341,6 +355,36 @@
return 0;
}
+static int read_saved_cmdline(struct pevent *pevent)
+{
+ unsigned long long size;
+ char *buf;
+ int ret;
+
+ /* it can have 0 size */
+ size = read8(pevent);
+ if (!size)
+ return 0;
+
+ buf = malloc(size + 1);
+ if (buf == NULL) {
+ pr_debug("memory allocation failure\n");
+ return -1;
+ }
+
+ ret = do_read(buf, size);
+ if (ret < 0) {
+ pr_debug("error reading saved cmdlines\n");
+ goto out;
+ }
+
+ parse_saved_cmdline(pevent, buf, size);
+ ret = 0;
+out:
+ free(buf);
+ return ret;
+}
+
ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
{
char buf[BUFSIZ];
@@ -379,10 +423,11 @@
return -1;
if (show_version)
printf("version = %s\n", version);
- free(version);
- if (do_read(buf, 1) < 0)
+ if (do_read(buf, 1) < 0) {
+ free(version);
return -1;
+ }
file_bigendian = buf[0];
host_bigendian = bigendian();
@@ -423,6 +468,11 @@
err = read_ftrace_printk(pevent);
if (err)
goto out;
+ if (atof(version) >= 0.6) {
+ err = read_saved_cmdline(pevent);
+ if (err)
+ goto out;
+ }
size = trace_data_size;
repipe = false;
@@ -438,5 +488,6 @@
out:
if (pevent)
trace_event__cleanup(tevent);
+ free(version);
return size;
}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b0af9c8..1fbc044 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -42,6 +42,7 @@
void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
+void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size);
ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6fec84d..bfb9b79 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -35,6 +35,7 @@
#include "util.h"
#include "debug.h"
#include "asm/bug.h"
+#include "dso.h"
extern int
UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
@@ -297,15 +298,58 @@
int fd;
u64 ofs = dso->data.debug_frame_offset;
+ /* debug_frame can reside in:
+ * - dso
+ * - debug pointed by symsrc_filename
+ * - gnu_debuglink, which doesn't necessary
+ * has to be pointed by symsrc_filename
+ */
if (ofs == 0) {
fd = dso__data_get_fd(dso, machine);
- if (fd < 0)
- return -EINVAL;
+ if (fd >= 0) {
+ ofs = elf_section_offset(fd, ".debug_frame");
+ dso__data_put_fd(dso);
+ }
- /* Check the .debug_frame section for unwinding info */
- ofs = elf_section_offset(fd, ".debug_frame");
+ if (ofs <= 0) {
+ fd = open(dso->symsrc_filename, O_RDONLY);
+ if (fd >= 0) {
+ ofs = elf_section_offset(fd, ".debug_frame");
+ close(fd);
+ }
+ }
+
+ if (ofs <= 0) {
+ char *debuglink = malloc(PATH_MAX);
+ int ret = 0;
+
+ ret = dso__read_binary_type_filename(
+ dso, DSO_BINARY_TYPE__DEBUGLINK,
+ machine->root_dir, debuglink, PATH_MAX);
+ if (!ret) {
+ fd = open(debuglink, O_RDONLY);
+ if (fd >= 0) {
+ ofs = elf_section_offset(fd,
+ ".debug_frame");
+ close(fd);
+ }
+ }
+ if (ofs > 0) {
+ if (dso->symsrc_filename != NULL) {
+ pr_warning(
+ "%s: overwrite symsrc(%s,%s)\n",
+ __func__,
+ dso->symsrc_filename,
+ debuglink);
+ free(dso->symsrc_filename);
+ }
+ dso->symsrc_filename = debuglink;
+ } else {
+ free(debuglink);
+ }
+ }
+
dso->data.debug_frame_offset = ofs;
- dso__data_put_fd(dso);
}
*offset = ofs;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9ddd988..d8b45ce 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -85,7 +85,7 @@
return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
}
-int rm_rf(char *path)
+int rm_rf(const char *path)
{
DIR *dir;
int ret = 0;
@@ -789,3 +789,16 @@
}
return 1;
}
+
+int unit_number__scnprintf(char *buf, size_t size, u64 n)
+{
+ char unit[4] = "BKMG";
+ int i = 0;
+
+ while (((n / 1024) > 1) && (i < 3)) {
+ n /= 1024;
+ i++;
+ }
+
+ return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1d639e3..c74708d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -209,7 +209,7 @@
}
int mkdir_p(char *path, mode_t mode);
-int rm_rf(char *path);
+int rm_rf(const char *path);
struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *));
bool lsdir_no_dot_filter(const char *name, struct dirent *d);
int copyfile(const char *from, const char *to);
@@ -363,4 +363,5 @@
int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
+int unit_number__scnprintf(char *buf, size_t size, u64 n);
#endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 8abbef1..621578a 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -32,7 +32,6 @@
EXTRA_WARNINGS += -Wpacked
EXTRA_WARNINGS += -Wredundant-decls
EXTRA_WARNINGS += -Wshadow
-EXTRA_WARNINGS += -Wstrict-aliasing=3
EXTRA_WARNINGS += -Wstrict-prototypes
EXTRA_WARNINGS += -Wswitch-default
EXTRA_WARNINGS += -Wswitch-enum
@@ -40,12 +39,26 @@
EXTRA_WARNINGS += -Wwrite-strings
EXTRA_WARNINGS += -Wformat
+ifneq ($(CC), clang)
+EXTRA_WARNINGS += -Wstrict-aliasing=3
+endif
+
ifneq ($(findstring $(MAKEFLAGS), w),w)
PRINT_DIR = --no-print-directory
else
NO_SUBDIR = :
endif
+ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4
+ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
+ silent=1
+endif
+else # make-3.8x
+ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
+ silent=1
+endif
+endif
+
#
# Define a callable command for descending to a new directory
#
@@ -58,7 +71,7 @@
QUIET_SUBDIR0 = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir
QUIET_SUBDIR1 =
-ifneq ($(findstring $(MAKEFLAGS),s),s)
+ifneq ($(silent),1)
ifneq ($(V),1)
QUIET_CC = @echo ' CC '$@;
QUIET_CC_FPIC = @echo ' CC FPIC '$@;
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index b13fed5..9f7bd19 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -67,21 +67,23 @@
return map_subset(lru_map, expected) && map_subset(expected, lru_map);
}
-static int sched_next_online(int pid, int next_to_try)
+static int sched_next_online(int pid, int *next_to_try)
{
cpu_set_t cpuset;
+ int next = *next_to_try;
+ int ret = -1;
- if (next_to_try == nr_cpus)
- return -1;
-
- while (next_to_try < nr_cpus) {
+ while (next < nr_cpus) {
CPU_ZERO(&cpuset);
- CPU_SET(next_to_try++, &cpuset);
- if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset))
+ CPU_SET(next++, &cpuset);
+ if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) {
+ ret = 0;
break;
+ }
}
- return next_to_try;
+ *next_to_try = next;
+ return ret;
}
/* Size of the LRU amp is 2
@@ -96,11 +98,12 @@
{
unsigned long long key, value[nr_cpus];
int lru_map_fd, expected_map_fd;
+ int next_cpu = 0;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
- assert(sched_next_online(0, 0) != -1);
+ assert(sched_next_online(0, &next_cpu) != -1);
if (map_flags & BPF_F_NO_COMMON_LRU)
lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus);
@@ -183,6 +186,7 @@
int lru_map_fd, expected_map_fd;
unsigned int batch_size;
unsigned int map_size;
+ int next_cpu = 0;
if (map_flags & BPF_F_NO_COMMON_LRU)
/* Ther percpu lru list (i.e each cpu has its own LRU
@@ -196,7 +200,7 @@
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
- assert(sched_next_online(0, 0) != -1);
+ assert(sched_next_online(0, &next_cpu) != -1);
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
@@ -262,6 +266,7 @@
int lru_map_fd, expected_map_fd;
unsigned int batch_size;
unsigned int map_size;
+ int next_cpu = 0;
if (map_flags & BPF_F_NO_COMMON_LRU)
/* Ther percpu lru list (i.e each cpu has its own LRU
@@ -275,7 +280,7 @@
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
- assert(sched_next_online(0, 0) != -1);
+ assert(sched_next_online(0, &next_cpu) != -1);
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
@@ -370,11 +375,12 @@
int lru_map_fd, expected_map_fd;
unsigned int batch_size;
unsigned int map_size;
+ int next_cpu = 0;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
- assert(sched_next_online(0, 0) != -1);
+ assert(sched_next_online(0, &next_cpu) != -1);
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
@@ -430,11 +436,12 @@
int lru_map_fd, expected_map_fd;
unsigned long long key, value[nr_cpus];
unsigned long long end_key;
+ int next_cpu = 0;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
- assert(sched_next_online(0, 0) != -1);
+ assert(sched_next_online(0, &next_cpu) != -1);
if (map_flags & BPF_F_NO_COMMON_LRU)
lru_map_fd = create_map(map_type, map_flags,
@@ -502,9 +509,8 @@
static void test_lru_sanity5(int map_type, int map_flags)
{
unsigned long long key, value[nr_cpus];
- int next_sched_cpu = 0;
+ int next_cpu = 0;
int map_fd;
- int i;
if (map_flags & BPF_F_NO_COMMON_LRU)
return;
@@ -519,27 +525,20 @@
key = 0;
assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
- for (i = 0; i < nr_cpus; i++) {
+ while (sched_next_online(0, &next_cpu) != -1) {
pid_t pid;
pid = fork();
if (pid == 0) {
- next_sched_cpu = sched_next_online(0, next_sched_cpu);
- if (next_sched_cpu != -1)
- do_test_lru_sanity5(key, map_fd);
+ do_test_lru_sanity5(key, map_fd);
exit(0);
} else if (pid == -1) {
- printf("couldn't spawn #%d process\n", i);
