diff --git a/.mailmap b/.mailmap
index d357e1b..0d971cf 100644
--- a/.mailmap
+++ b/.mailmap
@@ -73,6 +73,7 @@
 Juha Yrjola <juha.yrjola@solidboot.com>
 Kay Sievers <kay.sievers@vrfy.org>
 Kenneth W Chen <kenneth.w.chen@intel.com>
+Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Koushik <raghavendra.koushik@neterion.com>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 Leonid I Ananiev <leonid.i.ananiev@intel.com>
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index ed186a9..b57c0c1 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -15,7 +15,7 @@
 	21 seconds.
 
 	This configuration parameter may be changed at runtime via the
-	/sys/module/rcutree/parameters/rcu_cpu_stall_timeout, however
+	/sys/module/rcupdate/parameters/rcu_cpu_stall_timeout, however
 	this parameter is checked only at the beginning of a cycle.
 	So if you are 10 seconds into a 40-second stall, setting this
 	sysfs parameter to (say) five will shorten the timeout for the
@@ -152,6 +152,15 @@
 "D" indicates that dyntick-idle processing is enabled ("." is printed
 otherwise, for example, if disabled via the "nohz=" kernel boot parameter).
 
+If the relevant grace-period kthread has been unable to run prior to
+the stall warning, the following additional line is printed:
+
+	rcu_preempt kthread starved for 2023 jiffies!
+
+Starving the grace-period kthreads of CPU time can of course result in
+RCU CPU stall warnings even when all CPUs and tasks have passed through
+the required quiescent states.
+
 
 Multiple Warnings From One Stall
 
@@ -187,6 +196,11 @@
 	behavior, you might need to replace some of the cond_resched()
 	calls with calls to cond_resched_rcu_qs().
 
+o	Anything that prevents RCU's grace-period kthreads from running.
+	This can result in the "All QSes seen" console-log message.
+	This message will include information on when the kthread last
+	ran and how often it should be expected to run.
+
 o	A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
 	happen to preempt a low-priority task in the middle of an RCU
 	read-side critical section.   This is especially damaging if
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index b63b9bb..08651da 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -56,14 +56,14 @@
 
 The output of "cat rcu/rcu_preempt/rcudata" looks as follows:
 
-  0!c=30455 g=30456 pq=1 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716
-  1!c=30719 g=30720 pq=1 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982
-  2!c=30150 g=30151 pq=1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458
-  3 c=31249 g=31250 pq=1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622
-  4!c=29502 g=29503 pq=1 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521
-  5 c=31201 g=31202 pq=1 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698
-  6!c=30253 g=30254 pq=1 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353
-  7 c=31178 g=31178 pq=1 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969
+  0!c=30455 g=30456 pq=1/0 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716
+  1!c=30719 g=30720 pq=1/0 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982
+  2!c=30150 g=30151 pq=1/1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458
+  3 c=31249 g=31250 pq=1/1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622
+  4!c=29502 g=29503 pq=1/0 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521
+  5 c=31201 g=31202 pq=1/0 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698
+  6!c=30253 g=30254 pq=1/0 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353
+  7 c=31178 g=31178 pq=1/0 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969
 
 This file has one line per CPU, or eight for this 8-CPU system.
 The fields are as follows:
@@ -188,14 +188,14 @@
 Kernels compiled with CONFIG_RCU_BOOST=y display the following from
 /debug/rcu/rcu_preempt/rcudata:
 
-  0!c=12865 g=12866 pq=1 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871
-  1 c=14407 g=14408 pq=1 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485
-  2 c=14407 g=14408 pq=1 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490
-  3 c=14407 g=14408 pq=1 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290
-  4 c=14405 g=14406 pq=1 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114
-  5!c=14168 g=14169 pq=1 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722
-  6 c=14404 g=14405 pq=1 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811
-  7 c=14407 g=14408 pq=1 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042
+  0!c=12865 g=12866 pq=1/0 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871
+  1 c=14407 g=14408 pq=1/0 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485
+  2 c=14407 g=14408 pq=1/0 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490
+  3 c=14407 g=14408 pq=1/0 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290
+  4 c=14405 g=14406 pq=1/0 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114
+  5!c=14168 g=14169 pq=1/0 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722
+  6 c=14404 g=14405 pq=1/0 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811
+  7 c=14407 g=14408 pq=1/0 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042
 
 This is similar to the output discussed above, but contains the following
 additional fields:
diff --git a/Documentation/devicetree/bindings/mfd/max77686.txt b/Documentation/devicetree/bindings/mfd/max77686.txt
index 75fdfaf..e39f0bc 100644
--- a/Documentation/devicetree/bindings/mfd/max77686.txt
+++ b/Documentation/devicetree/bindings/mfd/max77686.txt
@@ -39,6 +39,12 @@
 	-BUCKn	:	1-4.
   Use standard regulator bindings for it ('regulator-off-in-suspend').
 
+  LDO20, LDO21, LDO22, BUCK8 and BUCK9 can be configured to GPIO enable
+  control. To turn this feature on this property must be added to the regulator
+  sub-node:
+	- maxim,ena-gpios :	one GPIO specifier enable control (the gpio
+				flags are actually ignored and always
+				ACTIVE_HIGH is used)
 
 Example:
 
@@ -65,4 +71,12 @@
 				regulator-always-on;
 				regulator-boot-on;
 			};
+
+			buck9_reg {
+				regulator-compatible = "BUCK9";
+				regulator-name = "CAM_ISP_CORE_1.2V";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1200000>;
+				maxim,ena-gpios = <&gpm0 3 GPIO_ACTIVE_HIGH>;
+			};
 	}
diff --git a/Documentation/devicetree/bindings/regulator/da9211.txt b/Documentation/devicetree/bindings/regulator/da9211.txt
index 240019a..eb61890 100644
--- a/Documentation/devicetree/bindings/regulator/da9211.txt
+++ b/Documentation/devicetree/bindings/regulator/da9211.txt
@@ -11,6 +11,7 @@
   BUCKA and BUCKB.
 
 Optional properties:
+- enable-gpios: platform gpio for control of BUCKA/BUCKB.
 - Any optional property defined in regulator.txt
 
 Example 1) DA9211
@@ -27,6 +28,7 @@
 				regulator-max-microvolt = <1570000>;
 				regulator-min-microamp 	= <2000000>;
 				regulator-max-microamp 	= <5000000>;
+				enable-gpios = <&gpio 27 0>;
 			};
 			BUCKB {
 				regulator-name = "VBUCKB";
@@ -34,11 +36,12 @@
 				regulator-max-microvolt = <1570000>;
 				regulator-min-microamp 	= <2000000>;
 				regulator-max-microamp 	= <5000000>;
+				enable-gpios = <&gpio 17 0>;
 			};
 		};
 	};
 
-Example 2) DA92113
+Example 2) DA9213
 	pmic: da9213@68 {
 		compatible = "dlg,da9213";
 		reg = <0x68>;
@@ -51,6 +54,7 @@
 				regulator-max-microvolt = <1570000>;
 				regulator-min-microamp 	= <3000000>;
 				regulator-max-microamp 	= <6000000>;
+				enable-gpios = <&gpio 27 0>;
 			};
 			BUCKB {
 				regulator-name = "VBUCKB";
@@ -58,6 +62,7 @@
 				regulator-max-microvolt = <1570000>;
 				regulator-min-microamp 	= <3000000>;
 				regulator-max-microamp 	= <6000000>;
+				enable-gpios = <&gpio 17 0>;
 			};
 		};
 	};
diff --git a/Documentation/devicetree/bindings/regulator/isl9305.txt b/Documentation/devicetree/bindings/regulator/isl9305.txt
index a626fc1..d6e7c9e 100644
--- a/Documentation/devicetree/bindings/regulator/isl9305.txt
+++ b/Documentation/devicetree/bindings/regulator/isl9305.txt
@@ -2,7 +2,7 @@
 
 Required properties:
 
-- compatible: "isl,isl9305" or "isl,isl9305h"
+- compatible: "isil,isl9305" or "isil,isl9305h"
 - reg: I2C slave address, usually 0x68.
 - regulators: A node that houses a sub-node for each regulator within the
   device. Each sub-node is identified using the node's name, with valid
@@ -19,7 +19,7 @@
 Example
 
 	pmic: isl9305@68 {
-		compatible = "isl,isl9305";
+		compatible = "isil,isl9305";
 		reg = <0x68>;
 
 		VINDCD1-supply = <&system_power>;
diff --git a/Documentation/devicetree/bindings/regulator/mt6397-regulator.txt b/Documentation/devicetree/bindings/regulator/mt6397-regulator.txt
new file mode 100644
index 0000000..a42b1d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/mt6397-regulator.txt
@@ -0,0 +1,217 @@
+Mediatek MT6397 Regulator Driver
+
+Required properties:
+- compatible: "mediatek,mt6397-regulator"
+- mt6397regulator: List of regulators provided by this controller. It is named
+  according to its regulator type, buck_<name> and ldo_<name>.
+  The definition for each of these nodes is defined using the standard binding
+  for regulators at Documentation/devicetree/bindings/regulator/regulator.txt.
+
+The valid names for regulators are::
+BUCK:
+  buck_vpca15, buck_vpca7, buck_vsramca15, buck_vsramca7, buck_vcore, buck_vgpu,
+  buck_vdrm, buck_vio18
+LDO:
+  ldo_vtcxo, ldo_va28, ldo_vcama, ldo_vio28, ldo_vusb, ldo_vmc, ldo_vmch,
+  ldo_vemc3v3, ldo_vgp1, ldo_vgp2, ldo_vgp3, ldo_vgp4, ldo_vgp5, ldo_vgp6,
+  ldo_vibr
+
+Example:
+	pmic {
+		compatible = "mediatek,mt6397";
+
+		mt6397regulator: mt6397regulator {
+			compatible = "mediatek,mt6397-regulator";
+
+			mt6397_vpca15_reg: buck_vpca15 {
+				regulator-compatible = "buck_vpca15";
+				regulator-name = "vpca15";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <200>;
+			};
+
+			mt6397_vpca7_reg: buck_vpca7 {
+				regulator-compatible = "buck_vpca7";
+				regulator-name = "vpca7";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <115>;
+			};
+
+			mt6397_vsramca15_reg: buck_vsramca15 {
+				regulator-compatible = "buck_vsramca15";
+				regulator-name = "vsramca15";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <115>;
+
+			};
+
+			mt6397_vsramca7_reg: buck_vsramca7 {
+				regulator-compatible = "buck_vsramca7";
+				regulator-name = "vsramca7";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <115>;
+
+			};
+
+			mt6397_vcore_reg: buck_vcore {
+				regulator-compatible = "buck_vcore";
+				regulator-name = "vcore";
+				regulator-min-microvolt = < 850000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <115>;
+			};
+
+			mt6397_vgpu_reg: buck_vgpu {
+				regulator-compatible = "buck_vgpu";
+				regulator-name = "vgpu";
+				regulator-min-microvolt = < 700000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <115>;
+			};
+
+			mt6397_vdrm_reg: buck_vdrm {
+				regulator-compatible = "buck_vdrm";
+				regulator-name = "vdrm";
+				regulator-min-microvolt = < 800000>;
+				regulator-max-microvolt = <1400000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <500>;
+			};
+
+			mt6397_vio18_reg: buck_vio18 {
+				regulator-compatible = "buck_vio18";
+				regulator-name = "vio18";
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <2120000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <500>;
+			};
+
+			mt6397_vtcxo_reg: ldo_vtcxo {
+				regulator-compatible = "ldo_vtcxo";
+				regulator-name = "vtcxo";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <90>;
+			};
+
+			mt6397_va28_reg: ldo_va28 {
+				regulator-compatible = "ldo_va28";
+				regulator-name = "va28";
+				/* fixed output 2.8 V */
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vcama_reg: ldo_vcama {
+				regulator-compatible = "ldo_vcama";
+				regulator-name = "vcama";
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vio28_reg: ldo_vio28 {
+				regulator-compatible = "ldo_vio28";
+				regulator-name = "vio28";
+				/* fixed output 2.8 V */
+				regulator-enable-ramp-delay = <240>;
+			};
+
+			mt6397_usb_reg: ldo_vusb {
+				regulator-compatible = "ldo_vusb";
+				regulator-name = "vusb";
+				/* fixed output 3.3 V */
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vmc_reg: ldo_vmc {
+				regulator-compatible = "ldo_vmc";
+				regulator-name = "vmc";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vmch_reg: ldo_vmch {
+				regulator-compatible = "ldo_vmch";
+				regulator-name = "vmch";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vemc_3v3_reg: ldo_vemc3v3 {
+				regulator-compatible = "ldo_vemc3v3";
+				regulator-name = "vemc_3v3";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp1_reg: ldo_vgp1 {
+				regulator-compatible = "ldo_vgp1";
+				regulator-name = "vcamd";
+				regulator-min-microvolt = <1220000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <240>;
+			};
+
+			mt6397_vgp2_reg: ldo_vgp2 {
+				egulator-compatible = "ldo_vgp2";
+				regulator-name = "vcamio";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp3_reg: ldo_vgp3 {
+				regulator-compatible = "ldo_vgp3";
+				regulator-name = "vcamaf";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp4_reg: ldo_vgp4 {
+				regulator-compatible = "ldo_vgp4";
+				regulator-name = "vgp4";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp5_reg: ldo_vgp5 {
+				regulator-compatible = "ldo_vgp5";
+				regulator-name = "vgp5";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vgp6_reg: ldo_vgp6 {
+				regulator-compatible = "ldo_vgp6";
+				regulator-name = "vgp6";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+
+			mt6397_vibr_reg: ldo_vibr {
+				regulator-compatible = "ldo_vibr";
+				regulator-name = "vibr";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <218>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt
index 34ef5d1..9b40db8 100644
--- a/Documentation/devicetree/bindings/regulator/pfuze100.txt
+++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt
@@ -1,7 +1,7 @@
 PFUZE100 family of regulators
 
 Required properties:
-- compatible: "fsl,pfuze100" or "fsl,pfuze200"
+- compatible: "fsl,pfuze100", "fsl,pfuze200", "fsl,pfuze3000"
 - reg: I2C slave address
 
 Required child node:
@@ -14,6 +14,8 @@
   sw1ab,sw1c,sw2,sw3a,sw3b,sw4,swbst,vsnvs,vrefddr,vgen1~vgen6
   --PFUZE200
   sw1ab,sw2,sw3a,sw3b,swbst,vsnvs,vrefddr,vgen1~vgen6
+  --PFUZE3000
+  sw1a,sw1b,sw2,sw3,swbst,vsnvs,vrefddr,vldo1,vldo2,vccsd,v33,vldo3,vldo4
 
 Each regulator is defined using the standard binding for regulators.
 
@@ -205,3 +207,93 @@
 			};
 		};
 	};
+
+Example 3: PFUZE3000
+
+	pmic: pfuze3000@08 {
+		compatible = "fsl,pfuze3000";
+		reg = <0x08>;
+
+		regulators {
+			sw1a_reg: sw1a {
+				regulator-min-microvolt = <700000>;
+				regulator-max-microvolt = <1475000>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <6250>;
+			};
+			/* use sw1c_reg to align with pfuze100/pfuze200 */
+			sw1c_reg: sw1b {
+				regulator-min-microvolt = <700000>;
+				regulator-max-microvolt = <1475000>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <6250>;
+			};
+
+			sw2_reg: sw2 {
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3a_reg: sw3 {
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <1650000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			swbst_reg: swbst {
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5150000>;
+			};
+
+			snvs_reg: vsnvs {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vref_reg: vrefddr {
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vgen1_reg: vldo1 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen2_reg: vldo2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1550000>;
+			};
+
+			vgen3_reg: vccsd {
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen4_reg: v33 {
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			vgen5_reg: vldo3 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen6_reg: vldo4 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt
index d11c372..4c388bb 100644
--- a/Documentation/devicetree/bindings/spi/sh-msiof.txt
+++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt
@@ -30,6 +30,22 @@
 			 specifiers, one for transmission, and one for
 			 reception.
 - dma-names            : Must contain a list of two DMA names, "tx" and "rx".
+- renesas,dtdl         : delay sync signal (setup) in transmit mode.
+			 Must contain one of the following values:
+			 0   (no bit delay)
+			 50  (0.5-clock-cycle delay)
+			 100 (1-clock-cycle delay)
+			 150 (1.5-clock-cycle delay)
+			 200 (2-clock-cycle delay)
+
+- renesas,syncdl       : delay sync signal (hold) in transmit mode.
+			 Must contain one of the following values:
+			 0   (no bit delay)
+			 50  (0.5-clock-cycle delay)
+			 100 (1-clock-cycle delay)
+			 150 (1.5-clock-cycle delay)
+			 200 (2-clock-cycle delay)
+			 300 (3-clock-cycle delay)
 
 Optional properties, deprecated for soctype-specific bindings:
 - renesas,tx-fifo-size : Overrides the default tx fifo size given in words
diff --git a/Documentation/devicetree/bindings/spi/spi-sirf.txt b/Documentation/devicetree/bindings/spi/spi-sirf.txt
new file mode 100644
index 0000000..4c7adb8f
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-sirf.txt
@@ -0,0 +1,41 @@
+* CSR SiRFprimaII Serial Peripheral Interface
+
+Required properties:
+- compatible : Should be "sirf,prima2-spi"
+- reg : Offset and length of the register set for the device
+- interrupts : Should contain SPI interrupt
+- resets: phandle to the reset controller asserting this device in
+          reset
+  See ../reset/reset.txt for details.
+- dmas : Must contain an entry for each entry in clock-names.
+  See ../dma/dma.txt for details.
+- dma-names : Must include the following entries:
+  - rx
+  - tx
+- clocks : Must contain an entry for each entry in clock-names.
+  See ../clocks/clock-bindings.txt for details.
+
+- #address-cells: Number of cells required to define a chip select
+                  address on the SPI bus. Should be set to 1.
+- #size-cells:    Should be zero.
+
+Optional properties:
+- spi-max-frequency: Specifies maximum SPI clock frequency,
+                     Units - Hz. Definition as per
+                     Documentation/devicetree/bindings/spi/spi-bus.txt
+- cs-gpios:     should specify GPIOs used for chipselects.
+
+Example:
+
+spi0: spi@b00d0000 {
+	compatible = "sirf,prima2-spi";
+	reg = <0xb00d0000 0x10000>;
+	interrupts = <15>;
+	dmas = <&dmac1 9>,
+		<&dmac1 4>;
+	dma-names = "rx", "tx";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	clocks = <&clks 19>;
+	resets = <&rstc 26>;
+};
diff --git a/Documentation/devicetree/bindings/spi/spi-st-ssc.txt b/Documentation/devicetree/bindings/spi/spi-st-ssc.txt
new file mode 100644
index 0000000..fe54959
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-st-ssc.txt
@@ -0,0 +1,40 @@
+STMicroelectronics SSC (SPI) Controller
+---------------------------------------
+
+Required properties:
+- compatible	: "st,comms-ssc4-spi"
+- reg		: Offset and length of the device's register set
+- interrupts	: The interrupt specifier
+- clock-names	: Must contain "ssc"
+- clocks	: Must contain an entry for each name in clock-names
+		    See ../clk/*
+- pinctrl-names	: Uses "default", can use "sleep" if provided
+		    See ../pinctrl/pinctrl-binding.txt
+
+Optional properties:
+- cs-gpios	: List of GPIO chip selects
+		    See ../spi/spi-bus.txt
+
+Child nodes represent devices on the SPI bus
+  See ../spi/spi-bus.txt
+
+Example:
+	spi@9840000 {
+		compatible	= "st,comms-ssc4-spi";
+		reg		= <0x9840000 0x110>;
+		interrupts	= <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
+		clocks		= <&clk_s_c0_flexgen CLK_EXT2F_A9>;
+		clock-names	= "ssc";
+		pinctrl-0	= <&pinctrl_spi0_default>;
+		pinctrl-names	= "default";
+		cs-gpios	= <&pio17 5 0>;
+		#address-cells	= <1>;
+		#size-cells	= <0>;
+
+		st95hf@0{
+			compatible		= "st,st95hf";
+			reg			= <0>;
+			spi-max-frequency	= <1000000>;
+			interrupts		= <2 IRQ_TYPE_EDGE_FALLING>;
+		};
+	};
diff --git a/Documentation/hwmon/ina2xx b/Documentation/hwmon/ina2xx
index 4223c2d..cfd31d9 100644
--- a/Documentation/hwmon/ina2xx
+++ b/Documentation/hwmon/ina2xx
@@ -26,6 +26,12 @@
     Datasheet: Publicly available at the Texas Instruments website
                http://www.ti.com/
 
+  * Texas Instruments INA231
+    Prefix: 'ina231'
+    Addresses: I2C 0x40 - 0x4f
+    Datasheet: Publicly available at the Texas Instruments website
+               http://www.ti.com/
+
 Author: Lothar Felten <l-felten@ti.com>
 
 Description
@@ -41,9 +47,18 @@
 The INA226 is a current shunt and power monitor with an I2C interface.
 The INA226 monitors both a shunt voltage drop and bus supply voltage.
 
-The INA230 is a high or low side current shunt and power monitor with an I2C
-interface. The INA230 monitors both a shunt voltage drop and bus supply voltage.
+INA230 and INA231 are high or low side current shunt and power monitors
+with an I2C interface. The chips monitor both a shunt voltage drop and
+bus supply voltage.
 
-The shunt value in micro-ohms can be set via platform data or device tree.
-Please refer to the Documentation/devicetree/bindings/i2c/ina2xx.txt for bindings
+The shunt value in micro-ohms can be set via platform data or device tree at
+compile-time or via the shunt_resistor attribute in sysfs at run-time. Please
+refer to the Documentation/devicetree/bindings/i2c/ina2xx.txt for bindings
 if the device tree is used.
+
+Additionally ina226 supports update_interval attribute as described in
+Documentation/hwmon/sysfs-interface. Internally the interval is the sum of
+bus and shunt voltage conversion times multiplied by the averaging rate. We
+don't touch the conversion times and only modify the number of averages. The
+lower limit of the update_interval is 2 ms, the upper limit is 2253 ms.
+The actual programmed interval may vary from the desired value.
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 70a09f8..ca2387e 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -269,6 +269,50 @@
 	STORE *(A + 4) = Y; STORE *A = X;
 	STORE {*A, *(A + 4) } = {X, Y};
 
+And there are anti-guarantees:
+
+ (*) These guarantees do not apply to bitfields, because compilers often
+     generate code to modify these using non-atomic read-modify-write
+     sequences.  Do not attempt to use bitfields to synchronize parallel
+     algorithms.
+
+ (*) Even in cases where bitfields are protected by locks, all fields
+     in a given bitfield must be protected by one lock.  If two fields
+     in a given bitfield are protected by different locks, the compiler's
+     non-atomic read-modify-write sequences can cause an update to one
+     field to corrupt the value of an adjacent field.
+
+ (*) These guarantees apply only to properly aligned and sized scalar
+     variables.  "Properly sized" currently means variables that are
+     the same size as "char", "short", "int" and "long".  "Properly
+     aligned" means the natural alignment, thus no constraints for
+     "char", two-byte alignment for "short", four-byte alignment for
+     "int", and either four-byte or eight-byte alignment for "long",
+     on 32-bit and 64-bit systems, respectively.  Note that these
+     guarantees were introduced into the C11 standard, so beware when
+     using older pre-C11 compilers (for example, gcc 4.6).  The portion
+     of the standard containing this guarantee is Section 3.14, which
+     defines "memory location" as follows:
+
+     	memory location
+		either an object of scalar type, or a maximal sequence
+		of adjacent bit-fields all having nonzero width
+
+		NOTE 1: Two threads of execution can update and access
+		separate memory locations without interfering with
+		each other.
+
+		NOTE 2: A bit-field and an adjacent non-bit-field member
+		are in separate memory locations. The same applies
+		to two bit-fields, if one is declared inside a nested
+		structure declaration and the other is not, or if the two
+		are separated by a zero-length bit-field declaration,
+		or if they are separated by a non-bit-field member
+		declaration. It is not safe to concurrently update two
+		bit-fields in the same structure if all members declared
+		between them are also bit-fields, no matter what the
+		sizes of those intervening bit-fields happen to be.
+
 
 =========================
 WHAT ARE MEMORY BARRIERS?
@@ -750,7 +794,7 @@
       However, they do -not- guarantee any other sort of ordering:
       Not prior loads against later loads, nor prior stores against
       later anything.  If you need these other forms of ordering,
-      use smb_rmb(), smp_wmb(), or, in the case of prior stores and
+      use smp_rmb(), smp_wmb(), or, in the case of prior stores and
       later loads, smp_mb().
 
   (*) If both legs of the "if" statement begin with identical stores
diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt
index c6af4ba..54f1047 100644
--- a/Documentation/networking/netlink_mmap.txt
+++ b/Documentation/networking/netlink_mmap.txt
@@ -199,16 +199,9 @@
 TX limitations
 --------------
 
-Kernel processing usually involves validation of the message received by
-user-space, then processing its contents. The kernel must assure that
-userspace is not able to modify the message contents after they have been
-validated. In order to do so, the message is copied from the ring frame
-to an allocated buffer if either of these conditions is false:
-
-- only a single mapping of the ring exists
-- the file descriptor is not shared between processes
-
-This means that for threaded programs, the kernel will fall back to copying.
+As of Jan 2015 the message is always copied from the ring frame to an
+allocated buffer due to unresolved security concerns.
+See commit 4682a0358639b29cf ("netlink: Always copy on mmap TX.").
 
 Example
 -------
diff --git a/MAINTAINERS b/MAINTAINERS
index aaa039d..d66a97d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4953,6 +4953,16 @@
 F:	drivers/input/input-mt.c
 K:	\b(ABS|SYN)_MT_
 
+INTEL ASoC BDW/HSW DRIVERS
+M:	Jie Yang <yang.jie@linux.intel.com>
+L:	alsa-devel@alsa-project.org
+S:	Supported
+F:	sound/soc/intel/sst-haswell*
+F:	sound/soc/intel/sst-dsp*
+F:	sound/soc/intel/sst-firmware.c
+F:	sound/soc/intel/broadwell.c
+F:	sound/soc/intel/haswell.c
+
 INTEL C600 SERIES SAS CONTROLLER DRIVER
 M:	Intel SCU Linux support <intel-linux-scu@intel.com>
 M:	Artur Paszkiewicz <artur.paszkiewicz@intel.com>
@@ -9241,7 +9251,6 @@
 
 SUPERH
 L:	linux-sh@vger.kernel.org
-W:	http://www.linux-sh.org
 Q:	http://patchwork.kernel.org/project/linux-sh/list/
 S:	Orphan
 F:	Documentation/sh/
diff --git a/Makefile b/Makefile
index c8e17c0..b15036b 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 19
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION =
 NAME = Diseased Newt
 
 # *DOCUMENTATION*
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 68be901..132c70e 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -263,16 +263,37 @@
 		 * OK... Let's do some funky business here.
 		 * If we do have a DTB appended to zImage, and we do have
 		 * an ATAG list around, we want the later to be translated
-		 * and folded into the former here.  To be on the safe side,
-		 * let's temporarily move  the stack away into the malloc
-		 * area.  No GOT fixup has occurred yet, but none of the
-		 * code we're about to call uses any global variable.
+		 * and folded into the former here. No GOT fixup has occurred
+		 * yet, but none of the code we're about to call uses any
+		 * global variable.
 		*/
-		add	sp, sp, #0x10000
+
+		/* Get the initial DTB size */
+		ldr	r5, [r6, #4]
+#ifndef __ARMEB__
+		/* convert to little endian */
+		eor	r1, r5, r5, ror #16
+		bic	r1, r1, #0x00ff0000
+		mov	r5, r5, ror #8
+		eor	r5, r5, r1, lsr #8
+#endif
+		/* 50% DTB growth should be good enough */
+		add	r5, r5, r5, lsr #1
+		/* preserve 64-bit alignment */
+		add	r5, r5, #7
+		bic	r5, r5, #7
+		/* clamp to 32KB min and 1MB max */
+		cmp	r5, #(1 << 15)
+		movlo	r5, #(1 << 15)
+		cmp	r5, #(1 << 20)
+		movhi	r5, #(1 << 20)
+		/* temporarily relocate the stack past the DTB work space */
+		add	sp, sp, r5
+
 		stmfd	sp!, {r0-r3, ip, lr}
 		mov	r0, r8
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bl	atags_to_fdt
 
 		/*
@@ -285,11 +306,11 @@
 		bic	r0, r0, #1
 		add	r0, r0, #0x100
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bleq	atags_to_fdt
 
 		ldmfd	sp!, {r0-r3, ip, lr}
-		sub	sp, sp, #0x10000
+		sub	sp, sp, r5
 #endif
 
 		mov	r8, r6			@ use the appended device tree
@@ -306,7 +327,7 @@
 		subs	r1, r5, r1
 		addhi	r9, r9, r1
 
-		/* Get the dtb's size */
+		/* Get the current DTB size */
 		ldr	r5, [r6, #4]
 #ifndef __ARMEB__
 		/* convert r5 (dtb size) to little endian */
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index b8168f1..24ff270 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -368,7 +368,7 @@
 	};
 
 	i2s1: i2s@13960000 {
-		compatible = "samsung,s5pv210-i2s";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x13960000 0x100>;
 		clocks = <&clock CLK_I2S1>;
 		clock-names = "iis";
@@ -378,7 +378,7 @@
 	};
 
 	i2s2: i2s@13970000 {
-		compatible = "samsung,s5pv210-i2s";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x13970000 0x100>;
 		clocks = <&clock CLK_I2S2>;
 		clock-names = "iis";
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 2260f18..8944f49 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -22,10 +22,12 @@
 
 __invalid_entry:
 	v7m_exception_entry
+#ifdef CONFIG_PRINTK
 	adr	r0, strerr
 	mrs	r1, ipsr
 	mov	r2, lr
 	bl	printk
+#endif
 	mov	r0, sp
 	bl	show_regs
 1:	b	1b
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 466bd29..3afee5f 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -23,6 +23,7 @@
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
+	select SRCU
 	depends on ARM_VIRT_EXT && ARM_LPAE
 	---help---
 	  Support hosting virtualized guest machines. You will also
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 03823e7..c43c714 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1012,6 +1012,7 @@
 
 config ARM_KERNMEM_PERMS
 	bool "Restrict kernel memory permissions"
+	depends on MMU
 	help
 	  If this is set, kernel memory other than kernel text (and rodata)
 	  will be made non-executable. The tradeoff is that each region is
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 9189256..845769e 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -144,21 +144,17 @@
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
 	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 	for_each_possible_cpu(i) {
-		if (i == cpu) {
-			asid = 0;
-		} else {
-			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			/*
-			 * If this CPU has already been through a
-			 * rollover, but hasn't run another task in
-			 * the meantime, we must preserve its reserved
-			 * ASID, as this is the only trace we have of
-			 * the process it is still running.
-			 */
-			if (asid == 0)
-				asid = per_cpu(reserved_asids, i);
-			__set_bit(asid & ~ASID_MASK, asid_map);
-		}
+		asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
+		/*
+		 * If this CPU has already been through a
+		 * rollover, but hasn't run another task in
+		 * the meantime, we must preserve its reserved
+		 * ASID, as this is the only trace we have of
+		 * the process it is still running.
+		 */
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, i);
+		__set_bit(asid & ~ASID_MASK, asid_map);
 		per_cpu(reserved_asids, i) = asid;
 	}
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index a673c7f..903dba0 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -2048,6 +2048,9 @@
 {
 	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
 
+	if (!mapping)
+		return;
+
 	__arm_iommu_detach_device(dev);
 	arm_iommu_release_mapping(mapping);
 }
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 8ba85e9..b334084 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -26,6 +26,7 @@
 	select KVM_ARM_HOST
 	select KVM_ARM_VGIC
 	select KVM_ARM_TIMER
+	select SRCU
 	---help---
 	  Support hosting virtualized guest machines.
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 3289969..843713c 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2656,27 +2656,21 @@
 	bool
 
 config MIPS32_COMPAT
-	bool "Kernel support for Linux/MIPS 32-bit binary compatibility"
-	depends on 64BIT
-	help
-	  Select this option if you want Linux/MIPS 32-bit binary
-	  compatibility. Since all software available for Linux/MIPS is
-	  currently 32-bit you should say Y here.
+	bool
 
 config COMPAT
 	bool
-	depends on MIPS32_COMPAT
-	select ARCH_WANT_OLD_COMPAT_IPC
-	default y
 
 config SYSVIPC_COMPAT
 	bool
-	depends on COMPAT && SYSVIPC
-	default y
 
 config MIPS32_O32
 	bool "Kernel support for o32 binaries"
-	depends on MIPS32_COMPAT
+	depends on 64BIT
+	select ARCH_WANT_OLD_COMPAT_IPC
+	select COMPAT
+	select MIPS32_COMPAT
+	select SYSVIPC_COMPAT if SYSVIPC
 	help
 	  Select this option if you want to run o32 binaries.  These are pure
 	  32-bit binaries as used by the 32-bit Linux/MIPS port.  Most of
@@ -2686,7 +2680,10 @@
 
 config MIPS32_N32
 	bool "Kernel support for n32 binaries"
-	depends on MIPS32_COMPAT
+	depends on 64BIT
+	select COMPAT
+	select MIPS32_COMPAT
+	select SYSVIPC_COMPAT if SYSVIPC
 	help
 	  Select this option if you want to run n32 binaries.  These are
 	  64-bit binaries using 32-bit quantities for addressing and certain
diff --git a/arch/mips/boot/elf2ecoff.c b/arch/mips/boot/elf2ecoff.c
index 8585078..2a4c52e 100644
--- a/arch/mips/boot/elf2ecoff.c
+++ b/arch/mips/boot/elf2ecoff.c
@@ -49,7 +49,8 @@
 /*
  * Some extra ELF definitions
  */
-#define PT_MIPS_REGINFO 0x70000000	/* Register usage information */
+#define PT_MIPS_REGINFO 	0x70000000	/* Register usage information */
+#define PT_MIPS_ABIFLAGS	0x70000003	/* Records ABI related flags  */
 
 /* -------------------------------------------------------------------- */
 
@@ -349,39 +350,46 @@
 
 	for (i = 0; i < ex.e_phnum; i++) {
 		/* Section types we can ignore... */
-		if (ph[i].p_type == PT_NULL || ph[i].p_type == PT_NOTE ||
-		    ph[i].p_type == PT_PHDR
-		    || ph[i].p_type == PT_MIPS_REGINFO)
+		switch (ph[i].p_type) {
+		case PT_NULL:
+		case PT_NOTE:
+		case PT_PHDR:
+		case PT_MIPS_REGINFO:
+		case PT_MIPS_ABIFLAGS:
 			continue;
-		/* Section types we can't handle... */
-		else if (ph[i].p_type != PT_LOAD) {
+
+		case PT_LOAD:
+			/* Writable (data) segment? */
+			if (ph[i].p_flags & PF_W) {
+				struct sect ndata, nbss;
+
+				ndata.vaddr = ph[i].p_vaddr;
+				ndata.len = ph[i].p_filesz;
+				nbss.vaddr = ph[i].p_vaddr + ph[i].p_filesz;
+				nbss.len = ph[i].p_memsz - ph[i].p_filesz;
+
+				combine(&data, &ndata, 0);
+				combine(&bss, &nbss, 1);
+			} else {
+				struct sect ntxt;
+
+				ntxt.vaddr = ph[i].p_vaddr;
+				ntxt.len = ph[i].p_filesz;
+
+				combine(&text, &ntxt, 0);
+			}
+			/* Remember the lowest segment start address. */
+			if (ph[i].p_vaddr < cur_vma)
+				cur_vma = ph[i].p_vaddr;
+			break;
+
+		default:
+			/* Section types we can't handle... */
 			fprintf(stderr,
 				"Program header %d type %d can't be converted.\n",
 				ex.e_phnum, ph[i].p_type);
 			exit(1);
 		}
-		/* Writable (data) segment? */
-		if (ph[i].p_flags & PF_W) {
-			struct sect ndata, nbss;
-
-			ndata.vaddr = ph[i].p_vaddr;
-			ndata.len = ph[i].p_filesz;
-			nbss.vaddr = ph[i].p_vaddr + ph[i].p_filesz;
-			nbss.len = ph[i].p_memsz - ph[i].p_filesz;
-
-			combine(&data, &ndata, 0);
-			combine(&bss, &nbss, 1);
-		} else {
-			struct sect ntxt;
-
-			ntxt.vaddr = ph[i].p_vaddr;
-			ntxt.len = ph[i].p_filesz;
-
-			combine(&text, &ntxt, 0);
-		}
-		/* Remember the lowest segment start address. */
-		if (ph[i].p_vaddr < cur_vma)
-			cur_vma = ph[i].p_vaddr;
 	}
 
 	/* Sections must be in order to be converted... */
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index ecd903d..8b1eeff 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -240,9 +240,7 @@
 
 	set_cpu_online(cpu, false);
 	cpu_clear(cpu, cpu_callin_map);
-	local_irq_disable();
 	octeon_fixup_irqs();
-	local_irq_enable();
 
 	flush_cache_all();
 	local_flush_tlb_all();
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index f57b96d..61a4460 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -132,7 +132,6 @@
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
@@ -175,7 +174,6 @@
 CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
-CONFIG_BRIDGE_EBT_ULOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
 CONFIG_IP_SCTP=m
 CONFIG_BRIDGE=m
@@ -220,8 +218,6 @@
 CONFIG_NET_CLS_IND=y
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
-CONFIG_MAC80211_RC_PID=y
-CONFIG_MAC80211_RC_DEFAULT_PID=y
 CONFIG_MAC80211_MESH=y
 CONFIG_RFKILL=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
@@ -248,19 +244,13 @@
 CONFIG_IDE=y
 CONFIG_BLK_DEV_IDECD=y
 CONFIG_IDE_GENERIC=y
-CONFIG_BLK_DEV_GENERIC=y
-CONFIG_BLK_DEV_PIIX=y
-CONFIG_BLK_DEV_IT8213=m
-CONFIG_BLK_DEV_TC86C001=m
 CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=m
-CONFIG_BLK_DEV_SD=m
+CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=m
 CONFIG_CHR_DEV_OSST=m
 CONFIG_BLK_DEV_SR=m
 CONFIG_BLK_DEV_SR_VENDOR=y
 CONFIG_CHR_DEV_SG=m
-CONFIG_SCSI_MULTI_LUN=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
@@ -273,6 +263,8 @@
 CONFIG_SCSI_AIC7XXX=m
 CONFIG_AIC7XXX_RESET_DELAY_MS=15000
 # CONFIG_AIC7XXX_DEBUG_ENABLE is not set
+CONFIG_ATA=y
+CONFIG_ATA_PIIX=y
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=m
 CONFIG_MD_LINEAR=m
@@ -340,6 +332,7 @@
 CONFIG_UIO_CIF=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_REISERFS_PROC_INFO=y
 CONFIG_REISERFS_FS_XATTR=y
@@ -441,4 +434,3 @@
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC16=m
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 994d219..affebb7 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -64,7 +64,7 @@
 			return SIGFPE;
 
 		/* set FRE */
-		write_c0_config5(read_c0_config5() | MIPS_CONF5_FRE);
+		set_c0_config5(MIPS_CONF5_FRE);
 		goto fr_common;
 
 	case FPU_64BIT:
@@ -74,8 +74,10 @@
 #endif
 		/* fall through */
 	case FPU_32BIT:
-		/* clear FRE */
-		write_c0_config5(read_c0_config5() & ~MIPS_CONF5_FRE);
+		if (cpu_has_fre) {
+			/* clear FRE */
+			clear_c0_config5(MIPS_CONF5_FRE);
+		}
 fr_common:
 		/* set CU1 & change FR appropriately */
 		fr = (int)mode & FPU_FR_MASK;
@@ -182,25 +184,32 @@
 	int ret = 0;
 
 	if (cpu_has_fpu) {
+		unsigned int config5;
+
 		ret = __own_fpu();
-		if (!ret) {
-			unsigned int config5 = read_c0_config5();
+		if (ret)
+			return ret;
 
-			/*
-			 * Ensure FRE is clear whilst running _init_fpu, since
-			 * single precision FP instructions are used. If FRE
-			 * was set then we'll just end up initialising all 32
-			 * 64b registers.
-			 */
-			write_c0_config5(config5 & ~MIPS_CONF5_FRE);
-			enable_fpu_hazard();
-
+		if (!cpu_has_fre) {
 			_init_fpu();
 
-			/* Restore FRE */
-			write_c0_config5(config5);
-			enable_fpu_hazard();
+			return 0;
 		}
+
+		/*
+		 * Ensure FRE is clear whilst running _init_fpu, since
+		 * single precision FP instructions are used. If FRE
+		 * was set then we'll just end up initialising all 32
+		 * 64b registers.
+		 */
+		config5 = clear_c0_config5(MIPS_CONF5_FRE);
+		enable_fpu_hazard();
+
+		_init_fpu();
+
+		/* Restore FRE */
+		write_c0_config5(config5);
+		enable_fpu_hazard();
 	} else
 		fpu_emulator_init_fpu();
 
diff --git a/arch/mips/include/asm/fw/arc/hinv.h b/arch/mips/include/asm/fw/arc/hinv.h
index f8d37d1..9fac64a 100644
--- a/arch/mips/include/asm/fw/arc/hinv.h
+++ b/arch/mips/include/asm/fw/arc/hinv.h
@@ -119,7 +119,7 @@
 #define SGI_ARCS_REV	10			/* rev .10, 3/04/92 */
 #endif
 
-typedef struct component {
+typedef struct {
 	CONFIGCLASS	Class;
 	CONFIGTYPE	Type;
 	IDENTIFIERFLAG	Flags;
@@ -140,7 +140,7 @@
 };
 
 /* System ID */
-typedef struct systemid {
+typedef struct {
 	CHAR VendorId[8];
 	CHAR ProductId[8];
 } SYSTEMID;
@@ -166,7 +166,7 @@
 #endif	/* _NT_PROM */
 } MEMORYTYPE;
 
-typedef struct memorydescriptor {
+typedef struct {
 	MEMORYTYPE	Type;
 	LONG		BasePage;
 	LONG		PageCount;
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index b95a827..59c0901 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -89,9 +89,9 @@
 
 /* Macros to ease the creation of register access functions */
 #define BUILD_CM_R_(name, off)					\
-static inline u32 *addr_gcr_##name(void)			\
+static inline u32 __iomem *addr_gcr_##name(void)		\
 {								\
-	return (u32 *)(mips_cm_base + (off));			\
+	return (u32 __iomem *)(mips_cm_base + (off));		\
 }								\
 								\
 static inline u32 read_gcr_##name(void)				\
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 5e4aef3..5b720d8 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1386,12 +1386,27 @@
 	__res;								\
 })
 
+#define _write_32bit_cp1_register(dest, val, gas_hardfloat)		\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	reorder					\n"	\
+	"	"STR(gas_hardfloat)"				\n"	\
+	"	ctc1	%0,"STR(dest)"				\n"	\
+	"	.set	pop					\n"	\
+	: : "r" (val));							\
+} while (0)
+
 #ifdef GAS_HAS_SET_HARDFLOAT
 #define read_32bit_cp1_register(source)					\
 	_read_32bit_cp1_register(source, .set hardfloat)
+#define write_32bit_cp1_register(dest, val)				\
+	_write_32bit_cp1_register(dest, val, .set hardfloat)
 #else
 #define read_32bit_cp1_register(source)					\
 	_read_32bit_cp1_register(source, )
+#define write_32bit_cp1_register(dest, val)				\
+	_write_32bit_cp1_register(dest, val, )
 #endif
 
 #ifdef HAVE_AS_DSP
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index bb79637..6499d93 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -29,13 +29,7 @@
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {
-	/* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */
-	if ((config_enabled(CONFIG_32BIT) ||
-	    test_tsk_thread_flag(task, TIF_32BIT_REGS)) &&
-	    (regs->regs[2] == __NR_syscall))
-		return regs->regs[4];
-	else
-		return regs->regs[2];
+	return current_thread_info()->syscall;
 }
 
 static inline unsigned long mips_get_syscall_arg(unsigned long *arg,
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 99eea59..e4440f9 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -36,6 +36,7 @@
 						 */
 	struct restart_block	restart_block;
 	struct pt_regs		*regs;
+	long			syscall;	/* syscall number */
 };
 
 /*
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index d001bb1..c03088f 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -376,16 +376,17 @@
 #define __NR_getrandom			(__NR_Linux + 353)
 #define __NR_memfd_create		(__NR_Linux + 354)
 #define __NR_bpf			(__NR_Linux + 355)
+#define __NR_execveat			(__NR_Linux + 356)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		355
+#define __NR_Linux_syscalls		356
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		355
+#define __NR_O32_Linux_syscalls		356
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -709,16 +710,17 @@
 #define __NR_getrandom			(__NR_Linux + 313)
 #define __NR_memfd_create		(__NR_Linux + 314)
 #define __NR_bpf			(__NR_Linux + 315)
+#define __NR_execveat			(__NR_Linux + 316)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		315
+#define __NR_Linux_syscalls		316
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		315
+#define __NR_64_Linux_syscalls		316
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1046,15 +1048,16 @@
 #define __NR_getrandom			(__NR_Linux + 317)
 #define __NR_memfd_create		(__NR_Linux + 318)
 #define __NR_bpf			(__NR_Linux + 319)
+#define __NR_execveat			(__NR_Linux + 320)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		319
+#define __NR_Linux_syscalls		320
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		319
+#define __NR_N32_Linux_syscalls		320
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/jz4740/irq.c b/arch/mips/jz4740/irq.c
index 2531da1..97206b3 100644
--- a/arch/mips/jz4740/irq.c
+++ b/arch/mips/jz4740/irq.c
@@ -30,6 +30,9 @@
 #include <asm/irq_cpu.h>
 
 #include <asm/mach-jz4740/base.h>
+#include <asm/mach-jz4740/irq.h>
+
+#include "irq.h"
 
 static void __iomem *jz_intc_base;
 
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index c92b15d..a5b5b56 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -19,8 +19,8 @@
 int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
 		     bool is_interp, struct arch_elf_state *state)
 {
-	struct elfhdr *ehdr = _ehdr;
-	struct elf_phdr *phdr = _phdr;
+	struct elf32_hdr *ehdr = _ehdr;
+	struct elf32_phdr *phdr = _phdr;
 	struct mips_elf_abiflags_v0 abiflags;
 	int ret;
 
@@ -48,7 +48,7 @@
 	return 0;
 }
 
-static inline unsigned get_fp_abi(struct elfhdr *ehdr, int in_abi)
+static inline unsigned get_fp_abi(struct elf32_hdr *ehdr, int in_abi)
 {
 	/* If the ABI requirement is provided, simply return that */
 	if (in_abi != -1)
@@ -65,7 +65,7 @@
 int arch_check_elf(void *_ehdr, bool has_interpreter,
 		   struct arch_elf_state *state)
 {
-	struct elfhdr *ehdr = _ehdr;
+	struct elf32_hdr *ehdr = _ehdr;
 	unsigned fp_abi, interp_fp_abi, abi0, abi1;
 
 	/* Ignore non-O32 binaries */
diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c
index 590c2c9..6eb7a3f 100644
--- a/arch/mips/kernel/irq_cpu.c
+++ b/arch/mips/kernel/irq_cpu.c
@@ -57,6 +57,8 @@
 	.irq_mask_ack	= mask_mips_irq,
 	.irq_unmask	= unmask_mips_irq,
 	.irq_eoi	= unmask_mips_irq,
+	.irq_disable	= mask_mips_irq,
+	.irq_enable	= unmask_mips_irq,
 };
 
 /*
@@ -93,6 +95,8 @@
 	.irq_mask_ack	= mips_mt_cpu_irq_ack,
 	.irq_unmask	= unmask_mips_irq,
 	.irq_eoi	= unmask_mips_irq,
+	.irq_disable	= mask_mips_irq,
+	.irq_enable	= unmask_mips_irq,
 };
 
 asmlinkage void __weak plat_irq_dispatch(void)
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index eb76434..85bff5d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -82,6 +82,30 @@
 {
 }
 
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+	/*
+	 * Save any process state which is live in hardware registers to the
+	 * parent context prior to duplication. This prevents the new child
+	 * state becoming stale if the parent is preempted before copy_thread()
+	 * gets a chance to save the parent's live hardware registers to the
+	 * child context.
+	 */
+	preempt_disable();
+
+	if (is_msa_enabled())
+		save_msa(current);
+	else if (is_fpu_owner())
+		_save_fp(current);
+
+	save_dsp(current);
+
+	preempt_enable();
+
+	*dst = *src;
+	return 0;
+}
+
 int copy_thread(unsigned long clone_flags, unsigned long usp,
 	unsigned long arg, struct task_struct *p)
 {
@@ -92,18 +116,6 @@
 
 	childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
 
-	preempt_disable();
-
-	if (is_msa_enabled())
-		save_msa(p);
-	else if (is_fpu_owner())
-		save_fp(p);
-
-	if (cpu_has_dsp)
-		save_dsp(p);
-
-	preempt_enable();
-
 	/* set up new TSS. */
 	childregs = (struct pt_regs *) childksp - 1;
 	/*  Put the stack after the struct pt_regs.  */
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 9d1487d..5104528 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -770,6 +770,8 @@
 	long ret = 0;
 	user_exit();
 
+	current_thread_info()->syscall = syscall;
+
 	if (secure_computing() == -1)
 		return -1;
 
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 00cad10..6e8de80 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -181,6 +181,7 @@
 	sll	t1, t0, 2
 	beqz	v0, einval
 	lw	t2, sys_call_table(t1)		# syscall routine
+	sw	a0, PT_R2(sp)			# call routine directly on restart
 
 	/* Some syscalls like execve get their arguments from struct pt_regs
 	   and claim zero arguments in the syscall table. Thus we have to
@@ -580,3 +581,4 @@
 	PTR	sys_getrandom
 	PTR	sys_memfd_create
 	PTR	sys_bpf				/* 4355 */
+	PTR	sys_execveat
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 5251565..ad4d4463 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -435,4 +435,5 @@
 	PTR	sys_getrandom
 	PTR	sys_memfd_create
 	PTR	sys_bpf				/* 5315 */
+	PTR	sys_execveat
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 77e7439..446cc65 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -428,4 +428,5 @@
 	PTR	sys_getrandom
 	PTR	sys_memfd_create
 	PTR	sys_bpf
+	PTR	compat_sys_execveat		/* 6320 */
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 6f8db9f..d07b210 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -186,6 +186,7 @@
 	dsll	t1, t0, 3
 	beqz	v0, einval
 	ld	t2, sys32_call_table(t1)		# syscall routine
+	sd	a0, PT_R2(sp)		# call routine directly on restart
 
 	move	a0, a1			# shift argument registers
 	move	a1, a2
@@ -565,4 +566,5 @@
 	PTR	sys_getrandom
 	PTR	sys_memfd_create
 	PTR	sys_bpf				/* 4355 */
+	PTR	compat_sys_execveat
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index 1e0a93c..e36a859 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -44,8 +44,8 @@
 	struct cpuinfo_mips *c __maybe_unused = &current_cpu_data;
 
 	/* Assume GIC is present */
-	change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 | STATUSF_IP6 |
-				 STATUSF_IP7);
+	change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP4 |
+				 STATUSF_IP5 | STATUSF_IP6 | STATUSF_IP7);
 
 	/* Enable per-cpu interrupts: platform specific */
 
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index ad86951..17ea705 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -161,7 +161,8 @@
 #ifdef CONFIG_MIPS_GIC
 	/* This is Malta specific: IPI,performance and timer interrupts */
 	if (gic_present)
-		change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 |
+		change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 |
+					 STATUSF_IP4 | STATUSF_IP5 |
 					 STATUSF_IP6 | STATUSF_IP7);
 	else
 #endif
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index c94c4e9..1c0d8c5 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -123,10 +123,10 @@
 	unsigned int cpu;
 
 	cpu_probe();
-	cpu_report();
 	per_cpu_trap_init(false);
 	mips_clockevent_init();
 	mp_ops->init_secondary();
+	cpu_report();
 
 	/*
 	 * XXX parity protection should be folded in here when it's converted
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index ad3d203..c3b41e2 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1231,7 +1231,8 @@
 
 		/* Restore the scalar FP control & status register */
 		if (!was_fpu_owner)
-			asm volatile("ctc1 %0, $31" : : "r"(current->thread.fpu.fcr31));
+			write_32bit_cp1_register(CP1_STATUS,
+						 current->thread.fpu.fcr31);
 	}
 
 out:
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index 30e334e..2ae1282 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -20,6 +20,7 @@
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select KVM_MMIO
+	select SRCU
 	---help---
 	  Support for hosting Guest kernels.
 	  Currently supported on MIPS32 processors.
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index e90b2e8..30639a6 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -489,6 +489,8 @@
 #ifdef CONFIG_64BIT
 		pg |= PG_ELPA;
 #endif
+		if (cpu_has_rixiex)
+			pg |= PG_IEC;
 		write_c0_pagegrain(pg);
 	}
 
diff --git a/arch/mn10300/include/asm/cacheflush.h b/arch/mn10300/include/asm/cacheflush.h
index faed902..6d6df83 100644
--- a/arch/mn10300/include/asm/cacheflush.h
+++ b/arch/mn10300/include/asm/cacheflush.h
@@ -159,13 +159,6 @@
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
 	memcpy(dst, src, len)
 
-/*
- * Internal debugging function
- */
-#ifdef CONFIG_DEBUG_PAGEALLOC
-extern void kernel_map_pages(struct page *page, int numpages, int enable);
-#endif
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_CACHEFLUSH_H */
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 34429d5..d194c04 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -159,9 +159,11 @@
 bad_area_nosemaphore:
 	/* User mode accesses just cause a SIGSEGV */
 	if (user_mode(regs)) {
-		pr_alert("%s: unhandled page fault (%d) at 0x%08lx, "
-			"cause %ld\n", current->comm, SIGSEGV, address, cause);
-		show_regs(regs);
+		if (unhandled_signal(current, SIGSEGV) && printk_ratelimit()) {
+			pr_info("%s: unhandled page fault (%d) at 0x%08lx, "
+				"cause %ld\n", current->comm, SIGSEGV, address, cause);
+			show_regs(regs);
+		}
 		_exception(SIGSEGV, regs, code, address);
 		return;
 	}
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 5b93122..30b35ff 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -60,13 +60,6 @@
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
 	memcpy(dst, src, len)
 
-
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-/* internal debugging function */
-void kernel_map_pages(struct page *page, int numpages, int enable);
-#endif
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_POWERPC_CACHEFLUSH_H */
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index f5769f1..11850f3 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -21,6 +21,7 @@
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_EVENTFD
+	select SRCU
 
 config KVM_BOOK3S_HANDLER
 	bool
diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h
index 3e20383..58fae7d 100644
--- a/arch/s390/include/asm/cacheflush.h
+++ b/arch/s390/include/asm/cacheflush.h
@@ -4,10 +4,6 @@
 /* Caches aren't brain-dead on the s390. */
 #include <asm-generic/cacheflush.h>
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-void kernel_map_pages(struct page *page, int numpages, int enable);
-#endif
-
 int set_memory_ro(unsigned long addr, int numpages);
 int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 646db9c4..5fce52c 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -28,6 +28,7 @@
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
+	select SRCU
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work
diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h
index 3896537..68513c4 100644
--- a/arch/sparc/include/asm/cacheflush_64.h
+++ b/arch/sparc/include/asm/cacheflush_64.h
@@ -74,11 +74,6 @@
 #define flush_cache_vmap(start, end)		do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-/* internal debugging function */
-void kernel_map_pages(struct page *page, int numpages, int enable);
-#endif
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _SPARC64_CACHEFLUSH_H */
diff --git a/arch/tile/kvm/Kconfig b/arch/tile/kvm/Kconfig
index 2298cb1..1e968f7 100644
--- a/arch/tile/kvm/Kconfig
+++ b/arch/tile/kvm/Kconfig
@@ -21,6 +21,7 @@
 	depends on HAVE_KVM && MODULES
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select SRCU
 	---help---
 	  Support hosting paravirtualized guest machines.
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0dc9d01..85588a8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -138,6 +138,7 @@
 	select HAVE_ACPI_APEI_NMI if ACPI
 	select ACPI_LEGACY_TABLES_LOOKUP if ACPI
 	select X86_FEATURE_NAMES if PROC_FS
+	select SRCU
 
 config INSTRUCTION_DECODER
 	def_bool y
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 15c2909..36a8361 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -552,7 +552,7 @@
 	int error;
 
 	if (paravirt_enabled() || dis_ucode_ldr)
-		return 0;
+		return -EINVAL;
 
 	if (c->x86_vendor == X86_VENDOR_INTEL)
 		microcode_ops = init_intel_microcode();
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index f9d16ff..7dc7ba5 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -40,6 +40,7 @@
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_VFIO
+	select SRCU
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 7b20bcc..2fb3847 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -448,6 +448,22 @@
 			DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"),
 		},
 	},
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"),
+                },
+        },
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"),
+                },
+        },
 	{}
 };
 
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 44b9271..852aa4c 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -293,7 +293,6 @@
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0801, mrst_power_off_unused_dev);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0809, mrst_power_off_unused_dev);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x080C, mrst_power_off_unused_dev);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0812, mrst_power_off_unused_dev);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0815, mrst_power_off_unused_dev);
 
 /*
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 6774a0e..1630a20 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -15,26 +15,6 @@
 
 static void blk_mq_sysfs_release(struct kobject *kobj)
 {
-	struct request_queue *q;
-
-	q = container_of(kobj, struct request_queue, mq_kobj);
-	free_percpu(q->queue_ctx);
-}
-
-static void blk_mq_ctx_release(struct kobject *kobj)
-{
-	struct blk_mq_ctx *ctx;
-
-	ctx = container_of(kobj, struct blk_mq_ctx, kobj);
-	kobject_put(&ctx->queue->mq_kobj);
-}
-
-static void blk_mq_hctx_release(struct kobject *kobj)
-{
-	struct blk_mq_hw_ctx *hctx;
-
-	hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj);
-	kfree(hctx);
 }
 
 struct blk_mq_ctx_sysfs_entry {
@@ -338,13 +318,13 @@
 static struct kobj_type blk_mq_ctx_ktype = {
 	.sysfs_ops	= &blk_mq_sysfs_ops,
 	.default_attrs	= default_ctx_attrs,
-	.release	= blk_mq_ctx_release,
+	.release	= blk_mq_sysfs_release,
 };
 
 static struct kobj_type blk_mq_hw_ktype = {
 	.sysfs_ops	= &blk_mq_hw_sysfs_ops,
 	.default_attrs	= default_hw_ctx_attrs,
-	.release	= blk_mq_hctx_release,
+	.release	= blk_mq_sysfs_release,
 };
 
 static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx)
@@ -375,7 +355,6 @@
 		return ret;
 
 	hctx_for_each_ctx(hctx, ctx, i) {
-		kobject_get(&q->mq_kobj);
 		ret = kobject_add(&ctx->kobj, &hctx->kobj, "cpu%u", ctx->cpu);
 		if (ret)
 			break;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9ee3b87..2390c55 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1867,6 +1867,27 @@
 	mutex_unlock(&set->tag_list_lock);
 }
 
+/*
+ * It is the actual release handler for mq, but we do it from
+ * request queue's release handler for avoiding use-after-free
+ * and headache because q->mq_kobj shouldn't have been introduced,
+ * but we can't group ctx/kctx kobj without it.
+ */
+void blk_mq_release(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	/* hctx kobj stays in hctx */
+	queue_for_each_hw_ctx(q, hctx, i)
+		kfree(hctx);
+
+	kfree(q->queue_hw_ctx);
+
+	/* ctx kobj stays in queue_ctx */
+	free_percpu(q->queue_ctx);
+}
+
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 {
 	struct blk_mq_hw_ctx **hctxs;
@@ -2000,10 +2021,8 @@
 
 	percpu_ref_exit(&q->mq_usage_counter);
 
-	kfree(q->queue_hw_ctx);
 	kfree(q->mq_map);
 
-	q->queue_hw_ctx = NULL;
 	q->mq_map = NULL;
 
 	mutex_lock(&all_q_mutex);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 4f4f943..6a48c4c 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -62,6 +62,8 @@
 
 extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
 
+void blk_mq_release(struct request_queue *q);
+
 /*
  * Basic implementation of sparser bitmap, allowing the user to spread
  * the bits over more cachelines.
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 935ea2a..faaf36a 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -517,6 +517,8 @@
 
 	if (!q->mq_ops)
 		blk_free_flush_queue(q->fq);
+	else
+		blk_mq_release(q);
 
 	blk_trace_shutdown(q);
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 4f3febf..e75737f 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -1,7 +1,7 @@
 /*
  * ACPI support for Intel Lynxpoint LPSS.
  *
- * Copyright (C) 2013, 2014, Intel Corporation
+ * Copyright (C) 2013, Intel Corporation
  * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
  *          Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  *
@@ -60,8 +60,6 @@
 #define LPSS_CLK_DIVIDER		BIT(2)
 #define LPSS_LTR			BIT(3)
 #define LPSS_SAVE_CTX			BIT(4)
-#define LPSS_DEV_PROXY			BIT(5)
-#define LPSS_PROXY_REQ			BIT(6)
 
 struct lpss_private_data;
 
@@ -72,10 +70,8 @@
 	void (*setup)(struct lpss_private_data *pdata);
 };
 
-static struct device *proxy_device;
-
 static struct lpss_device_desc lpss_dma_desc = {
-	.flags = LPSS_CLK | LPSS_PROXY_REQ,
+	.flags = LPSS_CLK,
 };
 
 struct lpss_private_data {
@@ -150,24 +146,22 @@
 };
 
 static struct lpss_device_desc byt_uart_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX |
-		 LPSS_DEV_PROXY,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
 
 static struct lpss_device_desc byt_spi_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX |
-		 LPSS_DEV_PROXY,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.prv_offset = 0x400,
 };
 
 static struct lpss_device_desc byt_sdio_dev_desc = {
-	.flags = LPSS_CLK | LPSS_DEV_PROXY,
+	.flags = LPSS_CLK,
 };
 
 static struct lpss_device_desc byt_i2c_dev_desc = {
-	.flags = LPSS_CLK | LPSS_SAVE_CTX | LPSS_DEV_PROXY,
+	.flags = LPSS_CLK | LPSS_SAVE_CTX,
 	.prv_offset = 0x800,
 	.setup = byt_i2c_setup,
 };
@@ -374,8 +368,6 @@
 	adev->driver_data = pdata;
 	pdev = acpi_create_platform_device(adev);
 	if (!IS_ERR_OR_NULL(pdev)) {
-		if (!proxy_device && dev_desc->flags & LPSS_DEV_PROXY)
-			proxy_device = &pdev->dev;
 		return 1;
 	}
 
@@ -600,14 +592,7 @@
 	if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
 		acpi_lpss_save_ctx(dev, pdata);
 
-	ret = acpi_dev_runtime_suspend(dev);
-	if (ret)
-		return ret;
-
-	if (pdata->dev_desc->flags & LPSS_PROXY_REQ && proxy_device)
-		return pm_runtime_put_sync_suspend(proxy_device);
-
-	return 0;
+	return acpi_dev_runtime_suspend(dev);
 }
 
 static int acpi_lpss_runtime_resume(struct device *dev)
@@ -615,12 +600,6 @@
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
 	int ret;
 
-	if (pdata->dev_desc->flags & LPSS_PROXY_REQ && proxy_device) {
-		ret = pm_runtime_get_sync(proxy_device);
-		if (ret)
-			return ret;
-	}
-
 	ret = acpi_dev_runtime_resume(dev);
 	if (ret)
 		return ret;
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 0da5865..beb8b27 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -51,9 +51,11 @@
 struct regmap {
 	union {
 		struct mutex mutex;
-		spinlock_t spinlock;
+		struct {
+			spinlock_t spinlock;
+			unsigned long spinlock_flags;
+		};
 	};
-	unsigned long spinlock_flags;
 	regmap_lock lock;
 	regmap_unlock unlock;
 	void *lock_arg; /* This is passed to lock/unlock functions */
@@ -233,6 +235,10 @@
 
 void regmap_async_complete_cb(struct regmap_async *async, int ret);
 
+enum regmap_endian regmap_get_val_endian(struct device *dev,
+					 const struct regmap_bus *bus,
+					 const struct regmap_config *config);
+
 extern struct regcache_ops regcache_rbtree_ops;
 extern struct regcache_ops regcache_lzo_ops;
 extern struct regcache_ops regcache_flat_ops;
diff --git a/drivers/base/regmap/regmap-ac97.c b/drivers/base/regmap/regmap-ac97.c
index e4c45d2..8d304e2 100644
--- a/drivers/base/regmap/regmap-ac97.c
+++ b/drivers/base/regmap/regmap-ac97.c
@@ -74,8 +74,8 @@
 }
 
 static const struct regmap_bus ac97_regmap_bus = {
-		.reg_write = regmap_ac97_reg_write,
-		.reg_read = regmap_ac97_reg_read,
+	.reg_write = regmap_ac97_reg_write,
+	.reg_read = regmap_ac97_reg_read,
 };
 
 /**
diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c
index 053150a..4b76e33 100644
--- a/drivers/base/regmap/regmap-i2c.c
+++ b/drivers/base/regmap/regmap-i2c.c
@@ -14,6 +14,7 @@
 #include <linux/i2c.h>
 #include <linux/module.h>
 
+#include "internal.h"
 
 static int regmap_smbus_byte_reg_read(void *context, unsigned int reg,
 				      unsigned int *val)
@@ -87,6 +88,42 @@
 	.reg_read = regmap_smbus_word_reg_read,
 };
 
+static int regmap_smbus_word_read_swapped(void *context, unsigned int reg,
+					  unsigned int *val)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	int ret;
+
+	if (reg > 0xff)
+		return -EINVAL;
+
+	ret = i2c_smbus_read_word_swapped(i2c, reg);
+	if (ret < 0)
+		return ret;
+
+	*val = ret;
+
+	return 0;
+}
+
+static int regmap_smbus_word_write_swapped(void *context, unsigned int reg,
+					   unsigned int val)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+
+	if (val > 0xffff || reg > 0xff)
+		return -EINVAL;
+
+	return i2c_smbus_write_word_swapped(i2c, reg, val);
+}
+
+static struct regmap_bus regmap_smbus_word_swapped = {
+	.reg_write = regmap_smbus_word_write_swapped,
+	.reg_read = regmap_smbus_word_read_swapped,
+};
+
 static int regmap_i2c_write(void *context, const void *data, size_t count)
 {
 	struct device *dev = context;
@@ -180,7 +217,14 @@
 	else if (config->val_bits == 16 && config->reg_bits == 8 &&
 		 i2c_check_functionality(i2c->adapter,
 					 I2C_FUNC_SMBUS_WORD_DATA))
-		return &regmap_smbus_word;
+		switch (regmap_get_val_endian(&i2c->dev, NULL, config)) {
+		case REGMAP_ENDIAN_LITTLE:
+			return &regmap_smbus_word;
+		case REGMAP_ENDIAN_BIG:
+			return &regmap_smbus_word_swapped;
+		default:		/* everything else is not supported */
+			break;
+		}
 	else if (config->val_bits == 8 && config->reg_bits == 8 &&
 		 i2c_check_functionality(i2c->adapter,
 					 I2C_FUNC_SMBUS_BYTE_DATA))
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index d2f8a81..f99b098 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -473,9 +473,9 @@
 	return REGMAP_ENDIAN_BIG;
 }
 
-static enum regmap_endian regmap_get_val_endian(struct device *dev,
-					const struct regmap_bus *bus,
-					const struct regmap_config *config)
+enum regmap_endian regmap_get_val_endian(struct device *dev,
+					 const struct regmap_bus *bus,
+					 const struct regmap_config *config)
 {
 	struct device_node *np;
 	enum regmap_endian endian;
@@ -513,6 +513,7 @@
 	/* Use this if no other value was found */
 	return REGMAP_ENDIAN_BIG;
 }
+EXPORT_SYMBOL_GPL(regmap_get_val_endian);
 
 /**
  * regmap_init(): Initialise register map
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 04645c0..9cd6968 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -569,19 +569,19 @@
 	__u32 c = f->pool[2],	d = f->pool[3];
 
 	a += b;			c += d;
-	b = rol32(a, 6);	d = rol32(c, 27);
+	b = rol32(b, 6);	d = rol32(d, 27);
 	d ^= a;			b ^= c;
 
 	a += b;			c += d;
-	b = rol32(a, 16);	d = rol32(c, 14);
+	b = rol32(b, 16);	d = rol32(d, 14);
 	d ^= a;			b ^= c;
 
 	a += b;			c += d;
-	b = rol32(a, 6);	d = rol32(c, 27);
+	b = rol32(b, 6);	d = rol32(d, 27);
 	d ^= a;			b ^= c;
 
 	a += b;			c += d;
-	b = rol32(a, 16);	d = rol32(c, 14);
+	b = rol32(b, 16);	d = rol32(d, 14);
 	d ^= a;			b ^= c;
 
 	f->pool[0] = a;  f->pool[1] = b;
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 3f44f29..91f8613 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -13,6 +13,7 @@
 	bool
 	select HAVE_CLK_PREPARE
 	select CLKDEV_LOOKUP
+	select SRCU
 	---help---
 	  The common clock framework is a single definition of struct
 	  clk, useful across many platforms, as well as an
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 29b2ef5..a171fef 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -2,6 +2,7 @@
 
 config CPU_FREQ
 	bool "CPU Frequency scaling"
+	select SRCU
 	help
 	  CPU Frequency scaling allows you to change the clock speed of 
 	  CPUs on the fly. This is a nice method to save power, because 
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index faf4e70..3891f67 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -1,5 +1,6 @@
 menuconfig PM_DEVFREQ
 	bool "Generic Dynamic Voltage and Frequency Scaling (DVFS) support"
+	select SRCU
 	help
 	  A device may have a list of frequencies and voltages available.
 	  devfreq, a generic DVFS framework can be registered for a device
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index da9c316..eea5d7e 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -801,9 +801,11 @@
 		client->irq = irq_of_parse_and_map(client->dev.of_node, 0);
 	} else {
 		pdata = dev_get_platdata(&client->dev);
-		if (!pdata || !gpio_is_valid(pdata->base)) {
-			dev_dbg(&client->dev, "invalid platform data\n");
-			return -EINVAL;
+		if (!pdata) {
+			pdata = devm_kzalloc(&client->dev,
+					sizeof(struct mcp23s08_platform_data),
+					GFP_KERNEL);
+			pdata->base = -1;
 		}
 	}
 
@@ -924,10 +926,11 @@
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
 		pdata = dev_get_platdata(&spi->dev);
-		if (!pdata || !gpio_is_valid(pdata->base)) {
-			dev_dbg(&spi->dev,
-					"invalid or missing platform data\n");
-			return -EINVAL;
+		if (!pdata) {
+			pdata = devm_kzalloc(&spi->dev,
+					sizeof(struct mcp23s08_platform_data),
+					GFP_KERNEL);
+			pdata->base = -1;
 		}
 
 		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) {
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 30646cf..f476ae2 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -88,6 +88,8 @@
 #define BANK_USED(bank) (bank->mod_usage || bank->irq_usage)
 #define LINE_USED(line, offset) (line & (BIT(offset)))
 
+static void omap_gpio_unmask_irq(struct irq_data *d);
+
 static int omap_irq_to_gpio(struct gpio_bank *bank, unsigned int gpio_irq)
 {
 	return bank->chip.base + gpio_irq;
@@ -477,6 +479,16 @@
 	return readl_relaxed(reg) & mask;
 }
 
+static void omap_gpio_init_irq(struct gpio_bank *bank, unsigned gpio,
+			       unsigned offset)
+{
+	if (!LINE_USED(bank->mod_usage, offset)) {
+		omap_enable_gpio_module(bank, offset);
+		omap_set_gpio_direction(bank, offset, 1);
+	}
+	bank->irq_usage |= BIT(GPIO_INDEX(bank, gpio));
+}
+
 static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
 {
 	struct gpio_bank *bank = omap_irq_data_get_bank(d);
@@ -506,15 +518,11 @@
 	spin_lock_irqsave(&bank->lock, flags);
 	offset = GPIO_INDEX(bank, gpio);
 	retval = omap_set_gpio_triggering(bank, offset, type);
-	if (!LINE_USED(bank->mod_usage, offset)) {
-		omap_enable_gpio_module(bank, offset);
-		omap_set_gpio_direction(bank, offset, 1);
-	} else if (!omap_gpio_is_input(bank, BIT(offset))) {
+	omap_gpio_init_irq(bank, gpio, offset);
+	if (!omap_gpio_is_input(bank, BIT(offset))) {
 		spin_unlock_irqrestore(&bank->lock, flags);
 		return -EINVAL;
 	}
-
-	bank->irq_usage |= BIT(GPIO_INDEX(bank, gpio));
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
@@ -792,6 +800,24 @@
 	pm_runtime_put(bank->dev);
 }
 
+static unsigned int omap_gpio_irq_startup(struct irq_data *d)
+{
+	struct gpio_bank *bank = omap_irq_data_get_bank(d);
+	unsigned int gpio = omap_irq_to_gpio(bank, d->hwirq);
+	unsigned long flags;
+	unsigned offset = GPIO_INDEX(bank, gpio);
+
+	if (!BANK_USED(bank))
+		pm_runtime_get_sync(bank->dev);
+
+	spin_lock_irqsave(&bank->lock, flags);
+	omap_gpio_init_irq(bank, gpio, offset);
+	spin_unlock_irqrestore(&bank->lock, flags);
+	omap_gpio_unmask_irq(d);
+
+	return 0;
+}
+
 static void omap_gpio_irq_shutdown(struct irq_data *d)
 {
 	struct gpio_bank *bank = omap_irq_data_get_bank(d);
@@ -1181,6 +1207,7 @@
 	if (!irqc)
 		return -ENOMEM;
 
+	irqc->irq_startup = omap_gpio_irq_startup,
 	irqc->irq_shutdown = omap_gpio_irq_shutdown,
 	irqc->irq_ack = omap_gpio_ack_irq,
 	irqc->irq_mask = omap_gpio_mask_irq,
diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index f62aa11..7722ed5 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -648,6 +648,7 @@
 		if (tdev != NULL) {
 			status = sysfs_create_link(&dev->kobj, &tdev->kobj,
 						name);
+			put_device(tdev);
 		} else {
 			status = -ENODEV;
 		}
@@ -695,7 +696,7 @@
 	}
 
 	status = sysfs_set_active_low(desc, dev, value);
-
+	put_device(dev);
 unlock:
 	mutex_unlock(&sysfs_lock);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 0d8694f..0fd59279 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -822,7 +822,7 @@
 	 * Unconditionally decrement this counter, regardless of the queue's
 	 * type.
 	 */
-	dqm->total_queue_count++;
+	dqm->total_queue_count--;
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
 	mutex_unlock(&dqm->lock);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index a8be6df..1c385c2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -95,10 +95,10 @@
 	}
 
 	/* Verify module parameters */
-	if ((max_num_of_queues_per_device < 0) ||
+	if ((max_num_of_queues_per_device < 1) ||
 		(max_num_of_queues_per_device >
 			KFD_MAX_NUM_OF_QUEUES_PER_DEVICE)) {
-		pr_err("kfd: max_num_of_queues_per_device must be between 0 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n");
+		pr_err("kfd: max_num_of_queues_per_device must be between 1 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n");
 		return -1;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index f37cf5e..2fda1927 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -315,7 +315,11 @@
 	BUG_ON(!pqm);
 
 	pqn = get_queue_by_qid(pqm, qid);
-	BUG_ON(!pqn);
+	if (!pqn) {
+		pr_debug("amdkfd: No queue %d exists for update operation\n",
+				qid);
+		return -EFAULT;
+	}
 
 	pqn->q->properties.queue_address = p->queue_address;
 	pqn->q->properties.queue_size = p->queue_size;
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index c2a1cba..b914003 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -16,9 +16,12 @@
 #include "cirrus_drv.h"
 
 int cirrus_modeset = -1;
+int cirrus_bpp = 24;
 
 MODULE_PARM_DESC(modeset, "Disable/Enable modesetting");
 module_param_named(modeset, cirrus_modeset, int, 0400);
+MODULE_PARM_DESC(bpp, "Max bits-per-pixel (default:24)");
+module_param_named(bpp, cirrus_bpp, int, 0400);
 
 /*
  * This is the generic driver code. This binds the driver to the drm core,
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index 693a456..7050615 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -262,4 +262,7 @@
 
 int cirrus_bo_push_sysram(struct cirrus_bo *bo);
 int cirrus_bo_pin(struct cirrus_bo *bo, u32 pl_flag, u64 *gpu_addr);
+
+extern int cirrus_bpp;
+
 #endif				/* __CIRRUS_DRV_H__ */
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index 4c2d68e..e4b9766 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -320,6 +320,8 @@
 	const int max_pitch = 0x1FF << 3; /* (4096 - 1) & ~111b bytes */
 	const int max_size = cdev->mc.vram_size;
 
+	if (bpp > cirrus_bpp)
+		return false;
 	if (bpp > 32)
 		return false;
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index 99d4a74..61385f2 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -501,8 +501,13 @@
 	int count;
 
 	/* Just add a static list of modes */
-	count = drm_add_modes_noedid(connector, 1280, 1024);
-	drm_set_preferred_mode(connector, 1024, 768);
+	if (cirrus_bpp <= 24) {
+		count = drm_add_modes_noedid(connector, 1280, 1024);
+		drm_set_preferred_mode(connector, 1024, 768);
+	} else {
+		count = drm_add_modes_noedid(connector, 800, 600);
+		drm_set_preferred_mode(connector, 800, 600);
+	}
 	return count;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index 9e7f23dd..87d5fb2 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -34,7 +34,8 @@
 
 static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
 				    uint64_t saddr, uint64_t daddr,
-				    int flag, int n)
+				    int flag, int n,
+				    struct reservation_object *resv)
 {
 	unsigned long start_jiffies;
 	unsigned long end_jiffies;
@@ -47,12 +48,12 @@
 		case RADEON_BENCHMARK_COPY_DMA:
 			fence = radeon_copy_dma(rdev, saddr, daddr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						resv);
 			break;
 		case RADEON_BENCHMARK_COPY_BLIT:
 			fence = radeon_copy_blit(rdev, saddr, daddr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 resv);
 			break;
 		default:
 			DRM_ERROR("Unknown copy method\n");
@@ -120,7 +121,8 @@
 
 	if (rdev->asic->copy.dma) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_DMA, n);
+						RADEON_BENCHMARK_COPY_DMA, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
@@ -130,7 +132,8 @@
 
 	if (rdev->asic->copy.blit) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_BLIT, n);
+						RADEON_BENCHMARK_COPY_BLIT, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 1021169..913fafa 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -960,6 +960,9 @@
 	if (pll->flags & RADEON_PLL_USE_FRAC_FB_DIV &&
 	    pll->flags & RADEON_PLL_USE_REF_DIV)
 		ref_div_max = pll->reference_div;
+	else if (pll->flags & RADEON_PLL_PREFER_MINM_OVER_MAXP)
+		/* fix for problems on RS880 */
+		ref_div_max = min(pll->max_ref_div, 7u);
 	else
 		ref_div_max = pll->max_ref_div;
 
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index d0b4f7d..ac3c131 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -146,7 +146,8 @@
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return 0;
 	}
 
@@ -176,7 +177,8 @@
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 3cf9c1f..686411e 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -605,14 +605,14 @@
 			return -ENOMEM;
 		}
 
-		vm = &fpriv->vm;
-		r = radeon_vm_init(rdev, vm);
-		if (r) {
-			kfree(fpriv);
-			return r;
-		}
-
 		if (rdev->accel_working) {
+			vm = &fpriv->vm;
+			r = radeon_vm_init(rdev, vm);
+			if (r) {
+				kfree(fpriv);
+				return r;
+			}
+
 			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 			if (r) {
 				radeon_vm_fini(rdev, vm);
@@ -668,9 +668,9 @@
 					radeon_vm_bo_rmv(rdev, vm->ib_bo_va);
 				radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 			}
+			radeon_vm_fini(rdev, vm);
 		}
 
-		radeon_vm_fini(rdev, vm);
 		kfree(fpriv);
 		file_priv->driver_priv = NULL;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 07b506b..79181816 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -119,11 +119,11 @@
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, gtt_addr, vram_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, gtt_addr, vram_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed GTT->VRAM copy %d\n", i);
 			r = PTR_ERR(fence);
@@ -170,11 +170,11 @@
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, vram_addr, gtt_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, vram_addr, gtt_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed VRAM->GTT copy %d\n", i);
 			r = PTR_ERR(fence);
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 06d2246..2a5a4a9 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -743,9 +743,11 @@
 	 */
 
 	/* NI is optimized for 256KB fragments, SI and newer for 64KB */
-	uint64_t frag_flags = rdev->family == CHIP_CAYMAN ?
+	uint64_t frag_flags = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ?
 			R600_PTE_FRAG_256KB : R600_PTE_FRAG_64KB;
-	uint64_t frag_align = rdev->family == CHIP_CAYMAN ? 0x200 : 0x80;
+	uint64_t frag_align = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ? 0x200 : 0x80;
 
 	uint64_t frag_start = ALIGN(pe_start, frag_align);
 	uint64_t frag_end = pe_end & ~(frag_align - 1);
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index a7de26d..d931cbb 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1389,6 +1389,7 @@
 config SENSORS_ADS7828
 	tristate "Texas Instruments ADS7828 and compatibles"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	  If you say yes here you get support for Texas Instruments ADS7828 and
 	  ADS7830 8-channel A/D converters. ADS7828 resolution is 12-bit, while
@@ -1430,8 +1431,8 @@
 	tristate "Texas Instruments INA219 and compatibles"
 	depends on I2C
 	help
-	  If you say yes here you get support for INA219, INA220, INA226, and
-	  INA230 power monitor chips.
+	  If you say yes here you get support for INA219, INA220, INA226,
+	  INA230, and INA231 power monitor chips.
 
