Merge branch 'for-linus' of git://git.kernel.dk/linux-2.6-block

* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
  block: Remove the extra check in queue_requests_store
  block, blk-sysfs: Fix an err return path in blk_register_queue()
  block: remove stale kerneldoc member from __blk_run_queue()
  block: get rid of QUEUE_FLAG_REENTER
  cfq-iosched: read_lock() does not always imply rcu_read_lock()
  block: kill blk_flush_plug_list() export
diff --git a/Documentation/input/event-codes.txt b/Documentation/input/event-codes.txt
new file mode 100644
index 0000000..23fcb05
--- /dev/null
+++ b/Documentation/input/event-codes.txt
@@ -0,0 +1,262 @@
+The input protocol uses a map of types and codes to express input device values
+to userspace. This document describes the types and codes and how and when they
+may be used.
+
+A single hardware event generates multiple input events. Each input event
+contains the new value of a single data item. A special event type, EV_SYN, is
+used to separate input events into packets of input data changes occurring at
+the same moment in time. In the following, the term "event" refers to a single
+input event encompassing a type, code, and value.
+
+The input protocol is a stateful protocol. Events are emitted only when values
+of event codes have changed. However, the state is maintained within the Linux
+input subsystem; drivers do not need to maintain the state and may attempt to
+emit unchanged values without harm. Userspace may obtain the current state of
+event code values using the EVIOCG* ioctls defined in linux/input.h. The event
+reports supported by a device are also provided by sysfs in
+class/input/event*/device/capabilities/, and the properties of a device are
+provided in class/input/event*/device/properties.
+
+Types:
+==========
+Types are groupings of codes under a logical input construct. Each type has a
+set of applicable codes to be used in generating events. See the Codes section
+for details on valid codes for each type.
+
+* EV_SYN:
+  - Used as markers to separate events. Events may be separated in time or in
+    space, such as with the multitouch protocol.
+
+* EV_KEY:
+  - Used to describe state changes of keyboards, buttons, or other key-like
+    devices.
+
+* EV_REL:
+  - Used to describe relative axis value changes, e.g. moving the mouse 5 units
+    to the left.
+
+* EV_ABS:
+  - Used to describe absolute axis value changes, e.g. describing the
+    coordinates of a touch on a touchscreen.
+
+* EV_MSC:
+  - Used to describe miscellaneous input data that do not fit into other types.
+
+* EV_SW:
+  - Used to describe binary state input switches.
+
+* EV_LED:
+  - Used to turn LEDs on devices on and off.
+
+* EV_SND:
+  - Used to output sound to devices.
+
+* EV_REP:
+  - Used for autorepeating devices.
+
+* EV_FF:
+  - Used to send force feedback commands to an input device.
+
+* EV_PWR:
+  - A special type for power button and switch input.
+
+* EV_FF_STATUS:
+  - Used to receive force feedback device status.
+
+Codes:
+==========
+Codes define the precise type of event.
+
+EV_SYN:
+----------
+EV_SYN event values are undefined. Their usage is defined only by when they are
+sent in the evdev event stream.
+
+* SYN_REPORT:
+  - Used to synchronize and separate events into packets of input data changes
+    occurring at the same moment in time. For example, motion of a mouse may set
+    the REL_X and REL_Y values for one motion, then emit a SYN_REPORT. The next
+    motion will emit more REL_X and REL_Y values and send another SYN_REPORT.
+
+* SYN_CONFIG:
+  - TBD
+
+* SYN_MT_REPORT:
+  - Used to synchronize and separate touch events. See the
+    multi-touch-protocol.txt document for more information.
+
+* SYN_DROPPED:
+  - Used to indicate buffer overrun in the evdev client's event queue.
+    Client should ignore all events up to and including next SYN_REPORT
+    event and query the device (using EVIOCG* ioctls) to obtain its
+    current state.
+
+EV_KEY:
+----------
+EV_KEY events take the form KEY_<name> or BTN_<name>. For example, KEY_A is used
+to represent the 'A' key on a keyboard. When a key is depressed, an event with
+the key's code is emitted with value 1. When the key is released, an event is
+emitted with value 0. Some hardware send events when a key is repeated. These
+events have a value of 2. In general, KEY_<name> is used for keyboard keys, and
+BTN_<name> is used for other types of momentary switch events.
+
+A few EV_KEY codes have special meanings:
+
+* BTN_TOOL_<name>:
+  - These codes are used in conjunction with input trackpads, tablets, and
+    touchscreens. These devices may be used with fingers, pens, or other tools.
+    When an event occurs and a tool is used, the corresponding BTN_TOOL_<name>
+    code should be set to a value of 1. When the tool is no longer interacting
+    with the input device, the BTN_TOOL_<name> code should be reset to 0. All
+    trackpads, tablets, and touchscreens should use at least one BTN_TOOL_<name>
+    code when events are generated.
+
+* BTN_TOUCH:
+    BTN_TOUCH is used for touch contact. While an input tool is determined to be
+    within meaningful physical contact, the value of this property must be set
+    to 1. Meaningful physical contact may mean any contact, or it may mean
+    contact conditioned by an implementation defined property. For example, a
+    touchpad may set the value to 1 only when the touch pressure rises above a
+    certain value. BTN_TOUCH may be combined with BTN_TOOL_<name> codes. For
+    example, a pen tablet may set BTN_TOOL_PEN to 1 and BTN_TOUCH to 0 while the
+    pen is hovering over but not touching the tablet surface.
+
+Note: For appropriate function of the legacy mousedev emulation driver,
+BTN_TOUCH must be the first evdev code emitted in a synchronization frame.
+
+Note: Historically a touch device with BTN_TOOL_FINGER and BTN_TOUCH was
+interpreted as a touchpad by userspace, while a similar device without
+BTN_TOOL_FINGER was interpreted as a touchscreen. For backwards compatibility
+with current userspace it is recommended to follow this distinction. In the
+future, this distinction will be deprecated and the device properties ioctl
+EVIOCGPROP, defined in linux/input.h, will be used to convey the device type.
+
+* BTN_TOOL_FINGER, BTN_TOOL_DOUBLETAP, BTN_TOOL_TRIPLETAP, BTN_TOOL_QUADTAP:
+  - These codes denote one, two, three, and four finger interaction on a
+    trackpad or touchscreen. For example, if the user uses two fingers and moves
+    them on the touchpad in an effort to scroll content on screen,
+    BTN_TOOL_DOUBLETAP should be set to value 1 for the duration of the motion.
+    Note that all BTN_TOOL_<name> codes and the BTN_TOUCH code are orthogonal in
+    purpose. A trackpad event generated by finger touches should generate events
+    for one code from each group. At most only one of these BTN_TOOL_<name>
+    codes should have a value of 1 during any synchronization frame.
+
+Note: Historically some drivers emitted multiple of the finger count codes with
+a value of 1 in the same synchronization frame. This usage is deprecated.
+
+Note: In multitouch drivers, the input_mt_report_finger_count() function should
+be used to emit these codes. Please see multi-touch-protocol.txt for details.
+
+EV_REL:
+----------
+EV_REL events describe relative changes in a property. For example, a mouse may
+move to the left by a certain number of units, but its absolute position in
+space is unknown. If the absolute position is known, EV_ABS codes should be used
+instead of EV_REL codes.
+
+A few EV_REL codes have special meanings:
+
+* REL_WHEEL, REL_HWHEEL:
+  - These codes are used for vertical and horizontal scroll wheels,
+    respectively.
+
+EV_ABS:
+----------
+EV_ABS events describe absolute changes in a property. For example, a touchpad
+may emit coordinates for a touch location.
+
+A few EV_ABS codes have special meanings:
+
+* ABS_DISTANCE:
+  - Used to describe the distance of a tool from an interaction surface. This
+    event should only be emitted while the tool is hovering, meaning in close
+    proximity of the device and while the value of the BTN_TOUCH code is 0. If
+    the input device may be used freely in three dimensions, consider ABS_Z
+    instead.
+
+* ABS_MT_<name>:
+  - Used to describe multitouch input events. Please see
+    multi-touch-protocol.txt for details.
+
+EV_SW:
+----------
+EV_SW events describe stateful binary switches. For example, the SW_LID code is
+used to denote when a laptop lid is closed.
+
+Upon binding to a device or resuming from suspend, a driver must report
+the current switch state. This ensures that the device, kernel, and userspace
+state is in sync.
+
+Upon resume, if the switch state is the same as before suspend, then the input
+subsystem will filter out the duplicate switch state reports. The driver does
+not need to keep the state of the switch at any time.
+
+EV_MSC:
+----------
+EV_MSC events are used for input and output events that do not fall under other
+categories.
+
+EV_LED:
+----------
+EV_LED events are used for input and output to set and query the state of
+various LEDs on devices.
+
+EV_REP:
+----------
+EV_REP events are used for specifying autorepeating events.
+
+EV_SND:
+----------
+EV_SND events are used for sending sound commands to simple sound output
+devices.
+
+EV_FF:
+----------
+EV_FF events are used to initialize a force feedback capable device and to cause
+such device to feedback.
+
+EV_PWR:
+----------
+EV_PWR events are a special type of event used specifically for power
+mangement. Its usage is not well defined. To be addressed later.
+
+Guidelines:
+==========
+The guidelines below ensure proper single-touch and multi-finger functionality.
+For multi-touch functionality, see the multi-touch-protocol.txt document for
+more information.
+
+Mice:
+----------
+REL_{X,Y} must be reported when the mouse moves. BTN_LEFT must be used to report
+the primary button press. BTN_{MIDDLE,RIGHT,4,5,etc.} should be used to report
+further buttons of the device. REL_WHEEL and REL_HWHEEL should be used to report
+scroll wheel events where available.
+
+Touchscreens:
+----------
+ABS_{X,Y} must be reported with the location of the touch. BTN_TOUCH must be
+used to report when a touch is active on the screen.
+BTN_{MOUSE,LEFT,MIDDLE,RIGHT} must not be reported as the result of touch
+contact. BTN_TOOL_<name> events should be reported where possible.
+
+Trackpads:
+----------
+Legacy trackpads that only provide relative position information must report
+events like mice described above.
+
+Trackpads that provide absolute touch position must report ABS_{X,Y} for the
+location of the touch. BTN_TOUCH should be used to report when a touch is active
+on the trackpad. Where multi-finger support is available, BTN_TOOL_<name> should
+be used to report the number of touches active on the trackpad.
+
+Tablets:
+----------
+BTN_TOOL_<name> events must be reported when a stylus or other tool is active on
+the tablet. ABS_{X,Y} must be reported with the location of the tool. BTN_TOUCH
+should be used to report when the tool is in contact with the tablet.
+BTN_{STYLUS,STYLUS2} should be used to report buttons on the tool itself. Any
+button may be used for buttons on the tablet except BTN_{MOUSE,LEFT}.
+BTN_{0,1,2,etc} are good generic codes for unlabeled buttons. Do not use
+meaningful buttons, like BTN_FORWARD, unless the button is labeled for that
+purpose on the device.
diff --git a/MAINTAINERS b/MAINTAINERS
index ec36003..1e2724e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -151,6 +151,7 @@
 F:	drivers/net/hamradio/6pack.c
 