+ printf("couldn't spawn process to test key:%llu\n",
+ key);
exit(1);
} else {
int status;
- /* It is mostly redundant and just allow the parent
- * process to update next_shced_cpu for the next child
- * process
- */
- next_sched_cpu = sched_next_online(pid, next_sched_cpu);
-
assert(waitpid(pid, &status, 0) == pid);
assert(status == 0);
key++;
@@ -547,6 +546,8 @@
}
close(map_fd);
+ /* At least one key should be tested */
+ assert(key > 0);
printf("Pass\n");
}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index c22860a..30e1ac6 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -66,7 +66,7 @@
FAIL_IF(ebb_event_enable(&event));
- mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+ mtspr(SPRN_PMC2, pmc_sample_period(sample_period));
mtspr(SPRN_PMC5, 0);
mtspr(SPRN_PMC6, 0);
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
index f824b4c..d2d2a86 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
@@ -1,5 +1,2 @@
CONFIG_RCU_TORTURE_TEST=y
CONFIG_PRINTK_TIME=y
-CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
-CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
-CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
index 0a63e07..6db705e 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
@@ -7,6 +7,7 @@
CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
CONFIG_RCU_TRACE=n
+#CHECK#CONFIG_RCU_STALL_COMMON=n
CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_PREEMPT_COUNT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
index f1892e0..a59f768 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
@@ -8,7 +8,8 @@
CONFIG_NO_HZ_FULL=n
CONFIG_RCU_TRACE=y
CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU_REPEATEDLY=y
#CHECK#CONFIG_PROVE_RCU=y
CONFIG_DEBUG_LOCK_ALLOC=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
CONFIG_PREEMPT_COUNT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index f572b87..359cb25 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -16,3 +16,6 @@
CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index ef6a22c..c1ab592 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -20,3 +20,7 @@
CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
index 7a17c50..3b93ee5 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
@@ -17,3 +17,6 @@
CONFIG_RCU_KTHREAD_PRIO=2
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 17cbe09..5af758e 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -19,3 +19,7 @@
CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
+CONFIG_RCU_EQS_DEBUG=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index 1257d32..d4cdc0d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -19,3 +19,6 @@
#CHECK#CONFIG_PROVE_RCU=y
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index d3e456b..4cb02bd 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -20,3 +20,6 @@
#CHECK#CONFIG_PROVE_RCU=y
CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index 3956b41..b12a3ea 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -19,3 +19,6 @@
CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index bb9b0c1..099cc63 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -17,8 +17,8 @@
CONFIG_RCU_NOCB_CPU=y
CONFIG_RCU_NOCB_CPU_ALL=y
CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_LOCKING=y
-#CHECK#CONFIG_PROVE_RCU=y
+CONFIG_PROVE_LOCKING=n
CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
+CONFIG_RCU_EQS_DEBUG=y
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index 4e2b189..364801b 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -14,6 +14,7 @@
CONFIG_PREEMPT -- Do half. (First three and #8.)
CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not.
CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING.
+CONFIG_PROVE_RCU_REPEATEDLY -- Do one.
CONFIG_RCU_BOOST -- one of PREEMPT_RCU.
CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing.
CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others.
@@ -25,7 +26,12 @@
CONFIG_RCU_NOCB_CPU_ZERO -- Do one.
CONFIG_RCU_TRACE -- Do half.
CONFIG_SMP -- Need one !SMP for PREEMPT_RCU.
-!RCU_EXPERT -- Do a few, but these have to be vanilla configurations.
+CONFIG_RCU_EXPERT=n -- Do a few, but these have to be vanilla configurations.
+CONFIG_RCU_EQS_DEBUG -- Do at least one for CONFIG_NO_HZ_FULL and not.
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP -- Do for all but a couple TREE scenarios.
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT -- Do for all but a couple TREE scenarios.
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT -- Do for all but a couple TREE scenarios.
+
RCU-bh: Do one with PREEMPT and one with !PREEMPT.
RCU-sched: Do one with PREEMPT but not BOOST.
@@ -72,7 +78,30 @@
Always used in KVM testing.
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY
+
+ Inspection suffices, ignore.
+
CONFIG_PREEMPT_RCU
CONFIG_TREE_RCU
+CONFIG_TINY_RCU
- These are controlled by CONFIG_PREEMPT.
+ These are controlled by CONFIG_PREEMPT and/or CONFIG_SMP.
+
+CONFIG_SPARSE_RCU_POINTER
+
+ Makes sense only for sparse runs, not for kernel builds.
+
+CONFIG_SRCU
+CONFIG_TASKS_RCU
+
+ Selected by CONFIG_RCU_TORTURE_TEST, so cannot disable.
+
+CONFIG_RCU_TRACE
+
+ Implied by CONFIG_RCU_TRACE for Tree RCU.
+
+
+boot parameters ignored: TBD
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore
new file mode 100644
index 0000000..712a3d4
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore
@@ -0,0 +1 @@
+srcu.c
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile
new file mode 100644
index 0000000..16b0155
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile
@@ -0,0 +1,16 @@
+all: srcu.c store_buffering
+
+LINUX_SOURCE = ../../../../../..
+
+modified_srcu_input = $(LINUX_SOURCE)/include/linux/srcu.h \
+ $(LINUX_SOURCE)/kernel/rcu/srcu.c
+
+modified_srcu_output = include/linux/srcu.h srcu.c
+
+include/linux/srcu.h: srcu.c
+
+srcu.c: modify_srcu.awk Makefile $(modified_srcu_input)
+ awk -f modify_srcu.awk $(modified_srcu_input) $(modified_srcu_output)
+
+store_buffering:
+ @cd tests/store_buffering; make
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore
new file mode 100644
index 0000000..1d016e6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore
@@ -0,0 +1 @@
+srcu.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h
new file mode 100644
index 0000000..f2860dd
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h
@@ -0,0 +1 @@
+#include <LINUX_SOURCE/linux/kconfig.h>
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
new file mode 100644
index 0000000..4a3d538
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
@@ -0,0 +1,155 @@
+/*
+ * This header has been modifies to remove definitions of types that
+ * are defined in standard userspace headers or are problematic for some
+ * other reason.
+ */
+
+#ifndef _LINUX_TYPES_H
+#define _LINUX_TYPES_H
+
+#define __EXPORTED_HEADERS__
+#include <uapi/linux/types.h>
+
+#ifndef __ASSEMBLY__
+
+#define DECLARE_BITMAP(name, bits) \
+ unsigned long name[BITS_TO_LONGS(bits)]
+
+typedef __u32 __kernel_dev_t;
+
+/* bsd */
+typedef unsigned char u_char;
+typedef unsigned short u_short;
+typedef unsigned int u_int;
+typedef unsigned long u_long;
+
+/* sysv */
+typedef unsigned char unchar;
+typedef unsigned short ushort;
+typedef unsigned int uint;
+typedef unsigned long ulong;
+
+#ifndef __BIT_TYPES_DEFINED__
+#define __BIT_TYPES_DEFINED__
+
+typedef __u8 u_int8_t;
+typedef __s8 int8_t;
+typedef __u16 u_int16_t;
+typedef __s16 int16_t;
+typedef __u32 u_int32_t;
+typedef __s32 int32_t;
+
+#endif /* !(__BIT_TYPES_DEFINED__) */
+
+typedef __u8 uint8_t;
+typedef __u16 uint16_t;
+typedef __u32 uint32_t;
+
+/* this is a special 64bit data type that is 8-byte aligned */
+#define aligned_u64 __u64 __attribute__((aligned(8)))
+#define aligned_be64 __be64 __attribute__((aligned(8)))
+#define aligned_le64 __le64 __attribute__((aligned(8)))
+
+/**
+ * The type used for indexing onto a disc or disc partition.
+ *
+ * Linux always considers sectors to be 512 bytes long independently
+ * of the devices real block size.
+ *
+ * blkcnt_t is the type of the inode's block count.
+ */
+#ifdef CONFIG_LBDAF
+typedef u64 sector_t;
+#else
+typedef unsigned long sector_t;
+#endif
+
+/*
+ * The type of an index into the pagecache.
+ */
+#define pgoff_t unsigned long
+
+/*
+ * A dma_addr_t can hold any valid DMA address, i.e., any address returned
+ * by the DMA API.
+ *
+ * If the DMA API only uses 32-bit addresses, dma_addr_t need only be 32
+ * bits wide. Bus addresses, e.g., PCI BARs, may be wider than 32 bits,
+ * but drivers do memory-mapped I/O to ioremapped kernel virtual addresses,
+ * so they don't care about the size of the actual bus addresses.