 	  The INA2xx driver is configured for the default configuration of
 	  the part as described in the datasheet.
diff --git a/drivers/hwmon/abx500.c b/drivers/hwmon/abx500.c
index 1387596..6cb89c0 100644
--- a/drivers/hwmon/abx500.c
+++ b/drivers/hwmon/abx500.c
@@ -221,7 +221,7 @@
 	struct abx500_temp *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 
-	return sprintf(buf, "%ld\n", data->min[attr->index]);
+	return sprintf(buf, "%lu\n", data->min[attr->index]);
 }
 
 static ssize_t show_max(struct device *dev,
@@ -230,7 +230,7 @@
 	struct abx500_temp *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 
-	return sprintf(buf, "%ld\n", data->max[attr->index]);
+	return sprintf(buf, "%lu\n", data->max[attr->index]);
 }
 
 static ssize_t show_max_hyst(struct device *dev,
@@ -239,7 +239,7 @@
 	struct abx500_temp *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 
-	return sprintf(buf, "%ld\n", data->max_hyst[attr->index]);
+	return sprintf(buf, "%lu\n", data->max_hyst[attr->index]);
 }
 
 static ssize_t show_min_alarm(struct device *dev,
diff --git a/drivers/hwmon/ad7314.c b/drivers/hwmon/ad7314.c
index f4f9b21..1195546 100644
--- a/drivers/hwmon/ad7314.c
+++ b/drivers/hwmon/ad7314.c
@@ -16,6 +16,7 @@
 #include <linux/err.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <linux/bitops.h>
 
 /*
  * AD7314 temperature masks
@@ -67,7 +68,7 @@
 	switch (spi_get_device_id(chip->spi_dev)->driver_data) {
 	case ad7314:
 		data = (ret & AD7314_TEMP_MASK) >> AD7314_TEMP_SHIFT;
-		data = (data << 6) >> 6;
+		data = sign_extend32(data, 9);
 
 		return sprintf(buf, "%d\n", 250 * data);
 	case adt7301:
@@ -78,7 +79,7 @@
 		 * register.  1lsb - 31.25 milli degrees centigrade
 		 */
 		data = ret & ADT7301_TEMP_MASK;
-		data = (data << 2) >> 2;
+		data = sign_extend32(data, 13);
 
 		return sprintf(buf, "%d\n",
 			       DIV_ROUND_CLOSEST(data * 3125, 100));
diff --git a/drivers/hwmon/adc128d818.c b/drivers/hwmon/adc128d818.c
index 0625e50..ad2b47e 100644
--- a/drivers/hwmon/adc128d818.c
+++ b/drivers/hwmon/adc128d818.c
@@ -27,6 +27,7 @@
 #include <linux/err.h>
 #include <linux/regulator/consumer.h>
 #include <linux/mutex.h>
+#include <linux/bitops.h>
 
 /* Addresses to scan
  * The chip also supports addresses 0x35..0x37. Don't scan those addresses
@@ -189,7 +190,7 @@
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
-	temp = (data->temp[index] << 7) >> 7;	/* sign extend */
+	temp = sign_extend32(data->temp[index], 8);
 	return sprintf(buf, "%d\n", temp * 500);/* 0.5 degrees C resolution */
 }
 
diff --git a/drivers/hwmon/ads7828.c b/drivers/hwmon/ads7828.c
index a622d40..bce4e9f 100644
--- a/drivers/hwmon/ads7828.c
+++ b/drivers/hwmon/ads7828.c
@@ -30,14 +30,12 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/i2c.h>
 #include <linux/init.h>
-#include <linux/jiffies.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/platform_data/ads7828.h>
+#include <linux/regmap.h>
 #include <linux/slab.h>
 
 /* The ADS7828 registers */
-#define ADS7828_NCH		8	/* 8 channels supported */
 #define ADS7828_CMD_SD_SE	0x80	/* Single ended inputs */
 #define ADS7828_CMD_PD1		0x04	/* Internal vref OFF && A/D ON */
 #define ADS7828_CMD_PD3		0x0C	/* Internal vref ON && A/D ON */
@@ -50,17 +48,9 @@
 
 /* Client specific data */
 struct ads7828_data {
-	struct i2c_client *client;
-	struct mutex update_lock;	/* Mutex protecting updates */
-	unsigned long last_updated;	/* Last updated time (in jiffies) */
-	u16 adc_input[ADS7828_NCH];	/* ADS7828_NCH samples */
-	bool valid;			/* Validity flag */
-	bool diff_input;		/* Differential input */
-	bool ext_vref;			/* External voltage reference */
-	unsigned int vref_mv;		/* voltage reference value */
+	struct regmap *regmap;
 	u8 cmd_byte;			/* Command byte without channel bits */
 	unsigned int lsb_resol;		/* Resolution of the ADC sample LSB */
-	s32 (*read_channel)(const struct i2c_client *client, u8 command);
 };
 
 /* Command byte C2,C1,C0 - see datasheet */
@@ -69,42 +59,22 @@
 	return cmd | (((ch >> 1) | (ch & 0x01) << 2) << 4);
 }
 
-/* Update data for the device (all 8 channels) */
-static struct ads7828_data *ads7828_update_device(struct device *dev)
-{
-	struct ads7828_data *data = dev_get_drvdata(dev);
-	struct i2c_client *client = data->client;
-
-	mutex_lock(&data->update_lock);
-
-	if (time_after(jiffies, data->last_updated + HZ + HZ / 2)
-			|| !data->valid) {
-		unsigned int ch;
-		dev_dbg(&client->dev, "Starting ads7828 update\n");
-
-		for (ch = 0; ch < ADS7828_NCH; ch++) {
-			u8 cmd = ads7828_cmd_byte(data->cmd_byte, ch);
-			data->adc_input[ch] = data->read_channel(client, cmd);
-		}
-		data->last_updated = jiffies;
-		data->valid = true;
-	}
-
-	mutex_unlock(&data->update_lock);
-
-	return data;
-}
-
 /* sysfs callback function */
 static ssize_t ads7828_show_in(struct device *dev, struct device_attribute *da,
 			       char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
-	struct ads7828_data *data = ads7828_update_device(dev);
-	unsigned int value = DIV_ROUND_CLOSEST(data->adc_input[attr->index] *
-					       data->lsb_resol, 1000);
+	struct ads7828_data *data = dev_get_drvdata(dev);
+	u8 cmd = ads7828_cmd_byte(data->cmd_byte, attr->index);
+	unsigned int regval;
+	int err;
 
-	return sprintf(buf, "%d\n", value);
+	err = regmap_read(data->regmap, cmd, &regval);
+	if (err < 0)
+		return err;
+
+	return sprintf(buf, "%d\n",
+		       DIV_ROUND_CLOSEST(regval * data->lsb_resol, 1000));
 }
 
 static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, ads7828_show_in, NULL, 0);
@@ -130,6 +100,16 @@
 
 ATTRIBUTE_GROUPS(ads7828);
 
+static const struct regmap_config ads2828_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 16,
+};
+
+static const struct regmap_config ads2830_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+};
+
 static int ads7828_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
@@ -137,42 +117,40 @@
 	struct ads7828_platform_data *pdata = dev_get_platdata(dev);
 	struct ads7828_data *data;
 	struct device *hwmon_dev;
+	unsigned int vref_mv = ADS7828_INT_VREF_MV;
+	bool diff_input = false;
+	bool ext_vref = false;
 
 	data = devm_kzalloc(dev, sizeof(struct ads7828_data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
 	if (pdata) {
-		data->diff_input = pdata->diff_input;
-		data->ext_vref = pdata->ext_vref;
-		if (data->ext_vref)
-			data->vref_mv = pdata->vref_mv;
+		diff_input = pdata->diff_input;
+		ext_vref = pdata->ext_vref;
+		if (ext_vref && pdata->vref_mv)
+			vref_mv = pdata->vref_mv;
 	}
 
-	/* Bound Vref with min/max values if it was provided */
-	if (data->vref_mv)
-		data->vref_mv = clamp_val(data->vref_mv,
-					  ADS7828_EXT_VREF_MV_MIN,
-					  ADS7828_EXT_VREF_MV_MAX);
-	else
-		data->vref_mv = ADS7828_INT_VREF_MV;
+	/* Bound Vref with min/max values */
+	vref_mv = clamp_val(vref_mv, ADS7828_EXT_VREF_MV_MIN,
+			    ADS7828_EXT_VREF_MV_MAX);
 
 	/* ADS7828 uses 12-bit samples, while ADS7830 is 8-bit */
 	if (id->driver_data == ads7828) {
-		data->lsb_resol = DIV_ROUND_CLOSEST(data->vref_mv * 1000, 4096);
-		data->read_channel = i2c_smbus_read_word_swapped;
+		data->lsb_resol = DIV_ROUND_CLOSEST(vref_mv * 1000, 4096);
+		data->regmap = devm_regmap_init_i2c(client,
+						    &ads2828_regmap_config);
 	} else {
-		data->lsb_resol = DIV_ROUND_CLOSEST(data->vref_mv * 1000, 256);
-		data->read_channel = i2c_smbus_read_byte_data;
+		data->lsb_resol = DIV_ROUND_CLOSEST(vref_mv * 1000, 256);
+		data->regmap = devm_regmap_init_i2c(client,
+						    &ads2830_regmap_config);
 	}
 
-	data->cmd_byte = data->ext_vref ? ADS7828_CMD_PD1 : ADS7828_CMD_PD3;
-	if (!data->diff_input)
+	data->cmd_byte = ext_vref ? ADS7828_CMD_PD1 : ADS7828_CMD_PD3;
+	if (!diff_input)
 		data->cmd_byte |= ADS7828_CMD_SD_SE;
 
-	data->client = client;
-	mutex_init(&data->update_lock);
-
 	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
 							   data,
 							   ads7828_groups);
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index e01feba..d1542b7 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -35,6 +35,7 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/jiffies.h>
 #include <linux/of.h>
+#include <linux/delay.h>
 
 #include <linux/platform_data/ina2xx.h>
 
@@ -51,7 +52,6 @@
 #define INA226_ALERT_LIMIT		0x07
 #define INA226_DIE_ID			0xFF
 
-
 /* register count */
 #define INA219_REGISTERS		6
 #define INA226_REGISTERS		8
@@ -64,6 +64,24 @@
 
 /* worst case is 68.10 ms (~14.6Hz, ina219) */
 #define INA2XX_CONVERSION_RATE		15
+#define INA2XX_MAX_DELAY		69 /* worst case delay in ms */
+
+#define INA2XX_RSHUNT_DEFAULT		10000
+
+/* bit mask for reading the averaging setting in the configuration register */
+#define INA226_AVG_RD_MASK		0x0E00
+
+#define INA226_READ_AVG(reg)		(((reg) & INA226_AVG_RD_MASK) >> 9)
+#define INA226_SHIFT_AVG(val)		((val) << 9)
+
+/* common attrs, ina226 attrs and NULL */
+#define INA2XX_MAX_ATTRIBUTE_GROUPS	3
+
+/*
+ * Both bus voltage and shunt voltage conversion times for ina226 are set
+ * to 0b0100 on POR, which translates to 2200 microseconds in total.
+ */
+#define INA226_TOTAL_CONV_TIME_DEFAULT	2200
 
 enum ina2xx_ids { ina219, ina226 };
 
@@ -81,11 +99,16 @@
 	struct i2c_client *client;
 	const struct ina2xx_config *config;
 
+	long rshunt;
+	u16 curr_config;
+
 	struct mutex update_lock;
 	bool valid;
 	unsigned long last_updated;
+	int update_interval; /* in jiffies */
 
 	int kind;
+	const struct attribute_group *groups[INA2XX_MAX_ATTRIBUTE_GROUPS];
 	u16 regs[INA2XX_MAX_REGISTERS];
 };
 
@@ -110,34 +133,156 @@
 	},
 };
 
-static struct ina2xx_data *ina2xx_update_device(struct device *dev)
+/*
+ * Available averaging rates for ina226. The indices correspond with
+ * the bit values expected by the chip (according to the ina226 datasheet,
+ * table 3 AVG bit settings, found at
+ * http://www.ti.com/lit/ds/symlink/ina226.pdf.
+ */
+static const int ina226_avg_tab[] = { 1, 4, 16, 64, 128, 256, 512, 1024 };
+
+static int ina226_avg_bits(int avg)
+{
+	int i;
+
+	/* Get the closest average from the tab. */
+	for (i = 0; i < ARRAY_SIZE(ina226_avg_tab) - 1; i++) {
+		if (avg <= (ina226_avg_tab[i] + ina226_avg_tab[i + 1]) / 2)
+			break;
+	}
+
+	return i; /* Return 0b0111 for values greater than 1024. */
+}
+
+static int ina226_reg_to_interval(u16 config)
+{
+	int avg = ina226_avg_tab[INA226_READ_AVG(config)];
+
+	/*
+	 * Multiply the total conversion time by the number of averages.
+	 * Return the result in milliseconds.
+	 */
+	return DIV_ROUND_CLOSEST(avg * INA226_TOTAL_CONV_TIME_DEFAULT, 1000);
+}
+
+static u16 ina226_interval_to_reg(int interval, u16 config)
+{
+	int avg, avg_bits;
+
+	avg = DIV_ROUND_CLOSEST(interval * 1000,
+				INA226_TOTAL_CONV_TIME_DEFAULT);
+	avg_bits = ina226_avg_bits(avg);
+
+	return (config & ~INA226_AVG_RD_MASK) | INA226_SHIFT_AVG(avg_bits);
+}
+
+static void ina226_set_update_interval(struct ina2xx_data *data)
+{
+	int ms;
+
+	ms = ina226_reg_to_interval(data->curr_config);
+	data->update_interval = msecs_to_jiffies(ms);
+}
+
+static int ina2xx_calibrate(struct ina2xx_data *data)
+{
+	u16 val = DIV_ROUND_CLOSEST(data->config->calibration_factor,
+				    data->rshunt);
+
+	return i2c_smbus_write_word_swapped(data->client,
+					    INA2XX_CALIBRATION, val);
+}
+
+/*
+ * Initialize the configuration and calibration registers.
+ */
+static int ina2xx_init(struct ina2xx_data *data)
+{
+	struct i2c_client *client = data->client;
+	int ret;
+
+	/* device configuration */
+	ret = i2c_smbus_write_word_swapped(client, INA2XX_CONFIG,
+					   data->curr_config);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Set current LSB to 1mA, shunt is in uOhms
+	 * (equation 13 in datasheet).
+	 */
+	return ina2xx_calibrate(data);
+}
+
+static int ina2xx_do_update(struct device *dev)
 {
 	struct ina2xx_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
+	int i, rv, retry;
+
+	dev_dbg(&client->dev, "Starting ina2xx update\n");
+
+	for (retry = 5; retry; retry--) {
+		/* Read all registers */
+		for (i = 0; i < data->config->registers; i++) {
+			rv = i2c_smbus_read_word_swapped(client, i);
+			if (rv < 0)
+				return rv;
+			data->regs[i] = rv;
+		}
+
+		/*
+		 * If the current value in the calibration register is 0, the
+		 * power and current registers will also remain at 0. In case
+		 * the chip has been reset let's check the calibration
+		 * register and reinitialize if needed.
+		 */
+		if (data->regs[INA2XX_CALIBRATION] == 0) {
+			dev_warn(dev, "chip not calibrated, reinitializing\n");
+
+			rv = ina2xx_init(data);
+			if (rv < 0)
+				return rv;
+
+			/*
+			 * Let's make sure the power and current registers
+			 * have been updated before trying again.
+			 */
+			msleep(INA2XX_MAX_DELAY);
+			continue;
+		}
+
+		data->last_updated = jiffies;
+		data->valid = 1;
+
+		return 0;
+	}
+
+	/*
+	 * If we're here then although all write operations succeeded, the
+	 * chip still returns 0 in the calibration register. Nothing more we
+	 * can do here.
+	 */
+	dev_err(dev, "unable to reinitialize the chip\n");
+	return -ENODEV;
+}
+
+static struct ina2xx_data *ina2xx_update_device(struct device *dev)
+{
+	struct ina2xx_data *data = dev_get_drvdata(dev);
 	struct ina2xx_data *ret = data;
+	unsigned long after;
+	int rv;
 
 	mutex_lock(&data->update_lock);
 
-	if (time_after(jiffies, data->last_updated +
-		       HZ / INA2XX_CONVERSION_RATE) || !data->valid) {
-
-		int i;
-
-		dev_dbg(&client->dev, "Starting ina2xx update\n");
-
-		/* Read all registers */
-		for (i = 0; i < data->config->registers; i++) {
-			int rv = i2c_smbus_read_word_swapped(client, i);
-			if (rv < 0) {
-				ret = ERR_PTR(rv);
-				goto abort;
-			}
-			data->regs[i] = rv;
-		}
-		data->last_updated = jiffies;
-		data->valid = 1;
+	after = data->last_updated + data->update_interval;
+	if (time_after(jiffies, after) || !data->valid) {
+		rv = ina2xx_do_update(dev);
+		if (rv < 0)
+			ret = ERR_PTR(rv);
 	}
-abort:
+
 	mutex_unlock(&data->update_lock);
 	return ret;
 }
@@ -164,6 +309,10 @@
 		/* signed register, LSB=1mA (selected), in mA */
 		val = (s16)data->regs[reg];
 		break;
+	case INA2XX_CALIBRATION:
+		val = DIV_ROUND_CLOSEST(data->config->calibration_factor,
+					data->regs[reg]);
+		break;
 	default:
 		/* programmer goofed */
 		WARN_ON_ONCE(1);
@@ -187,6 +336,85 @@
 			ina2xx_get_value(data, attr->index));
 }
 
+static ssize_t ina2xx_set_shunt(struct device *dev,
+				struct device_attribute *da,
+				const char *buf, size_t count)
+{
+	struct ina2xx_data *data = ina2xx_update_device(dev);
+	unsigned long val;
+	int status;
+
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	status = kstrtoul(buf, 10, &val);
+	if (status < 0)
+		return status;
+
+	if (val == 0 ||
+	    /* Values greater than the calibration factor make no sense. */
+	    val > data->config->calibration_factor)
+		return -EINVAL;
+
+	mutex_lock(&data->update_lock);
+	data->rshunt = val;
+	status = ina2xx_calibrate(data);
+	mutex_unlock(&data->update_lock);
+	if (status < 0)
+		return status;
+
+	return count;
+}
+
+static ssize_t ina226_set_interval(struct device *dev,
+				   struct device_attribute *da,
+				   const char *buf, size_t count)
+{
+	struct ina2xx_data *data = dev_get_drvdata(dev);
+	unsigned long val;
+	int status;
+
+	status = kstrtoul(buf, 10, &val);
+	if (status < 0)
+		return status;
+
+	if (val > INT_MAX || val == 0)
+		return -EINVAL;
+
+	mutex_lock(&data->update_lock);
+	data->curr_config = ina226_interval_to_reg(val,
+						   data->regs[INA2XX_CONFIG]);
+	status = i2c_smbus_write_word_swapped(data->client,
+					      INA2XX_CONFIG,
+					      data->curr_config);
+
+	ina226_set_update_interval(data);
+	/* Make sure the next access re-reads all registers. */
+	data->valid = 0;
+	mutex_unlock(&data->update_lock);
+	if (status < 0)
+		return status;
+
+	return count;
+}
+
+static ssize_t ina226_show_interval(struct device *dev,
+				    struct device_attribute *da, char *buf)
+{
+	struct ina2xx_data *data = ina2xx_update_device(dev);
+
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	/*
+	 * We don't use data->update_interval here as we want to display
+	 * the actual interval used by the chip and jiffies_to_msecs()
+	 * doesn't seem to be accurate enough.
+	 */
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			ina226_reg_to_interval(data->regs[INA2XX_CONFIG]));
+}
+
 /* shunt voltage */
 static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, ina2xx_show_value, NULL,
 			  INA2XX_SHUNT_VOLTAGE);
@@ -203,15 +431,37 @@
 static SENSOR_DEVICE_ATTR(power1_input, S_IRUGO, ina2xx_show_value, NULL,
 			  INA2XX_POWER);
 
+/* shunt resistance */
+static SENSOR_DEVICE_ATTR(shunt_resistor, S_IRUGO | S_IWUSR,
+			  ina2xx_show_value, ina2xx_set_shunt,
+			  INA2XX_CALIBRATION);
+
+/* update interval (ina226 only) */
+static SENSOR_DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR,
+			  ina226_show_interval, ina226_set_interval, 0);
+
 /* pointers to created device attributes */
 static struct attribute *ina2xx_attrs[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
 	&sensor_dev_attr_in1_input.dev_attr.attr,
 	&sensor_dev_attr_curr1_input.dev_attr.attr,
 	&sensor_dev_attr_power1_input.dev_attr.attr,
+	&sensor_dev_attr_shunt_resistor.dev_attr.attr,
 	NULL,
 };
-ATTRIBUTE_GROUPS(ina2xx);
+
+static const struct attribute_group ina2xx_group = {
+	.attrs = ina2xx_attrs,
+};
+
+static struct attribute *ina226_attrs[] = {
+	&sensor_dev_attr_update_interval.dev_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group ina226_group = {
+	.attrs = ina226_attrs,
+};
 
 static int ina2xx_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
@@ -221,9 +471,8 @@
 	struct device *dev = &client->dev;
 	struct ina2xx_data *data;
 	struct device *hwmon_dev;
-	long shunt = 10000; /* default shunt value 10mOhms */
 	u32 val;
-	int ret;
+	int ret, group = 0;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA))
 		return -ENODEV;
@@ -234,50 +483,52 @@
 
 	if (dev_get_platdata(dev)) {
 		pdata = dev_get_platdata(dev);
-		shunt = pdata->shunt_uohms;
+		data->rshunt = pdata->shunt_uohms;
 	} else if (!of_property_read_u32(dev->of_node,
 					 "shunt-resistor", &val)) {
-		shunt = val;
+		data->rshunt = val;
+	} else {
+		data->rshunt = INA2XX_RSHUNT_DEFAULT;
 	}
 
-	if (shunt <= 0)
-		return -ENODEV;
-
 	/* set the device type */
 	data->kind = id->driver_data;
 	data->config = &ina2xx_config[data->kind];
-
-	/* device configuration */
-	ret = i2c_smbus_write_word_swapped(client, INA2XX_CONFIG,
-					   data->config->config_default);
-	if (ret < 0) {
-		dev_err(dev,
-			"error writing to the config register: %d", ret);
-		return -ENODEV;
-	}
+	data->curr_config = data->config->config_default;
+	data->client = client;
 
 	/*
-	 * Set current LSB to 1mA, shunt is in uOhms
-	 * (equation 13 in datasheet).
+	 * Ina226 has a variable update_interval. For ina219 we
+	 * use a constant value.
 	 */
-	ret = i2c_smbus_write_word_swapped(client, INA2XX_CALIBRATION,
-				data->config->calibration_factor / shunt);
+	if (data->kind == ina226)
+		ina226_set_update_interval(data);
+	else
+		data->update_interval = HZ / INA2XX_CONVERSION_RATE;
+
+	if (data->rshunt <= 0 ||
+	    data->rshunt > data->config->calibration_factor)
+		return -ENODEV;
+
+	ret = ina2xx_init(data);
 	if (ret < 0) {
-		dev_err(dev,
-			"error writing to the calibration register: %d", ret);
+		dev_err(dev, "error configuring the device: %d\n", ret);
 		return -ENODEV;
 	}
 
-	data->client = client;
 	mutex_init(&data->update_lock);
 
+	data->groups[group++] = &ina2xx_group;
+	if (data->kind == ina226)
+		data->groups[group++] = &ina226_group;
+
 	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
-							   data, ina2xx_groups);
+							   data, data->groups);
 	if (IS_ERR(hwmon_dev))
 		return PTR_ERR(hwmon_dev);
 
 	dev_info(dev, "power monitor %s (Rshunt = %li uOhm)\n",
-		 id->name, shunt);
+		 id->name, data->rshunt);
 
 	return 0;
 }
@@ -287,6 +538,7 @@
 	{ "ina220", ina219 },
 	{ "ina226", ina226 },
 	{ "ina230", ina226 },
+	{ "ina231", ina226 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, ina2xx_id);
diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c
index 388f8bc..996bdfd 100644
--- a/drivers/hwmon/jc42.c
+++ b/drivers/hwmon/jc42.c
@@ -201,7 +201,7 @@
 #define JC42_TEMP_MIN		0
 #define JC42_TEMP_MAX		125000
 
-static u16 jc42_temp_to_reg(int temp, bool extended)
+static u16 jc42_temp_to_reg(long temp, bool extended)
 {
 	int ntemp = clamp_val(temp,
 			      extended ? JC42_TEMP_MIN_EXTENDED :
@@ -213,11 +213,7 @@
 
 static int jc42_temp_from_reg(s16 reg)
 {
-	reg &= 0x1fff;
-
-	/* sign extend register */
-	if (reg & 0x1000)
-		reg |= 0xf000;
+	reg = sign_extend32(reg, 12);
 
 	/* convert from 0.0625 to 0.001 resolution */
 	return reg * 125 / 2;
@@ -308,15 +304,18 @@
 				  const char *buf, size_t count)
 {
 	struct jc42_data *data = dev_get_drvdata(dev);
-	unsigned long val;
+	long val;
 	int diff, hyst;
 	int err;
 	int ret = count;
 
-	if (kstrtoul(buf, 10, &val) < 0)
+	if (kstrtol(buf, 10, &val) < 0)
 		return -EINVAL;
 
+	val = clamp_val(val, (data->extended ? JC42_TEMP_MIN_EXTENDED :
+			      JC42_TEMP_MIN) - 6000, JC42_TEMP_MAX);
 	diff = jc42_temp_from_reg(data->temp[t_crit]) - val;
+
 	hyst = 0;
 	if (diff > 0) {
 		if (diff < 2250)
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index ec56782..5576579 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -779,7 +779,7 @@
 	return reg != REG_BANK && reg <= 0x20;
 }
 
-static struct regmap_config nct7802_regmap_config = {
+static const struct regmap_config nct7802_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 	.cache_type = REGCACHE_RBTREE,
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index ba9f478..9da2735 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -253,7 +253,7 @@
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int tmp102_suspend(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
@@ -279,17 +279,10 @@
 	config &= ~TMP102_CONF_SD;
 	return i2c_smbus_write_word_swapped(client, TMP102_CONF_REG, config);
 }
-
-static const struct dev_pm_ops tmp102_dev_pm_ops = {
-	.suspend	= tmp102_suspend,
-	.resume		= tmp102_resume,
-};
-
-#define TMP102_DEV_PM_OPS (&tmp102_dev_pm_ops)
-#else
-#define	TMP102_DEV_PM_OPS NULL
 #endif /* CONFIG_PM */
 
+static SIMPLE_DEV_PM_OPS(tmp102_dev_pm_ops, tmp102_suspend, tmp102_resume);
+
 static const struct i2c_device_id tmp102_id[] = {
 	{ "tmp102", 0 },
 	{ }
@@ -298,7 +291,7 @@
 
 static struct i2c_driver tmp102_driver = {
 	.driver.name	= DRIVER_NAME,
-	.driver.pm	= TMP102_DEV_PM_OPS,
+	.driver.pm	= &tmp102_dev_pm_ops,
 	.probe		= tmp102_probe,
 	.remove		= tmp102_remove,
 	.id_table	= tmp102_id,
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index b716b08..643c08a 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -258,6 +258,5 @@
 
 IB_UVERBS_DECLARE_EX_CMD(create_flow);
 IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
-IB_UVERBS_DECLARE_EX_CMD(query_device);
 
 #endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 532d8eba8..b7943ff 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -400,52 +400,6 @@
 	return ret;
 }
 
-static void copy_query_dev_fields(struct ib_uverbs_file *file,
-				  struct ib_uverbs_query_device_resp *resp,
-				  struct ib_device_attr *attr)
-{
-	resp->fw_ver		= attr->fw_ver;
-	resp->node_guid		= file->device->ib_dev->node_guid;
-	resp->sys_image_guid	= attr->sys_image_guid;
-	resp->max_mr_size	= attr->max_mr_size;
-	resp->page_size_cap	= attr->page_size_cap;
-	resp->vendor_id		= attr->vendor_id;
-	resp->vendor_part_id	= attr->vendor_part_id;
-	resp->hw_ver		= attr->hw_ver;
-	resp->max_qp		= attr->max_qp;
-	resp->max_qp_wr		= attr->max_qp_wr;
-	resp->device_cap_flags	= attr->device_cap_flags;
-	resp->max_sge		= attr->max_sge;
-	resp->max_sge_rd	= attr->max_sge_rd;
-	resp->max_cq		= attr->max_cq;
-	resp->max_cqe		= attr->max_cqe;
-	resp->max_mr		= attr->max_mr;
-	resp->max_pd		= attr->max_pd;
-	resp->max_qp_rd_atom	= attr->max_qp_rd_atom;
-	resp->max_ee_rd_atom	= attr->max_ee_rd_atom;
-	resp->max_res_rd_atom	= attr->max_res_rd_atom;
-	resp->max_qp_init_rd_atom	= attr->max_qp_init_rd_atom;
-	resp->max_ee_init_rd_atom	= attr->max_ee_init_rd_atom;
-	resp->atomic_cap		= attr->atomic_cap;
-	resp->max_ee			= attr->max_ee;
-	resp->max_rdd			= attr->max_rdd;
-	resp->max_mw			= attr->max_mw;
-	resp->max_raw_ipv6_qp		= attr->max_raw_ipv6_qp;
-	resp->max_raw_ethy_qp		= attr->max_raw_ethy_qp;
-	resp->max_mcast_grp		= attr->max_mcast_grp;
-	resp->max_mcast_qp_attach	= attr->max_mcast_qp_attach;
-	resp->max_total_mcast_qp_attach	= attr->max_total_mcast_qp_attach;
-	resp->max_ah			= attr->max_ah;
-	resp->max_fmr			= attr->max_fmr;
-	resp->max_map_per_fmr		= attr->max_map_per_fmr;
-	resp->max_srq			= attr->max_srq;
-	resp->max_srq_wr		= attr->max_srq_wr;
-	resp->max_srq_sge		= attr->max_srq_sge;
-	resp->max_pkeys			= attr->max_pkeys;
-	resp->local_ca_ack_delay	= attr->local_ca_ack_delay;
-	resp->phys_port_cnt		= file->device->ib_dev->phys_port_cnt;
-}
-
 ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 			       const char __user *buf,
 			       int in_len, int out_len)
@@ -466,7 +420,47 @@
 		return ret;
 
 	memset(&resp, 0, sizeof resp);
-	copy_query_dev_fields(file, &resp, &attr);
+
+	resp.fw_ver 		       = attr.fw_ver;
+	resp.node_guid 		       = file->device->ib_dev->node_guid;
+	resp.sys_image_guid 	       = attr.sys_image_guid;
+	resp.max_mr_size 	       = attr.max_mr_size;
+	resp.page_size_cap 	       = attr.page_size_cap;
+	resp.vendor_id 		       = attr.vendor_id;
+	resp.vendor_part_id 	       = attr.vendor_part_id;
+	resp.hw_ver 		       = attr.hw_ver;
+	resp.max_qp 		       = attr.max_qp;
+	resp.max_qp_wr 		       = attr.max_qp_wr;
+	resp.device_cap_flags 	       = attr.device_cap_flags;
+	resp.max_sge 		       = attr.max_sge;
+	resp.max_sge_rd 	       = attr.max_sge_rd;
+	resp.max_cq 		       = attr.max_cq;
+	resp.max_cqe 		       = attr.max_cqe;
+	resp.max_mr 		       = attr.max_mr;
+	resp.max_pd 		       = attr.max_pd;
+	resp.max_qp_rd_atom 	       = attr.max_qp_rd_atom;
+	resp.max_ee_rd_atom 	       = attr.max_ee_rd_atom;
+	resp.max_res_rd_atom 	       = attr.max_res_rd_atom;
+	resp.max_qp_init_rd_atom       = attr.max_qp_init_rd_atom;
+	resp.max_ee_init_rd_atom       = attr.max_ee_init_rd_atom;
+	resp.atomic_cap 	       = attr.atomic_cap;
+	resp.max_ee 		       = attr.max_ee;
+	resp.max_rdd 		       = attr.max_rdd;
+	resp.max_mw 		       = attr.max_mw;
+	resp.max_raw_ipv6_qp 	       = attr.max_raw_ipv6_qp;
+	resp.max_raw_ethy_qp 	       = attr.max_raw_ethy_qp;
+	resp.max_mcast_grp 	       = attr.max_mcast_grp;
+	resp.max_mcast_qp_attach       = attr.max_mcast_qp_attach;
+	resp.max_total_mcast_qp_attach = attr.max_total_mcast_qp_attach;
+	resp.max_ah 		       = attr.max_ah;
+	resp.max_fmr 		       = attr.max_fmr;
+	resp.max_map_per_fmr 	       = attr.max_map_per_fmr;
+	resp.max_srq 		       = attr.max_srq;
+	resp.max_srq_wr 	       = attr.max_srq_wr;
+	resp.max_srq_sge 	       = attr.max_srq_sge;
+	resp.max_pkeys 		       = attr.max_pkeys;
+	resp.local_ca_ack_delay        = attr.local_ca_ack_delay;
+	resp.phys_port_cnt	       = file->device->ib_dev->phys_port_cnt;
 
 	if (copy_to_user((void __user *) (unsigned long) cmd.response,
 			 &resp, sizeof resp))
@@ -3293,52 +3287,3 @@
 
 	return ret ? ret : in_len;
 }
-
-int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
-			      struct ib_udata *ucore,
-			      struct ib_udata *uhw)
-{
-	struct ib_uverbs_ex_query_device_resp resp;
-	struct ib_uverbs_ex_query_device  cmd;
-	struct ib_device_attr attr;
-	struct ib_device *device;
-	int err;
-
-	device = file->device->ib_dev;
-	if (ucore->inlen < sizeof(cmd))
-		return -EINVAL;
-
-	err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
-	if (err)
-		return err;
-
-	if (cmd.reserved)
-		return -EINVAL;
-
-	err = device->query_device(device, &attr);
-	if (err)
-		return err;
-
-	memset(&resp, 0, sizeof(resp));
-	copy_query_dev_fields(file, &resp.base, &attr);
-	resp.comp_mask = 0;
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (cmd.comp_mask & IB_USER_VERBS_EX_QUERY_DEVICE_ODP) {
-		resp.odp_caps.general_caps = attr.odp_caps.general_caps;
-		resp.odp_caps.per_transport_caps.rc_odp_caps =
-			attr.odp_caps.per_transport_caps.rc_odp_caps;
-		resp.odp_caps.per_transport_caps.uc_odp_caps =
-			attr.odp_caps.per_transport_caps.uc_odp_caps;
-		resp.odp_caps.per_transport_caps.ud_odp_caps =
-			attr.odp_caps.per_transport_caps.ud_odp_caps;
-		resp.comp_mask |= IB_USER_VERBS_EX_QUERY_DEVICE_ODP;
-	}
-#endif
-
-	err = ib_copy_to_udata(ucore, &resp, sizeof(resp));
-	if (err)
-		return err;
-
-	return 0;
-}
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index e6c23b9..5db1a8c 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -123,7 +123,6 @@
 				    struct ib_udata *uhw) = {
 	[IB_USER_VERBS_EX_CMD_CREATE_FLOW]	= ib_uverbs_ex_create_flow,
 	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow,
-	[IB_USER_VERBS_EX_CMD_QUERY_DEVICE]	= ib_uverbs_ex_query_device
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 8a87404..03bf812 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1331,8 +1331,6 @@
 		(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ)		|
 		(1ull << IB_USER_VERBS_CMD_CREATE_XSRQ)		|
 		(1ull << IB_USER_VERBS_CMD_OPEN_QP);
-	dev->ib_dev.uverbs_ex_cmd_mask =
-		(1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE);
 
 	dev->ib_dev.query_device	= mlx5_ib_query_device;
 	dev->ib_dev.query_port		= mlx5_ib_query_port;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 8ba80a6..d7562be 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -98,15 +98,9 @@
 
 	IPOIB_MCAST_FLAG_FOUND	  = 0,	/* used in set_multicast_list */
 	IPOIB_MCAST_FLAG_SENDONLY = 1,
-	/*
-	 * For IPOIB_MCAST_FLAG_BUSY
-	 * When set, in flight join and mcast->mc is unreliable
-	 * When clear and mcast->mc IS_ERR_OR_NULL, need to restart or
-	 *   haven't started yet
-	 * When clear and mcast->mc is valid pointer, join was successful
-	 */
-	IPOIB_MCAST_FLAG_BUSY	  = 2,
+	IPOIB_MCAST_FLAG_BUSY	  = 2,	/* joining or already joined */
 	IPOIB_MCAST_FLAG_ATTACHED = 3,
+	IPOIB_MCAST_JOIN_STARTED  = 4,
 
 	MAX_SEND_CQE		  = 16,
 	IPOIB_CM_COPYBREAK	  = 256,
@@ -323,7 +317,6 @@
 	struct list_head multicast_list;
 	struct rb_root multicast_tree;
 
-	struct workqueue_struct *wq;
 	struct delayed_work mcast_task;
 	struct work_struct carrier_on_task;
 	struct work_struct flush_light;
@@ -484,10 +477,10 @@
 void ipoib_pkey_event(struct work_struct *work);
 void ipoib_ib_dev_cleanup(struct net_device *dev);
 
-int ipoib_ib_dev_open(struct net_device *dev);
+int ipoib_ib_dev_open(struct net_device *dev, int flush);
 int ipoib_ib_dev_up(struct net_device *dev);
-int ipoib_ib_dev_down(struct net_device *dev);
-int ipoib_ib_dev_stop(struct net_device *dev);
+int ipoib_ib_dev_down(struct net_device *dev, int flush);
+int ipoib_ib_dev_stop(struct net_device *dev, int flush);
 void ipoib_pkey_dev_check_presence(struct net_device *dev);
 
 int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
@@ -499,7 +492,7 @@
 
 void ipoib_mcast_restart_task(struct work_struct *work);
 int ipoib_mcast_start_thread(struct net_device *dev);
-int ipoib_mcast_stop_thread(struct net_device *dev);
+int ipoib_mcast_stop_thread(struct net_device *dev, int flush);
 
 void ipoib_mcast_dev_down(struct net_device *dev);
 void ipoib_mcast_dev_flush(struct net_device *dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 56959ad..933efce 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -474,7 +474,7 @@
 	}
 
 	spin_lock_irq(&priv->lock);
-	queue_delayed_work(priv->wq,
+	queue_delayed_work(ipoib_workqueue,
 			   &priv->cm.stale_task, IPOIB_CM_RX_DELAY);
 	/* Add this entry to passive ids list head, but do not re-add it
 	 * if IB_EVENT_QP_LAST_WQE_REACHED has moved it to flush list. */
@@ -576,7 +576,7 @@
 			spin_lock_irqsave(&priv->lock, flags);
 			list_splice_init(&priv->cm.rx_drain_list, &priv->cm.rx_reap_list);
 			ipoib_cm_start_rx_drain(priv);
-			queue_work(priv->wq, &priv->cm.rx_reap_task);
+			queue_work(ipoib_workqueue, &priv->cm.rx_reap_task);
 			spin_unlock_irqrestore(&priv->lock, flags);
 		} else
 			ipoib_warn(priv, "cm recv completion event with wrid %d (> %d)\n",
@@ -603,7 +603,7 @@
 				spin_lock_irqsave(&priv->lock, flags);
 				list_move(&p->list, &priv->cm.rx_reap_list);
 				spin_unlock_irqrestore(&priv->lock, flags);
-				queue_work(priv->wq, &priv->cm.rx_reap_task);
+				queue_work(ipoib_workqueue, &priv->cm.rx_reap_task);
 			}
 			return;
 		}
@@ -827,7 +827,7 @@
 
 		if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
 			list_move(&tx->list, &priv->cm.reap_list);
-			queue_work(priv->wq, &priv->cm.reap_task);
+			queue_work(ipoib_workqueue, &priv->cm.reap_task);
 		}
 
 		clear_bit(IPOIB_FLAG_OPER_UP, &tx->flags);
@@ -1255,7 +1255,7 @@
 
 		if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
 			list_move(&tx->list, &priv->cm.reap_list);
-			queue_work(priv->wq, &priv->cm.reap_task);
+			queue_work(ipoib_workqueue, &priv->cm.reap_task);
 		}
 
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1284,7 +1284,7 @@
 	tx->dev = dev;
 	list_add(&tx->list, &priv->cm.start_list);
 	set_bit(IPOIB_FLAG_INITIALIZED, &tx->flags);
-	queue_work(priv->wq, &priv->cm.start_task);
+	queue_work(ipoib_workqueue, &priv->cm.start_task);
 	return tx;
 }
 
@@ -1295,7 +1295,7 @@
 	if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
 		spin_lock_irqsave(&priv->lock, flags);
 		list_move(&tx->list, &priv->cm.reap_list);
-		queue_work(priv->wq, &priv->cm.reap_task);
+		queue_work(ipoib_workqueue, &priv->cm.reap_task);
 		ipoib_dbg(priv, "Reap connection for gid %pI6\n",
 			  tx->neigh->daddr + 4);
 		tx->neigh = NULL;
@@ -1417,7 +1417,7 @@
 
 	skb_queue_tail(&priv->cm.skb_queue, skb);
 	if (e)
-		queue_work(priv->wq, &priv->cm.skb_task);
+		queue_work(ipoib_workqueue, &priv->cm.skb_task);
 }
 
 static void ipoib_cm_rx_reap(struct work_struct *work)
@@ -1450,7 +1450,7 @@
 	}
 
 	if (!list_empty(&priv->cm.passive_ids))
-		queue_delayed_work(priv->wq,
+		queue_delayed_work(ipoib_workqueue,
 				   &priv->cm.stale_task, IPOIB_CM_RX_DELAY);
 	spin_unlock_irq(&priv->lock);
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index fe65abb..72626c34 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -655,7 +655,7 @@
 	__ipoib_reap_ah(dev);
 
 	if (!test_bit(IPOIB_STOP_REAPER, &priv->flags))
-		queue_delayed_work(priv->wq, &priv->ah_reap_task,
+		queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
 				   round_jiffies_relative(HZ));
 }
 
@@ -664,7 +664,7 @@
 	drain_tx_cq((struct net_device *)ctx);
 }
 
-int ipoib_ib_dev_open(struct net_device *dev)
+int ipoib_ib_dev_open(struct net_device *dev, int flush)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret;
@@ -696,7 +696,7 @@
 	}
 
 	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
-	queue_delayed_work(priv->wq, &priv->ah_reap_task,
+	queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
 			   round_jiffies_relative(HZ));
 
 	if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
@@ -706,7 +706,7 @@
 dev_stop:
 	if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
 		napi_enable(&priv->napi);
-	ipoib_ib_dev_stop(dev);
+	ipoib_ib_dev_stop(dev, flush);
 	return -1;
 }
 
@@ -738,7 +738,7 @@
 	return ipoib_mcast_start_thread(dev);
 }
 
-int ipoib_ib_dev_down(struct net_device *dev)
+int ipoib_ib_dev_down(struct net_device *dev, int flush)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -747,7 +747,7 @@
 	clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
 	netif_carrier_off(dev);
 
-	ipoib_mcast_stop_thread(dev);
+	ipoib_mcast_stop_thread(dev, flush);
 	ipoib_mcast_dev_flush(dev);
 
 	ipoib_flush_paths(dev);
@@ -807,7 +807,7 @@
 	local_bh_enable();
 }
 
-int ipoib_ib_dev_stop(struct net_device *dev)
+int ipoib_ib_dev_stop(struct net_device *dev, int flush)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_qp_attr qp_attr;
@@ -880,7 +880,8 @@
 	/* Wait for all AHs to be reaped */
 	set_bit(IPOIB_STOP_REAPER, &priv->flags);
 	cancel_delayed_work(&priv->ah_reap_task);
-	flush_workqueue(priv->wq);
+	if (flush)
+		flush_workqueue(ipoib_workqueue);
 
 	begin = jiffies;
 
@@ -917,7 +918,7 @@
 		    (unsigned long) dev);
 
 	if (dev->flags & IFF_UP) {
-		if (ipoib_ib_dev_open(dev)) {
+		if (ipoib_ib_dev_open(dev, 1)) {
 			ipoib_transport_dev_cleanup(dev);
 			return -ENODEV;
 		}
@@ -1039,12 +1040,12 @@
 	}
 
 	if (level >= IPOIB_FLUSH_NORMAL)
-		ipoib_ib_dev_down(dev);
+		ipoib_ib_dev_down(dev, 0);
 
 	if (level == IPOIB_FLUSH_HEAVY) {
 		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
-			ipoib_ib_dev_stop(dev);
-		if (ipoib_ib_dev_open(dev) != 0)
+			ipoib_ib_dev_stop(dev, 0);
+		if (ipoib_ib_dev_open(dev, 0) != 0)
 			return;
 		if (netif_queue_stopped(dev))
 			netif_start_queue(dev);
@@ -1096,7 +1097,7 @@
 	 */
 	ipoib_flush_paths(dev);
 
-	ipoib_mcast_stop_thread(dev);
+	ipoib_mcast_stop_thread(dev, 1);
 	ipoib_mcast_dev_flush(dev);
 
 	ipoib_transport_dev_cleanup(dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 6bad17d..58b5aa3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -108,7 +108,7 @@
 
 	set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
 
-	if (ipoib_ib_dev_open(dev)) {
+	if (ipoib_ib_dev_open(dev, 1)) {
 		if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
 			return 0;
 		goto err_disable;
@@ -139,7 +139,7 @@
 	return 0;
 
 err_stop:
-	ipoib_ib_dev_stop(dev);
+	ipoib_ib_dev_stop(dev, 1);
 
 err_disable:
 	clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
@@ -157,8 +157,8 @@
 
 	netif_stop_queue(dev);
 
-	ipoib_ib_dev_down(dev);
-	ipoib_ib_dev_stop(dev);
+	ipoib_ib_dev_down(dev, 1);
+	ipoib_ib_dev_stop(dev, 0);
 
 	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
 		struct ipoib_dev_priv *cpriv;
@@ -839,7 +839,7 @@
 		return;
 	}
 
-	queue_work(priv->wq, &priv->restart_task);
+	queue_work(ipoib_workqueue, &priv->restart_task);
 }
 
 static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr)
@@ -954,7 +954,7 @@
 	__ipoib_reap_neigh(priv);
 
 	if (!test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
-		queue_delayed_work(priv->wq, &priv->neigh_reap_task,
+		queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task,
 				   arp_tbl.gc_interval);
 }
 
@@ -1133,7 +1133,7 @@
 
 	/* start garbage collection */
 	clear_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
-	queue_delayed_work(priv->wq, &priv->neigh_reap_task,
+	queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task,
 			   arp_tbl.gc_interval);
 
 	return 0;
@@ -1262,13 +1262,15 @@
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
+	if (ipoib_neigh_hash_init(priv) < 0)
+		goto out;
 	/* Allocate RX/TX "rings" to hold queued skbs */
 	priv->rx_ring =	kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring,
 				GFP_KERNEL);
 	if (!priv->rx_ring) {
 		printk(KERN_WARNING "%s: failed to allocate RX ring (%d entries)\n",
 		       ca->name, ipoib_recvq_size);
-		goto out;
+		goto out_neigh_hash_cleanup;
 	}
 
 	priv->tx_ring = vzalloc(ipoib_sendq_size * sizeof *priv->tx_ring);
@@ -1283,24 +1285,16 @@
 	if (ipoib_ib_dev_init(dev, ca, port))
 		goto out_tx_ring_cleanup;
 
-	/*
-	 * Must be after ipoib_ib_dev_init so we can allocate a per
-	 * device wq there and use it here
-	 */
-	if (ipoib_neigh_hash_init(priv) < 0)
-		goto out_dev_uninit;
-
 	return 0;
 
-out_dev_uninit:
-	ipoib_ib_dev_cleanup(dev);
-
 out_tx_ring_cleanup:
 	vfree(priv->tx_ring);
 
 out_rx_ring_cleanup:
 	kfree(priv->rx_ring);
 
+out_neigh_hash_cleanup:
+	ipoib_neigh_hash_uninit(dev);
 out:
 	return -ENOMEM;
 }
@@ -1323,12 +1317,6 @@
 	}
 	unregister_netdevice_many(&head);
 
-	/*
-	 * Must be before ipoib_ib_dev_cleanup or we delete an in use
-	 * work queue
-	 */
-	ipoib_neigh_hash_uninit(dev);
-
 	ipoib_ib_dev_cleanup(dev);
 
 	kfree(priv->rx_ring);
@@ -1336,6 +1324,8 @@
 
 	priv->rx_ring = NULL;
 	priv->tx_ring = NULL;
+
+	ipoib_neigh_hash_uninit(dev);
 }
 
 static const struct header_ops ipoib_header_ops = {
@@ -1646,7 +1636,7 @@
 	/* Stop GC if started before flush */
 	set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 	cancel_delayed_work(&priv->neigh_reap_task);
-	flush_workqueue(priv->wq);
+	flush_workqueue(ipoib_workqueue);
 
 event_failed:
 	ipoib_dev_cleanup(priv->dev);
@@ -1717,7 +1707,7 @@
 		/* Stop GC */
 		set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 		cancel_delayed_work(&priv->neigh_reap_task);
-		flush_workqueue(priv->wq);
+		flush_workqueue(ipoib_workqueue);
 
 		unregister_netdev(priv->dev);
 		free_netdev(priv->dev);
@@ -1758,13 +1748,8 @@
 	 * unregister_netdev() and linkwatch_event take the rtnl lock,
 	 * so flush_scheduled_work() can deadlock during device
 	 * removal.
-	 *
-	 * In addition, bringing one device up and another down at the
-	 * same time can deadlock a single workqueue, so we have this
-	 * global fallback workqueue, but we also attempt to open a
-	 * per device workqueue each time we bring an interface up
 	 */
-	ipoib_workqueue = create_singlethread_workqueue("ipoib_flush");
+	ipoib_workqueue = create_singlethread_workqueue("ipoib");
 	if (!ipoib_workqueue) {
 		ret = -ENOMEM;
 		goto err_fs;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index bc50dd0..ffb83b5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -190,6 +190,12 @@
 		spin_unlock_irq(&priv->lock);
 		priv->tx_wr.wr.ud.remote_qkey = priv->qkey;
 		set_qkey = 1;
+
+		if (!ipoib_cm_admin_enabled(dev)) {
+			rtnl_lock();
+			dev_set_mtu(dev, min(priv->mcast_mtu, priv->admin_mtu));
+			rtnl_unlock();
+		}
 	}
 
 	if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
@@ -271,27 +277,16 @@
 	struct ipoib_mcast *mcast = multicast->context;
 	struct net_device *dev = mcast->dev;
 
-	/*
-	 * We have to take the mutex to force mcast_sendonly_join to
-	 * return from ib_sa_multicast_join and set mcast->mc to a
-	 * valid value.  Otherwise we were racing with ourselves in
-	 * that we might fail here, but get a valid return from
-	 * ib_sa_multicast_join after we had cleared mcast->mc here,
-	 * resulting in mis-matched joins and leaves and a deadlock
-	 */
-	mutex_lock(&mcast_mutex);
-
 	/* We trap for port events ourselves. */
 	if (status == -ENETRESET)
-		goto out;
+		return 0;
 
 	if (!status)
 		status = ipoib_mcast_join_finish(mcast, &multicast->rec);
 
 	if (status) {
 		if (mcast->logcount++ < 20)
-			ipoib_dbg_mcast(netdev_priv(dev), "sendonly multicast "
-					"join failed for %pI6, status %d\n",
+			ipoib_dbg_mcast(netdev_priv(dev), "multicast join failed for %pI6, status %d\n",
 					mcast->mcmember.mgid.raw, status);
 
 		/* Flush out any queued packets */
@@ -301,15 +296,11 @@
 			dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));
 		}
 		netif_tx_unlock_bh(dev);
+
+		/* Clear the busy flag so we try again */
+		status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY,
+					    &mcast->flags);
 	}
-out:
-	clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-	if (status)
-		mcast->mc = NULL;
-	complete(&mcast->done);
-	if (status == -ENETRESET)
-		status = 0;
-	mutex_unlock(&mcast_mutex);
 	return status;
 }
 
@@ -327,14 +318,12 @@
 	int ret = 0;
 
 	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) {
-		ipoib_dbg_mcast(priv, "device shutting down, no sendonly "
-				"multicast joins\n");
+		ipoib_dbg_mcast(priv, "device shutting down, no multicast joins\n");
 		return -ENODEV;
 	}
 
-	if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) {
-		ipoib_dbg_mcast(priv, "multicast entry busy, skipping "
-				"sendonly join\n");
+	if (test_and_set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) {
+		ipoib_dbg_mcast(priv, "multicast entry busy, skipping\n");
 		return -EBUSY;
 	}
 
@@ -342,9 +331,6 @@
 	rec.port_gid = priv->local_gid;
 	rec.pkey     = cpu_to_be16(priv->pkey);
 
-	mutex_lock(&mcast_mutex);
-	init_completion(&mcast->done);
-	set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
 	mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca,
 					 priv->port, &rec,
 					 IB_SA_MCMEMBER_REC_MGID	|
@@ -357,14 +343,12 @@
 	if (IS_ERR(mcast->mc)) {
 		ret = PTR_ERR(mcast->mc);
 		clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-		complete(&mcast->done);
-		ipoib_warn(priv, "ib_sa_join_multicast for sendonly join "
-			   "failed (ret = %d)\n", ret);
+		ipoib_warn(priv, "ib_sa_join_multicast failed (ret = %d)\n",
+			   ret);
 	} else {
-		ipoib_dbg_mcast(priv, "no multicast record for %pI6, starting "
-				"sendonly join\n", mcast->mcmember.mgid.raw);
+		ipoib_dbg_mcast(priv, "no multicast record for %pI6, starting join\n",
+				mcast->mcmember.mgid.raw);
 	}
-	mutex_unlock(&mcast_mutex);
 
 	return ret;
 }
@@ -375,29 +359,18 @@
 						   carrier_on_task);
 	struct ib_port_attr attr;
 
+	/*
+	 * Take rtnl_lock to avoid racing with ipoib_stop() and
+	 * turning the carrier back on while a device is being
+	 * removed.
+	 */
 	if (ib_query_port(priv->ca, priv->port, &attr) ||
 	    attr.state != IB_PORT_ACTIVE) {
 		ipoib_dbg(priv, "Keeping carrier off until IB port is active\n");
 		return;
 	}
 
-	/*
-	 * Take rtnl_lock to avoid racing with ipoib_stop() and
-	 * turning the carrier back on while a device is being
-	 * removed.  However, ipoib_stop() will attempt to flush
-	 * the workqueue while holding the rtnl lock, so loop
-	 * on trylock until either we get the lock or we see
-	 * FLAG_ADMIN_UP go away as that signals that we are bailing
-	 * and can safely ignore the carrier on work.
-	 */
-	while (!rtnl_trylock()) {
-		if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
-			return;
-		else
-			msleep(20);
-	}
-	if (!ipoib_cm_admin_enabled(priv->dev))
-		dev_set_mtu(priv->dev, min(priv->mcast_mtu, priv->admin_mtu));
+	rtnl_lock();
 	netif_carrier_on(priv->dev);
 	rtnl_unlock();
 }
@@ -412,63 +385,60 @@
 	ipoib_dbg_mcast(priv, "join completion for %pI6 (status %d)\n",
 			mcast->mcmember.mgid.raw, status);
 
-	/*
-	 * We have to take the mutex to force mcast_join to
-	 * return from ib_sa_multicast_join and set mcast->mc to a
-	 * valid value.  Otherwise we were racing with ourselves in
-	 * that we might fail here, but get a valid return from
-	 * ib_sa_multicast_join after we had cleared mcast->mc here,
-	 * resulting in mis-matched joins and leaves and a deadlock
-	 */
-	mutex_lock(&mcast_mutex);
-
 	/* We trap for port events ourselves. */
-	if (status == -ENETRESET)
+	if (status == -ENETRESET) {
+		status = 0;
 		goto out;
+	}
 
 	if (!status)
 		status = ipoib_mcast_join_finish(mcast, &multicast->rec);
 
 	if (!status) {
 		mcast->backoff = 1;
+		mutex_lock(&mcast_mutex);
 		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
-			queue_delayed_work(priv->wq, &priv->mcast_task, 0);
+			queue_delayed_work(ipoib_workqueue,
+					   &priv->mcast_task, 0);
+		mutex_unlock(&mcast_mutex);
 
 		/*
-		 * Defer carrier on work to priv->wq to avoid a
+		 * Defer carrier on work to ipoib_workqueue to avoid a
 		 * deadlock on rtnl_lock here.
 		 */
 		if (mcast == priv->broadcast)
-			queue_work(priv->wq, &priv->carrier_on_task);
-	} else {
-		if (mcast->logcount++ < 20) {
-			if (status == -ETIMEDOUT || status == -EAGAIN) {
-				ipoib_dbg_mcast(priv, "multicast join failed for %pI6, status %d\n",
-						mcast->mcmember.mgid.raw, status);
-			} else {
-				ipoib_warn(priv, "multicast join failed for %pI6, status %d\n",
-					   mcast->mcmember.mgid.raw, status);
-			}
-		}
+			queue_work(ipoib_workqueue, &priv->carrier_on_task);
 
-		mcast->backoff *= 2;
-		if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
-			mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
-	}
-out:
-	spin_lock_irq(&priv->lock);
-	clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-	if (status)
-		mcast->mc = NULL;
-	complete(&mcast->done);
-	if (status == -ENETRESET)
 		status = 0;
-	if (status && test_bit(IPOIB_MCAST_RUN, &priv->flags))
-		queue_delayed_work(priv->wq, &priv->mcast_task,
+		goto out;
+	}
+
+	if (mcast->logcount++ < 20) {
+		if (status == -ETIMEDOUT || status == -EAGAIN) {
+			ipoib_dbg_mcast(priv, "multicast join failed for %pI6, status %d\n",
+					mcast->mcmember.mgid.raw, status);
+		} else {
+			ipoib_warn(priv, "multicast join failed for %pI6, status %d\n",
+				   mcast->mcmember.mgid.raw, status);
+		}
+	}
+
+	mcast->backoff *= 2;
+	if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
+		mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
+
+	/* Clear the busy flag so we try again */
+	status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+
+	mutex_lock(&mcast_mutex);
+	spin_lock_irq(&priv->lock);
+	if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
+		queue_delayed_work(ipoib_workqueue, &priv->mcast_task,
 				   mcast->backoff * HZ);
 	spin_unlock_irq(&priv->lock);
 	mutex_unlock(&mcast_mutex);
-
+out:
+	complete(&mcast->done);
 	return status;
 }
 
@@ -517,9 +487,10 @@
 		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;
 	}
 
-	mutex_lock(&mcast_mutex);
-	init_completion(&mcast->done);
 	set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+	init_completion(&mcast->done);
+	set_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags);
+
 	mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
 					 &rec, comp_mask, GFP_KERNEL,
 					 ipoib_mcast_join_complete, mcast);
@@ -533,11 +504,13 @@
 		if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
 			mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
 
+		mutex_lock(&mcast_mutex);
 		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
-			queue_delayed_work(priv->wq, &priv->mcast_task,
+			queue_delayed_work(ipoib_workqueue,
+					   &priv->mcast_task,
 					   mcast->backoff * HZ);
+		mutex_unlock(&mcast_mutex);
 	}
-	mutex_unlock(&mcast_mutex);
 }
 
 void ipoib_mcast_join_task(struct work_struct *work)
@@ -574,8 +547,8 @@
 			ipoib_warn(priv, "failed to allocate broadcast group\n");
 			mutex_lock(&mcast_mutex);
 			if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
-				queue_delayed_work(priv->wq, &priv->mcast_task,
-						   HZ);
+				queue_delayed_work(ipoib_workqueue,
+						   &priv->mcast_task, HZ);
 			mutex_unlock(&mcast_mutex);
 			return;
 		}
@@ -590,8 +563,7 @@
 	}
 
 	if (!test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) {
-		if (IS_ERR_OR_NULL(priv->broadcast->mc) &&
-		    !test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags))
+		if (!test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags))
 			ipoib_mcast_join(dev, priv->broadcast, 0);
 		return;
 	}
@@ -599,33 +571,23 @@
 	while (1) {
 		struct ipoib_mcast *mcast = NULL;
 
-		/*
-		 * Need the mutex so our flags are consistent, need the
-		 * priv->lock so we don't race with list removals in either
-		 * mcast_dev_flush or mcast_restart_task
-		 */
-		mutex_lock(&mcast_mutex);
 		spin_lock_irq(&priv->lock);
 		list_for_each_entry(mcast, &priv->multicast_list, list) {
-			if (IS_ERR_OR_NULL(mcast->mc) &&
-			    !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags) &&
-			    !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
+			if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)
+			    && !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)
+			    && !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
 				/* Found the next unjoined group */
 				break;
 			}
 		}
 		spin_unlock_irq(&priv->lock);
-		mutex_unlock(&mcast_mutex);
 
 		if (&mcast->list == &priv->multicast_list) {
 			/* All done */
 			break;
 		}
 
-		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-			ipoib_mcast_sendonly_join(mcast);
-		else
-			ipoib_mcast_join(dev, mcast, 1);
+		ipoib_mcast_join(dev, mcast, 1);
 		return;
 	}
 
@@ -642,13 +604,13 @@
 
 	mutex_lock(&mcast_mutex);
 	if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags))
-		queue_delayed_work(priv->wq, &priv->mcast_task, 0);
+		queue_delayed_work(ipoib_workqueue, &priv->mcast_task, 0);
 	mutex_unlock(&mcast_mutex);
 
 	return 0;
 }
 
-int ipoib_mcast_stop_thread(struct net_device *dev)
+int ipoib_mcast_stop_thread(struct net_device *dev, int flush)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -659,7 +621,8 @@
 	cancel_delayed_work(&priv->mcast_task);
 	mutex_unlock(&mcast_mutex);
 
-	flush_workqueue(priv->wq);
+	if (flush)
+		flush_workqueue(ipoib_workqueue);
 
 	return 0;
 }
@@ -670,9 +633,6 @@
 	int ret = 0;
 
 	if (test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-		ipoib_warn(priv, "ipoib_mcast_leave on an in-flight join\n");
-
-	if (!IS_ERR_OR_NULL(mcast->mc))
 		ib_sa_free_multicast(mcast->mc);
 
 	if (test_and_clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
@@ -725,8 +685,6 @@
 		memcpy(mcast->mcmember.mgid.raw, mgid, sizeof (union ib_gid));
 		__ipoib_mcast_add(dev, mcast);
 		list_add_tail(&mcast->list, &priv->multicast_list);
-		if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags))
-			queue_delayed_work(priv->wq, &priv->mcast_task, 0);
 	}
 
 	if (!mcast->ah) {
@@ -740,6 +698,8 @@
 		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
 			ipoib_dbg_mcast(priv, "no address vector, "
 					"but multicast join already started\n");
+		else if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
+			ipoib_mcast_sendonly_join(mcast);
 
 		/*
 		 * If lookup completes between here and out:, don't
@@ -799,12 +759,9 @@
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
+	/* seperate between the wait to the leave*/
 	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
+		if (test_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags))
 			wait_for_completion(&mcast->done);
 
 	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
@@ -837,6 +794,8 @@
 
 	ipoib_dbg_mcast(priv, "restarting multicast task\n");
 
+	ipoib_mcast_stop_thread(dev, 0);
+
 	local_irq_save(flags);
 	netif_addr_lock(dev);
 	spin_lock(&priv->lock);
@@ -921,38 +880,14 @@
 	netif_addr_unlock(dev);
 	local_irq_restore(flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
-	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-			wait_for_completion(&mcast->done);
-
-	/*
-	 * We have to cancel outside of the spinlock, but we have to
-	 * take the rtnl lock or else we race with the removal of
-	 * entries from the remove list in mcast_dev_flush as part
-	 * of ipoib_stop().  We detect the drop of the ADMIN_UP flag
-	 * to signal that we have hit this particular race, and we
-	 * return since we know we don't need to do anything else
-	 * anyway.
-	 */
-	while (!rtnl_trylock()) {
-		if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
-			return;
-		else
-			msleep(20);
-	}
+	/* We have to cancel outside of the spinlock */
 	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
 		ipoib_mcast_leave(mcast->dev, mcast);
 		ipoib_mcast_free(mcast);
 	}
-	/*
-	 * Restart our join task if needed
-	 */
-	ipoib_mcast_start_thread(dev);
-	rtnl_unlock();
+
+	if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
+		ipoib_mcast_start_thread(dev);
 }
 
 #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index b72a753..c56d5d4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -145,20 +145,10 @@
 	int ret, size;
 	int i;
 
-	/*
-	 * the various IPoIB tasks assume they will never race against
-	 * themselves, so always use a single thread workqueue
-	 */
-	priv->wq = create_singlethread_workqueue("ipoib_wq");
-	if (!priv->wq) {
-		printk(KERN_WARNING "ipoib: failed to allocate device WQ\n");
-		return -ENODEV;
-	}
-
 	priv->pd = ib_alloc_pd(priv->ca);
 	if (IS_ERR(priv->pd)) {
 		printk(KERN_WARNING "%s: failed to allocate PD\n", ca->name);
-		goto out_free_wq;
+		return -ENODEV;
 	}
 
 	priv->mr = ib_get_dma_mr(priv->pd, IB_ACCESS_LOCAL_WRITE);
@@ -252,10 +242,6 @@
 
 out_free_pd:
 	ib_dealloc_pd(priv->pd);
-
-out_free_wq:
-	destroy_workqueue(priv->wq);
-	priv->wq = NULL;
 	return -ENODEV;
 }
 