 8169 10/100/1000 GIGABIT ETHERNET DRIVER
+M:	Realtek linux nic maintainers <nic_swsd@realtek.com>
 M:	Francois Romieu <romieu@fr.zoreil.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
diff --git a/Makefile b/Makefile
index 322e733..b967b96 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 39
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*
diff --git a/arch/arm/mach-msm/board-qsd8x50.c b/arch/arm/mach-msm/board-qsd8x50.c
index 7f56861..6a96911 100644
--- a/arch/arm/mach-msm/board-qsd8x50.c
+++ b/arch/arm/mach-msm/board-qsd8x50.c
@@ -160,10 +160,7 @@
 
 static void __init qsd8x50_init_mmc(void)
 {
-	if (machine_is_qsd8x50_ffa() || machine_is_qsd8x50a_ffa())
-		vreg_mmc = vreg_get(NULL, "gp6");
-	else
-		vreg_mmc = vreg_get(NULL, "gp5");
+	vreg_mmc = vreg_get(NULL, "gp5");
 
 	if (IS_ERR(vreg_mmc)) {
 		pr_err("vreg get for vreg_mmc failed (%ld)\n",
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 56f920c..38b95e9 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -269,7 +269,7 @@
 
 	/* Use existing clock_event for cpu 0 */
 	if (!smp_processor_id())
-		return;
+		return 0;
 
 	writel(DGT_CLK_CTL_DIV_4, MSM_TMR_BASE + DGT_CLK_CTL);
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b6ff882..8f4d50b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -209,7 +209,7 @@
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 	depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx || \
-		   PPC_85xx || PPC_86xx || PPC_PSERIES || 44x || 40x
+		   (PPC_85xx && !SMP) || PPC_86xx || PPC_PSERIES || 44x || 40x
 
 config PPC_DCR_NATIVE
 	bool
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index be3cdf9..1833d1a 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -382,10 +382,12 @@
 #define CPU_FTRS_E500_2	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
 	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_E500MC	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
-	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
+#define CPU_FTRS_E500MC	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL)
+#define CPU_FTRS_E5500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
+	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD)
 #define CPU_FTRS_GENERIC_32	(CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
 
 /* 64-bit CPUs */
@@ -435,11 +437,15 @@
 #define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
 
 #ifdef __powerpc64__
+#ifdef CONFIG_PPC_BOOK3E
+#define CPU_FTRS_POSSIBLE	(CPU_FTRS_E5500)
+#else
 #define CPU_FTRS_POSSIBLE	\
 	    (CPU_FTRS_POWER3 | CPU_FTRS_RS64 | CPU_FTRS_POWER4 |	\
 	    CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | CPU_FTRS_POWER6 |	\
 	    CPU_FTRS_POWER7 | CPU_FTRS_CELL | CPU_FTRS_PA6T |		\
 	    CPU_FTR_1T_SEGMENT | CPU_FTR_VSX)
+#endif
 #else
 enum {
 	CPU_FTRS_POSSIBLE =
@@ -473,16 +479,21 @@
 #endif
 #ifdef CONFIG_E500
 	    CPU_FTRS_E500 | CPU_FTRS_E500_2 | CPU_FTRS_E500MC |
+	    CPU_FTRS_E5500 |
 #endif
 	    0,
 };
 #endif /* __powerpc64__ */
 
 #ifdef __powerpc64__
+#ifdef CONFIG_PPC_BOOK3E
+#define CPU_FTRS_ALWAYS		(CPU_FTRS_E5500)
+#else
 #define CPU_FTRS_ALWAYS		\
 	    (CPU_FTRS_POWER3 & CPU_FTRS_RS64 & CPU_FTRS_POWER4 &	\
 	    CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & CPU_FTRS_POWER6 &	\
 	    CPU_FTRS_POWER7 & CPU_FTRS_CELL & CPU_FTRS_PA6T & CPU_FTRS_POSSIBLE)
+#endif
 #else
 enum {
 	CPU_FTRS_ALWAYS =
@@ -513,6 +524,7 @@
 #endif
 #ifdef CONFIG_E500
 	    CPU_FTRS_E500 & CPU_FTRS_E500_2 & CPU_FTRS_E500MC &
+	    CPU_FTRS_E5500 &
 #endif
 	    CPU_FTRS_POSSIBLE,
 };
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index 811f04a..8d1569c 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -162,7 +162,7 @@
  * on platforms where such control is possible.
  */
 #if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\
-	defined(CONFIG_KPROBES)
+	defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE)
 #define PAGE_KERNEL_TEXT	PAGE_KERNEL_X
 #else
 #define PAGE_KERNEL_TEXT	PAGE_KERNEL_ROX
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index c9b68d0..b9602ee 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1973,7 +1973,7 @@
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x80240000,
 		.cpu_name		= "e5500",
-		.cpu_features		= CPU_FTRS_E500MC,
+		.cpu_features		= CPU_FTRS_E5500,
 		.cpu_user_features	= COMMON_USER_BOOKE,
 		.mmu_features		= MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
 			MMU_FTR_USE_TLBILX,
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 3d3d416..5b5e1f0 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -163,7 +163,7 @@
 }
 
 /* wait for all the CPUs to hit real mode but timeout if they don't come in */
-#if defined(CONFIG_PPC_STD_MMU_64) && defined(CONFIG_SMP)
+#ifdef CONFIG_PPC_STD_MMU_64
 static void crash_kexec_wait_realmode(int cpu)
 {
 	unsigned int msecs;
@@ -188,9 +188,7 @@
 	}
 	mb();
 }
-#else
-static inline void crash_kexec_wait_realmode(int cpu) {}
-#endif
+#endif	/* CONFIG_PPC_STD_MMU_64 */
 
 /*
  * This function will be called by secondary cpus or by kexec cpu
@@ -235,7 +233,9 @@
 	crash_ipi_callback(regs);
 }
 
-#else
+#else	/* ! CONFIG_SMP */
+static inline void crash_kexec_wait_realmode(int cpu) {}
+
 static void crash_kexec_prepare_cpus(int cpu)
 {
 	/*
@@ -255,7 +255,7 @@
 {
 	cpus_in_sr = CPU_MASK_NONE;
 }
-#endif
+#endif	/* CONFIG_SMP */
 
 /*
  * Register a function to be called on shutdown.  Only use this if you
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index c834757..2b97b80 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -330,9 +330,11 @@
 		if (!parent)
 			continue;
 		if (of_match_node(legacy_serial_parents, parent) != NULL) {
-			index = add_legacy_soc_port(np, np);
-			if (index >= 0 && np == stdout)
-				legacy_serial_console = index;
+			if (of_device_is_available(np)) {
+				index = add_legacy_soc_port(np, np);
+				if (index >= 0 && np == stdout)
+					legacy_serial_console = index;
+			}
 		}
 		of_node_put(parent);
 	}
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index c4063b7..822f630 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -398,6 +398,25 @@
 	return 0;
 }
 
+static u64 check_and_compute_delta(u64 prev, u64 val)
+{
+	u64 delta = (val - prev) & 0xfffffffful;
+
+	/*
+	 * POWER7 can roll back counter values, if the new value is smaller
+	 * than the previous value it will cause the delta and the counter to
+	 * have bogus values unless we rolled a counter over.  If a coutner is
+	 * rolled back, it will be smaller, but within 256, which is the maximum
+	 * number of events to rollback at once.  If we dectect a rollback
+	 * return 0.  This can lead to a small lack of precision in the
+	 * counters.
+	 */
+	if (prev > val && (prev - val) < 256)
+		delta = 0;
+
+	return delta;
+}
+
 static void power_pmu_read(struct perf_event *event)
 {
 	s64 val, delta, prev;
@@ -416,10 +435,11 @@
 		prev = local64_read(&event->hw.prev_count);
 		barrier();
 		val = read_pmc(event->hw.idx);
+		delta = check_and_compute_delta(prev, val);
+		if (!delta)
+			return;
 	} while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
 
-	/* The counters are only 32 bits wide */
-	delta = (val - prev) & 0xfffffffful;
 	local64_add(delta, &event->count);
 	local64_sub(delta, &event->hw.period_left);
 }
@@ -449,8 +469,9 @@
 		val = (event->hw.idx == 5) ? pmc5 : pmc6;
 		prev = local64_read(&event->hw.prev_count);
 		event->hw.idx = 0;
-		delta = (val - prev) & 0xfffffffful;
-		local64_add(delta, &event->count);
+		delta = check_and_compute_delta(prev, val);
+		if (delta)
+			local64_add(delta, &event->count);
 	}
 }
 
@@ -458,14 +479,16 @@
 				  unsigned long pmc5, unsigned long pmc6)
 {
 	struct perf_event *event;
-	u64 val;
+	u64 val, prev;
 	int i;
 
 	for (i = 0; i < cpuhw->n_limited; ++i) {
 		event = cpuhw->limited_counter[i];
 		event->hw.idx = cpuhw->limited_hwidx[i];
 		val = (event->hw.idx == 5) ? pmc5 : pmc6;
-		local64_set(&event->hw.prev_count, val);
+		prev = local64_read(&event->hw.prev_count);
+		if (check_and_compute_delta(prev, val))
+			local64_set(&event->hw.prev_count, val);
 		perf_event_update_userpage(event);
 	}
 }
@@ -1197,7 +1220,7 @@
 
 	/* we don't have to worry about interrupts here */
 	prev = local64_read(&event->hw.prev_count);
-	delta = (val - prev) & 0xfffffffful;
+	delta = check_and_compute_delta(prev, val);
 	local64_add(delta, &event->count);
 
 	/*
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 375480c..f33acfd 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -229,6 +229,9 @@
 	u64 stolen = 0;
 	u64 dtb;
 
+	if (!dtl)
+		return 0;
+
 	if (i == vpa->dtl_idx)
 		return 0;
 	while (i < vpa->dtl_idx) {
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index a830c5e..bc5f0dc 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -842,6 +842,7 @@
 	mpic_setup_this_cpu();
 }
 
+#ifdef CONFIG_PPC64
 #ifdef CONFIG_HOTPLUG_CPU
 static int smp_core99_cpu_notify(struct notifier_block *self,
 				 unsigned long action, void *hcpu)
@@ -879,7 +880,6 @@
 
 static void __init smp_core99_bringup_done(void)
 {
-#ifdef CONFIG_PPC64
 	extern void g5_phy_disable_cpu1(void);
 
 	/* Close i2c bus if it was used for tb sync */
@@ -894,14 +894,14 @@
 		set_cpu_present(1, false);
 		g5_phy_disable_cpu1();
 	}
-#endif /* CONFIG_PPC64 */
-
 #ifdef CONFIG_HOTPLUG_CPU
 	register_cpu_notifier(&smp_core99_cpu_nb);
 #endif
+
 	if (ppc_md.progress)
 		ppc_md.progress("smp_core99_bringup_done", 0x349);
 }
+#endif /* CONFIG_PPC64 */
 