+ */
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+typedef u64 dma_addr_t;
+#else
+typedef u32 dma_addr_t;
+#endif
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+typedef u64 phys_addr_t;
+#else
+typedef u32 phys_addr_t;
+#endif
+
+typedef phys_addr_t resource_size_t;
+
+/*
+ * This type is the placeholder for a hardware interrupt number. It has to be
+ * big enough to enclose whatever representation is used by a given platform.
+ */
+typedef unsigned long irq_hw_number_t;
+
+typedef struct {
+ int counter;
+} atomic_t;
+
+#ifdef CONFIG_64BIT
+typedef struct {
+ long counter;
+} atomic64_t;
+#endif
+
+struct list_head {
+ struct list_head *next, *prev;
+};
+
+struct hlist_head {
+ struct hlist_node *first;
+};
+
+struct hlist_node {
+ struct hlist_node *next, **pprev;
+};
+
+/**
+ * struct callback_head - callback structure for use with RCU and task_work
+ * @next: next update requests in a list
+ * @func: actual update function to call after the grace period.
+ *
+ * The struct is aligned to size of pointer. On most architectures it happens
+ * naturally due ABI requirements, but some architectures (like CRIS) have
+ * weird ABI and we need to ask it explicitly.
+ *
+ * The alignment is required to guarantee that bits 0 and 1 of @next will be
+ * clear under normal conditions -- as long as we use call_rcu(),
+ * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback.
+ *
+ * This guarantee is important for few reasons:
+ * - future call_rcu_lazy() will make use of lower bits in the pointer;
+ * - the structure shares storage spacer in struct page with @compound_head,
+ * which encode PageTail() in bit 0. The guarantee is needed to avoid
+ * false-positive PageTail().
+ */
+struct callback_head {
+ struct callback_head *next;
+ void (*func)(struct callback_head *head);
+} __attribute__((aligned(sizeof(void *))));
+#define rcu_head callback_head
+
+typedef void (*rcu_callback_t)(struct rcu_head *head);
+typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func);
+
+/* clocksource cycle base type */
+typedef u64 cycle_t;
+
+#endif /* __ASSEMBLY__ */
+#endif /* _LINUX_TYPES_H */
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
new file mode 100755
index 0000000..8ff8904
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
@@ -0,0 +1,375 @@
+#!/bin/awk -f
+
+# Modify SRCU for formal verification. The first argument should be srcu.h and
+# the second should be srcu.c. Outputs modified srcu.h and srcu.c into the
+# current directory.
+
+BEGIN {
+ if (ARGC != 5) {
+ print "Usange: input.h input.c output.h output.c" > "/dev/stderr";
+ exit 1;
+ }
+ h_output = ARGV[3];
+ c_output = ARGV[4];
+ ARGC = 3;
+
+ # Tokenize using FS and not RS as FS supports regular expressions. Each
+ # record is one line of source, except that backslashed lines are
+ # combined. Comments are treated as field separators, as are quotes.
+ quote_regexp="\"([^\\\\\"]|\\\\.)*\"";
+ comment_regexp="\\/\\*([^*]|\\*+[^*/])*\\*\\/|\\/\\/.*(\n|$)";
+ FS="([ \\\\\t\n\v\f;,.=(){}+*/<>&|^-]|\\[|\\]|" comment_regexp "|" quote_regexp ")+";
+
+ inside_srcu_struct = 0;
+ inside_srcu_init_def = 0;
+ srcu_init_param_name = "";
+ in_macro = 0;
+ brace_nesting = 0;
+ paren_nesting = 0;
+
+ # Allow the manipulation of the last field separator after has been
+ # seen.
+ last_fs = "";
+ # Whether the last field separator was intended to be output.
+ last_fs_print = 0;
+
+ # rcu_batches stores the initialization for each instance of struct
+ # rcu_batch
+
+ in_comment = 0;
+
+ outputfile = "";
+}
+
+{
+ prev_outputfile = outputfile;
+ if (FILENAME ~ /\.h$/) {
+ outputfile = h_output;
+ if (FNR != NR) {
+ print "Incorrect file order" > "/dev/stderr";
+ exit 1;
+ }
+ }
+ else
+ outputfile = c_output;
+
+ if (prev_outputfile && outputfile != prev_outputfile) {
+ new_outputfile = outputfile;
+ outputfile = prev_outputfile;
+ update_fieldsep("", 0);
+ outputfile = new_outputfile;
+ }
+}
+
+# Combine the next line into $0.
+function combine_line() {
+ ret = getline next_line;
+ if (ret == 0) {
+ # Don't allow two consecutive getlines at the end of the file
+ if (eof_found) {
+ print "Error: expected more input." > "/dev/stderr";
+ exit 1;
+ } else {
+ eof_found = 1;
+ }
+ } else if (ret == -1) {
+ print "Error reading next line of file" FILENAME > "/dev/stderr";
+ exit 1;
+ }
+ $0 = $0 "\n" next_line;
+}
+
+# Combine backslashed lines and multiline comments.
+function combine_backslashes() {
+ while (/\\$|\/\*([^*]|\*+[^*\/])*\**$/) {
+ combine_line();
+ }
+}
+
+function read_line() {
+ combine_line();
+ combine_backslashes();
+}
+
+# Print out field separators and update variables that depend on them. Only
+# print if p is true. Call with sep="" and p=0 to print out the last field
+# separator.
+function update_fieldsep(sep, p) {
+ # Count braces
+ sep_tmp = sep;
+ gsub(quote_regexp "|" comment_regexp, "", sep_tmp);
+ while (1)
+ {
+ if (sub("[^{}()]*\\{", "", sep_tmp)) {
+ brace_nesting++;
+ continue;
+ }
+ if (sub("[^{}()]*\\}", "", sep_tmp)) {
+ brace_nesting--;
+ if (brace_nesting < 0) {
+ print "Unbalanced braces!" > "/dev/stderr";
+ exit 1;
+ }
+ continue;
+ }
+ if (sub("[^{}()]*\\(", "", sep_tmp)) {
+ paren_nesting++;
+ continue;
+ }
+ if (sub("[^{}()]*\\)", "", sep_tmp)) {
+ paren_nesting--;
+ if (paren_nesting < 0) {
+ print "Unbalanced parenthesis!" > "/dev/stderr";
+ exit 1;
+ }
+ continue;
+ }
+
+ break;
+ }
+
+ if (last_fs_print)
+ printf("%s", last_fs) > outputfile;
+ last_fs = sep;
+ last_fs_print = p;
+}
+
+# Shifts the fields down by n positions. Calls next if there are no more. If p
+# is true then print out field separators.
+function shift_fields(n, p) {
+ do {
+ if (match($0, FS) > 0) {
+ update_fieldsep(substr($0, RSTART, RLENGTH), p);
+ if (RSTART + RLENGTH <= length())
+ $0 = substr($0, RSTART + RLENGTH);
+ else
+ $0 = "";
+ } else {
+ update_fieldsep("", 0);
+ print "" > outputfile;
+ next;
+ }
+ } while (--n > 0);
+}
+
+# Shifts and prints the first n fields.
+function print_fields(n) {
+ do {
+ update_fieldsep("", 0);
+ printf("%s", $1) > outputfile;
+ shift_fields(1, 1);
+ } while (--n > 0);
+}
+
+{
+ combine_backslashes();
+}
+
+# Print leading FS
+{
+ if (match($0, "^(" FS ")+") > 0) {
+ update_fieldsep(substr($0, RSTART, RLENGTH), 1);
+ if (RSTART + RLENGTH <= length())
+ $0 = substr($0, RSTART + RLENGTH);
+ else
+ $0 = "";
+ }
+}
+
+# Parse the line.
+{
+ while (NF > 0) {
+ if ($1 == "struct" && NF < 3) {
+ read_line();
+ continue;
+ }
+
+ if (FILENAME ~ /\.h$/ && !inside_srcu_struct &&
+ brace_nesting == 0 && paren_nesting == 0 &&
+ $1 == "struct" && $2 == "srcu_struct" &&
+ $0 ~ "^struct(" FS ")+srcu_struct(" FS ")+\\{") {
+ inside_srcu_struct = 1;
+ print_fields(2);
+ continue;
+ }
+ if (inside_srcu_struct && brace_nesting == 0 &&
+ paren_nesting == 0) {
+ inside_srcu_struct = 0;
+ update_fieldsep("", 0);
+ for (name in rcu_batches)
+ print "extern struct rcu_batch " name ";" > outputfile;
+ }
+
+ if (inside_srcu_struct && $1 == "struct" && $2 == "rcu_batch") {
+ # Move rcu_batches outside of the struct.
+ rcu_batches[$3] = "";
+ shift_fields(3, 1);
+ sub(/;[[:space:]]*$/, "", last_fs);
+ continue;
+ }
+
+ if (FILENAME ~ /\.h$/ && !inside_srcu_init_def &&
+ $1 == "#define" && $2 == "__SRCU_STRUCT_INIT") {
+ inside_srcu_init_def = 1;
+ srcu_init_param_name = $3;
+ in_macro = 1;
+ print_fields(3);
+ continue;
+ }
+ if (inside_srcu_init_def && brace_nesting == 0 &&
+ paren_nesting == 0) {
+ inside_srcu_init_def = 0;
+ in_macro = 0;
+ continue;
+ }
+
+ if (inside_srcu_init_def && brace_nesting == 1 &&
+ paren_nesting == 0 && last_fs ~ /\.[[:space:]]*$/ &&
+ $1 ~ /^[[:alnum:]_]+$/) {
+ name = $1;
+ if (name in rcu_batches) {
+ # Remove the dot.