@@ -284,12 +270,6 @@
 
 	if (ib_dealloc_pd(priv->pd))
 		ipoib_warn(priv, "ib_dealloc_pd failed\n");
-
-	if (priv->wq) {
-		flush_workqueue(priv->wq);
-		destroy_workqueue(priv->wq);
-		priv->wq = NULL;
-	}
 }
 
 void ipoib_event(struct ib_event_handler *handler,
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 2b0468e..56b96c6 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -37,6 +37,7 @@
 static int gic_shared_intrs;
 static int gic_vpes;
 static unsigned int gic_cpu_pin;
+static unsigned int timer_cpu_pin;
 static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller;
 
 static void __gic_irq_dispatch(void);
@@ -616,6 +617,8 @@
 			gic_write(GIC_REG(VPE_OTHER, GIC_VPE_COMPARE_MAP), val);
 			break;
 		case GIC_LOCAL_INT_TIMER:
+			/* CONFIG_MIPS_CMP workaround (see __gic_init) */
+			val = GIC_MAP_TO_PIN_MSK | timer_cpu_pin;
 			gic_write(GIC_REG(VPE_OTHER, GIC_VPE_TIMER_MAP), val);
 			break;
 		case GIC_LOCAL_INT_PERFCTR:
@@ -713,12 +716,36 @@
 	if (cpu_has_veic) {
 		/* Always use vector 1 in EIC mode */
 		gic_cpu_pin = 0;
+		timer_cpu_pin = gic_cpu_pin;
 		set_vi_handler(gic_cpu_pin + GIC_PIN_TO_VEC_OFFSET,
 			       __gic_irq_dispatch);
 	} else {
 		gic_cpu_pin = cpu_vec - GIC_CPU_PIN_OFFSET;
 		irq_set_chained_handler(MIPS_CPU_IRQ_BASE + cpu_vec,
 					gic_irq_dispatch);
+		/*
+		 * With the CMP implementation of SMP (deprecated), other CPUs
+		 * are started by the bootloader and put into a timer based
+		 * waiting poll loop. We must not re-route those CPU's local
+		 * timer interrupts as the wait instruction will never finish,
+		 * so just handle whatever CPU interrupt it is routed to by
+		 * default.
+		 *
+		 * This workaround should be removed when CMP support is
+		 * dropped.
+		 */
+		if (IS_ENABLED(CONFIG_MIPS_CMP) &&
+		    gic_local_irq_is_routable(GIC_LOCAL_INT_TIMER)) {
+			timer_cpu_pin = gic_read(GIC_REG(VPE_LOCAL,
+							 GIC_VPE_TIMER_MAP)) &
+					GIC_MAP_MSK;
+			irq_set_chained_handler(MIPS_CPU_IRQ_BASE +
+						GIC_CPU_PIN_OFFSET +
+						timer_cpu_pin,
+						gic_irq_dispatch);
+		} else {
+			timer_cpu_pin = gic_cpu_pin;
+		}
 	}
 
 	gic_irq_domain = irq_domain_add_simple(node, GIC_NUM_LOCAL_INTRS +
diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c
index 0b38060..d7c2866 100644
--- a/drivers/isdn/hardware/eicon/message.c
+++ b/drivers/isdn/hardware/eicon/message.c
@@ -1474,7 +1474,7 @@
 					add_ai(plci, &parms[5]);
 					sig_req(plci, REJECT, 0);
 				}
-				else if (Reject == 1 || Reject > 9)
+				else if (Reject == 1 || Reject >= 9)
 				{
 					add_ai(plci, &parms[5]);
 					sig_req(plci, HANGUP, 0);
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 5bdedf6..c355a22 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -5,6 +5,7 @@
 menuconfig MD
 	bool "Multiple devices driver support (RAID and LVM)"
 	depends on BLOCK
+	select SRCU
 	help
 	  Support multiple physical spindles through a single logical device.
 	  Required for RAID and logical volume management.
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index da3604e..1695ee5 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -72,6 +72,19 @@
 	/* this page has not been allocated yet */
 
 	spin_unlock_irq(&bitmap->lock);
+	/* It is possible that this is being called inside a
+	 * prepare_to_wait/finish_wait loop from raid5c:make_request().
+	 * In general it is not permitted to sleep in that context as it
+	 * can cause the loop to spin freely.
+	 * That doesn't apply here as we can only reach this point
+	 * once with any loop.
+	 * When this function completes, either bp[page].map or
+	 * bp[page].hijacked.  In either case, this function will
+	 * abort before getting to this point again.  So there is
+	 * no risk of a free-spin, and so it is safe to assert
+	 * that sleeping here is allowed.
+	 */
+	sched_annotate_sleep();
 	mappage = kzalloc(PAGE_SIZE, GFP_NOIO);
 	spin_lock_irq(&bitmap->lock);
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c1b0d52..b98765f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3195,6 +3195,11 @@
 					  (unsigned long long)sh->sector,
 					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
 	}
+
+	if (rcw > disks && rmw > disks &&
+	    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+		set_bit(STRIPE_DELAYED, &sh->state);
+
 	/* now if nothing is locked, and if we have enough data,
 	 * we can start a write request
 	 */
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index d6607ee..84673eb 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -197,6 +197,7 @@
 
 config NETPOLL
 	def_bool NETCONSOLE
+	select SRCU
 
 config NET_POLL_CONTROLLER
 	def_bool NETPOLL
diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index 5e40a8b..b3b922a 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -1415,7 +1415,6 @@
 
 	cfhsi = netdev_priv(dev);
 	cfhsi_netlink_parms(data, cfhsi);
-	dev_net_set(cfhsi->ndev, src_net);
 
 	get_ops = symbol_get(cfhsi_get_ops);
 	if (!get_ops) {
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index 7a5e4aa..77f1f60 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -45,7 +45,7 @@
 
 config LANCE
 	tristate "AMD LANCE and PCnet (AT1500 and NE2100) support"
-	depends on ISA && ISA_DMA_API
+	depends on ISA && ISA_DMA_API && !ARM
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y and read
 	  the Ethernet-HOWTO, available from
@@ -142,7 +142,7 @@
 
 config NI65
 	tristate "NI6510 support"
-	depends on ISA && ISA_DMA_API
+	depends on ISA && ISA_DMA_API && !ARM
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y and read
 	  the Ethernet-HOWTO, available from
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index 5b22764..27245ef 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -952,6 +952,8 @@
   do {
     /* WARNING: MACE_IR is a READ/CLEAR port! */
     status = inb(ioaddr + AM2150_MACE_BASE + MACE_IR);
+    if (!(status & ~MACE_IMR_DEFAULT) && IntrCnt == MACE_MAX_IR_ITERATIONS)
+      return IRQ_NONE;
 
     pr_debug("mace_interrupt: irq 0x%X status 0x%X.\n", irq, status);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 7bb5f07..e5ffb2c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -523,6 +523,7 @@
 	hw_feat->sph           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, SPHEN);
 	hw_feat->tso           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, TSOEN);
 	hw_feat->dma_debug     = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, DBGMEMA);
+	hw_feat->rss           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, RSSEN);
 	hw_feat->tc_cnt	       = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, NUMTC);
 	hw_feat->hash_table_size = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R,
 						  HASHTBLSZ);
@@ -552,13 +553,14 @@
 		break;
 	}
 
-	/* The Queue and Channel counts are zero based so increment them
+	/* The Queue, Channel and TC counts are zero based so increment them
 	 * to get the actual number
 	 */
 	hw_feat->rx_q_cnt++;
 	hw_feat->tx_q_cnt++;
 	hw_feat->rx_ch_cnt++;
 	hw_feat->tx_ch_cnt++;
+	hw_feat->tc_cnt++;
 
 	DBGPR("<--xgbe_get_all_hw_features\n");
 }
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 83a5028..793f3b7 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -369,6 +369,8 @@
 		if (unlikely(xgene_enet_is_desc_slot_empty(raw_desc)))
 			break;
 
+		/* read fpqnum field after dataaddr field */
+		dma_rmb();
 		if (is_rx_desc(raw_desc))
 			ret = xgene_enet_rx_frame(ring, raw_desc);
 		else
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index 7403dff..905ac5f 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -32,7 +32,8 @@
 	  will be called cs89x0.
 
 config CS89x0_PLATFORM
-	bool "CS89x0 platform driver support"
+	bool "CS89x0 platform driver support" if HAS_IOPORT_MAP
+	default !HAS_IOPORT_MAP
 	depends on CS89x0
 	help
 	  Say Y to compile the cs89x0 driver as a platform driver. This
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 3e1a9c1..fda12fb 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -1586,7 +1586,7 @@
 		return -EBUSY;
 
 	/* Fill regular entries */
-	for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].ctrl);
+	for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].prop);
 	     i++)
 		gfar_write_filer(priv, i, tab->fe[i].ctrl, tab->fe[i].prop);
 	/* Fill the rest with fall-troughs */
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 63c807c..edea13b 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1907,7 +1907,8 @@
 
 static int igbvf_tso(struct igbvf_adapter *adapter,
                      struct igbvf_ring *tx_ring,
-                     struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
+		     struct sk_buff *skb, u32 tx_flags, u8 *hdr_len,
+		     __be16 protocol)
 {
 	struct e1000_adv_tx_context_desc *context_desc;
 	struct igbvf_buffer *buffer_info;
@@ -1927,7 +1928,7 @@
 	l4len = tcp_hdrlen(skb);
 	*hdr_len += l4len;
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	if (protocol == htons(ETH_P_IP)) {
 		struct iphdr *iph = ip_hdr(skb);
 		iph->tot_len = 0;
 		iph->check = 0;
@@ -1958,7 +1959,7 @@
 	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
 	tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);
 
-	if (skb->protocol == htons(ETH_P_IP))
+	if (protocol == htons(ETH_P_IP))
 		tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
 	tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
 
@@ -1984,7 +1985,8 @@
 
 static inline bool igbvf_tx_csum(struct igbvf_adapter *adapter,
                                  struct igbvf_ring *tx_ring,
-                                 struct sk_buff *skb, u32 tx_flags)
+				 struct sk_buff *skb, u32 tx_flags,
+				 __be16 protocol)
 {
 	struct e1000_adv_tx_context_desc *context_desc;
 	unsigned int i;
@@ -2011,7 +2013,7 @@
 		tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			switch (skb->protocol) {
+			switch (protocol) {
 			case htons(ETH_P_IP):
 				tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
 				if (ip_hdr(skb)->protocol == IPPROTO_TCP)
@@ -2211,6 +2213,7 @@
 	u8 hdr_len = 0;
 	int count = 0;
 	int tso = 0;
+	__be16 protocol = vlan_get_protocol(skb);
 
 	if (test_bit(__IGBVF_DOWN, &adapter->state)) {
 		dev_kfree_skb_any(skb);
@@ -2239,13 +2242,13 @@
 		tx_flags |= (vlan_tx_tag_get(skb) << IGBVF_TX_FLAGS_VLAN_SHIFT);
 	}
 
-	if (skb->protocol == htons(ETH_P_IP))
+	if (protocol == htons(ETH_P_IP))
 		tx_flags |= IGBVF_TX_FLAGS_IPV4;
 
 	first = tx_ring->next_to_use;
 
 	tso = skb_is_gso(skb) ?
-		igbvf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len) : 0;
+		igbvf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len, protocol) : 0;
 	if (unlikely(tso < 0)) {
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
@@ -2253,7 +2256,7 @@
 
 	if (tso)
 		tx_flags |= IGBVF_TX_FLAGS_TSO;
-	else if (igbvf_tx_csum(adapter, tx_ring, skb, tx_flags) &&
+	else if (igbvf_tx_csum(adapter, tx_ring, skb, tx_flags, protocol) &&
 	         (skb->ip_summed == CHECKSUM_PARTIAL))
 		tx_flags |= IGBVF_TX_FLAGS_CSUM;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2ed2c7d..67b02bd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7227,11 +7227,11 @@
 		if (!vhdr)
 			goto out_drop;
 
-		protocol = vhdr->h_vlan_encapsulated_proto;
 		tx_flags |= ntohs(vhdr->h_vlan_TCI) <<
 				  IXGBE_TX_FLAGS_VLAN_SHIFT;
 		tx_flags |= IXGBE_TX_FLAGS_SW_VLAN;
 	}
+	protocol = vlan_get_protocol(skb);
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 	    adapter->ptp_clock &&
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 62a0d8e..38c7a0b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3099,7 +3099,7 @@
 	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
 	type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP;
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	if (first->protocol == htons(ETH_P_IP)) {
 		struct iphdr *iph = ip_hdr(skb);
 		iph->tot_len = 0;
 		iph->check = 0;
@@ -3156,7 +3156,7 @@
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u8 l4_hdr = 0;
-		switch (skb->protocol) {
+		switch (first->protocol) {
 		case htons(ETH_P_IP):
 			vlan_macip_lens |= skb_network_header_len(skb);
 			type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index bdd4eea..210691c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -235,7 +235,8 @@
 extern int mlx4_log_num_mgm_entry_size;
 extern int log_mtts_per_seg;
 
-#define MLX4_MAX_NUM_SLAVES	(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF)
+#define MLX4_MAX_NUM_SLAVES	(min(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF, \
+				     MLX4_MFUNC_MAX))
 #define ALL_SLAVES 0xff
 
 struct mlx4_bitmap {
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 18e5de7..4e1f58c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -967,7 +967,12 @@
 	tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring,
 					      budget);
 	work_done = qlcnic_process_rcv_ring(sds_ring, budget);
-	if ((work_done < budget) && tx_complete) {
+
+	/* Check if we need a repoll */
+	if (!tx_complete)
+		work_done = budget;
+
+	if (work_done < budget) {
 		napi_complete(&sds_ring->napi);
 		if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) {
 			qlcnic_enable_sds_intr(adapter, sds_ring);
@@ -992,6 +997,9 @@
 		napi_complete(&tx_ring->napi);
 		if (test_bit(__QLCNIC_DEV_UP, &adapter->state))
 			qlcnic_enable_tx_intr(adapter, tx_ring);
+	} else {
+		/* As qlcnic_process_cmd_ring() returned 0, we need a repoll*/
+		work_done = budget;
 	}
 
 	return work_done;
@@ -1950,7 +1958,12 @@
 
 	tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring, budget);
 	work_done = qlcnic_83xx_process_rcv_ring(sds_ring, budget);
-	if ((work_done < budget) && tx_complete) {
+
+	/* Check if we need a repoll */
+	if (!tx_complete)
+		work_done = budget;
+
+	if (work_done < budget) {
 		napi_complete(&sds_ring->napi);
 		qlcnic_enable_sds_intr(adapter, sds_ring);
 	}
@@ -1973,7 +1986,12 @@
 
 	tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring, budget);
 	work_done = qlcnic_83xx_process_rcv_ring(sds_ring, budget);
-	if ((work_done < budget) && tx_complete) {
+
+	/* Check if we need a repoll */
+	if (!tx_complete)
+		work_done = budget;
+
+	if (work_done < budget) {
 		napi_complete(&sds_ring->napi);
 		qlcnic_enable_sds_intr(adapter, sds_ring);
 	}
@@ -1995,6 +2013,9 @@
 		napi_complete(&tx_ring->napi);
 		if (test_bit(__QLCNIC_DEV_UP , &adapter->state))
 			qlcnic_enable_tx_intr(adapter, tx_ring);
+	} else {
+		/* need a repoll */
+		work_done = budget;
 	}
 
 	return work_done;
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 6c904a6..ef5aed3 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2351,23 +2351,29 @@
 {
 	struct ql_adapter *qdev = netdev_priv(ndev);
 	int status = 0;
+	bool need_restart = netif_running(ndev);
 
-	status = ql_adapter_down(qdev);
-	if (status) {
-		netif_err(qdev, link, qdev->ndev,
-			  "Failed to bring down the adapter\n");
-		return status;
+	if (need_restart) {
+		status = ql_adapter_down(qdev);
+		if (status) {
+			netif_err(qdev, link, qdev->ndev,
+				  "Failed to bring down the adapter\n");
+			return status;
+		}
 	}
 
 	/* update the features with resent change */
 	ndev->features = features;
 
-	status = ql_adapter_up(qdev);
-	if (status) {
-		netif_err(qdev, link, qdev->ndev,
-			  "Failed to bring up the adapter\n");
-		return status;
+	if (need_restart) {
+		status = ql_adapter_up(qdev);
+		if (status) {
+			netif_err(qdev, link, qdev->ndev,
+				  "Failed to bring up the adapter\n");
+			return status;
+		}
 	}
+
 	return status;
 }
 
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index d2835bf..3699b98 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1119,6 +1119,7 @@
 			skb_shinfo(nskb)->gso_size = skb_shinfo(skb)->gso_size;
 			skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type;
 		}
+		nskb->queue_mapping = skb->queue_mapping;
 		dev_kfree_skb(skb);
 		skb = nskb;
 	}
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 9f49c01..7cd4eb3 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -716,7 +716,7 @@
 	u64 req_id;
 	unsigned int section_index = NETVSC_INVALID_INDEX;
 	u32 msg_size = 0;
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	u16 q_idx = packet->q_idx;
 
 
@@ -743,8 +743,6 @@
 							   packet);
 			skb = (struct sk_buff *)
 			      (unsigned long)packet->send_completion_tid;
-			if (skb)
-				dev_kfree_skb_any(skb);
 			packet->page_buf_cnt = 0;
 		}
 	}
@@ -810,6 +808,13 @@
 			   packet, ret);
 	}
 
+	if (ret != 0) {
+		if (section_index != NETVSC_INVALID_INDEX)
+			netvsc_free_send_slot(net_device, section_index);
+	} else if (skb) {
+		dev_kfree_skb_any(skb);
+	}
+
 	return ret;
 }
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 7df2217..919f4fc 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -17,7 +17,6 @@
 #include <linux/fs.h>
 #include <linux/uio.h>
 
-#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include <net/rtnetlink.h>
 #include <net/sock.h>
@@ -81,7 +80,7 @@
 static const struct proto_ops macvtap_socket_ops;
 
 #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
-		      NETIF_F_TSO6)
+		      NETIF_F_TSO6 | NETIF_F_UFO)
 #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
 #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
 
@@ -586,11 +585,7 @@
 			gso_type = SKB_GSO_TCPV6;
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
-			pr_warn_once("macvtap: %s: using disabled UFO feature; please fix this program\n",
-				     current->comm);
 			gso_type = SKB_GSO_UDP;
-			if (skb->protocol == htons(ETH_P_IPV6))
-				ipv6_proxy_select_ident(skb);
 			break;
 		default:
 			return -EINVAL;
@@ -636,6 +631,8 @@
 			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 		else if (sinfo->gso_type & SKB_GSO_TCPV6)
 			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+		else if (sinfo->gso_type & SKB_GSO_UDP)
+			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
 		else
 			BUG();
 		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
@@ -965,6 +962,9 @@
 			if (arg & TUN_F_TSO6)
 				feature_mask |= NETIF_F_TSO6;
 		}
+
+		if (arg & TUN_F_UFO)
+			feature_mask |= NETIF_F_UFO;
 	}
 
 	/* tun/tap driver inverts the usage for TSO offloads, where
@@ -975,7 +975,7 @@
 	 * When user space turns off TSO, we turn off GSO/LRO so that
 	 * user-space will not receive TSO frames.
 	 */
-	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6))
+	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_UFO))
 		features |= RX_OFFLOADS;
 	else
 		features &= ~RX_OFFLOADS;
@@ -1090,7 +1090,7 @@
 	case TUNSETOFFLOAD:
 		/* let the user check for future flags */
 		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
-			    TUN_F_TSO_ECN))
+			    TUN_F_TSO_ECN | TUN_F_UFO))
 			return -EINVAL;
 
 		rtnl_lock();
diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c
index 602c625..b5edc7f 100644
--- a/drivers/net/ppp/ppp_deflate.c
+++ b/drivers/net/ppp/ppp_deflate.c
@@ -246,7 +246,7 @@
 	/*
 	 * See if we managed to reduce the size of the packet.
 	 */
-	if (olen < isize) {
+	if (olen < isize && olen <= osize) {
 		state->stats.comp_bytes += olen;
 		state->stats.comp_packets++;
 	} else {
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 8c8dc16..10f9e40 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -65,7 +65,6 @@
 #include <linux/nsproxy.h>
 #include <linux/virtio_net.h>
 #include <linux/rcupdate.h>
-#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
@@ -187,7 +186,7 @@
 	struct net_device	*dev;
 	netdev_features_t	set_features;
 #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
-			  NETIF_F_TSO6)
+			  NETIF_F_TSO6|NETIF_F_UFO)
 
 	int			vnet_hdr_sz;
 	int			sndbuf;
@@ -1167,8 +1166,6 @@
 		break;
 	}
 
-	skb_reset_network_header(skb);
-
 	if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		pr_debug("GSO!\n");
 		switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -1179,20 +1176,8 @@
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
-		{
-			static bool warned;
-
-			if (!warned) {
-				warned = true;
-				netdev_warn(tun->dev,
-					    "%s: using disabled UFO feature; please fix this program\n",
-					    current->comm);
-			}
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-			if (skb->protocol == htons(ETH_P_IPV6))
-				ipv6_proxy_select_ident(skb);
 			break;
-		}
 		default:
 			tun->dev->stats.rx_frame_errors++;
 			kfree_skb(skb);
@@ -1221,6 +1206,7 @@
 		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
 	}
 
+	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb, 0);
 
 	rxhash = skb_get_hash(skb);
@@ -1298,6 +1284,8 @@
 				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 			else if (sinfo->gso_type & SKB_GSO_TCPV6)
 				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+			else if (sinfo->gso_type & SKB_GSO_UDP)
+				gso.gso_type = VIRTIO_NET_HDR_GSO_UDP;
 			else {
 				pr_err("unexpected GSO type: "
 				       "0x%x, gso_size %d, hdr_len %d\n",
@@ -1746,6 +1734,11 @@
 				features |= NETIF_F_TSO6;
 			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
 		}
+
+		if (arg & TUN_F_UFO) {
+			features |= NETIF_F_UFO;
+			arg &= ~TUN_F_UFO;
+		}
 	}
 
 	/* This gives the user a way to test for new features in future by
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 99b69af..4a1e9c4 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -77,7 +77,7 @@
 		int ret;
 
 		udelay(1);
-		ret = sr_read_reg(dev, EPCR, &tmp);
+		ret = sr_read_reg(dev, SR_EPCR, &tmp);
 		if (ret < 0)
 			return ret;
 
@@ -98,15 +98,15 @@
 
 	mutex_lock(&dev->phy_mutex);
 
-	sr_write_reg(dev, EPAR, phy ? (reg | EPAR_PHY_ADR) : reg);
-	sr_write_reg(dev, EPCR, phy ? (EPCR_EPOS | EPCR_ERPRR) : EPCR_ERPRR);
+	sr_write_reg(dev, SR_EPAR, phy ? (reg | EPAR_PHY_ADR) : reg);
+	sr_write_reg(dev, SR_EPCR, phy ? (EPCR_EPOS | EPCR_ERPRR) : EPCR_ERPRR);
 
 	ret = wait_phy_eeprom_ready(dev, phy);
 	if (ret < 0)
 		goto out_unlock;
 
-	sr_write_reg(dev, EPCR, 0x0);
-	ret = sr_read(dev, EPDR, 2, value);
+	sr_write_reg(dev, SR_EPCR, 0x0);
+	ret = sr_read(dev, SR_EPDR, 2, value);
 
 	netdev_dbg(dev->net, "read shared %d 0x%02x returned 0x%04x, %d\n",
 		   phy, reg, *value, ret);
@@ -123,19 +123,19 @@
 
 	mutex_lock(&dev->phy_mutex);
 
-	ret = sr_write(dev, EPDR, 2, &value);
+	ret = sr_write(dev, SR_EPDR, 2, &value);
 	if (ret < 0)
 		goto out_unlock;
 
-	sr_write_reg(dev, EPAR, phy ? (reg | EPAR_PHY_ADR) : reg);
-	sr_write_reg(dev, EPCR, phy ? (EPCR_WEP | EPCR_EPOS | EPCR_ERPRW) :
+	sr_write_reg(dev, SR_EPAR, phy ? (reg | EPAR_PHY_ADR) : reg);
+	sr_write_reg(dev, SR_EPCR, phy ? (EPCR_WEP | EPCR_EPOS | EPCR_ERPRW) :
 		    (EPCR_WEP | EPCR_ERPRW));
 
 	ret = wait_phy_eeprom_ready(dev, phy);
 	if (ret < 0)
 		goto out_unlock;
 
-	sr_write_reg(dev, EPCR, 0x0);
+	sr_write_reg(dev, SR_EPCR, 0x0);
 
 out_unlock:
 	mutex_unlock(&dev->phy_mutex);
@@ -188,7 +188,7 @@
 	if (loc == MII_BMSR) {
 		u8 value;
 
-		sr_read_reg(dev, NSR, &value);
+		sr_read_reg(dev, SR_NSR, &value);
 		if (value & NSR_LINKST)
 			rc = 1;
 	}
@@ -228,7 +228,7 @@
 	int rc = 0;
 
 	/* Get the Link Status directly */
-	sr_read_reg(dev, NSR, &value);
+	sr_read_reg(dev, SR_NSR, &value);
 	if (value & NSR_LINKST)
 		rc = 1;
 
@@ -281,8 +281,8 @@
 		}
 	}
 
-	sr_write_async(dev, MAR, SR_MCAST_SIZE, hashes);
-	sr_write_reg_async(dev, RCR, rx_ctl);
+	sr_write_async(dev, SR_MAR, SR_MCAST_SIZE, hashes);
+	sr_write_reg_async(dev, SR_RCR, rx_ctl);
 }
 
 static int sr9700_set_mac_address(struct net_device *netdev, void *p)
@@ -297,7 +297,7 @@
 	}
 
 	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
-	sr_write_async(dev, PAR, 6, netdev->dev_addr);
+	sr_write_async(dev, SR_PAR, 6, netdev->dev_addr);
 
 	return 0;
 }
@@ -340,7 +340,7 @@
 	mii->phy_id_mask = 0x1f;
 	mii->reg_num_mask = 0x1f;
 
-	sr_write_reg(dev, NCR, NCR_RST);
+	sr_write_reg(dev, SR_NCR, NCR_RST);
 	udelay(20);
 
 	/* read MAC
@@ -348,17 +348,17 @@
 	 * EEPROM automatically to PAR. In case there is no EEPROM externally,
 	 * a default MAC address is stored in PAR for making chip work properly.
 	 */
-	if (sr_read(dev, PAR, ETH_ALEN, netdev->dev_addr) < 0) {
+	if (sr_read(dev, SR_PAR, ETH_ALEN, netdev->dev_addr) < 0) {
 		netdev_err(netdev, "Error reading MAC address\n");
 		ret = -ENODEV;
 		goto out;
 	}
 
 	/* power up and reset phy */
-	sr_write_reg(dev, PRR, PRR_PHY_RST);
+	sr_write_reg(dev, SR_PRR, PRR_PHY_RST);
 	/* at least 10ms, here 20ms for safe */
 	mdelay(20);
-	sr_write_reg(dev, PRR, 0);
+	sr_write_reg(dev, SR_PRR, 0);
 	/* at least 1ms, here 2ms for reading right register */
 	udelay(2 * 1000);
 
diff --git a/drivers/net/usb/sr9700.h b/drivers/net/usb/sr9700.h
index fd687c5..258b030 100644
--- a/drivers/net/usb/sr9700.h
+++ b/drivers/net/usb/sr9700.h
@@ -14,13 +14,13 @@
 /* sr9700 spec. register table on Linux platform */
 
 /* Network Control Reg */
-#define	NCR			0x00
+#define	SR_NCR			0x00
 #define		NCR_RST			(1 << 0)
 #define		NCR_LBK			(3 << 1)
 #define		NCR_FDX			(1 << 3)
 #define		NCR_WAKEEN		(1 << 6)
 /* Network Status Reg */
-#define	NSR			0x01
+#define	SR_NSR			0x01
 #define		NSR_RXRDY		(1 << 0)
 #define		NSR_RXOV		(1 << 1)
 #define		NSR_TX1END		(1 << 2)
@@ -30,7 +30,7 @@
 #define		NSR_LINKST		(1 << 6)
 #define		NSR_SPEED		(1 << 7)
 /* Tx Control Reg */
-#define	TCR			0x02
+#define	SR_TCR			0x02
 #define		TCR_CRC_DIS		(1 << 1)
 #define		TCR_PAD_DIS		(1 << 2)
 #define		TCR_LC_CARE		(1 << 3)
@@ -38,7 +38,7 @@
 #define		TCR_EXCECM		(1 << 5)
 #define		TCR_LF_EN		(1 << 6)
 /* Tx Status Reg for Packet Index 1 */
-#define	TSR1		0x03
+#define	SR_TSR1		0x03
 #define		TSR1_EC			(1 << 2)
 #define		TSR1_COL		(1 << 3)
 #define		TSR1_LC			(1 << 4)
@@ -46,7 +46,7 @@
 #define		TSR1_LOC		(1 << 6)
 #define		TSR1_TLF		(1 << 7)
 /* Tx Status Reg for Packet Index 2 */
-#define	TSR2		0x04
+#define	SR_TSR2		0x04
 #define		TSR2_EC			(1 << 2)
 #define		TSR2_COL		(1 << 3)
 #define		TSR2_LC			(1 << 4)
@@ -54,7 +54,7 @@
 #define		TSR2_LOC		(1 << 6)
 #define		TSR2_TLF		(1 << 7)
 /* Rx Control Reg*/
-#define	RCR			0x05
+#define	SR_RCR			0x05
 #define		RCR_RXEN		(1 << 0)
 #define		RCR_PRMSC		(1 << 1)
 #define		RCR_RUNT		(1 << 2)
@@ -62,87 +62,87 @@
 #define		RCR_DIS_CRC		(1 << 4)
 #define		RCR_DIS_LONG	(1 << 5)
 /* Rx Status Reg */
-#define	RSR			0x06
+#define	SR_RSR			0x06
 #define		RSR_AE			(1 << 2)
 #define		RSR_MF			(1 << 6)
 #define		RSR_RF			(1 << 7)
 /* Rx Overflow Counter Reg */
-#define	ROCR		0x07
+#define	SR_ROCR		0x07
 #define		ROCR_ROC		(0x7F << 0)
 #define		ROCR_RXFU		(1 << 7)
 /* Back Pressure Threshold Reg */
-#define	BPTR		0x08
+#define	SR_BPTR		0x08
 #define		BPTR_JPT		(0x0F << 0)
 #define		BPTR_BPHW		(0x0F << 4)
 /* Flow Control Threshold Reg */
-#define	FCTR		0x09
+#define	SR_FCTR		0x09
 #define		FCTR_LWOT		(0x0F << 0)
 #define		FCTR_HWOT		(0x0F << 4)
 /* rx/tx Flow Control Reg */
-#define	FCR			0x0A
+#define	SR_FCR			0x0A
 #define		FCR_FLCE		(1 << 0)
 #define		FCR_BKPA		(1 << 4)
 #define		FCR_TXPEN		(1 << 5)
 #define		FCR_TXPF		(1 << 6)
 #define		FCR_TXP0		(1 << 7)
 /* Eeprom & Phy Control Reg */
-#define	EPCR		0x0B
+#define	SR_EPCR		0x0B
 #define		EPCR_ERRE		(1 << 0)
 #define		EPCR_ERPRW		(1 << 1)
 #define		EPCR_ERPRR		(1 << 2)
 #define		EPCR_EPOS		(1 << 3)
 #define		EPCR_WEP		(1 << 4)
 /* Eeprom & Phy Address Reg */
-#define	EPAR		0x0C
+#define	SR_EPAR		0x0C
 #define		EPAR_EROA		(0x3F << 0)
 #define		EPAR_PHY_ADR_MASK	(0x03 << 6)
 #define		EPAR_PHY_ADR		(0x01 << 6)
 /* Eeprom &	Phy Data Reg */
-#define	EPDR		0x0D	/* 0x0D ~ 0x0E for Data Reg Low & High */
+#define	SR_EPDR		0x0D	/* 0x0D ~ 0x0E for Data Reg Low & High */
 /* Wakeup Control Reg */
-#define	WCR			0x0F
+#define	SR_WCR			0x0F
 #define		WCR_MAGICST		(1 << 0)
 #define		WCR_LINKST		(1 << 2)
 #define		WCR_MAGICEN		(1 << 3)
 #define		WCR_LINKEN		(1 << 5)
 /* Physical Address Reg */
-#define	PAR			0x10	/* 0x10 ~ 0x15 6 bytes for PAR */
+#define	SR_PAR			0x10	/* 0x10 ~ 0x15 6 bytes for PAR */
 /* Multicast Address Reg */
-#define	MAR			0x16	/* 0x16 ~ 0x1D 8 bytes for MAR */
+#define	SR_MAR			0x16	/* 0x16 ~ 0x1D 8 bytes for MAR */
 /* 0x1e unused */
 /* Phy Reset Reg */
-#define	PRR			0x1F
+#define	SR_PRR			0x1F
 #define		PRR_PHY_RST		(1 << 0)
 /* Tx sdram Write Pointer Address Low */
-#define	TWPAL		0x20
+#define	SR_TWPAL		0x20
 /* Tx sdram Write Pointer Address High */
-#define	TWPAH		0x21
+#define	SR_TWPAH		0x21
 /* Tx sdram Read Pointer Address Low */
-#define	TRPAL		0x22
+#define	SR_TRPAL		0x22
 /* Tx sdram Read Pointer Address High */
-#define	TRPAH		0x23
+#define	SR_TRPAH		0x23
 /* Rx sdram Write Pointer Address Low */
-#define	RWPAL		0x24
+#define	SR_RWPAL		0x24
 /* Rx sdram Write Pointer Address High */
-#define	RWPAH		0x25
+#define	SR_RWPAH		0x25
 /* Rx sdram Read Pointer Address Low */
-#define	RRPAL		0x26
+#define	SR_RRPAL		0x26
 /* Rx sdram Read Pointer Address High */
-#define	RRPAH		0x27
+#define	SR_RRPAH		0x27
 /* Vendor ID register */
-#define	VID			0x28	/* 0x28 ~ 0x29 2 bytes for VID */
+#define	SR_VID			0x28	/* 0x28 ~ 0x29 2 bytes for VID */
 /* Product ID register */
-#define	PID			0x2A	/* 0x2A ~ 0x2B 2 bytes for PID */
+#define	SR_PID			0x2A	/* 0x2A ~ 0x2B 2 bytes for PID */
 /* CHIP Revision register */
-#define	CHIPR		0x2C
+#define	SR_CHIPR		0x2C
 /* 0x2D --> 0xEF unused */
 /* USB Device Address */
-#define	USBDA		0xF0
+#define	SR_USBDA		0xF0
 #define		USBDA_USBFA		(0x7F << 0)
 /* RX packet Counter Reg */
-#define	RXC			0xF1
+#define	SR_RXC			0xF1
 /* Tx packet Counter & USB Status Reg */
-#define	TXC_USBS	0xF2
+#define	SR_TXC_USBS		0xF2
 #define		TXC_USBS_TXC0		(1 << 0)
 #define		TXC_USBS_TXC1		(1 << 1)
 #define		TXC_USBS_TXC2		(1 << 2)
@@ -150,7 +150,7 @@
 #define		TXC_USBS_SUSFLAG	(1 << 6)
 #define		TXC_USBS_RXFAULT	(1 << 7)
 /* USB Control register */
-#define	USBC		0xF4
+#define	SR_USBC			0xF4
 #define		USBC_EP3NAK		(1 << 4)
 #define		USBC_EP3ACK		(1 << 5)
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5ca9771..059fdf1 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -490,17 +490,8 @@
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
-		{
-			static bool warned;
-
-			if (!warned) {
-				warned = true;
-				netdev_warn(dev,
-					    "host using disabled UFO feature; please fix it\n");
-			}
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 			break;
-		}
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 			break;
@@ -888,6 +879,8 @@
 			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
 			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+		else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
 		else
 			BUG();
 		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
@@ -1748,7 +1741,7 @@
 			dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
 
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
-			dev->hw_features |= NETIF_F_TSO
+			dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO
 				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
 		}
 		/* Individual feature bits: what can host handle? */
@@ -1758,9 +1751,11 @@
 			dev->hw_features |= NETIF_F_TSO6;
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN))
 			dev->hw_features |= NETIF_F_TSO_ECN;
+		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO))
+			dev->hw_features |= NETIF_F_UFO;
 
 		if (gso)
-			dev->features |= dev->hw_features & NETIF_F_ALL_TSO;
+			dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO);
 		/* (!csum && gso) case will be fixed by register_netdev() */
 	}
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
@@ -1798,7 +1793,8 @@
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
 		vi->big_packets = true;
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
@@ -1994,9 +1990,9 @@
 static unsigned int features[] = {
 	VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM,
 	VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC,
-	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_TSO6,
+	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6,
 	VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
-	VIRTIO_NET_F_GUEST_ECN,
+	VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
 	VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
 	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 7fbd89f..a8c755d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2432,10 +2432,10 @@
 	dev_put(vxlan->dev);
 }
 
-static int vxlan_newlink(struct net *net, struct net_device *dev,
+static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
-	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	__u32 vni;
@@ -2445,7 +2445,7 @@
 	if (!data[IFLA_VXLAN_ID])
 		return -EINVAL;
 
-	vxlan->net = dev_net(dev);
+	vxlan->net = src_net;
 
 	vni = nla_get_u32(data[IFLA_VXLAN_ID]);
 	dst->remote_vni = vni;
@@ -2481,7 +2481,7 @@
 	if (data[IFLA_VXLAN_LINK] &&
 	    (dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) {
 		struct net_device *lowerdev
-			 = __dev_get_by_index(net, dst->remote_ifindex);
+			 = __dev_get_by_index(src_net, dst->remote_ifindex);
 
 		if (!lowerdev) {
 			pr_info("ifindex %d does not exist\n", dst->remote_ifindex);
@@ -2557,7 +2557,7 @@
 	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
 		vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
 
-	if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
+	if (vxlan_find_vni(src_net, vni, use_ipv6 ? AF_INET6 : AF_INET,
 			   vxlan->dst_port)) {
 		pr_info("duplicate VNI %u\n", vni);
 		return -EEXIST;
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 94e2349..a2fdd15 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -25,7 +25,7 @@
 # There is no way to detect a comtrol sv11 - force it modular for now.
 config HOSTESS_SV11
 	tristate "Comtrol Hostess SV-11 support"
-	depends on ISA && m && ISA_DMA_API && INET && HDLC
+	depends on ISA && m && ISA_DMA_API && INET && HDLC && VIRT_TO_BUS
 	help
 	  Driver for Comtrol Hostess SV-11 network card which
 	  operates on low speed synchronous serial links at up to
@@ -37,7 +37,7 @@
 # The COSA/SRP driver has not been tested as non-modular yet.
 config COSA
 	tristate "COSA/SRP sync serial boards support"
-	depends on ISA && m && ISA_DMA_API && HDLC
+	depends on ISA && m && ISA_DMA_API && HDLC && VIRT_TO_BUS
 	---help---
 	  Driver for COSA and SRP synchronous serial boards.
 
@@ -87,7 +87,7 @@
 # There is no way to detect a Sealevel board. Force it modular
 config SEALEVEL_4021
 	tristate "Sealevel Systems 4021 support"
-	depends on ISA && m && ISA_DMA_API && INET && HDLC
+	depends on ISA && m && ISA_DMA_API && INET && HDLC && VIRT_TO_BUS
 	help
 	  This is a driver for the Sealevel Systems ACB 56 serial I/O adapter.
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 9259a73..037f74f 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -578,6 +578,7 @@
 		goto err_rx_unbind;
 	}
 	queue->task = task;
+	get_task_struct(task);
 
 	task = kthread_create(xenvif_dealloc_kthread,
 			      (void *)queue, "%s-dealloc", queue->name);
@@ -634,6 +635,7 @@
 
 		if (queue->task) {
 			kthread_stop(queue->task);
+			put_task_struct(queue->task);
 			queue->task = NULL;
 		}
 
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 908e65e..c8ce701 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -2109,8 +2109,7 @@
 		 */
 		if (unlikely(vif->disabled && queue->id == 0)) {
 			xenvif_carrier_off(vif);
-			xenvif_rx_queue_purge(queue);
-			continue;
+			break;
 		}
 
 		if (!skb_queue_empty(&queue->rx_queue))
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index df781cd..17ca986 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -283,6 +283,9 @@
 	struct msi_msg msg;
 	struct pcie_port *pp = sys_to_pcie(pdev->bus->sysdata);
 
+	if (desc->msi_attrib.is_msix)
+		return -EINVAL;
+
 	irq = assign_irq(1, desc, &pos);
 	if (irq < 0)
 		return irq;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index e52356a..903d507 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -324,18 +324,52 @@
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_868,		quirk_s3_64M);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_968,		quirk_s3_64M);
 
+static void quirk_io(struct pci_dev *dev, int pos, unsigned size,
+		     const char *name)
+{
+	u32 region;
+	struct pci_bus_region bus_region;
+	struct resource *res = dev->resource + pos;
+
+	pci_read_config_dword(dev, PCI_BASE_ADDRESS_0 + (pos << 2), &region);
+
+	if (!region)
+		return;
+
+	res->name = pci_name(dev);
+	res->flags = region & ~PCI_BASE_ADDRESS_IO_MASK;
+	res->flags |=
+		(IORESOURCE_IO | IORESOURCE_PCI_FIXED | IORESOURCE_SIZEALIGN);
+	region &= ~(size - 1);
+
+	/* Convert from PCI bus to resource space */
+	bus_region.start = region;
+	bus_region.end = region + size - 1;
+	pcibios_bus_to_resource(dev->bus, res, &bus_region);
+
+	dev_info(&dev->dev, FW_BUG "%s quirk: reg 0x%x: %pR\n",
+		 name, PCI_BASE_ADDRESS_0 + (pos << 2), res);
+}
+
 /*
  * Some CS5536 BIOSes (for example, the Soekris NET5501 board w/ comBIOS
  * ver. 1.33  20070103) don't set the correct ISA PCI region header info.
  * BAR0 should be 8 bytes; instead, it may be set to something like 8k
  * (which conflicts w/ BAR1's memory range).
+ *
+ * CS553x's ISA PCI BARs may also be read-only (ref:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=85991 - Comment #4 forward).
  */
 static void quirk_cs5536_vsa(struct pci_dev *dev)
 {
+	static char *name = "CS5536 ISA bridge";
+
 	if (pci_resource_len(dev, 0) != 8) {
-		struct resource *res = &dev->resource[0];
-		res->end = res->start + 8 - 1;
-		dev_info(&dev->dev, "CS5536 ISA bridge bug detected (incorrect header); workaround applied\n");
+		quirk_io(dev, 0,   8, name);	/* SMB */
+		quirk_io(dev, 1, 256, name);	/* GPIO */
+		quirk_io(dev, 2,  64, name);	/* MFGPT */
+		dev_info(&dev->dev, "%s bug detected (incorrect header); workaround applied\n",
+			 name);
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, quirk_cs5536_vsa);
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index c3a60b5..a6f116a 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -414,6 +414,14 @@
 	  Exynos5420/Exynos5800 SoCs to control various voltages.
 	  It includes support for control of voltage and ramp speed.
 
+config REGULATOR_MAX77843
+	tristate "Maxim 77843 regulator"
+	depends on MFD_MAX77843
+	help
+	  This driver controls a Maxim 77843 regulator.
+	  The regulator include two 'SAFEOUT' for USB(Universal Serial Bus)
+	  This is suitable for Exynos5433 SoC chips.
+
 config REGULATOR_MC13XXX_CORE
 	tristate
 
@@ -433,6 +441,15 @@
 	  Say y here to support the regulators found on the Freescale MC13892
 	  PMIC.
 
+config REGULATOR_MT6397
+	tristate "MediaTek MT6397 PMIC"
+	depends on MFD_MT6397
+	help
+	  Say y here to select this option to enable the power regulator of
+	  MediaTek MT6397 PMIC.
+	  This driver supports the control of different power rails of device
+	  through regulator interface.
+
 config REGULATOR_PALMAS
 	tristate "TI Palmas PMIC Regulators"
 	depends on MFD_PALMAS
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 1f28ebf..2c4da15 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -55,9 +55,11 @@
 obj-$(CONFIG_REGULATOR_MAX77686) += max77686.o
 obj-$(CONFIG_REGULATOR_MAX77693) += max77693.o
 obj-$(CONFIG_REGULATOR_MAX77802) += max77802.o
+obj-$(CONFIG_REGULATOR_MAX77843) += max77843.o
 obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o
 obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o
 obj-$(CONFIG_REGULATOR_MC13XXX_CORE) +=  mc13xxx-regulator-core.o
+obj-$(CONFIG_REGULATOR_MT6397)	+= mt6397-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_RPM) += qcom_rpm-regulator.o
 obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o
 obj-$(CONFIG_REGULATOR_PFUZE100) += pfuze100-regulator.o
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index f23d7e1..e4331f5 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -32,11 +32,13 @@
 
 #define AXP20X_FREQ_DCDC_MASK		0x0f
 
-#define AXP20X_DESC_IO(_id, _supply, _min, _max, _step, _vreg, _vmask, _ereg,   \
-		       _emask, _enable_val, _disable_val)			\
+#define AXP20X_DESC_IO(_id, _match, _supply, _min, _max, _step, _vreg, _vmask,	\
+		       _ereg, _emask, _enable_val, _disable_val)		\
 	[AXP20X_##_id] = {							\
 		.name		= #_id,						\
 		.supply_name	= (_supply),					\
+		.of_match	= of_match_ptr(_match),				\
+		.regulators_node = of_match_ptr("regulators"),			\
 		.type		= REGULATOR_VOLTAGE,				\
 		.id		= AXP20X_##_id,					\
 		.n_voltages	= (((_max) - (_min)) / (_step) + 1),		\
@@ -52,11 +54,13 @@
 		.ops		= &axp20x_ops,					\
 	}
 
-#define AXP20X_DESC(_id, _supply, _min, _max, _step, _vreg, _vmask, _ereg,	\
-		    _emask) 							\
+#define AXP20X_DESC(_id, _match, _supply, _min, _max, _step, _vreg, _vmask,	\
+		    _ereg, _emask)						\
 	[AXP20X_##_id] = {							\
 		.name		= #_id,						\
 		.supply_name	= (_supply),					\
+		.of_match	= of_match_ptr(_match),				\
+		.regulators_node = of_match_ptr("regulators"),			\
 		.type		= REGULATOR_VOLTAGE,				\
 		.id		= AXP20X_##_id,					\
 		.n_voltages	= (((_max) - (_min)) / (_step) + 1),		\
@@ -70,10 +74,12 @@
 		.ops		= &axp20x_ops,					\
 	}
 
-#define AXP20X_DESC_FIXED(_id, _supply, _volt)					\
+#define AXP20X_DESC_FIXED(_id, _match, _supply, _volt)				\
 	[AXP20X_##_id] = {							\
 		.name		= #_id,						\
 		.supply_name	= (_supply),					\
+		.of_match	= of_match_ptr(_match),				\
+		.regulators_node = of_match_ptr("regulators"),			\
 		.type		= REGULATOR_VOLTAGE,				\
 		.id		= AXP20X_##_id,					\
 		.n_voltages	= 1,						\
@@ -82,10 +88,13 @@
 		.ops		= &axp20x_ops_fixed				\
 	}
 
-#define AXP20X_DESC_TABLE(_id, _supply, _table, _vreg, _vmask, _ereg, _emask)	\
+#define AXP20X_DESC_TABLE(_id, _match, _supply, _table, _vreg, _vmask, _ereg,	\
+			  _emask)						\
 	[AXP20X_##_id] = {							\
 		.name		= #_id,						\
 		.supply_name	= (_supply),					\
+		.of_match	= of_match_ptr(_match),				\
+		.regulators_node = of_match_ptr("regulators"),			\
 		.type		= REGULATOR_VOLTAGE,				\
 		.id		= AXP20X_##_id,					\
 		.n_voltages	= ARRAY_SIZE(_table),				\
@@ -127,36 +136,20 @@
 };
 
 static const struct regulator_desc axp20x_regulators[] = {
-	AXP20X_DESC(DCDC2, "vin2", 700, 2275, 25, AXP20X_DCDC2_V_OUT, 0x3f,
-		    AXP20X_PWR_OUT_CTRL, 0x10),
-	AXP20X_DESC(DCDC3, "vin3", 700, 3500, 25, AXP20X_DCDC3_V_OUT, 0x7f,
-		    AXP20X_PWR_OUT_CTRL, 0x02),
-	AXP20X_DESC_FIXED(LDO1, "acin", 1300),
-	AXP20X_DESC(LDO2, "ldo24in", 1800, 3300, 100, AXP20X_LDO24_V_OUT, 0xf0,
-		    AXP20X_PWR_OUT_CTRL, 0x04),
-	AXP20X_DESC(LDO3, "ldo3in", 700, 3500, 25, AXP20X_LDO3_V_OUT, 0x7f,
-		    AXP20X_PWR_OUT_CTRL, 0x40),
-	AXP20X_DESC_TABLE(LDO4, "ldo24in", axp20x_ldo4_data, AXP20X_LDO24_V_OUT, 0x0f,
-			  AXP20X_PWR_OUT_CTRL, 0x08),
-	AXP20X_DESC_IO(LDO5, "ldo5in", 1800, 3300, 100, AXP20X_LDO5_V_OUT, 0xf0,
-		       AXP20X_GPIO0_CTRL, 0x07, AXP20X_IO_ENABLED,
-		       AXP20X_IO_DISABLED),
-};
-
-#define AXP_MATCH(_name, _id) \
-	[AXP20X_##_id] = { \
-		.name		= #_name, \
-		.driver_data	= (void *) &axp20x_regulators[AXP20X_##_id], \
-	}
-
-static struct of_regulator_match axp20x_matches[] = {
-	AXP_MATCH(dcdc2, DCDC2),
-	AXP_MATCH(dcdc3, DCDC3),
-	AXP_MATCH(ldo1, LDO1),
-	AXP_MATCH(ldo2, LDO2),
-	AXP_MATCH(ldo3, LDO3),
-	AXP_MATCH(ldo4, LDO4),
-	AXP_MATCH(ldo5, LDO5),
+	AXP20X_DESC(DCDC2, "dcdc2", "vin2", 700, 2275, 25, AXP20X_DCDC2_V_OUT,
+		    0x3f, AXP20X_PWR_OUT_CTRL, 0x10),
+	AXP20X_DESC(DCDC3, "dcdc3", "vin3", 700, 3500, 25, AXP20X_DCDC3_V_OUT,
+		    0x7f, AXP20X_PWR_OUT_CTRL, 0x02),
+	AXP20X_DESC_FIXED(LDO1, "ldo1", "acin", 1300),
+	AXP20X_DESC(LDO2, "ldo2", "ldo24in", 1800, 3300, 100,
+		    AXP20X_LDO24_V_OUT, 0xf0, AXP20X_PWR_OUT_CTRL, 0x04),
+	AXP20X_DESC(LDO3, "ldo3", "ldo3in", 700, 3500, 25, AXP20X_LDO3_V_OUT,
+		    0x7f, AXP20X_PWR_OUT_CTRL, 0x40),
+	AXP20X_DESC_TABLE(LDO4, "ldo4", "ldo24in", axp20x_ldo4_data,
+			  AXP20X_LDO24_V_OUT, 0x0f, AXP20X_PWR_OUT_CTRL, 0x08),
+	AXP20X_DESC_IO(LDO5, "ldo5", "ldo5in", 1800, 3300, 100,
+		       AXP20X_LDO5_V_OUT, 0xf0, AXP20X_GPIO0_CTRL, 0x07,
+		       AXP20X_IO_ENABLED, AXP20X_IO_DISABLED),
 };
 
 static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq)
@@ -193,13 +186,6 @@
 	if (!regulators) {
 		dev_warn(&pdev->dev, "regulators node not found\n");
 	} else {
-		ret = of_regulator_match(&pdev->dev, regulators, axp20x_matches,
-					 ARRAY_SIZE(axp20x_matches));
-		if (ret < 0) {
-			dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", ret);
-			return ret;
-		}
-
 		dcdcfreq = 1500;
 		of_property_read_u32(regulators, "x-powers,dcdc-freq", &dcdcfreq);
 		ret = axp20x_set_dcdc_freq(pdev, dcdcfreq);
@@ -233,23 +219,17 @@
 {
 	struct regulator_dev *rdev;
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
-	struct regulator_config config = { };
-	struct regulator_init_data *init_data;
+	struct regulator_config config = {
+		.dev = pdev->dev.parent,
+		.regmap = axp20x->regmap,
+	};
 	int ret, i;
 	u32 workmode;
 
-	ret = axp20x_regulator_parse_dt(pdev);
-	if (ret)
-		return ret;
+	/* This only sets the dcdc freq. Ignore any errors */
+	axp20x_regulator_parse_dt(pdev);
 
 	for (i = 0; i < AXP20X_REG_ID_MAX; i++) {
-		init_data = axp20x_matches[i].init_data;
-
-		config.dev = pdev->dev.parent;
-		config.init_data = init_data;
-		config.regmap = axp20x->regmap;
-		config.of_node = axp20x_matches[i].of_node;
-
 		rdev = devm_regulator_register(&pdev->dev, &axp20x_regulators[i],
 					       &config);
 		if (IS_ERR(rdev)) {
@@ -259,7 +239,8 @@
 			return PTR_ERR(rdev);
 		}
 
-		ret = of_property_read_u32(axp20x_matches[i].of_node, "x-powers,dcdc-workmode",
+		ret = of_property_read_u32(rdev->dev.of_node,
+					   "x-powers,dcdc-workmode",
 					   &workmode);
 		if (!ret) {
 			if (axp20x_set_dcdc_workmode(rdev, i, workmode))
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 9c48fb3..b899947 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -632,49 +632,34 @@
 static DEVICE_ATTR(bypass, 0444,
 		   regulator_bypass_show, NULL);
 
-/*
- * These are the only attributes are present for all regulators.
- * Other attributes are a function of regulator functionality.
- */
-static struct attribute *regulator_dev_attrs[] = {
-	&dev_attr_name.attr,
-	&dev_attr_num_users.attr,
-	&dev_attr_type.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(regulator_dev);
-
-static void regulator_dev_release(struct device *dev)
-{
-	struct regulator_dev *rdev = dev_get_drvdata(dev);
-	kfree(rdev);
-}
-
-static struct class regulator_class = {
-	.name = "regulator",
-	.dev_release = regulator_dev_release,
-	.dev_groups = regulator_dev_groups,
-};
-
 /* Calculate the new optimum regulator operating mode based on the new total
  * consumer load. All locks held by caller */
-static void drms_uA_update(struct regulator_dev *rdev)
+static int drms_uA_update(struct regulator_dev *rdev)
 {
 	struct regulator *sibling;
 	int current_uA = 0, output_uV, input_uV, err;
 	unsigned int mode;
 
+	/*
+	 * first check to see if we can set modes at all, otherwise just
+	 * tell the consumer everything is OK.
+	 */
 	err = regulator_check_drms(rdev);
-	if (err < 0 || !rdev->desc->ops->get_optimum_mode ||
-	    (!rdev->desc->ops->get_voltage &&
-	     !rdev->desc->ops->get_voltage_sel) ||
-	    !rdev->desc->ops->set_mode)
-		return;
+	if (err < 0)
+		return 0;
+
+	if (!rdev->desc->ops->get_optimum_mode)
+		return 0;
+
+	if (!rdev->desc->ops->set_mode)
+		return -EINVAL;
 
 	/* get output voltage */
 	output_uV = _regulator_get_voltage(rdev);
-	if (output_uV <= 0)
-		return;
+	if (output_uV <= 0) {
+		rdev_err(rdev, "invalid output voltage found\n");
+		return -EINVAL;
+	}
 
 	/* get input voltage */
 	input_uV = 0;
@@ -682,8 +667,10 @@
 		input_uV = regulator_get_voltage(rdev->supply);
 	if (input_uV <= 0)
 		input_uV = rdev->constraints->input_uV;
-	if (input_uV <= 0)
-		return;
+	if (input_uV <= 0) {
+		rdev_err(rdev, "invalid input voltage found\n");
+		return -EINVAL;
+	}
 
 	/* calc total requested load */
 	list_for_each_entry(sibling, &rdev->consumer_list, list)
@@ -695,8 +682,17 @@
 
 	/* check the new mode is allowed */
 	err = regulator_mode_constrain(rdev, &mode);
-	if (err == 0)
-		rdev->desc->ops->set_mode(rdev, mode);
+	if (err < 0) {
+		rdev_err(rdev, "failed to get optimum mode @ %d uA %d -> %d uV\n",
+			 current_uA, input_uV, output_uV);
+		return err;
+	}
+
+	err = rdev->desc->ops->set_mode(rdev, mode);
+	if (err < 0)
+		rdev_err(rdev, "failed to set optimum mode %x\n", mode);
+
+	return err;
 }
 
 static int suspend_set_state(struct regulator_dev *rdev,
@@ -3026,75 +3022,13 @@
 int regulator_set_optimum_mode(struct regulator *regulator, int uA_load)
 {
 	struct regulator_dev *rdev = regulator->rdev;
-	struct regulator *consumer;
-	int ret, output_uV, input_uV = 0, total_uA_load = 0;
-	unsigned int mode;
-
-	if (rdev->supply)
-		input_uV = regulator_get_voltage(rdev->supply);
+	int ret;
 
 	mutex_lock(&rdev->mutex);
-
-	/*
-	 * first check to see if we can set modes at all, otherwise just
-	 * tell the consumer everything is OK.
-	 */
 	regulator->uA_load = uA_load;
-	ret = regulator_check_drms(rdev);
-	if (ret < 0) {
-		ret = 0;
-		goto out;
-	}
-
-	if (!rdev->desc->ops->get_optimum_mode)
-		goto out;
-
-	/*
-	 * we can actually do this so any errors are indicators of
-	 * potential real failure.
-	 */
-	ret = -EINVAL;
-
-	if (!rdev->desc->ops->set_mode)
-		goto out;
-
-	/* get output voltage */
-	output_uV = _regulator_get_voltage(rdev);
-	if (output_uV <= 0) {
-		rdev_err(rdev, "invalid output voltage found\n");
-		goto out;
-	}
-
-	/* No supply? Use constraint voltage */
-	if (input_uV <= 0)
-		input_uV = rdev->constraints->input_uV;
-	if (input_uV <= 0) {
-		rdev_err(rdev, "invalid input voltage found\n");
-		goto out;
-	}
-
-	/* calc total requested load for this regulator */
-	list_for_each_entry(consumer, &rdev->consumer_list, list)
-		total_uA_load += consumer->uA_load;
-
-	mode = rdev->desc->ops->get_optimum_mode(rdev,
-						 input_uV, output_uV,
-						 total_uA_load);
-	ret = regulator_mode_constrain(rdev, &mode);
-	if (ret < 0) {
-		rdev_err(rdev, "failed to get optimum mode @ %d uA %d -> %d uV\n",
-			 total_uA_load, input_uV, output_uV);
-		goto out;
-	}
-
-	ret = rdev->desc->ops->set_mode(rdev, mode);
-	if (ret < 0) {
-		rdev_err(rdev, "failed to set optimum mode %x\n", mode);
-		goto out;
-	}
-	ret = mode;
-out:
+	ret = drms_uA_update(rdev);
 	mutex_unlock(&rdev->mutex);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(regulator_set_optimum_mode);
@@ -3436,126 +3370,136 @@
 }
 EXPORT_SYMBOL_GPL(regulator_mode_to_status);
 
+static struct attribute *regulator_dev_attrs[] = {
+	&dev_attr_name.attr,
+	&dev_attr_num_users.attr,
+	&dev_attr_type.attr,
+	&dev_attr_microvolts.attr,
+	&dev_attr_microamps.attr,
+	&dev_attr_opmode.attr,
+	&dev_attr_state.attr,
+	&dev_attr_status.attr,
+	&dev_attr_bypass.attr,
+	&dev_attr_requested_microamps.attr,
+	&dev_attr_min_microvolts.attr,
+	&dev_attr_max_microvolts.attr,
+	&dev_attr_min_microamps.attr,
+	&dev_attr_max_microamps.attr,
+	&dev_attr_suspend_standby_state.attr,
+	&dev_attr_suspend_mem_state.attr,
+	&dev_attr_suspend_disk_state.attr,
+	&dev_attr_suspend_standby_microvolts.attr,
+	&dev_attr_suspend_mem_microvolts.attr,
+	&dev_attr_suspend_disk_microvolts.attr,
+	&dev_attr_suspend_standby_mode.attr,
+	&dev_attr_suspend_mem_mode.attr,
+	&dev_attr_suspend_disk_mode.attr,
+	NULL
+};
+
 /*
  * To avoid cluttering sysfs (and memory) with useless state, only
  * create attributes that can be meaningfully displayed.
  */
-static int add_regulator_attributes(struct regulator_dev *rdev)
+static umode_t regulator_attr_is_visible(struct kobject *kobj,
+					 struct attribute *attr, int idx)
 {
-	struct device *dev = &rdev->dev;
+	struct device *dev = kobj_to_dev(kobj);
+	struct regulator_dev *rdev = container_of(dev, struct regulator_dev, dev);
 	const struct regulator_ops *ops = rdev->desc->ops;
-	int status = 0;
+	umode_t mode = attr->mode;
+
+	/* these three are always present */
+	if (attr == &dev_attr_name.attr ||
+	    attr == &dev_attr_num_users.attr ||
+	    attr == &dev_attr_type.attr)
+		return mode;
 
 	/* some attributes need specific methods to be displayed */
-	if ((ops->get_voltage && ops->get_voltage(rdev) >= 0) ||
-	    (ops->get_voltage_sel && ops->get_voltage_sel(rdev) >= 0) ||
-	    (ops->list_voltage && ops->list_voltage(rdev, 0) >= 0) ||
-		(rdev->desc->fixed_uV && (rdev->desc->n_voltages == 1))) {
-		status = device_create_file(dev, &dev_attr_microvolts);
-		if (status < 0)
-			return status;
-	}
-	if (ops->get_current_limit) {
-		status = device_create_file(dev, &dev_attr_microamps);
-		if (status < 0)
-			return status;
-	}
-	if (ops->get_mode) {
-		status = device_create_file(dev, &dev_attr_opmode);
-		if (status < 0)
-			return status;
-	}
-	if (rdev->ena_pin || ops->is_enabled) {
-		status = device_create_file(dev, &dev_attr_state);
-		if (status < 0)
-			return status;
-	}
-	if (ops->get_status) {
-		status = device_create_file(dev, &dev_attr_status);
-		if (status < 0)
-			return status;
-	}
-	if (ops->get_bypass) {
-		status = device_create_file(dev, &dev_attr_bypass);
-		if (status < 0)
-			return status;
+	if (attr == &dev_attr_microvolts.attr) {
+		if ((ops->get_voltage && ops->get_voltage(rdev) >= 0) ||
+		    (ops->get_voltage_sel && ops->get_voltage_sel(rdev) >= 0) ||
+		    (ops->list_voltage && ops->list_voltage(rdev, 0) >= 0) ||
+		    (rdev->desc->fixed_uV && rdev->desc->n_voltages == 1))
+			return mode;
+		return 0;
 	}
 
+	if (attr == &dev_attr_microamps.attr)
+		return ops->get_current_limit ? mode : 0;
+
+	if (attr == &dev_attr_opmode.attr)
+		return ops->get_mode ? mode : 0;
+
+	if (attr == &dev_attr_state.attr)
+		return (rdev->ena_pin || ops->is_enabled) ? mode : 0;
+
+	if (attr == &dev_attr_status.attr)
+		return ops->get_status ? mode : 0;
+
+	if (attr == &dev_attr_bypass.attr)
+		return ops->get_bypass ? mode : 0;
+
 	/* some attributes are type-specific */
-	if (rdev->desc->type == REGULATOR_CURRENT) {
-		status = device_create_file(dev, &dev_attr_requested_microamps);
-		if (status < 0)
-			return status;
-	}
+	if (attr == &dev_attr_requested_microamps.attr)
+		return rdev->desc->type == REGULATOR_CURRENT ? mode : 0;
 
 	/* all the other attributes exist to support constraints;
 	 * don't show them if there are no constraints, or if the
 	 * relevant supporting methods are missing.
 	 */
 	if (!rdev->constraints)
-		return status;
+		return 0;
 
 	/* constraints need specific supporting methods */
-	if (ops->set_voltage || ops->set_voltage_sel) {
-		status = device_create_file(dev, &dev_attr_min_microvolts);
-		if (status < 0)
-			return status;
-		status = device_create_file(dev, &dev_attr_max_microvolts);
-		if (status < 0)
-			return status;
-	}
-	if (ops->set_current_limit) {
-		status = device_create_file(dev, &dev_attr_min_microamps);
-		if (status < 0)
-			return status;
-		status = device_create_file(dev, &dev_attr_max_microamps);
-		if (status < 0)
-			return status;
-	}
+	if (attr == &dev_attr_min_microvolts.attr ||
+	    attr == &dev_attr_max_microvolts.attr)
+		return (ops->set_voltage || ops->set_voltage_sel) ? mode : 0;
 
-	status = device_create_file(dev, &dev_attr_suspend_standby_state);
-	if (status < 0)
-		return status;
-	status = device_create_file(dev, &dev_attr_suspend_mem_state);
-	if (status < 0)
-		return status;
-	status = device_create_file(dev, &dev_attr_suspend_disk_state);
-	if (status < 0)
-		return status;
+	if (attr == &dev_attr_min_microamps.attr ||
+	    attr == &dev_attr_max_microamps.attr)
+		return ops->set_current_limit ? mode : 0;
 
-	if (ops->set_suspend_voltage) {
-		status = device_create_file(dev,
-				&dev_attr_suspend_standby_microvolts);
-		if (status < 0)
-			return status;
-		status = device_create_file(dev,
-				&dev_attr_suspend_mem_microvolts);
-		if (status < 0)
-			return status;
-		status = device_create_file(dev,
-				&dev_attr_suspend_disk_microvolts);
-		if (status < 0)
-			return status;
-	}
+	if (attr == &dev_attr_suspend_standby_state.attr ||
+	    attr == &dev_attr_suspend_mem_state.attr ||
+	    attr == &dev_attr_suspend_disk_state.attr)
+		return mode;
 
-	if (ops->set_suspend_mode) {
-		status = device_create_file(dev,
-				&dev_attr_suspend_standby_mode);
-		if (status < 0)
-			return status;
-		status = device_create_file(dev,
-				&dev_attr_suspend_mem_mode);
-		if (status < 0)
-			return status;
-		status = device_create_file(dev,
-				&dev_attr_suspend_disk_mode);
-		if (status < 0)
-			return status;
-	}
+	if (attr == &dev_attr_suspend_standby_microvolts.attr ||
+	    attr == &dev_attr_suspend_mem_microvolts.attr ||
+	    attr == &dev_attr_suspend_disk_microvolts.attr)
+		return ops->set_suspend_voltage ? mode : 0;
 
-	return status;
+	if (attr == &dev_attr_suspend_standby_mode.attr ||
+	    attr == &dev_attr_suspend_mem_mode.attr ||
+	    attr == &dev_attr_suspend_disk_mode.attr)
+		return ops->set_suspend_mode ? mode : 0;
+
+	return mode;
 }
 
+static const struct attribute_group regulator_dev_group = {
+	.attrs = regulator_dev_attrs,
+	.is_visible = regulator_attr_is_visible,
+};
+
+static const struct attribute_group *regulator_dev_groups[] = {
+	&regulator_dev_group,
+	NULL
+};
+
+static void regulator_dev_release(struct device *dev)
+{
+	struct regulator_dev *rdev = dev_get_drvdata(dev);
+	kfree(rdev);
+}
+
+static struct class regulator_class = {
+	.name = "regulator",
+	.dev_release = regulator_dev_release,
+	.dev_groups = regulator_dev_groups,
+};
+
 static void rdev_init_debugfs(struct regulator_dev *rdev)
 {
 	rdev->debugfs = debugfs_create_dir(rdev_get_name(rdev), debugfs_root);
@@ -3575,7 +3519,7 @@
 /**
  * regulator_register - register regulator
  * @regulator_desc: regulator to register
- * @config: runtime configuration for regulator
+ * @cfg: runtime configuration for regulator
  *
  * Called by regulator drivers to register a regulator.
  * Returns a valid pointer to struct regulator_dev on success
@@ -3583,20 +3527,21 @@
  */
 struct regulator_dev *
 regulator_register(const struct regulator_desc *regulator_desc,
-		   const struct regulator_config *config)
+		   const struct regulator_config *cfg)
 {
 	const struct regulation_constraints *constraints = NULL;
 	const struct regulator_init_data *init_data;
-	static atomic_t regulator_no = ATOMIC_INIT(0);
+	struct regulator_config *config = NULL;
+	static atomic_t regulator_no = ATOMIC_INIT(-1);
 	struct regulator_dev *rdev;
 	struct device *dev;
 	int ret, i;
 	const char *supply = NULL;
 
-	if (regulator_desc == NULL || config == NULL)
+	if (regulator_desc == NULL || cfg == NULL)
 		return ERR_PTR(-EINVAL);
 
-	dev = config->dev;
+	dev = cfg->dev;
 	WARN_ON(!dev);
 
 	if (regulator_desc->name == NULL || regulator_desc->ops == NULL)
@@ -3626,7 +3571,17 @@
 	if (rdev == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	init_data = regulator_of_get_init_data(dev, regulator_desc,
+	/*
+	 * Duplicate the config so the driver could override it after
+	 * parsing init data.
+	 */
+	config = kmemdup(cfg, sizeof(*cfg), GFP_KERNEL);
+	if (config == NULL) {
+		kfree(rdev);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	init_data = regulator_of_get_init_data(dev, regulator_desc, config,
 					       &rdev->dev.of_node);
 	if (!init_data) {
 		init_data = config->init_data;
@@ -3660,8 +3615,8 @@
 	/* register with sysfs */
 	rdev->dev.class = &regulator_class;
 	rdev->dev.parent = dev;
-	dev_set_name(&rdev->dev, "regulator.%d",
-		     atomic_inc_return(&regulator_no) - 1);
+	dev_set_name(&rdev->dev, "regulator.%lu",
+		    (unsigned long) atomic_inc_return(&regulator_no));
 	ret = device_register(&rdev->dev);
 	if (ret != 0) {
 		put_device(&rdev->dev);
@@ -3694,11 +3649,6 @@
 	if (ret < 0)
 		goto scrub;
 
-	/* add attributes supported by this regulator */
-	ret = add_regulator_attributes(rdev);
-	if (ret < 0)
-		goto scrub;
-
 	if (init_data && init_data->supply_regulator)
 		supply = init_data->supply_regulator;
 	else if (regulator_desc->supply_name)
@@ -3754,6 +3704,7 @@
 	rdev_init_debugfs(rdev);
 out:
 	mutex_unlock(&regulator_list_mutex);
+	kfree(config);
 	return rdev;
 
 unset_supplies:
diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c
index c78d210..0134341 100644
--- a/drivers/regulator/da9211-regulator.c
+++ b/drivers/regulator/da9211-regulator.c
@@ -24,6 +24,7 @@
 #include <linux/regmap.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
+#include <linux/of_gpio.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/regulator/da9211.h>
 #include "da9211-regulator.h"
@@ -276,7 +277,10 @@
 			continue;
 
 		pdata->init_data[n] = da9211_matches[i].init_data;
-
+		pdata->reg_node[n] = da9211_matches[i].of_node;
+		pdata->gpio_ren[n] =
+			of_get_named_gpio(da9211_matches[i].of_node,
+				"enable-gpios", 0);
 		n++;
 	}
 
@@ -364,7 +368,15 @@
 		config.dev = chip->dev;
 		config.driver_data = chip;
 		config.regmap = chip->regmap;
-		config.of_node = chip->dev->of_node;
+		config.of_node = chip->pdata->reg_node[i];
+
+		if (gpio_is_valid(chip->pdata->gpio_ren[i])) {
+			config.ena_gpio = chip->pdata->gpio_ren[i];
+			config.ena_gpio_initialized = true;
+		} else {
+			config.ena_gpio = -EINVAL;
+			config.ena_gpio_initialized = false;
+		}
 
 		chip->rdev[i] = devm_regulator_register(chip->dev,
 			&da9211_regulators[i], &config);
diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c
index 6c43ab2..3c25db8 100644
--- a/drivers/regulator/fan53555.c
+++ b/drivers/regulator/fan53555.c
@@ -147,7 +147,7 @@
 		return REGULATOR_MODE_NORMAL;
 }
 
-static int slew_rates[] = {
+static const int slew_rates[] = {
 	64000,
 	32000,
 	16000,
@@ -296,7 +296,7 @@
 	return PTR_ERR_OR_ZERO(di->rdev);
 }
 
-static struct regmap_config fan53555_regmap_config = {
+static const struct regmap_config fan53555_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 };
diff --git a/drivers/regulator/internal.h b/drivers/regulator/internal.h
index 80ba2a3..c74ac87 100644
--- a/drivers/regulator/internal.h
+++ b/drivers/regulator/internal.h
@@ -38,11 +38,13 @@
 #ifdef CONFIG_OF
 struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
 			         const struct regulator_desc *desc,
+				 struct regulator_config *config,
 				 struct device_node **node);
 #else
 static inline struct regulator_init_data *
 regulator_of_get_init_data(struct device *dev,
 			   const struct regulator_desc *desc,
+			   struct regulator_config *config,
 			   struct device_node **node)
 {
 	return NULL;
diff --git a/drivers/regulator/isl9305.c b/drivers/regulator/isl9305.c
index 92fefd9..6e3a15f 100644
--- a/drivers/regulator/isl9305.c
+++ b/drivers/regulator/isl9305.c
@@ -177,8 +177,10 @@
 