 #ifdef CONFIG_HOTPLUG_CPU
 
@@ -975,7 +975,9 @@
 struct smp_ops_t core99_smp_ops = {
 	.message_pass	= smp_mpic_message_pass,
 	.probe		= smp_core99_probe,
+#ifdef CONFIG_PPC64
 	.bringup_done	= smp_core99_bringup_done,
+#endif
 	.kick_cpu	= smp_core99_kick_cpu,
 	.setup_cpu	= smp_core99_setup_cpu,
 	.give_timebase	= smp_core99_give_timebase,
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 0007241..6c42cfd 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -287,14 +287,22 @@
 	int cpu, ret;
 	struct paca_struct *pp;
 	struct dtl_entry *dtl;
+	struct kmem_cache *dtl_cache;
 
 	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
 		return 0;
 
+	dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES,
+						DISPATCH_LOG_BYTES, 0, NULL);
+	if (!dtl_cache) {
+		pr_warn("Failed to create dispatch trace log buffer cache\n");
+		pr_warn("Stolen time statistics will be unreliable\n");
+		return 0;
+	}
+
 	for_each_possible_cpu(cpu) {
 		pp = &paca[cpu];
-		dtl = kmalloc_node(DISPATCH_LOG_BYTES, GFP_KERNEL,
-				   cpu_to_node(cpu));
+		dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL);
 		if (!dtl) {
 			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
 				cpu);
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index f8f7f28..68ca929 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -324,6 +324,11 @@
 	struct resource rsrc;
 	const int *bus_range;
 
+	if (!of_device_is_available(dev)) {
+		pr_warning("%s: disabled\n", dev->full_name);
+		return -ENODEV;
+	}
+
 	pr_debug("Adding PCI host bridge %s\n", dev->full_name);
 
 	/* Fetch host bridge registers address */
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 43085bf..156cd5d 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -66,7 +66,7 @@
 	 * Don't enable translation but enable GART IO and CPU accesses.
 	 * Also, set DISTLBWALKPRB since GART tables memory is UC.
 	 */
-	ctl = DISTLBWALKPRB | order << 1;
+	ctl = order << 1;
 
 	pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 }
@@ -75,17 +75,17 @@
 {
 	u32 tmp, ctl;
 
-        /* address of the mappings table */
-        addr >>= 12;
-        tmp = (u32) addr<<4;
-        tmp &= ~0xf;
-        pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
+	/* address of the mappings table */
+	addr >>= 12;
+	tmp = (u32) addr<<4;
+	tmp &= ~0xf;
+	pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
 
-        /* Enable GART translation for this hammer. */
-        pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
-        ctl |= GARTEN;
-        ctl &= ~(DISGARTCPU | DISGARTIO);
-        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+	/* Enable GART translation for this hammer. */
+	pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
+	ctl |= GARTEN | DISTLBWALKPRB;
+	ctl &= ~(DISGARTCPU | DISGARTIO);
+	pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 }
 
 static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 86d1ad4..73fb469 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -499,7 +499,7 @@
 		 * Don't enable translation yet but enable GART IO and CPU
 		 * accesses and set DISTLBWALKPRB since GART table memory is UC.
 		 */
-		u32 ctl = DISTLBWALKPRB | aper_order << 1;
+		u32 ctl = aper_order << 1;
 
 		bus = amd_nb_bus_dev_ranges[i].bus;
 		dev_base = amd_nb_bus_dev_ranges[i].dev_base;
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 461f62b..cf4e369 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -8,7 +8,7 @@
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
-		[ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
+		[ C(RESULT_MISS)   ] = 0x0141, /* Data Cache Misses          */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
@@ -427,7 +427,9 @@
  *
  * Exceptions:
  *
+ * 0x000	FP	PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x003	FP	PERF_CTL[3]
+ * 0x004	FP	PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x00B	FP	PERF_CTL[3]
  * 0x00D	FP	PERF_CTL[3]
  * 0x023	DE	PERF_CTL[2:0]
@@ -448,6 +450,8 @@
  * 0x0DF	LS	PERF_CTL[5:0]
  * 0x1D6	EX	PERF_CTL[5:0]
  * 0x1D8	EX	PERF_CTL[5:0]
+ *
+ * (*) depending on the umask all FPU counters may be used
  */
 
 static struct event_constraint amd_f15_PMC0  = EVENT_CONSTRAINT(0, 0x01, 0);
@@ -460,18 +464,28 @@
 static struct event_constraint *
 amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
-	unsigned int event_code = amd_get_event_code(&event->hw);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int event_code = amd_get_event_code(hwc);
 
 	switch (event_code & AMD_EVENT_TYPE_MASK) {
 	case AMD_EVENT_FP:
 		switch (event_code) {
+		case 0x000:
+			if (!(hwc->config & 0x0000F000ULL))
+				break;
+			if (!(hwc->config & 0x00000F00ULL))
+				break;
+			return &amd_f15_PMC3;
+		case 0x004:
+			if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)
+				break;
+			return &amd_f15_PMC3;
 		case 0x003:
 		case 0x00B:
 		case 0x00D:
 			return &amd_f15_PMC3;
-		default:
-			return &amd_f15_PMC53;
 		}
+		return &amd_f15_PMC53;
 	case AMD_EVENT_LS:
 	case AMD_EVENT_DC:
 	case AMD_EVENT_EX_LS:
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 82ada01..b117efd 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -81,6 +81,9 @@
 #define AGPEXTERN
 #endif
 
+/* GART can only remap to physical addresses < 1TB */
+#define GART_MAX_PHYS_ADDR	(1ULL << 40)
+
 /* backdoor interface to AGP driver */
 AGPEXTERN int agp_memory_reserved;
 AGPEXTERN __u32 *agp_gatt_table;
@@ -212,9 +215,13 @@
 				size_t size, int dir, unsigned long align_mask)
 {
 	unsigned long npages = iommu_num_pages(phys_mem, size, PAGE_SIZE);
-	unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
+	unsigned long iommu_page;
 	int i;
 
+	if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
+		return bad_dma_addr;
+
+	iommu_page = alloc_iommu(dev, npages, align_mask);
 	if (iommu_page == -1) {
 		if (!nonforced_iommu(dev, phys_mem, size))
 			return phys_mem;
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index d770058..219d88a 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -142,6 +142,7 @@
 		cbq->callback(msg, nsp);
 		kfree_skb(skb);
 		cn_queue_release_callback(cbq);
+		err = 0;
 	}
 
 	return err;
diff --git a/drivers/gpu/drm/nouveau/nouveau_dma.c b/drivers/gpu/drm/nouveau/nouveau_dma.c
index ce38e97..568caed 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dma.c
@@ -83,7 +83,7 @@
 		return ret;
 
 	/* NV_MEMORY_TO_MEMORY_FORMAT requires a notifier object */
-	ret = nouveau_notifier_alloc(chan, NvNotify0, 32, 0xfd0, 0x1000,
+	ret = nouveau_notifier_alloc(chan, NvNotify0, 32, 0xfe0, 0x1000,
 				     &chan->m2mf_ntfy);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 856d56a..a76514a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -682,6 +682,9 @@
 	/* For PFIFO and PGRAPH. */
 	spinlock_t context_switch_lock;
 
+	/* VM/PRAMIN flush, legacy PRAMIN aperture */
+	spinlock_t vm_lock;
+
 	/* RAMIN configuration, RAMFC, RAMHT and RAMRO offsets */
 	struct nouveau_ramht  *ramht;
 	struct nouveau_gpuobj *ramfc;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 889c445..39aee6d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -181,13 +181,13 @@
 		OUT_RING  (chan, 0);
 	}
 
-	nouveau_bo_wr32(chan->notifier_bo, chan->m2mf_ntfy + 3, 0xffffffff);
+	nouveau_bo_wr32(chan->notifier_bo, chan->m2mf_ntfy/4 + 3, 0xffffffff);
 	FIRE_RING(chan);
 	mutex_unlock(&chan->mutex);
 
 	ret = -EBUSY;
 	for (i = 0; i < 100000; i++) {
-		if (!nouveau_bo_rd32(chan->notifier_bo, chan->m2mf_ntfy + 3)) {
+		if (!nouveau_bo_rd32(chan->notifier_bo, chan->m2mf_ntfy/4 + 3)) {
 			ret = 0;
 			break;
 		}
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index 78f467f..5045f8b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -398,7 +398,7 @@
 			dma_bits = 40;
 	} else
 	if (drm_pci_device_is_pcie(dev) &&
-	    dev_priv->chipset != 0x40 &&
+	    dev_priv->chipset  > 0x40 &&
 	    dev_priv->chipset != 0x45) {
 		if (pci_dma_supported(dev->pdev, DMA_BIT_MASK(39)))
 			dma_bits = 39;
diff --git a/drivers/gpu/drm/nouveau/nouveau_notifier.c b/drivers/gpu/drm/nouveau/nouveau_notifier.c
index 7ba3fc0..5b39718 100644
--- a/drivers/gpu/drm/nouveau/nouveau_notifier.c
+++ b/drivers/gpu/drm/nouveau/nouveau_notifier.c
@@ -35,19 +35,22 @@
 {
 	struct drm_device *dev = chan->dev;
 	struct nouveau_bo *ntfy = NULL;
-	uint32_t flags;
+	uint32_t flags, ttmpl;
 	int ret;
 
-	if (nouveau_vram_notify)
+	if (nouveau_vram_notify) {
 		flags = NOUVEAU_GEM_DOMAIN_VRAM;
-	else
+		ttmpl = TTM_PL_FLAG_VRAM;
+	} else {
 		flags = NOUVEAU_GEM_DOMAIN_GART;
+		ttmpl = TTM_PL_FLAG_TT;
+	}
 
 	ret = nouveau_gem_new(dev, NULL, PAGE_SIZE, 0, flags, 0, 0, &ntfy);
 	if (ret)
 		return ret;
 
-	ret = nouveau_bo_pin(ntfy, flags);
+	ret = nouveau_bo_pin(ntfy, ttmpl);
 	if (ret)
 		goto out_err;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_object.c b/drivers/gpu/drm/nouveau/nouveau_object.c
index 4f00c87..67a16e0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_object.c
+++ b/drivers/gpu/drm/nouveau/nouveau_object.c
@@ -1039,19 +1039,20 @@
 {
 	struct drm_nouveau_private *dev_priv = gpuobj->dev->dev_private;
 	struct drm_device *dev = gpuobj->dev;
+	unsigned long flags;
 
 	if (gpuobj->pinst == ~0 || !dev_priv->ramin_available) {
 		u64  ptr = gpuobj->vinst + offset;
 		u32 base = ptr >> 16;
 		u32  val;
 