+ sub(/\.[[:space:]]*$/, "", last_fs);
+
+ old_record = $0;
+ do
+ shift_fields(1, 0);
+ while (last_fs !~ /,/ || paren_nesting > 0);
+ end_loc = length(old_record) - length($0);
+ end_loc += index(last_fs, ",") - length(last_fs);
+
+ last_fs = substr(last_fs, index(last_fs, ",") + 1);
+ last_fs_print = 1;
+
+ match(old_record, "^"name"("FS")+=");
+ start_loc = RSTART + RLENGTH;
+
+ len = end_loc - start_loc;
+ initializer = substr(old_record, start_loc, len);
+ gsub(srcu_init_param_name "\\.", "", initializer);
+ rcu_batches[name] = initializer;
+ continue;
+ }
+ }
+
+ # Don't include a nonexistent file
+ if (!in_macro && $1 == "#include" && /^#include[[:space:]]+"rcu\.h"/) {
+ update_fieldsep("", 0);
+ next;
+ }
+
+ # Ignore most preprocessor stuff.
+ if (!in_macro && $1 ~ /#/) {
+ break;
+ }
+
+ if (brace_nesting > 0 && $1 ~ "^[[:alnum:]_]+$" && NF < 2) {
+ read_line();
+ continue;
+ }
+ if (brace_nesting > 0 &&
+ $0 ~ "^[[:alnum:]_]+[[:space:]]*(\\.|->)[[:space:]]*[[:alnum:]_]+" &&
+ $2 in rcu_batches) {
+ # Make uses of rcu_batches global. Somewhat unreliable.
+ shift_fields(1, 0);
+ print_fields(1);
+ continue;
+ }
+
+ if ($1 == "static" && NF < 3) {
+ read_line();
+ continue;
+ }
+ if ($1 == "static" && ($2 == "bool" && $3 == "try_check_zero" ||
+ $2 == "void" && $3 == "srcu_flip")) {
+ shift_fields(1, 1);
+ print_fields(2);
+ continue;
+ }
+
+ # Distinguish between read-side and write-side memory barriers.
+ if ($1 == "smp_mb" && NF < 2) {
+ read_line();
+ continue;
+ }
+ if (match($0, /^smp_mb[[:space:]();\/*]*[[:alnum:]]/)) {
+ barrier_letter = substr($0, RLENGTH, 1);
+ if (barrier_letter ~ /A|D/)
+ new_barrier_name = "sync_smp_mb";
+ else if (barrier_letter ~ /B|C/)
+ new_barrier_name = "rs_smp_mb";
+ else {
+ print "Unrecognized memory barrier." > "/dev/null";
+ exit 1;
+ }
+
+ shift_fields(1, 1);
+ printf("%s", new_barrier_name) > outputfile;
+ continue;
+ }
+
+ # Skip definition of rcu_synchronize, since it is already
+ # defined in misc.h. Only present in old versions of srcu.
+ if (brace_nesting == 0 && paren_nesting == 0 &&
+ $1 == "struct" && $2 == "rcu_synchronize" &&
+ $0 ~ "^struct(" FS ")+rcu_synchronize(" FS ")+\\{") {
+ shift_fields(2, 0);
+ while (brace_nesting) {
+ if (NF < 2)
+ read_line();
+ shift_fields(1, 0);
+ }
+ }
+
+ # Skip definition of wakeme_after_rcu for the same reason
+ if (brace_nesting == 0 && $1 == "static" && $2 == "void" &&
+ $3 == "wakeme_after_rcu") {
+ while (NF < 5)
+ read_line();
+ shift_fields(3, 0);
+ do {
+ while (NF < 3)
+ read_line();
+ shift_fields(1, 0);
+ } while (paren_nesting || brace_nesting);
+ }
+
+ if ($1 ~ /^(unsigned|long)$/ && NF < 3) {
+ read_line();
+ continue;
+ }
+
+ # Give srcu_batches_completed the correct type for old SRCU.
+ if (brace_nesting == 0 && $1 == "long" &&
+ $2 == "srcu_batches_completed") {
+ update_fieldsep("", 0);
+ printf("unsigned ") > outputfile;
+ print_fields(2);
+ continue;
+ }
+ if (brace_nesting == 0 && $1 == "unsigned" && $2 == "long" &&
+ $3 == "srcu_batches_completed") {
+ print_fields(3);
+ continue;
+ }
+
+ # Just print out the input code by default.
+ print_fields(1);
+ }
+ update_fieldsep("", 0);
+ print > outputfile;
+ next;
+}
+
+END {
+ update_fieldsep("", 0);
+
+ if (brace_nesting != 0) {
+ print "Unbalanced braces!" > "/dev/stderr";
+ exit 1;
+ }
+
+ # Define the rcu_batches
+ for (name in rcu_batches)
+ print "struct rcu_batch " name " = " rcu_batches[name] ";" > c_output;
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h
new file mode 100644
index 0000000..a649554
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h
@@ -0,0 +1,16 @@
+#ifndef ASSUME_H
+#define ASSUME_H
+
+/* Provide an assumption macro that can be disabled for gcc. */
+#ifdef RUN
+#define assume(x) \
+ do { \
+ /* Evaluate x to suppress warnings. */ \
+ (void) (x); \
+ } while (0)
+
+#else
+#define assume(x) __CPROVER_assume(x)
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
new file mode 100644
index 0000000..6687acc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
@@ -0,0 +1,41 @@
+#ifndef BARRIERS_H
+#define BARRIERS_H
+
+#define barrier() __asm__ __volatile__("" : : : "memory")
+
+#ifdef RUN
+#define smp_mb() __sync_synchronize()
+#define smp_mb__after_unlock_lock() __sync_synchronize()
+#else
+/*
+ * Copied from CBMC's implementation of __sync_synchronize(), which
+ * seems to be disabled by default.
+ */
+#define smp_mb() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \
+ "WWcumul", "RRcumul", "RWcumul", "WRcumul")
+#define smp_mb__after_unlock_lock() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \
+ "WWcumul", "RRcumul", "RWcumul", "WRcumul")
+#endif
+
+/*
+ * Allow memory barriers to be disabled in either the read or write side
+ * of SRCU individually.
+ */
+
+#ifndef NO_SYNC_SMP_MB
+#define sync_smp_mb() smp_mb()
+#else
+#define sync_smp_mb() do {} while (0)
+#endif
+
+#ifndef NO_READ_SIDE_SMP_MB
+#define rs_smp_mb() smp_mb()
+#else
+#define rs_smp_mb() do {} while (0)
+#endif
+
+#define ACCESS_ONCE(x) (*(volatile typeof(x) *) &(x))
+#define READ_ONCE(x) ACCESS_ONCE(x)
+#define WRITE_ONCE(x, val) (ACCESS_ONCE(x) = (val))
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h
new file mode 100644
index 0000000..2a80e91
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h
@@ -0,0 +1,13 @@
+#ifndef BUG_ON_H
+#define BUG_ON_H
+
+#include <assert.h>
+
+#define BUG() assert(0)
+#define BUG_ON(x) assert(!(x))
+
+/* Does it make sense to treat warnings as errors? */
+#define WARN() BUG()
+#define WARN_ON(x) (BUG_ON(x), false)
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c
new file mode 100644
index 0000000..29eb5d26
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c
@@ -0,0 +1,13 @@
+#include <config.h>
+
+/* Include all source files. */
+
+#include "include_srcu.c"
+
+#include "preempt.c"
+#include "misc.c"
+
+/* Used by test.c files */
+#include <pthread.h>
+#include <stdlib.h>
+#include <linux/srcu.h>
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h
new file mode 100644
index 0000000..a60038a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h
@@ -0,0 +1,27 @@
+/* "Cheater" definitions based on restricted Kconfig choices. */
+
+#undef CONFIG_TINY_RCU
+#undef __CHECKER__
+#undef CONFIG_DEBUG_LOCK_ALLOC
+#undef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+#undef CONFIG_HOTPLUG_CPU
+#undef CONFIG_MODULES
+#undef CONFIG_NO_HZ_FULL_SYSIDLE
+#undef CONFIG_PREEMPT_COUNT
+#undef CONFIG_PREEMPT_RCU
+#undef CONFIG_PROVE_RCU
+#undef CONFIG_RCU_NOCB_CPU
+#undef CONFIG_RCU_NOCB_CPU_ALL
+#undef CONFIG_RCU_STALL_COMMON
+#undef CONFIG_RCU_TRACE
+#undef CONFIG_RCU_USER_QS
+#undef CONFIG_TASKS_RCU
+#define CONFIG_TREE_RCU
+
+#define CONFIG_GENERIC_ATOMIC64
+
+#if NR_CPUS > 1
+#define CONFIG_SMP
+#else
+#undef CONFIG_SMP
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c
new file mode 100644
index 0000000..5ec582a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c
@@ -0,0 +1,31 @@
+#include <config.h>
+
+#include <assert.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <pthread.h>
+#include <stddef.h>
+#include <string.h>
+#include <sys/types.h>
+
+#include "int_typedefs.h"
+
+#include "barriers.h"