 #ifdef CONFIG_OF
 static const struct of_device_id isl9305_dt_ids[] = {
-	{ .compatible = "isl,isl9305" },
-	{ .compatible = "isl,isl9305h" },
+	{ .compatible = "isl,isl9305" }, /* for backward compat., don't use */
+	{ .compatible = "isil,isl9305" },
+	{ .compatible = "isl,isl9305h" }, /* for backward compat., don't use */
+	{ .compatible = "isil,isl9305h" },
 	{},
 };
 #endif
diff --git a/drivers/regulator/lp872x.c b/drivers/regulator/lp872x.c
index 021d64d..3de328a 100644
--- a/drivers/regulator/lp872x.c
+++ b/drivers/regulator/lp872x.c
@@ -106,7 +106,6 @@
 	struct device *dev;
 	enum lp872x_id chipid;
 	struct lp872x_platform_data *pdata;
-	struct regulator_dev **regulators;
 	int num_regulators;
 	enum lp872x_dvs_state dvs_pin;
 	int dvs_gpio;
@@ -801,8 +800,6 @@
 			dev_err(lp->dev, "regulator register err");
 			return PTR_ERR(rdev);
 		}
-
-		*(lp->regulators + i) = rdev;
 	}
 
 	return 0;
@@ -906,7 +903,7 @@
 static int lp872x_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 {
 	struct lp872x *lp;
-	int ret, size, num_regulators;
+	int ret;
 	const int lp872x_num_regulators[] = {
 		[LP8720] = LP8720_NUM_REGULATORS,
 		[LP8725] = LP8725_NUM_REGULATORS,
@@ -918,38 +915,27 @@
 
 	lp = devm_kzalloc(&cl->dev, sizeof(struct lp872x), GFP_KERNEL);
 	if (!lp)
-		goto err_mem;
+		return -ENOMEM;
 
-	num_regulators = lp872x_num_regulators[id->driver_data];
-	size = sizeof(struct regulator_dev *) * num_regulators;
-
-	lp->regulators = devm_kzalloc(&cl->dev, size, GFP_KERNEL);
-	if (!lp->regulators)
-		goto err_mem;
+	lp->num_regulators = lp872x_num_regulators[id->driver_data];
 
 	lp->regmap = devm_regmap_init_i2c(cl, &lp872x_regmap_config);
 	if (IS_ERR(lp->regmap)) {
 		ret = PTR_ERR(lp->regmap);
 		dev_err(&cl->dev, "regmap init i2c err: %d\n", ret);
-		goto err_dev;
+		return ret;
 	}
 
 	lp->dev = &cl->dev;
 	lp->pdata = dev_get_platdata(&cl->dev);
 	lp->chipid = id->driver_data;
-	lp->num_regulators = num_regulators;
 	i2c_set_clientdata(cl, lp);
 
 	ret = lp872x_config(lp);
 	if (ret)
-		goto err_dev;
+		return ret;
 
 	return lp872x_regulator_register(lp);
-
-err_mem:
-	return -ENOMEM;
-err_dev:
-	return ret;
 }
 
 static const struct of_device_id lp872x_dt_ids[] = {
diff --git a/drivers/regulator/max14577.c b/drivers/regulator/max14577.c
index bf9a44c..b3678d2 100644
--- a/drivers/regulator/max14577.c
+++ b/drivers/regulator/max14577.c
@@ -103,6 +103,8 @@
 static const struct regulator_desc max14577_supported_regulators[] = {
 	[MAX14577_SAFEOUT] = {
 		.name		= "SAFEOUT",
+		.of_match	= of_match_ptr("SAFEOUT"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id		= MAX14577_SAFEOUT,
 		.ops		= &max14577_safeout_ops,
 		.type		= REGULATOR_VOLTAGE,
@@ -114,6 +116,8 @@
 	},
 	[MAX14577_CHARGER] = {
 		.name		= "CHARGER",
+		.of_match	= of_match_ptr("CHARGER"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id		= MAX14577_CHARGER,
 		.ops		= &max14577_charger_ops,
 		.type		= REGULATOR_CURRENT,
@@ -137,6 +141,8 @@
 static const struct regulator_desc max77836_supported_regulators[] = {
 	[MAX14577_SAFEOUT] = {
 		.name		= "SAFEOUT",
+		.of_match	= of_match_ptr("SAFEOUT"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id		= MAX14577_SAFEOUT,
 		.ops		= &max14577_safeout_ops,
 		.type		= REGULATOR_VOLTAGE,
@@ -148,6 +154,8 @@
 	},
 	[MAX14577_CHARGER] = {
 		.name		= "CHARGER",
+		.of_match	= of_match_ptr("CHARGER"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id		= MAX14577_CHARGER,
 		.ops		= &max14577_charger_ops,
 		.type		= REGULATOR_CURRENT,
@@ -157,6 +165,8 @@
 	},
 	[MAX77836_LDO1] = {
 		.name		= "LDO1",
+		.of_match	= of_match_ptr("LDO1"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id		= MAX77836_LDO1,
 		.ops		= &max77836_ldo_ops,
 		.type		= REGULATOR_VOLTAGE,
@@ -171,6 +181,8 @@
 	},
 	[MAX77836_LDO2] = {
 		.name		= "LDO2",
+		.of_match	= of_match_ptr("LDO2"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id		= MAX77836_LDO2,
 		.ops		= &max77836_ldo_ops,
 		.type		= REGULATOR_VOLTAGE,
@@ -198,43 +210,6 @@
 	{ .name = "LDO2", },
 };
 
-static int max14577_regulator_dt_parse_pdata(struct platform_device *pdev,
-		enum maxim_device_type dev_type)
-{
-	int ret;
-	struct device_node *np;
-	struct of_regulator_match *regulator_matches;
-	unsigned int regulator_matches_size;
-
-	np = of_get_child_by_name(pdev->dev.parent->of_node, "regulators");
-	if (!np) {
-		dev_err(&pdev->dev, "Failed to get child OF node for regulators\n");
-		return -EINVAL;
-	}
-
-	switch (dev_type) {
-	case MAXIM_DEVICE_TYPE_MAX77836:
-		regulator_matches = max77836_regulator_matches;
-		regulator_matches_size = ARRAY_SIZE(max77836_regulator_matches);
-		break;
-	case MAXIM_DEVICE_TYPE_MAX14577:
-	default:
-		regulator_matches = max14577_regulator_matches;
-		regulator_matches_size = ARRAY_SIZE(max14577_regulator_matches);
-	}
-
-	ret = of_regulator_match(&pdev->dev, np, regulator_matches,
-			regulator_matches_size);
-	if (ret < 0)
-		dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", ret);
-	else
-		ret = 0;
-
-	of_node_put(np);
-
-	return ret;
-}
-
 static inline struct regulator_init_data *match_init_data(int index,
 		enum maxim_device_type dev_type)
 {
@@ -261,11 +236,6 @@
 	}
 }
 #else /* CONFIG_OF */
-static int max14577_regulator_dt_parse_pdata(struct platform_device *pdev,
-		enum maxim_device_type dev_type)
-{
-	return 0;
-}
 static inline struct regulator_init_data *match_init_data(int index,
 		enum maxim_device_type dev_type)
 {
@@ -308,16 +278,12 @@
 {
 	struct max14577 *max14577 = dev_get_drvdata(pdev->dev.parent);
 	struct max14577_platform_data *pdata = dev_get_platdata(max14577->dev);
-	int i, ret;
+	int i, ret = 0;
 	struct regulator_config config = {};
 	const struct regulator_desc *supported_regulators;
 	unsigned int supported_regulators_size;
 	enum maxim_device_type dev_type = max14577->dev_type;
 
-	ret = max14577_regulator_dt_parse_pdata(pdev, dev_type);
-	if (ret)
-		return ret;
-
 	switch (dev_type) {
 	case MAXIM_DEVICE_TYPE_MAX77836:
 		supported_regulators = max77836_supported_regulators;
@@ -329,7 +295,7 @@
 		supported_regulators_size = ARRAY_SIZE(max14577_supported_regulators);
 	}
 
-	config.dev = &pdev->dev;
+	config.dev = max14577->dev;
 	config.driver_data = max14577;
 
 	for (i = 0; i < supported_regulators_size; i++) {
diff --git a/drivers/regulator/max77686.c b/drivers/regulator/max77686.c
index 10d2062..15fb141 100644
--- a/drivers/regulator/max77686.c
+++ b/drivers/regulator/max77686.c
@@ -26,6 +26,7 @@
 #include <linux/bug.h>
 #include <linux/err.h>
 #include <linux/gpio.h>
+#include <linux/of_gpio.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
@@ -46,6 +47,11 @@
 #define MAX77686_DVS_UVSTEP	12500
 
 /*
+ * Value for configuring buck[89] and LDO{20,21,22} as GPIO control.
+ * It is the same as 'off' for other regulators.
+ */
+#define MAX77686_GPIO_CONTROL		0x0
+/*
  * Values used for configuring LDOs and bucks.
  * Forcing low power mode: LDO1, 3-5, 9, 13, 17-26
  */
@@ -82,6 +88,8 @@
 };
 
 struct max77686_data {
+	u64 gpio_enabled:MAX77686_REGULATORS;
+
 	/* Array indexed by regulator id */
 	unsigned int opmode[MAX77686_REGULATORS];
 };
@@ -100,6 +108,26 @@
 	}
 }
 
+/*
+ * When regulator is configured for GPIO control then it
+ * replaces "normal" mode. Any change from low power mode to normal
+ * should actually change to GPIO control.
+ * Map normal mode to proper value for such regulators.
+ */
+static unsigned int max77686_map_normal_mode(struct max77686_data *max77686,
+					     int id)
+{
+	switch (id) {
+	case MAX77686_BUCK8:
+	case MAX77686_BUCK9:
+	case MAX77686_LDO20 ... MAX77686_LDO22:
+		if (max77686->gpio_enabled & (1 << id))
+			return MAX77686_GPIO_CONTROL;
+	}
+
+	return MAX77686_NORMAL;
+}
+
 /* Some BUCKs and LDOs supports Normal[ON/OFF] mode during suspend */
 static int max77686_set_suspend_disable(struct regulator_dev *rdev)
 {
@@ -136,7 +164,7 @@
 		val = MAX77686_LDO_LOWPOWER_PWRREQ;
 		break;
 	case REGULATOR_MODE_NORMAL:			/* ON in Normal Mode */
-		val = MAX77686_NORMAL;
+		val = max77686_map_normal_mode(max77686, id);
 		break;
 	default:
 		pr_warn("%s: regulator_suspend_mode : 0x%x not supported\n",
@@ -160,7 +188,7 @@
 {
 	unsigned int val;
 	struct max77686_data *max77686 = rdev_get_drvdata(rdev);
-	int ret;
+	int ret, id = rdev_get_id(rdev);
 
 	switch (mode) {
 	case REGULATOR_MODE_STANDBY:			/* switch off */
@@ -170,7 +198,7 @@
 		val = MAX77686_LDO_LOWPOWER_PWRREQ;
 		break;
 	case REGULATOR_MODE_NORMAL:			/* ON in Normal Mode */
-		val = MAX77686_NORMAL;
+		val = max77686_map_normal_mode(max77686, id);
 		break;
 	default:
 		pr_warn("%s: regulator_suspend_mode : 0x%x not supported\n",
@@ -184,7 +212,7 @@
 	if (ret)
 		return ret;
 
-	max77686->opmode[rdev_get_id(rdev)] = val;
+	max77686->opmode[id] = val;
 	return 0;
 }
 
@@ -197,7 +225,7 @@
 	shift = max77686_get_opmode_shift(id);
 
 	if (max77686->opmode[id] == MAX77686_OFF_PWRREQ)
-		max77686->opmode[id] = MAX77686_NORMAL;
+		max77686->opmode[id] = max77686_map_normal_mode(max77686, id);
 
 	return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg,
 				  rdev->desc->enable_mask,
@@ -229,6 +257,36 @@
 				  MAX77686_RAMP_RATE_MASK, ramp_value << 6);
 }
 
+static int max77686_of_parse_cb(struct device_node *np,
+		const struct regulator_desc *desc,
+		struct regulator_config *config)
+{
+	struct max77686_data *max77686 = config->driver_data;
+
+	switch (desc->id) {
+	case MAX77686_BUCK8:
+	case MAX77686_BUCK9:
+	case MAX77686_LDO20 ... MAX77686_LDO22:
+		config->ena_gpio = of_get_named_gpio(np,
+					"maxim,ena-gpios", 0);
+		config->ena_gpio_flags = GPIOF_OUT_INIT_HIGH;
+		config->ena_gpio_initialized = true;
+		break;
+	default:
+		return 0;
+	}
+
+	if (gpio_is_valid(config->ena_gpio)) {
+		max77686->gpio_enabled |= (1 << desc->id);
+
+		return regmap_update_bits(config->regmap, desc->enable_reg,
+					  desc->enable_mask,
+					  MAX77686_GPIO_CONTROL);
+	}
+
+	return 0;
+}
+
 static struct regulator_ops max77686_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
@@ -283,6 +341,7 @@
 	.name		= "LDO"#num,					\
 	.of_match	= of_match_ptr("LDO"#num),			\
 	.regulators_node	= of_match_ptr("voltage-regulators"),	\
+	.of_parse_cb	= max77686_of_parse_cb,				\
 	.id		= MAX77686_LDO##num,				\
 	.ops		= &max77686_ops,				\
 	.type		= REGULATOR_VOLTAGE,				\
@@ -355,6 +414,7 @@
 	.name		= "BUCK"#num,					\
 	.of_match	= of_match_ptr("BUCK"#num),			\
 	.regulators_node	= of_match_ptr("voltage-regulators"),	\
+	.of_parse_cb	= max77686_of_parse_cb,				\
 	.id		= MAX77686_BUCK##num,				\
 	.ops		= &max77686_ops,				\
 	.type		= REGULATOR_VOLTAGE,				\
diff --git a/drivers/regulator/max77843.c b/drivers/regulator/max77843.c
new file mode 100644
index 0000000..c132ef5
--- /dev/null
+++ b/drivers/regulator/max77843.c
@@ -0,0 +1,227 @@
+/*
+ * max77843.c - Regulator driver for the Maxim MAX77843
+ *
+ * Copyright (C) 2015 Samsung Electronics
+ * Author: Jaewon Kim <jaewon02.kim@samsung.com>
+ * Author: Beomho Seo <beomho.seo@samsung.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/module.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/mfd/max77843-private.h>
+#include <linux/regulator/of_regulator.h>
+
+enum max77843_regulator_type {
+	MAX77843_SAFEOUT1 = 0,
+	MAX77843_SAFEOUT2,
+	MAX77843_CHARGER,
+
+	MAX77843_NUM,
+};
+
+static const unsigned int max77843_safeout_voltage_table[] = {
+	4850000,
+	4900000,
+	4950000,
+	3300000,
+};
+
+static int max77843_reg_is_enabled(struct regulator_dev *rdev)
+{
+	struct regmap *regmap = rdev->regmap;
+	int ret;
+	unsigned int reg;
+
+	ret = regmap_read(regmap, rdev->desc->enable_reg, &reg);
+	if (ret) {
+		dev_err(&rdev->dev, "Fialed to read charger register\n");
+		return ret;
+	}
+
+	return (reg & rdev->desc->enable_mask) == rdev->desc->enable_mask;
+}
+
+static int max77843_reg_get_current_limit(struct regulator_dev *rdev)
+{
+	struct regmap *regmap = rdev->regmap;
+	unsigned int chg_min_uA = rdev->constraints->min_uA;
+	unsigned int chg_max_uA = rdev->constraints->max_uA;
+	unsigned int val;
+	int ret;
+	unsigned int reg, sel;
+
+	ret = regmap_read(regmap, MAX77843_CHG_REG_CHG_CNFG_02, &reg);
+	if (ret) {
+		dev_err(&rdev->dev, "Failed to read charger register\n");
+		return ret;
+	}
+
+	sel = reg & MAX77843_CHG_FAST_CHG_CURRENT_MASK;
+
+	if (sel < 0x03)
+		sel = 0;
+	else
+		sel -= 2;
+
+	val = chg_min_uA + MAX77843_CHG_FAST_CHG_CURRENT_STEP * sel;
+	if (val > chg_max_uA)
+		return -EINVAL;
+
+	return val;
+}
+
+static int max77843_reg_set_current_limit(struct regulator_dev *rdev,
+		int min_uA, int max_uA)
+{
+	struct regmap *regmap = rdev->regmap;
+	unsigned int chg_min_uA = rdev->constraints->min_uA;
+	int sel = 0;
+
+	while (chg_min_uA + MAX77843_CHG_FAST_CHG_CURRENT_STEP * sel < min_uA)
+		sel++;
+
+	if (chg_min_uA + MAX77843_CHG_FAST_CHG_CURRENT_STEP * sel > max_uA)
+		return -EINVAL;
+
+	sel += 2;
+
+	return regmap_write(regmap, MAX77843_CHG_REG_CHG_CNFG_02, sel);
+}
+
+static struct regulator_ops max77843_charger_ops = {
+	.is_enabled		= max77843_reg_is_enabled,
+	.enable			= regulator_enable_regmap,
+	.disable		= regulator_disable_regmap,
+	.get_current_limit	= max77843_reg_get_current_limit,
+	.set_current_limit	= max77843_reg_set_current_limit,
+};
+
+static struct regulator_ops max77843_regulator_ops = {
+	.is_enabled             = regulator_is_enabled_regmap,
+	.enable                 = regulator_enable_regmap,
+	.disable                = regulator_disable_regmap,
+	.list_voltage		= regulator_list_voltage_table,
+	.get_voltage_sel        = regulator_get_voltage_sel_regmap,
+	.set_voltage_sel        = regulator_set_voltage_sel_regmap,
+};
+
+static const struct regulator_desc max77843_supported_regulators[] = {
+	[MAX77843_SAFEOUT1] = {
+		.name		= "SAFEOUT1",
+		.id		= MAX77843_SAFEOUT1,
+		.ops		= &max77843_regulator_ops,
+		.of_match	= of_match_ptr("SAFEOUT1"),
+		.regulators_node = of_match_ptr("regulators"),
+		.type		= REGULATOR_VOLTAGE,
+		.owner		= THIS_MODULE,
+		.n_voltages	= ARRAY_SIZE(max77843_safeout_voltage_table),
+		.volt_table	= max77843_safeout_voltage_table,
+		.enable_reg	= MAX77843_SYS_REG_SAFEOUTCTRL,
+		.enable_mask	= MAX77843_REG_SAFEOUTCTRL_ENSAFEOUT1,
+		.vsel_reg	= MAX77843_SYS_REG_SAFEOUTCTRL,
+		.vsel_mask	= MAX77843_REG_SAFEOUTCTRL_SAFEOUT1_MASK,
+	},
+	[MAX77843_SAFEOUT2] = {
+		.name           = "SAFEOUT2",
+		.id             = MAX77843_SAFEOUT2,
+		.ops            = &max77843_regulator_ops,
+		.of_match	= of_match_ptr("SAFEOUT2"),
+		.regulators_node = of_match_ptr("regulators"),
+		.type           = REGULATOR_VOLTAGE,
+		.owner          = THIS_MODULE,
+		.n_voltages	= ARRAY_SIZE(max77843_safeout_voltage_table),
+		.volt_table	= max77843_safeout_voltage_table,
+		.enable_reg     = MAX77843_SYS_REG_SAFEOUTCTRL,
+		.enable_mask    = MAX77843_REG_SAFEOUTCTRL_ENSAFEOUT2,
+		.vsel_reg	= MAX77843_SYS_REG_SAFEOUTCTRL,
+		.vsel_mask	= MAX77843_REG_SAFEOUTCTRL_SAFEOUT2_MASK,
+	},
+	[MAX77843_CHARGER] = {
+		.name		= "CHARGER",
+		.id		= MAX77843_CHARGER,
+		.ops		= &max77843_charger_ops,
+		.of_match	= of_match_ptr("CHARGER"),
+		.regulators_node = of_match_ptr("regulators"),
+		.type		= REGULATOR_CURRENT,
+		.owner		= THIS_MODULE,
+		.enable_reg	= MAX77843_CHG_REG_CHG_CNFG_00,
+		.enable_mask	= MAX77843_CHG_MASK,
+	},
+};
+
+static struct regmap *max77843_get_regmap(struct max77843 *max77843, int reg_id)
+{
+	switch (reg_id) {
+	case MAX77843_SAFEOUT1:
+	case MAX77843_SAFEOUT2:
+		return max77843->regmap;
+	case MAX77843_CHARGER:
+		return max77843->regmap_chg;
+	default:
+		return max77843->regmap;
+	}
+}
+
+static int max77843_regulator_probe(struct platform_device *pdev)
+{
+	struct max77843 *max77843 = dev_get_drvdata(pdev->dev.parent);
+	struct regulator_config config = {};
+	int i;
+
+	config.dev = max77843->dev;
+	config.driver_data = max77843;
+
+	for (i = 0; i < ARRAY_SIZE(max77843_supported_regulators); i++) {
+		struct regulator_dev *regulator;
+
+		config.regmap = max77843_get_regmap(max77843,
+				max77843_supported_regulators[i].id);
+
+		regulator = devm_regulator_register(&pdev->dev,
+				&max77843_supported_regulators[i], &config);
+		if (IS_ERR(regulator)) {
+			dev_err(&pdev->dev,
+					"Failed to regiser regulator-%d\n", i);
+			return PTR_ERR(regulator);
+		}
+	}
+
+	return 0;
+}
+
+static const struct platform_device_id max77843_regulator_id[] = {
+	{ "max77843-regulator", },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver max77843_regulator_driver = {
+	.driver	= {
+		.name = "max77843-regulator",
+	},
+	.probe		= max77843_regulator_probe,
+	.id_table	= max77843_regulator_id,
+};
+
+static int __init max77843_regulator_init(void)
+{
+	return platform_driver_register(&max77843_regulator_driver);
+}
+subsys_initcall(max77843_regulator_init);
+
+static void __exit max77843_regulator_exit(void)
+{
+	platform_driver_unregister(&max77843_regulator_driver);
+}
+module_exit(max77843_regulator_exit);
+
+MODULE_AUTHOR("Jaewon Kim <jaewon02.kim@samsung.com>");
+MODULE_AUTHOR("Beomho Seo <beomho.seo@samsung.com>");
+MODULE_DESCRIPTION("Maxim MAX77843 regulator driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/regulator/max8649.c b/drivers/regulator/max8649.c
index c8bddcc..8122957 100644
--- a/drivers/regulator/max8649.c
+++ b/drivers/regulator/max8649.c
@@ -115,7 +115,7 @@
 	return REGULATOR_MODE_NORMAL;
 }
 
-static struct regulator_ops max8649_dcdc_ops = {
+static const struct regulator_ops max8649_dcdc_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.list_voltage	= regulator_list_voltage_linear,
@@ -143,7 +143,7 @@
 	.enable_is_inverted = true,
 };
 
-static struct regmap_config max8649_regmap_config = {
+static const struct regmap_config max8649_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 };
diff --git a/drivers/regulator/mt6397-regulator.c b/drivers/regulator/mt6397-regulator.c
new file mode 100644
index 0000000..a5b2f47
--- /dev/null
+++ b/drivers/regulator/mt6397-regulator.c
@@ -0,0 +1,332 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Flora Fu <flora.fu@mediatek.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.
+ *
+ * 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/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/mfd/mt6397/core.h>
+#include <linux/mfd/mt6397/registers.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/mt6397-regulator.h>
+#include <linux/regulator/of_regulator.h>
+
+/*
+ * MT6397 regulators' information
+ *
+ * @desc: standard fields of regulator description.
+ * @qi: Mask for query enable signal status of regulators
+ * @vselon_reg: Register sections for hardware control mode of bucks
+ * @vselctrl_reg: Register for controlling the buck control mode.
+ * @vselctrl_mask: Mask for query buck's voltage control mode.
+ */
+struct mt6397_regulator_info {
+	struct regulator_desc desc;
+	u32 qi;
+	u32 vselon_reg;
+	u32 vselctrl_reg;
+	u32 vselctrl_mask;
+};
+
+#define MT6397_BUCK(match, vreg, min, max, step, volt_ranges, enreg,	\
+		vosel, vosel_mask, voselon, vosel_ctrl)			\
+[MT6397_ID_##vreg] = {							\
+	.desc = {							\
+		.name = #vreg,						\
+		.of_match = of_match_ptr(match),			\
+		.ops = &mt6397_volt_range_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = MT6397_ID_##vreg,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = (max - min)/step + 1,			\
+		.linear_ranges = volt_ranges,				\
+		.n_linear_ranges = ARRAY_SIZE(volt_ranges),		\
+		.vsel_reg = vosel,					\
+		.vsel_mask = vosel_mask,				\
+		.enable_reg = enreg,					\
+		.enable_mask = BIT(0),					\
+	},								\
+	.qi = BIT(13),							\
+	.vselon_reg = voselon,						\
+	.vselctrl_reg = vosel_ctrl,					\
+	.vselctrl_mask = BIT(1),					\
+}
+
+#define MT6397_LDO(match, vreg, ldo_volt_table, enreg, enbit, vosel,	\
+		vosel_mask)						\
+[MT6397_ID_##vreg] = {							\
+	.desc = {							\
+		.name = #vreg,						\
+		.of_match = of_match_ptr(match),			\
+		.ops = &mt6397_volt_table_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = MT6397_ID_##vreg,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = ARRAY_SIZE(ldo_volt_table),		\
+		.volt_table = ldo_volt_table,				\
+		.vsel_reg = vosel,					\
+		.vsel_mask = vosel_mask,				\
+		.enable_reg = enreg,					\
+		.enable_mask = BIT(enbit),				\
+	},								\
+	.qi = BIT(15),							\
+}
+
+#define MT6397_REG_FIXED(match, vreg, enreg, enbit, volt)		\
+[MT6397_ID_##vreg] = {							\
+	.desc = {							\
+		.name = #vreg,						\
+		.of_match = of_match_ptr(match),			\
+		.ops = &mt6397_volt_fixed_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = MT6397_ID_##vreg,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = 1,					\
+		.enable_reg = enreg,					\
+		.enable_mask = BIT(enbit),				\
+		.min_uV = volt,						\
+	},								\
+	.qi = BIT(15),							\
+}
+
+static const struct regulator_linear_range buck_volt_range1[] = {
+	REGULATOR_LINEAR_RANGE(700000, 0, 0x7f, 6250),
+};
+
+static const struct regulator_linear_range buck_volt_range2[] = {
+	REGULATOR_LINEAR_RANGE(800000, 0, 0x7f, 6250),
+};
+
+static const struct regulator_linear_range buck_volt_range3[] = {
+	REGULATOR_LINEAR_RANGE(1500000, 0, 0x1f, 20000),
+};
+
+static const u32 ldo_volt_table1[] = {
+	1500000, 1800000, 2500000, 2800000,
+};
+
+static const u32 ldo_volt_table2[] = {
+	1800000, 3300000,
+};
+
+static const u32 ldo_volt_table3[] = {
+	3000000, 3300000,
+};
+
+static const u32 ldo_volt_table4[] = {
+	1220000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000,
+};
+
+static const u32 ldo_volt_table5[] = {
+	1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000,
+};
+
+static const u32 ldo_volt_table5_v2[] = {
+	1200000, 1000000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000,
+};
+
+static const u32 ldo_volt_table6[] = {
+	1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 2000000,
+};
+
+static const u32 ldo_volt_table7[] = {
+	1300000, 1500000, 1800000, 2000000, 2500000, 2800000, 3000000, 3300000,
+};
+
+static int mt6397_get_status(struct regulator_dev *rdev)
+{
+	int ret;
+	u32 regval;
+	struct mt6397_regulator_info *info = rdev_get_drvdata(rdev);
+
+	ret = regmap_read(rdev->regmap, info->desc.enable_reg, &regval);
+	if (ret != 0) {
+		dev_err(&rdev->dev, "Failed to get enable reg: %d\n", ret);
+		return ret;
+	}
+
+	return (regval & info->qi) ? REGULATOR_STATUS_ON : REGULATOR_STATUS_OFF;
+}
+
+static struct regulator_ops mt6397_volt_range_ops = {
+	.list_voltage = regulator_list_voltage_linear_range,
+	.map_voltage = regulator_map_voltage_linear_range,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.get_status = mt6397_get_status,
+};
+
+static struct regulator_ops mt6397_volt_table_ops = {
+	.list_voltage = regulator_list_voltage_table,
+	.map_voltage = regulator_map_voltage_iterate,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.get_status = mt6397_get_status,
+};
+
+static struct regulator_ops mt6397_volt_fixed_ops = {
+	.list_voltage = regulator_list_voltage_linear,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.get_status = mt6397_get_status,
+};
+
+/* The array is indexed by id(MT6397_ID_XXX) */
+static struct mt6397_regulator_info mt6397_regulators[] = {
+	MT6397_BUCK("buck_vpca15", VPCA15, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VCA15_CON7, MT6397_VCA15_CON9, 0x7f,
+		MT6397_VCA15_CON10, MT6397_VCA15_CON5),
+	MT6397_BUCK("buck_vpca7", VPCA7, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VPCA7_CON7, MT6397_VPCA7_CON9, 0x7f,
+		MT6397_VPCA7_CON10, MT6397_VPCA7_CON5),
+	MT6397_BUCK("buck_vsramca15", VSRAMCA15, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VSRMCA15_CON7, MT6397_VSRMCA15_CON9,
+		0x7f, MT6397_VSRMCA15_CON10, MT6397_VSRMCA15_CON5),
+	MT6397_BUCK("buck_vsramca7", VSRAMCA7, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VSRMCA7_CON7, MT6397_VSRMCA7_CON9,
+		0x7f, MT6397_VSRMCA7_CON10, MT6397_VSRMCA7_CON5),
+	MT6397_BUCK("buck_vcore", VCORE, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VCORE_CON7, MT6397_VCORE_CON9, 0x7f,
+		MT6397_VCORE_CON10, MT6397_VCORE_CON5),
+	MT6397_BUCK("buck_vgpu", VGPU, 700000, 1493750, 6250, buck_volt_range1,
+		MT6397_VGPU_CON7, MT6397_VGPU_CON9, 0x7f,
+		MT6397_VGPU_CON10, MT6397_VGPU_CON5),
+	MT6397_BUCK("buck_vdrm", VDRM, 800000, 1593750, 6250, buck_volt_range2,
+		MT6397_VDRM_CON7, MT6397_VDRM_CON9, 0x7f,
+		MT6397_VDRM_CON10, MT6397_VDRM_CON5),
+	MT6397_BUCK("buck_vio18", VIO18, 1500000, 2120000, 20000,
+		buck_volt_range3, MT6397_VIO18_CON7, MT6397_VIO18_CON9, 0x1f,
+		MT6397_VIO18_CON10, MT6397_VIO18_CON5),
+	MT6397_REG_FIXED("ldo_vtcxo", VTCXO, MT6397_ANALDO_CON0, 10, 2800000),
+	MT6397_REG_FIXED("ldo_va28", VA28, MT6397_ANALDO_CON1, 14, 2800000),
+	MT6397_LDO("ldo_vcama", VCAMA, ldo_volt_table1,
+		MT6397_ANALDO_CON2, 15, MT6397_ANALDO_CON6, 0xC0),
+	MT6397_REG_FIXED("ldo_vio28", VIO28, MT6397_DIGLDO_CON0, 14, 2800000),
+	MT6397_REG_FIXED("ldo_vusb", VUSB, MT6397_DIGLDO_CON1, 14, 3300000),
+	MT6397_LDO("ldo_vmc", VMC, ldo_volt_table2,
+		MT6397_DIGLDO_CON2, 12, MT6397_DIGLDO_CON29, 0x10),
+	MT6397_LDO("ldo_vmch", VMCH, ldo_volt_table3,
+		MT6397_DIGLDO_CON3, 14, MT6397_DIGLDO_CON17, 0x80),
+	MT6397_LDO("ldo_vemc3v3", VEMC3V3, ldo_volt_table3,
+		MT6397_DIGLDO_CON4, 14, MT6397_DIGLDO_CON18, 0x10),
+	MT6397_LDO("ldo_vgp1", VGP1, ldo_volt_table4,
+		MT6397_DIGLDO_CON5, 15, MT6397_DIGLDO_CON19, 0xE0),
+	MT6397_LDO("ldo_vgp2", VGP2, ldo_volt_table5,
+		MT6397_DIGLDO_CON6, 15, MT6397_DIGLDO_CON20, 0xE0),
+	MT6397_LDO("ldo_vgp3", VGP3, ldo_volt_table5,
+		MT6397_DIGLDO_CON7, 15, MT6397_DIGLDO_CON21, 0xE0),
+	MT6397_LDO("ldo_vgp4", VGP4, ldo_volt_table5,
+		MT6397_DIGLDO_CON8, 15, MT6397_DIGLDO_CON22, 0xE0),
+	MT6397_LDO("ldo_vgp5", VGP5, ldo_volt_table6,
+		MT6397_DIGLDO_CON9, 15, MT6397_DIGLDO_CON23, 0xE0),
+	MT6397_LDO("ldo_vgp6", VGP6, ldo_volt_table5,
+		MT6397_DIGLDO_CON10, 15, MT6397_DIGLDO_CON33, 0xE0),
+	MT6397_LDO("ldo_vibr", VIBR, ldo_volt_table7,
+		MT6397_DIGLDO_CON24, 15, MT6397_DIGLDO_CON25, 0xE00),
+};
+
+static int mt6397_set_buck_vosel_reg(struct platform_device *pdev)
+{
+	struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent);
+	int i;
+	u32 regval;
+
+	for (i = 0; i < MT6397_MAX_REGULATOR; i++) {
+		if (mt6397_regulators[i].vselctrl_reg) {
+			if (regmap_read(mt6397->regmap,
+				mt6397_regulators[i].vselctrl_reg,
+				&regval) < 0) {
+				dev_err(&pdev->dev,
+					"Failed to read buck ctrl\n");
+				return -EIO;
+			}
+
+			if (regval & mt6397_regulators[i].vselctrl_mask) {
+				mt6397_regulators[i].desc.vsel_reg =
+				mt6397_regulators[i].vselon_reg;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int mt6397_regulator_probe(struct platform_device *pdev)
+{
+	struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent);
+	struct regulator_config config = {};
+	struct regulator_dev *rdev;
+	int i;
+	u32 reg_value, version;
+
+	/* Query buck controller to select activated voltage register part */
+	if (mt6397_set_buck_vosel_reg(pdev))
+		return -EIO;
+
+	/* Read PMIC chip revision to update constraints and voltage table */
+	if (regmap_read(mt6397->regmap, MT6397_CID, &reg_value) < 0) {
+		dev_err(&pdev->dev, "Failed to read Chip ID\n");
+		return -EIO;
+	}
+	dev_info(&pdev->dev, "Chip ID = 0x%x\n", reg_value);
+
+	version = (reg_value & 0xFF);
+	switch (version) {
+	case MT6397_REGULATOR_ID91:
+		mt6397_regulators[MT6397_ID_VGP2].desc.volt_table =
+		ldo_volt_table5_v2;
+		break;
+	default:
+		break;
+	}
+
+	for (i = 0; i < MT6397_MAX_REGULATOR; i++) {
+		config.dev = &pdev->dev;
+		config.driver_data = &mt6397_regulators[i];
+		config.regmap = mt6397->regmap;
+		rdev = devm_regulator_register(&pdev->dev,
+				&mt6397_regulators[i].desc, &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "failed to register %s\n",
+				mt6397_regulators[i].desc.name);
+			return PTR_ERR(rdev);
+		}
+	}
+
+	return 0;
+}
+
+static struct platform_driver mt6397_regulator_driver = {
+	.driver = {
+		.name = "mt6397-regulator",
+	},
+	.probe = mt6397_regulator_probe,
+};
+
+module_platform_driver(mt6397_regulator_driver);
+
+MODULE_AUTHOR("Flora Fu <flora.fu@mediatek.com>");
+MODULE_DESCRIPTION("Regulator Driver for MediaTek MT6397 PMIC");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mt6397-regulator");
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 91eaaf0..24e812c 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -270,6 +270,7 @@
 
 struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
 					    const struct regulator_desc *desc,
+					    struct regulator_config *config,
 					    struct device_node **node)
 {
 	struct device_node *search, *child;
@@ -307,6 +308,16 @@
 			break;
 		}
 
+		if (desc->of_parse_cb) {
+			if (desc->of_parse_cb(child, desc, config)) {
+				dev_err(dev,
+					"driver callback failed to parse DT for regulator %s\n",
+					child->name);
+				init_data = NULL;
+				break;
+			}
+		}
+
 		of_node_get(child);
 		*node = child;
 		break;
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index c879dff..8cc8d18 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -56,7 +56,7 @@
 #define PFUZE100_VGEN5VOL	0x70
 #define PFUZE100_VGEN6VOL	0x71
 
-enum chips { PFUZE100, PFUZE200 };
+enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3 };
 
 struct pfuze_regulator {
 	struct regulator_desc desc;
@@ -80,9 +80,18 @@
 	1000000, 1100000, 1200000, 1300000, 1500000, 1800000, 3000000,
 };
 
+static const int pfuze3000_sw2lo[] = {
+	1500000, 1550000, 1600000, 1650000, 1700000, 1750000, 1800000, 1850000,
+};
+
+static const int pfuze3000_sw2hi[] = {
+	2500000, 2800000, 2850000, 3000000, 3100000, 3150000, 3200000, 3300000,
+};
+
 static const struct i2c_device_id pfuze_device_id[] = {
 	{.name = "pfuze100", .driver_data = PFUZE100},
 	{.name = "pfuze200", .driver_data = PFUZE200},
+	{.name = "pfuze3000", .driver_data = PFUZE3000},
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, pfuze_device_id);
@@ -90,6 +99,7 @@
 static const struct of_device_id pfuze_dt_ids[] = {
 	{ .compatible = "fsl,pfuze100", .data = (void *)PFUZE100},
 	{ .compatible = "fsl,pfuze200", .data = (void *)PFUZE200},
+	{ .compatible = "fsl,pfuze3000", .data = (void *)PFUZE3000},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, pfuze_dt_ids);
@@ -219,6 +229,60 @@
 		.stby_mask = 0x20,	\
 	}
 
+#define PFUZE3000_VCC_REG(_chip, _name, base, min, max, step)	{	\
+	.desc = {	\
+		.name = #_name,	\
+		.n_voltages = ((max) - (min)) / (step) + 1,	\
+		.ops = &pfuze100_ldo_regulator_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = _chip ## _ ## _name,	\
+		.owner = THIS_MODULE,	\
+		.min_uV = (min),	\
+		.uV_step = (step),	\
+		.vsel_reg = (base),	\
+		.vsel_mask = 0x3,	\
+		.enable_reg = (base),	\
+		.enable_mask = 0x10,	\
+	},	\
+	.stby_reg = (base),	\
+	.stby_mask = 0x20,	\
+}
+
+
+#define PFUZE3000_SW2_REG(_chip, _name, base, min, max, step)	{	\
+	.desc = {	\
+		.name = #_name,\
+		.n_voltages = ((max) - (min)) / (step) + 1,	\
+		.ops = &pfuze100_sw_regulator_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = _chip ## _ ## _name,	\
+		.owner = THIS_MODULE,	\
+		.min_uV = (min),	\
+		.uV_step = (step),	\
+		.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
+		.vsel_mask = 0x7,	\
+	},	\
+	.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
+	.stby_mask = 0x7,	\
+}
+
+#define PFUZE3000_SW3_REG(_chip, _name, base, min, max, step)	{	\
+	.desc = {	\
+		.name = #_name,\
+		.n_voltages = ((max) - (min)) / (step) + 1,	\
+		.ops = &pfuze100_sw_regulator_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = _chip ## _ ## _name,	\
+		.owner = THIS_MODULE,	\
+		.min_uV = (min),	\
+		.uV_step = (step),	\
+		.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
+		.vsel_mask = 0xf,	\
+	},	\
+	.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
+	.stby_mask = 0xf,	\
+}
+
 /* PFUZE100 */
 static struct pfuze_regulator pfuze100_regulators[] = {
 	PFUZE100_SW_REG(PFUZE100, SW1AB, PFUZE100_SW1ABVOL, 300000, 1875000, 25000),
@@ -254,6 +318,22 @@
 	PFUZE100_VGEN_REG(PFUZE200, VGEN6, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
 };
 
+static struct pfuze_regulator pfuze3000_regulators[] = {
+	PFUZE100_SW_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 700000, 1475000, 25000),
+	PFUZE100_SW_REG(PFUZE3000, SW1B, PFUZE100_SW1CVOL, 700000, 1475000, 25000),
+	PFUZE100_SWB_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
+	PFUZE3000_SW3_REG(PFUZE3000, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000),
+	PFUZE100_SWB_REG(PFUZE3000, SWBST, PFUZE100_SWBSTCON1, 0x3, pfuze100_swbst),
+	PFUZE100_SWB_REG(PFUZE3000, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
+	PFUZE100_FIXED_REG(PFUZE3000, VREFDDR, PFUZE100_VREFDDRCON, 750000),
+	PFUZE100_VGEN_REG(PFUZE3000, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3000, VLDO2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000),
+	PFUZE3000_VCC_REG(PFUZE3000, VCCSD, PFUZE100_VGEN3VOL, 2850000, 3300000, 150000),
+	PFUZE3000_VCC_REG(PFUZE3000, V33, PFUZE100_VGEN4VOL, 2850000, 3300000, 150000),
+	PFUZE100_VGEN_REG(PFUZE3000, VLDO3, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3000, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
+};
+
 static struct pfuze_regulator *pfuze_regulators;
 
 #ifdef CONFIG_OF
@@ -294,6 +374,24 @@
 	{ .name = "vgen6",	},
 };
 
+/* PFUZE3000 */
+static struct of_regulator_match pfuze3000_matches[] = {
+
+	{ .name = "sw1a",	},
+	{ .name = "sw1b",	},
+	{ .name = "sw2",	},
+	{ .name = "sw3",	},
+	{ .name = "swbst",	},
+	{ .name = "vsnvs",	},
+	{ .name = "vrefddr",	},
+	{ .name = "vldo1",	},
+	{ .name = "vldo2",	},
+	{ .name = "vccsd",	},
+	{ .name = "v33",	},
+	{ .name = "vldo3",	},
+	{ .name = "vldo4",	},
+};
+
 static struct of_regulator_match *pfuze_matches;
 
 static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
@@ -313,6 +411,11 @@
 	}
 
 	switch (chip->chip_id) {
+	case PFUZE3000:
+		pfuze_matches = pfuze3000_matches;
+		ret = of_regulator_match(dev, parent, pfuze3000_matches,
+					 ARRAY_SIZE(pfuze3000_matches));
+		break;
 	case PFUZE200:
 		pfuze_matches = pfuze200_matches;
 		ret = of_regulator_match(dev, parent, pfuze200_matches,
@@ -378,7 +481,8 @@
 		 * as ID=8 in PFUZE100
 		 */
 		dev_info(pfuze_chip->dev, "Assuming misprogrammed ID=0x8");
-	} else if ((value & 0x0f) != pfuze_chip->chip_id) {
+	} else if ((value & 0x0f) != pfuze_chip->chip_id &&
+		   (value & 0xf0) >> 4 != pfuze_chip->chip_id) {
 		/* device id NOT match with your setting */
 		dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value);
 		return -ENODEV;
@@ -417,7 +521,7 @@
 	int i, ret;
 	const struct of_device_id *match;
 	u32 regulator_num;
-	u32 sw_check_start, sw_check_end;
+	u32 sw_check_start, sw_check_end, sw_hi = 0x40;
 
 	pfuze_chip = devm_kzalloc(&client->dev, sizeof(*pfuze_chip),
 			GFP_KERNEL);
@@ -458,13 +562,19 @@
 
 	/* use the right regulators after identify the right device */
 	switch (pfuze_chip->chip_id) {
+	case PFUZE3000:
+		pfuze_regulators = pfuze3000_regulators;
+		regulator_num = ARRAY_SIZE(pfuze3000_regulators);
+		sw_check_start = PFUZE3000_SW2;
+		sw_check_end = PFUZE3000_SW2;
+		sw_hi = 1 << 3;
+		break;
 	case PFUZE200:
 		pfuze_regulators = pfuze200_regulators;
 		regulator_num = ARRAY_SIZE(pfuze200_regulators);
 		sw_check_start = PFUZE200_SW2;
 		sw_check_end = PFUZE200_SW3B;
 		break;
-
 	case PFUZE100:
 	default:
 		pfuze_regulators = pfuze100_regulators;
@@ -474,7 +584,8 @@
 		break;
 	}
 	dev_info(&client->dev, "pfuze%s found.\n",
-		(pfuze_chip->chip_id == PFUZE100) ? "100" : "200");
+		(pfuze_chip->chip_id == PFUZE100) ? "100" :
+		((pfuze_chip->chip_id == PFUZE200) ? "200" : "3000"));
 
 	memcpy(pfuze_chip->regulator_descs, pfuze_regulators,
 		sizeof(pfuze_chip->regulator_descs));
@@ -498,10 +609,15 @@
 		/* SW2~SW4 high bit check and modify the voltage value table */
 		if (i >= sw_check_start && i <= sw_check_end) {
 			regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val);
-			if (val & 0x40) {
-				desc->min_uV = 800000;
-				desc->uV_step = 50000;
-				desc->n_voltages = 51;
+			if (val & sw_hi) {
+				if (pfuze_chip->chip_id == PFUZE3000) {
+					desc->volt_table = pfuze3000_sw2hi;
+					desc->n_voltages = ARRAY_SIZE(pfuze3000_sw2hi);
+				} else {
+					desc->min_uV = 800000;
+					desc->uV_step = 50000;
+					desc->n_voltages = 51;
+				}
 			}
 		}
 
diff --git a/drivers/regulator/qcom_rpm-regulator.c b/drivers/regulator/qcom_rpm-regulator.c
index 8364ff3..e8647f7 100644
--- a/drivers/regulator/qcom_rpm-regulator.c
+++ b/drivers/regulator/qcom_rpm-regulator.c
@@ -227,9 +227,11 @@
 		return uV;
 
 	mutex_lock(&vreg->lock);
-	vreg->uV = uV;
 	if (vreg->is_enabled)
-		ret = rpm_reg_write(vreg, req, vreg->uV / 1000);
+		ret = rpm_reg_write(vreg, req, uV / 1000);
+
+	if (!ret)
+		vreg->uV = uV;
 	mutex_unlock(&vreg->lock);
 
 	return ret;
@@ -252,9 +254,11 @@
 		return uV;
 
 	mutex_lock(&vreg->lock);
-	vreg->uV = uV;
 	if (vreg->is_enabled)
-		ret = rpm_reg_write(vreg, req, vreg->uV);
+		ret = rpm_reg_write(vreg, req, uV);
+
+	if (!ret)
+		vreg->uV = uV;
 	mutex_unlock(&vreg->lock);
 
 	return ret;
@@ -674,6 +678,7 @@
 	vreg->desc.owner = THIS_MODULE;
 	vreg->desc.type = REGULATOR_VOLTAGE;
 	vreg->desc.name = pdev->dev.of_node->name;
+	vreg->desc.supply_name = "vin";
 
 	vreg->rpm = dev_get_drvdata(pdev->dev.parent);
 	if (!vreg->rpm) {
@@ -768,7 +773,7 @@
 			break;
 		}
 
-		if (force_mode < 0) {
+		if (force_mode == -1) {
 			dev_err(&pdev->dev, "invalid force mode\n");
 			return -EINVAL;
 		}
diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c
index c94a3e0..1f93b75 100644
--- a/drivers/regulator/rk808-regulator.c
+++ b/drivers/regulator/rk808-regulator.c
@@ -97,7 +97,7 @@
 				  RK808_RAMP_RATE_MASK, ramp_value);
 }
 
-int rk808_set_suspend_voltage(struct regulator_dev *rdev, int uv)
+static int rk808_set_suspend_voltage(struct regulator_dev *rdev, int uv)
 {
 	unsigned int reg;
 	int sel = regulator_map_voltage_linear_range(rdev, uv, uv);
@@ -112,7 +112,7 @@
 				  sel);
 }
 
-int rk808_set_suspend_enable(struct regulator_dev *rdev)
+static int rk808_set_suspend_enable(struct regulator_dev *rdev)
 {
 	unsigned int reg;
 
@@ -123,7 +123,7 @@
 				  0);
 }
 
-int rk808_set_suspend_disable(struct regulator_dev *rdev)
+static int rk808_set_suspend_disable(struct regulator_dev *rdev)
 {
 	unsigned int reg;
 
diff --git a/drivers/regulator/rt5033-regulator.c b/drivers/regulator/rt5033-regulator.c
index 870cc49..96d2c18 100644
--- a/drivers/regulator/rt5033-regulator.c
+++ b/drivers/regulator/rt5033-regulator.c
@@ -36,6 +36,8 @@
 static const struct regulator_desc rt5033_supported_regulators[] = {
 	[RT5033_BUCK] = {
 		.name		= "BUCK",
+		.of_match	= of_match_ptr("BUCK"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id		= RT5033_BUCK,
 		.ops		= &rt5033_buck_ops,
 		.type		= REGULATOR_VOLTAGE,
@@ -50,6 +52,8 @@
 	},
 	[RT5033_LDO] = {
 		.name		= "LDO",
+		.of_match	= of_match_ptr("LDO"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id		= RT5033_LDO,
 		.ops		= &rt5033_buck_ops,
 		.type		= REGULATOR_VOLTAGE,
@@ -64,6 +68,8 @@
 	},
 	[RT5033_SAFE_LDO] = {
 		.name		= "SAFE_LDO",
+		.of_match	= of_match_ptr("SAFE_LDO"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id		= RT5033_SAFE_LDO,
 		.ops		= &rt5033_safe_ldo_ops,
 		.type		= REGULATOR_VOLTAGE,
@@ -81,7 +87,7 @@
 	int ret, i;
 	struct regulator_config config = {};
 
-	config.dev = &pdev->dev;
+	config.dev = rt5033->dev;
 	config.driver_data = rt5033;
 
 	for (i = 0; i < ARRAY_SIZE(rt5033_supported_regulators); i++) {
diff --git a/drivers/regulator/tps65023-regulator.c b/drivers/regulator/tps65023-regulator.c
index 7380af8..b941e56 100644
--- a/drivers/regulator/tps65023-regulator.c
+++ b/drivers/regulator/tps65023-regulator.c
@@ -173,7 +173,7 @@
 }
 
 /* Operations permitted on VDCDCx */
-static struct regulator_ops tps65023_dcdc_ops = {
+static const struct regulator_ops tps65023_dcdc_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
@@ -184,7 +184,7 @@
 };
 
 /* Operations permitted on LDOx */
-static struct regulator_ops tps65023_ldo_ops = {
+static const struct regulator_ops tps65023_ldo_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
@@ -194,7 +194,7 @@
 	.map_voltage = regulator_map_voltage_ascend,
 };
 
-static struct regmap_config tps65023_regmap_config = {
+static const struct regmap_config tps65023_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 };
diff --git a/drivers/scsi/device_handler/scsi_dh.c b/drivers/scsi/device_handler/scsi_dh.c
index 1dba62c..1efebc9 100644
--- a/drivers/scsi/device_handler/scsi_dh.c
+++ b/drivers/scsi/device_handler/scsi_dh.c
@@ -136,11 +136,12 @@
 	struct scsi_device_handler *scsi_dh = scsi_dh_data->scsi_dh;
 	struct scsi_device *sdev = scsi_dh_data->sdev;
 
+	scsi_dh->detach(sdev);
+
 	spin_lock_irq(sdev->request_queue->queue_lock);
 	sdev->scsi_dh_data = NULL;
 	spin_unlock_irq(sdev->request_queue->queue_lock);
 
-	scsi_dh->detach(sdev);
 	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", scsi_dh->name);
 	module_put(scsi_dh->module);
 }
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3995169..05ea0d4 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2800,9 +2800,11 @@
 	 */
 	sd_set_flush_flag(sdkp);
 
-	max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue),
-				sdkp->max_xfer_blocks);
+	max_xfer = sdkp->max_xfer_blocks;
 	max_xfer <<= ilog2(sdp->sector_size) - 9;
+
+	max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue),
+				max_xfer);
 	blk_queue_max_hw_sectors(sdkp->disk->queue, max_xfer);
 	set_capacity(disk, sdkp->capacity);
 	sd_config_write_same(sdkp);
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 9982998..95cceda 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -185,6 +185,16 @@
 	help
 	  SPI master controller for DaVinci/DA8x/OMAP-L/AM1x SPI modules.
 
+config SPI_DLN2
+       tristate "Diolan DLN-2 USB SPI adapter"
+       depends on MFD_DLN2
+       help
+         If you say yes to this option, support will be included for Diolan
+         DLN2, a USB to SPI interface.
+
+         This driver can also be built as a module.  If so, the module
+         will be called spi-dln2.
+
 config SPI_EFM32
 	tristate "EFM32 SPI controller"
 	depends on OF && ARM && (ARCH_EFM32 || COMPILE_TEST)
@@ -279,7 +289,7 @@
 	depends on FSL_SOC
 
 config SPI_FSL_SPI
-	bool "Freescale SPI controller and Aeroflex Gaisler GRLIB SPI controller"
+	tristate "Freescale SPI controller and Aeroflex Gaisler GRLIB SPI controller"
 	depends on OF
 	select SPI_FSL_LIB
 	select SPI_FSL_CPM if FSL_SOC
@@ -292,7 +302,6 @@
 
 config SPI_FSL_DSPI
 	tristate "Freescale DSPI controller"
-	select SPI_BITBANG
 	select REGMAP_MMIO
 	depends on SOC_VF610 || COMPILE_TEST
 	help
@@ -300,7 +309,7 @@
 	  mode. VF610 platform uses the controller.
 
 config SPI_FSL_ESPI
-	bool "Freescale eSPI controller"
+	tristate "Freescale eSPI controller"
 	depends on FSL_SOC
 	select SPI_FSL_LIB
 	help
@@ -460,7 +469,6 @@
 config SPI_S3C64XX
 	tristate "Samsung S3C64XX series type SPI"
 	depends on (PLAT_SAMSUNG || ARCH_EXYNOS)
-	select S3C64XX_PL080 if ARCH_S3C64XX
 	help
 	  SPI driver for Samsung S3C64XX and newer SoCs.
 
@@ -503,6 +511,13 @@
 	help
 	  SPI driver for CSR SiRFprimaII SoCs
 
+config SPI_ST_SSC4
+	tristate "STMicroelectronics SPI SSC-based driver"
+	depends on ARCH_STI
+	help
+	  STMicroelectronics SoCs support for SPI. If you say yes to
+	  this option, support will be included for the SSC driven SPI.
+
 config SPI_SUN4I
 	tristate "Allwinner A10 SoCs SPI controller"
 	depends on ARCH_SUNXI || COMPILE_TEST
@@ -595,7 +610,6 @@
 	  16 bit words in SPI mode 0, automatically asserting CS on transfer
 	  start and deasserting on end.
 
-
 config SPI_NUC900
 	tristate "Nuvoton NUC900 series SPI"
 	depends on ARCH_W90X900
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 6b9d2ac..d8cbf65 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -27,6 +27,7 @@
 obj-$(CONFIG_SPI_CLPS711X)		+= spi-clps711x.o
 obj-$(CONFIG_SPI_COLDFIRE_QSPI)		+= spi-coldfire-qspi.o
 obj-$(CONFIG_SPI_DAVINCI)		+= spi-davinci.o
+obj-$(CONFIG_SPI_DLN2)			+= spi-dln2.o
 obj-$(CONFIG_SPI_DESIGNWARE)		+= spi-dw.o
 obj-$(CONFIG_SPI_DW_MMIO)		+= spi-dw-mmio.o
 obj-$(CONFIG_SPI_DW_PCI)		+= spi-dw-midpci.o
@@ -76,6 +77,7 @@
 obj-$(CONFIG_SPI_SH_MSIOF)		+= spi-sh-msiof.o
 obj-$(CONFIG_SPI_SH_SCI)		+= spi-sh-sci.o
 obj-$(CONFIG_SPI_SIRF)		+= spi-sirf.o
+obj-$(CONFIG_SPI_ST_SSC4)		+= spi-st-ssc4.o
 obj-$(CONFIG_SPI_SUN4I)			+= spi-sun4i.o
 obj-$(CONFIG_SPI_SUN6I)			+= spi-sun6i.o
 obj-$(CONFIG_SPI_TEGRA114)		+= spi-tegra114.o
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 23d8f5f5..9af7841 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1046,6 +1046,7 @@
 	struct atmel_spi_device	*asd;
 	int			timeout;
 	int			ret;
+	unsigned long		dma_timeout;
 
 	as = spi_master_get_devdata(master);
 
@@ -1103,15 +1104,12 @@
 
 		/* interrupts are disabled, so free the lock for schedule */
 		atmel_spi_unlock(as);
-		ret = wait_for_completion_timeout(&as->xfer_completion,
-							SPI_DMA_TIMEOUT);
+		dma_timeout = wait_for_completion_timeout(&as->xfer_completion,
+							  SPI_DMA_TIMEOUT);
 		atmel_spi_lock(as);
-		if (WARN_ON(ret == 0)) {
-			dev_err(&spi->dev,
-				"spi trasfer timeout, err %d\n", ret);
+		if (WARN_ON(dma_timeout == 0)) {
+			dev_err(&spi->dev, "spi transfer timeout\n");
 			as->done_status = -EIO;
-		} else {
-			ret = 0;
 		}
 
 		if (as->done_status)
diff --git a/drivers/spi/spi-au1550.c b/drivers/spi/spi-au1550.c
index 326f479..f45e085 100644
--- a/drivers/spi/spi-au1550.c
+++ b/drivers/spi/spi-au1550.c
@@ -15,10 +15,6 @@
  * 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
  */
 
 #include <linux/init.h>
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 98aab457..419a782 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -17,10 +17,6 @@
  * 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.
  */
 
 #include <linux/clk.h>
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index c205309..e73e2b05 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -13,10 +13,6 @@
  * 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., 51 Franklin Street, Fifth Floor,
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index dc7d2c2..5ef6638 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -10,10 +10,6 @@
  * 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
  */
 
 #include <linux/spinlock.h>
diff --git a/drivers/spi/spi-butterfly.c b/drivers/spi/spi-butterfly.c
index ee4f91c..9a95862 100644
--- a/drivers/spi/spi-butterfly.c
+++ b/drivers/spi/spi-butterfly.c
@@ -12,10 +12,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index 41b5dc4..688956ff 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -12,11 +12,6 @@
  * 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., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA
- *
 */
 
 #include <linux/kernel.h>
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index b3707ba..5e99106 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -11,10 +11,6 @@
  * 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
  */
 