-		spin_lock(&dev_priv->ramin_lock);
+		spin_lock_irqsave(&dev_priv->vm_lock, flags);
 		if (dev_priv->ramin_base != base) {
 			dev_priv->ramin_base = base;
 			nv_wr32(dev, 0x001700, dev_priv->ramin_base);
 		}
 		val = nv_rd32(dev, 0x700000 + (ptr & 0xffff));
-		spin_unlock(&dev_priv->ramin_lock);
+		spin_unlock_irqrestore(&dev_priv->vm_lock, flags);
 		return val;
 	}
 
@@ -1063,18 +1064,19 @@
 {
 	struct drm_nouveau_private *dev_priv = gpuobj->dev->dev_private;
 	struct drm_device *dev = gpuobj->dev;
+	unsigned long flags;
 
 	if (gpuobj->pinst == ~0 || !dev_priv->ramin_available) {
 		u64  ptr = gpuobj->vinst + offset;
 		u32 base = ptr >> 16;
 
-		spin_lock(&dev_priv->ramin_lock);
+		spin_lock_irqsave(&dev_priv->vm_lock, flags);
 		if (dev_priv->ramin_base != base) {
 			dev_priv->ramin_base = base;
 			nv_wr32(dev, 0x001700, dev_priv->ramin_base);
 		}
 		nv_wr32(dev, 0x700000 + (ptr & 0xffff), val);
-		spin_unlock(&dev_priv->ramin_lock);
+		spin_unlock_irqrestore(&dev_priv->vm_lock, flags);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index a33fe40..4bce801 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -55,6 +55,7 @@
 				be->func->clear(be);
 				return -EFAULT;
 			}
+			nvbe->ttm_alloced[nvbe->nr_pages] = false;
 		}
 
 		nvbe->nr_pages++;
@@ -427,7 +428,7 @@
 	u32 aper_size, align;
 	int ret;
 
-	if (dev_priv->card_type >= NV_50 || drm_pci_device_is_pcie(dev))
+	if (dev_priv->card_type >= NV_40 && drm_pci_device_is_pcie(dev))
 		aper_size = 512 * 1024 * 1024;
 	else
 		aper_size = 64 * 1024 * 1024;
@@ -457,7 +458,7 @@
 		dev_priv->gart_info.func = &nv50_sgdma_backend;
 	} else
 	if (drm_pci_device_is_pcie(dev) &&
-	    dev_priv->chipset != 0x40 && dev_priv->chipset != 0x45) {
+	    dev_priv->chipset > 0x40 && dev_priv->chipset != 0x45) {
 		if (nv44_graph_class(dev)) {
 			dev_priv->gart_info.func = &nv44_sgdma_backend;
 			align = 512 * 1024;
diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
index 6e2b1a6..a30adec 100644
--- a/drivers/gpu/drm/nouveau/nouveau_state.c
+++ b/drivers/gpu/drm/nouveau/nouveau_state.c
@@ -608,6 +608,7 @@
 	spin_lock_init(&dev_priv->channels.lock);
 	spin_lock_init(&dev_priv->tile.lock);
 	spin_lock_init(&dev_priv->context_switch_lock);
+	spin_lock_init(&dev_priv->vm_lock);
 
 	/* Make the CRTCs and I2C buses accessible */
 	ret = engine->display.early_init(dev);
diff --git a/drivers/gpu/drm/nouveau/nv50_instmem.c b/drivers/gpu/drm/nouveau/nv50_instmem.c
index a6f8aa6..4f95a1e 100644
--- a/drivers/gpu/drm/nouveau/nv50_instmem.c
+++ b/drivers/gpu/drm/nouveau/nv50_instmem.c
@@ -404,23 +404,25 @@
 nv50_instmem_flush(struct drm_device *dev)
 {
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	unsigned long flags;
 
-	spin_lock(&dev_priv->ramin_lock);
+	spin_lock_irqsave(&dev_priv->vm_lock, flags);
 	nv_wr32(dev, 0x00330c, 0x00000001);
 	if (!nv_wait(dev, 0x00330c, 0x00000002, 0x00000000))
 		NV_ERROR(dev, "PRAMIN flush timeout\n");
-	spin_unlock(&dev_priv->ramin_lock);
+	spin_unlock_irqrestore(&dev_priv->vm_lock, flags);
 }
 
 void
 nv84_instmem_flush(struct drm_device *dev)
 {
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	unsigned long flags;
 
-	spin_lock(&dev_priv->ramin_lock);
+	spin_lock_irqsave(&dev_priv->vm_lock, flags);
 	nv_wr32(dev, 0x070000, 0x00000001);
 	if (!nv_wait(dev, 0x070000, 0x00000002, 0x00000000))
 		NV_ERROR(dev, "PRAMIN flush timeout\n");
-	spin_unlock(&dev_priv->ramin_lock);
+	spin_unlock_irqrestore(&dev_priv->vm_lock, flags);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nv50_vm.c b/drivers/gpu/drm/nouveau/nv50_vm.c
index 4fd3432..6c26944 100644
--- a/drivers/gpu/drm/nouveau/nv50_vm.c
+++ b/drivers/gpu/drm/nouveau/nv50_vm.c
@@ -174,10 +174,11 @@
 nv50_vm_flush_engine(struct drm_device *dev, int engine)
 {
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	unsigned long flags;
 
-	spin_lock(&dev_priv->ramin_lock);
+	spin_lock_irqsave(&dev_priv->vm_lock, flags);
 	nv_wr32(dev, 0x100c80, (engine << 16) | 1);
 	if (!nv_wait(dev, 0x100c80, 0x00000001, 0x00000000))
 		NV_ERROR(dev, "vm flush timeout: engine %d\n", engine);
-	spin_unlock(&dev_priv->ramin_lock);
+	spin_unlock_irqrestore(&dev_priv->vm_lock, flags);
 }
diff --git a/drivers/gpu/drm/nouveau/nvc0_vm.c b/drivers/gpu/drm/nouveau/nvc0_vm.c
index a0a2a02..a179e6c 100644
--- a/drivers/gpu/drm/nouveau/nvc0_vm.c
+++ b/drivers/gpu/drm/nouveau/nvc0_vm.c
@@ -104,11 +104,12 @@
 	struct nouveau_instmem_engine *pinstmem = &dev_priv->engine.instmem;
 	struct drm_device *dev = vm->dev;
 	struct nouveau_vm_pgd *vpgd;
+	unsigned long flags;
 	u32 engine = (dev_priv->chan_vm == vm) ? 1 : 5;
 
 	pinstmem->flush(vm->dev);
 
-	spin_lock(&dev_priv->ramin_lock);
+	spin_lock_irqsave(&dev_priv->vm_lock, flags);
 	list_for_each_entry(vpgd, &vm->pgd_list, head) {
 		/* looks like maybe a "free flush slots" counter, the
 		 * faster you write to 0x100cbc to more it decreases
@@ -125,5 +126,5 @@
 				 nv_rd32(dev, 0x100c80), engine);
 		}
 	}
-	spin_unlock(&dev_priv->ramin_lock);
+	spin_unlock_irqrestore(&dev_priv->vm_lock, flags);
 }
diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c
index d71d375..7bd7456 100644
--- a/drivers/gpu/drm/radeon/atom.c
+++ b/drivers/gpu/drm/radeon/atom.c
@@ -135,7 +135,7 @@
 		case ATOM_IIO_MOVE_INDEX:
 			temp &=
 			    ~((0xFFFFFFFF >> (32 - CU8(base + 1))) <<
-			      CU8(base + 2));
+			      CU8(base + 3));
 			temp |=
 			    ((index >> CU8(base + 2)) &
 			     (0xFFFFFFFF >> (32 - CU8(base + 1)))) << CU8(base +
@@ -145,7 +145,7 @@
 		case ATOM_IIO_MOVE_DATA:
 			temp &=
 			    ~((0xFFFFFFFF >> (32 - CU8(base + 1))) <<
-			      CU8(base + 2));
+			      CU8(base + 3));
 			temp |=
 			    ((data >> CU8(base + 2)) &
 			     (0xFFFFFFFF >> (32 - CU8(base + 1)))) << CU8(base +
@@ -155,7 +155,7 @@
 		case ATOM_IIO_MOVE_ATTR:
 			temp &=
 			    ~((0xFFFFFFFF >> (32 - CU8(base + 1))) <<
-			      CU8(base + 2));
+			      CU8(base + 3));
 			temp |=
 			    ((ctx->
 			      io_attr >> CU8(base + 2)) & (0xFFFFFFFF >> (32 -
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 9d516a8..529a3a7 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -532,10 +532,7 @@
 		else
 			pll->flags |= RADEON_PLL_PREFER_LOW_REF_DIV;
 
-		if ((rdev->family == CHIP_R600) ||
-		    (rdev->family == CHIP_RV610) ||
-		    (rdev->family == CHIP_RV630) ||
-		    (rdev->family == CHIP_RV670))
+		if (rdev->family < CHIP_RV770)
 			pll->flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP;
 	} else {
 		pll->flags |= RADEON_PLL_LEGACY;
@@ -565,7 +562,6 @@
 			if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
 				if (ss_enabled) {
 					if (ss->refdiv) {
-						pll->flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP;
 						pll->flags |= RADEON_PLL_USE_REF_DIV;
 						pll->reference_div = ss->refdiv;
 						if (ASIC_IS_AVIVO(rdev))
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 3453910..43fd016 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -353,7 +353,7 @@
 					struct drm_display_mode *mode,
 					struct drm_display_mode *other_mode)
 {
-	u32 tmp = 0;
+	u32 tmp;
 	/*
 	 * Line Buffer Setup
 	 * There are 3 line buffers, each one shared by 2 display controllers.
@@ -363,64 +363,63 @@
 	 * first display controller
 	 *  0 - first half of lb (3840 * 2)
 	 *  1 - first 3/4 of lb (5760 * 2)
-	 *  2 - whole lb (7680 * 2)
+	 *  2 - whole lb (7680 * 2), other crtc must be disabled
 	 *  3 - first 1/4 of lb (1920 * 2)
 	 * second display controller
 	 *  4 - second half of lb (3840 * 2)
 	 *  5 - second 3/4 of lb (5760 * 2)
-	 *  6 - whole lb (7680 * 2)
+	 *  6 - whole lb (7680 * 2), other crtc must be disabled
 	 *  7 - last 1/4 of lb (1920 * 2)
 	 */
-	if (mode && other_mode) {
-		if (mode->hdisplay > other_mode->hdisplay) {
-			if (mode->hdisplay > 2560)
-				tmp = 1; /* 3/4 */
-			else
-				tmp = 0; /* 1/2 */
-		} else if (other_mode->hdisplay > mode->hdisplay) {
-			if (other_mode->hdisplay > 2560)
-				tmp = 3; /* 1/4 */
-			else
-				tmp = 0; /* 1/2 */
-		} else
+	/* this can get tricky if we have two large displays on a paired group
+	 * of crtcs.  Ideally for multiple large displays we'd assign them to
+	 * non-linked crtcs for maximum line buffer allocation.
+	 */
+	if (radeon_crtc->base.enabled && mode) {
+		if (other_mode)
 			tmp = 0; /* 1/2 */
-	} else if (mode)
-		tmp = 2; /* whole */
-	else if (other_mode)
-		tmp = 3; /* 1/4 */
+		else
+			tmp = 2; /* whole */
+	} else
+		tmp = 0;
 