+#include "bug_on.h"
+#include "locks.h"
+#include "misc.h"
+#include "preempt.h"
+#include "percpu.h"
+#include "workqueues.h"
+
+#ifdef USE_SIMPLE_SYNC_SRCU
+#define synchronize_srcu(sp) synchronize_srcu_original(sp)
+#endif
+
+#include <srcu.c>
+
+#ifdef USE_SIMPLE_SYNC_SRCU
+#undef synchronize_srcu
+
+#include "simple_sync_srcu.c"
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h
new file mode 100644
index 0000000..3aad639
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h
@@ -0,0 +1,33 @@
+#ifndef INT_TYPEDEFS_H
+#define INT_TYPEDEFS_H
+
+#include <inttypes.h>
+
+typedef int8_t s8;
+typedef uint8_t u8;
+typedef int16_t s16;
+typedef uint16_t u16;
+typedef int32_t s32;
+typedef uint32_t u32;
+typedef int64_t s64;
+typedef uint64_t u64;
+
+typedef int8_t __s8;
+typedef uint8_t __u8;
+typedef int16_t __s16;
+typedef uint16_t __u16;
+typedef int32_t __s32;
+typedef uint32_t __u32;
+typedef int64_t __s64;
+typedef uint64_t __u64;
+
+#define S8_C(x) INT8_C(x)
+#define U8_C(x) UINT8_C(x)
+#define S16_C(x) INT16_C(x)
+#define U16_C(x) UINT16_C(x)
+#define S32_C(x) INT32_C(x)
+#define U32_C(x) UINT32_C(x)
+#define S64_C(x) INT64_C(x)
+#define U64_C(x) UINT64_C(x)
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h
new file mode 100644
index 0000000..3560046
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h
@@ -0,0 +1,220 @@
+#ifndef LOCKS_H
+#define LOCKS_H
+
+#include <limits.h>
+#include <pthread.h>
+#include <stdbool.h>
+
+#include "assume.h"
+#include "bug_on.h"
+#include "preempt.h"
+
+int nondet_int(void);
+
+#define __acquire(x)
+#define __acquires(x)
+#define __release(x)
+#define __releases(x)
+
+/* Only use one lock mechanism. Select which one. */
+#ifdef PTHREAD_LOCK
+struct lock_impl {
+ pthread_mutex_t mutex;
+};
+
+static inline void lock_impl_lock(struct lock_impl *lock)
+{
+ BUG_ON(pthread_mutex_lock(&lock->mutex));
+}
+
+static inline void lock_impl_unlock(struct lock_impl *lock)
+{
+ BUG_ON(pthread_mutex_unlock(&lock->mutex));
+}
+
+static inline bool lock_impl_trylock(struct lock_impl *lock)
+{
+ int err = pthread_mutex_trylock(&lock->mutex);
+
+ if (!err)
+ return true;
+ else if (err == EBUSY)
+ return false;
+ BUG();
+}
+
+static inline void lock_impl_init(struct lock_impl *lock)
+{
+ pthread_mutex_init(&lock->mutex, NULL);
+}
+
+#define LOCK_IMPL_INITIALIZER {.mutex = PTHREAD_MUTEX_INITIALIZER}
+
+#else /* !defined(PTHREAD_LOCK) */
+/* Spinlock that assumes that it always gets the lock immediately. */
+
+struct lock_impl {
+ bool locked;
+};
+
+static inline bool lock_impl_trylock(struct lock_impl *lock)
+{
+#ifdef RUN
+ /* TODO: Should this be a test and set? */
+ return __sync_bool_compare_and_swap(&lock->locked, false, true);
+#else
+ __CPROVER_atomic_begin();
+ bool old_locked = lock->locked;
+ lock->locked = true;
+ __CPROVER_atomic_end();
+
+ /* Minimal barrier to prevent accesses leaking out of lock. */
+ __CPROVER_fence("RRfence", "RWfence");
+
+ return !old_locked;
+#endif
+}
+
+static inline void lock_impl_lock(struct lock_impl *lock)
+{
+ /*
+ * CBMC doesn't support busy waiting, so just assume that the
+ * lock is available.
+ */
+ assume(lock_impl_trylock(lock));
+
+ /*
+ * If the lock was already held by this thread then the assumption
+ * is unsatisfiable (deadlock).
+ */
+}
+
+static inline void lock_impl_unlock(struct lock_impl *lock)
+{
+#ifdef RUN
+ BUG_ON(!__sync_bool_compare_and_swap(&lock->locked, true, false));
+#else
+ /* Minimal barrier to prevent accesses leaking out of lock. */
+ __CPROVER_fence("RWfence", "WWfence");
+
+ __CPROVER_atomic_begin();
+ bool old_locked = lock->locked;
+ lock->locked = false;
+ __CPROVER_atomic_end();
+
+ BUG_ON(!old_locked);
+#endif
+}
+
+static inline void lock_impl_init(struct lock_impl *lock)
+{
+ lock->locked = false;
+}
+
+#define LOCK_IMPL_INITIALIZER {.locked = false}
+
+#endif /* !defined(PTHREAD_LOCK) */
+
+/*
+ * Implement spinlocks using the lock mechanism. Wrap the lock to prevent mixing
+ * locks of different types.
+ */
+typedef struct {
+ struct lock_impl internal_lock;
+} spinlock_t;
+
+#define SPIN_LOCK_UNLOCKED {.internal_lock = LOCK_IMPL_INITIALIZER}
+#define __SPIN_LOCK_UNLOCKED(x) SPIN_LOCK_UNLOCKED
+#define DEFINE_SPINLOCK(x) spinlock_t x = SPIN_LOCK_UNLOCKED
+
+static inline void spin_lock_init(spinlock_t *lock)
+{
+ lock_impl_init(&lock->internal_lock);
+}
+
+static inline void spin_lock(spinlock_t *lock)
+{
+ /*
+ * Spin locks also need to be removed in order to eliminate all
+ * memory barriers. They are only used by the write side anyway.
+ */
+#ifndef NO_SYNC_SMP_MB
+ preempt_disable();
+ lock_impl_lock(&lock->internal_lock);
+#endif
+}
+
+static inline void spin_unlock(spinlock_t *lock)
+{
+#ifndef NO_SYNC_SMP_MB
+ lock_impl_unlock(&lock->internal_lock);
+ preempt_enable();
+#endif
+}
+
+/* Don't bother with interrupts */
+#define spin_lock_irq(lock) spin_lock(lock)
+#define spin_unlock_irq(lock) spin_unlock(lock)
+#define spin_lock_irqsave(lock, flags) spin_lock(lock)
+#define spin_unlock_irqrestore(lock, flags) spin_unlock(lock)
+
+/*
+ * This is supposed to return an int, but I think that a bool should work as
+ * well.
+ */
+static inline bool spin_trylock(spinlock_t *lock)
+{
+#ifndef NO_SYNC_SMP_MB
+ preempt_disable();
+ return lock_impl_trylock(&lock->internal_lock);
+#else
+ return true;
+#endif
+}
+
+struct completion {
+ /* Hopefuly this won't overflow. */
+ unsigned int count;
+};
+
+#define COMPLETION_INITIALIZER(x) {.count = 0}
+#define DECLARE_COMPLETION(x) struct completion x = COMPLETION_INITIALIZER(x)
+#define DECLARE_COMPLETION_ONSTACK(x) DECLARE_COMPLETION(x)
+
+static inline void init_completion(struct completion *c)
+{
+ c->count = 0;
+}
+
+static inline void wait_for_completion(struct completion *c)
+{
+ unsigned int prev_count = __sync_fetch_and_sub(&c->count, 1);
+
+ assume(prev_count);
+}
+
+static inline void complete(struct completion *c)
+{
+ unsigned int prev_count = __sync_fetch_and_add(&c->count, 1);
+
+ BUG_ON(prev_count == UINT_MAX);
+}
+
+/* This function probably isn't very useful for CBMC. */
+static inline bool try_wait_for_completion(struct completion *c)
+{
+ BUG();
+}
+
+static inline bool completion_done(struct completion *c)
+{
+ return c->count;
+}
+
+/* TODO: Implement complete_all */
+static inline void complete_all(struct completion *c)
+{
+ BUG();
+}
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c
new file mode 100644
index 0000000..ca892e3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c
@@ -0,0 +1,11 @@
+#include <config.h>
+
+#include "misc.h"
+#include "bug_on.h"
+
+struct rcu_head;
+
+void wakeme_after_rcu(struct rcu_head *head)
+{
+ BUG();
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h
new file mode 100644
index 0000000..aca5003
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h
@@ -0,0 +1,58 @@
+#ifndef MISC_H
+#define MISC_H
+
+#include "assume.h"
+#include "int_typedefs.h"
+#include "locks.h"
+
+#include <linux/types.h>
+
+/* Probably won't need to deal with bottom halves. */
+static inline void local_bh_disable(void) {}
+static inline void local_bh_enable(void) {}
+
+#define MODULE_ALIAS(X)
+#define module_param(...)