 #include <linux/interrupt.h>
diff --git a/drivers/spi/spi-dln2.c b/drivers/spi/spi-dln2.c
new file mode 100644
index 0000000..3b7d91d
--- /dev/null
+++ b/drivers/spi/spi-dln2.c
@@ -0,0 +1,881 @@
+/*
+ * Driver for the Diolan DLN-2 USB-SPI adapter
+ *
+ * Copyright (c) 2014 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/dln2.h>
+#include <linux/spi/spi.h>
+#include <linux/pm_runtime.h>
+#include <asm/unaligned.h>
+
+#define DLN2_SPI_MODULE_ID		0x02
+#define DLN2_SPI_CMD(cmd)		DLN2_CMD(cmd, DLN2_SPI_MODULE_ID)
+
+/* SPI commands */
+#define DLN2_SPI_GET_PORT_COUNT			DLN2_SPI_CMD(0x00)
+#define DLN2_SPI_ENABLE				DLN2_SPI_CMD(0x11)
+#define DLN2_SPI_DISABLE			DLN2_SPI_CMD(0x12)
+#define DLN2_SPI_IS_ENABLED			DLN2_SPI_CMD(0x13)
+#define DLN2_SPI_SET_MODE			DLN2_SPI_CMD(0x14)
+#define DLN2_SPI_GET_MODE			DLN2_SPI_CMD(0x15)
+#define DLN2_SPI_SET_FRAME_SIZE			DLN2_SPI_CMD(0x16)
+#define DLN2_SPI_GET_FRAME_SIZE			DLN2_SPI_CMD(0x17)
+#define DLN2_SPI_SET_FREQUENCY			DLN2_SPI_CMD(0x18)
+#define DLN2_SPI_GET_FREQUENCY			DLN2_SPI_CMD(0x19)
+#define DLN2_SPI_READ_WRITE			DLN2_SPI_CMD(0x1A)
+#define DLN2_SPI_READ				DLN2_SPI_CMD(0x1B)
+#define DLN2_SPI_WRITE				DLN2_SPI_CMD(0x1C)
+#define DLN2_SPI_SET_DELAY_BETWEEN_SS		DLN2_SPI_CMD(0x20)
+#define DLN2_SPI_GET_DELAY_BETWEEN_SS		DLN2_SPI_CMD(0x21)
+#define DLN2_SPI_SET_DELAY_AFTER_SS		DLN2_SPI_CMD(0x22)
+#define DLN2_SPI_GET_DELAY_AFTER_SS		DLN2_SPI_CMD(0x23)
+#define DLN2_SPI_SET_DELAY_BETWEEN_FRAMES	DLN2_SPI_CMD(0x24)
+#define DLN2_SPI_GET_DELAY_BETWEEN_FRAMES	DLN2_SPI_CMD(0x25)
+#define DLN2_SPI_SET_SS				DLN2_SPI_CMD(0x26)
+#define DLN2_SPI_GET_SS				DLN2_SPI_CMD(0x27)
+#define DLN2_SPI_RELEASE_SS			DLN2_SPI_CMD(0x28)
+#define DLN2_SPI_SS_VARIABLE_ENABLE		DLN2_SPI_CMD(0x2B)
+#define DLN2_SPI_SS_VARIABLE_DISABLE		DLN2_SPI_CMD(0x2C)
+#define DLN2_SPI_SS_VARIABLE_IS_ENABLED		DLN2_SPI_CMD(0x2D)
+#define DLN2_SPI_SS_AAT_ENABLE			DLN2_SPI_CMD(0x2E)
+#define DLN2_SPI_SS_AAT_DISABLE			DLN2_SPI_CMD(0x2F)
+#define DLN2_SPI_SS_AAT_IS_ENABLED		DLN2_SPI_CMD(0x30)
+#define DLN2_SPI_SS_BETWEEN_FRAMES_ENABLE	DLN2_SPI_CMD(0x31)
+#define DLN2_SPI_SS_BETWEEN_FRAMES_DISABLE	DLN2_SPI_CMD(0x32)
+#define DLN2_SPI_SS_BETWEEN_FRAMES_IS_ENABLED	DLN2_SPI_CMD(0x33)
+#define DLN2_SPI_SET_CPHA			DLN2_SPI_CMD(0x34)
+#define DLN2_SPI_GET_CPHA			DLN2_SPI_CMD(0x35)
+#define DLN2_SPI_SET_CPOL			DLN2_SPI_CMD(0x36)
+#define DLN2_SPI_GET_CPOL			DLN2_SPI_CMD(0x37)
+#define DLN2_SPI_SS_MULTI_ENABLE		DLN2_SPI_CMD(0x38)
+#define DLN2_SPI_SS_MULTI_DISABLE		DLN2_SPI_CMD(0x39)
+#define DLN2_SPI_SS_MULTI_IS_ENABLED		DLN2_SPI_CMD(0x3A)
+#define DLN2_SPI_GET_SUPPORTED_MODES		DLN2_SPI_CMD(0x40)
+#define DLN2_SPI_GET_SUPPORTED_CPHA_VALUES	DLN2_SPI_CMD(0x41)
+#define DLN2_SPI_GET_SUPPORTED_CPOL_VALUES	DLN2_SPI_CMD(0x42)
+#define DLN2_SPI_GET_SUPPORTED_FRAME_SIZES	DLN2_SPI_CMD(0x43)
+#define DLN2_SPI_GET_SS_COUNT			DLN2_SPI_CMD(0x44)
+#define DLN2_SPI_GET_MIN_FREQUENCY		DLN2_SPI_CMD(0x45)
+#define DLN2_SPI_GET_MAX_FREQUENCY		DLN2_SPI_CMD(0x46)
+#define DLN2_SPI_GET_MIN_DELAY_BETWEEN_SS	DLN2_SPI_CMD(0x47)
+#define DLN2_SPI_GET_MAX_DELAY_BETWEEN_SS	DLN2_SPI_CMD(0x48)
+#define DLN2_SPI_GET_MIN_DELAY_AFTER_SS		DLN2_SPI_CMD(0x49)
+#define DLN2_SPI_GET_MAX_DELAY_AFTER_SS		DLN2_SPI_CMD(0x4A)
+#define DLN2_SPI_GET_MIN_DELAY_BETWEEN_FRAMES	DLN2_SPI_CMD(0x4B)
+#define DLN2_SPI_GET_MAX_DELAY_BETWEEN_FRAMES	DLN2_SPI_CMD(0x4C)
+
+#define DLN2_SPI_MAX_XFER_SIZE			256
+#define DLN2_SPI_BUF_SIZE			(DLN2_SPI_MAX_XFER_SIZE + 16)
+#define DLN2_SPI_ATTR_LEAVE_SS_LOW		BIT(0)
+#define DLN2_TRANSFERS_WAIT_COMPLETE		1
+#define DLN2_TRANSFERS_CANCEL			0
+#define DLN2_RPM_AUTOSUSPEND_TIMEOUT		2000
+
+struct dln2_spi {
+	struct platform_device *pdev;
+	struct spi_master *master;
+	u8 port;
+
+	/*
+	 * This buffer will be used mainly for read/write operations. Since
+	 * they're quite large, we cannot use the stack. Protection is not
+	 * needed because all SPI communication is serialized by the SPI core.
+	 */
+	void *buf;
+
+	u8 bpw;
+	u32 speed;
+	u16 mode;
+	u8 cs;
+};
+
+/*
+ * Enable/Disable SPI module. The disable command will wait for transfers to
+ * complete first.
+ */
+static int dln2_spi_enable(struct dln2_spi *dln2, bool enable)
+{
+	u16 cmd;
+	struct {
+		u8 port;
+		u8 wait_for_completion;
+	} tx;
+	unsigned len = sizeof(tx);
+
+	tx.port = dln2->port;
+
+	if (enable) {
+		cmd = DLN2_SPI_ENABLE;
+		len -= sizeof(tx.wait_for_completion);
+	} else {
+		tx.wait_for_completion = DLN2_TRANSFERS_WAIT_COMPLETE;
+		cmd = DLN2_SPI_DISABLE;
+	}
+
+	return dln2_transfer_tx(dln2->pdev, cmd, &tx, len);
+}
+
+/*
+ * Select/unselect multiple CS lines. The selected lines will be automatically
+ * toggled LOW/HIGH by the board firmware during transfers, provided they're
+ * enabled first.
+ *
+ * Ex: cs_mask = 0x03 -> CS0 & CS1 will be selected and the next WR/RD operation
+ *                       will toggle the lines LOW/HIGH automatically.
+ */
+static int dln2_spi_cs_set(struct dln2_spi *dln2, u8 cs_mask)
+{
+	struct {
+		u8 port;
+		u8 cs;
+	} tx;
+
+	tx.port = dln2->port;
+
+	/*
+	 * According to Diolan docs, "a slave device can be selected by changing
+	 * the corresponding bit value to 0". The rest must be set to 1. Hence
+	 * the bitwise NOT in front.
+	 */
+	tx.cs = ~cs_mask;
+
+	return dln2_transfer_tx(dln2->pdev, DLN2_SPI_SET_SS, &tx, sizeof(tx));
+}
+
+/*
+ * Select one CS line. The other lines will be un-selected.
+ */
+static int dln2_spi_cs_set_one(struct dln2_spi *dln2, u8 cs)
+{
+	return dln2_spi_cs_set(dln2, BIT(cs));
+}
+
+/*
+ * Enable/disable CS lines for usage. The module has to be disabled first.
+ */
+static int dln2_spi_cs_enable(struct dln2_spi *dln2, u8 cs_mask, bool enable)
+{
+	struct {
+		u8 port;
+		u8 cs;
+	} tx;
+	u16 cmd;
+
+	tx.port = dln2->port;
+	tx.cs = cs_mask;
+	cmd = enable ? DLN2_SPI_SS_MULTI_ENABLE : DLN2_SPI_SS_MULTI_DISABLE;
+
+	return dln2_transfer_tx(dln2->pdev, cmd, &tx, sizeof(tx));
+}
+
+static int dln2_spi_cs_enable_all(struct dln2_spi *dln2, bool enable)
+{
+	u8 cs_mask = GENMASK(dln2->master->num_chipselect - 1, 0);
+
+	return dln2_spi_cs_enable(dln2, cs_mask, enable);
+}
+
+static int dln2_spi_get_cs_num(struct dln2_spi *dln2, u16 *cs_num)
+{
+	int ret;
+	struct {
+		u8 port;
+	} tx;
+	struct {
+		__le16 cs_count;
+	} rx;
+	unsigned rx_len = sizeof(rx);
+
+	tx.port = dln2->port;
+	ret = dln2_transfer(dln2->pdev, DLN2_SPI_GET_SS_COUNT, &tx, sizeof(tx),
+			    &rx, &rx_len);
+	if (ret < 0)
+		return ret;
+	if (rx_len < sizeof(rx))
+		return -EPROTO;
+
+	*cs_num = le16_to_cpu(rx.cs_count);
+
+	dev_dbg(&dln2->pdev->dev, "cs_num = %d\n", *cs_num);
+
+	return 0;
+}
+
+static int dln2_spi_get_speed(struct dln2_spi *dln2, u16 cmd, u32 *freq)
+{
+	int ret;
+	struct {
+		u8 port;
+	} tx;
+	struct {
+		__le32 speed;
+	} rx;
+	unsigned rx_len = sizeof(rx);
+
+	tx.port = dln2->port;
+
+	ret = dln2_transfer(dln2->pdev, cmd, &tx, sizeof(tx), &rx, &rx_len);
+	if (ret < 0)
+		return ret;
+	if (rx_len < sizeof(rx))
+		return -EPROTO;
+
+	*freq = le32_to_cpu(rx.speed);
+
+	return 0;
+}
+
+/*
+ * Get bus min/max frequencies.
+ */
+static int dln2_spi_get_speed_range(struct dln2_spi *dln2, u32 *fmin, u32 *fmax)
+{
+	int ret;
+
+	ret = dln2_spi_get_speed(dln2, DLN2_SPI_GET_MIN_FREQUENCY, fmin);
+	if (ret < 0)
+		return ret;
+
+	ret = dln2_spi_get_speed(dln2, DLN2_SPI_GET_MAX_FREQUENCY, fmax);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(&dln2->pdev->dev, "freq_min = %d, freq_max = %d\n",
+		*fmin, *fmax);
+
+	return 0;
+}
+
+/*
+ * Set the bus speed. The module will automatically round down to the closest
+ * available frequency and returns it. The module has to be disabled first.
+ */
+static int dln2_spi_set_speed(struct dln2_spi *dln2, u32 speed)
+{
+	int ret;
+	struct {
+		u8 port;
+		__le32 speed;
+	} __packed tx;
+	struct {
+		__le32 speed;
+	} rx;
+	int rx_len = sizeof(rx);
+
+	tx.port = dln2->port;
+	tx.speed = cpu_to_le32(speed);
+
+	ret = dln2_transfer(dln2->pdev, DLN2_SPI_SET_FREQUENCY, &tx, sizeof(tx),
+			    &rx, &rx_len);
+	if (ret < 0)
+		return ret;
+	if (rx_len < sizeof(rx))
+		return -EPROTO;
+
+	return 0;
+}
+
+/*
+ * Change CPOL & CPHA. The module has to be disabled first.
+ */
+static int dln2_spi_set_mode(struct dln2_spi *dln2, u8 mode)
+{
+	struct {
+		u8 port;
+		u8 mode;
+	} tx;
+
+	tx.port = dln2->port;
+	tx.mode = mode;
+
+	return dln2_transfer_tx(dln2->pdev, DLN2_SPI_SET_MODE, &tx, sizeof(tx));
+}
+
+/*
+ * Change frame size. The module has to be disabled first.
+ */
+static int dln2_spi_set_bpw(struct dln2_spi *dln2, u8 bpw)
+{
+	struct {
+		u8 port;
+		u8 bpw;
+	} tx;
+
+	tx.port = dln2->port;
+	tx.bpw = bpw;
+
+	return dln2_transfer_tx(dln2->pdev, DLN2_SPI_SET_FRAME_SIZE,
+				&tx, sizeof(tx));
+}
+
+static int dln2_spi_get_supported_frame_sizes(struct dln2_spi *dln2,
+					      u32 *bpw_mask)
+{
+	int ret;
+	struct {
+		u8 port;
+	} tx;
+	struct {
+		u8 count;
+		u8 frame_sizes[36];
+	} *rx = dln2->buf;
+	unsigned rx_len = sizeof(*rx);
+	int i;
+
+	tx.port = dln2->port;
+
+	ret = dln2_transfer(dln2->pdev, DLN2_SPI_GET_SUPPORTED_FRAME_SIZES,
+			    &tx, sizeof(tx), rx, &rx_len);
+	if (ret < 0)
+		return ret;
+	if (rx_len < sizeof(*rx))
+		return -EPROTO;
+	if (rx->count > ARRAY_SIZE(rx->frame_sizes))
+		return -EPROTO;
+
+	*bpw_mask = 0;
+	for (i = 0; i < rx->count; i++)
+		*bpw_mask |= BIT(rx->frame_sizes[i] - 1);
+
+	dev_dbg(&dln2->pdev->dev, "bpw_mask = 0x%X\n", *bpw_mask);
+
+	return 0;
+}
+
+/*
+ * Copy the data to DLN2 buffer and change the byte order to LE, requested by
+ * DLN2 module. SPI core makes sure that the data length is a multiple of word
+ * size.
+ */
+static int dln2_spi_copy_to_buf(u8 *dln2_buf, const u8 *src, u16 len, u8 bpw)
+{
+#ifdef __LITTLE_ENDIAN
+	memcpy(dln2_buf, src, len);
+#else
+	if (bpw <= 8) {
+		memcpy(dln2_buf, src, len);
+	} else if (bpw <= 16) {
+		__le16 *d = (__le16 *)dln2_buf;
+		u16 *s = (u16 *)src;
+
+		len = len / 2;
+		while (len--)
+			*d++ = cpu_to_le16p(s++);
+	} else {
+		__le32 *d = (__le32 *)dln2_buf;
+		u32 *s = (u32 *)src;
+
+		len = len / 4;
+		while (len--)
+			*d++ = cpu_to_le32p(s++);
+	}
+#endif
+
+	return 0;
+}
+
+/*
+ * Copy the data from DLN2 buffer and convert to CPU byte order since the DLN2
+ * buffer is LE ordered. SPI core makes sure that the data length is a multiple
+ * of word size. The RX dln2_buf is 2 byte aligned so, for BE, we have to make
+ * sure we avoid unaligned accesses for 32 bit case.
+ */
+static int dln2_spi_copy_from_buf(u8 *dest, const u8 *dln2_buf, u16 len, u8 bpw)
+{
+#ifdef __LITTLE_ENDIAN
+	memcpy(dest, dln2_buf, len);
+#else
+	if (bpw <= 8) {
+		memcpy(dest, dln2_buf, len);
+	} else if (bpw <= 16) {
+		u16 *d = (u16 *)dest;
+		__le16 *s = (__le16 *)dln2_buf;
+
+		len = len / 2;
+		while (len--)
+			*d++ = le16_to_cpup(s++);
+	} else {
+		u32 *d = (u32 *)dest;
+		__le32 *s = (__le32 *)dln2_buf;
+
+		len = len / 4;
+		while (len--)
+			*d++ = get_unaligned_le32(s++);
+	}
+#endif
+
+	return 0;
+}
+
+/*
+ * Perform one write operation.
+ */
+static int dln2_spi_write_one(struct dln2_spi *dln2, const u8 *data,
+			      u16 data_len, u8 attr)
+{
+	struct {
+		u8 port;
+		__le16 size;
+		u8 attr;
+		u8 buf[DLN2_SPI_MAX_XFER_SIZE];
+	} __packed *tx = dln2->buf;
+	unsigned tx_len;
+
+	BUILD_BUG_ON(sizeof(*tx) > DLN2_SPI_BUF_SIZE);
+
+	if (data_len > DLN2_SPI_MAX_XFER_SIZE)
+		return -EINVAL;
+
+	tx->port = dln2->port;
+	tx->size = cpu_to_le16(data_len);
+	tx->attr = attr;
+
+	dln2_spi_copy_to_buf(tx->buf, data, data_len, dln2->bpw);
+
+	tx_len = sizeof(*tx) + data_len - DLN2_SPI_MAX_XFER_SIZE;
+	return dln2_transfer_tx(dln2->pdev, DLN2_SPI_WRITE, tx, tx_len);
+}
+
+/*
+ * Perform one read operation.
+ */
+static int dln2_spi_read_one(struct dln2_spi *dln2, u8 *data,
+			     u16 data_len, u8 attr)
+{
+	int ret;
+	struct {
+		u8 port;
+		__le16 size;
+		u8 attr;
+	} __packed tx;
+	struct {
+		__le16 size;
+		u8 buf[DLN2_SPI_MAX_XFER_SIZE];
+	} __packed *rx = dln2->buf;
+	unsigned rx_len = sizeof(*rx);
+
+	BUILD_BUG_ON(sizeof(*rx) > DLN2_SPI_BUF_SIZE);
+
+	if (data_len > DLN2_SPI_MAX_XFER_SIZE)
+		return -EINVAL;
+
+	tx.port = dln2->port;
+	tx.size = cpu_to_le16(data_len);
+	tx.attr = attr;
+
+	ret = dln2_transfer(dln2->pdev, DLN2_SPI_READ, &tx, sizeof(tx),
+			    rx, &rx_len);
+	if (ret < 0)
+		return ret;
+	if (rx_len < sizeof(rx->size) + data_len)
+		return -EPROTO;
+	if (le16_to_cpu(rx->size) != data_len)
+		return -EPROTO;
+
+	dln2_spi_copy_from_buf(data, rx->buf, data_len, dln2->bpw);
+
+	return 0;
+}
+
+/*
+ * Perform one write & read operation.
+ */
+static int dln2_spi_read_write_one(struct dln2_spi *dln2, const u8 *tx_data,
+				   u8 *rx_data, u16 data_len, u8 attr)
+{
+	int ret;
+	struct {
+		u8 port;
+		__le16 size;
+		u8 attr;
+		u8 buf[DLN2_SPI_MAX_XFER_SIZE];
+	} __packed *tx;
+	struct {
+		__le16 size;
+		u8 buf[DLN2_SPI_MAX_XFER_SIZE];
+	} __packed *rx;
+	unsigned tx_len, rx_len;
+
+	BUILD_BUG_ON(sizeof(*tx) > DLN2_SPI_BUF_SIZE ||
+		     sizeof(*rx) > DLN2_SPI_BUF_SIZE);
+
+	if (data_len > DLN2_SPI_MAX_XFER_SIZE)
+		return -EINVAL;
+
+	/*
+	 * Since this is a pseudo full-duplex communication, we're perfectly
+	 * safe to use the same buffer for both tx and rx. When DLN2 sends the
+	 * response back, with the rx data, we don't need the tx buffer anymore.
+	 */
+	tx = dln2->buf;
+	rx = dln2->buf;
+
+	tx->port = dln2->port;
+	tx->size = cpu_to_le16(data_len);
+	tx->attr = attr;
+
+	dln2_spi_copy_to_buf(tx->buf, tx_data, data_len, dln2->bpw);
+
+	tx_len = sizeof(*tx) + data_len - DLN2_SPI_MAX_XFER_SIZE;
+	rx_len = sizeof(*rx);
+
+	ret = dln2_transfer(dln2->pdev, DLN2_SPI_READ_WRITE, tx, tx_len,
+			    rx, &rx_len);
+	if (ret < 0)
+		return ret;
+	if (rx_len < sizeof(rx->size) + data_len)
+		return -EPROTO;
+	if (le16_to_cpu(rx->size) != data_len)
+		return -EPROTO;
+
+	dln2_spi_copy_from_buf(rx_data, rx->buf, data_len, dln2->bpw);
+
+	return 0;
+}
+
+/*
+ * Read/Write wrapper. It will automatically split an operation into multiple
+ * single ones due to device buffer constraints.
+ */
+static int dln2_spi_rdwr(struct dln2_spi *dln2, const u8 *tx_data,
+			 u8 *rx_data, u16 data_len, u8 attr) {
+	int ret;
+	u16 len;
+	u8 temp_attr;
+	u16 remaining = data_len;
+	u16 offset;
+
+	do {
+		if (remaining > DLN2_SPI_MAX_XFER_SIZE) {
+			len = DLN2_SPI_MAX_XFER_SIZE;
+			temp_attr = DLN2_SPI_ATTR_LEAVE_SS_LOW;
+		} else {
+			len = remaining;
+			temp_attr = attr;
+		}
+
+		offset = data_len - remaining;
+
+		if (tx_data && rx_data) {
+			ret = dln2_spi_read_write_one(dln2,
+						      tx_data + offset,
+						      rx_data + offset,
+						      len, temp_attr);
+		} else if (tx_data) {
+			ret = dln2_spi_write_one(dln2,
+						 tx_data + offset,
+						 len, temp_attr);
+		} else if (rx_data) {
+			ret = dln2_spi_read_one(dln2,
+						rx_data + offset,
+						len, temp_attr);
+		 } else {
+			return -EINVAL;
+		 }
+
+		if (ret < 0)
+			return ret;
+
+		remaining -= len;
+	} while (remaining);
+
+	return 0;
+}
+
+static int dln2_spi_prepare_message(struct spi_master *master,
+				    struct spi_message *message)
+{
+	int ret;
+	struct dln2_spi *dln2 = spi_master_get_devdata(master);
+	struct spi_device *spi = message->spi;
+
+	if (dln2->cs != spi->chip_select) {
+		ret = dln2_spi_cs_set_one(dln2, spi->chip_select);
+		if (ret < 0)
+			return ret;
+
+		dln2->cs = spi->chip_select;
+	}
+
+	return 0;
+}
+
+static int dln2_spi_transfer_setup(struct dln2_spi *dln2, u32 speed,
+				   u8 bpw, u8 mode)
+{
+	int ret;
+	bool bus_setup_change;
+
+	bus_setup_change = dln2->speed != speed || dln2->mode != mode ||
+			   dln2->bpw != bpw;
+
+	if (!bus_setup_change)
+		return 0;
+
+	ret = dln2_spi_enable(dln2, false);
+	if (ret < 0)
+		return ret;
+
+	if (dln2->speed != speed) {
+		ret = dln2_spi_set_speed(dln2, speed);
+		if (ret < 0)
+			return ret;
+
+		dln2->speed = speed;
+	}
+
+	if (dln2->mode != mode) {
+		ret = dln2_spi_set_mode(dln2, mode & 0x3);
+		if (ret < 0)
+			return ret;
+
+		dln2->mode = mode;
+	}
+
+	if (dln2->bpw != bpw) {
+		ret = dln2_spi_set_bpw(dln2, bpw);
+		if (ret < 0)
+			return ret;
+
+		dln2->bpw = bpw;
+	}
+
+	return dln2_spi_enable(dln2, true);
+}
+
+static int dln2_spi_transfer_one(struct spi_master *master,
+				 struct spi_device *spi,
+				 struct spi_transfer *xfer)
+{
+	struct dln2_spi *dln2 = spi_master_get_devdata(master);
+	int status;
+	u8 attr = 0;
+
+	status = dln2_spi_transfer_setup(dln2, xfer->speed_hz,
+					 xfer->bits_per_word,
+					 spi->mode);
+	if (status < 0) {
+		dev_err(&dln2->pdev->dev, "Cannot setup transfer\n");
+		return status;
+	}
+
+	if (!xfer->cs_change && !spi_transfer_is_last(master, xfer))
+		attr = DLN2_SPI_ATTR_LEAVE_SS_LOW;
+
+	status = dln2_spi_rdwr(dln2, xfer->tx_buf, xfer->rx_buf,
+			       xfer->len, attr);
+	if (status < 0)
+		dev_err(&dln2->pdev->dev, "write/read failed!\n");
+
+	return status;
+}
+
+static int dln2_spi_probe(struct platform_device *pdev)
+{
+	struct spi_master *master;
+	struct dln2_spi *dln2;
+	struct dln2_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	int ret;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*dln2));
+	if (!master)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, master);
+
+	dln2 = spi_master_get_devdata(master);
+
+	dln2->buf = devm_kmalloc(&pdev->dev, DLN2_SPI_BUF_SIZE, GFP_KERNEL);
+	if (!dln2->buf) {
+		ret = -ENOMEM;
+		goto exit_free_master;
+	}
+
+	dln2->master = master;
+	dln2->pdev = pdev;
+	dln2->port = pdata->port;
+	/* cs/mode can never be 0xff, so the first transfer will set them */
+	dln2->cs = 0xff;
+	dln2->mode = 0xff;
+
+	/* disable SPI module before continuing with the setup */
+	ret = dln2_spi_enable(dln2, false);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to disable SPI module\n");
+		goto exit_free_master;
+	}
+
+	ret = dln2_spi_get_cs_num(dln2, &master->num_chipselect);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to get number of CS pins\n");
+		goto exit_free_master;
+	}
+
+	ret = dln2_spi_get_speed_range(dln2,
+				       &master->min_speed_hz,
+				       &master->max_speed_hz);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to read bus min/max freqs\n");
+		goto exit_free_master;
+	}
+
+	ret = dln2_spi_get_supported_frame_sizes(dln2,
+						 &master->bits_per_word_mask);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to read supported frame sizes\n");
+		goto exit_free_master;
+	}
+
+	ret = dln2_spi_cs_enable_all(dln2, true);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to enable CS pins\n");
+		goto exit_free_master;
+	}
+
+	master->bus_num = -1;
+	master->mode_bits = SPI_CPOL | SPI_CPHA;
+	master->prepare_message = dln2_spi_prepare_message;
+	master->transfer_one = dln2_spi_transfer_one;
+	master->auto_runtime_pm = true;
+
+	/* enable SPI module, we're good to go */
+	ret = dln2_spi_enable(dln2, true);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to enable SPI module\n");
+		goto exit_free_master;
+	}
+
+	pm_runtime_set_autosuspend_delay(&pdev->dev,
+					 DLN2_RPM_AUTOSUSPEND_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to register master\n");
+		goto exit_register;
+	}
+
+	return ret;
+
+exit_register:
+	pm_runtime_disable(&pdev->dev);
+	pm_runtime_set_suspended(&pdev->dev);
+
+	if (dln2_spi_enable(dln2, false) < 0)
+		dev_err(&pdev->dev, "Failed to disable SPI module\n");
+exit_free_master:
+	spi_master_put(master);
+
+	return ret;
+}
+
+static int dln2_spi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = spi_master_get(platform_get_drvdata(pdev));
+	struct dln2_spi *dln2 = spi_master_get_devdata(master);
+
+	pm_runtime_disable(&pdev->dev);
+
+	if (dln2_spi_enable(dln2, false) < 0)
+		dev_err(&pdev->dev, "Failed to disable SPI module\n");
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int dln2_spi_suspend(struct device *dev)
+{
+	int ret;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct dln2_spi *dln2 = spi_master_get_devdata(master);
+
+	ret = spi_master_suspend(master);
+	if (ret < 0)
+		return ret;
+
+	if (!pm_runtime_suspended(dev)) {
+		ret = dln2_spi_enable(dln2, false);
+		if (ret < 0)
+			return ret;
+	}
+
+	/*
+	 * USB power may be cut off during sleep. Resetting the following
+	 * parameters will force the board to be set up before first transfer.
+	 */
+	dln2->cs = 0xff;
+	dln2->speed = 0;
+	dln2->bpw = 0;
+	dln2->mode = 0xff;
+
+	return 0;
+}
+
+static int dln2_spi_resume(struct device *dev)
+{
+	int ret;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct dln2_spi *dln2 = spi_master_get_devdata(master);
+
+	if (!pm_runtime_suspended(dev)) {
+		ret = dln2_spi_cs_enable_all(dln2, true);
+		if (ret < 0)
+			return ret;
+
+		ret = dln2_spi_enable(dln2, true);
+		if (ret < 0)
+			return ret;
+	}
+
+	return spi_master_resume(master);
+}
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM
+static int dln2_spi_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct dln2_spi *dln2 = spi_master_get_devdata(master);
+
+	return dln2_spi_enable(dln2, false);
+}
+
+static int dln2_spi_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct dln2_spi *dln2 = spi_master_get_devdata(master);
+
+	return  dln2_spi_enable(dln2, true);
+}
+#endif /* CONFIG_PM */
+
+static const struct dev_pm_ops dln2_spi_pm = {
+	SET_SYSTEM_SLEEP_PM_OPS(dln2_spi_suspend, dln2_spi_resume)
+	SET_RUNTIME_PM_OPS(dln2_spi_runtime_suspend,
+			   dln2_spi_runtime_resume, NULL)
+};
+
+static struct platform_driver spi_dln2_driver = {
+	.driver = {
+		.name	= "dln2-spi",
+		.pm	= &dln2_spi_pm,
+	},
+	.probe		= dln2_spi_probe,
+	.remove		= dln2_spi_remove,
+};
+module_platform_driver(spi_dln2_driver);
+
+MODULE_DESCRIPTION("Driver for the Diolan DLN2 SPI master interface");
+MODULE_AUTHOR("Laurentiu Palcu <laurentiu.palcu@intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:dln2-spi");
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index a67d37c..a0197fd 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -247,9 +247,9 @@
 
 /* Some specific info for SPI0 controller on Intel MID */
 
-/* HW info for MRST CLk Control Unit, one 32b reg */
+/* HW info for MRST Clk Control Unit, 32b reg per controller */
 #define MRST_SPI_CLK_BASE	100000000	/* 100m */
-#define MRST_CLK_SPI0_REG	0xff11d86c
+#define MRST_CLK_SPI_REG	0xff11d86c
 #define CLK_SPI_BDIV_OFFSET	0
 #define CLK_SPI_BDIV_MASK	0x00000007
 #define CLK_SPI_CDIV_OFFSET	9
@@ -261,16 +261,17 @@
 	void __iomem *clk_reg;
 	u32 clk_cdiv;
 
-	clk_reg = ioremap_nocache(MRST_CLK_SPI0_REG, 16);
+	clk_reg = ioremap_nocache(MRST_CLK_SPI_REG, 16);
 	if (!clk_reg)
 		return -ENOMEM;
 
-	/* get SPI controller operating freq info */
-	clk_cdiv  = (readl(clk_reg) & CLK_SPI_CDIV_MASK) >> CLK_SPI_CDIV_OFFSET;
+	/* Get SPI controller operating freq info */
+	clk_cdiv = readl(clk_reg + dws->bus_num * sizeof(u32));
+	clk_cdiv &= CLK_SPI_CDIV_MASK;
+	clk_cdiv >>= CLK_SPI_CDIV_OFFSET;
 	dws->max_freq = MRST_SPI_CLK_BASE / (clk_cdiv + 1);
-	iounmap(clk_reg);
 
-	dws->num_cs = 16;
+	iounmap(clk_reg);
 
 #ifdef CONFIG_SPI_DW_MID_DMA
 	dws->dma_priv = kzalloc(sizeof(struct mid_dma), GFP_KERNEL);
diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c
index ba68da1..5ba3310 100644
--- a/drivers/spi/spi-dw-pci.c
+++ b/drivers/spi/spi-dw-pci.c
@@ -30,10 +30,20 @@
 
 struct spi_pci_desc {
 	int	(*setup)(struct dw_spi *);
+	u16	num_cs;
+	u16	bus_num;
 };
 
-static struct spi_pci_desc spi_pci_mid_desc = {
+static struct spi_pci_desc spi_pci_mid_desc_1 = {
 	.setup = dw_spi_mid_init,
+	.num_cs = 32,
+	.bus_num = 0,
+};
+
+static struct spi_pci_desc spi_pci_mid_desc_2 = {
+	.setup = dw_spi_mid_init,
+	.num_cs = 4,
+	.bus_num = 1,
 };
 
 static int spi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
@@ -65,18 +75,23 @@
 
 	dws->regs = pcim_iomap_table(pdev)[pci_bar];
 
-	dws->bus_num = 0;
-	dws->num_cs = 4;
 	dws->irq = pdev->irq;
 
 	/*
 	 * Specific handling for paltforms, like dma setup,
 	 * clock rate, FIFO depth.
 	 */
-	if (desc && desc->setup) {
-		ret = desc->setup(dws);
-		if (ret)
-			return ret;
+	if (desc) {
+		dws->num_cs = desc->num_cs;
+		dws->bus_num = desc->bus_num;
+
+		if (desc->setup) {
+			ret = desc->setup(dws);
+			if (ret)
+				return ret;
+		}
+	} else {
+		return -ENODEV;
 	}
 
 	ret = dw_spi_add_host(&pdev->dev, dws);
@@ -121,7 +136,14 @@
 
 static const struct pci_device_id pci_ids[] = {
 	/* Intel MID platform SPI controller 0 */
-	{ PCI_VDEVICE(INTEL, 0x0800), (kernel_ulong_t)&spi_pci_mid_desc},
+	/*
+	 * The access to the device 8086:0801 is disabled by HW, since it's
+	 * exclusively used by SCU to communicate with MSIC.
+	 */
+	/* Intel MID platform SPI controller 1 */
+	{ PCI_VDEVICE(INTEL, 0x0800), (kernel_ulong_t)&spi_pci_mid_desc_1},
+	/* Intel MID platform SPI controller 2 */
+	{ PCI_VDEVICE(INTEL, 0x0812), (kernel_ulong_t)&spi_pci_mid_desc_2},
 	{},
 };
 
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index 8edcd1b..5a97a62 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -608,7 +608,7 @@
 }
 
 /* Restart the controller, disable all interrupts, clean rx fifo */
-static void spi_hw_init(struct dw_spi *dws)
+static void spi_hw_init(struct device *dev, struct dw_spi *dws)
 {
 	spi_enable_chip(dws, 0);
 	spi_mask_intr(dws, 0xff);
@@ -626,9 +626,10 @@
 			if (fifo != dw_readw(dws, DW_SPI_TXFLTR))
 				break;
 		}
+		dw_writew(dws, DW_SPI_TXFLTR, 0);
 
 		dws->fifo_len = (fifo == 2) ? 0 : fifo - 1;
-		dw_writew(dws, DW_SPI_TXFLTR, 0);
+		dev_dbg(dev, "Detected FIFO size: %u bytes\n", dws->fifo_len);
 	}
 }
 
@@ -668,7 +669,7 @@
 	master->dev.of_node = dev->of_node;
 
 	/* Basic HW init */
-	spi_hw_init(dws);
+	spi_hw_init(dev, dws);
 
 	if (dws->dma_ops && dws->dma_ops->dma_init) {
 		ret = dws->dma_ops->dma_init(dws);
@@ -731,7 +732,7 @@
 {
 	int ret;
 
-	spi_hw_init(dws);
+	spi_hw_init(&dws->master->dev, dws);
 	ret = spi_master_resume(dws->master);
 	if (ret)
 		dev_err(&dws->master->dev, "fail to start queue (%d)\n", ret);
diff --git a/drivers/spi/spi-falcon.c b/drivers/spi/spi-falcon.c
index 912b903..286b2c8 100644
--- a/drivers/spi/spi-falcon.c
+++ b/drivers/spi/spi-falcon.c
@@ -353,16 +353,6 @@
 	return 0;
 }
 
-static int falcon_sflash_prepare_xfer(struct spi_master *master)
-{
-	return 0;
-}
-
-static int falcon_sflash_unprepare_xfer(struct spi_master *master)
-{
-	return 0;
-}
-
 static int falcon_sflash_xfer_one(struct spi_master *master,
 					struct spi_message *m)
 {
@@ -420,9 +410,7 @@
 	master->mode_bits = SPI_MODE_3;
 	master->flags = SPI_MASTER_HALF_DUPLEX;
 	master->setup = falcon_sflash_setup;
-	master->prepare_transfer_hardware = falcon_sflash_prepare_xfer;
 	master->transfer_one_message = falcon_sflash_xfer_one;
-	master->unprepare_transfer_hardware = falcon_sflash_unprepare_xfer;
 	master->dev.of_node = pdev->dev.of_node;
 
 	ret = devm_spi_register_master(&pdev->dev, master);
diff --git a/drivers/spi/spi-fsl-cpm.c b/drivers/spi/spi-fsl-cpm.c
index e85ab1c..9c46a30 100644
--- a/drivers/spi/spi-fsl-cpm.c
+++ b/drivers/spi/spi-fsl-cpm.c
@@ -20,6 +20,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/fsl_devices.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/spi/spi.h>
 #include <linux/types.h>
@@ -68,6 +69,7 @@
 		}
 	}
 }
+EXPORT_SYMBOL_GPL(fsl_spi_cpm_reinit_txrx);
 
 static void fsl_spi_cpm_bufs_start(struct mpc8xxx_spi *mspi)
 {
@@ -162,6 +164,7 @@
 		dma_unmap_single(dev, mspi->tx_dma, t->len, DMA_TO_DEVICE);
 	return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(fsl_spi_cpm_bufs);
 
 void fsl_spi_cpm_bufs_complete(struct mpc8xxx_spi *mspi)
 {
@@ -174,6 +177,7 @@
 		dma_unmap_single(dev, mspi->rx_dma, t->len, DMA_FROM_DEVICE);
 	mspi->xfer_in_progress = NULL;
 }
+EXPORT_SYMBOL_GPL(fsl_spi_cpm_bufs_complete);
 
 void fsl_spi_cpm_irq(struct mpc8xxx_spi *mspi, u32 events)
 {
@@ -198,6 +202,7 @@
 	else
 		complete(&mspi->done);
 }
+EXPORT_SYMBOL_GPL(fsl_spi_cpm_irq);
 
 static void *fsl_spi_alloc_dummy_rx(void)
 {
@@ -375,6 +380,7 @@
 	fsl_spi_free_dummy_rx();
 	return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(fsl_spi_cpm_init);
 
 void fsl_spi_cpm_free(struct mpc8xxx_spi *mspi)
 {
@@ -389,3 +395,6 @@
 	cpm_muram_free(cpm_muram_offset(mspi->pram));
 	fsl_spi_free_dummy_rx();
 }
+EXPORT_SYMBOL_GPL(fsl_spi_cpm_free);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 4cda994..d1a3924 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -106,7 +106,7 @@
 };
 
 struct fsl_dspi {
-	struct spi_bitbang	bitbang;
+	struct spi_master	*master;
 	struct platform_device	*pdev;
 
 	struct regmap		*regmap;
@@ -114,6 +114,7 @@
 	struct clk		*clk;
 
 	struct spi_transfer	*cur_transfer;
+	struct spi_message	*cur_msg;
 	struct chip_data	*cur_chip;
 	size_t			len;
 	void			*tx;
@@ -123,6 +124,7 @@
 	char			dataflags;
 	u8			cs;
 	u16			void_write_data;
+	u32			cs_change;
 
 	wait_queue_head_t	waitq;
 	u32			waitflags;
@@ -225,6 +227,8 @@
 		if (dspi->len == 0 || tx_count == DSPI_FIFO_SIZE - 1) {
 			/* last transfer in the transfer */
 			dspi_pushr |= SPI_PUSHR_EOQ;
+			if ((dspi->cs_change) && (!dspi->len))
+				dspi_pushr &= ~SPI_PUSHR_CONT;
 		} else if (tx_word && (dspi->len == 1))
 			dspi_pushr |= SPI_PUSHR_EOQ;
 
@@ -246,6 +250,7 @@
 	int rx_count = 0;
 	int rx_word = is_double_byte_mode(dspi);
 	u16 d;
+
 	while ((dspi->rx < dspi->rx_end)
 			&& (rx_count < DSPI_FIFO_SIZE)) {
 		if (rx_word) {
@@ -276,80 +281,72 @@
 	return rx_count;
 }
 
-static int dspi_txrx_transfer(struct spi_device *spi, struct spi_transfer *t)
+static int dspi_transfer_one_message(struct spi_master *master,
+		struct spi_message *message)
 {
-	struct fsl_dspi *dspi = spi_master_get_devdata(spi->master);
-	dspi->cur_transfer = t;
-	dspi->cur_chip = spi_get_ctldata(spi);
-	dspi->cs = spi->chip_select;
-	dspi->void_write_data = dspi->cur_chip->void_write_data;
+	struct fsl_dspi *dspi = spi_master_get_devdata(master);
+	struct spi_device *spi = message->spi;
+	struct spi_transfer *transfer;
+	int status = 0;
+	message->actual_length = 0;
 
-	dspi->dataflags = 0;
-	dspi->tx = (void *)t->tx_buf;
-	dspi->tx_end = dspi->tx + t->len;
-	dspi->rx = t->rx_buf;
-	dspi->rx_end = dspi->rx + t->len;
-	dspi->len = t->len;
+	list_for_each_entry(transfer, &message->transfers, transfer_list) {
+		dspi->cur_transfer = transfer;
+		dspi->cur_msg = message;
+		dspi->cur_chip = spi_get_ctldata(spi);
+		dspi->cs = spi->chip_select;
+		if (dspi->cur_transfer->transfer_list.next
+				== &dspi->cur_msg->transfers)
+			transfer->cs_change = 1;
+		dspi->cs_change = transfer->cs_change;
+		dspi->void_write_data = dspi->cur_chip->void_write_data;
 
-	if (!dspi->rx)
-		dspi->dataflags |= TRAN_STATE_RX_VOID;
+		dspi->dataflags = 0;
+		dspi->tx = (void *)transfer->tx_buf;
+		dspi->tx_end = dspi->tx + transfer->len;
+		dspi->rx = transfer->rx_buf;
+		dspi->rx_end = dspi->rx + transfer->len;
+		dspi->len = transfer->len;
 
-	if (!dspi->tx)
-		dspi->dataflags |= TRAN_STATE_TX_VOID;
+		if (!dspi->rx)
+			dspi->dataflags |= TRAN_STATE_RX_VOID;
 
-	regmap_write(dspi->regmap, SPI_MCR, dspi->cur_chip->mcr_val);
-	regmap_write(dspi->regmap, SPI_CTAR(dspi->cs), dspi->cur_chip->ctar_val);
-	regmap_write(dspi->regmap, SPI_RSER, SPI_RSER_EOQFE);
+		if (!dspi->tx)
+			dspi->dataflags |= TRAN_STATE_TX_VOID;
 
-	if (t->speed_hz)
+		regmap_write(dspi->regmap, SPI_MCR, dspi->cur_chip->mcr_val);
+		regmap_update_bits(dspi->regmap, SPI_MCR,
+				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
+				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
 		regmap_write(dspi->regmap, SPI_CTAR(dspi->cs),
 				dspi->cur_chip->ctar_val);
+		if (transfer->speed_hz)
+			regmap_write(dspi->regmap, SPI_CTAR(dspi->cs),
+					dspi->cur_chip->ctar_val);
 
-	dspi_transfer_write(dspi);
+		regmap_write(dspi->regmap, SPI_RSER, SPI_RSER_EOQFE);
+		message->actual_length += dspi_transfer_write(dspi);
 
-	if (wait_event_interruptible(dspi->waitq, dspi->waitflags))
-		dev_err(&dspi->pdev->dev, "wait transfer complete fail!\n");
-	dspi->waitflags = 0;
+		if (wait_event_interruptible(dspi->waitq, dspi->waitflags))
+			dev_err(&dspi->pdev->dev, "wait transfer complete fail!\n");
+		dspi->waitflags = 0;
 
-	return t->len - dspi->len;
-}
-
-static void dspi_chipselect(struct spi_device *spi, int value)
-{
-	struct fsl_dspi *dspi = spi_master_get_devdata(spi->master);
-	unsigned int pushr;
-
-	regmap_read(dspi->regmap, SPI_PUSHR, &pushr);
-
-	switch (value) {
-	case BITBANG_CS_ACTIVE:
-		pushr |= SPI_PUSHR_CONT;
-		break;
-	case BITBANG_CS_INACTIVE:
-		pushr &= ~SPI_PUSHR_CONT;
-		break;
+		if (transfer->delay_usecs)
+			udelay(transfer->delay_usecs);
 	}
 
-	regmap_write(dspi->regmap, SPI_PUSHR, pushr);
+	message->status = status;
+	spi_finalize_current_message(master);
+
+	return status;
 }
 
-static int dspi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
+static int dspi_setup(struct spi_device *spi)
 {
 	struct chip_data *chip;
 	struct fsl_dspi *dspi = spi_master_get_devdata(spi->master);
 	unsigned char br = 0, pbr = 0, fmsz = 0;
 
-	/* Only alloc on first setup */
-	chip = spi_get_ctldata(spi);
-	if (chip == NULL) {
-		chip = devm_kzalloc(&spi->dev, sizeof(struct chip_data),
-				    GFP_KERNEL);
-		if (!chip)
-			return -ENOMEM;
-	}
-
-	chip->mcr_val = SPI_MCR_MASTER | SPI_MCR_PCSIS |
-		SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF;
 	if ((spi->bits_per_word >= 4) && (spi->bits_per_word <= 16)) {
 		fmsz = spi->bits_per_word - 1;
 	} else {
@@ -357,6 +354,17 @@
 		return -ENODEV;
 	}
 
+	/* Only alloc on first setup */
+	chip = spi_get_ctldata(spi);
+	if (chip == NULL) {
+		chip = kzalloc(sizeof(struct chip_data), GFP_KERNEL);
+		if (!chip)
+			return -ENOMEM;
+	}
+
+	chip->mcr_val = SPI_MCR_MASTER | SPI_MCR_PCSIS |
+		SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF;
+
 	chip->void_write_data = 0;
 
 	hz_to_spi_baud(&pbr, &br,
@@ -374,34 +382,34 @@
 	return 0;
 }
 
-static int dspi_setup(struct spi_device *spi)
+static void dspi_cleanup(struct spi_device *spi)
 {
-	if (!spi->max_speed_hz)
-		return -EINVAL;
+	struct chip_data *chip = spi_get_ctldata((struct spi_device *)spi);
 
-	return dspi_setup_transfer(spi, NULL);
+	dev_dbg(&spi->dev, "spi_device %u.%u cleanup\n",
+			spi->master->bus_num, spi->chip_select);
+
+	kfree(chip);
 }
 
 static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 {
 	struct fsl_dspi *dspi = (struct fsl_dspi *)dev_id;
 
-	regmap_write(dspi->regmap, SPI_SR, SPI_SR_EOQF);
+	struct spi_message *msg = dspi->cur_msg;
 
+	regmap_write(dspi->regmap, SPI_SR, SPI_SR_EOQF);
 	dspi_transfer_read(dspi);
 
 	if (!dspi->len) {
 		if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM)
 			regmap_update_bits(dspi->regmap, SPI_CTAR(dspi->cs),
-				SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(16));
+			SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(16));
 
 		dspi->waitflags = 1;
 		wake_up_interruptible(&dspi->waitq);
-	} else {
-		dspi_transfer_write(dspi);
-
-		return IRQ_HANDLED;
-	}
+	} else
+		msg->actual_length += dspi_transfer_write(dspi);
 
 	return IRQ_HANDLED;
 }
@@ -460,13 +468,14 @@
 
 	dspi = spi_master_get_devdata(master);
 	dspi->pdev = pdev;
-	dspi->bitbang.master = master;
-	dspi->bitbang.chipselect = dspi_chipselect;
-	dspi->bitbang.setup_transfer = dspi_setup_transfer;
-	dspi->bitbang.txrx_bufs = dspi_txrx_transfer;
-	dspi->bitbang.master->setup = dspi_setup;
-	dspi->bitbang.master->dev.of_node = pdev->dev.of_node;
+	dspi->master = master;
 
+	master->transfer = NULL;
+	master->setup = dspi_setup;
+	master->transfer_one_message = dspi_transfer_one_message;
+	master->dev.of_node = pdev->dev.of_node;
+
+	master->cleanup = dspi_cleanup;
 	master->mode_bits = SPI_CPOL | SPI_CPHA;
 	master->bits_per_word_mask = SPI_BPW_MASK(4) | SPI_BPW_MASK(8) |
 					SPI_BPW_MASK(16);
@@ -525,7 +534,7 @@
 	init_waitqueue_head(&dspi->waitq);
 	platform_set_drvdata(pdev, master);
 
-	ret = spi_bitbang_start(&dspi->bitbang);
+	ret = spi_register_master(master);
 	if (ret != 0) {
 		dev_err(&pdev->dev, "Problem registering DSPI master\n");
 		goto out_clk_put;
@@ -547,9 +556,9 @@
 	struct fsl_dspi *dspi = spi_master_get_devdata(master);
 
 	/* Disconnect from the SPI framework */
-	spi_bitbang_stop(&dspi->bitbang);
 	clk_disable_unprepare(dspi->clk);
-	spi_master_put(dspi->bitbang.master);
+	spi_unregister_master(dspi->master);
+	spi_master_put(dspi->master);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-fsl-lib.c b/drivers/spi/spi-fsl-lib.c
index 446b737..cb35d2f 100644
--- a/drivers/spi/spi-fsl-lib.c
+++ b/drivers/spi/spi-fsl-lib.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/module.h>
 #include <linux/of_platform.h>
 #include <linux/spi/spi.h>
 #ifdef CONFIG_FSL_SOC
@@ -35,7 +36,8 @@
 	type *rx = mpc8xxx_spi->rx;					  \
 	*rx++ = (type)(data >> mpc8xxx_spi->rx_shift);			  \
 	mpc8xxx_spi->rx = rx;						  \
-}
+}									  \
+EXPORT_SYMBOL_GPL(mpc8xxx_spi_rx_buf_##type);
 
 #define MPC8XXX_SPI_TX_BUF(type)				\
 u32 mpc8xxx_spi_tx_buf_##type(struct mpc8xxx_spi *mpc8xxx_spi)	\
@@ -47,7 +49,8 @@
 	data = *tx++ << mpc8xxx_spi->tx_shift;			\
 	mpc8xxx_spi->tx = tx;					\
 	return data;						\
-}
+}								\
+EXPORT_SYMBOL_GPL(mpc8xxx_spi_tx_buf_##type);
 
 MPC8XXX_SPI_RX_BUF(u8)
 MPC8XXX_SPI_RX_BUF(u16)
@@ -60,6 +63,7 @@
 {
 	return container_of(pdata, struct mpc8xxx_spi_probe_info, pdata);
 }
+EXPORT_SYMBOL_GPL(to_of_pinfo);
 
 const char *mpc8xxx_spi_strmode(unsigned int flags)
 {
@@ -75,6 +79,7 @@
 	}
 	return "CPU";
 }
+EXPORT_SYMBOL_GPL(mpc8xxx_spi_strmode);
 
 void mpc8xxx_spi_probe(struct device *dev, struct resource *mem,
 			unsigned int irq)
@@ -102,13 +107,12 @@
 	mpc8xxx_spi->rx_shift = 0;
 	mpc8xxx_spi->tx_shift = 0;
 
-	init_completion(&mpc8xxx_spi->done);
-
 	master->bus_num = pdata->bus_num;
 	master->num_chipselect = pdata->max_chipselect;
 
 	init_completion(&mpc8xxx_spi->done);
 }
+EXPORT_SYMBOL_GPL(mpc8xxx_spi_probe);
 
 int mpc8xxx_spi_remove(struct device *dev)
 {
@@ -127,6 +131,7 @@
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mpc8xxx_spi_remove);
 
 int of_mpc8xxx_spi_probe(struct platform_device *ofdev)
 {
@@ -173,3 +178,6 @@
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(of_mpc8xxx_spi_probe);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-fsl-lib.h b/drivers/spi/spi-fsl-lib.h
index b4ed04e..1326a39 100644
--- a/drivers/spi/spi-fsl-lib.h
+++ b/drivers/spi/spi-fsl-lib.h
@@ -28,7 +28,7 @@
 	/* rx & tx bufs from the spi_transfer */
 	const void *tx;
 	void *rx;
-#ifdef CONFIG_SPI_FSL_ESPI
+#if IS_ENABLED(CONFIG_SPI_FSL_ESPI)
 	int len;
 #endif
 
@@ -68,7 +68,7 @@
 
 	unsigned int flags;
 
-#ifdef CONFIG_SPI_FSL_SPI
+#if IS_ENABLED(CONFIG_SPI_FSL_SPI)
 	int type;
 	int native_chipselects;
 	u8 max_bits_per_word;
diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c
index aee4e75..1c34c93 100644
--- a/drivers/spi/spi-gpio.c
+++ b/drivers/spi/spi-gpio.c
@@ -12,10 +12,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -92,7 +88,7 @@
 
 /*----------------------------------------------------------------------*/
 
-static inline struct spi_gpio * __pure
+static inline struct spi_gpio *__pure
 spi_to_spi_gpio(const struct spi_device *spi)
 {
 	const struct spi_bitbang	*bang;
@@ -103,7 +99,7 @@
 	return spi_gpio;
 }
 
-static inline struct spi_gpio_platform_data * __pure
+static inline struct spi_gpio_platform_data *__pure
 spi_to_pdata(const struct spi_device *spi)
 {
 	return &spi_to_spi_gpio(spi)->pdata;
diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c
index aad6683..c01567d 100644
--- a/drivers/spi/spi-img-spfi.c
+++ b/drivers/spi/spi-img-spfi.c
@@ -160,16 +160,16 @@
 	unsigned int count = 0;
 	u32 status;
 
-	while (count < max) {
+	while (count < max / 4) {
 		spfi_writel(spfi, SPFI_INTERRUPT_SDFUL, SPFI_INTERRUPT_CLEAR);
 		status = spfi_readl(spfi, SPFI_INTERRUPT_STATUS);
 		if (status & SPFI_INTERRUPT_SDFUL)
 			break;
-		spfi_writel(spfi, buf[count / 4], SPFI_TX_32BIT_VALID_DATA);
-		count += 4;
+		spfi_writel(spfi, buf[count], SPFI_TX_32BIT_VALID_DATA);
+		count++;
 	}
 
-	return count;
+	return count * 4;
 }
 
 static unsigned int spfi_pio_write8(struct img_spfi *spfi, const u8 *buf,
@@ -196,17 +196,17 @@
 	unsigned int count = 0;
 	u32 status;
 
-	while (count < max) {
+	while (count < max / 4) {
 		spfi_writel(spfi, SPFI_INTERRUPT_GDEX32BIT,
 			    SPFI_INTERRUPT_CLEAR);
 		status = spfi_readl(spfi, SPFI_INTERRUPT_STATUS);
 		if (!(status & SPFI_INTERRUPT_GDEX32BIT))
 			break;
-		buf[count / 4] = spfi_readl(spfi, SPFI_RX_32BIT_VALID_DATA);
-		count += 4;
+		buf[count] = spfi_readl(spfi, SPFI_RX_32BIT_VALID_DATA);
+		count++;
 	}
 
-	return count;
+	return count * 4;
 }
 
 static unsigned int spfi_pio_read8(struct img_spfi *spfi, u8 *buf,
@@ -251,17 +251,15 @@
 	       time_before(jiffies, timeout)) {
 		unsigned int tx_count, rx_count;
 
-		switch (xfer->bits_per_word) {
-		case 32:
+		if (tx_bytes >= 4)
 			tx_count = spfi_pio_write32(spfi, tx_buf, tx_bytes);
-			rx_count = spfi_pio_read32(spfi, rx_buf, rx_bytes);
-			break;
-		case 8:
-		default:
+		else
 			tx_count = spfi_pio_write8(spfi, tx_buf, tx_bytes);
+
+		if (rx_bytes >= 4)
+			rx_count = spfi_pio_read32(spfi, rx_buf, rx_bytes);
+		else
 			rx_count = spfi_pio_read8(spfi, rx_buf, rx_bytes);
-			break;
-		}
 
 		tx_buf += tx_count;
 		rx_buf += rx_count;
@@ -331,14 +329,11 @@
 
 	if (xfer->rx_buf) {
 		rxconf.direction = DMA_DEV_TO_MEM;
-		switch (xfer->bits_per_word) {
-		case 32:
+		if (xfer->len % 4 == 0) {
 			rxconf.src_addr = spfi->phys + SPFI_RX_32BIT_VALID_DATA;
 			rxconf.src_addr_width = 4;
 			rxconf.src_maxburst = 4;
-			break;
-		case 8:
-		default:
+		} else {
 			rxconf.src_addr = spfi->phys + SPFI_RX_8BIT_VALID_DATA;
 			rxconf.src_addr_width = 1;
 			rxconf.src_maxburst = 4;
@@ -358,18 +353,14 @@
 
 	if (xfer->tx_buf) {
 		txconf.direction = DMA_MEM_TO_DEV;
-		switch (xfer->bits_per_word) {
-		case 32:
+		if (xfer->len % 4 == 0) {
 			txconf.dst_addr = spfi->phys + SPFI_TX_32BIT_VALID_DATA;
 			txconf.dst_addr_width = 4;
 			txconf.dst_maxburst = 4;
-			break;
-		case 8:
-		default:
+		} else {
 			txconf.dst_addr = spfi->phys + SPFI_TX_8BIT_VALID_DATA;
 			txconf.dst_addr_width = 1;
 			txconf.dst_maxburst = 4;
-			break;
 		}
 		dmaengine_slave_config(spfi->tx_ch, &txconf);
 
@@ -508,9 +499,7 @@
 static bool img_spfi_can_dma(struct spi_master *master, struct spi_device *spi,
 			     struct spi_transfer *xfer)
 {
-	if (xfer->bits_per_word == 8 && xfer->len > SPFI_8BIT_FIFO_SIZE)
-		return true;
-	if (xfer->bits_per_word == 32 && xfer->len > SPFI_32BIT_FIFO_SIZE)
+	if (xfer->len > SPFI_32BIT_FIFO_SIZE)
 		return true;
 	return false;
 }
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 961b97d..6fea4af 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -89,7 +89,6 @@
 
 	struct completion xfer_done;
 	void __iomem *base;
-	int irq;
 	struct clk *clk_per;
 	struct clk *clk_ipg;
 	unsigned long spi_clk;
@@ -823,6 +822,10 @@
 	struct dma_slave_config slave_config = {};
 	int ret;
 
+	/* use pio mode for i.mx6dl chip TKT238285 */
+	if (of_machine_is_compatible("fsl,imx6dl"))
+		return 0;
+
 	/* Prepare for TX DMA: */
 	master->dma_tx = dma_request_slave_channel(dev, "tx");
 	if (!master->dma_tx) {
@@ -892,6 +895,7 @@
 {
 	struct dma_async_tx_descriptor *desc_tx = NULL, *desc_rx = NULL;
 	int ret;
+	unsigned long timeout;
 	u32 dma;
 	int left;
 	struct spi_master *master = spi_imx->bitbang.master;
@@ -939,17 +943,17 @@
 	dma_async_issue_pending(master->dma_tx);
 	dma_async_issue_pending(master->dma_rx);
 	/* Wait SDMA to finish the data transfer.*/
-	ret = wait_for_completion_timeout(&spi_imx->dma_tx_completion,
+	timeout = wait_for_completion_timeout(&spi_imx->dma_tx_completion,
 						IMX_DMA_TIMEOUT);
-	if (!ret) {
+	if (!timeout) {
 		pr_warn("%s %s: I/O Error in DMA TX\n",
 			dev_driver_string(&master->dev),
 			dev_name(&master->dev));
 		dmaengine_terminate_all(master->dma_tx);
 	} else {
-		ret = wait_for_completion_timeout(&spi_imx->dma_rx_completion,
-				IMX_DMA_TIMEOUT);
-		if (!ret) {
+		timeout = wait_for_completion_timeout(
+				&spi_imx->dma_rx_completion, IMX_DMA_TIMEOUT);
+		if (!timeout) {
 			pr_warn("%s %s: I/O Error in DMA RX\n",
 				dev_driver_string(&master->dev),
 				dev_name(&master->dev));
@@ -964,9 +968,9 @@
 	spi_imx->dma_finished = 1;
 	spi_imx->devtype_data->trigger(spi_imx);
 
-	if (!ret)
+	if (!timeout)
 		ret = -ETIMEDOUT;
-	else if (ret > 0)
+	else
 		ret = transfer->len;
 
 	return ret;
@@ -1076,7 +1080,7 @@
 	struct spi_master *master;
 	struct spi_imx_data *spi_imx;
 	struct resource *res;
-	int i, ret, num_cs;
+	int i, ret, num_cs, irq;
 
 	if (!np && !mxc_platform_info) {
 		dev_err(&pdev->dev, "can't get the platform data\n");
@@ -1143,16 +1147,16 @@
 		goto out_master_put;
 	}
 
-	spi_imx->irq = platform_get_irq(pdev, 0);
-	if (spi_imx->irq < 0) {
-		ret = spi_imx->irq;
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		ret = irq;
 		goto out_master_put;
 	}
 
-	ret = devm_request_irq(&pdev->dev, spi_imx->irq, spi_imx_isr, 0,
+	ret = devm_request_irq(&pdev->dev, irq, spi_imx_isr, 0,
 			       dev_name(&pdev->dev), spi_imx);
 	if (ret) {
-		dev_err(&pdev->dev, "can't get irq%d: %d\n", spi_imx->irq, ret);
+		dev_err(&pdev->dev, "can't get irq%d: %d\n", irq, ret);
 		goto out_master_put;
 	}
 
diff --git a/drivers/spi/spi-lm70llp.c b/drivers/spi/spi-lm70llp.c
index 41c5765..ba72347 100644
--- a/drivers/spi/spi-lm70llp.c
+++ b/drivers/spi/spi-lm70llp.c
@@ -12,10 +12,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
diff --git a/drivers/spi/spi-meson-spifc.c b/drivers/spi/spi-meson-spifc.c
index 1bbac03..5468fc7 100644
--- a/drivers/spi/spi-meson-spifc.c
+++ b/drivers/spi/spi-meson-spifc.c
@@ -85,7 +85,7 @@
 	struct device *dev;
 };
 
-static struct regmap_config spifc_regmap_config = {
+static const struct regmap_config spifc_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
 	.reg_stride = 4,
diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c
index 4045a1e..5b0e9a3 100644
--- a/drivers/spi/spi-mxs.c
+++ b/drivers/spi/spi-mxs.c
@@ -282,9 +282,8 @@
 	dmaengine_submit(desc);
 	dma_async_issue_pending(ssp->dmach);
 
-	ret = wait_for_completion_timeout(&spi->c,
-				msecs_to_jiffies(SSP_TIMEOUT));
-	if (!ret) {
+	if (!wait_for_completion_timeout(&spi->c,
+					 msecs_to_jiffies(SSP_TIMEOUT))) {
 		dev_err(ssp->dev, "DMA transfer timeout\n");
 		ret = -ETIMEDOUT;
 		dmaengine_terminate_all(ssp->dmach);
diff --git a/drivers/spi/spi-omap-100k.c b/drivers/spi/spi-omap-100k.c
index 79399ae..d890d30 100644
--- a/drivers/spi/spi-omap-100k.c
+++ b/drivers/spi/spi-omap-100k.c
@@ -16,11 +16,6 @@
  * 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
- *
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c
index daf1ada..3c08444 100644
--- a/drivers/spi/spi-omap-uwire.c
+++ b/drivers/spi/spi-omap-uwire.c
@@ -28,10 +28,6 @@
  * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
  * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 3bc3cba..4df8942 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -14,11 +14,6 @@
  * 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
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 3dec9e0..8616647 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -28,7 +28,12 @@
 /* Runtime PM autosuspend timeout: PM is fairly light on this driver */
 #define SPI_AUTOSUSPEND_TIMEOUT		200
 
-#define ORION_NUM_CHIPSELECTS		1 /* only one slave is supported*/
+/* Some SoCs using this driver support up to 8 chip selects.
+ * It is up to the implementer to only use the chip selects
+ * that are available.
+ */
+#define ORION_NUM_CHIPSELECTS		8
+
 #define ORION_SPI_WAIT_RDY_MAX_LOOP	2000 /* in usec */
 
 #define ORION_SPI_IF_CTRL_REG		0x00
@@ -44,6 +49,10 @@
 #define ARMADA_SPI_CLK_PRESCALE_MASK	0xDF
 #define ORION_SPI_MODE_MASK		(ORION_SPI_MODE_CPOL | \
 					 ORION_SPI_MODE_CPHA)
+#define ORION_SPI_CS_MASK	0x1C
+#define ORION_SPI_CS_SHIFT	2
+#define ORION_SPI_CS(cs)	((cs << ORION_SPI_CS_SHIFT) & \
+					ORION_SPI_CS_MASK)
 
 enum orion_spi_type {
 	ORION_SPI,
@@ -215,9 +224,18 @@
 	return 0;
 }
 
-static void orion_spi_set_cs(struct orion_spi *orion_spi, int enable)
+static void orion_spi_set_cs(struct spi_device *spi, bool enable)
 {
-	if (enable)
+	struct orion_spi *orion_spi;
+
+	orion_spi = spi_master_get_devdata(spi->master);
+
+	orion_spi_clrbits(orion_spi, ORION_SPI_IF_CTRL_REG, ORION_SPI_CS_MASK);
+	orion_spi_setbits(orion_spi, ORION_SPI_IF_CTRL_REG,
+				ORION_SPI_CS(spi->chip_select));
+
+	/* Chip select logic is inverted from spi_set_cs */
+	if (!enable)
 		orion_spi_setbits(orion_spi, ORION_SPI_IF_CTRL_REG, 0x1);
 	else
 		orion_spi_clrbits(orion_spi, ORION_SPI_IF_CTRL_REG, 0x1);
@@ -332,64 +350,31 @@
 	return xfer->len - count;
 }
 
-static int orion_spi_transfer_one_message(struct spi_master *master,
-					   struct spi_message *m)
+static int orion_spi_transfer_one(struct spi_master *master,
+					struct spi_device *spi,
+					struct spi_transfer *t)
 {
-	struct orion_spi *orion_spi = spi_master_get_devdata(master);
-	struct spi_device *spi = m->spi;
-	struct spi_transfer *t = NULL;
-	int par_override = 0;
 	int status = 0;
-	int cs_active = 0;
 
-	/* Load defaults */
-	status = orion_spi_setup_transfer(spi, NULL);
-
+	status = orion_spi_setup_transfer(spi, t);
 	if (status < 0)
-		goto msg_done;
+		return status;
 
-	list_for_each_entry(t, &m->transfers, transfer_list) {
-		if (par_override || t->speed_hz || t->bits_per_word) {
-			par_override = 1;
-			status = orion_spi_setup_transfer(spi, t);
-			if (status < 0)
-				break;
-			if (!t->speed_hz && !t->bits_per_word)
-				par_override = 0;
-		}
+	if (t->len)
+		orion_spi_write_read(spi, t);
 
-		if (!cs_active) {
-			orion_spi_set_cs(orion_spi, 1);
-			cs_active = 1;
-		}
+	return status;
+}
 
-		if (t->len)
-			m->actual_length += orion_spi_write_read(spi, t);
-
-		if (t->delay_usecs)
-			udelay(t->delay_usecs);
-
-		if (t->cs_change) {
-			orion_spi_set_cs(orion_spi, 0);
-			cs_active = 0;
-		}
-	}
-
-msg_done:
-	if (cs_active)
-		orion_spi_set_cs(orion_spi, 0);
-
-	m->status = status;
-	spi_finalize_current_message(master);
-
-	return 0;
+static int orion_spi_setup(struct spi_device *spi)
+{
+	return orion_spi_setup_transfer(spi, NULL);
 }
 
 static int orion_spi_reset(struct orion_spi *orion_spi)
 {
 	/* Verify that the CS is deasserted */
-	orion_spi_set_cs(orion_spi, 0);
-
+	orion_spi_clrbits(orion_spi, ORION_SPI_IF_CTRL_REG, 0x1);
 	return 0;
 }
 
@@ -442,9 +427,10 @@
 
 	/* we support only mode 0, and no options */
 	master->mode_bits = SPI_CPHA | SPI_CPOL;
-
-	master->transfer_one_message = orion_spi_transfer_one_message;
+	master->set_cs = orion_spi_set_cs;
+	master->transfer_one = orion_spi_transfer_one;
 	master->num_chipselect = ORION_NUM_CHIPSELECTS;
+	master->setup = orion_spi_setup;
 	master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
 	master->auto_runtime_pm = true;
 
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index 62a9297..66a1739 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -111,23 +111,24 @@
 	 * by using ->dma_running.
 	 */
 	if (atomic_dec_and_test(&drv_data->dma_running)) {
-		void __iomem *reg = drv_data->ioaddr;
-
 		/*
 		 * If the other CPU is still handling the ROR interrupt we
 		 * might not know about the error yet. So we re-check the
 		 * ROR bit here before we clear the status register.
 		 */
 		if (!error) {
-			u32 status = read_SSSR(reg) & drv_data->mask_sr;
+			u32 status = pxa2xx_spi_read(drv_data, SSSR)
+				     & drv_data->mask_sr;
 			error = status & SSSR_ROR;
 		}
 
 		/* Clear status & disable interrupts */
-		write_SSCR1(read_SSCR1(reg) & ~drv_data->dma_cr1, reg);
+		pxa2xx_spi_write(drv_data, SSCR1,
+				 pxa2xx_spi_read(drv_data, SSCR1)
+				 & ~drv_data->dma_cr1);
 		write_SSSR_CS(drv_data, drv_data->clear_sr);
 		if (!pxa25x_ssp_comp(drv_data))
-			write_SSTO(0, reg);
+			pxa2xx_spi_write(drv_data, SSTO, 0);
 
 		if (!error) {
 			pxa2xx_spi_unmap_dma_buffers(drv_data);
@@ -139,7 +140,9 @@
 			msg->state = pxa2xx_spi_next_transfer(drv_data);
 		} else {
 			/* In case we got an error we disable the SSP now */
-			write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg);
+			pxa2xx_spi_write(drv_data, SSCR0,
+					 pxa2xx_spi_read(drv_data, SSCR0)
+					 & ~SSCR0_SSE);
 
 			msg->state = ERROR_STATE;
 		}
@@ -247,7 +250,7 @@
 {
 	u32 status;
 
-	status = read_SSSR(drv_data->ioaddr) & drv_data->mask_sr;
+	status = pxa2xx_spi_read(drv_data, SSSR) & drv_data->mask_sr;
 	if (status & SSSR_ROR) {
 		dev_err(&drv_data->pdev->dev, "FIFO overrun\n");
 
diff --git a/drivers/spi/spi-pxa2xx-pxadma.c b/drivers/spi/spi-pxa2xx-pxadma.c
index e8a26f2..2e0796a 100644
--- a/drivers/spi/spi-pxa2xx-pxadma.c
+++ b/drivers/spi/spi-pxa2xx-pxadma.c
@@ -12,10 +12,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/delay.h>
@@ -25,6 +21,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/pxa2xx_spi.h>
 
+#include <mach/dma.h>
 #include "spi-pxa2xx.h"
 
 #define DMA_INT_MASK		(DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR)
@@ -118,11 +115,11 @@
 	drv_data->dma_mapped = 0;
 }
 
-static int wait_ssp_rx_stall(void const __iomem *ioaddr)
+static int wait_ssp_rx_stall(struct driver_data *drv_data)
 {
 	unsigned long limit = loops_per_jiffy << 1;
 
-	while ((read_SSSR(ioaddr) & SSSR_BSY) && --limit)
+	while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_BSY) && --limit)
 		cpu_relax();
 
 	return limit;
@@ -141,17 +138,18 @@
 static void pxa2xx_spi_dma_error_stop(struct driver_data *drv_data,
 				      const char *msg)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
 	/* Stop and reset */
 	DCSR(drv_data->rx_channel) = RESET_DMA_CHANNEL;
 	DCSR(drv_data->tx_channel) = RESET_DMA_CHANNEL;
 	write_SSSR_CS(drv_data, drv_data->clear_sr);
-	write_SSCR1(read_SSCR1(reg) & ~drv_data->dma_cr1, reg);
+	pxa2xx_spi_write(drv_data, SSCR1,
+			 pxa2xx_spi_read(drv_data, SSCR1)
+			 & ~drv_data->dma_cr1);
 	if (!pxa25x_ssp_comp(drv_data))
-		write_SSTO(0, reg);
+		pxa2xx_spi_write(drv_data, SSTO, 0);
 	pxa2xx_spi_flush(drv_data);
-	write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg);
+	pxa2xx_spi_write(drv_data, SSCR0,
+			 pxa2xx_spi_read(drv_data, SSCR0) & ~SSCR0_SSE);
 
 	pxa2xx_spi_unmap_dma_buffers(drv_data);
 
@@ -163,11 +161,12 @@
 
 static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
 	struct spi_message *msg = drv_data->cur_msg;
 
 	/* Clear and disable interrupts on SSP and DMA channels*/
-	write_SSCR1(read_SSCR1(reg) & ~drv_data->dma_cr1, reg);
+	pxa2xx_spi_write(drv_data, SSCR1,
+			 pxa2xx_spi_read(drv_data, SSCR1)
+			 & ~drv_data->dma_cr1);
 	write_SSSR_CS(drv_data, drv_data->clear_sr);
 	DCSR(drv_data->tx_channel) = RESET_DMA_CHANNEL;
 	DCSR(drv_data->rx_channel) = RESET_DMA_CHANNEL;
@@ -228,7 +227,7 @@
 		&& (drv_data->ssp_type == PXA25x_SSP)) {
 
 		/* Wait for rx to stall */
-		if (wait_ssp_rx_stall(drv_data->ioaddr) == 0)
+		if (wait_ssp_rx_stall(drv_data) == 0)
 			dev_err(&drv_data->pdev->dev,
 				"dma_handler: ssp rx stall failed\n");
 
@@ -240,9 +239,8 @@
 irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data)
 {
 	u32 irq_status;
-	void __iomem *reg = drv_data->ioaddr;
 
-	irq_status = read_SSSR(reg) & drv_data->mask_sr;
+	irq_status = pxa2xx_spi_read(drv_data, SSSR) & drv_data->mask_sr;
 	if (irq_status & SSSR_ROR) {
 		pxa2xx_spi_dma_error_stop(drv_data,
 					  "dma_transfer: fifo overrun");
@@ -252,7 +250,7 @@
 	/* Check for false positive timeout */
 	if ((irq_status & SSSR_TINT)
 		&& (DCSR(drv_data->tx_channel) & DCSR_RUN)) {
-		write_SSSR(SSSR_TINT, reg);
+		pxa2xx_spi_write(drv_data, SSSR, SSSR_TINT);
 		return IRQ_HANDLED;
 	}
 
@@ -261,7 +259,7 @@
 		/* Clear and disable timeout interrupt, do the rest in
 		 * dma_transfer_complete */
 		if (!pxa25x_ssp_comp(drv_data))
-			write_SSTO(0, reg);
+			pxa2xx_spi_write(drv_data, SSTO, 0);
 
 		/* finish this transfer, start the next */
 		pxa2xx_spi_dma_transfer_complete(drv_data);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 23822e7..6f72ad0 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -11,10 +11,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
@@ -45,8 +41,6 @@
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:pxa2xx-spi");
 
-#define MAX_BUSES 3
-
 #define TIMOUT_DFLT		1000
 
 /*
@@ -162,7 +156,6 @@
 
 static bool pxa2xx_spi_txfifo_full(const struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
 	u32 mask;
 
 	switch (drv_data->ssp_type) {
@@ -174,7 +167,7 @@
 		break;
 	}
 
-	return (read_SSSR(reg) & mask) == mask;
+	return (pxa2xx_spi_read(drv_data, SSSR) & mask) == mask;
 }
 
 static void pxa2xx_spi_clear_rx_thre(const struct driver_data *drv_data,
@@ -253,9 +246,6 @@
 	unsigned offset = 0x400;
 	u32 value, orig;
 
-	if (!is_lpss_ssp(drv_data))
-		return;
-
 	/*
 	 * Perform auto-detection of the LPSS SSP private registers. They
 	 * can be either at 1k or 2k offset from the base address.
@@ -304,9 +294,6 @@
 {
 	u32 value;
 
-	if (!is_lpss_ssp(drv_data))
-		return;
-
 	value = __lpss_ssp_read_priv(drv_data, SPI_CS_CONTROL);
 	if (enable)
 		value &= ~SPI_CS_CONTROL_CS_HIGH;
@@ -320,7 +307,7 @@
 	struct chip_data *chip = drv_data->cur_chip;
 
 	if (drv_data->ssp_type == CE4100_SSP) {
-		write_SSSR(drv_data->cur_chip->frm, drv_data->ioaddr);
+		pxa2xx_spi_write(drv_data, SSSR, drv_data->cur_chip->frm);
 		return;
 	}
 
@@ -334,7 +321,8 @@
 		return;
 	}
 
-	lpss_ssp_cs_control(drv_data, true);
+	if (is_lpss_ssp(drv_data))
+		lpss_ssp_cs_control(drv_data, true);
 }
 
 static void cs_deassert(struct driver_data *drv_data)
@@ -354,20 +342,18 @@
 		return;
 	}
 
-	lpss_ssp_cs_control(drv_data, false);
+	if (is_lpss_ssp(drv_data))
+		lpss_ssp_cs_control(drv_data, false);
 }
 
 int pxa2xx_spi_flush(struct driver_data *drv_data)
 {
 	unsigned long limit = loops_per_jiffy << 1;
 
-	void __iomem *reg = drv_data->ioaddr;
-
 	do {
-		while (read_SSSR(reg) & SSSR_RNE) {
-			read_SSDR(reg);
-		}
-	} while ((read_SSSR(reg) & SSSR_BSY) && --limit);
+		while (pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE)
+			pxa2xx_spi_read(drv_data, SSDR);
+	} while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_BSY) && --limit);
 	write_SSSR_CS(drv_data, SSSR_ROR);
 
 	return limit;
@@ -375,14 +361,13 @@
 
 static int null_writer(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
 	u8 n_bytes = drv_data->n_bytes;
 
 	if (pxa2xx_spi_txfifo_full(drv_data)
 		|| (drv_data->tx == drv_data->tx_end))
 		return 0;
 
-	write_SSDR(0, reg);
+	pxa2xx_spi_write(drv_data, SSDR, 0);
 	drv_data->tx += n_bytes;
 
 	return 1;
@@ -390,12 +375,11 @@
 
 static int null_reader(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
 	u8 n_bytes = drv_data->n_bytes;
 
-	while ((read_SSSR(reg) & SSSR_RNE)
-		&& (drv_data->rx < drv_data->rx_end)) {
-		read_SSDR(reg);
+	while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE)
+	       && (drv_data->rx < drv_data->rx_end)) {
+		pxa2xx_spi_read(drv_data, SSDR);
 		drv_data->rx += n_bytes;
 	}
 
@@ -404,13 +388,11 @@
 
 static int u8_writer(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
 	if (pxa2xx_spi_txfifo_full(drv_data)
 		|| (drv_data->tx == drv_data->tx_end))
 		return 0;
 
-	write_SSDR(*(u8 *)(drv_data->tx), reg);
+	pxa2xx_spi_write(drv_data, SSDR, *(u8 *)(drv_data->tx));
 	++drv_data->tx;
 
 	return 1;
@@ -418,11 +400,9 @@
 
 static int u8_reader(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
-	while ((read_SSSR(reg) & SSSR_RNE)
-		&& (drv_data->rx < drv_data->rx_end)) {
-		*(u8 *)(drv_data->rx) = read_SSDR(reg);
+	while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE)
+	       && (drv_data->rx < drv_data->rx_end)) {
+		*(u8 *)(drv_data->rx) = pxa2xx_spi_read(drv_data, SSDR);
 		++drv_data->rx;
 	}
 
@@ -431,13 +411,11 @@
 
 static int u16_writer(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
 	if (pxa2xx_spi_txfifo_full(drv_data)
 		|| (drv_data->tx == drv_data->tx_end))
 		return 0;
 
-	write_SSDR(*(u16 *)(drv_data->tx), reg);
+	pxa2xx_spi_write(drv_data, SSDR, *(u16 *)(drv_data->tx));
 	drv_data->tx += 2;
 
 	return 1;
@@ -445,11 +423,9 @@
 
 static int u16_reader(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
-	while ((read_SSSR(reg) & SSSR_RNE)
-		&& (drv_data->rx < drv_data->rx_end)) {
-		*(u16 *)(drv_data->rx) = read_SSDR(reg);
+	while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE)
+	       && (drv_data->rx < drv_data->rx_end)) {
+		*(u16 *)(drv_data->rx) = pxa2xx_spi_read(drv_data, SSDR);
 		drv_data->rx += 2;
 	}
 
@@ -458,13 +434,11 @@
 
 static int u32_writer(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
 	if (pxa2xx_spi_txfifo_full(drv_data)
 		|| (drv_data->tx == drv_data->tx_end))
 		return 0;
 
-	write_SSDR(*(u32 *)(drv_data->tx), reg);
+	pxa2xx_spi_write(drv_data, SSDR, *(u32 *)(drv_data->tx));
 	drv_data->tx += 4;
 
 	return 1;
@@ -472,11 +446,9 @@
 
 static int u32_reader(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
-	while ((read_SSSR(reg) & SSSR_RNE)
-		&& (drv_data->rx < drv_data->rx_end)) {
-		*(u32 *)(drv_data->rx) = read_SSDR(reg);
+	while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE)
+	       && (drv_data->rx < drv_data->rx_end)) {
+		*(u32 *)(drv_data->rx) = pxa2xx_spi_read(drv_data, SSDR);
 		drv_data->rx += 4;
 	}
 
@@ -552,27 +524,25 @@
 
 static void reset_sccr1(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
 	struct chip_data *chip = drv_data->cur_chip;
 	u32 sccr1_reg;
 
-	sccr1_reg = read_SSCR1(reg) & ~drv_data->int_cr1;
+	sccr1_reg = pxa2xx_spi_read(drv_data, SSCR1) & ~drv_data->int_cr1;
 	sccr1_reg &= ~SSCR1_RFT;
 	sccr1_reg |= chip->threshold;
-	write_SSCR1(sccr1_reg, reg);
+	pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg);
 }
 
 static void int_error_stop(struct driver_data *drv_data, const char* msg)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
 	/* Stop and reset SSP */
 	write_SSSR_CS(drv_data, drv_data->clear_sr);
 	reset_sccr1(drv_data);
 	if (!pxa25x_ssp_comp(drv_data))
-		write_SSTO(0, reg);
+		pxa2xx_spi_write(drv_data, SSTO, 0);
 	pxa2xx_spi_flush(drv_data);
-	write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg);
+	pxa2xx_spi_write(drv_data, SSCR0,
+			 pxa2xx_spi_read(drv_data, SSCR0) & ~SSCR0_SSE);
 
 	dev_err(&drv_data->pdev->dev, "%s\n", msg);
 
@@ -582,13 +552,11 @@
 
 static void int_transfer_complete(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
 	/* Stop SSP */
 	write_SSSR_CS(drv_data, drv_data->clear_sr);
 	reset_sccr1(drv_data);
 	if (!pxa25x_ssp_comp(drv_data))
-		write_SSTO(0, reg);
+		pxa2xx_spi_write(drv_data, SSTO, 0);
 
 	/* Update total byte transferred return count actual bytes read */
 	drv_data->cur_msg->actual_length += drv_data->len -
@@ -607,12 +575,10 @@
 
 static irqreturn_t interrupt_transfer(struct driver_data *drv_data)
 {
-	void __iomem *reg = drv_data->ioaddr;
+	u32 irq_mask = (pxa2xx_spi_read(drv_data, SSCR1) & SSCR1_TIE) ?
+		       drv_data->mask_sr : drv_data->mask_sr & ~SSSR_TFS;
 
-	u32 irq_mask = (read_SSCR1(reg) & SSCR1_TIE) ?
-			drv_data->mask_sr : drv_data->mask_sr & ~SSSR_TFS;
-
-	u32 irq_status = read_SSSR(reg) & irq_mask;
+	u32 irq_status = pxa2xx_spi_read(drv_data, SSSR) & irq_mask;
 
 	if (irq_status & SSSR_ROR) {
 		int_error_stop(drv_data, "interrupt_transfer: fifo overrun");
@@ -620,7 +586,7 @@
 	}
 
 	if (irq_status & SSSR_TINT) {
-		write_SSSR(SSSR_TINT, reg);
+		pxa2xx_spi_write(drv_data, SSSR, SSSR_TINT);
 		if (drv_data->read(drv_data)) {
 			int_transfer_complete(drv_data);
 			return IRQ_HANDLED;
@@ -644,7 +610,7 @@
 		u32 bytes_left;
 		u32 sccr1_reg;
 
-		sccr1_reg = read_SSCR1(reg);
+		sccr1_reg = pxa2xx_spi_read(drv_data, SSCR1);
 		sccr1_reg &= ~SSCR1_TIE;
 
 		/*
@@ -670,7 +636,7 @@
 
 			pxa2xx_spi_set_rx_thre(drv_data, &sccr1_reg, rx_thre);
 		}
-		write_SSCR1(sccr1_reg, reg);
+		pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg);
 	}
 
 	/* We did something */
@@ -680,7 +646,6 @@
 static irqreturn_t ssp_int(int irq, void *dev_id)
 {
 	struct driver_data *drv_data = dev_id;
-	void __iomem *reg = drv_data->ioaddr;
 	u32 sccr1_reg;
 	u32 mask = drv_data->mask_sr;
 	u32 status;
@@ -700,11 +665,11 @@
 	 * are all set to one. That means that the device is already
 	 * powered off.
 	 */
-	status = read_SSSR(reg);
+	status = pxa2xx_spi_read(drv_data, SSSR);
 	if (status == ~0)
 		return IRQ_NONE;
 
-	sccr1_reg = read_SSCR1(reg);
+	sccr1_reg = pxa2xx_spi_read(drv_data, SSCR1);
 
 	/* Ignore possible writes if we don't need to write */
 	if (!(sccr1_reg & SSCR1_TIE))
@@ -715,10 +680,14 @@
 
 	if (!drv_data->cur_msg) {
 
-		write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg);
-		write_SSCR1(read_SSCR1(reg) & ~drv_data->int_cr1, reg);
+		pxa2xx_spi_write(drv_data, SSCR0,
+				 pxa2xx_spi_read(drv_data, SSCR0)
+				 & ~SSCR0_SSE);
+		pxa2xx_spi_write(drv_data, SSCR1,
+				 pxa2xx_spi_read(drv_data, SSCR1)
+				 & ~drv_data->int_cr1);
 		if (!pxa25x_ssp_comp(drv_data))
-			write_SSTO(0, reg);
+			pxa2xx_spi_write(drv_data, SSTO, 0);
 		write_SSSR_CS(drv_data, drv_data->clear_sr);
 
 		dev_err(&drv_data->pdev->dev,
@@ -787,7 +756,6 @@
 	struct spi_transfer *transfer = NULL;
 	struct spi_transfer *previous = NULL;
 	struct chip_data *chip = NULL;
-	void __iomem *reg = drv_data->ioaddr;
 	u32 clk_div = 0;
 	u8 bits = 0;
 	u32 speed = 0;
@@ -931,7 +899,7 @@
 