 	/* second controller of the pair uses second half of the lb */
 	if (radeon_crtc->crtc_id % 2)
 		tmp += 4;
 	WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset, tmp);
 
-	switch (tmp) {
-	case 0:
-	case 4:
-	default:
-		if (ASIC_IS_DCE5(rdev))
-			return 4096 * 2;
-		else
-			return 3840 * 2;
-	case 1:
-	case 5:
-		if (ASIC_IS_DCE5(rdev))
-			return 6144 * 2;
-		else
-			return 5760 * 2;
-	case 2:
-	case 6:
-		if (ASIC_IS_DCE5(rdev))
-			return 8192 * 2;
-		else
-			return 7680 * 2;
-	case 3:
-	case 7:
-		if (ASIC_IS_DCE5(rdev))
-			return 2048 * 2;
-		else
-			return 1920 * 2;
+	if (radeon_crtc->base.enabled && mode) {
+		switch (tmp) {
+		case 0:
+		case 4:
+		default:
+			if (ASIC_IS_DCE5(rdev))
+				return 4096 * 2;
+			else
+				return 3840 * 2;
+		case 1:
+		case 5:
+			if (ASIC_IS_DCE5(rdev))
+				return 6144 * 2;
+			else
+				return 5760 * 2;
+		case 2:
+		case 6:
+			if (ASIC_IS_DCE5(rdev))
+				return 8192 * 2;
+			else
+				return 7680 * 2;
+		case 3:
+		case 7:
+			if (ASIC_IS_DCE5(rdev))
+				return 2048 * 2;
+			else
+				return 1920 * 2;
+		}
 	}
+
+	/* controller not enabled, so no lb used */
+	return 0;
 }
 
 static u32 evergreen_get_number_of_dram_channels(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 2ef6d51..5f45fa1 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1199,7 +1199,7 @@
 	if (router->ddc_valid || router->cd_valid) {
 		radeon_connector->router_bus = radeon_i2c_lookup(rdev, &router->i2c_info);
 		if (!radeon_connector->router_bus)
-			goto failed;
+			DRM_ERROR("Failed to assign router i2c bus! Check dmesg for i2c errors.\n");
 	}
 	switch (connector_type) {
 	case DRM_MODE_CONNECTOR_VGA:
@@ -1208,7 +1208,7 @@
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("VGA: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		radeon_connector->dac_load_detect = true;
 		drm_connector_attach_property(&radeon_connector->base,
@@ -1226,7 +1226,7 @@
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("DVIA: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		radeon_connector->dac_load_detect = true;
 		drm_connector_attach_property(&radeon_connector->base,
@@ -1249,7 +1249,7 @@
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("DVI: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		subpixel_order = SubPixelHorizontalRGB;
 		drm_connector_attach_property(&radeon_connector->base,
@@ -1290,7 +1290,7 @@
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("HDMI: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		drm_connector_attach_property(&radeon_connector->base,
 					      rdev->mode_info.coherent_mode_property,
@@ -1329,10 +1329,10 @@
 			else
 				radeon_dig_connector->dp_i2c_bus = radeon_i2c_create_dp(dev, i2c_bus, "DP-auxch");
 			if (!radeon_dig_connector->dp_i2c_bus)
-				goto failed;
+				DRM_ERROR("DP: Failed to assign dp ddc bus! Check dmesg for i2c errors.\n");
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("DP: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		subpixel_order = SubPixelHorizontalRGB;
 		drm_connector_attach_property(&radeon_connector->base,
@@ -1381,7 +1381,7 @@
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("LVDS: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		drm_connector_attach_property(&radeon_connector->base,
 					      dev->mode_config.scaling_mode_property,
@@ -1457,7 +1457,7 @@
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("VGA: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		radeon_connector->dac_load_detect = true;
 		drm_connector_attach_property(&radeon_connector->base,
@@ -1475,7 +1475,7 @@
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("DVIA: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		radeon_connector->dac_load_detect = true;
 		drm_connector_attach_property(&radeon_connector->base,
@@ -1493,7 +1493,7 @@
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("DVI: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		if (connector_type == DRM_MODE_CONNECTOR_DVII) {
 			radeon_connector->dac_load_detect = true;
@@ -1538,7 +1538,7 @@
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
-				goto failed;
+				DRM_ERROR("LVDS: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
 		}
 		drm_connector_attach_property(&radeon_connector->base,
 					      dev->mode_config.scaling_mode_property,
@@ -1567,9 +1567,4 @@
 				radeon_legacy_backlight_init(radeon_encoder, connector);
 		}
 	}
-	return;
-
-failed:
-	drm_connector_cleanup(connector);
-	kfree(connector);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index ccbabf7..983cbac7 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -1096,6 +1096,9 @@
 	if (!radeon_connector->router.ddc_valid)
 		return;
 
+	if (!radeon_connector->router_bus)
+		return;
+
 	radeon_i2c_get_byte(radeon_connector->router_bus,
 			    radeon_connector->router.i2c_addr,
 			    0x3, &val);
@@ -1121,6 +1124,9 @@
 	if (!radeon_connector->router.cd_valid)
 		return;
 
+	if (!radeon_connector->router_bus)
+		return;
+
 	radeon_i2c_get_byte(radeon_connector->router_bus,
 			    radeon_connector->router.i2c_addr,
 			    0x3, &val);
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index 7f42d3a..88d8e4c 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -39,13 +39,13 @@
 };
 
 struct evdev_client {
-	int head;
-	int tail;
+	unsigned int head;
+	unsigned int tail;
 	spinlock_t buffer_lock; /* protects access to buffer, head and tail */
 	struct fasync_struct *fasync;
 	struct evdev *evdev;
 	struct list_head node;
-	int bufsize;
+	unsigned int bufsize;
 	struct input_event buffer[];
 };
 
@@ -55,16 +55,25 @@
 static void evdev_pass_event(struct evdev_client *client,
 			     struct input_event *event)
 {
-	/*
-	 * Interrupts are disabled, just acquire the lock.
-	 * Make sure we don't leave with the client buffer
-	 * "empty" by having client->head == client->tail.
-	 */
+	/* Interrupts are disabled, just acquire the lock. */
 	spin_lock(&client->buffer_lock);
-	do {
-		client->buffer[client->head++] = *event;
-		client->head &= client->bufsize - 1;
-	} while (client->head == client->tail);
+
+	client->buffer[client->head++] = *event;
+	client->head &= client->bufsize - 1;
+
+	if (unlikely(client->head == client->tail)) {
+		/*
+		 * This effectively "drops" all unconsumed events, leaving
+		 * EV_SYN/SYN_DROPPED plus the newest event in the queue.
+		 */
+		client->tail = (client->head - 2) & (client->bufsize - 1);
+
+		client->buffer[client->tail].time = event->time;
+		client->buffer[client->tail].type = EV_SYN;
+		client->buffer[client->tail].code = SYN_DROPPED;
+		client->buffer[client->tail].value = 0;
+	}
+
 	spin_unlock(&client->buffer_lock);
 
 	if (event->type == EV_SYN)
diff --git a/drivers/input/input.c b/drivers/input/input.c
index d6e8bd8..ebbceed 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1746,6 +1746,42 @@
 }
 EXPORT_SYMBOL(input_set_capability);
 
+static unsigned int input_estimate_events_per_packet(struct input_dev *dev)
+{
+	int mt_slots;
+	int i;
+	unsigned int events;
+
+	if (dev->mtsize) {
+		mt_slots = dev->mtsize;
+	} else if (test_bit(ABS_MT_TRACKING_ID, dev->absbit)) {
+		mt_slots = dev->absinfo[ABS_MT_TRACKING_ID].maximum -
+			   dev->absinfo[ABS_MT_TRACKING_ID].minimum + 1,
+		clamp(mt_slots, 2, 32);
+	} else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) {
+		mt_slots = 2;
+	} else {
+		mt_slots = 0;
+	}
+
+	events = mt_slots + 1; /* count SYN_MT_REPORT and SYN_REPORT */
+
+	for (i = 0; i < ABS_CNT; i++) {
+		if (test_bit(i, dev->absbit)) {
+			if (input_is_mt_axis(i))
+				events += mt_slots;
+			else
+				events++;
+		}
+	}
+
+	for (i = 0; i < REL_CNT; i++)
+		if (test_bit(i, dev->relbit))
+			events++;
+
+	return events;
+}
+
 #define INPUT_CLEANSE_BITMASK(dev, type, bits)				\
 	do {								\
 		if (!test_bit(EV_##type, dev->evbit))			\
@@ -1793,6 +1829,10 @@
 	/* Make sure that bitmasks not mentioned in dev->evbit are clean. */
 	input_cleanse_bitmasks(dev);
 
+	if (!dev->hint_events_per_packet)
+		dev->hint_events_per_packet =
+				input_estimate_events_per_packet(dev);
+
 	/*
 	 * If delay and period are pre-set by the driver, then autorepeating
 	 * is handled by the driver itself and we don't do it in input.c.
diff --git a/drivers/input/keyboard/twl4030_keypad.c b/drivers/input/keyboard/twl4030_keypad.c
index 09bef79..a26922c 100644
--- a/drivers/input/keyboard/twl4030_keypad.c
+++ b/drivers/input/keyboard/twl4030_keypad.c
@@ -332,18 +332,20 @@
 static int __devinit twl4030_kp_probe(struct platform_device *pdev)
 {
 	struct twl4030_keypad_data *pdata = pdev->dev.platform_data;
-	const struct matrix_keymap_data *keymap_data = pdata->keymap_data;
+	const struct matrix_keymap_data *keymap_data;
 	struct twl4030_keypad *kp;
 	struct input_dev *input;
 	u8 reg;
 	int error;
 
-	if (!pdata || !pdata->rows || !pdata->cols ||
+	if (!pdata || !pdata->rows || !pdata->cols || !pdata->keymap_data ||
 	    pdata->rows > TWL4030_MAX_ROWS || pdata->cols > TWL4030_MAX_COLS) {
 		dev_err(&pdev->dev, "Invalid platform_data\n");
 		return -EINVAL;
 	}
 