+#define EXPORT_SYMBOL_GPL(x)
+
+#define container_of(ptr, type, member) ({ \
+ const typeof(((type *)0)->member) *__mptr = (ptr); \
+ (type *)((char *)__mptr - offsetof(type, member)); \
+})
+
+#ifndef USE_SIMPLE_SYNC_SRCU
+/* Abuse udelay to make sure that busy loops terminate. */
+#define udelay(x) assume(0)
+
+#else
+
+/* The simple custom synchronize_srcu is ok with try_check_zero failing. */
+#define udelay(x) do { } while (0)
+#endif
+
+#define trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
+ do { } while (0)
+
+#define notrace
+
+/* Avoid including rcupdate.h */
+struct rcu_synchronize {
+ struct rcu_head head;
+ struct completion completion;
+};
+
+void wakeme_after_rcu(struct rcu_head *head);
+
+#define rcu_lock_acquire(a) do { } while (0)
+#define rcu_lock_release(a) do { } while (0)
+#define rcu_lockdep_assert(c, s) do { } while (0)
+#define RCU_LOCKDEP_WARN(c, s) do { } while (0)
+
+/* Let CBMC non-deterministically choose switch between normal and expedited. */
+bool rcu_gp_is_normal(void);
+bool rcu_gp_is_expedited(void);
+
+/* Do the same for old versions of rcu. */
+#define rcu_expedited (rcu_gp_is_expedited())
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h
new file mode 100644
index 0000000..3de5a49
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h
@@ -0,0 +1,92 @@
+#ifndef PERCPU_H
+#define PERCPU_H
+
+#include <stddef.h>
+#include "bug_on.h"
+#include "preempt.h"
+
+#define __percpu
+
+/* Maximum size of any percpu data. */
+#define PERCPU_OFFSET (4 * sizeof(long))
+
+/* Ignore alignment, as CBMC doesn't care about false sharing. */
+#define alloc_percpu(type) __alloc_percpu(sizeof(type), 1)
+
+static inline void *__alloc_percpu(size_t size, size_t align)
+{
+ BUG();
+ return NULL;
+}
+
+static inline void free_percpu(void *ptr)
+{
+ BUG();
+}
+
+#define per_cpu_ptr(ptr, cpu) \
+ ((typeof(ptr)) ((char *) (ptr) + PERCPU_OFFSET * cpu))
+
+#define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1)
+#define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1)
+#define __this_cpu_sub(pcp, n) __this_cpu_add(pcp, -(typeof(pcp)) (n))
+
+#define this_cpu_inc(pcp) this_cpu_add(pcp, 1)
+#define this_cpu_dec(pcp) this_cpu_sub(pcp, 1)
+#define this_cpu_sub(pcp, n) this_cpu_add(pcp, -(typeof(pcp)) (n))
+
+/* Make CBMC use atomics to work around bug. */
+#ifdef RUN
+#define THIS_CPU_ADD_HELPER(ptr, x) (*(ptr) += (x))
+#else
+/*
+ * Split the atomic into a read and a write so that it has the least
+ * possible ordering.
+ */
+#define THIS_CPU_ADD_HELPER(ptr, x) \
+ do { \
+ typeof(ptr) this_cpu_add_helper_ptr = (ptr); \
+ typeof(ptr) this_cpu_add_helper_x = (x); \
+ typeof(*ptr) this_cpu_add_helper_temp; \
+ __CPROVER_atomic_begin(); \
+ this_cpu_add_helper_temp = *(this_cpu_add_helper_ptr); \
+ __CPROVER_atomic_end(); \
+ this_cpu_add_helper_temp += this_cpu_add_helper_x; \
+ __CPROVER_atomic_begin(); \
+ *(this_cpu_add_helper_ptr) = this_cpu_add_helper_temp; \
+ __CPROVER_atomic_end(); \
+ } while (0)
+#endif
+
+/*
+ * For some reason CBMC needs an atomic operation even though this is percpu
+ * data.
+ */
+#define __this_cpu_add(pcp, n) \
+ do { \
+ BUG_ON(preemptible()); \
+ THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), thread_cpu_id), \
+ (typeof(pcp)) (n)); \
+ } while (0)
+
+#define this_cpu_add(pcp, n) \
+ do { \
+ int this_cpu_add_impl_cpu = get_cpu(); \
+ THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), this_cpu_add_impl_cpu), \
+ (typeof(pcp)) (n)); \
+ put_cpu(); \
+ } while (0)
+
+/*
+ * This will cause a compiler warning because of the cast from char[][] to
+ * type*. This will cause a compile time error if type is too big.
+ */
+#define DEFINE_PER_CPU(type, name) \
+ char name[NR_CPUS][PERCPU_OFFSET]; \
+ typedef char percpu_too_big_##name \
+ [sizeof(type) > PERCPU_OFFSET ? -1 : 1]
+
+#define for_each_possible_cpu(cpu) \
+ for ((cpu) = 0; (cpu) < NR_CPUS; ++(cpu))
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c
new file mode 100644
index 0000000..4f1b068
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c
@@ -0,0 +1,78 @@
+#include <config.h>
+
+#include "preempt.h"
+
+#include "assume.h"
+#include "locks.h"
+
+/* Support NR_CPUS of at most 64 */
+#define CPU_PREEMPTION_LOCKS_INIT0 LOCK_IMPL_INITIALIZER
+#define CPU_PREEMPTION_LOCKS_INIT1 \
+ CPU_PREEMPTION_LOCKS_INIT0, CPU_PREEMPTION_LOCKS_INIT0
+#define CPU_PREEMPTION_LOCKS_INIT2 \
+ CPU_PREEMPTION_LOCKS_INIT1, CPU_PREEMPTION_LOCKS_INIT1
+#define CPU_PREEMPTION_LOCKS_INIT3 \
+ CPU_PREEMPTION_LOCKS_INIT2, CPU_PREEMPTION_LOCKS_INIT2
+#define CPU_PREEMPTION_LOCKS_INIT4 \
+ CPU_PREEMPTION_LOCKS_INIT3, CPU_PREEMPTION_LOCKS_INIT3
+#define CPU_PREEMPTION_LOCKS_INIT5 \
+ CPU_PREEMPTION_LOCKS_INIT4, CPU_PREEMPTION_LOCKS_INIT4
+
+/*
+ * Simulate disabling preemption by locking a particular cpu. NR_CPUS
+ * should be the actual number of cpus, not just the maximum.
+ */
+struct lock_impl cpu_preemption_locks[NR_CPUS] = {
+ CPU_PREEMPTION_LOCKS_INIT0
+#if (NR_CPUS - 1) & 1
+ , CPU_PREEMPTION_LOCKS_INIT0
+#endif
+#if (NR_CPUS - 1) & 2
+ , CPU_PREEMPTION_LOCKS_INIT1
+#endif
+#if (NR_CPUS - 1) & 4
+ , CPU_PREEMPTION_LOCKS_INIT2
+#endif
+#if (NR_CPUS - 1) & 8
+ , CPU_PREEMPTION_LOCKS_INIT3
+#endif
+#if (NR_CPUS - 1) & 16
+ , CPU_PREEMPTION_LOCKS_INIT4
+#endif
+#if (NR_CPUS - 1) & 32
+ , CPU_PREEMPTION_LOCKS_INIT5
+#endif
+};
+
+#undef CPU_PREEMPTION_LOCKS_INIT0
+#undef CPU_PREEMPTION_LOCKS_INIT1
+#undef CPU_PREEMPTION_LOCKS_INIT2
+#undef CPU_PREEMPTION_LOCKS_INIT3
+#undef CPU_PREEMPTION_LOCKS_INIT4
+#undef CPU_PREEMPTION_LOCKS_INIT5
+
+__thread int thread_cpu_id;
+__thread int preempt_disable_count;
+
+void preempt_disable(void)
+{
+ BUG_ON(preempt_disable_count < 0 || preempt_disable_count == INT_MAX);
+
+ if (preempt_disable_count++)
+ return;
+
+ thread_cpu_id = nondet_int();
+ assume(thread_cpu_id >= 0);
+ assume(thread_cpu_id < NR_CPUS);
+ lock_impl_lock(&cpu_preemption_locks[thread_cpu_id]);
+}
+
+void preempt_enable(void)
+{
+ BUG_ON(preempt_disable_count < 1);
+
+ if (--preempt_disable_count)
+ return;
+
+ lock_impl_unlock(&cpu_preemption_locks[thread_cpu_id]);
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h
new file mode 100644
index 0000000..2f95ee0
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h
@@ -0,0 +1,58 @@
+#ifndef PREEMPT_H
+#define PREEMPT_H
+
+#include <stdbool.h>
+
+#include "bug_on.h"
+
+/* This flag contains garbage if preempt_disable_count is 0. */
+extern __thread int thread_cpu_id;
+
+/* Support recursive preemption disabling. */
+extern __thread int preempt_disable_count;
+
+void preempt_disable(void);
+void preempt_enable(void);
+
+static inline void preempt_disable_notrace(void)
+{
+ preempt_disable();
+}
+
+static inline void preempt_enable_no_resched(void)
+{
+ preempt_enable();
+}
+
+static inline void preempt_enable_notrace(void)
+{
+ preempt_enable();
+}
+
+static inline int preempt_count(void)
+{
+ return preempt_disable_count;
+}
+
+static inline bool preemptible(void)
+{
+ return !preempt_count();
+}
+
+static inline int get_cpu(void)
+{
+ preempt_disable();
+ return thread_cpu_id;
+}
+
+static inline void put_cpu(void)
+{
+ preempt_enable();
+}
+
+static inline void might_sleep(void)
+{
+ BUG_ON(preempt_disable_count);
+}
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c
new file mode 100644
index 0000000..ac9cbc6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c
@@ -0,0 +1,50 @@
+#include <config.h>
+
+#include <assert.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <pthread.h>
+#include <stddef.h>
+#include <string.h>
+#include <sys/types.h>
+
+#include "int_typedefs.h"
+
+#include "barriers.h"
+#include "bug_on.h"
+#include "locks.h"
+#include "misc.h"
+#include "preempt.h"
+#include "percpu.h"
+#include "workqueues.h"
+
+#include <linux/srcu.h>
+
+/* Functions needed from modify_srcu.c */
+bool try_check_zero(struct srcu_struct *sp, int idx, int trycount);
+void srcu_flip(struct srcu_struct *sp);
+
+/* Simpler implementation of synchronize_srcu that ignores batching. */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+ int idx;
+ /*
+ * This code assumes that try_check_zero will succeed anyway,
+ * so there is no point in multiple tries.