 		/* Clear status and start DMA engine */
 		cr1 = chip->cr1 | dma_thresh | drv_data->dma_cr1;
-		write_SSSR(drv_data->clear_sr, reg);
+		pxa2xx_spi_write(drv_data, SSSR, drv_data->clear_sr);
 
 		pxa2xx_spi_dma_start(drv_data);
 	} else {
@@ -944,39 +912,43 @@
 	}
 
 	if (is_lpss_ssp(drv_data)) {
-		if ((read_SSIRF(reg) & 0xff) != chip->lpss_rx_threshold)
-			write_SSIRF(chip->lpss_rx_threshold, reg);
-		if ((read_SSITF(reg) & 0xffff) != chip->lpss_tx_threshold)
-			write_SSITF(chip->lpss_tx_threshold, reg);
+		if ((pxa2xx_spi_read(drv_data, SSIRF) & 0xff)
+		    != chip->lpss_rx_threshold)
+			pxa2xx_spi_write(drv_data, SSIRF,
+					 chip->lpss_rx_threshold);
+		if ((pxa2xx_spi_read(drv_data, SSITF) & 0xffff)
+		    != chip->lpss_tx_threshold)
+			pxa2xx_spi_write(drv_data, SSITF,
+					 chip->lpss_tx_threshold);
 	}
 
 	if (is_quark_x1000_ssp(drv_data) &&
-	    (read_DDS_RATE(reg) != chip->dds_rate))
-		write_DDS_RATE(chip->dds_rate, reg);
+	    (pxa2xx_spi_read(drv_data, DDS_RATE) != chip->dds_rate))
+		pxa2xx_spi_write(drv_data, DDS_RATE, chip->dds_rate);
 
 	/* see if we need to reload the config registers */
-	if ((read_SSCR0(reg) != cr0) ||
-	    (read_SSCR1(reg) & change_mask) != (cr1 & change_mask)) {
-
+	if ((pxa2xx_spi_read(drv_data, SSCR0) != cr0)
+	    || (pxa2xx_spi_read(drv_data, SSCR1) & change_mask)
+	    != (cr1 & change_mask)) {
 		/* stop the SSP, and update the other bits */
-		write_SSCR0(cr0 & ~SSCR0_SSE, reg);
+		pxa2xx_spi_write(drv_data, SSCR0, cr0 & ~SSCR0_SSE);
 		if (!pxa25x_ssp_comp(drv_data))
-			write_SSTO(chip->timeout, reg);
+			pxa2xx_spi_write(drv_data, SSTO, chip->timeout);
 		/* first set CR1 without interrupt and service enables */
-		write_SSCR1(cr1 & change_mask, reg);
+		pxa2xx_spi_write(drv_data, SSCR1, cr1 & change_mask);
 		/* restart the SSP */
-		write_SSCR0(cr0, reg);
+		pxa2xx_spi_write(drv_data, SSCR0, cr0);
 
 	} else {
 		if (!pxa25x_ssp_comp(drv_data))
-			write_SSTO(chip->timeout, reg);
+			pxa2xx_spi_write(drv_data, SSTO, chip->timeout);
 	}
 
 	cs_assert(drv_data);
 
 	/* after chip select, release the data by enabling service
 	 * requests and interrupts, without changing any mode bits */
-	write_SSCR1(cr1, reg);
+	pxa2xx_spi_write(drv_data, SSCR1, cr1);
 }
 
 static int pxa2xx_spi_transfer_one_message(struct spi_master *master,
@@ -1005,8 +977,8 @@
 	struct driver_data *drv_data = spi_master_get_devdata(master);
 
 	/* Disable the SSP now */
-	write_SSCR0(read_SSCR0(drv_data->ioaddr) & ~SSCR0_SSE,
-		    drv_data->ioaddr);
+	pxa2xx_spi_write(drv_data, SSCR0,
+			 pxa2xx_spi_read(drv_data, SSCR0) & ~SSCR0_SSE);
 
 	return 0;
 }
@@ -1289,6 +1261,7 @@
 	struct driver_data *drv_data;
 	struct ssp_device *ssp;
 	int status;
+	u32 tmp;
 
 	platform_info = dev_get_platdata(dev);
 	if (!platform_info) {
@@ -1386,38 +1359,35 @@
 	drv_data->max_clk_rate = clk_get_rate(ssp->clk);
 
 	/* Load default SSP configuration */
-	write_SSCR0(0, drv_data->ioaddr);
+	pxa2xx_spi_write(drv_data, SSCR0, 0);
 	switch (drv_data->ssp_type) {
 	case QUARK_X1000_SSP:
-		write_SSCR1(QUARK_X1000_SSCR1_RxTresh(
-					RX_THRESH_QUARK_X1000_DFLT) |
-			    QUARK_X1000_SSCR1_TxTresh(
-					TX_THRESH_QUARK_X1000_DFLT),
-			    drv_data->ioaddr);
+		tmp = QUARK_X1000_SSCR1_RxTresh(RX_THRESH_QUARK_X1000_DFLT)
+		      | QUARK_X1000_SSCR1_TxTresh(TX_THRESH_QUARK_X1000_DFLT);
+		pxa2xx_spi_write(drv_data, SSCR1, tmp);
 
 		/* using the Motorola SPI protocol and use 8 bit frame */
-		write_SSCR0(QUARK_X1000_SSCR0_Motorola
-			    | QUARK_X1000_SSCR0_DataSize(8),
-			    drv_data->ioaddr);
+		pxa2xx_spi_write(drv_data, SSCR0,
+				 QUARK_X1000_SSCR0_Motorola
+				 | QUARK_X1000_SSCR0_DataSize(8));
 		break;
 	default:
-		write_SSCR1(SSCR1_RxTresh(RX_THRESH_DFLT) |
-			    SSCR1_TxTresh(TX_THRESH_DFLT),
-			    drv_data->ioaddr);
-		write_SSCR0(SSCR0_SCR(2)
-			    | SSCR0_Motorola
-			    | SSCR0_DataSize(8),
-			    drv_data->ioaddr);
+		tmp = SSCR1_RxTresh(RX_THRESH_DFLT) |
+		      SSCR1_TxTresh(TX_THRESH_DFLT);
+		pxa2xx_spi_write(drv_data, SSCR1, tmp);
+		tmp = SSCR0_SCR(2) | SSCR0_Motorola | SSCR0_DataSize(8);
+		pxa2xx_spi_write(drv_data, SSCR0, tmp);
 		break;
 	}
 
 	if (!pxa25x_ssp_comp(drv_data))
-		write_SSTO(0, drv_data->ioaddr);
+		pxa2xx_spi_write(drv_data, SSTO, 0);
 
 	if (!is_quark_x1000_ssp(drv_data))
-		write_SSPSP(0, drv_data->ioaddr);
+		pxa2xx_spi_write(drv_data, SSPSP, 0);
 
-	lpss_ssp_setup(drv_data);
+	if (is_lpss_ssp(drv_data))
+		lpss_ssp_setup(drv_data);
 
 	tasklet_init(&drv_data->pump_transfers, pump_transfers,
 		     (unsigned long)drv_data);
@@ -1460,7 +1430,7 @@
 	pm_runtime_get_sync(&pdev->dev);
 
 	/* Disable the SSP at the peripheral and SOC level */
-	write_SSCR0(0, drv_data->ioaddr);
+	pxa2xx_spi_write(drv_data, SSCR0, 0);
 	clk_disable_unprepare(ssp->clk);
 
 	/* Release DMA */
@@ -1497,7 +1467,7 @@
 	status = spi_master_suspend(drv_data->master);
 	if (status != 0)
 		return status;
-	write_SSCR0(0, drv_data->ioaddr);
+	pxa2xx_spi_write(drv_data, SSCR0, 0);
 
 	if (!pm_runtime_suspended(dev))
 		clk_disable_unprepare(ssp->clk);
@@ -1518,7 +1488,8 @@
 		clk_prepare_enable(ssp->clk);
 
 	/* Restore LPSS private register bits */
-	lpss_ssp_setup(drv_data);
+	if (is_lpss_ssp(drv_data))
+		lpss_ssp_setup(drv_data);
 
 	/* Start the queue running */
 	status = spi_master_resume(drv_data->master);
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index 6bec59c..85a58c9 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -115,23 +115,17 @@
 	void (*cs_control)(u32 command);
 };
 
-#define DEFINE_SSP_REG(reg, off) \
-static inline u32 read_##reg(void const __iomem *p) \
-{ return __raw_readl(p + (off)); } \
-\
-static inline void write_##reg(u32 v, void __iomem *p) \
-{ __raw_writel(v, p + (off)); }
+static inline u32 pxa2xx_spi_read(const struct driver_data *drv_data,
+				  unsigned reg)
+{
+	return __raw_readl(drv_data->ioaddr + reg);
+}
 
-DEFINE_SSP_REG(SSCR0, 0x00)
-DEFINE_SSP_REG(SSCR1, 0x04)
-DEFINE_SSP_REG(SSSR, 0x08)
-DEFINE_SSP_REG(SSITR, 0x0c)
-DEFINE_SSP_REG(SSDR, 0x10)
-DEFINE_SSP_REG(DDS_RATE, 0x28)  /* DDS Clock Rate */
-DEFINE_SSP_REG(SSTO, 0x28)
-DEFINE_SSP_REG(SSPSP, 0x2c)
-DEFINE_SSP_REG(SSITF, SSITF)
-DEFINE_SSP_REG(SSIRF, SSIRF)
+static  inline void pxa2xx_spi_write(const struct driver_data *drv_data,
+				     unsigned reg, u32 val)
+{
+	__raw_writel(val, drv_data->ioaddr + reg);
+}
 
 #define START_STATE ((void *)0)
 #define RUNNING_STATE ((void *)1)
@@ -155,13 +149,11 @@
 
 static inline void write_SSSR_CS(struct driver_data *drv_data, u32 val)
 {
-	void __iomem *reg = drv_data->ioaddr;
-
 	if (drv_data->ssp_type == CE4100_SSP ||
 	    drv_data->ssp_type == QUARK_X1000_SSP)
-		val |= read_SSSR(reg) & SSSR_ALT_FRM_MASK;
+		val |= pxa2xx_spi_read(drv_data, SSSR) & SSSR_ALT_FRM_MASK;
 
-	write_SSSR(val, reg);
+	pxa2xx_spi_write(drv_data, SSSR, val);
 }
 
 extern int pxa2xx_spi_flush(struct driver_data *drv_data);
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index e7fb5a0..ff9cdbd 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -337,7 +337,7 @@
 static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer)
 {
 	struct spi_qup *controller = spi_master_get_devdata(spi->master);
-	u32 config, iomode, mode;
+	u32 config, iomode, mode, control;
 	int ret, n_words, w_size;
 
 	if (spi->mode & SPI_LOOP && xfer->len > controller->in_fifo_sz) {
@@ -392,6 +392,15 @@
 
 	writel_relaxed(iomode, controller->base + QUP_IO_M_MODES);
 
+	control = readl_relaxed(controller->base + SPI_IO_CONTROL);
+
+	if (spi->mode & SPI_CPOL)
+		control |= SPI_IO_C_CLK_IDLE_HIGH;
+	else
+		control &= ~SPI_IO_C_CLK_IDLE_HIGH;
+
+	writel_relaxed(control, controller->base + SPI_IO_CONTROL);
+
 	config = readl_relaxed(controller->base + SPI_CONFIG);
 
 	if (spi->mode & SPI_LOOP)
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index daabbab..1a777dc 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -437,6 +437,7 @@
 	rs->state &= ~TXBUSY;
 	spin_unlock_irqrestore(&rs->lock, flags);
 
+	rxdesc = NULL;
 	if (rs->rx) {
 		rxconf.direction = rs->dma_rx.direction;
 		rxconf.src_addr = rs->dma_rx.addr;
@@ -453,6 +454,7 @@
 		rxdesc->callback_param = rs;
 	}
 
+	txdesc = NULL;
 	if (rs->tx) {
 		txconf.direction = rs->dma_tx.direction;
 		txconf.dst_addr = rs->dma_tx.addr;
@@ -470,7 +472,7 @@
 	}
 
 	/* rx must be started before tx due to spi instinct */
-	if (rs->rx) {
+	if (rxdesc) {
 		spin_lock_irqsave(&rs->lock, flags);
 		rs->state |= RXBUSY;
 		spin_unlock_irqrestore(&rs->lock, flags);
@@ -478,7 +480,7 @@
 		dma_async_issue_pending(rs->dma_rx.ch);
 	}
 
-	if (rs->tx) {
+	if (txdesc) {
 		spin_lock_irqsave(&rs->lock, flags);
 		rs->state |= TXBUSY;
 		spin_unlock_irqrestore(&rs->lock, flags);
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 2071f78..46ce470 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -15,11 +15,6 @@
  * 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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
  */
 
 #include <linux/module.h>
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 37b1983..9231c34 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -11,10 +11,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c
index 237f2e7..5a56acf 100644
--- a/drivers/spi/spi-sc18is602.c
+++ b/drivers/spi/spi-sc18is602.c
@@ -12,10 +12,6 @@
  * 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
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/spi/spi-sh-hspi.c b/drivers/spi/spi-sh-hspi.c
index fc29233..20e800e 100644
--- a/drivers/spi/spi-sh-hspi.c
+++ b/drivers/spi/spi-sh-hspi.c
@@ -16,11 +16,6 @@
  * 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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
  */
 
 #include <linux/clk.h>
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 3ab7a21..e57eec0 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -82,6 +82,8 @@
 #define MDR1_SYNCMD_LR	 0x30000000 /*   L/R mode */
 #define MDR1_SYNCAC_SHIFT	 25 /* Sync Polarity (1 = Active-low) */
 #define MDR1_BITLSB_SHIFT	 24 /* MSB/LSB First (1 = LSB first) */
+#define MDR1_DTDL_SHIFT		 20 /* Data Pin Bit Delay for MSIOF_SYNC */
+#define MDR1_SYNCDL_SHIFT	 16 /* Frame Sync Signal Timing Delay */
 #define MDR1_FLD_MASK	 0x0000000c /* Frame Sync Signal Interval (0-3) */
 #define MDR1_FLD_SHIFT		  2
 #define MDR1_XXSTP	 0x00000001 /* Transmission/Reception Stop on FIFO */
@@ -241,42 +243,80 @@
 
 static struct {
 	unsigned short div;
-	unsigned short scr;
-} const sh_msiof_spi_clk_table[] = {
-	{ 1,	SCR_BRPS( 1) | SCR_BRDV_DIV_1 },
-	{ 2,	SCR_BRPS( 1) | SCR_BRDV_DIV_2 },
-	{ 4,	SCR_BRPS( 1) | SCR_BRDV_DIV_4 },
-	{ 8,	SCR_BRPS( 1) | SCR_BRDV_DIV_8 },
-	{ 16,	SCR_BRPS( 1) | SCR_BRDV_DIV_16 },
-	{ 32,	SCR_BRPS( 1) | SCR_BRDV_DIV_32 },
-	{ 64,	SCR_BRPS(32) | SCR_BRDV_DIV_2 },
-	{ 128,	SCR_BRPS(32) | SCR_BRDV_DIV_4 },
-	{ 256,	SCR_BRPS(32) | SCR_BRDV_DIV_8 },
-	{ 512,	SCR_BRPS(32) | SCR_BRDV_DIV_16 },
-	{ 1024,	SCR_BRPS(32) | SCR_BRDV_DIV_32 },
+	unsigned short brdv;
+} const sh_msiof_spi_div_table[] = {
+	{ 1,	SCR_BRDV_DIV_1 },
+	{ 2,	SCR_BRDV_DIV_2 },
+	{ 4,	SCR_BRDV_DIV_4 },
+	{ 8,	SCR_BRDV_DIV_8 },
+	{ 16,	SCR_BRDV_DIV_16 },
+	{ 32,	SCR_BRDV_DIV_32 },
 };
 
 static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p,
 				      unsigned long parent_rate, u32 spi_hz)
 {
 	unsigned long div = 1024;
+	u32 brps, scr;
 	size_t k;
 
 	if (!WARN_ON(!spi_hz || !parent_rate))
 		div = DIV_ROUND_UP(parent_rate, spi_hz);
 
-	/* TODO: make more fine grained */
-
-	for (k = 0; k < ARRAY_SIZE(sh_msiof_spi_clk_table); k++) {
-		if (sh_msiof_spi_clk_table[k].div >= div)
+	for (k = 0; k < ARRAY_SIZE(sh_msiof_spi_div_table); k++) {
+		brps = DIV_ROUND_UP(div, sh_msiof_spi_div_table[k].div);
+		if (brps <= 32) /* max of brdv is 32 */
 			break;
 	}
 
-	k = min_t(int, k, ARRAY_SIZE(sh_msiof_spi_clk_table) - 1);
+	k = min_t(int, k, ARRAY_SIZE(sh_msiof_spi_div_table) - 1);
 
-	sh_msiof_write(p, TSCR, sh_msiof_spi_clk_table[k].scr);
+	scr = sh_msiof_spi_div_table[k].brdv | SCR_BRPS(brps);
+	sh_msiof_write(p, TSCR, scr);
 	if (!(p->chipdata->master_flags & SPI_MASTER_MUST_TX))
-		sh_msiof_write(p, RSCR, sh_msiof_spi_clk_table[k].scr);
+		sh_msiof_write(p, RSCR, scr);
+}
+
+static u32 sh_msiof_get_delay_bit(u32 dtdl_or_syncdl)
+{
+	/*
+	 * DTDL/SYNCDL bit	: p->info->dtdl or p->info->syncdl
+	 * b'000		: 0
+	 * b'001		: 100
+	 * b'010		: 200
+	 * b'011 (SYNCDL only)	: 300
+	 * b'101		: 50
+	 * b'110		: 150
+	 */
+	if (dtdl_or_syncdl % 100)
+		return dtdl_or_syncdl / 100 + 5;
+	else
+		return dtdl_or_syncdl / 100;
+}
+
+static u32 sh_msiof_spi_get_dtdl_and_syncdl(struct sh_msiof_spi_priv *p)
+{
+	u32 val;
+
+	if (!p->info)
+		return 0;
+
+	/* check if DTDL and SYNCDL is allowed value */
+	if (p->info->dtdl > 200 || p->info->syncdl > 300) {
+		dev_warn(&p->pdev->dev, "DTDL or SYNCDL is too large\n");
+		return 0;
+	}
+
+	/* check if the sum of DTDL and SYNCDL becomes an integer value  */
+	if ((p->info->dtdl + p->info->syncdl) % 100) {
+		dev_warn(&p->pdev->dev, "the sum of DTDL/SYNCDL is not good\n");
+		return 0;
+	}
+
+	val = sh_msiof_get_delay_bit(p->info->dtdl) << MDR1_DTDL_SHIFT;
+	val |= sh_msiof_get_delay_bit(p->info->syncdl) << MDR1_SYNCDL_SHIFT;
+
+	return val;
 }
 
 static void sh_msiof_spi_set_pin_regs(struct sh_msiof_spi_priv *p,
@@ -296,6 +336,7 @@
 	tmp = MDR1_SYNCMD_SPI | 1 << MDR1_FLD_SHIFT | MDR1_XXSTP;
 	tmp |= !cs_high << MDR1_SYNCAC_SHIFT;
 	tmp |= lsb_first << MDR1_BITLSB_SHIFT;
+	tmp |= sh_msiof_spi_get_dtdl_and_syncdl(p);
 	sh_msiof_write(p, TMDR1, tmp | MDR1_TRMD | TMDR1_PCON);
 	if (p->chipdata->master_flags & SPI_MASTER_MUST_TX) {
 		/* These bits are reserved if RX needs TX */
@@ -501,7 +542,7 @@
 		gpio_set_value(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH));
 
 
-	pm_runtime_put_sync(&p->pdev->dev);
+	pm_runtime_put(&p->pdev->dev);
 
 	return 0;
 }
@@ -595,8 +636,7 @@
 	}
 
 	/* wait for tx fifo to be emptied / rx fifo to be filled */
-	ret = wait_for_completion_timeout(&p->done, HZ);
-	if (!ret) {
+	if (!wait_for_completion_timeout(&p->done, HZ)) {
 		dev_err(&p->pdev->dev, "PIO timeout\n");
 		ret = -ETIMEDOUT;
 		goto stop_reset;
@@ -706,8 +746,7 @@
 	}
 
 	/* wait for tx fifo to be emptied / rx fifo to be filled */
-	ret = wait_for_completion_timeout(&p->done, HZ);
-	if (!ret) {
+	if (!wait_for_completion_timeout(&p->done, HZ)) {
 		dev_err(&p->pdev->dev, "DMA timeout\n");
 		ret = -ETIMEDOUT;
 		goto stop_reset;
@@ -957,6 +996,8 @@
 					&info->tx_fifo_override);
 	of_property_read_u32(np, "renesas,rx-fifo-size",
 					&info->rx_fifo_override);
+	of_property_read_u32(np, "renesas,dtdl", &info->dtdl);
+	of_property_read_u32(np, "renesas,syncdl", &info->syncdl);
 
 	info->num_chipselect = num_cs;
 
diff --git a/drivers/spi/spi-sh.c b/drivers/spi/spi-sh.c
index 1cfc906..5025011 100644
--- a/drivers/spi/spi-sh.c
+++ b/drivers/spi/spi-sh.c
@@ -14,11 +14,6 @@
  * 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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
  */
 
 #include <linux/module.h>
diff --git a/drivers/spi/spi-sirf.c b/drivers/spi/spi-sirf.c
index d075191..f5715c9 100644
--- a/drivers/spi/spi-sirf.c
+++ b/drivers/spi/spi-sirf.c
@@ -818,7 +818,6 @@
 
 static const struct of_device_id spi_sirfsoc_of_match[] = {
 	{ .compatible = "sirf,prima2-spi", },
-	{ .compatible = "sirf,marco-spi", },
 	{}
 };
 MODULE_DEVICE_TABLE(of, spi_sirfsoc_of_match);
diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c
new file mode 100644
index 0000000..2faeaa7
--- /dev/null
+++ b/drivers/spi/spi-st-ssc4.c
@@ -0,0 +1,504 @@
+/*
+ *  Copyright (c) 2008-2014 STMicroelectronics Limited
+ *
+ *  Author: Angus Clark <Angus.Clark@st.com>
+ *          Patrice Chotard <patrice.chotard@st.com>
+ *          Lee Jones <lee.jones@linaro.org>
+ *
+ *  SPI master mode controller driver, used in STMicroelectronics devices.
+ *
+ *  May be copied or modified under the terms of the GNU General Public
+ *  License Version 2.0 only.  See linux/COPYING for more information.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/of_irq.h>
+#include <linux/pm_runtime.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi_bitbang.h>
+
+/* SSC registers */
+#define SSC_BRG				0x000
+#define SSC_TBUF			0x004
+#define SSC_RBUF			0x008
+#define SSC_CTL				0x00C
+#define SSC_IEN				0x010
+#define SSC_I2C				0x018
+
+/* SSC Control */
+#define SSC_CTL_DATA_WIDTH_9		0x8
+#define SSC_CTL_DATA_WIDTH_MSK		0xf
+#define SSC_CTL_BM			0xf
+#define SSC_CTL_HB			BIT(4)
+#define SSC_CTL_PH			BIT(5)
+#define SSC_CTL_PO			BIT(6)
+#define SSC_CTL_SR			BIT(7)
+#define SSC_CTL_MS			BIT(8)
+#define SSC_CTL_EN			BIT(9)
+#define SSC_CTL_LPB			BIT(10)
+#define SSC_CTL_EN_TX_FIFO		BIT(11)
+#define SSC_CTL_EN_RX_FIFO		BIT(12)
+#define SSC_CTL_EN_CLST_RX		BIT(13)
+
+/* SSC Interrupt Enable */
+#define SSC_IEN_TEEN			BIT(2)
+
+#define FIFO_SIZE			8
+
+struct spi_st {
+	/* SSC SPI Controller */
+	void __iomem		*base;
+	struct clk		*clk;
+	struct device		*dev;
+
+	/* SSC SPI current transaction */
+	const u8		*tx_ptr;
+	u8			*rx_ptr;
+	u16			bytes_per_word;
+	unsigned int		words_remaining;
+	unsigned int		baud;
+	struct completion	done;
+};
+
+static int spi_st_clk_enable(struct spi_st *spi_st)
+{
+	/*
+	 * Current platforms use one of the core clocks for SPI and I2C.
+	 * If we attempt to disable the clock, the system will hang.
+	 *
+	 * TODO: Remove this when platform supports power domains.
+	 */
+	return 0;
+
+	return clk_prepare_enable(spi_st->clk);
+}
+
+static void spi_st_clk_disable(struct spi_st *spi_st)
+{
+	/*
+	 * Current platforms use one of the core clocks for SPI and I2C.
+	 * If we attempt to disable the clock, the system will hang.
+	 *
+	 * TODO: Remove this when platform supports power domains.
+	 */
+	return;
+
+	clk_disable_unprepare(spi_st->clk);
+}
+
+/* Load the TX FIFO */
+static void ssc_write_tx_fifo(struct spi_st *spi_st)
+{
+	unsigned int count, i;
+	uint32_t word = 0;
+
+	if (spi_st->words_remaining > FIFO_SIZE)
+		count = FIFO_SIZE;
+	else
+		count = spi_st->words_remaining;
+
+	for (i = 0; i < count; i++) {
+		if (spi_st->tx_ptr) {
+			if (spi_st->bytes_per_word == 1) {
+				word = *spi_st->tx_ptr++;
+			} else {
+				word = *spi_st->tx_ptr++;
+				word = *spi_st->tx_ptr++ | (word << 8);
+			}
+		}
+		writel_relaxed(word, spi_st->base + SSC_TBUF);
+	}
+}
+
+/* Read the RX FIFO */
+static void ssc_read_rx_fifo(struct spi_st *spi_st)
+{
+	unsigned int count, i;
+	uint32_t word = 0;
+
+	if (spi_st->words_remaining > FIFO_SIZE)
+		count = FIFO_SIZE;
+	else
+		count = spi_st->words_remaining;
+
+	for (i = 0; i < count; i++) {
+		word = readl_relaxed(spi_st->base + SSC_RBUF);
+
+		if (spi_st->rx_ptr) {
+			if (spi_st->bytes_per_word == 1) {
+				*spi_st->rx_ptr++ = (uint8_t)word;
+			} else {
+				*spi_st->rx_ptr++ = (word >> 8);
+				*spi_st->rx_ptr++ = word & 0xff;
+			}
+		}
+	}
+	spi_st->words_remaining -= count;
+}
+
+static int spi_st_transfer_one(struct spi_master *master,
+			       struct spi_device *spi, struct spi_transfer *t)
+{
+	struct spi_st *spi_st = spi_master_get_devdata(master);
+	uint32_t ctl = 0;
+
+	/* Setup transfer */
+	spi_st->tx_ptr = t->tx_buf;
+	spi_st->rx_ptr = t->rx_buf;
+
+	if (spi->bits_per_word > 8) {
+		/*
+		 * Anything greater than 8 bits-per-word requires 2
+		 * bytes-per-word in the RX/TX buffers
+		 */
+		spi_st->bytes_per_word = 2;
+		spi_st->words_remaining = t->len / 2;
+
+	} else if (spi->bits_per_word == 8 && !(t->len & 0x1)) {
+		/*
+		 * If transfer is even-length, and 8 bits-per-word, then
+		 * implement as half-length 16 bits-per-word transfer
+		 */
+		spi_st->bytes_per_word = 2;
+		spi_st->words_remaining = t->len / 2;
+
+		/* Set SSC_CTL to 16 bits-per-word */
+		ctl = readl_relaxed(spi_st->base + SSC_CTL);
+		writel_relaxed((ctl | 0xf), spi_st->base + SSC_CTL);
+
+		readl_relaxed(spi_st->base + SSC_RBUF);
+
+	} else {
+		spi_st->bytes_per_word = 1;
+		spi_st->words_remaining = t->len;
+	}
+
+	reinit_completion(&spi_st->done);
+
+	/* Start transfer by writing to the TX FIFO */
+	ssc_write_tx_fifo(spi_st);
+	writel_relaxed(SSC_IEN_TEEN, spi_st->base + SSC_IEN);
+
+	/* Wait for transfer to complete */
+	wait_for_completion(&spi_st->done);
+
+	/* Restore SSC_CTL if necessary */
+	if (ctl)
+		writel_relaxed(ctl, spi_st->base + SSC_CTL);
+
+	spi_finalize_current_transfer(spi->master);
+
+	return t->len;
+}
+
+static void spi_st_cleanup(struct spi_device *spi)
+{
+	int cs = spi->cs_gpio;
+
+	if (gpio_is_valid(cs))
+		devm_gpio_free(&spi->dev, cs);
+}
+
+/* the spi->mode bits understood by this driver: */
+#define MODEBITS  (SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST | SPI_LOOP | SPI_CS_HIGH)
+static int spi_st_setup(struct spi_device *spi)
+{
+	struct spi_st *spi_st = spi_master_get_devdata(spi->master);
+	u32 spi_st_clk, sscbrg, var;
+	u32 hz = spi->max_speed_hz;
+	int cs = spi->cs_gpio;
+	int ret;
+
+	if (!hz)  {
+		dev_err(&spi->dev, "max_speed_hz unspecified\n");
+		return -EINVAL;
+	}
+
+	if (!gpio_is_valid(cs)) {
+		dev_err(&spi->dev, "%d is not a valid gpio\n", cs);
+		return -EINVAL;
+	}
+
+	if (devm_gpio_request(&spi->dev, cs, dev_name(&spi->dev))) {
+		dev_err(&spi->dev, "could not request gpio:%d\n", cs);
+		return -EINVAL;
+	}
+
+	ret = gpio_direction_output(cs, spi->mode & SPI_CS_HIGH);
+	if (ret)
+		return ret;
+
+	spi_st_clk = clk_get_rate(spi_st->clk);
+
+	/* Set SSC_BRF */
+	sscbrg = spi_st_clk / (2 * hz);
+	if (sscbrg < 0x07 || sscbrg > BIT(16)) {
+		dev_err(&spi->dev,
+			"baudrate %d outside valid range %d\n", sscbrg, hz);
+		return -EINVAL;
+	}
+
+	spi_st->baud = spi_st_clk / (2 * sscbrg);
+	if (sscbrg == BIT(16)) /* 16-bit counter wraps */
+		sscbrg = 0x0;
+
+	writel_relaxed(sscbrg, spi_st->base + SSC_BRG);
+
+	dev_dbg(&spi->dev,
+		"setting baudrate:target= %u hz, actual= %u hz, sscbrg= %u\n",
+		hz, spi_st->baud, sscbrg);
+
+	 /* Set SSC_CTL and enable SSC */
+	 var = readl_relaxed(spi_st->base + SSC_CTL);
+	 var |= SSC_CTL_MS;
+
+	 if (spi->mode & SPI_CPOL)
+		var |= SSC_CTL_PO;
+	 else
+		var &= ~SSC_CTL_PO;
+
+	 if (spi->mode & SPI_CPHA)
+		var |= SSC_CTL_PH;
+	 else
+		var &= ~SSC_CTL_PH;
+
+	 if ((spi->mode & SPI_LSB_FIRST) == 0)
+		var |= SSC_CTL_HB;
+	 else
+		var &= ~SSC_CTL_HB;
+
+	 if (spi->mode & SPI_LOOP)
+		var |= SSC_CTL_LPB;
+	 else
+		var &= ~SSC_CTL_LPB;
+
+	 var &= ~SSC_CTL_DATA_WIDTH_MSK;
+	 var |= (spi->bits_per_word - 1);
+
+	 var |= SSC_CTL_EN_TX_FIFO | SSC_CTL_EN_RX_FIFO;
+	 var |= SSC_CTL_EN;
+
+	 writel_relaxed(var, spi_st->base + SSC_CTL);
+
+	 /* Clear the status register */
+	 readl_relaxed(spi_st->base + SSC_RBUF);
+
+	 return 0;
+}
+
+/* Interrupt fired when TX shift register becomes empty */
+static irqreturn_t spi_st_irq(int irq, void *dev_id)
+{
+	struct spi_st *spi_st = (struct spi_st *)dev_id;
+
+	/* Read RX FIFO */
+	ssc_read_rx_fifo(spi_st);
+
+	/* Fill TX FIFO */
+	if (spi_st->words_remaining) {
+		ssc_write_tx_fifo(spi_st);
+	} else {
+		/* TX/RX complete */
+		writel_relaxed(0x0, spi_st->base + SSC_IEN);
+		/*
+		 * read SSC_IEN to ensure that this bit is set
+		 * before re-enabling interrupt
+		 */
+		readl(spi_st->base + SSC_IEN);
+		complete(&spi_st->done);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int spi_st_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct spi_master *master;
+	struct resource *res;
+	struct spi_st *spi_st;
+	int irq, ret = 0;
+	u32 var;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*spi_st));
+	if (!master)
+		return -ENOMEM;
+
+	master->dev.of_node		= np;
+	master->mode_bits		= MODEBITS;
+	master->setup			= spi_st_setup;
+	master->cleanup			= spi_st_cleanup;
+	master->transfer_one		= spi_st_transfer_one;
+	master->bits_per_word_mask	= SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
+	master->auto_runtime_pm		= true;
+	master->bus_num			= pdev->id;
+	spi_st				= spi_master_get_devdata(master);
+
+	spi_st->clk = devm_clk_get(&pdev->dev, "ssc");
+	if (IS_ERR(spi_st->clk)) {
+		dev_err(&pdev->dev, "Unable to request clock\n");
+		return PTR_ERR(spi_st->clk);
+	}
+
+	ret = spi_st_clk_enable(spi_st);
+	if (ret)
+		return ret;
+
+	init_completion(&spi_st->done);
+
+	/* Get resources */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	spi_st->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(spi_st->base)) {
+		ret = PTR_ERR(spi_st->base);
+		goto clk_disable;
+	}
+
+	/* Disable I2C and Reset SSC */
+	writel_relaxed(0x0, spi_st->base + SSC_I2C);
+	var = readw_relaxed(spi_st->base + SSC_CTL);
+	var |= SSC_CTL_SR;
+	writel_relaxed(var, spi_st->base + SSC_CTL);
+
+	udelay(1);
+	var = readl_relaxed(spi_st->base + SSC_CTL);
+	var &= ~SSC_CTL_SR;
+	writel_relaxed(var, spi_st->base + SSC_CTL);
+
+	/* Set SSC into slave mode before reconfiguring PIO pins */
+	var = readl_relaxed(spi_st->base + SSC_CTL);
+	var &= ~SSC_CTL_MS;
+	writel_relaxed(var, spi_st->base + SSC_CTL);
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (!irq) {
+		dev_err(&pdev->dev, "IRQ missing or invalid\n");
+		ret = -EINVAL;
+		goto clk_disable;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, spi_st_irq, 0,
+			       pdev->name, spi_st);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to request irq %d\n", irq);
+		goto clk_disable;
+	}
+
+	/* by default the device is on */
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	platform_set_drvdata(pdev, master);
+
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to register master\n");
+		goto clk_disable;
+	}
+
+	return 0;
+
+clk_disable:
+	spi_st_clk_disable(spi_st);
+
+	return ret;
+}
+
+static int spi_st_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_st *spi_st = spi_master_get_devdata(master);
+
+	spi_st_clk_disable(spi_st);
+
+	pinctrl_pm_select_sleep_state(&pdev->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int spi_st_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_st *spi_st = spi_master_get_devdata(master);
+
+	writel_relaxed(0, spi_st->base + SSC_IEN);
+	pinctrl_pm_select_sleep_state(dev);
+
+	spi_st_clk_disable(spi_st);
+
+	return 0;
+}
+
+static int spi_st_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_st *spi_st = spi_master_get_devdata(master);
+	int ret;
+
+	ret = spi_st_clk_enable(spi_st);
+	pinctrl_pm_select_default_state(dev);
+
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+static int spi_st_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	int ret;
+
+	ret = spi_master_suspend(master);
+	if (ret)
+		return ret;
+
+	return pm_runtime_force_suspend(dev);
+}
+
+static int spi_st_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	int ret;
+
+	ret = spi_master_resume(master);
+	if (ret)
+		return ret;
+
+	return pm_runtime_force_resume(dev);
+}
+#endif
+
+static const struct dev_pm_ops spi_st_pm = {
+	SET_SYSTEM_SLEEP_PM_OPS(spi_st_suspend, spi_st_resume)
+	SET_RUNTIME_PM_OPS(spi_st_runtime_suspend, spi_st_runtime_resume, NULL)
+};
+
+static struct of_device_id stm_spi_match[] = {
+	{ .compatible = "st,comms-ssc4-spi", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, stm_spi_match);
+
+static struct platform_driver spi_st_driver = {
+	.driver = {
+		.name = "spi-st",
+		.pm = &spi_st_pm,
+		.of_match_table = of_match_ptr(stm_spi_match),
+	},
+	.probe = spi_st_probe,
+	.remove = spi_st_remove,
+};
+module_platform_driver(spi_st_driver);
+
+MODULE_AUTHOR("Patrice Chotard <patrice.chotard@st.com>");
+MODULE_DESCRIPTION("STM SSC SPI driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 6146c4cd..884a716 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -201,7 +201,7 @@
 
 static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 {
-	int wlen, count, ret;
+	int wlen, count;
 	unsigned int cmd;
 	const u8 *txbuf;
 
@@ -230,9 +230,8 @@
 		}
 
 		ti_qspi_write(qspi, cmd, QSPI_SPI_CMD_REG);
-		ret = wait_for_completion_timeout(&qspi->transfer_complete,
-						  QSPI_COMPLETION_TIMEOUT);
-		if (ret == 0) {
+		if (!wait_for_completion_timeout(&qspi->transfer_complete,
+						 QSPI_COMPLETION_TIMEOUT)) {
 			dev_err(qspi->dev, "write timed out\n");
 			return -ETIMEDOUT;
 		}
@@ -245,7 +244,7 @@
 
 static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 {
-	int wlen, count, ret;
+	int wlen, count;
 	unsigned int cmd;
 	u8 *rxbuf;
 
@@ -268,9 +267,8 @@
 	while (count) {
 		dev_dbg(qspi->dev, "rx cmd %08x dc %08x\n", cmd, qspi->dc);
 		ti_qspi_write(qspi, cmd, QSPI_SPI_CMD_REG);
-		ret = wait_for_completion_timeout(&qspi->transfer_complete,
-				QSPI_COMPLETION_TIMEOUT);
-		if (ret == 0) {
+		if (!wait_for_completion_timeout(&qspi->transfer_complete,
+						 QSPI_COMPLETION_TIMEOUT)) {
 			dev_err(qspi->dev, "read timed out\n");
 			return -ETIMEDOUT;
 		}
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index be692ad..93dfcee 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -11,10 +11,6 @@
  * 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.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/spi/spi-xilinx.c b/drivers/spi/spi-xilinx.c
index 79bd84f..133f53a 100644
--- a/drivers/spi/spi-xilinx.c
+++ b/drivers/spi/spi-xilinx.c
@@ -22,6 +22,8 @@
 #include <linux/spi/xilinx_spi.h>
 #include <linux/io.h>
 
+#define XILINX_SPI_MAX_CS	32
+
 #define XILINX_SPI_NAME "xilinx_spi"
 
 /* Register definitions as per "OPB Serial Peripheral Interface (SPI) (v1.00e)
@@ -34,7 +36,8 @@
 #define XSPI_CR_MASTER_MODE	0x04
 #define XSPI_CR_CPOL		0x08
 #define XSPI_CR_CPHA		0x10
-#define XSPI_CR_MODE_MASK	(XSPI_CR_CPHA | XSPI_CR_CPOL)
+#define XSPI_CR_MODE_MASK	(XSPI_CR_CPHA | XSPI_CR_CPOL | \
+				 XSPI_CR_LSB_FIRST | XSPI_CR_LOOP)
 #define XSPI_CR_TXFIFO_RESET	0x20
 #define XSPI_CR_RXFIFO_RESET	0x40
 #define XSPI_CR_MANUAL_SSELECT	0x80
@@ -85,12 +88,11 @@
 
 	u8 *rx_ptr;		/* pointer in the Tx buffer */
 	const u8 *tx_ptr;	/* pointer in the Rx buffer */
-	int remaining_bytes;	/* the number of bytes left to transfer */
-	u8 bits_per_word;
+	u8 bytes_per_word;
+	int buffer_size;	/* buffer size in words */
+	u32 cs_inactive;	/* Level of the CS pins when inactive*/
 	unsigned int (*read_fn)(void __iomem *);
 	void (*write_fn)(u32, void __iomem *);
-	void (*tx_fn)(struct xilinx_spi *);
-	void (*rx_fn)(struct xilinx_spi *);
 };
 
 static void xspi_write32(u32 val, void __iomem *addr)
@@ -113,49 +115,51 @@
 	return ioread32be(addr);
 }
 
-static void xspi_tx8(struct xilinx_spi *xspi)
+static void xilinx_spi_tx(struct xilinx_spi *xspi)
 {
-	xspi->write_fn(*xspi->tx_ptr, xspi->regs + XSPI_TXD_OFFSET);
-	xspi->tx_ptr++;
-}
+	u32 data = 0;
 
-static void xspi_tx16(struct xilinx_spi *xspi)
-{
-	xspi->write_fn(*(u16 *)(xspi->tx_ptr), xspi->regs + XSPI_TXD_OFFSET);
-	xspi->tx_ptr += 2;
-}
-
-static void xspi_tx32(struct xilinx_spi *xspi)
-{
-	xspi->write_fn(*(u32 *)(xspi->tx_ptr), xspi->regs + XSPI_TXD_OFFSET);
-	xspi->tx_ptr += 4;
-}
-
-static void xspi_rx8(struct xilinx_spi *xspi)
-{
-	u32 data = xspi->read_fn(xspi->regs + XSPI_RXD_OFFSET);
-	if (xspi->rx_ptr) {
-		*xspi->rx_ptr = data & 0xff;
-		xspi->rx_ptr++;
+	if (!xspi->tx_ptr) {
+		xspi->write_fn(0, xspi->regs + XSPI_TXD_OFFSET);
+		return;
 	}
-}
 
-static void xspi_rx16(struct xilinx_spi *xspi)
-{
-	u32 data = xspi->read_fn(xspi->regs + XSPI_RXD_OFFSET);
-	if (xspi->rx_ptr) {
-		*(u16 *)(xspi->rx_ptr) = data & 0xffff;
-		xspi->rx_ptr += 2;
+	switch (xspi->bytes_per_word) {
+	case 1:
+		data = *(u8 *)(xspi->tx_ptr);
+		break;
+	case 2:
+		data = *(u16 *)(xspi->tx_ptr);
+		break;
+	case 4:
+		data = *(u32 *)(xspi->tx_ptr);
+		break;
 	}
+
+	xspi->write_fn(data, xspi->regs + XSPI_TXD_OFFSET);
+	xspi->tx_ptr += xspi->bytes_per_word;
 }
 
-static void xspi_rx32(struct xilinx_spi *xspi)
+static void xilinx_spi_rx(struct xilinx_spi *xspi)
 {
 	u32 data = xspi->read_fn(xspi->regs + XSPI_RXD_OFFSET);
-	if (xspi->rx_ptr) {
+
+	if (!xspi->rx_ptr)
+		return;
+
+	switch (xspi->bytes_per_word) {
+	case 1:
+		*(u8 *)(xspi->rx_ptr) = data;
+		break;
+	case 2:
+		*(u16 *)(xspi->rx_ptr) = data;
+		break;
+	case 4:
 		*(u32 *)(xspi->rx_ptr) = data;
-		xspi->rx_ptr += 4;
+		break;
 	}
+
+	xspi->rx_ptr += xspi->bytes_per_word;
 }
 
 static void xspi_init_hw(struct xilinx_spi *xspi)
@@ -165,46 +169,56 @@
 	/* Reset the SPI device */
 	xspi->write_fn(XIPIF_V123B_RESET_MASK,
 		regs_base + XIPIF_V123B_RESETR_OFFSET);
-	/* Disable all the interrupts just in case */
-	xspi->write_fn(0, regs_base + XIPIF_V123B_IIER_OFFSET);
-	/* Enable the global IPIF interrupt */
-	xspi->write_fn(XIPIF_V123B_GINTR_ENABLE,
-		regs_base + XIPIF_V123B_DGIER_OFFSET);
+	/* Enable the transmit empty interrupt, which we use to determine
+	 * progress on the transmission.
+	 */
+	xspi->write_fn(XSPI_INTR_TX_EMPTY,
+			regs_base + XIPIF_V123B_IIER_OFFSET);
+	/* Disable the global IPIF interrupt */
+	xspi->write_fn(0, regs_base + XIPIF_V123B_DGIER_OFFSET);
 	/* Deselect the slave on the SPI bus */
 	xspi->write_fn(0xffff, regs_base + XSPI_SSR_OFFSET);
 	/* Disable the transmitter, enable Manual Slave Select Assertion,
 	 * put SPI controller into master mode, and enable it */
-	xspi->write_fn(XSPI_CR_TRANS_INHIBIT | XSPI_CR_MANUAL_SSELECT |
-		XSPI_CR_MASTER_MODE | XSPI_CR_ENABLE | XSPI_CR_TXFIFO_RESET |
-		XSPI_CR_RXFIFO_RESET, regs_base + XSPI_CR_OFFSET);
+	xspi->write_fn(XSPI_CR_MANUAL_SSELECT |	XSPI_CR_MASTER_MODE |
+		XSPI_CR_ENABLE | XSPI_CR_TXFIFO_RESET |	XSPI_CR_RXFIFO_RESET,
+		regs_base + XSPI_CR_OFFSET);
 }
 
 static void xilinx_spi_chipselect(struct spi_device *spi, int is_on)
 {
 	struct xilinx_spi *xspi = spi_master_get_devdata(spi->master);
+	u16 cr;
+	u32 cs;
 
 	if (is_on == BITBANG_CS_INACTIVE) {
 		/* Deselect the slave on the SPI bus */
-		xspi->write_fn(0xffff, xspi->regs + XSPI_SSR_OFFSET);
-	} else if (is_on == BITBANG_CS_ACTIVE) {
-		/* Set the SPI clock phase and polarity */
-		u16 cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET)
-			 & ~XSPI_CR_MODE_MASK;
-		if (spi->mode & SPI_CPHA)
-			cr |= XSPI_CR_CPHA;
-		if (spi->mode & SPI_CPOL)
-			cr |= XSPI_CR_CPOL;
-		xspi->write_fn(cr, xspi->regs + XSPI_CR_OFFSET);
-
-		/* We do not check spi->max_speed_hz here as the SPI clock
-		 * frequency is not software programmable (the IP block design
-		 * parameter)
-		 */
-
-		/* Activate the chip select */
-		xspi->write_fn(~(0x0001 << spi->chip_select),
-			xspi->regs + XSPI_SSR_OFFSET);
+		xspi->write_fn(xspi->cs_inactive, xspi->regs + XSPI_SSR_OFFSET);
+		return;
 	}
+
+	/* Set the SPI clock phase and polarity */
+	cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET)	& ~XSPI_CR_MODE_MASK;
+	if (spi->mode & SPI_CPHA)
+		cr |= XSPI_CR_CPHA;
+	if (spi->mode & SPI_CPOL)
+		cr |= XSPI_CR_CPOL;
+	if (spi->mode & SPI_LSB_FIRST)
+		cr |= XSPI_CR_LSB_FIRST;
+	if (spi->mode & SPI_LOOP)
+		cr |= XSPI_CR_LOOP;
+	xspi->write_fn(cr, xspi->regs + XSPI_CR_OFFSET);
+
+	/* We do not check spi->max_speed_hz here as the SPI clock
+	 * frequency is not software programmable (the IP block design
+	 * parameter)
+	 */
+
+	cs = xspi->cs_inactive;
+	cs ^= BIT(spi->chip_select);
+
+	/* Activate the chip select */
+	xspi->write_fn(cs, xspi->regs + XSPI_SSR_OFFSET);
 }
 
 /* spi_bitbang requires custom setup_transfer() to be defined if there is a
@@ -213,85 +227,85 @@
 static int xilinx_spi_setup_transfer(struct spi_device *spi,
 		struct spi_transfer *t)
 {
+	struct xilinx_spi *xspi = spi_master_get_devdata(spi->master);
+
+	if (spi->mode & SPI_CS_HIGH)
+		xspi->cs_inactive &= ~BIT(spi->chip_select);
+	else
+		xspi->cs_inactive |= BIT(spi->chip_select);
+
 	return 0;
 }
 
-static void xilinx_spi_fill_tx_fifo(struct xilinx_spi *xspi)
-{
-	u8 sr;
-
-	/* Fill the Tx FIFO with as many bytes as possible */
-	sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET);
-	while ((sr & XSPI_SR_TX_FULL_MASK) == 0 && xspi->remaining_bytes > 0) {
-		if (xspi->tx_ptr)
-			xspi->tx_fn(xspi);
-		else
-			xspi->write_fn(0, xspi->regs + XSPI_TXD_OFFSET);
-		xspi->remaining_bytes -= xspi->bits_per_word / 8;
-		sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET);
-	}
-}
-
 static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct xilinx_spi *xspi = spi_master_get_devdata(spi->master);
-	u32 ipif_ier;
+	int remaining_words;	/* the number of words left to transfer */
+	bool use_irq = false;
+	u16 cr = 0;
 
 	/* We get here with transmitter inhibited */
 
 	xspi->tx_ptr = t->tx_buf;
 	xspi->rx_ptr = t->rx_buf;
-	xspi->remaining_bytes = t->len;
+	remaining_words = t->len / xspi->bytes_per_word;
 	reinit_completion(&xspi->done);
 
+	if (xspi->irq >= 0 &&  remaining_words > xspi->buffer_size) {
+		use_irq = true;
+		xspi->write_fn(XSPI_INTR_TX_EMPTY,
+				xspi->regs + XIPIF_V123B_IISR_OFFSET);
+		/* Enable the global IPIF interrupt */
+		xspi->write_fn(XIPIF_V123B_GINTR_ENABLE,
+				xspi->regs + XIPIF_V123B_DGIER_OFFSET);
+		/* Inhibit irq to avoid spurious irqs on tx_empty*/
+		cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET);
+		xspi->write_fn(cr | XSPI_CR_TRANS_INHIBIT,
+			       xspi->regs + XSPI_CR_OFFSET);
+	}
 
-	/* Enable the transmit empty interrupt, which we use to determine
-	 * progress on the transmission.
-	 */
-	ipif_ier = xspi->read_fn(xspi->regs + XIPIF_V123B_IIER_OFFSET);
-	xspi->write_fn(ipif_ier | XSPI_INTR_TX_EMPTY,
-		xspi->regs + XIPIF_V123B_IIER_OFFSET);
+	while (remaining_words) {
+		int n_words, tx_words, rx_words;
 
-	for (;;) {
-		u16 cr;
-		u8 sr;
+		n_words = min(remaining_words, xspi->buffer_size);
 
-		xilinx_spi_fill_tx_fifo(xspi);
+		tx_words = n_words;
+		while (tx_words--)
+			xilinx_spi_tx(xspi);
 
 		/* Start the transfer by not inhibiting the transmitter any
 		 * longer
 		 */
-		cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET) &
-							~XSPI_CR_TRANS_INHIBIT;
-		xspi->write_fn(cr, xspi->regs + XSPI_CR_OFFSET);
 
-		wait_for_completion(&xspi->done);
+		if (use_irq) {
+			xspi->write_fn(cr, xspi->regs + XSPI_CR_OFFSET);
+			wait_for_completion(&xspi->done);
+		} else
+			while (!(xspi->read_fn(xspi->regs + XSPI_SR_OFFSET) &
+						XSPI_SR_TX_EMPTY_MASK))
+				;
 
 		/* A transmit has just completed. Process received data and
 		 * check for more data to transmit. Always inhibit the
 		 * transmitter while the Isr refills the transmit register/FIFO,
 		 * or make sure it is stopped if we're done.
 		 */
-		cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET);
-		xspi->write_fn(cr | XSPI_CR_TRANS_INHIBIT,
+		if (use_irq)
+			xspi->write_fn(cr | XSPI_CR_TRANS_INHIBIT,
 			       xspi->regs + XSPI_CR_OFFSET);
 
 		/* Read out all the data from the Rx FIFO */
-		sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET);
-		while ((sr & XSPI_SR_RX_EMPTY_MASK) == 0) {
-			xspi->rx_fn(xspi);
-			sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET);
-		}
+		rx_words = n_words;
+		while (rx_words--)
+			xilinx_spi_rx(xspi);
 
-		/* See if there is more data to send */
-		if (xspi->remaining_bytes <= 0)
-			break;
+		remaining_words -= n_words;
 	}
 
-	/* Disable the transmit empty interrupt */
-	xspi->write_fn(ipif_ier, xspi->regs + XIPIF_V123B_IIER_OFFSET);
+	if (use_irq)
+		xspi->write_fn(0, xspi->regs + XIPIF_V123B_DGIER_OFFSET);
 
-	return t->len - xspi->remaining_bytes;
+	return t->len;
 }
 
 
@@ -316,6 +330,28 @@
 	return IRQ_HANDLED;
 }
 
+static int xilinx_spi_find_buffer_size(struct xilinx_spi *xspi)
+{
+	u8 sr;
+	int n_words = 0;
+
+	/*
+	 * Before the buffer_size detection we reset the core
+	 * to make sure we start with a clean state.
+	 */
+	xspi->write_fn(XIPIF_V123B_RESET_MASK,
+		xspi->regs + XIPIF_V123B_RESETR_OFFSET);
+
+	/* Fill the Tx FIFO with as many words as possible */
+	do {
+		xspi->write_fn(0, xspi->regs + XSPI_TXD_OFFSET);
+		sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET);
+		n_words++;
+	} while (!(sr & XSPI_SR_TX_FULL_MASK));
+
+	return n_words;
+}
+
 static const struct of_device_id xilinx_spi_of_match[] = {
 	{ .compatible = "xlnx,xps-spi-2.00.a", },
 	{ .compatible = "xlnx,xps-spi-2.00.b", },
@@ -348,14 +384,21 @@
 		return -EINVAL;
 	}
 
+	if (num_cs > XILINX_SPI_MAX_CS) {
+		dev_err(&pdev->dev, "Invalid number of spi slaves\n");
+		return -EINVAL;
+	}
+
 	master = spi_alloc_master(&pdev->dev, sizeof(struct xilinx_spi));
 	if (!master)
 		return -ENODEV;
 
 	/* the spi->mode bits understood by this driver: */
-	master->mode_bits = SPI_CPOL | SPI_CPHA;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST | SPI_LOOP |
+			    SPI_CS_HIGH;
 
 	xspi = spi_master_get_devdata(master);
+	xspi->cs_inactive = 0xffffffff;
 	xspi->bitbang.master = master;
 	xspi->bitbang.chipselect = xilinx_spi_chipselect;
 	xspi->bitbang.setup_transfer = xilinx_spi_setup_transfer;
@@ -392,36 +435,21 @@
 	}
 
 	master->bits_per_word_mask = SPI_BPW_MASK(bits_per_word);
-	xspi->bits_per_word = bits_per_word;
-	if (xspi->bits_per_word == 8) {
-		xspi->tx_fn = xspi_tx8;
-		xspi->rx_fn = xspi_rx8;
-	} else if (xspi->bits_per_word == 16) {
-		xspi->tx_fn = xspi_tx16;
-		xspi->rx_fn = xspi_rx16;
-	} else if (xspi->bits_per_word == 32) {
-		xspi->tx_fn = xspi_tx32;
-		xspi->rx_fn = xspi_rx32;
-	} else {
-		ret = -EINVAL;
-		goto put_master;
+	xspi->bytes_per_word = bits_per_word / 8;
+	xspi->buffer_size = xilinx_spi_find_buffer_size(xspi);
+
+	xspi->irq = platform_get_irq(pdev, 0);
+	if (xspi->irq >= 0) {
+		/* Register for SPI Interrupt */
+		ret = devm_request_irq(&pdev->dev, xspi->irq, xilinx_spi_irq, 0,
+				dev_name(&pdev->dev), xspi);
+		if (ret)
+			goto put_master;
 	}
 
 	/* SPI controller initializations */
 	xspi_init_hw(xspi);
 
-	xspi->irq = platform_get_irq(pdev, 0);
-	if (xspi->irq < 0) {
-		ret = xspi->irq;
-		goto put_master;
-	}
-
-	/* Register for SPI Interrupt */
-	ret = devm_request_irq(&pdev->dev, xspi->irq, xilinx_spi_irq, 0,
-			       dev_name(&pdev->dev), xspi);
-	if (ret)
-		goto put_master;
-
 	ret = spi_bitbang_start(&xspi->bitbang);
 	if (ret) {
 		dev_err(&pdev->dev, "spi_bitbang_start FAILED\n");
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 66a70e9..c64a3e5 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -13,10 +13,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/kernel.h>
@@ -788,7 +784,7 @@
 	struct spi_transfer *xfer;
 	bool keep_cs = false;
 	int ret = 0;
-	int ms = 1;
+	unsigned long ms = 1;
 
 	spi_set_cs(msg->spi, true);
 
@@ -875,31 +871,59 @@
 EXPORT_SYMBOL_GPL(spi_finalize_current_transfer);
 
 /**
- * spi_pump_messages - kthread work function which processes spi message queue
- * @work: pointer to kthread work struct contained in the master struct
+ * __spi_pump_messages - function which processes spi message queue
+ * @master: master to process queue for
+ * @in_kthread: true if we are in the context of the message pump thread
  *
  * This function checks if there is any spi message in the queue that
  * needs processing and if so call out to the driver to initialize hardware
  * and transfer each message.
  *
+ * Note that it is called both from the kthread itself and also from
+ * inside spi_sync(); the queue extraction handling at the top of the
+ * function should deal with this safely.
  */
-static void spi_pump_messages(struct kthread_work *work)
+static void __spi_pump_messages(struct spi_master *master, bool in_kthread)
 {
-	struct spi_master *master =
-		container_of(work, struct spi_master, pump_messages);
 	unsigned long flags;
 	bool was_busy = false;
 	int ret;
 
-	/* Lock queue and check for queue work */
+	/* Lock queue */
 	spin_lock_irqsave(&master->queue_lock, flags);
+
+	/* Make sure we are not already running a message */
+	if (master->cur_msg) {
+		spin_unlock_irqrestore(&master->queue_lock, flags);
+		return;
+	}
+
+	/* If another context is idling the device then defer */
+	if (master->idling) {
+		queue_kthread_work(&master->kworker, &master->pump_messages);
+		spin_unlock_irqrestore(&master->queue_lock, flags);
+		return;
+	}
+
+	/* Check if the queue is idle */
 	if (list_empty(&master->queue) || !master->running) {
 		if (!master->busy) {
 			spin_unlock_irqrestore(&master->queue_lock, flags);
 			return;
 		}
+
+		/* Only do teardown in the thread */
+		if (!in_kthread) {
+			queue_kthread_work(&master->kworker,
+					   &master->pump_messages);
+			spin_unlock_irqrestore(&master->queue_lock, flags);
+			return;
+		}
+
 		master->busy = false;
+		master->idling = true;
 		spin_unlock_irqrestore(&master->queue_lock, flags);
+
 		kfree(master->dummy_rx);
 		master->dummy_rx = NULL;
 		kfree(master->dummy_tx);
@@ -913,14 +937,13 @@
 			pm_runtime_put_autosuspend(master->dev.parent);
 		}
 		trace_spi_master_idle(master);
-		return;
-	}
 
-	/* Make sure we are not already running a message */
-	if (master->cur_msg) {
+		spin_lock_irqsave(&master->queue_lock, flags);
+		master->idling = false;
 		spin_unlock_irqrestore(&master->queue_lock, flags);
 		return;
 	}
+
 	/* Extract head of queue */
 	master->cur_msg =
 		list_first_entry(&master->queue, struct spi_message, queue);
@@ -985,13 +1008,22 @@
 	}
 }
 
+/**
+ * spi_pump_messages - kthread work function which processes spi message queue
+ * @work: pointer to kthread work struct contained in the master struct
+ */
+static void spi_pump_messages(struct kthread_work *work)
+{
+	struct spi_master *master =
+		container_of(work, struct spi_master, pump_messages);
+
+	__spi_pump_messages(master, true);
+}
+
 static int spi_init_queue(struct spi_master *master)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
 
-	INIT_LIST_HEAD(&master->queue);
-	spin_lock_init(&master->queue_lock);
-
 	master->running = false;
 	master->busy = false;
 
@@ -1161,12 +1193,9 @@
 	return 0;
 }
 
-/**
- * spi_queued_transfer - transfer function for queued transfers
- * @spi: spi device which is requesting transfer
- * @msg: spi message which is to handled is queued to driver queue
- */
-static int spi_queued_transfer(struct spi_device *spi, struct spi_message *msg)
+static int __spi_queued_transfer(struct spi_device *spi,
+				 struct spi_message *msg,
+				 bool need_pump)
 {
 	struct spi_master *master = spi->master;
 	unsigned long flags;
@@ -1181,13 +1210,23 @@
 	msg->status = -EINPROGRESS;
 
 	list_add_tail(&msg->queue, &master->queue);
-	if (!master->busy)
+	if (!master->busy && need_pump)
 		queue_kthread_work(&master->kworker, &master->pump_messages);
 
 	spin_unlock_irqrestore(&master->queue_lock, flags);
 	return 0;
 }
 
+/**
+ * spi_queued_transfer - transfer function for queued transfers
+ * @spi: spi device which is requesting transfer
+ * @msg: spi message which is to handled is queued to driver queue
+ */
+static int spi_queued_transfer(struct spi_device *spi, struct spi_message *msg)
+{
+	return __spi_queued_transfer(spi, msg, true);
+}
+
 static int spi_master_initialize_queue(struct spi_master *master)
 {
 	int ret;
@@ -1609,6 +1648,8 @@
 		dynamic = 1;
 	}
 
+	INIT_LIST_HEAD(&master->queue);
+	spin_lock_init(&master->queue_lock);
 	spin_lock_init(&master->bus_lock_spinlock);
 	mutex_init(&master->bus_lock_mutex);
 	master->bus_lock_flag = 0;
@@ -2114,19 +2155,46 @@
 	DECLARE_COMPLETION_ONSTACK(done);
 	int status;
 	struct spi_master *master = spi->master;
+	unsigned long flags;
+
+	status = __spi_validate(spi, message);
+	if (status != 0)
+		return status;
 
 	message->complete = spi_complete;
 	message->context = &done;
+	message->spi = spi;
 
 	if (!bus_locked)
 		mutex_lock(&master->bus_lock_mutex);
 
-	status = spi_async_locked(spi, message);
+	/* If we're not using the legacy transfer method then we will
+	 * try to transfer in the calling context so special case.
+	 * This code would be less tricky if we could remove the
+	 * support for driver implemented message queues.
+	 */
+	if (master->transfer == spi_queued_transfer) {
+		spin_lock_irqsave(&master->bus_lock_spinlock, flags);
+
+		trace_spi_message_submit(message);
+
+		status = __spi_queued_transfer(spi, message, false);
+
+		spin_unlock_irqrestore(&master->bus_lock_spinlock, flags);
+	} else {
+		status = spi_async_locked(spi, message);
+	}
 
 	if (!bus_locked)
 		mutex_unlock(&master->bus_lock_mutex);
 
 	if (status == 0) {
+		/* Push out the messages in the calling context if we
+		 * can.
+		 */
+		if (master->transfer == spi_queued_transfer)
+			__spi_pump_messages(master, false);
+
 		wait_for_completion(&done);
 		status = message->status;
 	}
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 6941e04..4eb7a98 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -14,10 +14,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
@@ -317,6 +313,37 @@
 	return status;
 }
 
+static struct spi_ioc_transfer *
+spidev_get_ioc_message(unsigned int cmd, struct spi_ioc_transfer __user *u_ioc,
+		unsigned *n_ioc)
+{
+	struct spi_ioc_transfer	*ioc;
+	u32	tmp;
+
+	/* Check type, command number and direction */
+	if (_IOC_TYPE(cmd) != SPI_IOC_MAGIC
+			|| _IOC_NR(cmd) != _IOC_NR(SPI_IOC_MESSAGE(0))
+			|| _IOC_DIR(cmd) != _IOC_WRITE)
+		return ERR_PTR(-ENOTTY);
+
+	tmp = _IOC_SIZE(cmd);
+	if ((tmp % sizeof(struct spi_ioc_transfer)) != 0)
+		return ERR_PTR(-EINVAL);
+	*n_ioc = tmp / sizeof(struct spi_ioc_transfer);
+	if (*n_ioc == 0)
+		return NULL;
+
+	/* copy into scratch area */
+	ioc = kmalloc(tmp, GFP_KERNEL);
+	if (!ioc)
+		return ERR_PTR(-ENOMEM);
+	if (__copy_from_user(ioc, u_ioc, tmp)) {
+		kfree(ioc);
+		return ERR_PTR(-EFAULT);
+	}
+	return ioc;
+}
+
 static long
 spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
@@ -456,32 +483,15 @@
 
 	default:
 		/* segmented and/or full-duplex I/O request */
-		if (_IOC_NR(cmd) != _IOC_NR(SPI_IOC_MESSAGE(0))
-				|| _IOC_DIR(cmd) != _IOC_WRITE) {
-			retval = -ENOTTY;
+		/* Check message and copy into scratch area */
+		ioc = spidev_get_ioc_message(cmd,
+				(struct spi_ioc_transfer __user *)arg, &n_ioc);
+		if (IS_ERR(ioc)) {
+			retval = PTR_ERR(ioc);
 			break;
 		}
-
-		tmp = _IOC_SIZE(cmd);
-		if ((tmp % sizeof(struct spi_ioc_transfer)) != 0) {
-			retval = -EINVAL;
-			break;
-		}
-		n_ioc = tmp / sizeof(struct spi_ioc_transfer);
-		if (n_ioc == 0)
-			break;
-
-		/* copy into scratch area */
-		ioc = kmalloc(tmp, GFP_KERNEL);
-		if (!ioc) {
-			retval = -ENOMEM;
-			break;
-		}
-		if (__copy_from_user(ioc, (void __user *)arg, tmp)) {
-			kfree(ioc);
-			retval = -EFAULT;
-			break;
-		}
+		if (!ioc)
+			break;	/* n_ioc is also 0 */
 
 		/* translate to spi_message, execute */
 		retval = spidev_message(spidev, ioc, n_ioc);
@@ -496,8 +506,67 @@
 
 #ifdef CONFIG_COMPAT
 static long
+spidev_compat_ioc_message(struct file *filp, unsigned int cmd,
+		unsigned long arg)
+{
+	struct spi_ioc_transfer __user	*u_ioc;
+	int				retval = 0;
+	struct spidev_data		*spidev;
+	struct spi_device		*spi;
+	unsigned			n_ioc, n;
+	struct spi_ioc_transfer		*ioc;
+
+	u_ioc = (struct spi_ioc_transfer __user *) compat_ptr(arg);
+	if (!access_ok(VERIFY_READ, u_ioc, _IOC_SIZE(cmd)))
+		return -EFAULT;
+
+	/* guard against device removal before, or while,
+	 * we issue this ioctl.
+	 */
+	spidev = filp->private_data;
+	spin_lock_irq(&spidev->spi_lock);
+	spi = spi_dev_get(spidev->spi);
+	spin_unlock_irq(&spidev->spi_lock);
+
+	if (spi == NULL)
+		return -ESHUTDOWN;
+
+	/* SPI_IOC_MESSAGE needs the buffer locked "normally" */
+	mutex_lock(&spidev->buf_lock);
+
+	/* Check message and copy into scratch area */
+	ioc = spidev_get_ioc_message(cmd, u_ioc, &n_ioc);
+	if (IS_ERR(ioc)) {
+		retval = PTR_ERR(ioc);
+		goto done;
+	}
+	if (!ioc)
+		goto done;	/* n_ioc is also 0 */
+
+	/* Convert buffer pointers */
+	for (n = 0; n < n_ioc; n++) {
+		ioc[n].rx_buf = (uintptr_t) compat_ptr(ioc[n].rx_buf);
+		ioc[n].tx_buf = (uintptr_t) compat_ptr(ioc[n].tx_buf);
+	}
+
+	/* translate to spi_message, execute */
+	retval = spidev_message(spidev, ioc, n_ioc);
+	kfree(ioc);
+
+done:
+	mutex_unlock(&spidev->buf_lock);
+	spi_dev_put(spi);
+	return retval;
+}
+
+static long
 spidev_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
+	if (_IOC_TYPE(cmd) == SPI_IOC_MAGIC
+			&& _IOC_NR(cmd) == _IOC_NR(SPI_IOC_MESSAGE(0))
+			&& _IOC_DIR(cmd) == _IOC_WRITE)
+		return spidev_compat_ioc_message(filp, cmd, arg);
+
 	return spidev_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
 }
 #else
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index d415d69..9484d56 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -650,8 +650,10 @@
 			break;
 		}
 		/* TODO: Should check and handle checksum. */
+
+		hdr.num_buffers = cpu_to_vhost16(vq, headcount);
 		if (likely(mergeable) &&
-		    memcpy_toiovecend(nvq->hdr, (unsigned char *)&headcount,
+		    memcpy_toiovecend(nvq->hdr, (void *)&hdr.num_buffers,
 				      offsetof(typeof(hdr), num_buffers),
 				      sizeof hdr.num_buffers)) {
 			vq_err(vq, "Failed num_buffers write");
diff --git a/fs/aio.c b/fs/aio.c
index 1b7893e..c428871 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1140,6 +1140,13 @@
 	long ret = 0;
 	int copy_ret;
 
+	/*
+	 * The mutex can block and wake us up and that will cause
+	 * wait_event_interruptible_hrtimeout() to schedule without sleeping
+	 * and repeat. This should be rare enough that it doesn't cause
+	 * peformance issues. See the comment in read_events() for more detail.
+	 */
+	sched_annotate_sleep();
 	mutex_lock(&ctx->ring_lock);
 
 	/* Access to ->ring_pages here is protected by ctx->ring_lock. */
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index a66768e..80e9c18 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -8,6 +8,7 @@
 	select LZO_DECOMPRESS
 	select RAID6_PQ
 	select XOR_BLOCKS
+	select SRCU
 
 	help
 	  Btrfs is a general purpose copy-on-write filesystem with extents,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9a02da1..1a9585d 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2591,6 +2591,7 @@
 	}
 
 	if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
+		blk_finish_plug(&plug);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = root_log_ctx.log_ret;
 		goto out;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 9c56ef7..7febcf2 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -606,9 +606,11 @@
 		*flags = CIFSSEC_MUST_NTLMV2;
 	else if ((*flags & CIFSSEC_MUST_NTLM) == CIFSSEC_MUST_NTLM)
 		*flags = CIFSSEC_MUST_NTLM;
-	else if ((*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN)
+	else if (CIFSSEC_MUST_LANMAN &&
+		 (*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN)
 		*flags = CIFSSEC_MUST_LANMAN;
-	else if ((*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT)
+	else if (CIFSSEC_MUST_PLNTXT &&
+		 (*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT)
 		*flags = CIFSSEC_MUST_PLNTXT;
 
 	*flags |= signflags;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 96b7e9b..74f1287 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -366,6 +366,7 @@
 	struct cifsLockInfo *li, *tmp;
 	struct cifs_fid fid;
 	struct cifs_pending_open open;
+	bool oplock_break_cancelled;
 
 	spin_lock(&cifs_file_list_lock);
 	if (--cifs_file->count > 0) {
@@ -397,7 +398,7 @@
 	}
 	spin_unlock(&cifs_file_list_lock);
 
-	cancel_work_sync(&cifs_file->oplock_break);
+	oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break);
 
 	if (!tcon->need_reconnect && !cifs_file->invalidHandle) {
 		struct TCP_Server_Info *server = tcon->ses->server;
@@ -409,6 +410,9 @@
 		_free_xid(xid);
 	}
 
+	if (oplock_break_cancelled)
+		cifs_done_oplock_break(cifsi);
+
 	cifs_del_pending_open(&open);
 
 	/*
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 6c15663..a4232ec 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -221,7 +221,7 @@
 	}
 
 	rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__le16));
-	memset(wpwd, 0, 129 * sizeof(__le16));
+	memzero_explicit(wpwd, sizeof(wpwd));
 
 	return rc;
 }
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 91093cd..3857040 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -141,7 +141,6 @@
  * @ti_save: Backup of journal_info field of task_struct
  * @ti_flags: Flags
  * @ti_count: Nest level
- * @ti_garbage:	List of inode to be put when releasing semaphore
  */
 struct nilfs_transaction_info {
 	u32			ti_magic;
@@ -150,7 +149,6 @@
 				   one of other filesystems has a bug. */
 	unsigned short		ti_flags;
 	unsigned short		ti_count;
-	struct list_head	ti_garbage;
 };
 
 /* ti_magic */
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 7ef18fc..469086b 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -305,7 +305,6 @@
 	ti->ti_count = 0;
 	ti->ti_save = cur_ti;
 	ti->ti_magic = NILFS_TI_MAGIC;
-	INIT_LIST_HEAD(&ti->ti_garbage);
 	current->journal_info = ti;
 
 	for (;;) {
@@ -332,8 +331,6 @@
 
 	up_write(&nilfs->ns_segctor_sem);
 	current->journal_info = ti->ti_save;
-	if (!list_empty(&ti->ti_garbage))
-		nilfs_dispose_list(nilfs, &ti->ti_garbage, 0);
 }
 
 static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
@@ -746,6 +743,15 @@
 	}
 }
 