+	keymap_data = pdata->keymap_data;
+
 	kp = kzalloc(sizeof(*kp), GFP_KERNEL);
 	input = input_allocate_device();
 	if (!kp || !input) {
diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c
index 7077f9b..62bae99 100644
--- a/drivers/input/misc/xen-kbdfront.c
+++ b/drivers/input/misc/xen-kbdfront.c
@@ -303,7 +303,7 @@
 				   enum xenbus_state backend_state)
 {
 	struct xenkbd_info *info = dev_get_drvdata(&dev->dev);
-	int val;
+	int ret, val;
 
 	switch (backend_state) {
 	case XenbusStateInitialising:
@@ -316,6 +316,17 @@
 
 	case XenbusStateInitWait:
 InitWait:
+		ret = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+				   "feature-abs-pointer", "%d", &val);
+		if (ret < 0)
+			val = 0;
+		if (val) {
+			ret = xenbus_printf(XBT_NIL, info->xbdev->nodename,
+					    "request-abs-pointer", "1");
+			if (ret)
+				pr_warning("xenkbd: can't request abs-pointer");
+		}
+
 		xenbus_switch_state(dev, XenbusStateConnected);
 		break;
 
diff --git a/drivers/input/touchscreen/h3600_ts_input.c b/drivers/input/touchscreen/h3600_ts_input.c
index efa0688..45f93d0 100644
--- a/drivers/input/touchscreen/h3600_ts_input.c
+++ b/drivers/input/touchscreen/h3600_ts_input.c
@@ -399,31 +399,34 @@
 			IRQF_SHARED | IRQF_DISABLED, "h3600_action", &ts->dev)) {
 		printk(KERN_ERR "h3600ts.c: Could not allocate Action Button IRQ!\n");
 		err = -EBUSY;
-		goto fail2;
+		goto fail1;
 	}
 
 	if (request_irq(IRQ_GPIO_BITSY_NPOWER_BUTTON, npower_button_handler,
 			IRQF_SHARED | IRQF_DISABLED, "h3600_suspend", &ts->dev)) {
 		printk(KERN_ERR "h3600ts.c: Could not allocate Power Button IRQ!\n");
 		err = -EBUSY;
-		goto fail3;
+		goto fail2;
 	}
 
 	serio_set_drvdata(serio, ts);
 
 	err = serio_open(serio, drv);
 	if (err)
-		return err;
+		goto fail3;
 
 	//h3600_flite_control(1, 25);     /* default brightness */
-	input_register_device(ts->dev);
+	err = input_register_device(ts->dev);
+	if (err)
+		goto fail4;
 
 	return 0;
 
-fail3:	free_irq(IRQ_GPIO_BITSY_NPOWER_BUTTON, ts->dev);
+fail4:	serio_close(serio);
+fail3:	serio_set_drvdata(serio, NULL);
+	free_irq(IRQ_GPIO_BITSY_NPOWER_BUTTON, ts->dev);
 fail2:	free_irq(IRQ_GPIO_BITSY_ACTION_BUTTON, ts->dev);
-fail1:	serio_set_drvdata(serio, NULL);
-	input_free_device(input_dev);
+fail1:	input_free_device(input_dev);
 	kfree(ts);
 	return err;
 }
diff --git a/drivers/media/video/videobuf-dma-contig.c b/drivers/media/video/videobuf-dma-contig.c
index c4742fc..c969111 100644
--- a/drivers/media/video/videobuf-dma-contig.c
+++ b/drivers/media/video/videobuf-dma-contig.c
@@ -300,7 +300,7 @@
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	retval = remap_pfn_range(vma, vma->vm_start,
-				 PFN_DOWN(virt_to_phys(mem->vaddr)),
+				 mem->dma_handle >> PAGE_SHIFT,
 				 size, vma->vm_page_prot);
 	if (retval) {
 		dev_err(q->dev, "mmap: remap failed with error %d. ", retval);
diff --git a/drivers/net/bna/bfa_ioc.c b/drivers/net/bna/bfa_ioc.c
index e3de0b8..7581518ec 100644
--- a/drivers/net/bna/bfa_ioc.c
+++ b/drivers/net/bna/bfa_ioc.c
@@ -38,6 +38,8 @@
 #define bfa_ioc_map_port(__ioc) ((__ioc)->ioc_hwif->ioc_map_port(__ioc))
 #define bfa_ioc_notify_fail(__ioc)			\
 			((__ioc)->ioc_hwif->ioc_notify_fail(__ioc))
+#define bfa_ioc_sync_start(__ioc)               \
+			((__ioc)->ioc_hwif->ioc_sync_start(__ioc))
 #define bfa_ioc_sync_join(__ioc)			\
 			((__ioc)->ioc_hwif->ioc_sync_join(__ioc))
 #define bfa_ioc_sync_leave(__ioc)			\
@@ -602,7 +604,7 @@
 	switch (event) {
 	case IOCPF_E_SEMLOCKED:
 		if (bfa_ioc_firmware_lock(ioc)) {
-			if (bfa_ioc_sync_complete(ioc)) {
+			if (bfa_ioc_sync_start(ioc)) {
 				iocpf->retry_count = 0;
 				bfa_ioc_sync_join(ioc);
 				bfa_fsm_set_state(iocpf, bfa_iocpf_sm_hwinit);
@@ -1314,7 +1316,7 @@
  * execution context (driver/bios) must match.
  */
 static bool
-bfa_ioc_fwver_valid(struct bfa_ioc *ioc)
+bfa_ioc_fwver_valid(struct bfa_ioc *ioc, u32 boot_env)
 {
 	struct bfi_ioc_image_hdr fwhdr, *drv_fwhdr;
 
@@ -1325,7 +1327,7 @@
 	if (fwhdr.signature != drv_fwhdr->signature)
 		return false;
 
-	if (fwhdr.exec != drv_fwhdr->exec)
+	if (swab32(fwhdr.param) != boot_env)
 		return false;
 
 	return bfa_nw_ioc_fwver_cmp(ioc, &fwhdr);
@@ -1352,9 +1354,12 @@
 {
 	enum bfi_ioc_state ioc_fwstate;
 	bool fwvalid;
+	u32 boot_env;
 
 	ioc_fwstate = readl(ioc->ioc_regs.ioc_fwstate);
 
+	boot_env = BFI_BOOT_LOADER_OS;
+
 	if (force)
 		ioc_fwstate = BFI_IOC_UNINIT;
 
@@ -1362,10 +1367,10 @@
 	 * check if firmware is valid
 	 */
 	fwvalid = (ioc_fwstate == BFI_IOC_UNINIT) ?
-		false : bfa_ioc_fwver_valid(ioc);
+		false : bfa_ioc_fwver_valid(ioc, boot_env);
 
 	if (!fwvalid) {
-		bfa_ioc_boot(ioc, BFI_BOOT_TYPE_NORMAL, ioc->pcidev.device_id);
+		bfa_ioc_boot(ioc, BFI_BOOT_TYPE_NORMAL, boot_env);
 		return;
 	}
 
@@ -1396,7 +1401,7 @@
 	/**
 	 * Initialize the h/w for any other states.
 	 */
-	bfa_ioc_boot(ioc, BFI_BOOT_TYPE_NORMAL, ioc->pcidev.device_id);
+	bfa_ioc_boot(ioc, BFI_BOOT_TYPE_NORMAL, boot_env);
 }
 
 void
@@ -1506,7 +1511,7 @@
  */
 static void
 bfa_ioc_download_fw(struct bfa_ioc *ioc, u32 boot_type,
-		    u32 boot_param)
+		    u32 boot_env)
 {
 	u32 *fwimg;
 	u32 pgnum, pgoff;
@@ -1558,10 +1563,10 @@
 	/*
 	 * Set boot type and boot param at the end.
 	*/
-	writel((swab32(swab32(boot_type))), ((ioc->ioc_regs.smem_page_start)
+	writel(boot_type, ((ioc->ioc_regs.smem_page_start)
 			+ (BFI_BOOT_TYPE_OFF)));
-	writel((swab32(swab32(boot_param))), ((ioc->ioc_regs.smem_page_start)
-			+ (BFI_BOOT_PARAM_OFF)));
+	writel(boot_env, ((ioc->ioc_regs.smem_page_start)
+			+ (BFI_BOOT_LOADER_OFF)));
 }
 
 static void
@@ -1721,7 +1726,7 @@
  * as the entry vector.
  */
 static void
-bfa_ioc_boot(struct bfa_ioc *ioc, u32 boot_type, u32 boot_param)
+bfa_ioc_boot(struct bfa_ioc *ioc, u32 boot_type, u32 boot_env)
 {
 	void __iomem *rb;
 
@@ -1734,7 +1739,7 @@
 	 * Initialize IOC state of all functions on a chip reset.
 	 */
 	rb = ioc->pcidev.pci_bar_kva;
-	if (boot_param == BFI_BOOT_TYPE_MEMTEST) {
+	if (boot_type == BFI_BOOT_TYPE_MEMTEST) {
 		writel(BFI_IOC_MEMTEST, (rb + BFA_IOC0_STATE_REG));
 		writel(BFI_IOC_MEMTEST, (rb + BFA_IOC1_STATE_REG));
 	} else {
@@ -1743,7 +1748,7 @@
 	}
 
 	bfa_ioc_msgflush(ioc);
-	bfa_ioc_download_fw(ioc, boot_type, boot_param);
+	bfa_ioc_download_fw(ioc, boot_type, boot_env);
 