+ */
+ const int trycount = 1;
+
+ might_sleep();
+
+ /* Ignore the lock, as multiple writers aren't working yet anyway. */
+
+ idx = 1 ^ (sp->completed & 1);
+
+ /* For comments see srcu_advance_batches. */
+
+ assume(try_check_zero(sp, idx, trycount));
+
+ srcu_flip(sp);
+
+ assume(try_check_zero(sp, idx^1, trycount));
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h
new file mode 100644
index 0000000..e58c8df
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h
@@ -0,0 +1,102 @@
+#ifndef WORKQUEUES_H
+#define WORKQUEUES_H
+
+#include <stdbool.h>
+
+#include "barriers.h"
+#include "bug_on.h"
+#include "int_typedefs.h"
+
+#include <linux/types.h>
+
+/* Stub workqueue implementation. */
+
+struct work_struct;
+typedef void (*work_func_t)(struct work_struct *work);
+void delayed_work_timer_fn(unsigned long __data);
+
+struct work_struct {
+/* atomic_long_t data; */
+ unsigned long data;
+
+ struct list_head entry;
+ work_func_t func;
+#ifdef CONFIG_LOCKDEP
+ struct lockdep_map lockdep_map;
+#endif
+};
+
+struct timer_list {
+ struct hlist_node entry;
+ unsigned long expires;
+ void (*function)(unsigned long);
+ unsigned long data;
+ u32 flags;
+ int slack;
+};
+
+struct delayed_work {
+ struct work_struct work;
+ struct timer_list timer;
+
+ /* target workqueue and CPU ->timer uses to queue ->work */
+ struct workqueue_struct *wq;
+ int cpu;
+};
+
+
+static inline bool schedule_work(struct work_struct *work)
+{
+ BUG();
+ return true;
+}
+
+static inline bool schedule_work_on(int cpu, struct work_struct *work)
+{
+ BUG();
+ return true;
+}
+
+static inline bool queue_work(struct workqueue_struct *wq,
+ struct work_struct *work)
+{
+ BUG();
+ return true;
+}
+
+static inline bool queue_delayed_work(struct workqueue_struct *wq,
+ struct delayed_work *dwork,
+ unsigned long delay)
+{
+ BUG();
+ return true;
+}
+
+#define INIT_WORK(w, f) \
+ do { \
+ (w)->data = 0; \
+ (w)->func = (f); \
+ } while (0)
+
+#define INIT_DELAYED_WORK(w, f) INIT_WORK(&(w)->work, (f))
+
+#define __WORK_INITIALIZER(n, f) { \
+ .data = 0, \
+ .entry = { &(n).entry, &(n).entry }, \
+ .func = f \
+ }
+
+/* Don't bother initializing timer. */
+#define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \
+ .work = __WORK_INITIALIZER((n).work, (f)), \
+ }
+
+#define DECLARE_WORK(n, f) \
+ struct workqueue_struct n = __WORK_INITIALIZER
+
+#define DECLARE_DELAYED_WORK(n, f) \
+ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0)
+
+#define system_power_efficient_wq ((struct workqueue_struct *) NULL)
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore
new file mode 100644
index 0000000..f47cb20
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore
@@ -0,0 +1 @@
+*.out
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile
new file mode 100644
index 0000000..3a3aee1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile
@@ -0,0 +1,11 @@
+CBMC_FLAGS = -I../.. -I../../src -I../../include -I../../empty_includes -32 -pointer-check -mm pso
+
+all:
+ for i in ./*.pass; do \
+ echo $$i ; \
+ CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-pass $$i > $$i.out 2>&1 ; \
+ done
+ for i in ./*.fail; do \
+ echo $$i ; \
+ CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-fail $$i > $$i.out 2>&1 ; \
+ done
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail
new file mode 100644
index 0000000..40c8075
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail
@@ -0,0 +1 @@
+test_cbmc_options="-DASSERT_END"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail
new file mode 100644
index 0000000..ada5baf
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail
@@ -0,0 +1 @@
+test_cbmc_options="-DFORCE_FAILURE"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail
new file mode 100644
index 0000000..8fe00c8
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail
@@ -0,0 +1 @@
+test_cbmc_options="-DFORCE_FAILURE_2"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail
new file mode 100644
index 0000000..612ed67
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail
@@ -0,0 +1 @@
+test_cbmc_options="-DFORCE_FAILURE_3"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c
new file mode 100644
index 0000000..470b110
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c
@@ -0,0 +1,72 @@
+#include <src/combined_source.c>
+
+int x;
+int y;
+
+int __unbuffered_tpr_x;
+int __unbuffered_tpr_y;
+
+DEFINE_SRCU(ss);
+
+void rcu_reader(void)
+{
+ int idx;
+
+#ifndef FORCE_FAILURE_3
+ idx = srcu_read_lock(&ss);
+#endif
+ might_sleep();
+
+ __unbuffered_tpr_y = READ_ONCE(y);
+#ifdef FORCE_FAILURE
+ srcu_read_unlock(&ss, idx);
+ idx = srcu_read_lock(&ss);
+#endif
+ WRITE_ONCE(x, 1);
+
+#ifndef FORCE_FAILURE_3
+ srcu_read_unlock(&ss, idx);
+#endif
+ might_sleep();
+}
+
+void *thread_update(void *arg)
+{
+ WRITE_ONCE(y, 1);
+#ifndef FORCE_FAILURE_2
+ synchronize_srcu(&ss);
+#endif
+ might_sleep();
+ __unbuffered_tpr_x = READ_ONCE(x);
+
+ return NULL;
+}
+
+void *thread_process_reader(void *arg)
+{
+ rcu_reader();
+
+ return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+ pthread_t tu;
+ pthread_t tpr;
+
+ if (pthread_create(&tu, NULL, thread_update, NULL))
+ abort();
+ if (pthread_create(&tpr, NULL, thread_process_reader, NULL))
+ abort();
+ if (pthread_join(tu, NULL))
+ abort();
+ if (pthread_join(tpr, NULL))
+ abort();
+ assert(__unbuffered_tpr_y != 0 || __unbuffered_tpr_x != 0);
+
+#ifdef ASSERT_END
+ assert(0);
+#endif
+
+ return 0;
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh
new file mode 100755
index 0000000..d154597
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh
@@ -0,0 +1,102 @@
+#!/bin/sh
+
+# This script expects a mode (either --should-pass or --should-fail) followed by
+# an input file. The script uses the following environment variables. The test C
+# source file is expected to be named test.c in the directory containing the
+# input file.
+#
+# CBMC: The command to run CBMC. Default: cbmc
+# CBMC_FLAGS: Additional flags to pass to CBMC
+# NR_CPUS: Number of cpus to run tests with. Default specified by the test
+# SYNC_SRCU_MODE: Choose implementation of synchronize_srcu. Defaults to simple.
+# kernel: Version included in the linux kernel source.
+# simple: Use try_check_zero directly.
+#
+# The input file is a script that is sourced by this file. It can define any of
+# the following variables to configure the test.
+#
+# test_cbmc_options: Extra options to pass to CBMC.
+# min_cpus_fail: Minimum number of CPUs (NR_CPUS) for verification to fail.
+# The test is expected to pass if it is run with fewer. (Only
+# useful for .fail files)
+# default_cpus: Quantity of CPUs to use for the test, if not specified on the
+# command line. Default: Larger of 2 and MIN_CPUS_FAIL.
+
+set -e
+
+if test "$#" -ne 2; then
+ echo "Expected one option followed by an input file" 1>&2
+ exit 99
+fi
+
+if test "x$1" = "x--should-pass"; then
+ should_pass="yes"
+elif test "x$1" = "x--should-fail"; then
+ should_pass="no"
+else
+ echo "Unrecognized argument '$1'" 1>&2
+
+ # Exit code 99 indicates a hard error.