+static void nilfs_iput_work_func(struct work_struct *work)
+{
+	struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info,
+						 sc_iput_work);
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+
+	nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0);
+}
+
 static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs,
 				     struct nilfs_root *root)
 {
@@ -1900,8 +1906,8 @@
 static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 					     struct the_nilfs *nilfs)
 {
-	struct nilfs_transaction_info *ti = current->journal_info;
 	struct nilfs_inode_info *ii, *n;
+	int defer_iput = false;
 
 	spin_lock(&nilfs->ns_inode_lock);
 	list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) {
@@ -1912,9 +1918,24 @@
 		clear_bit(NILFS_I_BUSY, &ii->i_state);
 		brelse(ii->i_bh);
 		ii->i_bh = NULL;
-		list_move_tail(&ii->i_dirty, &ti->ti_garbage);
+		list_del_init(&ii->i_dirty);
+		if (!ii->vfs_inode.i_nlink) {
+			/*
+			 * Defer calling iput() to avoid a deadlock
+			 * over I_SYNC flag for inodes with i_nlink == 0
+			 */
+			list_add_tail(&ii->i_dirty, &sci->sc_iput_queue);
+			defer_iput = true;
+		} else {
+			spin_unlock(&nilfs->ns_inode_lock);
+			iput(&ii->vfs_inode);
+			spin_lock(&nilfs->ns_inode_lock);
+		}
 	}
 	spin_unlock(&nilfs->ns_inode_lock);
+
+	if (defer_iput)
+		schedule_work(&sci->sc_iput_work);
 }
 
 /*
@@ -2583,6 +2604,8 @@
 	INIT_LIST_HEAD(&sci->sc_segbufs);
 	INIT_LIST_HEAD(&sci->sc_write_logs);
 	INIT_LIST_HEAD(&sci->sc_gc_inodes);
+	INIT_LIST_HEAD(&sci->sc_iput_queue);
+	INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func);
 	init_timer(&sci->sc_timer);
 
 	sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
@@ -2609,6 +2632,8 @@
 		ret = nilfs_segctor_construct(sci, SC_LSEG_SR);
 		nilfs_transaction_unlock(sci->sc_super);
 
+		flush_work(&sci->sc_iput_work);
+
 	} while (ret && retrycount-- > 0);
 }
 
@@ -2633,6 +2658,9 @@
 		|| sci->sc_seq_request != sci->sc_seq_done);
 	spin_unlock(&sci->sc_state_lock);
 
+	if (flush_work(&sci->sc_iput_work))
+		flag = true;
+
 	if (flag || !nilfs_segctor_confirm(sci))
 		nilfs_segctor_write_out(sci);
 
@@ -2642,6 +2670,12 @@
 		nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
 	}
 
+	if (!list_empty(&sci->sc_iput_queue)) {
+		nilfs_warning(sci->sc_super, __func__,
+			      "iput queue is not empty\n");
+		nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
+	}
+
 	WARN_ON(!list_empty(&sci->sc_segbufs));
 	WARN_ON(!list_empty(&sci->sc_write_logs));
 
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index 38a1d00..a48d6de 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -26,6 +26,7 @@
 #include <linux/types.h>
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
+#include <linux/workqueue.h>
 #include <linux/nilfs2_fs.h>
 #include "nilfs.h"
 
@@ -92,6 +93,8 @@
  * @sc_nblk_inc: Block count of current generation
  * @sc_dirty_files: List of files to be written
  * @sc_gc_inodes: List of GC inodes having blocks to be written
+ * @sc_iput_queue: list of inodes for which iput should be done
+ * @sc_iput_work: work struct to defer iput call
  * @sc_freesegs: array of segment numbers to be freed
  * @sc_nfreesegs: number of segments on @sc_freesegs
  * @sc_dsync_inode: inode whose data pages are written for a sync operation
@@ -135,6 +138,8 @@
 
 	struct list_head	sc_dirty_files;
 	struct list_head	sc_gc_inodes;
+	struct list_head	sc_iput_queue;
+	struct work_struct	sc_iput_work;
 
 	__u64		       *sc_freesegs;
 	size_t			sc_nfreesegs;
diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig
index 22c629e..2a24249 100644
--- a/fs/notify/Kconfig
+++ b/fs/notify/Kconfig
@@ -1,5 +1,6 @@
 config FSNOTIFY
 	def_bool n
+	select SRCU
 
 source "fs/notify/dnotify/Kconfig"
 source "fs/notify/inotify/Kconfig"
diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig
index c51df1d..4a09975 100644
--- a/fs/quota/Kconfig
+++ b/fs/quota/Kconfig
@@ -5,6 +5,7 @@
 config QUOTA
 	bool "Quota support"
 	select QUOTACTL
+	select SRCU
 	help
 	  If you say Y here, you will be able to set per user limits for disk
 	  usage (also called disk quotas). Currently, it works for the
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 33063f8..176bf81 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -385,7 +385,7 @@
 
 /* Is this type a native word size -- useful for atomic operations */
 #ifndef __native_word
-# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
 #endif
 
 /* Compile time object size, -1 for unknown */
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 515a35e2..960e666 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -472,27 +472,59 @@
 /**
  * vlan_get_protocol - get protocol EtherType.
  * @skb: skbuff to query
+ * @type: first vlan protocol
+ * @depth: buffer to store length of eth and vlan tags in bytes
  *
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
+static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+					 int *depth)
 {
-	__be16 protocol = 0;
+	unsigned int vlan_depth = skb->mac_len;
 
-	if (vlan_tx_tag_present(skb) ||
-	     skb->protocol != cpu_to_be16(ETH_P_8021Q))
-		protocol = skb->protocol;
-	else {
-		__be16 proto, *protop;
-		protop = skb_header_pointer(skb, offsetof(struct vlan_ethhdr,
-						h_vlan_encapsulated_proto),
-						sizeof(proto), &proto);
-		if (likely(protop))
-			protocol = *protop;
+	/* if type is 802.1Q/AD then the header should already be
+	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
+	 * ETH_HLEN otherwise
+	 */
+	if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
+		if (vlan_depth) {
+			if (WARN_ON(vlan_depth < VLAN_HLEN))
+				return 0;
+			vlan_depth -= VLAN_HLEN;
+		} else {
+			vlan_depth = ETH_HLEN;
+		}
+		do {
+			struct vlan_hdr *vh;
+
+			if (unlikely(!pskb_may_pull(skb,
+						    vlan_depth + VLAN_HLEN)))
+				return 0;
+
+			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
+			type = vh->h_vlan_encapsulated_proto;
+			vlan_depth += VLAN_HLEN;
+		} while (type == htons(ETH_P_8021Q) ||
+			 type == htons(ETH_P_8021AD));
 	}
 
-	return protocol;
+	if (depth)
+		*depth = vlan_depth;
+
+	return type;
+}
+
+/**
+ * vlan_get_protocol - get protocol EtherType.
+ * @skb: skbuff to query
+ *
+ * Returns the EtherType of the packet, regardless of whether it is
+ * vlan encapsulated (normal or hardware accelerated) or not.
+ */
+static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+{
+	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
 static inline void vlan_set_encap_proto(struct sk_buff *skb,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 25c791e..5f3a9aa 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -97,7 +97,7 @@
 	MLX4_MAX_NUM_PF		= 16,
 	MLX4_MAX_NUM_VF		= 126,
 	MLX4_MAX_NUM_VF_P_PORT  = 64,
-	MLX4_MFUNC_MAX		= 80,
+	MLX4_MFUNC_MAX		= 128,
 	MLX4_MAX_EQ_NUM		= 1024,
 	MLX4_MFUNC_EQ_NUM	= 4,
 	MLX4_MFUNC_MAX_EQES     = 8,
diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 77aed9e..dab545b 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -37,6 +37,7 @@
 #define SSDR		(0x10)  /* SSP Data Write/Data Read Register */
 
 #define SSTO		(0x28)  /* SSP Time Out Register */
+#define DDS_RATE	(0x28)  /* SSP DDS Clock Rate Register (Intel Quark) */
 #define SSPSP		(0x2C)  /* SSP Programmable Serial Protocol */
 #define SSTSA		(0x30)  /* SSP Tx Timeslot Active */
 #define SSRSA		(0x34)  /* SSP Rx Timeslot Active */
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 529bc94..a18b16f 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -524,11 +524,11 @@
  * @member:	the name of the hlist_node within the struct.
  */
 #define hlist_for_each_entry_continue_rcu(pos, member)			\
-	for (pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member);			\
+	for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \
+			&(pos)->member)), typeof(*(pos)), member);	\
 	     pos;							\
-	     pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 /**
  * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point
@@ -536,11 +536,11 @@
  * @member:	the name of the hlist_node within the struct.
  */
 #define hlist_for_each_entry_continue_rcu_bh(pos, member)		\
-	for (pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\
-			typeof(*(pos)), member);			\
+	for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(  \
+			&(pos)->member)), typeof(*(pos)), member);	\
 	     pos;							\
-	     pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 /**
  * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ed4f593..7809749 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -331,12 +331,13 @@
 extern struct srcu_struct tasks_rcu_exit_srcu;
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
+		rcu_all_qs(); \
 		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
 			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
 	} while (0)
 #else /* #ifdef CONFIG_TASKS_RCU */
 #define TASKS_RCU(x) do { } while (0)
-#define rcu_note_voluntary_context_switch(t)	do { } while (0)
+#define rcu_note_voluntary_context_switch(t)	rcu_all_qs()
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 /**
@@ -582,11 +583,11 @@
 })
 #define __rcu_dereference_check(p, c, space) \
 ({ \
-	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
+	/* Dependency order vs. p above. */ \
+	typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \
 	rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \
 	rcu_dereference_sparse(p, space); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
-	((typeof(*p) __force __kernel *)(_________p1)); \
+	((typeof(*p) __force __kernel *)(________p1)); \
 })
 #define __rcu_dereference_protected(p, c, space) \
 ({ \
@@ -603,10 +604,10 @@
 })
 #define __rcu_dereference_index_check(p, c) \
 ({ \
-	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	/* Dependency order vs. p above. */ \
+	typeof(p) _________p1 = lockless_dereference(p); \
 	rcu_lockdep_assert(c, \
 			   "suspicious rcu_dereference_index_check() usage"); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
 	(_________p1); \
 })
 
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 0e53662..937edae 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -92,17 +92,49 @@
 }
 
 /*
- * Return the number of grace periods.
+ * Return the number of grace periods started.
  */
-static inline long rcu_batches_completed(void)
+static inline unsigned long rcu_batches_started(void)
 {
 	return 0;
 }
 
 /*
- * Return the number of bottom-half grace periods.
+ * Return the number of bottom-half grace periods started.
  */
-static inline long rcu_batches_completed_bh(void)
+static inline unsigned long rcu_batches_started_bh(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of sched grace periods started.
+ */
+static inline unsigned long rcu_batches_started_sched(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of grace periods completed.
+ */
+static inline unsigned long rcu_batches_completed(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of bottom-half grace periods completed.
+ */
+static inline unsigned long rcu_batches_completed_bh(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of sched grace periods completed.
+ */
+static inline unsigned long rcu_batches_completed_sched(void)
 {
 	return 0;
 }
@@ -154,7 +186,10 @@
 	return true;
 }
 
-
 #endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
+static inline void rcu_all_qs(void)
+{
+}
+
 #endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 5295379..d2e583a 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -81,9 +81,12 @@
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
-long rcu_batches_completed(void);
-long rcu_batches_completed_bh(void);
-long rcu_batches_completed_sched(void);
+unsigned long rcu_batches_started(void);
+unsigned long rcu_batches_started_bh(void);
+unsigned long rcu_batches_started_sched(void);
+unsigned long rcu_batches_completed(void);
+unsigned long rcu_batches_completed_bh(void);
+unsigned long rcu_batches_completed_sched(void);
 void show_rcu_gp_kthreads(void);
 
 void rcu_force_quiescent_state(void);
@@ -97,4 +100,6 @@
 
 bool rcu_is_watching(void);
 
+void rcu_all_qs(void);
+
 #endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 4419b99..116655d 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -468,7 +468,7 @@
  *
  * @reg: Offset of the register within the regmap bank
  * @lsb: lsb of the register field.
- * @reg: msb of the register field.
+ * @msb: msb of the register field.
  * @id_size: port size if it has some ports
  * @id_offset: address offset for each ports
  */
diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h
index 5479394..5dd65ac 100644
--- a/include/linux/regulator/da9211.h
+++ b/include/linux/regulator/da9211.h
@@ -32,6 +32,8 @@
 	 * 2 : 2 phase 2 buck
 	 */
 	int num_buck;
+	int gpio_ren[DA9211_MAX_REGULATORS];
+	struct device_node *reg_node[DA9211_MAX_REGULATORS];
 	struct regulator_init_data *init_data[DA9211_MAX_REGULATORS];
 };
 #endif
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 5f1e9ca..d4ad5b5 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -21,6 +21,7 @@
 
 struct regmap;
 struct regulator_dev;
+struct regulator_config;
 struct regulator_init_data;
 struct regulator_enable_gpio;
 
@@ -205,6 +206,15 @@
  * @supply_name: Identifying the regulator supply
  * @of_match: Name used to identify regulator in DT.
  * @regulators_node: Name of node containing regulator definitions in DT.
+ * @of_parse_cb: Optional callback called only if of_match is present.
+ *               Will be called for each regulator parsed from DT, during
+ *               init_data parsing.
+ *               The regulator_config passed as argument to the callback will
+ *               be a copy of config passed to regulator_register, valid only
+ *               for this particular call. Callback may freely change the
+ *               config but it cannot store it for later usage.
+ *               Callback should return 0 on success or negative ERRNO
+ *               indicating failure.
  * @id: Numerical identifier for the regulator.
  * @ops: Regulator operations table.
  * @irq: Interrupt number for the regulator.
@@ -251,6 +261,9 @@
 	const char *supply_name;
 	const char *of_match;
 	const char *regulators_node;
+	int (*of_parse_cb)(struct device_node *,
+			    const struct regulator_desc *,
+			    struct regulator_config *);
 	int id;
 	bool continuous_voltage_range;
 	unsigned n_voltages;
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 0b08d05..b07562e 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -191,15 +191,22 @@
 	void *driver_data;	/* core does not touch this */
 };
 
-int regulator_suspend_prepare(suspend_state_t state);
-int regulator_suspend_finish(void);
-
 #ifdef CONFIG_REGULATOR
 void regulator_has_full_constraints(void);
+int regulator_suspend_prepare(suspend_state_t state);
+int regulator_suspend_finish(void);
 #else
 static inline void regulator_has_full_constraints(void)
 {
 }
+static inline int regulator_suspend_prepare(suspend_state_t state)
+{
+	return 0;
+}
+static inline int regulator_suspend_finish(void)
+{
+	return 0;
+}
 #endif
 
 #endif
diff --git a/include/linux/regulator/mt6397-regulator.h b/include/linux/regulator/mt6397-regulator.h
new file mode 100644
index 0000000..30cc596
--- /dev/null
+++ b/include/linux/regulator/mt6397-regulator.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Flora Fu <flora.fu@mediatek.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.
+ *
+ * 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.
+ */
+
+#ifndef __LINUX_REGULATOR_MT6397_H
+#define __LINUX_REGULATOR_MT6397_H
+
+enum {
+	MT6397_ID_VPCA15 = 0,
+	MT6397_ID_VPCA7,
+	MT6397_ID_VSRAMCA15,
+	MT6397_ID_VSRAMCA7,
+	MT6397_ID_VCORE,
+	MT6397_ID_VGPU,
+	MT6397_ID_VDRM,
+	MT6397_ID_VIO18 = 7,
+	MT6397_ID_VTCXO,
+	MT6397_ID_VA28,
+	MT6397_ID_VCAMA,
+	MT6397_ID_VIO28,
+	MT6397_ID_VUSB,
+	MT6397_ID_VMC,
+	MT6397_ID_VMCH,
+	MT6397_ID_VEMC3V3,
+	MT6397_ID_VGP1,
+	MT6397_ID_VGP2,
+	MT6397_ID_VGP3,
+	MT6397_ID_VGP4,
+	MT6397_ID_VGP5,
+	MT6397_ID_VGP6,
+	MT6397_ID_VIBR,
+	MT6397_ID_RG_MAX,
+};
+
+#define MT6397_MAX_REGULATOR	MT6397_ID_RG_MAX
+#define MT6397_REGULATOR_ID97	0x97
+#define MT6397_REGULATOR_ID91	0x91
+
+#endif /* __LINUX_REGULATOR_MT6397_H */
diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h
index 364f7a7..70c6c66 100644
--- a/include/linux/regulator/pfuze100.h
+++ b/include/linux/regulator/pfuze100.h
@@ -49,6 +49,20 @@
 #define PFUZE200_VGEN5		11
 #define PFUZE200_VGEN6		12
 
+#define PFUZE3000_SW1A		0
+#define PFUZE3000_SW1B		1
+#define PFUZE3000_SW2		2
+#define PFUZE3000_SW3		3
+#define PFUZE3000_SWBST		4
+#define PFUZE3000_VSNVS		5
+#define PFUZE3000_VREFDDR	6
+#define PFUZE3000_VLDO1		7
+#define PFUZE3000_VLDO2		8
+#define PFUZE3000_VCCSD		9
+#define PFUZE3000_V33		10
+#define PFUZE3000_VLDO3		11
+#define PFUZE3000_VLDO4		12
+
 struct regulator_init_data;
 
 struct pfuze_regulator_platform_data {
diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h
index b2b1afb..cd519a1 100644
--- a/include/linux/spi/at86rf230.h
+++ b/include/linux/spi/at86rf230.h
@@ -12,10 +12,6 @@
  * 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.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dmitry.baryshkov@siemens.com>
  */
diff --git a/include/linux/spi/l4f00242t03.h b/include/linux/spi/l4f00242t03.h
index bc8677c..e69e9b5 100644
--- a/include/linux/spi/l4f00242t03.h
+++ b/include/linux/spi/l4f00242t03.h
@@ -12,10 +12,6 @@
  * 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
 */
 
 #ifndef _INCLUDE_LINUX_SPI_L4F00242T03_H_
diff --git a/include/linux/spi/lms283gf05.h b/include/linux/spi/lms283gf05.h
index 555d254..fdd1d1d 100644
--- a/include/linux/spi/lms283gf05.h
+++ b/include/linux/spi/lms283gf05.h
@@ -11,10 +11,6 @@
  * 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
 */
 
 #ifndef _INCLUDE_LINUX_SPI_LMS283GF05_H_
diff --git a/include/linux/spi/mxs-spi.h b/include/linux/spi/mxs-spi.h
index 4835486..381d368 100644
--- a/include/linux/spi/mxs-spi.h
+++ b/include/linux/spi/mxs-spi.h
@@ -15,10 +15,6 @@
  * 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.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef __LINUX_SPI_MXS_SPI_H__
diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h
index d5a3165..6d36dac 100644
--- a/include/linux/spi/pxa2xx_spi.h
+++ b/include/linux/spi/pxa2xx_spi.h
@@ -10,10 +10,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef __linux_pxa2xx_spi_h
 #define __linux_pxa2xx_spi_h
@@ -57,7 +53,6 @@
 #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP)
 
 #include <linux/clk.h>
-#include <mach/dma.h>
 
 extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info);
 
diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h
index e546b2c..a693188 100644
--- a/include/linux/spi/rspi.h
+++ b/include/linux/spi/rspi.h
@@ -11,11 +11,6 @@
  * 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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
  */
 
 #ifndef __LINUX_SPI_RENESAS_SPI_H__
diff --git a/include/linux/spi/sh_hspi.h b/include/linux/spi/sh_hspi.h
index a1121f8..aa0d440 100644
--- a/include/linux/spi/sh_hspi.h
+++ b/include/linux/spi/sh_hspi.h
@@ -9,10 +9,6 @@
  * 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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #ifndef SH_HSPI_H
 #define SH_HSPI_H
diff --git a/include/linux/spi/sh_msiof.h b/include/linux/spi/sh_msiof.h
index 88a14d8..b087a85 100644
--- a/include/linux/spi/sh_msiof.h
+++ b/include/linux/spi/sh_msiof.h
@@ -7,6 +7,8 @@
 	u16 num_chipselect;
 	unsigned int dma_tx_id;
 	unsigned int dma_rx_id;
+	u32 dtdl;
+	u32 syncdl;
 };
 
 #endif /* __SPI_SH_MSIOF_H__ */
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index a6ef2a8..ed9489d 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -10,10 +10,6 @@
  * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __LINUX_SPI_H
@@ -260,6 +256,7 @@
  * @pump_messages: work struct for scheduling work to the message pump
  * @queue_lock: spinlock to syncronise access to message queue
  * @queue: message queue
+ * @idling: the device is entering idle state
  * @cur_msg: the currently in-flight message
  * @cur_msg_prepared: spi_prepare_message was called for the currently
  *                    in-flight message
@@ -425,6 +422,7 @@
 	spinlock_t			queue_lock;
 	struct list_head		queue;
 	struct spi_message		*cur_msg;
+	bool				idling;
 	bool				busy;
 	bool				running;
 	bool				rt;
diff --git a/include/linux/spi/tle62x0.h b/include/linux/spi/tle62x0.h
index 60b5918..414c6fd 100644
--- a/include/linux/spi/tle62x0.h
+++ b/include/linux/spi/tle62x0.h
@@ -12,10 +12,6 @@
  * 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
 */
 
 struct tle62x0_pdata {
diff --git a/include/linux/spi/tsc2005.h b/include/linux/spi/tsc2005.h
index 8f721e4..563b3b1 100644
--- a/include/linux/spi/tsc2005.h
+++ b/include/linux/spi/tsc2005.h
@@ -12,11 +12,6 @@
  * 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
- *
  */
 
 #ifndef _LINUX_SPI_TSC2005_H
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index a2783cb..9cfd962 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -45,7 +45,7 @@
 #define RCU_BATCH_INIT(name) { NULL, &(name.head) }
 
 struct srcu_struct {
-	unsigned completed;
+	unsigned long completed;
 	struct srcu_struct_array __percpu *per_cpu_ref;
 	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
 	bool running;
@@ -102,13 +102,11 @@
  * define and init a srcu struct at build time.
  * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it.
  */
-#define DEFINE_SRCU(name)						\
+#define __DEFINE_SRCU(name, is_static)					\
 	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
-	struct srcu_struct name = __SRCU_STRUCT_INIT(name);
-
-#define DEFINE_STATIC_SRCU(name)					\
-	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
-	static struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+	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)
 
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
@@ -135,7 +133,7 @@
 void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
 void synchronize_srcu_expedited(struct srcu_struct *sp);
-long srcu_batches_completed(struct srcu_struct *sp);
+unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void srcu_barrier(struct srcu_struct *sp);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index e08e21e..c728513 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -173,7 +173,7 @@
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond),,);			\
-		if (IS_ENABLED(CONFIG_LOCKDEP)) {			\
+		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			rcu_read_lock_sched_notrace();			\
 			rcu_dereference_sched(__tracepoint_##name.funcs);\
 			rcu_read_unlock_sched_notrace();		\
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 2232ed1..37423e0 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -363,7 +363,6 @@
  */
 #define wait_event_cmd(wq, condition, cmd1, cmd2)			\
 do {									\
-	might_sleep();							\
 	if (condition)							\
 		break;							\
 	__wait_event_cmd(wq, condition, cmd1, cmd2);			\
diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index 7ee2df0..dc8fd81 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -22,9 +22,9 @@
 		__be32 ports;
 		__be16 port16[2];
 	};
-	u16 thoff;
-	u16 n_proto;
-	u8 ip_proto;
+	u16	thoff;
+	__be16	n_proto;
+	u8	ip_proto;
 };
 
 bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
diff --git a/include/net/ip.h b/include/net/ip.h
index f7cbd70..09cf5ae 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -181,7 +181,7 @@
 	return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
 }
 
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4292929..6e416f6 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -671,6 +671,9 @@
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst,
+			struct in6_addr *src);
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
 void ipv6_proxy_select_ident(struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
@@ -708,7 +711,7 @@
 					__be32 flowlabel, bool autolabel)
 {
 	if (!flowlabel && (autolabel || net->ipv6.sysctl.auto_flowlabels)) {
-		__be32 hash;
+		u32 hash;
 
 		hash = skb_get_hash(skb);
 
@@ -718,7 +721,7 @@
 		 */
 		hash ^= hash >> 12;
 
-		flowlabel = hash & IPV6_FLOWLABEL_MASK;
+		flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 	}
 
 	return flowlabel;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3ae969e..9eaaa78 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -530,6 +530,8 @@
 
 int nft_chain_validate_dependency(const struct nft_chain *chain,
 				  enum nft_chain_type type);
+int nft_chain_validate_hooks(const struct nft_chain *chain,
+                             unsigned int hook_flags);
 
 struct nft_stats {
 	u64			bytes;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 24945ce..0ffef1a 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -52,6 +52,7 @@
 	struct inet_peer_base	*peers;
 	struct tcpm_hash_bucket	*tcp_metrics_hash;
 	unsigned int		tcp_metrics_hash_log;
+	struct sock  * __percpu	*tcp_sk;
 	struct netns_frags	frags;
 #ifdef CONFIG_NETFILTER
 	struct xt_table		*iptable_filter;
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 3d282cb..c605d30 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -79,6 +79,9 @@
 	struct netdev_queue	*dev_queue;
 
 	struct gnet_stats_rate_est64	rate_est;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_queue	__percpu *cpu_qstats;
+
 	struct Qdisc		*next_sched;
 	struct sk_buff		*gso_skb;
 	/*
@@ -86,15 +89,9 @@
 	 */
 	unsigned long		state;
 	struct sk_buff_head	q;
-	union {
-		struct gnet_stats_basic_packed bstats;
-		struct gnet_stats_basic_cpu __percpu *cpu_bstats;
-	} __packed;
+	struct gnet_stats_basic_packed bstats;
 	unsigned int		__state;
-	union {
-		struct gnet_stats_queue	qstats;
-		struct gnet_stats_queue	__percpu *cpu_qstats;
-	} __packed;
+	struct gnet_stats_queue	qstats;
 	struct rcu_head		rcu_head;
 	int			padded;
 	atomic_t		refcnt;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f50f29faf..9d9111e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -834,8 +834,8 @@
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
 int tcp_set_congestion_control(struct sock *sk, const char *name);
-void tcp_slow_start(struct tcp_sock *tp, u32 acked);
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
+u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
 
 u32 tcp_reno_ssthresh(struct sock *sk);
 void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 0d74f1d..65994a1 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1707,10 +1707,7 @@
 
 static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len)
 {
-	size_t copy_sz;
-
-	copy_sz = min_t(size_t, len, udata->outlen);
-	return copy_to_user(udata->outbuf, src, copy_sz) ? -EFAULT : 0;
+	return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
 }
 
 /**
diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h
index 2609048..3a34f6e 100644
--- a/include/sound/ak4113.h
+++ b/include/sound/ak4113.h
@@ -286,7 +286,7 @@
 	ak4113_write_t *write;
 	ak4113_read_t *read;
 	void *private_data;
-	unsigned int init:1;
+	atomic_t wq_processing;
 	spinlock_t lock;
 	unsigned char regmap[AK4113_WRITABLE_REGS];
 	struct snd_kcontrol *kctls[AK4113_CONTROLS];
diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h
index 52f02a6..069299a 100644
--- a/include/sound/ak4114.h
+++ b/include/sound/ak4114.h
@@ -168,7 +168,7 @@
 	ak4114_write_t * write;
 	ak4114_read_t * read;
 	void * private_data;
-	unsigned int init: 1;
+	atomic_t wq_processing;
 	spinlock_t lock;
 	unsigned char regmap[6];
 	unsigned char txcsb[5];
diff --git a/include/sound/soc.h b/include/sound/soc.h
index b4fca9a..ac8b333 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -498,6 +498,7 @@
 				unsigned int mask, unsigned int value);
 
 #ifdef CONFIG_SND_SOC_AC97_BUS
+struct snd_ac97 *snd_soc_alloc_ac97_codec(struct snd_soc_codec *codec);
 struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec);
 void snd_soc_free_ac97_codec(struct snd_ac97 *ac97);
 
diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h
index 13391d2..0e76357 100644
--- a/include/trace/events/tlb.h
+++ b/include/trace/events/tlb.h
@@ -13,11 +13,13 @@
 	{ TLB_LOCAL_SHOOTDOWN,		"local shootdown" },		\
 	{ TLB_LOCAL_MM_SHOOTDOWN,	"local mm shootdown" }
 
-TRACE_EVENT(tlb_flush,
+TRACE_EVENT_CONDITION(tlb_flush,
 
 	TP_PROTO(int reason, unsigned long pages),
 	TP_ARGS(reason, pages),
 
+	TP_CONDITION(cpu_online(smp_processor_id())),
+
 	TP_STRUCT__entry(
 		__field(	  int, reason)
 		__field(unsigned long,  pages)
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 4275b96..867cc50 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -90,7 +90,6 @@
 };
 
 enum {
-	IB_USER_VERBS_EX_CMD_QUERY_DEVICE = IB_USER_VERBS_CMD_QUERY_DEVICE,
 	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
 	IB_USER_VERBS_EX_CMD_DESTROY_FLOW,
 };
@@ -202,32 +201,6 @@
 	__u8  reserved[4];
 };
 
-enum {
-	IB_USER_VERBS_EX_QUERY_DEVICE_ODP =		1ULL << 0,
-};
-
-struct ib_uverbs_ex_query_device {
-	__u32 comp_mask;
-	__u32 reserved;
-};
-
-struct ib_uverbs_odp_caps {
-	__u64 general_caps;
-	struct {
-		__u32 rc_odp_caps;
-		__u32 uc_odp_caps;
-		__u32 ud_odp_caps;
-	} per_transport_caps;
-	__u32 reserved;
-};
-
-struct ib_uverbs_ex_query_device_resp {
-	struct ib_uverbs_query_device_resp base;
-	__u32 comp_mask;
-	__u32 reserved;
-	struct ib_uverbs_odp_caps odp_caps;
-};
-
 struct ib_uverbs_query_port {
 	__u64 response;
 	__u8  port_num;
diff --git a/init/Kconfig b/init/Kconfig
index 9afb971..1354ac09 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -470,7 +470,6 @@
 config TREE_RCU
 	bool "Tree-based hierarchical RCU"
 	depends on !PREEMPT && SMP
-	select IRQ_WORK
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
@@ -480,7 +479,6 @@
 config PREEMPT_RCU
 	bool "Preemptible tree-based hierarchical RCU"
 	depends on PREEMPT
-	select IRQ_WORK
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
@@ -501,9 +499,17 @@
 
 endchoice
 
+config SRCU
+	bool
+	help
+	  This option selects the sleepable version of RCU. This version
+	  permits arbitrary sleeping or blocking within RCU read-side critical
+	  sections.
+
 config TASKS_RCU
 	bool "Task_based RCU implementation using voluntary context switch"
 	default n
+	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses
 	  only voluntary context switch (not preemption!), idle, and
@@ -668,9 +674,10 @@
 
 config RCU_KTHREAD_PRIO
 	int "Real-time priority to use for RCU worker threads"
-	range 1 99
-	depends on RCU_BOOST
-	default 1
+	range 1 99 if RCU_BOOST
+	range 0 99 if !RCU_BOOST
+	default 1 if RCU_BOOST
+	default 0 if !RCU_BOOST
 	help
 	  This option specifies the SCHED_FIFO priority value that will be
 	  assigned to the rcuc/n and rcub/n threads and is also the value
@@ -1595,6 +1602,7 @@
 	depends on HAVE_PERF_EVENTS
 	select ANON_INODES
 	select IRQ_WORK
+	select SRCU
 	help
 	  Enable kernel support for various performance events provided
 	  by software and hardware.
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5d22023..1972b16 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -58,22 +58,23 @@
 
 static struct {
 	struct task_struct *active_writer;
-	struct mutex lock; /* Synchronizes accesses to refcount, */
+	/* wait queue to wake up the active_writer */
+	wait_queue_head_t wq;
+	/* verifies that no writer will get active while readers are active */
+	struct mutex lock;
 	/*
 	 * Also blocks the new readers during
 	 * an ongoing cpu hotplug operation.
 	 */
-	int refcount;
-	/* And allows lockless put_online_cpus(). */
-	atomic_t puts_pending;
+	atomic_t refcount;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
 #endif
 } cpu_hotplug = {
 	.active_writer = NULL,
+	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
 	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
-	.refcount = 0,
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	.dep_map = {.name = "cpu_hotplug.lock" },
 #endif
@@ -86,15 +87,6 @@
 #define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
 #define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
 
-static void apply_puts_pending(int max)
-{
-	int delta;
-
-	if (atomic_read(&cpu_hotplug.puts_pending) >= max) {
-		delta = atomic_xchg(&cpu_hotplug.puts_pending, 0);
-		cpu_hotplug.refcount -= delta;
-	}
-}
 
 void get_online_cpus(void)
 {
@@ -103,8 +95,7 @@
 		return;
 	cpuhp_lock_acquire_read();
 	mutex_lock(&cpu_hotplug.lock);
-	apply_puts_pending(65536);
-	cpu_hotplug.refcount++;
+	atomic_inc(&cpu_hotplug.refcount);
 	mutex_unlock(&cpu_hotplug.lock);
 }
 EXPORT_SYMBOL_GPL(get_online_cpus);
@@ -116,8 +107,7 @@
 	if (!mutex_trylock(&cpu_hotplug.lock))
 		return false;
 	cpuhp_lock_acquire_tryread();
-	apply_puts_pending(65536);
-	cpu_hotplug.refcount++;
+	atomic_inc(&cpu_hotplug.refcount);
 	mutex_unlock(&cpu_hotplug.lock);
 	return true;
 }
@@ -125,20 +115,18 @@
 
 void put_online_cpus(void)
 {
+	int refcount;
+
 	if (cpu_hotplug.active_writer == current)
 		return;
-	if (!mutex_trylock(&cpu_hotplug.lock)) {
-		atomic_inc(&cpu_hotplug.puts_pending);
-		cpuhp_lock_release();
-		return;
-	}
 
-	if (WARN_ON(!cpu_hotplug.refcount))
-		cpu_hotplug.refcount++; /* try to fix things up */
+	refcount = atomic_dec_return(&cpu_hotplug.refcount);
+	if (WARN_ON(refcount < 0)) /* try to fix things up */
+		atomic_inc(&cpu_hotplug.refcount);
 
-	if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
-		wake_up_process(cpu_hotplug.active_writer);
-	mutex_unlock(&cpu_hotplug.lock);
+	if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq))
+		wake_up(&cpu_hotplug.wq);
+
 	cpuhp_lock_release();
 
 }
@@ -168,18 +156,20 @@
  */
 void cpu_hotplug_begin(void)
 {
-	cpu_hotplug.active_writer = current;
+	DEFINE_WAIT(wait);
 
+	cpu_hotplug.active_writer = current;
 	cpuhp_lock_acquire();
+
 	for (;;) {
 		mutex_lock(&cpu_hotplug.lock);
-		apply_puts_pending(1);
-		if (likely(!cpu_hotplug.refcount))
-			break;
-		__set_current_state(TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE);
+		if (likely(!atomic_read(&cpu_hotplug.refcount)))
+				break;
 		mutex_unlock(&cpu_hotplug.lock);
 		schedule();
 	}
+	finish_wait(&cpu_hotplug.wq, &wait);
 }
 
 void cpu_hotplug_done(void)
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 4803da6..ae9fc7c 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -402,6 +402,7 @@
 }
 EXPORT_SYMBOL_GPL(raw_notifier_call_chain);
 
+#ifdef CONFIG_SRCU
 /*
  *	SRCU notifier chain routines.    Registration and unregistration
  *	use a mutex, and call_chain is synchronized by SRCU (no locks).
@@ -528,6 +529,8 @@
 }
 EXPORT_SYMBOL_GPL(srcu_init_notifier_head);
 
+#endif /* CONFIG_SRCU */
+
 static ATOMIC_NOTIFIER_HEAD(die_chain);
 
 int notrace notify_die(enum die_val val, const char *str,
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 48b28d3..7e01f78 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -251,6 +251,7 @@
 
 config PM_OPP
 	bool
+	select SRCU
 	---help---
 	  SOCs have a standard set of tuples consisting of frequency and
 	  voltage pairs that the device will support per voltage domain. This
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index e6fae50..50a8084 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,4 +1,5 @@
-obj-y += update.o srcu.o
+obj-y += update.o
+obj-$(CONFIG_SRCU) += srcu.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += tree.o
 obj-$(CONFIG_PREEMPT_RCU) += tree.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 07bb02e..80adef7 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -137,4 +137,10 @@
 
 void rcu_early_boot_tests(void);
 
+/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
 #endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 4d559ba..30d42aa 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -244,7 +244,8 @@
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
-	int (*completed)(void);
+	unsigned long (*started)(void);
+	unsigned long (*completed)(void);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*exp_sync)(void);
@@ -296,11 +297,6 @@
 	rcu_read_unlock();
 }
 
-static int rcu_torture_completed(void)
-{
-	return rcu_batches_completed();
-}
-
 /*
  * Update callback in the pipe.  This should be invoked after a grace period.
  */
@@ -356,7 +352,7 @@
 		cur_ops->deferred_free(rp);
 }
 
-static int rcu_no_completed(void)
+static unsigned long rcu_no_completed(void)
 {
 	return 0;
 }
@@ -377,7 +373,8 @@
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
-	.completed	= rcu_torture_completed,
+	.started	= rcu_batches_started,
+	.completed	= rcu_batches_completed,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
@@ -407,11 +404,6 @@
 	rcu_read_unlock_bh();
 }
 
-static int rcu_bh_torture_completed(void)
-{
-	return rcu_batches_completed_bh();
-}
-
 static void rcu_bh_torture_deferred_free(struct rcu_torture *p)
 {
 	call_rcu_bh(&p->rtort_rcu, rcu_torture_cb);
@@ -423,7 +415,8 @@
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
-	.completed	= rcu_bh_torture_completed,
+	.started	= rcu_batches_started_bh,
+	.completed	= rcu_batches_completed_bh,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
 	.exp_sync	= synchronize_rcu_bh_expedited,
@@ -466,6 +459,7 @@
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_busted_torture_deferred_free,
 	.sync		= synchronize_rcu_busted,
@@ -510,7 +504,7 @@
 	srcu_read_unlock(&srcu_ctl, idx);
 }
 
-static int srcu_torture_completed(void)
+static unsigned long srcu_torture_completed(void)
 {
 	return srcu_batches_completed(&srcu_ctl);
 }
@@ -564,6 +558,7 @@
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
+	.started	= NULL,
 	.completed	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
@@ -600,7 +595,8 @@
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
-	.completed	= rcu_no_completed,
+	.started	= rcu_batches_started_sched,
+	.completed	= rcu_batches_completed_sched,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
 	.exp_sync	= synchronize_sched_expedited,
@@ -638,6 +634,7 @@
 	.readlock	= tasks_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= tasks_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
@@ -1015,8 +1012,8 @@
 static void rcu_torture_timer(unsigned long unused)
 {
 	int idx;
-	int completed;
-	int completed_end;
+	unsigned long started;
+	unsigned long completed;
 	static DEFINE_TORTURE_RANDOM(rand);
 	static DEFINE_SPINLOCK(rand_lock);
 	struct rcu_torture *p;
@@ -1024,7 +1021,10 @@
 	unsigned long long ts;
 
 	idx = cur_ops->readlock();
-	completed = cur_ops->completed();
+	if (cur_ops->started)
+		started = cur_ops->started();
+	else
+		started = cur_ops->completed();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
@@ -1047,14 +1047,16 @@
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	completed_end = cur_ops->completed();
+	completed = cur_ops->completed();
 	if (pipe_count > 1) {
 		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
-					  completed, completed_end);
+					  started, completed);
 		rcutorture_trace_dump();
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = completed_end - completed;
+	completed = completed - started;
+	if (cur_ops->started)
+		completed++;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
@@ -1073,8 +1075,8 @@
 static int
 rcu_torture_reader(void *arg)
 {
-	int completed;
-	int completed_end;
+	unsigned long started;
+	unsigned long completed;
 	int idx;
 	DEFINE_TORTURE_RANDOM(rand);
 	struct rcu_torture *p;
@@ -1093,7 +1095,10 @@
 				mod_timer(&t, jiffies + 1);
 		}
 		idx = cur_ops->readlock();
-		completed = cur_ops->completed();
+		if (cur_ops->started)
+			started = cur_ops->started();
+		else
+			started = cur_ops->completed();
 		ts = rcu_trace_clock_local();
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
@@ -1114,14 +1119,16 @@
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		completed_end = cur_ops->completed();
+		completed = cur_ops->completed();
 		if (pipe_count > 1) {
 			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-						  ts, completed, completed_end);
+						  ts, started, completed);
 			rcutorture_trace_dump();
 		}
 		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = completed_end - completed;
+		completed = completed - started;
+		if (cur_ops->started)
+			completed++;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
@@ -1420,6 +1427,9 @@
 		cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
 		if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
 			n_rcu_torture_barrier_error++;
+			pr_err("barrier_cbs_invoked = %d, n_barrier_cbs = %d\n",
+			       atomic_read(&barrier_cbs_invoked),
+			       n_barrier_cbs);
 			WARN_ON_ONCE(1);
 		}
 		n_barrier_successes++;
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index e037f3e..445bf8f 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -546,7 +546,7 @@
  * Report the number of batches, correlated with, but not necessarily
  * precisely the same as, the number of grace periods that have elapsed.
  */
-long srcu_batches_completed(struct srcu_struct *sp)
+unsigned long srcu_batches_completed(struct srcu_struct *sp)
 {
 	return sp->completed;
 }
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 0db5649..cc9ceca 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -47,54 +47,14 @@
 		       void (*func)(struct rcu_head *rcu),
 		       struct rcu_ctrlblk *rcp);
 
-static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-
 #include "tiny_plugin.h"
 
-/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcu/tree.c. */
-static void rcu_idle_enter_common(long long newval)
-{
-	if (newval) {
-		RCU_TRACE(trace_rcu_dyntick(TPS("--="),
-					    rcu_dynticks_nesting, newval));
-		rcu_dynticks_nesting = newval;
-		return;
-	}
-	RCU_TRACE(trace_rcu_dyntick(TPS("Start"),
-				    rcu_dynticks_nesting, newval));
-	if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
-		struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
-
-		RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"),
-					    rcu_dynticks_nesting, newval));
-		ftrace_dump(DUMP_ALL);
-		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
-			  current->pid, current->comm,
-			  idle->pid, idle->comm); /* must be idle task! */
-	}
-	rcu_sched_qs(); /* implies rcu_bh_inc() */
-	barrier();
-	rcu_dynticks_nesting = newval;
-}
-
 /*
  * Enter idle, which is an extended quiescent state if we have fully
- * entered that mode (i.e., if the new value of dynticks_nesting is zero).
+ * entered that mode.
  */
 void rcu_idle_enter(void)
 {
-	unsigned long flags;
-	long long newval;
-
-	local_irq_save(flags);
-	WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
-	if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) ==
-	    DYNTICK_TASK_NEST_VALUE)
-		newval = 0;
-	else
-		newval = rcu_dynticks_nesting - DYNTICK_TASK_NEST_VALUE;
-	rcu_idle_enter_common(newval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
@@ -103,55 +63,14 @@
  */
 void rcu_irq_exit(void)
 {
-	unsigned long flags;
-	long long newval;
-
-	local_irq_save(flags);
-	newval = rcu_dynticks_nesting - 1;
-	WARN_ON_ONCE(newval < 0);
-	rcu_idle_enter_common(newval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_irq_exit);
 
-/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcu/tree.c. */
-static void rcu_idle_exit_common(long long oldval)
-{
-	if (oldval) {
-		RCU_TRACE(trace_rcu_dyntick(TPS("++="),
-					    oldval, rcu_dynticks_nesting));
-		return;
-	}
-	RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting));
-	if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
-		struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
-
-		RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"),
-			  oldval, rcu_dynticks_nesting));
-		ftrace_dump(DUMP_ALL);
-		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
-			  current->pid, current->comm,
-			  idle->pid, idle->comm); /* must be idle task! */
-	}
-}
-
 /*
  * Exit idle, so that we are no longer in an extended quiescent state.
  */
 void rcu_idle_exit(void)
 {
-	unsigned long flags;
-	long long oldval;
-
-	local_irq_save(flags);
-	oldval = rcu_dynticks_nesting;
-	WARN_ON_ONCE(rcu_dynticks_nesting < 0);
-	if (rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK)
-		rcu_dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
-	else
-		rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-	rcu_idle_exit_common(oldval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_exit);
 
@@ -160,15 +79,6 @@
  */
 void rcu_irq_enter(void)
 {
-	unsigned long flags;
-	long long oldval;
-
-	local_irq_save(flags);
-	oldval = rcu_dynticks_nesting;
-	rcu_dynticks_nesting++;
-	WARN_ON_ONCE(rcu_dynticks_nesting == 0);
-	rcu_idle_exit_common(oldval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_irq_enter);
 
@@ -179,23 +89,13 @@
  */
 bool notrace __rcu_is_watching(void)
 {
-	return rcu_dynticks_nesting;
+	return true;
 }
 EXPORT_SYMBOL(__rcu_is_watching);
 
 #endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
 /*
- * Test whether the current CPU was interrupted from idle.  Nested
- * interrupts don't count, we must be running at the first interrupt
- * level.
- */
-static int rcu_is_cpu_rrupt_from_idle(void)
-{
-	return rcu_dynticks_nesting <= 1;
-}
-
-/*
  * Helper function for rcu_sched_qs() and rcu_bh_qs().
  * Also irqs are disabled to avoid confusion due to interrupt handlers
  * invoking call_rcu().
@@ -250,7 +150,7 @@
 void rcu_check_callbacks(int user)
 {
 	RCU_TRACE(check_cpu_stalls());
-	if (user || rcu_is_cpu_rrupt_from_idle())
+	if (user)
 		rcu_sched_qs();
 	else if (!in_softirq())
 		rcu_bh_qs();
@@ -357,6 +257,11 @@
 	rcp->curtail = &head->next;
 	RCU_TRACE(rcp->qlen++);
 	local_irq_restore(flags);
+
+	if (unlikely(is_idle_task(current))) {
+		/* force scheduling for rcu_sched_qs() */
+		resched_cpu(0);
+	}
 }
 
 /*
@@ -383,6 +288,8 @@
 void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+	RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk));
+	RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk));
 
 	rcu_early_boot_tests();
 }
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index 858c565..f94e209 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -145,17 +145,16 @@
 	rcp->ticks_this_gp++;
 	j = jiffies;
 	js = ACCESS_ONCE(rcp->jiffies_stall);
-	if (*rcp->curtail && ULONG_CMP_GE(j, js)) {
+	if (rcp->rcucblist && ULONG_CMP_GE(j, js)) {
 		pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
-		       rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting,
+		       rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE,
 		       jiffies - rcp->gp_start, rcp->qlen);
 		dump_stack();
-	}
-	if (*rcp->curtail && ULONG_CMP_GE(j, js))
 		ACCESS_ONCE(rcp->jiffies_stall) = jiffies +
 			3 * rcu_jiffies_till_stall_check() + 3;
-	else if (ULONG_CMP_GE(j, js))
+	} else if (ULONG_CMP_GE(j, js)) {
 		ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
+	}
 }
 
 static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7680fc2..48d640c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -156,6 +156,10 @@
 static void invoke_rcu_core(void);
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 
+/* rcuc/rcub kthread realtime priority */
+static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
+module_param(kthread_prio, int, 0644);
+
 /*
  * Track the rcutorture test sequence number and the update version
  * number within a given test.  The rcutorture_testseq is incremented
@@ -215,6 +219,9 @@
 #endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 };
 
+DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
+EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
+
 /*
  * Let the RCU core know that this CPU has gone through the scheduler,
  * which is a quiescent state.  This is called when the need for a
@@ -284,6 +291,22 @@
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
+/*
+ * Register a quiesecent state for all RCU flavors.  If there is an
+ * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight
+ * dyntick-idle quiescent state visible to other CPUs (but only for those
+ * RCU flavors in desparate need of a quiescent state, which will normally
+ * be none of them).  Either way, do a lightweight quiescent state for
+ * all RCU flavors.
+ */
+void rcu_all_qs(void)
+{
+	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+		rcu_momentary_dyntick_idle();
+	this_cpu_inc(rcu_qs_ctr);
+}
+EXPORT_SYMBOL_GPL(rcu_all_qs);
+
 static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
 static long qhimark = 10000;	/* If this many pending, ignore blimit. */
 static long qlowmark = 100;	/* Once only this many pending, use blimit. */
@@ -315,18 +338,54 @@
 static int rcu_pending(void);
 
 /*
- * Return the number of RCU-sched batches processed thus far for debug & stats.
+ * Return the number of RCU batches started thus far for debug & stats.
  */
-long rcu_batches_completed_sched(void)
+unsigned long rcu_batches_started(void)
+{
+	return rcu_state_p->gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started);
+
+/*
+ * Return the number of RCU-sched batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started_sched(void)
+{
+	return rcu_sched_state.gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
+
+/*
+ * Return the number of RCU BH batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started_bh(void)
+{
+	return rcu_bh_state.gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
+
+/*
+ * Return the number of RCU batches completed thus far for debug & stats.
+ */
+unsigned long rcu_batches_completed(void)
+{
+	return rcu_state_p->completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Return the number of RCU-sched batches completed thus far for debug & stats.
+ */
+unsigned long rcu_batches_completed_sched(void)
 {
 	return rcu_sched_state.completed;
 }
 EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 
 /*
- * Return the number of RCU BH batches processed thus far for debug & stats.
+ * Return the number of RCU BH batches completed thus far for debug & stats.
  */
-long rcu_batches_completed_bh(void)
+unsigned long rcu_batches_completed_bh(void)
 {
 	return rcu_bh_state.completed;
 }
@@ -759,39 +818,71 @@
 /**
  * rcu_nmi_enter - inform RCU of entry to NMI context
  *
- * If the CPU was idle with dynamic ticks active, and there is no
- * irq handler running, this updates rdtp->dynticks_nmi to let the
- * RCU grace-period handling know that the CPU is active.
+ * If the CPU was idle from RCU's viewpoint, update rdtp->dynticks and
+ * rdtp->dynticks_nmi_nesting to let the RCU grace-period handling know
+ * that the CPU is active.  This implementation permits nested NMIs, as
+ * long as the nesting level does not overflow an int.  (You will probably
+ * run out of stack space first.)
  */
 void rcu_nmi_enter(void)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int incby = 2;
 
-	if (rdtp->dynticks_nmi_nesting == 0 &&
-	    (atomic_read(&rdtp->dynticks) & 0x1))
-		return;
-	rdtp->dynticks_nmi_nesting++;
-	smp_mb__before_atomic();  /* Force delay from prior write. */
-	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(!(atomic_read(&rdtp->dynticks) & 0x1));
+	/* Complain about underflow. */
+	WARN_ON_ONCE(rdtp->dynticks_nmi_nesting < 0);
+
+	/*
+	 * If idle from RCU viewpoint, atomically increment ->dynticks
+	 * to mark non-idle and increment ->dynticks_nmi_nesting by one.
+	 * Otherwise, increment ->dynticks_nmi_nesting by two.  This means
+	 * if ->dynticks_nmi_nesting is equal to one, we are guaranteed
+	 * 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));
+		incby = 1;
+	}
+	rdtp->dynticks_nmi_nesting += incby;
+	barrier();
 }
 
 /**
  * rcu_nmi_exit - inform RCU of exit from NMI context
  *
- * If the CPU was idle with dynamic ticks active, and there is no
- * irq handler running, this updates rdtp->dynticks_nmi to let the
- * RCU grace-period handling know that the CPU is no longer active.
+ * If we are returning from the outermost NMI handler that interrupted an
+ * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting
+ * to let the RCU grace-period handling know that the CPU is back to
+ * being RCU-idle.
  */
 void rcu_nmi_exit(void)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
-	if (rdtp->dynticks_nmi_nesting == 0 ||
-	    --rdtp->dynticks_nmi_nesting != 0)
+	/*
+	 * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
+	 * (We are exiting an NMI handler, so RCU better be paying attention
+	 * to us!)
+	 */
+	WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0);
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+
+	/*
+	 * If the nesting level is not 1, the CPU wasn't RCU-idle, so
+	 * leave it in non-RCU-idle state.
+	 */
+	if (rdtp->dynticks_nmi_nesting != 1) {
+		rdtp->dynticks_nmi_nesting -= 2;
 		return;
+	}
+
+	/* 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);
@@ -898,17 +989,14 @@
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
 		return 1;
 	} else {
+		if (ULONG_CMP_LT(ACCESS_ONCE(rdp->gpnum) + ULONG_MAX / 4,
+				 rdp->mynode->gpnum))
+			ACCESS_ONCE(rdp->gpwrap) = true;
 		return 0;
 	}
 }
 
 /*
- * This function really isn't for public consumption, but RCU is special in
- * that context switches can allow the state machine to make progress.
- */
-extern void resched_cpu(int cpu);
-
-/*
  * Return true if the specified CPU has passed through a quiescent
  * state by virtue of being in or having passed through an dynticks
  * idle state since the last call to dyntick_save_progress_counter()
@@ -1011,6 +1099,22 @@
 	j1 = rcu_jiffies_till_stall_check();
 	ACCESS_ONCE(rsp->jiffies_stall) = j + j1;
 	rsp->jiffies_resched = j + j1 / 2;
+	rsp->n_force_qs_gpstart = ACCESS_ONCE(rsp->n_force_qs);
+}
+
+/*
+ * Complain about starvation of grace-period kthread.
+ */
+static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
+{
+	unsigned long gpa;
+	unsigned long j;
+
+	j = jiffies;
+	gpa = ACCESS_ONCE(rsp->gp_activity);
+	if (j - gpa > 2 * HZ)
+		pr_err("%s kthread starved for %ld jiffies!\n",
+		       rsp->name, j - gpa);
 }
 
 /*
@@ -1033,11 +1137,13 @@
 	}
 }
 
-static void print_other_cpu_stall(struct rcu_state *rsp)
+static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 {
 	int cpu;
 	long delta;
 	unsigned long flags;
+	unsigned long gpa;
+	unsigned long j;
 	int ndetected = 0;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	long totqlen = 0;
@@ -1075,30 +1181,34 @@
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 
-	/*
-	 * Now rat on any tasks that got kicked up to the root rcu_node
-	 * due to CPU offlining.
-	 */
-	rnp = rcu_get_root(rsp);
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	ndetected += rcu_print_task_stall(rnp);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-
 	print_cpu_stall_info_end();
 	for_each_possible_cpu(cpu)
 		totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
 	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start),
 	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
-	if (ndetected == 0)
-		pr_err("INFO: Stall ended before state dump start\n");
-	else
+	if (ndetected) {
 		rcu_dump_cpu_stacks(rsp);
+	} else {
+		if (ACCESS_ONCE(rsp->gpnum) != gpnum ||
+		    ACCESS_ONCE(rsp->completed) == gpnum) {
+			pr_err("INFO: Stall ended before state dump start\n");
+		} else {
+			j = jiffies;
+			gpa = ACCESS_ONCE(rsp->gp_activity);
+			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld\n",
+			       rsp->name, j - gpa, j, gpa,
+			       jiffies_till_next_fqs);
+			/* In this case, the current CPU might be at fault. */
+			sched_show_task(current);
+		}
+	}
 
 	/* Complain about tasks blocking the grace period. */
-
 	rcu_print_detail_task_stall(rsp);
 
+	rcu_check_gp_kthread_starvation(rsp);
+
 	force_quiescent_state(rsp);  /* Kick them all. */
 }
 
@@ -1123,6 +1233,9 @@
 	pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
 		jiffies - rsp->gp_start,
 		(long)rsp->gpnum, (long)rsp->completed, totqlen);
+
+	rcu_check_gp_kthread_starvation(rsp);
+
 	rcu_dump_cpu_stacks(rsp);
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -1193,7 +1306,7 @@
 		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
 
 		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(rsp);
+		print_other_cpu_stall(rsp, gpnum);
 	}
 }
 
@@ -1530,7 +1643,8 @@
 	bool ret;
 
 	/* Handle the ends of any preceding grace periods first. */
-	if (rdp->completed == rnp->completed) {
+	if (rdp->completed == rnp->completed &&
+	    !unlikely(ACCESS_ONCE(rdp->gpwrap))) {
 
 		/* No grace period end, so just accelerate recent callbacks. */
 		ret = rcu_accelerate_cbs(rsp, rnp, rdp);
@@ -1545,7 +1659,7 @@
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
 	}
 
-	if (rdp->gpnum != rnp->gpnum) {
+	if (rdp->gpnum != rnp->gpnum || unlikely(ACCESS_ONCE(rdp->gpwrap))) {
 		/*
 		 * If the current grace period is waiting for this CPU,
 		 * set up to detect a quiescent state, otherwise don't
@@ -1554,8 +1668,10 @@
 		rdp->gpnum = rnp->gpnum;
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
 		rdp->passed_quiesce = 0;
+		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
 		zero_cpu_stall_ticks(rdp);
+		ACCESS_ONCE(rdp->gpwrap) = false;
 	}
 	return ret;
 }
@@ -1569,7 +1685,8 @@
 	local_irq_save(flags);
 	rnp = rdp->mynode;
 	if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) &&
-	     rdp->completed == ACCESS_ONCE(rnp->completed)) || /* w/out lock. */
+	     rdp->completed == ACCESS_ONCE(rnp->completed) &&
+	     !unlikely(ACCESS_ONCE(rdp->gpwrap))) || /* w/out lock. */
 	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
 		return;
@@ -1589,6 +1706,7 @@
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
+	ACCESS_ONCE(rsp->gp_activity) = jiffies;
 	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
 	smp_mb__after_unlock_lock();
@@ -1649,6 +1767,7 @@
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
+		ACCESS_ONCE(rsp->gp_activity) = jiffies;
 	}
 
 	mutex_unlock(&rsp->onoff_mutex);
@@ -1665,6 +1784,7 @@
 	unsigned long maxj;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
+	ACCESS_ONCE(rsp->gp_activity) = jiffies;
 	rsp->n_force_qs++;
 	if (fqs_state == RCU_SAVE_DYNTICK) {
 		/* Collect dyntick-idle snapshots. */
@@ -1703,6 +1823,7 @@
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
+	ACCESS_ONCE(rsp->gp_activity) = jiffies;
 	raw_spin_lock_irq(&rnp->lock);
 	smp_mb__after_unlock_lock();
 	gp_duration = jiffies - rsp->gp_start;
@@ -1739,6 +1860,7 @@
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
+		ACCESS_ONCE(rsp->gp_activity) = jiffies;
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
@@ -1788,6 +1910,7 @@
 			if (rcu_gp_init(rsp))
 				break;
 			cond_resched_rcu_qs();
+			ACCESS_ONCE(rsp->gp_activity) = jiffies;
 			WARN_ON(signal_pending(current));
 			trace_rcu_grace_period(rsp->name,
 					       ACCESS_ONCE(rsp->gpnum),
@@ -1831,9 +1954,11 @@
 						       ACCESS_ONCE(rsp->gpnum),
 						       TPS("fqsend"));
 				cond_resched_rcu_qs();
+				ACCESS_ONCE(rsp->gp_activity) = jiffies;
 			} else {
 				/* Deal with stray signal. */
 				cond_resched_rcu_qs();
+				ACCESS_ONCE(rsp->gp_activity) = jiffies;
 				WARN_ON(signal_pending(current));
 				trace_rcu_grace_period(rsp->name,
 						       ACCESS_ONCE(rsp->gpnum),
@@ -2010,8 +2135,10 @@
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();
-	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
-	    rnp->completed == rnp->gpnum) {
+	if ((rdp->passed_quiesce == 0 &&
+	     rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
+	    rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
+	    rdp->gpwrap) {
 
 		/*
 		 * The grace period in which this quiescent state was
@@ -2020,6 +2147,7 @@
 		 * within the current grace period.
 		 */
 		rdp->passed_quiesce = 0;	/* need qs for new gp. */
+		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
@@ -2064,7 +2192,8 @@
 	 * Was there a quiescent state since the beginning of the grace
 	 * period? If no, then exit and wait for the next call.
 	 */
-	if (!rdp->passed_quiesce)
+	if (!rdp->passed_quiesce &&
+	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr))
 		return;
 
 	/*
@@ -2195,6 +2324,46 @@
 }
 
 /*
+ * All CPUs for the specified rcu_node structure have gone offline,
+ * and all tasks that were preempted within an RCU read-side critical
+ * section while running on one of those CPUs have since exited their RCU
+ * read-side critical section.  Some other CPU is reporting this fact with
+ * the specified rcu_node structure's ->lock held and interrupts disabled.
+ * This function therefore goes up the tree of rcu_node structures,
+ * clearing the corresponding bits in the ->qsmaskinit fields.  Note that
+ * the leaf rcu_node structure's ->qsmaskinit field has already been
+ * updated
+ *
+ * This function does check that the specified rcu_node structure has
+ * all CPUs offline and no blocked tasks, so it is OK to invoke it
+ * prematurely.  That said, invoking it after the fact will cost you
+ * a needless lock acquisition.  So once it has done its work, don't
+ * invoke it again.
+ */
+static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
+{
+	long mask;
+	struct rcu_node *rnp = rnp_leaf;
+
+	if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+		return;
+	for (;;) {
+		mask = rnp->grpmask;
+		rnp = rnp->parent;
+		if (!rnp)
+			break;
+		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		smp_mb__after_unlock_lock(); /* GP memory ordering. */
+		rnp->qsmaskinit &= ~mask;
+		if (rnp->qsmaskinit) {
+			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+			return;
+		}
+		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+	}
+}
+
+/*
  * The CPU has been completely removed, and some other CPU is reporting
  * this fact from process context.  Do the remainder of the cleanup,
  * including orphaning the outgoing CPU's RCU callbacks, and also
@@ -2204,8 +2373,6 @@
 static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
-	unsigned long mask;
-	int need_report = 0;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
@@ -2219,40 +2386,15 @@
 	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
 	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
 	rcu_adopt_orphan_cbs(rsp, flags);
+	raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);
 
-	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
-	mask = rdp->grpmask;	/* rnp->grplo is constant. */
-	do {
-		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
-		smp_mb__after_unlock_lock();
-		rnp->qsmaskinit &= ~mask;
-		if (rnp->qsmaskinit != 0) {
-			if (rnp != rdp->mynode)
-				raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
-			break;
-		}
-		if (rnp == rdp->mynode)
-			need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp);
-		else
-			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
-		mask = rnp->grpmask;
-		rnp = rnp->parent;
-	} while (rnp != NULL);
-
-	/*
-	 * We still hold the leaf rcu_node structure lock here, and
-	 * irqs are still disabled.  The reason for this subterfuge is
-	 * because invoking rcu_report_unblock_qs_rnp() with ->orphan_lock
-	 * held leads to deadlock.
-	 */
-	raw_spin_unlock(&rsp->orphan_lock); /* irqs remain disabled. */
-	rnp = rdp->mynode;
-	if (need_report & RCU_OFL_TASKS_NORM_GP)
-		rcu_report_unblock_qs_rnp(rnp, flags);
-	else
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	if (need_report & RCU_OFL_TASKS_EXP_GP)
-		rcu_report_exp_rnp(rsp, rnp, true);
+	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();	/* Enforce GP memory-order guarantee. */
+	rnp->qsmaskinit &= ~rdp->grpmask;
+	if (rnp->qsmaskinit == 0 && !rcu_preempt_has_tasks(rnp))
+		rcu_cleanup_dead_rnp(rnp);
+	rcu_report_qs_rnp(rdp->grpmask, rsp, rnp, flags); /* Rlses rnp->lock. */
 	WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL,
 		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n",
 		  cpu, rdp->qlen, rdp->nxtlist);
@@ -2268,6 +2410,10 @@
 {
 }
 
+static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
+{
+}
+
 static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 {
 }
@@ -2464,12 +2610,6 @@
 		}
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
-	rnp = rcu_get_root(rsp);
-	if (rnp->qsmask == 0) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
-		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
-	}
 }
 
 /*
@@ -2569,7 +2709,7 @@
  * Schedule RCU callback invocation.  If the specified type of RCU
  * does not support RCU priority boosting, just do a direct call,
  * otherwise wake up the per-CPU kernel kthread.  Note that because we
- * are running on the current CPU with interrupts disabled, the
+ * are running on the current CPU with softirqs disabled, the
  * rcu_cpu_kthread_task cannot disappear out from under us.
  */
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
@@ -3109,9 +3249,12 @@
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
 	if (rcu_scheduler_fully_active &&
-	    rdp->qs_pending && !rdp->passed_quiesce) {
+	    rdp->qs_pending && !rdp->passed_quiesce &&
+	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
 		rdp->n_rp_qs_pending++;
-	} else if (rdp->qs_pending && rdp->passed_quiesce) {
+	} else if (rdp->qs_pending &&
+		   (rdp->passed_quiesce ||
+		    rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) {
 		rdp->n_rp_report_qs++;
 		return 1;
 	}
@@ -3135,7 +3278,8 @@
 	}
 
 	/* Has a new RCU grace period started? */
-	if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum) { /* outside lock */
+	if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum ||
+	    unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* outside lock */
 		rdp->n_rp_gp_started++;
 		return 1;
 	}
@@ -3318,6 +3462,7 @@
 			} else {
 				_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
 						   rsp->n_barrier_done);
+				smp_mb__before_atomic();
 				atomic_inc(&rsp->barrier_cpu_count);
 				__call_rcu(&rdp->barrier_head,
 					   rcu_barrier_callback, rsp, cpu, 0);
@@ -3385,9 +3530,6 @@
 	/* Set up local state, ensuring consistent view of global state. */
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
-	init_callback_list(rdp);
-	rdp->qlen_lazy = 0;
-	ACCESS_ONCE(rdp->qlen) = 0;
 	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);
@@ -3444,6 +3586,7 @@
 			rdp->gpnum = rnp->completed;
 			rdp->completed = rnp->completed;
 			rdp->passed_quiesce = 0;
+			rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 			rdp->qs_pending = 0;
 			trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
 		}
@@ -3535,17 +3678,35 @@
 static int __init rcu_spawn_gp_kthread(void)
 {
 	unsigned long flags;
+	int kthread_prio_in = kthread_prio;
 	struct rcu_node *rnp;
 	struct rcu_state *rsp;
+	struct sched_param sp;
 	struct task_struct *t;
 
+	/* Force priority into range. */
+	if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
+		kthread_prio = 1;
+	else if (kthread_prio < 0)
+		kthread_prio = 0;
+	else if (kthread_prio > 99)
+		kthread_prio = 99;
+	if (kthread_prio != kthread_prio_in)
+		pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n",
+			 kthread_prio, kthread_prio_in);
+
 	rcu_scheduler_fully_active = 1;
 	for_each_rcu_flavor(rsp) {
-		t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name);
+		t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name);
 		BUG_ON(IS_ERR(t));
 		rnp = rcu_get_root(rsp);
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rsp->gp_kthread = t;
+		if (kthread_prio) {
+			sp.sched_priority = kthread_prio;
+			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+		}
+		wake_up_process(t);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 	rcu_spawn_nocb_kthreads();
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8e7b184..119de39 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -27,7 +27,6 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
-#include <linux/irq_work.h>
 
 /*
  * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
@@ -172,11 +171,6 @@
 				/*  queued on this rcu_node structure that */
 				/*  are blocking the current grace period, */
 				/*  there can be no such task. */
-	struct completion boost_completion;
-				/* Used to ensure that the rt_mutex used */
-				/*  to carry out the boosting is fully */
-				/*  released with no future boostee accesses */
-				/*  before that rt_mutex is re-initialized. */
 	struct rt_mutex boost_mtx;
 				/* Used only for the priority-boosting */
 				/*  side effect, not as a lock. */
@@ -257,9 +251,12 @@
 					/*  in order to detect GP end. */
 	unsigned long	gpnum;		/* Highest gp number that this CPU */
 					/*  is aware of having started. */
+	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
+					/*  for rcu_all_qs() invocations. */
 	bool		passed_quiesce;	/* User-mode/idle loop etc. */
 	bool		qs_pending;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
+	bool		gpwrap;		/* Possible gpnum/completed wrap. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 #ifdef CONFIG_RCU_CPU_STALL_INFO
@@ -340,14 +337,10 @@
 #ifdef CONFIG_RCU_NOCB_CPU
 	struct rcu_head *nocb_head;	/* CBs waiting for kthread. */
 	struct rcu_head **nocb_tail;
-	atomic_long_t nocb_q_count;	/* # CBs waiting for kthread */
-	atomic_long_t nocb_q_count_lazy; /*  (approximate). */
+	atomic_long_t nocb_q_count;	/* # CBs waiting for nocb */
+	atomic_long_t nocb_q_count_lazy; /*  invocation (all stages). */
 	struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */
 	struct rcu_head **nocb_follower_tail;
-	atomic_long_t nocb_follower_count; /* # CBs ready to invoke. */
-	atomic_long_t nocb_follower_count_lazy; /*  (approximate). */
-	int nocb_p_count;		/* # CBs being invoked by kthread */
-	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
 	int nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
@@ -356,8 +349,6 @@
 	struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
 					/* CBs waiting for GP. */
 	struct rcu_head **nocb_gp_tail;
-	long nocb_gp_count;
-	long nocb_gp_count_lazy;
 	bool nocb_leader_sleep;		/* Is the nocb leader thread asleep? */
 	struct rcu_data *nocb_next_follower;
 					/* Next follower in wakeup chain. */
@@ -488,10 +479,14 @@
 						/*  due to no GP active. */
 	unsigned long gp_start;			/* Time at which GP started, */
 						/*  but in jiffies. */
+	unsigned long gp_activity;		/* Time of last GP kthread */
+						/*  activity in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 	unsigned long jiffies_resched;		/* Time at which to resched */
 						/*  a reluctant CPU. */
+	unsigned long n_force_qs_gpstart;	/* Snapshot of n_force_qs at */
+						/*  GP start. */
 	unsigned long gp_max;			/* Maximum GP duration in */
 						/*  jiffies. */
 	const char *name;			/* Name of structure. */
@@ -514,13 +509,6 @@
 #define for_each_rcu_flavor(rsp) \
 	list_for_each_entry((rsp), &rcu_struct_flavors, flavors)
 
-/* Return values for rcu_preempt_offline_tasks(). */
-
-#define RCU_OFL_TASKS_NORM_GP	0x1		/* Tasks blocking normal */
-						/*  GP were moved to root. */
-#define RCU_OFL_TASKS_EXP_GP	0x2		/* Tasks blocking expedited */
-						/*  GP were moved to root. */
-
 /*
  * RCU implementation internal declarations:
  */
@@ -546,27 +534,16 @@
 
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
-long rcu_batches_completed(void);
 static void rcu_preempt_note_context_switch(void);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
-static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
-				      unsigned long flags);
+static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static int rcu_print_task_stall(struct rcu_node *rnp);
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
-#ifdef CONFIG_HOTPLUG_CPU
-static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
-				     struct rcu_node *rnp,
-				     struct rcu_data *rdp);
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU)
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
-			       bool wake);
-#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU) */
 static void __init __rcu_init_preempt(void);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
@@ -622,24 +599,15 @@
 #endif /* #ifndef RCU_TREE_NONCORE */
 
 #ifdef CONFIG_RCU_TRACE
+/* Read out queue lengths for tracing. */
+static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
+{
 #ifdef CONFIG_RCU_NOCB_CPU
-/* Sum up queue lengths for tracing. */
-static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
-{
-	*ql = atomic_long_read(&rdp->nocb_q_count) +
-	      rdp->nocb_p_count +
-	      atomic_long_read(&rdp->nocb_follower_count) +
-	      rdp->nocb_p_count + rdp->nocb_gp_count;
-	*qll = atomic_long_read(&rdp->nocb_q_count_lazy) +
-	       rdp->nocb_p_count_lazy +
-	       atomic_long_read(&rdp->nocb_follower_count_lazy) +
-	       rdp->nocb_p_count_lazy + rdp->nocb_gp_count_lazy;
-}
+	*ql = atomic_long_read(&rdp->nocb_q_count);
+	*qll = atomic_long_read(&rdp->nocb_q_count_lazy);
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
-static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
-{
 	*ql = 0;
 	*qll = 0;
-}
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
+}
 #endif /* #ifdef CONFIG_RCU_TRACE */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3ec85cb..2e850a5 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -34,10 +34,6 @@
 
 #include "../locking/rtmutex_common.h"
 
-/* rcuc/rcub kthread realtime priority */
-static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
-module_param(kthread_prio, int, 0644);
-
 /*
  * Control variables for per-CPU and per-rcu_node kthreads.  These
  * handle all flavors of RCU.
@@ -103,6 +99,8 @@
 static struct rcu_state *rcu_state_p = &rcu_preempt_state;
 
 static int rcu_preempted_readers_exp(struct rcu_node *rnp);
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+			       bool wake);
 
 /*
  * Tell them what RCU they are running.
@@ -114,25 +112,6 @@
 }
 
 /*
- * Return the number of RCU-preempt batches processed thus far
- * for debug and statistics.
- */
-static long rcu_batches_completed_preempt(void)
-{
-	return rcu_preempt_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt);
-
-/*
- * Return the number of RCU batches processed thus far for debug & stats.
- */
-long rcu_batches_completed(void)
-{
-	return rcu_batches_completed_preempt();
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-/*
  * Record a preemptible-RCU quiescent state for the specified CPU.  Note
  * that this just means that the task currently running on the CPU is
  * not in a quiescent state.  There might be any number of tasks blocked
@@ -307,15 +286,25 @@
 }
 