 	/**
 	 * Enable interrupts just before starting LPU
diff --git a/drivers/net/bna/bfa_ioc.h b/drivers/net/bna/bfa_ioc.h
index e4974bc..bd48abe 100644
--- a/drivers/net/bna/bfa_ioc.h
+++ b/drivers/net/bna/bfa_ioc.h
@@ -194,6 +194,7 @@
 					bool msix);
 	void		(*ioc_notify_fail)	(struct bfa_ioc *ioc);
 	void		(*ioc_ownership_reset)	(struct bfa_ioc *ioc);
+	bool		(*ioc_sync_start)       (struct bfa_ioc *ioc);
 	void		(*ioc_sync_join)	(struct bfa_ioc *ioc);
 	void		(*ioc_sync_leave)	(struct bfa_ioc *ioc);
 	void		(*ioc_sync_ack)		(struct bfa_ioc *ioc);
diff --git a/drivers/net/bna/bfa_ioc_ct.c b/drivers/net/bna/bfa_ioc_ct.c
index 469997c..87aecdf 100644
--- a/drivers/net/bna/bfa_ioc_ct.c
+++ b/drivers/net/bna/bfa_ioc_ct.c
@@ -41,6 +41,7 @@
 static void bfa_ioc_ct_isr_mode_set(struct bfa_ioc *ioc, bool msix);
 static void bfa_ioc_ct_notify_fail(struct bfa_ioc *ioc);
 static void bfa_ioc_ct_ownership_reset(struct bfa_ioc *ioc);
+static bool bfa_ioc_ct_sync_start(struct bfa_ioc *ioc);
 static void bfa_ioc_ct_sync_join(struct bfa_ioc *ioc);
 static void bfa_ioc_ct_sync_leave(struct bfa_ioc *ioc);
 static void bfa_ioc_ct_sync_ack(struct bfa_ioc *ioc);
@@ -63,6 +64,7 @@
 	nw_hwif_ct.ioc_isr_mode_set = bfa_ioc_ct_isr_mode_set;
 	nw_hwif_ct.ioc_notify_fail = bfa_ioc_ct_notify_fail;
 	nw_hwif_ct.ioc_ownership_reset = bfa_ioc_ct_ownership_reset;
+	nw_hwif_ct.ioc_sync_start = bfa_ioc_ct_sync_start;
 	nw_hwif_ct.ioc_sync_join = bfa_ioc_ct_sync_join;
 	nw_hwif_ct.ioc_sync_leave = bfa_ioc_ct_sync_leave;
 	nw_hwif_ct.ioc_sync_ack = bfa_ioc_ct_sync_ack;
@@ -345,6 +347,32 @@
 /**
  * Synchronized IOC failure processing routines
  */
+static bool
+bfa_ioc_ct_sync_start(struct bfa_ioc *ioc)
+{
+	u32 r32 = readl(ioc->ioc_regs.ioc_fail_sync);
+	u32 sync_reqd = bfa_ioc_ct_get_sync_reqd(r32);
+
+	/*
+	 * Driver load time.  If the sync required bit for this PCI fn
+	 * is set, it is due to an unclean exit by the driver for this
+	 * PCI fn in the previous incarnation. Whoever comes here first
+	 * should clean it up, no matter which PCI fn.
+	 */
+
+	if (sync_reqd & bfa_ioc_ct_sync_pos(ioc)) {
+		writel(0, ioc->ioc_regs.ioc_fail_sync);
+		writel(1, ioc->ioc_regs.ioc_usage_reg);
+		writel(BFI_IOC_UNINIT, ioc->ioc_regs.ioc_fwstate);
+		writel(BFI_IOC_UNINIT, ioc->ioc_regs.alt_ioc_fwstate);
+		return true;
+	}
+
+	return bfa_ioc_ct_sync_complete(ioc);
+}
+/**
+ * Synchronized IOC failure processing routines
+ */
 static void
 bfa_ioc_ct_sync_join(struct bfa_ioc *ioc)
 {
diff --git a/drivers/net/bna/bfi.h b/drivers/net/bna/bfi.h
index a973968..6050379 100644
--- a/drivers/net/bna/bfi.h
+++ b/drivers/net/bna/bfi.h
@@ -184,12 +184,14 @@
 #define BFI_IOC_MSGLEN_MAX	32	/* 32 bytes */
 
 #define BFI_BOOT_TYPE_OFF		8
-#define BFI_BOOT_PARAM_OFF		12
+#define BFI_BOOT_LOADER_OFF		12
 
-#define BFI_BOOT_TYPE_NORMAL 		0	/* param is device id */
+#define BFI_BOOT_TYPE_NORMAL 		0
 #define	BFI_BOOT_TYPE_FLASH		1
 #define	BFI_BOOT_TYPE_MEMTEST		2
 
+#define BFI_BOOT_LOADER_OS		0
+
 #define BFI_BOOT_MEMTEST_RES_ADDR   0x900
 #define BFI_BOOT_MEMTEST_RES_SIG    0xA0A1A2A3
 
diff --git a/drivers/net/bna/bnad.c b/drivers/net/bna/bnad.c
index 9f356d5..8e6ceab 100644
--- a/drivers/net/bna/bnad.c
+++ b/drivers/net/bna/bnad.c
@@ -1837,7 +1837,6 @@
 	/* Initialize the Rx event handlers */
 	rx_cbfn.rcb_setup_cbfn = bnad_cb_rcb_setup;
 	rx_cbfn.rcb_destroy_cbfn = bnad_cb_rcb_destroy;
-	rx_cbfn.rcb_destroy_cbfn = NULL;
 	rx_cbfn.ccb_setup_cbfn = bnad_cb_ccb_setup;
 	rx_cbfn.ccb_destroy_cbfn = bnad_cb_ccb_destroy;
 	rx_cbfn.rx_cleanup_cbfn = bnad_cb_rx_cleanup;
diff --git a/drivers/net/bnx2x/bnx2x_ethtool.c b/drivers/net/bnx2x/bnx2x_ethtool.c
index f505015..89cb977 100644
--- a/drivers/net/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/bnx2x/bnx2x_ethtool.c
@@ -2114,19 +2114,18 @@
 	for (i = 0; i < (data * 2); i++) {
 		if ((i % 2) == 0)
 			bnx2x_set_led(&bp->link_params, &bp->link_vars,
-				      LED_MODE_OPER, SPEED_1000);
+				      LED_MODE_ON, SPEED_1000);
 		else
 			bnx2x_set_led(&bp->link_params, &bp->link_vars,
-				      LED_MODE_OFF, 0);
+				      LED_MODE_FRONT_PANEL_OFF, 0);
 
 		msleep_interruptible(500);
 		if (signal_pending(current))
 			break;
 	}
 
-	if (bp->link_vars.link_up)
-		bnx2x_set_led(&bp->link_params, &bp->link_vars, LED_MODE_OPER,
-			      bp->link_vars.line_speed);
+	bnx2x_set_led(&bp->link_params, &bp->link_vars,
+		      LED_MODE_OPER, bp->link_vars.line_speed);
 
 	return 0;
 }
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 9bc5de3..ba71582 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -176,7 +176,7 @@
 	bond_info->tx_hashtbl = new_hashtbl;
 
 	for (i = 0; i < TLB_HASH_TABLE_SIZE; i++) {
-		tlb_init_table_entry(&bond_info->tx_hashtbl[i], 1);
+		tlb_init_table_entry(&bond_info->tx_hashtbl[i], 0);
 	}
 
 	_unlock_tx_hashtbl(bond);
@@ -701,7 +701,7 @@
 		 */
 		rlb_choose_channel(skb, bond);
 
-		/* The ARP relpy packets must be delayed so that
+		/* The ARP reply packets must be delayed so that
 		 * they can cancel out the influence of the ARP request.
 		 */
 		bond->alb_info.rlb_update_delay_counter = RLB_UPDATE_DELAY;
@@ -1042,7 +1042,7 @@
  *
  * If the permanent hw address of @slave is @bond's hw address, we need to
  * find a different hw address to give @slave, that isn't in use by any other
- * slave in the bond. This address must be, of course, one of the premanent
+ * slave in the bond. This address must be, of course, one of the permanent
  * addresses of the other slaves.
  *
  * We go over the slave list, and for each slave there we compare its
diff --git a/drivers/net/bonding/bond_alb.h b/drivers/net/bonding/bond_alb.h
index 86861f0..8ca7158 100644
--- a/drivers/net/bonding/bond_alb.h
+++ b/drivers/net/bonding/bond_alb.h
@@ -75,7 +75,7 @@
 				 * gave this entry index.
 				 */
 	u32 tx_bytes;		/* Each Client accumulates the BytesTx that
-				 * were tranmitted to it, and after each
+				 * were transmitted to it, and after each
 				 * CallBack the LoadHistory is divided
 				 * by the balance interval
 				 */
@@ -122,7 +122,6 @@
 };
 
 struct alb_bond_info {
-	struct timer_list	alb_timer;
 	struct tlb_client_info	*tx_hashtbl; /* Dynamically allocated */
 	spinlock_t		tx_hashtbl_lock;
 	u32			unbalanced_load;
@@ -140,7 +139,6 @@
 	struct slave		*next_rx_slave;/* next slave to be assigned
 						* to a new rx client for
 						*/
-	u32			rlb_interval_counter;
 	u8			primary_is_promisc;	   /* boolean */
 	u32			rlb_promisc_timeout_counter;/* counts primary
 							     * promiscuity time
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index c0a1bc5..bd1d811 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -260,7 +260,7 @@
 
 	if (!ofdev->dev.of_match)
 		return -EINVAL;
-	data = (struct mpc5xxx_can_data *)of_dev->dev.of_match->data;
+	data = (struct mpc5xxx_can_data *)ofdev->dev.of_match->data;
 
 	base = of_iomap(np, 0);
 	if (!base) {
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index ea0dc45..d70fb76 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -173,7 +173,8 @@
 		| NETIF_F_RXCSUM
 		| NETIF_F_HIGHDMA
 		| NETIF_F_LLTX
-		| NETIF_F_NETNS_LOCAL;
+		| NETIF_F_NETNS_LOCAL
+		| NETIF_F_VLAN_CHALLENGED;
 	dev->ethtool_ops	= &loopback_ethtool_ops;
 	dev->header_ops		= &eth_header_ops;
 	dev->netdev_ops		= &loopback_ops;
diff --git a/drivers/net/natsemi.c b/drivers/net/natsemi.c
index aa2813e..1074231 100644
--- a/drivers/net/natsemi.c
+++ b/drivers/net/natsemi.c
@@ -860,6 +860,9 @@
 		prev_eedata = eedata;
 	}
 
+	/* Store MAC Address in perm_addr */
+	memcpy(dev->perm_addr, dev->dev_addr, ETH_ALEN);
+
 	dev->base_addr = (unsigned long __force) ioaddr;
 	dev->irq = irq;
 
diff --git a/drivers/net/netxen/netxen_nic.h b/drivers/net/netxen/netxen_nic.h
index d7299f1..679dc85 100644
--- a/drivers/net/netxen/netxen_nic.h
+++ b/drivers/net/netxen/netxen_nic.h
@@ -174,7 +174,7 @@
 
 #define	MAX_NUM_CARDS		4
 
-#define MAX_BUFFERS_PER_CMD	32
+#define NETXEN_MAX_FRAGS_PER_TX	14
 #define MAX_TSO_HEADER_DESC	2
 #define MGMT_CMD_DESC_RESV	4
 #define TX_STOP_THRESH		((MAX_SKB_FRAGS >> 2) + MAX_TSO_HEADER_DESC \
@@ -558,7 +558,7 @@
  */
 struct netxen_cmd_buffer {
 	struct sk_buff *skb;
-	struct netxen_skb_frag frag_array[MAX_BUFFERS_PER_CMD + 1];
+	struct netxen_skb_frag frag_array[MAX_SKB_FRAGS + 1];
 	u32 frag_count;
 };
 
diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c
index 83348dc..e8a4b66 100644
--- a/drivers/net/netxen/netxen_nic_main.c
+++ b/drivers/net/netxen/netxen_nic_main.c
@@ -1844,6 +1844,8 @@
 	struct cmd_desc_type0 *hwdesc, *first_desc;
 	struct pci_dev *pdev;
 	int i, k;
+	int delta = 0;
+	struct skb_frag_struct *frag;
 
 	u32 producer;
 	int frag_count, no_of_desc;
@@ -1851,6 +1853,21 @@
 
 	frag_count = skb_shinfo(skb)->nr_frags + 1;
 