+ exit 99
+fi
+
+CBMC=${CBMC:-cbmc}
+
+SYNC_SRCU_MODE=${SYNC_SRCU_MODE:-simple}
+
+case ${SYNC_SRCU_MODE} in
+kernel) sync_srcu_mode_flags="" ;;
+simple) sync_srcu_mode_flags="-DUSE_SIMPLE_SYNC_SRCU" ;;
+
+*)
+ echo "Unrecognized argument '${SYNC_SRCU_MODE}'" 1>&2
+ exit 99
+ ;;
+esac
+
+min_cpus_fail=1
+
+c_file=`dirname "$2"`/test.c
+
+# Source the input file.
+. $2
+
+if test ${min_cpus_fail} -gt 2; then
+ default_default_cpus=${min_cpus_fail}
+else
+ default_default_cpus=2
+fi
+default_cpus=${default_cpus:-${default_default_cpus}}
+cpus=${NR_CPUS:-${default_cpus}}
+
+# Check if there are two few cpus to make the test fail.
+if test $cpus -lt ${min_cpus_fail:-0}; then
+ should_pass="yes"
+fi
+
+cbmc_opts="-DNR_CPUS=${cpus} ${sync_srcu_mode_flags} ${test_cbmc_options} ${CBMC_FLAGS}"
+
+echo "Running CBMC: ${CBMC} ${cbmc_opts} ${c_file}"
+if ${CBMC} ${cbmc_opts} "${c_file}"; then
+ # Verification successful. Make sure that it was supposed to verify.
+ test "x${should_pass}" = xyes
+else
+ cbmc_exit_status=$?
+
+ # An exit status of 10 indicates a failed verification.
+ # (see cbmc_parse_optionst::do_bmc in the CBMC source code)
+ if test ${cbmc_exit_status} -eq 10 && test "x${should_pass}" = xno; then
+ :
+ else
+ echo "CBMC returned ${cbmc_exit_status} exit status" 1>&2
+
+ # Parse errors have exit status 6. Any other type of error
+ # should be considered a hard error.
+ if test ${cbmc_exit_status} -ne 6 && \
+ test ${cbmc_exit_status} -ne 10; then
+ exit 99
+ else
+ exit 1
+ fi
+ fi
+fi
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 34e63cc..14142fa 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -26,6 +26,16 @@
#define VMEXIT_CYCLES 500
#define VMENTRY_CYCLES 500
+#elif defined(__s390x__)
+static inline void wait_cycles(unsigned long long cycles)
+{
+ asm volatile("0: brctg %0,0b" : : "d" (cycles));
+}
+
+/* tweak me */
+#define VMEXIT_CYCLES 200
+#define VMENTRY_CYCLES 200
+
#else
static inline void wait_cycles(unsigned long long cycles)
{
@@ -81,6 +91,8 @@
/* Is there a portable way to do this? */
#if defined(__x86_64__) || defined(__i386__)
#define cpu_relax() asm ("rep; nop" ::: "memory")
+#elif defined(__s390x__)
+#define cpu_relax() barrier()
#else
#define cpu_relax() assert(0)
#endif
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 2e69ca8..29b0d39 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -1,12 +1,13 @@
#!/bin/sh
+CPUS_ONLINE=$(lscpu --online -p=cpu|grep -v -e '#')
#use last CPU for host. Why not the first?
#many devices tend to use cpu0 by default so
#it tends to be busier
-HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
+HOST_AFFINITY=$(echo "${CPUS_ONLINE}"|tail -n 1)
#run command on all cpus
-for cpu in $(seq 0 $HOST_AFFINITY)
+for cpu in $CPUS_ONLINE
do
#Don't run guest and host on same CPU
#It actually works ok if using signalling
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index a2dbbcc..6a084cd 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -24,6 +24,7 @@
#include <clocksource/arm_arch_timer.h>
#include <asm/arch_timer.h>
+#include <asm/kvm_hyp.h>
#include <kvm/arm_vgic.h>
#include <kvm/arm_arch_timer.h>
@@ -89,9 +90,6 @@
struct kvm_vcpu *vcpu;
vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
- vcpu->arch.timer_cpu.armed = false;
-
- WARN_ON(!kvm_timer_should_fire(vcpu));
/*
* If the vcpu is blocked we want to wake it up so that it will see
@@ -512,3 +510,25 @@
{
kvm->arch.timer.cntvoff = kvm_phys_timer_read();
}
+
+/*
+ * On VHE system, we only need to configure trap on physical timer and counter
+ * accesses in EL0 and EL1 once, not for every world switch.
+ * The host kernel runs at EL2 with HCR_EL2.TGE == 1,
+ * and this makes those bits have no effect for the host kernel execution.
+ */
+void kvm_timer_init_vhe(void)
+{
+ /* When HCR_EL2.E2H ==1, EL1PCEN and EL1PCTEN are shifted by 10 */
+ u32 cnthctl_shift = 10;
+ u64 val;
+
+ /*
+ * Disallow physical timer access for the guest.
+ * Physical counter access is allowed.
+ */
+ val = read_sysreg(cnthctl_el2);
+ val &= ~(CNTHCTL_EL1PCEN << cnthctl_shift);
+ val |= (CNTHCTL_EL1PCTEN << cnthctl_shift);
+ write_sysreg(val, cnthctl_el2);
+}
diff --git a/virt/kvm/arm/hyp/timer-sr.c b/virt/kvm/arm/hyp/timer-sr.c
index 798866a..63e28dd 100644
--- a/virt/kvm/arm/hyp/timer-sr.c
+++ b/virt/kvm/arm/hyp/timer-sr.c
@@ -35,10 +35,16 @@
/* Disable the virtual timer */
write_sysreg_el0(0, cntv_ctl);
- /* Allow physical timer/counter access for the host */
- val = read_sysreg(cnthctl_el2);
- val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
- write_sysreg(val, cnthctl_el2);
+ /*
+ * We don't need to do this for VHE since the host kernel runs in EL2
+ * with HCR_EL2.TGE ==1, which makes those bits have no impact.
+ */
+ if (!has_vhe()) {
+ /* Allow physical timer/counter access for the host */
+ val = read_sysreg(cnthctl_el2);
+ val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
+ write_sysreg(val, cnthctl_el2);
+ }
/* Clear cntvoff for the host */
write_sysreg(0, cntvoff_el2);
@@ -50,14 +56,17 @@
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
u64 val;
- /*
- * Disallow physical timer access for the guest
- * Physical counter access is allowed
- */
- val = read_sysreg(cnthctl_el2);
- val &= ~CNTHCTL_EL1PCEN;
- val |= CNTHCTL_EL1PCTEN;
- write_sysreg(val, cnthctl_el2);
+ /* Those bits are already configured at boot on VHE-system */
+ if (!has_vhe()) {
+ /*
+ * Disallow physical timer access for the guest
+ * Physical counter access is allowed
+ */
+ val = read_sysreg(cnthctl_el2);
+ val &= ~CNTHCTL_EL1PCEN;
+ val |= CNTHCTL_EL1PCTEN;
+ write_sysreg(val, cnthctl_el2);
+ }
if (timer->enabled) {
write_sysreg(kvm->arch.timer.cntvoff, cntvoff_el2);
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 5114391..c737ea0 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -268,15 +268,11 @@
{
struct vgic_dist *dist = &kvm->arch.vgic;
- mutex_lock(&kvm->lock);
-
dist->ready = false;
dist->initialized = false;
kfree(dist->spis);
dist->nr_spis = 0;
-
- mutex_unlock(&kvm->lock);
}
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -286,7 +282,8 @@
INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
}
-void kvm_vgic_destroy(struct kvm *kvm)
+/* To be called with kvm->lock held */
+static void __kvm_vgic_destroy(struct kvm *kvm)
{
struct kvm_vcpu *vcpu;
int i;
@@ -297,6 +294,13 @@
kvm_vgic_vcpu_destroy(vcpu);
}
+void kvm_vgic_destroy(struct kvm *kvm)
+{
+ mutex_lock(&kvm->lock);
+ __kvm_vgic_destroy(kvm);
+ mutex_unlock(&kvm->lock);
+}
+
/**
* vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest
* is a GICv2. A GICv3 must be explicitly initialized by the guest using the
@@ -348,6 +352,10 @@
ret = vgic_v2_map_resources(kvm);
else
ret = vgic_v3_map_resources(kvm);
+
+ if (ret)
+ __kvm_vgic_destroy(kvm);
+
out:
mutex_unlock(&kvm->lock);
return ret;
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 9bab867..834137e 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -293,8 +293,6 @@
dist->ready = true;
out:
- if (ret)
- kvm_vgic_destroy(kvm);
return ret;
}
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 5c9f974..e6b03fd 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -302,8 +302,6 @@
dist->ready = true;
out:
- if (ret)
- kvm_vgic_destroy(kvm);
return ret;
}
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
index 52abac4..6d2fcd6 100644
--- a/virt/lib/irqbypass.c
+++ b/virt/lib/irqbypass.c
@@ -195,7 +195,7 @@
mutex_lock(&lock);
list_for_each_entry(tmp, &consumers, node) {
- if (tmp->token == consumer->token) {
+ if (tmp->token == consumer->token || tmp == consumer) {
mutex_unlock(&lock);
module_put(THIS_MODULE);
return -EBUSY;
@@ -245,7 +245,7 @@
mutex_lock(&lock);
list_for_each_entry(tmp, &consumers, node) {
- if (tmp->token != consumer->token)
+ if (tmp != consumer)
continue;
list_for_each_entry(producer, &producers, node) {