 /*
+ * Return true if the specified rcu_node structure has tasks that were
+ * preempted within an RCU read-side critical section.
+ */
+static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
+{
+	return !list_empty(&rnp->blkd_tasks);
+}
+
+/*
  * Handle special cases during rcu_read_unlock(), such as needing to
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
  */
 void rcu_read_unlock_special(struct task_struct *t)
 {
-	int empty;
-	int empty_exp;
-	int empty_exp_now;
+	bool empty;
+	bool empty_exp;
+	bool empty_norm;
+	bool empty_exp_now;
 	unsigned long flags;
 	struct list_head *np;
 #ifdef CONFIG_RCU_BOOST
@@ -367,7 +356,8 @@
 				break;
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
-		empty = !rcu_preempt_blocked_readers_cgp(rnp);
+		empty = !rcu_preempt_has_tasks(rnp);
+		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
 		empty_exp = !rcu_preempted_readers_exp(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
 		np = rcu_next_node_entry(t, rnp);
@@ -387,13 +377,21 @@
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
 		/*
+		 * If this was the last task on the list, go see if we
+		 * need to propagate ->qsmaskinit bit clearing up the
+		 * rcu_node tree.
+		 */
+		if (!empty && !rcu_preempt_has_tasks(rnp))
+			rcu_cleanup_dead_rnp(rnp);
+
+		/*
 		 * If this was the last task on the current list, and if
 		 * we aren't waiting on any CPUs, report the quiescent state.
 		 * Note that rcu_report_unblock_qs_rnp() releases rnp->lock,
 		 * so we must take a snapshot of the expedited state.
 		 */
 		empty_exp_now = !rcu_preempted_readers_exp(rnp);
-		if (!empty && !rcu_preempt_blocked_readers_cgp(rnp)) {
+		if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
 			trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
 							 rnp->gpnum,
 							 0, rnp->qsmask,
@@ -408,10 +406,8 @@
 
 #ifdef CONFIG_RCU_BOOST
 		/* Unboost if we were boosted. */
-		if (drop_boost_mutex) {
+		if (drop_boost_mutex)
 			rt_mutex_unlock(&rnp->boost_mtx);
-			complete(&rnp->boost_completion);
-		}
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
 		/*
@@ -519,99 +515,13 @@
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 {
 	WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
-	if (!list_empty(&rnp->blkd_tasks))
+	if (rcu_preempt_has_tasks(rnp))
 		rnp->gp_tasks = rnp->blkd_tasks.next;
 	WARN_ON_ONCE(rnp->qsmask);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-/*
- * Handle tasklist migration for case in which all CPUs covered by the
- * specified rcu_node have gone offline.  Move them up to the root
- * rcu_node.  The reason for not just moving them to the immediate
- * parent is to remove the need for rcu_read_unlock_special() to
- * make more than two attempts to acquire the target rcu_node's lock.
- * Returns true if there were tasks blocking the current RCU grace
- * period.
- *
- * Returns 1 if there was previously a task blocking the current grace
- * period on the specified rcu_node structure.
- *
- * The caller must hold rnp->lock with irqs disabled.
- */
-static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
-				     struct rcu_node *rnp,
-				     struct rcu_data *rdp)
-{
-	struct list_head *lp;
-	struct list_head *lp_root;
-	int retval = 0;
-	struct rcu_node *rnp_root = rcu_get_root(rsp);
-	struct task_struct *t;
-
-	if (rnp == rnp_root) {
-		WARN_ONCE(1, "Last CPU thought to be offlined?");
-		return 0;  /* Shouldn't happen: at least one CPU online. */
-	}
-
-	/* If we are on an internal node, complain bitterly. */
-	WARN_ON_ONCE(rnp != rdp->mynode);
-
-	/*
-	 * Move tasks up to root rcu_node.  Don't try to get fancy for
-	 * this corner-case operation -- just put this node's tasks
-	 * at the head of the root node's list, and update the root node's
-	 * ->gp_tasks and ->exp_tasks pointers to those of this node's,
-	 * if non-NULL.  This might result in waiting for more tasks than
-	 * absolutely necessary, but this is a good performance/complexity
-	 * tradeoff.
-	 */
-	if (rcu_preempt_blocked_readers_cgp(rnp) && rnp->qsmask == 0)
-		retval |= RCU_OFL_TASKS_NORM_GP;
-	if (rcu_preempted_readers_exp(rnp))
-		retval |= RCU_OFL_TASKS_EXP_GP;
-	lp = &rnp->blkd_tasks;
-	lp_root = &rnp_root->blkd_tasks;
-	while (!list_empty(lp)) {
-		t = list_entry(lp->next, typeof(*t), rcu_node_entry);
-		raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
-		smp_mb__after_unlock_lock();
-		list_del(&t->rcu_node_entry);
-		t->rcu_blocked_node = rnp_root;
-		list_add(&t->rcu_node_entry, lp_root);
-		if (&t->rcu_node_entry == rnp->gp_tasks)
-			rnp_root->gp_tasks = rnp->gp_tasks;
-		if (&t->rcu_node_entry == rnp->exp_tasks)
-			rnp_root->exp_tasks = rnp->exp_tasks;
-#ifdef CONFIG_RCU_BOOST
-		if (&t->rcu_node_entry == rnp->boost_tasks)
-			rnp_root->boost_tasks = rnp->boost_tasks;
-#endif /* #ifdef CONFIG_RCU_BOOST */
-		raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
-	}
-
-	rnp->gp_tasks = NULL;
-	rnp->exp_tasks = NULL;
-#ifdef CONFIG_RCU_BOOST
-	rnp->boost_tasks = NULL;
-	/*
-	 * In case root is being boosted and leaf was not.  Make sure
-	 * that we boost the tasks blocking the current grace period
-	 * in this case.
-	 */
-	raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
-	smp_mb__after_unlock_lock();
-	if (rnp_root->boost_tasks != NULL &&
-	    rnp_root->boost_tasks != rnp_root->gp_tasks &&
-	    rnp_root->boost_tasks != rnp_root->exp_tasks)
-		rnp_root->boost_tasks = rnp_root->gp_tasks;
-	raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
-	return retval;
-}
-
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 /*
@@ -771,7 +681,7 @@
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();
-	if (list_empty(&rnp->blkd_tasks)) {
+	if (!rcu_preempt_has_tasks(rnp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else {
 		rnp->exp_tasks = rnp->blkd_tasks.next;
@@ -933,15 +843,6 @@
 }
 
 /*
- * Return the number of RCU batches processed thus far for debug & stats.
- */
-long rcu_batches_completed(void)
-{
-	return rcu_batches_completed_sched();
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-/*
  * Because preemptible RCU does not exist, we never have to check for
  * CPUs being in quiescent states.
  */
@@ -960,11 +861,12 @@
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-/* Because preemptible RCU does not exist, no quieting of tasks. */
-static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
-	__releases(rnp->lock)
+/*
+ * Because there is no preemptible RCU, there can be no readers blocked.
+ */
+static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
 {
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	return false;
 }
 
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
@@ -996,23 +898,6 @@
 	WARN_ON_ONCE(rnp->qsmask);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-/*
- * Because preemptible RCU does not exist, it never needs to migrate
- * tasks that were blocked within RCU read-side critical sections, and
- * such non-existent tasks cannot possibly have been blocking the current
- * grace period.
- */
-static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
-				     struct rcu_node *rnp,
-				     struct rcu_data *rdp)
-{
-	return 0;
-}
-
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Because preemptible RCU does not exist, it never has any callbacks
  * to check.
@@ -1031,20 +916,6 @@
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-/*
- * Because preemptible RCU does not exist, there is never any need to
- * report on tasks preempted in RCU read-side critical sections during
- * expedited RCU grace periods.
- */
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
-			       bool wake)
-{
-}
-
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Because preemptible RCU does not exist, rcu_barrier() is just
  * another name for rcu_barrier_sched().
@@ -1080,7 +951,7 @@
 
 static void rcu_initiate_boost_trace(struct rcu_node *rnp)
 {
-	if (list_empty(&rnp->blkd_tasks))
+	if (!rcu_preempt_has_tasks(rnp))
 		rnp->n_balk_blkd_tasks++;
 	else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL)
 		rnp->n_balk_exp_gp_tasks++;
@@ -1127,7 +998,8 @@
 	struct task_struct *t;
 	struct list_head *tb;
 
-	if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL)
+	if (ACCESS_ONCE(rnp->exp_tasks) == NULL &&
+	    ACCESS_ONCE(rnp->boost_tasks) == NULL)
 		return 0;  /* Nothing left to boost. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -1175,15 +1047,11 @@
 	 */
 	t = container_of(tb, struct task_struct, rcu_node_entry);
 	rt_mutex_init_proxy_locked(&rnp->boost_mtx, t);
-	init_completion(&rnp->boost_completion);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	/* Lock only for side effect: boosts task t's priority. */
 	rt_mutex_lock(&rnp->boost_mtx);
 	rt_mutex_unlock(&rnp->boost_mtx);  /* Then keep lockdep happy. */
 
-	/* Wait for boostee to be done w/boost_mtx before reinitializing. */
-	wait_for_completion(&rnp->boost_completion);
-
 	return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
 	       ACCESS_ONCE(rnp->boost_tasks) != NULL;
 }
@@ -1416,12 +1284,8 @@
 	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1)
 		if ((mask & 0x1) && cpu != outgoingcpu)
 			cpumask_set_cpu(cpu, cm);
-	if (cpumask_weight(cm) == 0) {
+	if (cpumask_weight(cm) == 0)
 		cpumask_setall(cm);
-		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++)
-			cpumask_clear_cpu(cpu, cm);
-		WARN_ON_ONCE(cpumask_weight(cm) == 0);
-	}
 	set_cpus_allowed_ptr(t, cm);
 	free_cpumask_var(cm);
 }
@@ -1446,12 +1310,8 @@
 	for_each_possible_cpu(cpu)
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
 	BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
-	rnp = rcu_get_root(rcu_state_p);
-	(void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
-	if (NUM_RCU_NODES > 1) {
-		rcu_for_each_leaf_node(rcu_state_p, rnp)
-			(void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
-	}
+	rcu_for_each_leaf_node(rcu_state_p, rnp)
+		(void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
 }
 
 static void rcu_prepare_kthreads(int cpu)
@@ -1605,7 +1465,8 @@
 		 * completed since we last checked and there are
 		 * callbacks not yet ready to invoke.
 		 */
-		if (rdp->completed != rnp->completed &&
+		if ((rdp->completed != rnp->completed ||
+		     unlikely(ACCESS_ONCE(rdp->gpwrap))) &&
 		    rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
 			note_gp_changes(rsp, rdp);
 
@@ -1898,11 +1759,12 @@
 		ticks_value = rsp->gpnum - rdp->gpnum;
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
-	pr_err("\t%d: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u %s\n",
+	pr_err("\t%d: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u fqs=%ld %s\n",
 	       cpu, ticks_value, ticks_title,
 	       atomic_read(&rdtp->dynticks) & 0xfff,
 	       rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
+	       ACCESS_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
 	       fast_no_hz);
 }
 
@@ -2056,9 +1918,26 @@
 static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
 {
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+	unsigned long ret;
+#ifdef CONFIG_PROVE_RCU
 	struct rcu_head *rhp;
+#endif /* #ifdef CONFIG_PROVE_RCU */
 
-	/* No-CBs CPUs might have callbacks on any of three lists. */
+	/*
+	 * Check count of all no-CBs callbacks awaiting invocation.
+	 * There needs to be a barrier before this function is called,
+	 * but associated with a prior determination that no more
+	 * callbacks would be posted.  In the worst case, the first
+	 * barrier in _rcu_barrier() suffices (but the caller cannot
+	 * necessarily rely on this, not a substitute for the caller
+	 * getting the concurrency design right!).  There must also be
+	 * a barrier between the following load an posting of a callback
+	 * (if a callback is in fact needed).  This is associated with an
+	 * atomic_inc() in the caller.
+	 */
+	ret = atomic_long_read(&rdp->nocb_q_count);
+
+#ifdef CONFIG_PROVE_RCU
 	rhp = ACCESS_ONCE(rdp->nocb_head);
 	if (!rhp)
 		rhp = ACCESS_ONCE(rdp->nocb_gp_head);
@@ -2072,8 +1951,9 @@
 		       cpu, rhp->func);
 		WARN_ON_ONCE(1);
 	}
+#endif /* #ifdef CONFIG_PROVE_RCU */
 
-	return !!rhp;
+	return !!ret;
 }
 
 /*
@@ -2095,9 +1975,10 @@
 	struct task_struct *t;
 
 	/* Enqueue the callback on the nocb list and update counts. */
+	atomic_long_add(rhcount, &rdp->nocb_q_count);
+	/* rcu_barrier() relies on ->nocb_q_count add before xchg. */
 	old_rhpp = xchg(&rdp->nocb_tail, rhtp);
 	ACCESS_ONCE(*old_rhpp) = rhp;
-	atomic_long_add(rhcount, &rdp->nocb_q_count);
 	atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy);
 	smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */
 
@@ -2288,9 +2169,6 @@
 		/* Move callbacks to wait-for-GP list, which is empty. */
 		ACCESS_ONCE(rdp->nocb_head) = NULL;
 		rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
-		rdp->nocb_gp_count = atomic_long_xchg(&rdp->nocb_q_count, 0);
-		rdp->nocb_gp_count_lazy =
-			atomic_long_xchg(&rdp->nocb_q_count_lazy, 0);
 		gotcbs = true;
 	}
 
@@ -2338,9 +2216,6 @@
 		/* Append callbacks to follower's "done" list. */
 		tail = xchg(&rdp->nocb_follower_tail, rdp->nocb_gp_tail);
 		*tail = rdp->nocb_gp_head;
-		atomic_long_add(rdp->nocb_gp_count, &rdp->nocb_follower_count);
-		atomic_long_add(rdp->nocb_gp_count_lazy,
-				&rdp->nocb_follower_count_lazy);
 		smp_mb__after_atomic(); /* Store *tail before wakeup. */
 		if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
 			/*
@@ -2415,13 +2290,11 @@
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty");
 		ACCESS_ONCE(rdp->nocb_follower_head) = NULL;
 		tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head);
-		c = atomic_long_xchg(&rdp->nocb_follower_count, 0);
-		cl = atomic_long_xchg(&rdp->nocb_follower_count_lazy, 0);
-		rdp->nocb_p_count += c;
-		rdp->nocb_p_count_lazy += cl;
 
 		/* Each pass through the following loop invokes a callback. */
-		trace_rcu_batch_start(rdp->rsp->name, cl, c, -1);
+		trace_rcu_batch_start(rdp->rsp->name,
+				      atomic_long_read(&rdp->nocb_q_count_lazy),
+				      atomic_long_read(&rdp->nocb_q_count), -1);
 		c = cl = 0;
 		while (list) {
 			next = list->next;
@@ -2443,9 +2316,9 @@
 			list = next;
 		}
 		trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1);
-		ACCESS_ONCE(rdp->nocb_p_count) = rdp->nocb_p_count - c;
-		ACCESS_ONCE(rdp->nocb_p_count_lazy) =
-						rdp->nocb_p_count_lazy - cl;
+		smp_mb__before_atomic();  /* _add after CB invocation. */
+		atomic_long_add(-c, &rdp->nocb_q_count);
+		atomic_long_add(-cl, &rdp->nocb_q_count_lazy);
 		rdp->n_nocbs_invoked += c;
 	}
 	return 0;
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 5cdc62e..fbb6240 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -46,6 +46,8 @@
 #define RCU_TREE_NONCORE
 #include "tree.h"
 
+DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
+
 static int r_open(struct inode *inode, struct file *file,
 					const struct seq_operations *op)
 {
@@ -115,11 +117,13 @@
 
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d qp=%d",
+	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d/%d qp=%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   ulong2long(rdp->completed), ulong2long(rdp->gpnum),
-		   rdp->passed_quiesce, rdp->qs_pending);
+		   rdp->passed_quiesce,
+		   rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
+		   rdp->qs_pending);
 	seq_printf(m, " dt=%d/%llx/%d df=%lu",
 		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e628cb1..5eab11d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1814,6 +1814,10 @@
 	dl_se->dl_period = 0;
 	dl_se->flags = 0;
 	dl_se->dl_bw = 0;
+
+	dl_se->dl_throttled = 0;
+	dl_se->dl_new = 1;
+	dl_se->dl_yielded = 0;
 }
 
 /*
@@ -1839,7 +1843,7 @@
 #endif
 
 	RB_CLEAR_NODE(&p->dl.rb_node);
-	hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	init_dl_task_timer(&p->dl);
 	__dl_clear_params(p);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -2049,6 +2053,9 @@
  * allocated bandwidth to reflect the new situation.
  *
  * This function is called while holding p's rq->lock.
+ *
+ * XXX we should delay bw change until the task's 0-lag point, see
+ * __setparam_dl().
  */
 static int dl_overflow(struct task_struct *p, int policy,
 		       const struct sched_attr *attr)
@@ -3251,15 +3258,31 @@
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 
-	init_dl_task_timer(dl_se);
 	dl_se->dl_runtime = attr->sched_runtime;
 	dl_se->dl_deadline = attr->sched_deadline;
 	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
 	dl_se->flags = attr->sched_flags;
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
-	dl_se->dl_throttled = 0;
-	dl_se->dl_new = 1;
-	dl_se->dl_yielded = 0;
+
+	/*
+	 * Changing the parameters of a task is 'tricky' and we're not doing
+	 * the correct thing -- also see task_dead_dl() and switched_from_dl().
+	 *
+	 * What we SHOULD do is delay the bandwidth release until the 0-lag
+	 * point. This would include retaining the task_struct until that time
+	 * and change dl_overflow() to not immediately decrement the current
+	 * amount.
+	 *
+	 * Instead we retain the current runtime/deadline and let the new
+	 * parameters take effect after the current reservation period lapses.
+	 * This is safe (albeit pessimistic) because the 0-lag point is always
+	 * before the current scheduling deadline.
+	 *
+	 * We can still have temporary overloads because we do not delay the
+	 * change in bandwidth until that time; so admission control is
+	 * not on the safe side. It does however guarantee tasks will never
+	 * consume more than promised.
+	 */
 }
 
 /*
@@ -4642,6 +4665,9 @@
 	struct dl_bw *cur_dl_b;
 	unsigned long flags;
 
+	if (!cpumask_weight(cur))
+		return ret;
+
 	rcu_read_lock_sched();
 	cur_dl_b = dl_bw_of(cpumask_any(cur));
 	trial_cpus = cpumask_weight(trial);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b52092f..726470d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1094,6 +1094,7 @@
 	 * Since we are TASK_DEAD we won't slip out of the domain!
 	 */
 	raw_spin_lock_irq(&dl_b->lock);
+	/* XXX we should retain the bw until 0-lag */
 	dl_b->total_bw -= p->dl.dl_bw;
 	raw_spin_unlock_irq(&dl_b->lock);
 
@@ -1614,8 +1615,8 @@
 
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
+	/* XXX we should retain the bw until 0-lag */
 	cancel_dl_timer(rq, p);
-
 	__dl_clear_params(p);
 
 	/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 40667cb..fe331fc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1730,7 +1730,7 @@
 	nodes = node_online_map;
 	for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
 		unsigned long max_faults = 0;
-		nodemask_t max_group;
+		nodemask_t max_group = NODE_MASK_NONE;
 		int a, b;
 
 		/* Are there nodes at this distance from each other? */
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index f032fb5..40190f2 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -280,6 +280,7 @@
 	unsigned int cpu;
 	int ret = 0;
 
+	get_online_cpus();
 	mutex_lock(&smpboot_threads_lock);
 	for_each_online_cpu(cpu) {
 		ret = __smpboot_create_thread(plug_thread, cpu);
@@ -292,6 +293,7 @@
 	list_add(&plug_thread->list, &hotplug_threads);
 out:
 	mutex_unlock(&smpboot_threads_lock);
+	put_online_cpus();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b9ae816..479e443 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -660,9 +660,8 @@
 		 * in the task stack here.
 		 */
 		__do_softirq();
-		rcu_note_context_switch();
 		local_irq_enable();
-		cond_resched();
+		cond_resched_rcu_qs();
 		return;
 	}
 	local_irq_enable();
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 37e50aa..d8c724c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -122,7 +122,7 @@
 	mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
 	boot = ktime_add(mono, off_boot);
 	xtim = ktime_add(mono, off_real);
-	tai = ktime_add(xtim, off_tai);
+	tai = ktime_add(mono, off_tai);
 
 	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
 	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 5f2ce61..a2ca213 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1215,6 +1215,7 @@
 	tristate "torture tests for RCU"
 	depends on DEBUG_KERNEL
 	select TORTURE_TEST
+	select SRCU
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
@@ -1257,7 +1258,7 @@
 config RCU_CPU_STALL_INFO
 	bool "Print additional diagnostics on RCU CPU stall"
 	depends on (TREE_RCU || PREEMPT_RCU) && DEBUG_KERNEL
-	default n
+	default y
 	help
 	  For each stalled CPU that is aware of the current RCU grace
 	  period, print out additional per-CPU diagnostic information
diff --git a/lib/checksum.c b/lib/checksum.c
index 129775e..8b39e86 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -181,6 +181,15 @@
 EXPORT_SYMBOL(csum_partial_copy);
 
 #ifndef csum_tcpudp_nofold
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
 __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 			unsigned short len,
 			unsigned short proto,
@@ -195,8 +204,7 @@
 #else
 	s += (proto + len) << 8;
 #endif
-	s += (s >> 32);
-	return (__force __wsum)s;
+	return (__force __wsum)from64to32(s);
 }
 EXPORT_SYMBOL(csum_tcpudp_nofold);
 #endif
diff --git a/mm/Kconfig b/mm/Kconfig
index 1d1ae6b..4395b12 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -325,6 +325,7 @@
 
 config MMU_NOTIFIER
 	bool
+	select SRCU
 
 config KSM
 	bool "Enable KSM for page merging"
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 683b478..2f6893c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5773,7 +5773,7 @@
  * mem_cgroup_migrate - migrate a charge to another page
  * @oldpage: currently charged page
  * @newpage: page to transfer the charge to
- * @lrucare: both pages might be on the LRU already
+ * @lrucare: either or both pages might be on the LRU already
  *
  * Migrate the charge from @oldpage to @newpage.
  *
diff --git a/mm/nommu.c b/mm/nommu.c
index b51eadf..28bd8c4 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -59,6 +59,7 @@
 #endif
 
 void *high_memory;
+EXPORT_SYMBOL(high_memory);
 struct page *mem_map;
 unsigned long max_mapnr;
 unsigned long highest_memmap_pfn;
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index ad83195..b264bda 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -199,7 +199,10 @@
 			 */
 			if ((vma->vm_start <= addr) &&
 			    (vma->vm_flags & VM_PFNMAP)) {
-				next = vma->vm_end;
+				if (walk->pte_hole)
+					err = walk->pte_hole(addr, next, walk);
+				if (err)
+					break;
 				pgd = pgd_offset(walk->mm, next);
 				continue;
 			}
diff --git a/mm/shmem.c b/mm/shmem.c
index 73ba1df..993e6ba 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1013,7 +1013,7 @@
 		 */
 		oldpage = newpage;
 	} else {
-		mem_cgroup_migrate(oldpage, newpage, false);
+		mem_cgroup_migrate(oldpage, newpage, true);
 		lru_cache_add_anon(newpage);
 		*pagep = newpage;
 	}
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index b0330ae..3244aea 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -265,22 +265,12 @@
 	data[NFT_REG_VERDICT].verdict = NF_DROP;
 }
 
-static int nft_reject_bridge_validate_hooks(const struct nft_chain *chain)
+static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
+				      const struct nft_expr *expr,
+				      const struct nft_data **data)
 {
-	struct nft_base_chain *basechain;
-
-	if (chain->flags & NFT_BASE_CHAIN) {
-		basechain = nft_base_chain(chain);
-
-		switch (basechain->ops[0].hooknum) {
-		case NF_BR_PRE_ROUTING:
-		case NF_BR_LOCAL_IN:
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-	}
-	return 0;
+	return nft_chain_validate_hooks(ctx->chain, (1 << NF_BR_PRE_ROUTING) |
+						    (1 << NF_BR_LOCAL_IN));
 }
 
 static int nft_reject_bridge_init(const struct nft_ctx *ctx,
@@ -290,7 +280,7 @@
 	struct nft_reject *priv = nft_expr_priv(expr);
 	int icmp_code, err;
 
-	err = nft_reject_bridge_validate_hooks(ctx->chain);
+	err = nft_reject_bridge_validate(ctx, expr, NULL);
 	if (err < 0)
 		return err;
 
@@ -341,13 +331,6 @@
 	return -1;
 }
 
-static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
-				      const struct nft_expr *expr,
-				      const struct nft_data **data)
-{
-	return nft_reject_bridge_validate_hooks(ctx->chain);
-}
-
 static struct nft_expr_type nft_reject_bridge_type;
 static const struct nft_expr_ops nft_reject_bridge_ops = {
 	.type		= &nft_reject_bridge_type,
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 4589ff67..67a4a36 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -470,7 +470,6 @@
 	ASSERT_RTNL();
 	caifdev = netdev_priv(dev);
 	caif_netlink_parms(data, &caifdev->conn_req);
-	dev_net_set(caifdev->netdev, src_net);
 
 	ret = register_netdevice(dev);
 	if (ret)
diff --git a/net/core/dev.c b/net/core/dev.c
index 171420e..7fe8292 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2352,7 +2352,6 @@
 
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
-	unsigned int vlan_depth = skb->mac_len;
 	__be16 type = skb->protocol;
 
 	/* Tunnel gso handlers can set protocol to ethernet. */
@@ -2366,35 +2365,7 @@
 		type = eth->h_proto;
 	}
 
-	/* if skb->protocol is 802.1Q/AD then the header should already be
-	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
-	 * ETH_HLEN otherwise
-	 */
-	if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
-		if (vlan_depth) {
-			if (WARN_ON(vlan_depth < VLAN_HLEN))
-				return 0;
-			vlan_depth -= VLAN_HLEN;
-		} else {
-			vlan_depth = ETH_HLEN;
-		}
-		do {
-			struct vlan_hdr *vh;
-
-			if (unlikely(!pskb_may_pull(skb,
-						    vlan_depth + VLAN_HLEN)))
-				return 0;
-
-			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
-			type = vh->h_vlan_encapsulated_proto;
-			vlan_depth += VLAN_HLEN;
-		} while (type == htons(ETH_P_8021Q) ||
-			 type == htons(ETH_P_8021AD));
-	}
-
-	*depth = vlan_depth;
-
-	return type;
+	return __vlan_get_protocol(skb, type, depth);
 }
 
 /**
@@ -5323,7 +5294,7 @@
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
-void netdev_adjacent_add_links(struct net_device *dev)
+static void netdev_adjacent_add_links(struct net_device *dev)
 {
 	struct netdev_adjacent *iter;
 
@@ -5348,7 +5319,7 @@
 	}
 }
 
-void netdev_adjacent_del_links(struct net_device *dev)
+static void netdev_adjacent_del_links(struct net_device *dev)
 {
 	struct netdev_adjacent *iter;
 
@@ -6656,7 +6627,7 @@
 	if (!queue)
 		return NULL;
 	netdev_init_one_queue(dev, queue, NULL);
-	queue->qdisc = &noop_qdisc;
+	RCU_INIT_POINTER(queue->qdisc, &noop_qdisc);
 	queue->qdisc_sleeping = &noop_qdisc;
 	rcu_assign_pointer(dev->ingress_queue, queue);
 #endif
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9cf6fe9..446cbaf 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2895,12 +2895,16 @@
 			goto errout;
 	}
 
+	if (!skb->len)
+		goto errout;
+
 	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
 	return 0;
 errout:
 	WARN_ON(err == -EMSGSIZE);
 	kfree_skb(skb);
-	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	if (err)
+		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
 	return err;
 }
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b50861b..c373c07 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1506,23 +1506,8 @@
 /*
  *	Generic function to send a packet as reply to another packet.
  *	Used to send some TCP resets/acks so far.
- *
- *	Use a fake percpu inet socket to avoid false sharing and contention.
  */
-static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
-	.sk = {
-		.__sk_common = {
-			.skc_refcnt = ATOMIC_INIT(1),
-		},
-		.sk_wmem_alloc	= ATOMIC_INIT(1),
-		.sk_allocation	= GFP_ATOMIC,
-		.sk_flags	= (1UL << SOCK_USE_WRITE_QUEUE),
-	},
-	.pmtudisc	= IP_PMTUDISC_WANT,
-	.uc_ttl		= -1,
-};
-
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
@@ -1532,9 +1517,8 @@
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	struct rtable *rt = skb_rtable(skb);
+	struct net *net = sock_net(sk);
 	struct sk_buff *nskb;
-	struct sock *sk;
-	struct inet_sock *inet;
 	int err;
 
 	if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))
@@ -1565,15 +1549,11 @@
 	if (IS_ERR(rt))
 		return;
 
-	inet = &get_cpu_var(unicast_sock);
+	inet_sk(sk)->tos = arg->tos;
 
-	inet->tos = arg->tos;
-	sk = &inet->sk;
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sock_net_set(sk, net);
-	__skb_queue_head_init(&sk->sk_write_queue);
 	sk->sk_sndbuf = sysctl_wmem_default;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
@@ -1589,13 +1569,10 @@
 			  arg->csumoffset) = csum_fold(csum_add(nskb->csum,
 								arg->csum));
 		nskb->ip_summed = CHECKSUM_NONE;
-		skb_orphan(nskb);
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
 out:
-	put_cpu_var(unicast_sock);
-
 	ip_rt_put(rt);
 }
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d58dd0e..52e1f2b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -966,6 +966,9 @@
 	if (dst->dev->mtu < mtu)
 		return;
 
+	if (rt->rt_pmtu && rt->rt_pmtu < mtu)
+		return;
+
 	if (mtu < ip_rt_min_pmtu)
 		mtu = ip_rt_min_pmtu;
 
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index bb395d4..c037644 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -150,7 +150,7 @@
 		tcp_slow_start(tp, acked);
 	else {
 		bictcp_update(ca, tp->snd_cwnd);
-		tcp_cong_avoid_ai(tp, ca->cnt);
+		tcp_cong_avoid_ai(tp, ca->cnt, 1);
 	}
 }
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 27ead0d..8670e68 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -291,26 +291,32 @@
  * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
  * returns the leftover acks to adjust cwnd in congestion avoidance mode.
  */
-void tcp_slow_start(struct tcp_sock *tp, u32 acked)
+u32 tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
 	u32 cwnd = tp->snd_cwnd + acked;
 
 	if (cwnd > tp->snd_ssthresh)
 		cwnd = tp->snd_ssthresh + 1;
+	acked -= cwnd - tp->snd_cwnd;
 	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+
+	return acked;
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
-/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
+/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w),
+ * for every packet that was ACKed.
+ */
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 {
+	tp->snd_cwnd_cnt += acked;
 	if (tp->snd_cwnd_cnt >= w) {
-		if (tp->snd_cwnd < tp->snd_cwnd_clamp)
-			tp->snd_cwnd++;
-		tp->snd_cwnd_cnt = 0;
-	} else {
-		tp->snd_cwnd_cnt++;
+		u32 delta = tp->snd_cwnd_cnt / w;
+
+		tp->snd_cwnd_cnt -= delta * w;
+		tp->snd_cwnd += delta;
 	}
+	tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
 }
 EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
 
@@ -329,11 +335,13 @@
 		return;
 
 	/* In "safe" area, increase. */
-	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp, acked);
+	if (tp->snd_cwnd <= tp->snd_ssthresh) {
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
+	}
 	/* In dangerous area, increase slowly. */
-	else
-		tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+	tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
 }
 EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 6b60024..4b276d1 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -93,9 +93,7 @@
 	u32	epoch_start;	/* beginning of an epoch */
 	u32	ack_cnt;	/* number of acks */
 	u32	tcp_cwnd;	/* estimated tcp cwnd */
-#define ACK_RATIO_SHIFT	4
-#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT)
-	u16	delayed_ack;	/* estimate the ratio of Packets/ACKs << 4 */
+	u16	unused;
 	u8	sample_cnt;	/* number of samples to decide curr_rtt */
 	u8	found;		/* the exit point is found? */
 	u32	round_start;	/* beginning of each round */
@@ -114,7 +112,6 @@
 	ca->bic_K = 0;
 	ca->delay_min = 0;
 	ca->epoch_start = 0;
-	ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
 	ca->ack_cnt = 0;
 	ca->tcp_cwnd = 0;
 	ca->found = 0;
@@ -205,23 +202,30 @@
 /*
  * Compute congestion window to use.
  */
-static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
+static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked)
 {
 	u32 delta, bic_target, max_cnt;
 	u64 offs, t;
 
-	ca->ack_cnt++;	/* count the number of ACKs */
+	ca->ack_cnt += acked;	/* count the number of ACKed packets */
 
 	if (ca->last_cwnd == cwnd &&
 	    (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32)
 		return;
 
+	/* The CUBIC function can update ca->cnt at most once per jiffy.
+	 * On all cwnd reduction events, ca->epoch_start is set to 0,
+	 * which will force a recalculation of ca->cnt.
+	 */
+	if (ca->epoch_start && tcp_time_stamp == ca->last_time)
+		goto tcp_friendliness;
+
 	ca->last_cwnd = cwnd;
 	ca->last_time = tcp_time_stamp;
 
 	if (ca->epoch_start == 0) {
 		ca->epoch_start = tcp_time_stamp;	/* record beginning */
-		ca->ack_cnt = 1;			/* start counting */
+		ca->ack_cnt = acked;			/* start counting */
 		ca->tcp_cwnd = cwnd;			/* syn with cubic */
 
 		if (ca->last_max_cwnd <= cwnd) {
@@ -283,6 +287,7 @@
 	if (ca->last_max_cwnd == 0 && ca->cnt > 20)
 		ca->cnt = 20;	/* increase cwnd 5% per RTT */
 
+tcp_friendliness:
 	/* TCP Friendly */
 	if (tcp_friendliness) {
 		u32 scale = beta_scale;
@@ -301,7 +306,6 @@
 		}
 	}
 
-	ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
 	if (ca->cnt == 0)			/* cannot be zero */
 		ca->cnt = 1;
 }
@@ -317,11 +321,12 @@
 	if (tp->snd_cwnd <= tp->snd_ssthresh) {
 		if (hystart && after(ack, ca->end_seq))
 			bictcp_hystart_reset(sk);
-		tcp_slow_start(tp, acked);
-	} else {
-		bictcp_update(ca, tp->snd_cwnd);
-		tcp_cong_avoid_ai(tp, ca->cnt);
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
 	}
+	bictcp_update(ca, tp->snd_cwnd, acked);
+	tcp_cong_avoid_ai(tp, ca->cnt, acked);
 }
 
 static u32 bictcp_recalc_ssthresh(struct sock *sk)
@@ -411,20 +416,10 @@
  */
 static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 	u32 delay;
 
-	if (icsk->icsk_ca_state == TCP_CA_Open) {
-		u32 ratio = ca->delayed_ack;
-
-		ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
-		ratio += cnt;
-
-		ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
-	}
-
 	/* Some calls are for duplicates without timetamps */
 	if (rtt_us < 0)
 		return;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a3f72d7..d22f544 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -683,7 +683,8 @@
 		arg.bound_dev_if = sk->sk_bound_dev_if;
 
 	arg.tos = ip_hdr(skb)->tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -767,7 +768,8 @@
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -2428,14 +2430,39 @@
 };
 EXPORT_SYMBOL(tcp_prot);
 
-static int __net_init tcp_sk_init(struct net *net)
-{
-	net->ipv4.sysctl_tcp_ecn = 2;
-	return 0;
-}
-
 static void __net_exit tcp_sk_exit(struct net *net)
 {
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
+	free_percpu(net->ipv4.tcp_sk);
+}
+
+static int __net_init tcp_sk_init(struct net *net)
+{
+	int res, cpu;
+
+	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
+	if (!net->ipv4.tcp_sk)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct sock *sk;
+
+		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+					   IPPROTO_TCP, net);
+		if (res)
+			goto fail;
+		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
+	}
+	net->ipv4.sysctl_tcp_ecn = 2;
+	return 0;
+
+fail:
+	tcp_sk_exit(net);
+
+	return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 6824afb..333bcb2 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -25,7 +25,8 @@
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
 		tcp_slow_start(tp, acked);
 	else
-		tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT));
+		tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT),
+				  1);
 }
 
 static u32 tcp_scalable_ssthresh(struct sock *sk)
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index a4d2d2d..112151e 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -159,7 +159,7 @@
 				/* In the "non-congestive state", increase cwnd
 				 *  every rtt.
 				 */
-				tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+				tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
 			} else {
 				/* In the "congestive state", increase cwnd
 				 * every other rtt.
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index cd72732..17d3566 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -92,7 +92,7 @@
 
 	} else {
 		/* Reno */
-		tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+		tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
 	}
 
 	/* The key players are v_vegas.beg_snd_una and v_beg_snd_nxt.
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 13cda4c..01ccc28 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -417,7 +417,7 @@
 		if (code == ICMPV6_HDR_FIELD)
 			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
 
-		if (teli && teli == info - 2) {
+		if (teli && teli == be32_to_cpu(info) - 2) {
 			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
 			if (tel->encap_limit == 0) {
 				net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
@@ -429,7 +429,7 @@
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
-		mtu = info - offset;
+		mtu = be32_to_cpu(info) - offset;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ce69a12..d28f2a2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -537,20 +537,6 @@
 	skb_copy_secmark(to, from);
 }
 
-static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static u32 ip6_idents_hashrnd __read_mostly;
-	u32 hash, id;
-
-	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
-
-	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
-
-	id = ip_idents_reserve(hash, 1);
-	fhdr->identification = htonl(id);
-}
-
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 97f41a3..54520a0 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -9,6 +9,24 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, struct in6_addr *src)
+{
+	u32 hash, id;
+
+	hash = __ipv6_addr_jhash(dst, hashrnd);
+	hash = __ipv6_addr_jhash(src, hash);
+
+	/* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve,
+	 * set the hight order instead thus minimizing possible future
+	 * collisions.
+	 */
+	id = ip_idents_reserve(hash, 1);
+	if (unlikely(!id))
+		id = 1 << 31;
+
+	return id;
+}
+
 /* This function exists only for tap drivers that must support broken
  * clients requesting UFO without specifying an IPv6 fragment ID.
  *
@@ -22,7 +40,7 @@
 	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
 	struct in6_addr *addrs;
-	u32 hash, id;
+	u32 id;
 
 	addrs = skb_header_pointer(skb,
 				   skb_network_offset(skb) +
@@ -34,14 +52,25 @@
 	net_get_random_once(&ip6_proxy_idents_hashrnd,
 			    sizeof(ip6_proxy_idents_hashrnd));
 
-	hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&addrs[0], hash);
-
-	id = ip_idents_reserve(hash, 1);
-	skb_shinfo(skb)->ip6_frag_id = htonl(id);
+	id = __ipv6_select_ident(ip6_proxy_idents_hashrnd,
+				 &addrs[1], &addrs[0]);
+	skb_shinfo(skb)->ip6_frag_id = id;
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	id = __ipv6_select_ident(ip6_idents_hashrnd, &rt->rt6i_dst.addr,
+				 &rt->rt6i_src.addr);
+	fhdr->identification = htonl(id);
+}
+EXPORT_SYMBOL(ipv6_select_ident);
+
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 213546b..cdbfe5a 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1506,12 +1506,12 @@
 
 	if (data[IFLA_IPTUN_ENCAP_SPORT]) {
 		ret = true;
-		ipencap->sport = nla_get_u16(data[IFLA_IPTUN_ENCAP_SPORT]);
+		ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
 	}
 
 	if (data[IFLA_IPTUN_ENCAP_DPORT]) {
 		ret = true;
-		ipencap->dport = nla_get_u16(data[IFLA_IPTUN_ENCAP_DPORT]);
+		ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
 	}
 
 	return ret;
@@ -1707,9 +1707,9 @@
 
 	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
 			tunnel->encap.type) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_SPORT,
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
 			tunnel->encap.sport) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_DPORT,
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
 			tunnel->encap.dport) ||
 	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
 			tunnel->encap.flags))
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b6aa8ed..a562769 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -52,6 +52,10 @@
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
 
+		/* Set the IPv6 fragment id if not set yet */
+		if (!skb_shinfo(skb)->ip6_frag_id)
+			ipv6_proxy_select_ident(skb);
+
 		segs = NULL;
 		goto out;
 	}
@@ -108,7 +112,11 @@
 		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 		fptr->nexthdr = nexthdr;
 		fptr->reserved = 0;
-		fptr->identification = skb_shinfo(skb)->ip6_frag_id;
+		if (skb_shinfo(skb)->ip6_frag_id)
+			fptr->identification = skb_shinfo(skb)->ip6_frag_id;
+		else
+			ipv6_select_ident(fptr,
+					  (struct rt6_info *)skb_dst(skb));
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
 		 * fragment header are updated in ipv6_gso_segment()
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 990decb..b87ca32 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -659,16 +659,24 @@
 	return err;
 }
 
-static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
+static int ip_vs_route_me_harder(int af, struct sk_buff *skb,
+				 unsigned int hooknum)
 {
+	if (!sysctl_snat_reroute(skb))
+		return 0;
+	/* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */
+	if (NF_INET_LOCAL_IN == hooknum)
+		return 0;
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0)
+		struct dst_entry *dst = skb_dst(skb);
+
+		if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
+		    ip6_route_me_harder(skb) != 0)
 			return 1;
 	} else
 #endif
-		if ((sysctl_snat_reroute(skb) ||
-		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			return 1;
 
@@ -791,7 +799,8 @@
 				union nf_inet_addr *snet,
 				__u8 protocol, struct ip_vs_conn *cp,
 				struct ip_vs_protocol *pp,
-				unsigned int offset, unsigned int ihl)
+				unsigned int offset, unsigned int ihl,
+				unsigned int hooknum)
 {
 	unsigned int verdict = NF_DROP;
 
@@ -821,7 +830,7 @@
 #endif
 		ip_vs_nat_icmp(skb, pp, cp, 1);
 
-	if (ip_vs_route_me_harder(af, skb))
+	if (ip_vs_route_me_harder(af, skb, hooknum))
 		goto out;
 
 	/* do the statistics and put it back */
@@ -916,7 +925,7 @@
 
 	snet.ip = iph->saddr;
 	return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
-				    pp, ciph.len, ihl);
+				    pp, ciph.len, ihl, hooknum);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -981,7 +990,8 @@
 	snet.in6 = ciph.saddr.in6;
 	writable = ciph.len;
 	return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
-				    pp, writable, sizeof(struct ipv6hdr));
+				    pp, writable, sizeof(struct ipv6hdr),
+				    hooknum);
 }
 #endif
 
@@ -1040,7 +1050,8 @@
  */
 static unsigned int
 handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
+		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph,
+		unsigned int hooknum)
 {
 	struct ip_vs_protocol *pp = pd->pp;
 
@@ -1078,7 +1089,7 @@
 	 * if it came from this machine itself.  So re-compute
 	 * the routing information.
 	 */
-	if (ip_vs_route_me_harder(af, skb))
+	if (ip_vs_route_me_harder(af, skb, hooknum))
 		goto drop;
 
 	IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
@@ -1181,7 +1192,7 @@
 	cp = pp->conn_out_get(af, skb, &iph, 0);
 
 	if (likely(cp))
-		return handle_response(af, skb, pd, cp, &iph);
+		return handle_response(af, skb, pd, cp, &iph, hooknum);
 	if (sysctl_nat_icmp_send(net) &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3b3ddb4..1ff04bc 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1134,9 +1134,11 @@
 	/* Restore old counters on this cpu, no problem. Per-cpu statistics
 	 * are not exposed to userspace.
 	 */
+	preempt_disable();
 	stats = this_cpu_ptr(newstats);
 	stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
 	stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
+	preempt_enable();
 
 	return newstats;
 }
@@ -1262,8 +1264,10 @@
 		nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
 		trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN,
 					sizeof(struct nft_trans_chain));
-		if (trans == NULL)
+		if (trans == NULL) {
+			free_percpu(stats);
 			return -ENOMEM;
+		}
 
 		nft_trans_chain_stats(trans) = stats;
 		nft_trans_chain_update(trans) = true;
@@ -1319,8 +1323,10 @@
 		hookfn = type->hooks[hooknum];
 
 		basechain = kzalloc(sizeof(*basechain), GFP_KERNEL);
-		if (basechain == NULL)
+		if (basechain == NULL) {
+			module_put(type->owner);
 			return -ENOMEM;
+		}
 
 		if (nla[NFTA_CHAIN_COUNTERS]) {
 			stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
@@ -3753,6 +3759,24 @@
 }
 EXPORT_SYMBOL_GPL(nft_chain_validate_dependency);
 
+int nft_chain_validate_hooks(const struct nft_chain *chain,
+			     unsigned int hook_flags)
+{
+	struct nft_base_chain *basechain;
+
+	if (chain->flags & NFT_BASE_CHAIN) {
+		basechain = nft_base_chain(chain);
+
+		if ((1 << basechain->ops[0].hooknum) & hook_flags)
+			return 0;
+
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_chain_validate_hooks);
+
 /*
  * Loop detection - walk through the ruleset beginning at the destination chain
  * of a new jump until either the source chain is reached (loop) or all
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index d1ffd5e..9aea747 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -21,6 +21,21 @@
 };
 EXPORT_SYMBOL_GPL(nft_masq_policy);
 
+int nft_masq_validate(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nft_data **data)
+{
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	return nft_chain_validate_hooks(ctx->chain,
+				        (1 << NF_INET_POST_ROUTING));
+}
+EXPORT_SYMBOL_GPL(nft_masq_validate);
+
 int nft_masq_init(const struct nft_ctx *ctx,
 		  const struct nft_expr *expr,
 		  const struct nlattr * const tb[])
@@ -28,8 +43,8 @@
 	struct nft_masq *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-	if (err < 0)
+	err = nft_masq_validate(ctx, expr, NULL);
+	if (err)
 		return err;
 
 	if (tb[NFTA_MASQ_FLAGS] == NULL)
@@ -60,12 +75,5 @@
 }
 EXPORT_SYMBOL_GPL(nft_masq_dump);
 
-int nft_masq_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		      const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-EXPORT_SYMBOL_GPL(nft_masq_validate);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index aff54fb1..a0837c6 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -88,6 +88,33 @@
 	[NFTA_NAT_FLAGS]	 = { .type = NLA_U32 },
 };
 
+static int nft_nat_validate(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nft_data **data)
+{
+	struct nft_nat *priv = nft_expr_priv(expr);
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	switch (priv->type) {
+	case NFT_NAT_SNAT:
+		err = nft_chain_validate_hooks(ctx->chain,
+					       (1 << NF_INET_POST_ROUTING) |
+					       (1 << NF_INET_LOCAL_IN));
+		break;
+	case NFT_NAT_DNAT:
+		err = nft_chain_validate_hooks(ctx->chain,
+					       (1 << NF_INET_PRE_ROUTING) |
+					       (1 << NF_INET_LOCAL_OUT));
+		break;
+	}
+
+	return err;
+}
+
 static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 			const struct nlattr * const tb[])
 {
@@ -95,10 +122,6 @@
 	u32 family;
 	int err;
 
-	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-	if (err < 0)
-		return err;
-
 	if (tb[NFTA_NAT_TYPE] == NULL ||
 	    (tb[NFTA_NAT_REG_ADDR_MIN] == NULL &&
 	     tb[NFTA_NAT_REG_PROTO_MIN] == NULL))
@@ -115,6 +138,10 @@
 		return -EINVAL;
 	}
 
+	err = nft_nat_validate(ctx, expr, NULL);
+	if (err < 0)
+		return err;
+
 	if (tb[NFTA_NAT_FAMILY] == NULL)
 		return -EINVAL;
 
@@ -219,13 +246,6 @@
 	return -1;
 }
 
-static int nft_nat_validate(const struct nft_ctx *ctx,
-			    const struct nft_expr *expr,
-			    const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-
 static struct nft_expr_type nft_nat_type;
 static const struct nft_expr_ops nft_nat_ops = {
 	.type           = &nft_nat_type,
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 9e8093f..d7e9e93 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -23,6 +23,22 @@
 };
 EXPORT_SYMBOL_GPL(nft_redir_policy);
 
+int nft_redir_validate(const struct nft_ctx *ctx,
+		       const struct nft_expr *expr,
+		       const struct nft_data **data)
+{
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	return nft_chain_validate_hooks(ctx->chain,
+					(1 << NF_INET_PRE_ROUTING) |
+					(1 << NF_INET_LOCAL_OUT));
+}
+EXPORT_SYMBOL_GPL(nft_redir_validate);
+
 int nft_redir_init(const struct nft_ctx *ctx,
 		   const struct nft_expr *expr,
 		   const struct nlattr * const tb[])
@@ -30,7 +46,7 @@
 	struct nft_redir *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	err = nft_redir_validate(ctx, expr, NULL);
 	if (err < 0)
 		return err;
 
@@ -88,12 +104,5 @@
 }
 EXPORT_SYMBOL_GPL(nft_redir_dump);
 
-int nft_redir_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		       const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-EXPORT_SYMBOL_GPL(nft_redir_validate);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 02fdde2..75532ef 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1438,7 +1438,7 @@
 
 	for (undo = 0; undo < group; undo++)
 		if (test_bit(undo, &groups))
-			nlk->netlink_unbind(sock_net(sk), undo);
+			nlk->netlink_unbind(sock_net(sk), undo + 1);
 }
 
 static int netlink_bind(struct socket *sock, struct sockaddr *addr,
@@ -1476,7 +1476,7 @@
 		for (group = 0; group < nlk->ngroups; group++) {
 			if (!test_bit(group, &groups))
 				continue;
-			err = nlk->netlink_bind(net, group);
+			err = nlk->netlink_bind(net, group + 1);
 			if (!err)
 				continue;
 			netlink_undo_bind(group, groups, sk);
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index c3b0cd43..c173f69 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -71,14 +71,14 @@
 	{
 		.procname	= "max_unacked_packets",
 		.data		= &rds_sysctl_max_unacked_packets,
-		.maxlen         = sizeof(unsigned long),
+		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
 	{
 		.procname	= "max_unacked_bytes",
 		.data		= &rds_sysctl_max_unacked_bytes,
-		.maxlen         = sizeof(unsigned long),
+		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index aad6a67..baef987 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -556,8 +556,9 @@
 }
 EXPORT_SYMBOL(tcf_exts_change);
 
-#define tcf_exts_first_act(ext) \
-		list_first_entry(&(exts)->actions, struct tc_action, list)
+#define tcf_exts_first_act(ext)					\
+	list_first_entry_or_null(&(exts)->actions,		\
+				 struct tc_action, list)
 
 int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
 {
@@ -603,7 +604,7 @@
 {
 #ifdef CONFIG_NET_CLS_ACT
 	struct tc_action *a = tcf_exts_first_act(exts);
-	if (tcf_action_copy_stats(skb, a, 1) < 0)
+	if (a != NULL && tcf_action_copy_stats(skb, a, 1) < 0)
 		return -1;
 #endif
 	return 0;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 9b05924..333cd94 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -670,8 +670,14 @@
 	if (tb[TCA_FQ_FLOW_PLIMIT])
 		q->flow_plimit = nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT]);
 
-	if (tb[TCA_FQ_QUANTUM])
-		q->quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
+	if (tb[TCA_FQ_QUANTUM]) {
+		u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
+
+		if (quantum > 0)
+			q->quantum = quantum;
+		else
+			err = -EINVAL;
+	}
 
 	if (tb[TCA_FQ_INITIAL_QUANTUM])
 		q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]);
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index e49e231..06320c8 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2608,7 +2608,7 @@
 
 		addr_param = param.v + sizeof(sctp_addip_param_t);
 
-		af = sctp_get_af_specific(param_type2af(param.p->type));
+		af = sctp_get_af_specific(param_type2af(addr_param->p.type));
 		if (af == NULL)
 			break;
 
diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig
index 8eb779b9d..604e718 100644
--- a/security/tomoyo/Kconfig
+++ b/security/tomoyo/Kconfig
@@ -5,6 +5,7 @@
 	select SECURITYFS
 	select SECURITY_PATH
 	select SECURITY_NETWORK
+	select SRCU
 	default n
 	help
 	  This selects TOMOYO Linux, pathname-based access control.
diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c
index 1a3a6fa..c6bba99 100644
--- a/sound/i2c/other/ak4113.c
+++ b/sound/i2c/other/ak4113.c
@@ -56,8 +56,7 @@
 
 static void snd_ak4113_free(struct ak4113 *chip)
 {
-	chip->init = 1;	/* don't schedule new work */
-	mb();
+	atomic_inc(&chip->wq_processing);	/* don't schedule new work */
 	cancel_delayed_work_sync(&chip->work);
 	kfree(chip);
 }
@@ -89,6 +88,7 @@
 	chip->write = write;
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4113_stats);
+	atomic_set(&chip->wq_processing, 0);
 
 	for (reg = 0; reg < AK4113_WRITABLE_REGS ; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -139,13 +139,11 @@
 
 void snd_ak4113_reinit(struct ak4113 *chip)
 {
-	chip->init = 1;
-	mb();
-	flush_delayed_work(&chip->work);
+	if (atomic_inc_return(&chip->wq_processing) == 1)
+		cancel_delayed_work_sync(&chip->work);
 	ak4113_init_regs(chip);
 	/* bring up statistics / event queing */
-	chip->init = 0;
-	if (chip->kctls[0])
+	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
 EXPORT_SYMBOL_GPL(snd_ak4113_reinit);
@@ -632,8 +630,9 @@
 {
 	struct ak4113 *chip = container_of(work, struct ak4113, work.work);
 
-	if (!chip->init)
+	if (atomic_inc_return(&chip->wq_processing) == 1)
 		snd_ak4113_check_rate_and_errors(chip, chip->check_flags);
 
-	schedule_delayed_work(&chip->work, HZ / 10);
+	if (atomic_dec_and_test(&chip->wq_processing))
+		schedule_delayed_work(&chip->work, HZ / 10);
 }
diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c
index c7f5633..b70e6ec 100644
--- a/sound/i2c/other/ak4114.c
+++ b/sound/i2c/other/ak4114.c
@@ -66,8 +66,7 @@
 
 static void snd_ak4114_free(struct ak4114 *chip)
 {
-	chip->init = 1;	/* don't schedule new work */
-	mb();
+	atomic_inc(&chip->wq_processing);	/* don't schedule new work */
 	cancel_delayed_work_sync(&chip->work);
 	kfree(chip);
 }
@@ -100,6 +99,7 @@
 	chip->write = write;
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4114_stats);
+	atomic_set(&chip->wq_processing, 0);
 
 	for (reg = 0; reg < 6; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -152,13 +152,11 @@
 
 void snd_ak4114_reinit(struct ak4114 *chip)
 {
-	chip->init = 1;
-	mb();
-	flush_delayed_work(&chip->work);
+	if (atomic_inc_return(&chip->wq_processing) == 1)
+		cancel_delayed_work_sync(&chip->work);
 	ak4114_init_regs(chip);
 	/* bring up statistics / event queing */
-	chip->init = 0;
-	if (chip->kctls[0])
+	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
 
@@ -612,10 +610,10 @@
 {
 	struct ak4114 *chip = container_of(work, struct ak4114, work.work);
 
-	if (!chip->init)
+	if (atomic_inc_return(&chip->wq_processing) == 1)
 		snd_ak4114_check_rate_and_errors(chip, chip->check_flags);
-
-	schedule_delayed_work(&chip->work, HZ / 10);
+	if (atomic_dec_and_test(&chip->wq_processing))
+		schedule_delayed_work(&chip->work, HZ / 10);
 }
 
 EXPORT_SYMBOL(snd_ak4114_create);
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index 99ff35e..35e44e4 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -348,7 +348,6 @@
 	struct atmel_pcm_dma_params *dma_params;
 	int dir, channels, bits;
 	u32 tfmr, rfmr, tcmr, rcmr;
-	int start_event;
 	int ret;
 	int fslen, fslen_ext;
 
@@ -457,19 +456,10 @@
 		 * The SSC transmit clock is obtained from the BCLK signal on
 		 * on the TK line, and the SSC receive clock is
 		 * generated from the transmit clock.
-		 *
-		 *  For single channel data, one sample is transferred
-		 * on the falling edge of the LRC clock.
-		 * For two channel data, one sample is
-		 * transferred on both edges of the LRC clock.
 		 */
-		start_event = ((channels == 1)
-				? SSC_START_FALLING_RF
-				: SSC_START_EDGE_RF);
-
 		rcmr =	  SSC_BF(RCMR_PERIOD, 0)
 			| SSC_BF(RCMR_STTDLY, START_DELAY)
-			| SSC_BF(RCMR_START, start_event)
+			| SSC_BF(RCMR_START, SSC_START_FALLING_RF)
 			| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
 			| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ?
@@ -478,14 +468,14 @@
 		rfmr =	  SSC_BF(RFMR_FSEDGE, SSC_FSEDGE_POSITIVE)
 			| SSC_BF(RFMR_FSOS, SSC_FSOS_NONE)
 			| SSC_BF(RFMR_FSLEN, 0)
-			| SSC_BF(RFMR_DATNB, 0)
+			| SSC_BF(RFMR_DATNB, (channels - 1))
 			| SSC_BIT(RFMR_MSBF)
 			| SSC_BF(RFMR_LOOP, 0)
 			| SSC_BF(RFMR_DATLEN, (bits - 1));
 
 		tcmr =	  SSC_BF(TCMR_PERIOD, 0)
 			| SSC_BF(TCMR_STTDLY, START_DELAY)
-			| SSC_BF(TCMR_START, start_event)
+			| SSC_BF(TCMR_START, SSC_START_FALLING_RF)
 			| SSC_BF(TCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(TCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(TCMR_CKS, ssc->clk_from_rk_pin ?
@@ -495,7 +485,7 @@
 			| SSC_BF(TFMR_FSDEN, 0)
 			| SSC_BF(TFMR_FSOS, SSC_FSOS_NONE)
 			| SSC_BF(TFMR_FSLEN, 0)
-			| SSC_BF(TFMR_DATNB, 0)
+			| SSC_BF(TFMR_DATNB, (channels - 1))
 			| SSC_BIT(TFMR_MSBF)
 			| SSC_BF(TFMR_DATDEF, 0)
 			| SSC_BF(TFMR_DATLEN, (bits - 1));
@@ -512,7 +502,7 @@
 		rcmr =	  SSC_BF(RCMR_PERIOD, ssc_p->rcmr_period)
 			| SSC_BF(RCMR_STTDLY, 1)
 			| SSC_BF(RCMR_START, SSC_START_RISING_RF)
-			| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
+			| SSC_BF(RCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(RCMR_CKS, SSC_CKS_DIV);
 
@@ -527,7 +517,7 @@
 		tcmr =	  SSC_BF(TCMR_PERIOD, ssc_p->tcmr_period)
 			| SSC_BF(TCMR_STTDLY, 1)
 			| SSC_BF(TCMR_START, SSC_START_RISING_RF)
-			| SSC_BF(TCMR_CKI, SSC_CKI_RISING)
+			| SSC_BF(TCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(TCMR_CKO, SSC_CKO_CONTINUOUS)
 			| SSC_BF(TCMR_CKS, SSC_CKS_DIV);
 
@@ -556,7 +546,7 @@
 		rcmr =	  SSC_BF(RCMR_PERIOD, 0)
 			| SSC_BF(RCMR_STTDLY, START_DELAY)
 			| SSC_BF(RCMR_START, SSC_START_RISING_RF)
-			| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
+			| SSC_BF(RCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ?
 					   SSC_CKS_PIN : SSC_CKS_CLOCK);
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index c3f2dec..1ff726c 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -2124,6 +2124,7 @@
 static struct acpi_device_id rt5640_acpi_match[] = {
 	{ "INT33CA", 0 },
 	{ "10EC5640", 0 },
+	{ "10EC5642", 0 },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, rt5640_acpi_match);
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 29cf7ce..aa98be3 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -483,21 +483,21 @@
 	/* setting i2s data format */
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_A:
-		i2sctl |= SGTL5000_I2S_MODE_PCM;
+		i2sctl |= SGTL5000_I2S_MODE_PCM << SGTL5000_I2S_MODE_SHIFT;
 		break;
 	case SND_SOC_DAIFMT_DSP_B:
-		i2sctl |= SGTL5000_I2S_MODE_PCM;
+		i2sctl |= SGTL5000_I2S_MODE_PCM << SGTL5000_I2S_MODE_SHIFT;
 		i2sctl |= SGTL5000_I2S_LRALIGN;
 		break;
 	case SND_SOC_DAIFMT_I2S:
-		i2sctl |= SGTL5000_I2S_MODE_I2S_LJ;
+		i2sctl |= SGTL5000_I2S_MODE_I2S_LJ << SGTL5000_I2S_MODE_SHIFT;
 		break;
 	case SND_SOC_DAIFMT_RIGHT_J:
-		i2sctl |= SGTL5000_I2S_MODE_RJ;
+		i2sctl |= SGTL5000_I2S_MODE_RJ << SGTL5000_I2S_MODE_SHIFT;
 		i2sctl |= SGTL5000_I2S_LRPOL;
 		break;
 	case SND_SOC_DAIFMT_LEFT_J:
-		i2sctl |= SGTL5000_I2S_MODE_I2S_LJ;
+		i2sctl |= SGTL5000_I2S_MODE_I2S_LJ << SGTL5000_I2S_MODE_SHIFT;
 		i2sctl |= SGTL5000_I2S_LRALIGN;
 		break;
 	default:
@@ -1462,6 +1462,9 @@
 	if (ret)
 		return ret;
 
+	/* Need 8 clocks before I2C accesses */
+	udelay(1);
+
 	/* read chip information */
 	ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ID, &reg);
 	if (ret)
diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c
index b7ebce0..dd222b1 100644
--- a/sound/soc/codecs/tlv320aic3x.c
+++ b/sound/soc/codecs/tlv320aic3x.c
@@ -1046,7 +1046,7 @@
 		delay += aic3x->tdm_delay;
 
 	/* Configure data delay */
-	snd_soc_write(codec, AIC3X_ASD_INTF_CTRLC, aic3x->tdm_delay);
+	snd_soc_write(codec, AIC3X_ASD_INTF_CTRLC, delay);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index b9211b4..b115ed8 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -717,6 +717,8 @@
 	if (wm8731 == NULL)
 		return -ENOMEM;
 
+	mutex_init(&wm8731->lock);
+
 	wm8731->regmap = devm_regmap_init_i2c(i2c, &wm8731_regmap);
 	if (IS_ERR(wm8731->regmap)) {
 		ret = PTR_ERR(wm8731->regmap);
diff --git a/sound/soc/codecs/wm9705.c b/sound/soc/codecs/wm9705.c
index 3eddb18..5cc457e 100644
--- a/sound/soc/codecs/wm9705.c
+++ b/sound/soc/codecs/wm9705.c
@@ -344,23 +344,27 @@
 	struct snd_ac97 *ac97;
 	int ret = 0;
 
-	ac97 = snd_soc_new_ac97_codec(codec);
+	ac97 = snd_soc_alloc_ac97_codec(codec);
 	if (IS_ERR(ac97)) {
 		ret = PTR_ERR(ac97);
 		dev_err(codec->dev, "Failed to register AC97 codec\n");
 		return ret;
 	}
 
-	snd_soc_codec_set_drvdata(codec, ac97);
-
 	ret = wm9705_reset(codec);
 	if (ret)
-		goto reset_err;
+		goto err_put_device;
+
+	ret = device_add(&ac97->dev);
+	if (ret)
+		goto err_put_device;
+
+	snd_soc_codec_set_drvdata(codec, ac97);
 
 	return 0;
 
-reset_err:
-	snd_soc_free_ac97_codec(ac97);
+err_put_device:
+	put_device(&ac97->dev);
 	return ret;
 }
 
diff --git a/sound/soc/codecs/wm9712.c b/sound/soc/codecs/wm9712.c
index e04643d..9517571 100644
--- a/sound/soc/codecs/wm9712.c
+++ b/sound/soc/codecs/wm9712.c
@@ -666,7 +666,7 @@
 	struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec);
 	int ret = 0;
 
-	wm9712->ac97 = snd_soc_new_ac97_codec(codec);
+	wm9712->ac97 = snd_soc_alloc_ac97_codec(codec);
 	if (IS_ERR(wm9712->ac97)) {
 		ret = PTR_ERR(wm9712->ac97);
 		dev_err(codec->dev, "Failed to register AC97 codec: %d\n", ret);
@@ -675,15 +675,19 @@
 
 	ret = wm9712_reset(codec, 0);
 	if (ret < 0)
-		goto reset_err;
+		goto err_put_device;
+
+	ret = device_add(&wm9712->ac97->dev);
+	if (ret)
+		goto err_put_device;
 
 	/* set alc mux to none */
 	ac97_write(codec, AC97_VIDEO, ac97_read(codec, AC97_VIDEO) | 0x3000);
 
 	return 0;
 
-reset_err:
-	snd_soc_free_ac97_codec(wm9712->ac97);
+err_put_device:
+	put_device(&wm9712->ac97->dev);
 	return ret;
 }
 
diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c
index 71b9d5b..6ab1122 100644
--- a/sound/soc/codecs/wm9713.c
+++ b/sound/soc/codecs/wm9713.c
@@ -1225,7 +1225,7 @@
 	struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec);
 	int ret = 0, reg;
 
-	wm9713->ac97 = snd_soc_new_ac97_codec(codec);
+	wm9713->ac97 = snd_soc_alloc_ac97_codec(codec);
 	if (IS_ERR(wm9713->ac97))
 		return PTR_ERR(wm9713->ac97);
 
@@ -1234,7 +1234,11 @@
 	wm9713_reset(codec, 0);
 	ret = wm9713_reset(codec, 1);
 	if (ret < 0)
-		goto reset_err;
+		goto err_put_device;
+
+	ret = device_add(&wm9713->ac97->dev);
+	if (ret)
+		goto err_put_device;
 
 	/* unmute the adc - move to kcontrol */
 	reg = ac97_read(codec, AC97_CD) & 0x7fff;
@@ -1242,8 +1246,8 @@
 
 	return 0;
 
-reset_err:
-	snd_soc_free_ac97_codec(wm9713->ac97);
+err_put_device:
+	put_device(&wm9713->ac97->dev);
 	return ret;
 }
 
diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c
index 5bf1404..8156cc1 100644
--- a/sound/soc/intel/sst-haswell-ipc.c
+++ b/sound/soc/intel/sst-haswell-ipc.c
@@ -651,11 +651,11 @@
 	}
 
 	/* tell DSP that notification has been handled */
-	sst_dsp_shim_update_bits_unlocked(hsw->dsp, SST_IPCD,
+	sst_dsp_shim_update_bits(hsw->dsp, SST_IPCD,
 		SST_IPCD_BUSY | SST_IPCD_DONE, SST_IPCD_DONE);
 
 	/* unmask busy interrupt */
-	sst_dsp_shim_update_bits_unlocked(hsw->dsp, SST_IMRX, SST_IMRX_BUSY, 0);
+	sst_dsp_shim_update_bits(hsw->dsp, SST_IMRX, SST_IMRX_BUSY, 0);
 }
 
 static struct ipc_message *reply_find_msg(struct sst_hsw *hsw, u32 header)
diff --git a/sound/soc/intel/sst/sst_acpi.c b/sound/soc/intel/sst/sst_acpi.c
index 2ac72eb..b336013 100644
--- a/sound/soc/intel/sst/sst_acpi.c
+++ b/sound/soc/intel/sst/sst_acpi.c
@@ -350,7 +350,7 @@
 
 /* Cherryview-based platforms: CherryTrail and Braswell */
 static struct sst_machines sst_acpi_chv[] = {
-	{"10EC5670", "cht-bsw", "cht-bsw-rt5672", NULL, "fw_sst_22a8.bin",
+	{"10EC5670", "cht-bsw", "cht-bsw-rt5672", NULL, "intel/fw_sst_22a8.bin",
 						&chv_platform_data },
 	{},
 };
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index 2e10e9a..08d7259 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -48,15 +48,18 @@
 }
 
 /**
- * snd_soc_new_ac97_codec - initailise AC97 device
- * @codec: audio codec
+ * snd_soc_alloc_ac97_codec() - Allocate new a AC'97 device
+ * @codec: The CODEC for which to create the AC'97 device
  *
- * Initialises AC97 codec resources for use by ad-hoc devices only.
+ * Allocated a new snd_ac97 device and intializes it, but does not yet register
+ * it. The caller is responsible to either call device_add(&ac97->dev) to
+ * register the device, or to call put_device(&ac97->dev) to free the device.
+ *
+ * Returns: A snd_ac97 device or a PTR_ERR in case of an error.
  */
-struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
+struct snd_ac97 *snd_soc_alloc_ac97_codec(struct snd_soc_codec *codec)
 {
 	struct snd_ac97 *ac97;
-	int ret;
 
 	ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
 	if (ac97 == NULL)
@@ -73,7 +76,28 @@
 		     codec->component.card->snd_card->number, 0,
 		     codec->component.name);
 
-	ret = device_register(&ac97->dev);
+	device_initialize(&ac97->dev);
+
+	return ac97;
+}
+EXPORT_SYMBOL(snd_soc_alloc_ac97_codec);
+
+/**
+ * snd_soc_new_ac97_codec - initailise AC97 device
+ * @codec: audio codec
+ *
+ * Initialises AC97 codec resources for use by ad-hoc devices only.
+ */
+struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
+{
+	struct snd_ac97 *ac97;
+	int ret;
+
+	ac97 = snd_soc_alloc_ac97_codec(codec);
+	if (IS_ERR(ac97))
+		return ac97;
+
+	ret = device_add(&ac97->dev);
 	if (ret) {
 		put_device(&ac97->dev);
 		return ERR_PTR(ret);
diff --git a/tools/lib/lockdep/.gitignore b/tools/lib/lockdep/.gitignore
new file mode 100644
index 0000000..cc0e7a9
--- /dev/null
+++ b/tools/lib/lockdep/.gitignore
@@ -0,0 +1 @@
+liblockdep.so.*
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 52f9279..4b866c5 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -104,7 +104,7 @@
 
 export Q VERBOSE
 
-INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES)
+INCLUDES = -I. -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES)
 
 # Set compile option CFLAGS if not set elsewhere
 CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g
diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
index abe14b7..bb99cde 100755
--- a/tools/testing/selftests/rcutorture/bin/cpus2use.sh
+++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
@@ -24,7 +24,7 @@
 
 ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
 idlecpus=`mpstat | tail -1 | \
-	awk -v ncpus=$ncpus '{ print ncpus * ($7 + $12) / 100 }'`
+	awk -v ncpus=$ncpus '{ print ncpus * ($7 + $NF) / 100 }'`
 awk -v ncpus=$ncpus -v idlecpus=$idlecpus < /dev/null '
 BEGIN {
 	cpus2use = idlecpus;
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index d6cc07f..559e01a 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -30,6 +30,7 @@
 	echo Unreadable results directory: $i
 	exit 1
 fi
+. tools/testing/selftests/rcutorture/bin/functions.sh
 
 configfile=`echo $i | sed -e 's/^.*\///'`
 ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'`
@@ -48,4 +49,21 @@
 		title="$title ($ngpsps per second)"
 	fi
 	echo $title
+	nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
+	if test -z "$nclosecalls"
+	then
+		exit 0
+	fi
+	if test "$nclosecalls" -eq 0
+	then
+		exit 0
+	fi
+	# Compute number of close calls per tenth of an hour
+	nclosecalls10=`awk -v nclosecalls=$nclosecalls -v dur=$dur 'BEGIN { print int(nclosecalls * 36000 / dur) }' < /dev/null`
+	if test $nclosecalls10 -gt 5 -a $nclosecalls -gt 1
+	then
+		print_bug $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
+	else
+		print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
+	fi
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 8ca9f21..5236e07 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -8,9 +8,9 @@
 #
 # Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args
 #
-# qemu-args defaults to "-nographic", along with arguments specifying the
-#			number of CPUs and other options generated from
-#			the underlying CPU architecture.
+# qemu-args defaults to "-enable-kvm -soundhw pcspk -nographic", along with
+#			arguments specifying the number of CPUs and other
+#			options generated from the underlying CPU architecture.
 # boot_args defaults to value returned by the per_version_boot_params
 #			shell function.
 #
@@ -138,7 +138,7 @@
 fi
 
 # Generate -smp qemu argument.
-qemu_args="-nographic $qemu_args"
+qemu_args="-enable-kvm -soundhw pcspk -nographic $qemu_args"
 cpu_count=`configNR_CPUS.sh $config_template`
 cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"`
 vcpus=`identify_qemu_vcpus`
@@ -168,6 +168,7 @@
 	touch $resdir/buildonly
 	exit 0
 fi
+echo "NOTE: $QEMU either did not run or was interactive" > $builddir/console.log
 echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
 ( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) &
 qemu_pid=$!
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index 499d1e5..a6b5762 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -26,12 +26,15 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=$1
+F=$1
 title=$2
+T=/tmp/parse-build.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
 
 . functions.sh
 
-if grep -q CC < $T
+if grep -q CC < $F
 then
 	:
 else
@@ -39,18 +42,21 @@
 	exit 1
 fi
 
-if grep -q "error:" < $T
+if grep -q "error:" < $F
 then
 	print_bug $title build errors:
-	grep "error:" < $T
+	grep "error:" < $F
 	exit 2
 fi
-exit 0
 
-if egrep -q "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+grep warning: < $F > $T/warnings
+grep "include/linux/*rcu*\.h:" $T/warnings > $T/hwarnings
+grep "kernel/rcu/[^/]*:" $T/warnings > $T/cwarnings
+cat $T/hwarnings $T/cwarnings > $T/rcuwarnings
+if test -s $T/rcuwarnings
 then
 	print_warning $title build errors:
-	egrep "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+	cat $T/rcuwarnings
 	exit 2
 fi
 exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index f962ba4..d8f35cf 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -36,7 +36,7 @@
 then
 	print_warning Console output contains nul bytes, old qemu still running?
 fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
 if test -s $T
 then
 	print_warning Assertion failure in $file $title