+	/* 14 frags supported for normal packet and
+	 * 32 frags supported for TSO packet
+	 */
+	if (!skb_is_gso(skb) && frag_count > NETXEN_MAX_FRAGS_PER_TX) {
+
+		for (i = 0; i < (frag_count - NETXEN_MAX_FRAGS_PER_TX); i++) {
+			frag = &skb_shinfo(skb)->frags[i];
+			delta += frag->size;
+		}
+
+		if (!__pskb_pull_tail(skb, delta))
+			goto drop_packet;
+
+		frag_count = 1 + skb_shinfo(skb)->nr_frags;
+	}
 	/* 4 fragments per cmd des */
 	no_of_desc = (frag_count + 3) >> 2;
 
diff --git a/drivers/net/qlcnic/qlcnic.h b/drivers/net/qlcnic/qlcnic.h
index dc44564..b0dead0 100644
--- a/drivers/net/qlcnic/qlcnic.h
+++ b/drivers/net/qlcnic/qlcnic.h
@@ -99,6 +99,7 @@
 #define TX_UDPV6_PKT	0x0c
 
 /* Tx defines */
+#define QLCNIC_MAX_FRAGS_PER_TX	14
 #define MAX_TSO_HEADER_DESC	2
 #define MGMT_CMD_DESC_RESV	4
 #define TX_STOP_THRESH		((MAX_SKB_FRAGS >> 2) + MAX_TSO_HEADER_DESC \
diff --git a/drivers/net/qlcnic/qlcnic_main.c b/drivers/net/qlcnic/qlcnic_main.c
index cd88c7e..cb1a1ef 100644
--- a/drivers/net/qlcnic/qlcnic_main.c
+++ b/drivers/net/qlcnic/qlcnic_main.c
@@ -2099,6 +2099,7 @@
 	struct cmd_desc_type0 *hwdesc, *first_desc;
 	struct pci_dev *pdev;
 	struct ethhdr *phdr;
+	int delta = 0;
 	int i, k;
 
 	u32 producer;
@@ -2118,6 +2119,19 @@
 	}
 
 	frag_count = skb_shinfo(skb)->nr_frags + 1;
+	/* 14 frags supported for normal packet and
+	 * 32 frags supported for TSO packet
+	 */
+	if (!skb_is_gso(skb) && frag_count > QLCNIC_MAX_FRAGS_PER_TX) {
+
+		for (i = 0; i < (frag_count - QLCNIC_MAX_FRAGS_PER_TX); i++)
+			delta += skb_shinfo(skb)->frags[i].size;
+
+		if (!__pskb_pull_tail(skb, delta))
+			goto drop_packet;
+
+		frag_count = 1 + skb_shinfo(skb)->nr_frags;
+	}
 
 	/* 4 fragments per cmd des */
 	no_of_desc = (frag_count + 3) >> 2;
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index d890679..a3c2aab 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -328,7 +328,8 @@
  * processing to finish, then directly poll (and ack ) the eventq.
  * Finally reenable NAPI and interrupts.
  *
- * Since we are touching interrupts the caller should hold the suspend lock
+ * This is for use only during a loopback self-test.  It must not
+ * deliver any packets up the stack as this can result in deadlock.
  */
 void efx_process_channel_now(struct efx_channel *channel)
 {
@@ -336,6 +337,7 @@
 
 	BUG_ON(channel->channel >= efx->n_channels);
 	BUG_ON(!channel->enabled);
+	BUG_ON(!efx->loopback_selftest);
 
 	/* Disable interrupts and wait for ISRs to complete */
 	efx_nic_disable_interrupts(efx);
@@ -1436,7 +1438,7 @@
 	 * restart the transmit interface early so the watchdog timer stops */
 	efx_start_port(efx);
 
-	if (efx_dev_registered(efx))
+	if (efx_dev_registered(efx) && !efx->port_inhibited)
 		netif_tx_wake_all_queues(efx->net_dev);
 
 	efx_for_each_channel(channel, efx)
diff --git a/drivers/net/sfc/io.h b/drivers/net/sfc/io.h
index d9d8c2e..cc97880 100644
--- a/drivers/net/sfc/io.h
+++ b/drivers/net/sfc/io.h
@@ -152,6 +152,7 @@
 
 	spin_lock_irqsave(&efx->biu_lock, flags);
 	value->u32[0] = _efx_readd(efx, reg + 0);
+	rmb();
 	value->u32[1] = _efx_readd(efx, reg + 4);
 	value->u32[2] = _efx_readd(efx, reg + 8);
 	value->u32[3] = _efx_readd(efx, reg + 12);
@@ -174,6 +175,7 @@
 	value->u64[0] = (__force __le64)__raw_readq(membase + addr);
 #else
 	value->u32[0] = (__force __le32)__raw_readl(membase + addr);
+	rmb();
 	value->u32[1] = (__force __le32)__raw_readl(membase + addr + 4);
 #endif
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h
index 9ffa9a6..191a311 100644
--- a/drivers/net/sfc/net_driver.h
+++ b/drivers/net/sfc/net_driver.h
@@ -330,7 +330,6 @@
  * @eventq_mask: Event queue pointer mask
  * @eventq_read_ptr: Event queue read pointer
  * @last_eventq_read_ptr: Last event queue read pointer value.
- * @magic_count: Event queue test event count
  * @irq_count: Number of IRQs since last adaptive moderation decision
  * @irq_mod_score: IRQ moderation score
  * @rx_alloc_level: Watermark based heuristic counter for pushing descriptors
@@ -360,7 +359,6 @@
 	unsigned int eventq_mask;
 	unsigned int eventq_read_ptr;
 	unsigned int last_eventq_read_ptr;
-	unsigned int magic_count;
 
 	unsigned int irq_count;
 	unsigned int irq_mod_score;
diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c
index e839661..10f1cb7 100644
--- a/drivers/net/sfc/nic.c
+++ b/drivers/net/sfc/nic.c
@@ -84,7 +84,8 @@
 static inline efx_qword_t *efx_event(struct efx_channel *channel,
 				     unsigned int index)
 {
-	return ((efx_qword_t *) (channel->eventq.addr)) + index;
+	return ((efx_qword_t *) (channel->eventq.addr)) +
+		(index & channel->eventq_mask);
 }
 
 /* See if an event is present
@@ -673,7 +674,8 @@
 	efx_dword_t reg;
 	struct efx_nic *efx = channel->efx;
 
-	EFX_POPULATE_DWORD_1(reg, FRF_AZ_EVQ_RPTR, channel->eventq_read_ptr);
+	EFX_POPULATE_DWORD_1(reg, FRF_AZ_EVQ_RPTR,
+			     channel->eventq_read_ptr & channel->eventq_mask);
 	efx_writed_table(efx, &reg, efx->type->evq_rptr_tbl_base,
 			 channel->channel);
 }
@@ -908,7 +910,7 @@
 
 	code = EFX_QWORD_FIELD(*event, FSF_AZ_DRV_GEN_EV_MAGIC);
 	if (code == EFX_CHANNEL_MAGIC_TEST(channel))
-		++channel->magic_count;
+		; /* ignore */
 	else if (code == EFX_CHANNEL_MAGIC_FILL(channel))
 		/* The queue must be empty, so we won't receive any rx
 		 * events, so efx_process_channel() won't refill the
@@ -1015,8 +1017,7 @@
 		/* Clear this event by marking it all ones */
 		EFX_SET_QWORD(*p_event);
 
-		/* Increment read pointer */
-		read_ptr = (read_ptr + 1) & channel->eventq_mask;
+		++read_ptr;
 
 		ev_code = EFX_QWORD_FIELD(event, FSF_AZ_EV_CODE);
 
@@ -1060,6 +1061,13 @@
 	return spent;
 }
 
+/* Check whether an event is present in the eventq at the current
+ * read pointer.  Only useful for self-test.
+ */
+bool efx_nic_event_present(struct efx_channel *channel)
+{
+	return efx_event_present(efx_event(channel, channel->eventq_read_ptr));
+}
 
 /* Allocate buffer table entries for event queue */
 int efx_nic_probe_eventq(struct efx_channel *channel)
@@ -1165,7 +1173,7 @@
 	struct efx_tx_queue *tx_queue;
 	struct efx_rx_queue *rx_queue;
 	unsigned int read_ptr = channel->eventq_read_ptr;
-	unsigned int end_ptr = (read_ptr - 1) & channel->eventq_mask;
+	unsigned int end_ptr = read_ptr + channel->eventq_mask - 1;
 
 	do {
 		efx_qword_t *event = efx_event(channel, read_ptr);
@@ -1205,7 +1213,7 @@
 		 * it's ok to throw away every non-flush event */
 		EFX_SET_QWORD(*event);
 
-		read_ptr = (read_ptr + 1) & channel->eventq_mask;
+		++read_ptr;
 	} while (read_ptr != end_ptr);
 
 	channel->eventq_read_ptr = read_ptr;
diff --git a/drivers/net/sfc/nic.h b/drivers/net/sfc/nic.h
index d9de1b6..a42db6e 100644
--- a/drivers/net/sfc/nic.h
+++ b/drivers/net/sfc/nic.h
@@ -184,6 +184,7 @@
 extern void efx_nic_remove_eventq(struct efx_channel *channel);
 extern int efx_nic_process_eventq(struct efx_channel *channel, int rx_quota);
 extern void efx_nic_eventq_read_ack(struct efx_channel *channel);
+extern bool efx_nic_event_present(struct efx_channel *channel);
 
 /* MAC/PHY */
 extern void falcon_drain_tx_fifo(struct efx_nic *efx);
diff --git a/drivers/net/sfc/selftest.c b/drivers/net/sfc/selftest.c
index a0f49b3..50ad3bc 100644
--- a/drivers/net/sfc/selftest.c
+++ b/drivers/net/sfc/selftest.c
@@ -131,8 +131,6 @@
 static int efx_test_interrupts(struct efx_nic *efx,
 			       struct efx_self_tests *tests)
 {
-	struct efx_channel *channel;
-
 	netif_dbg(efx, drv, efx->net_dev, "testing interrupts\n");
 	tests->interrupt = -1;
 
@@ -140,15 +138,6 @@
 	efx->last_irq_cpu = -1;
 	smp_wmb();
 
-	/* ACK each interrupting event queue. Receiving an interrupt due to
-	 * traffic before a test event is raised is considered a pass */
-	efx_for_each_channel(channel, efx) {
-		if (channel->work_pending)
-			efx_process_channel_now(channel);
-		if (efx->last_irq_cpu >= 0)
-			goto success;
-	}
-
 	efx_nic_generate_interrupt(efx);
 
 	/* Wait for arrival of test interrupt. */
@@ -173,13 +162,13 @@
 			       struct efx_self_tests *tests)
 {
 	struct efx_nic *efx = channel->efx;
-	unsigned int magic_count, count;
+	unsigned int read_ptr, count;
 
 	tests->eventq_dma[channel->channel] = -1;
 	tests->eventq_int[channel->channel] = -1;
 	tests->eventq_poll[channel->channel] = -1;
 
-	magic_count = channel->magic_count;
+	read_ptr = channel->eventq_read_ptr;
 	channel->efx->last_irq_cpu = -1;
 	smp_wmb();
 
@@ -190,10 +179,7 @@
 	do {
 		schedule_timeout_uninterruptible(HZ / 100);
 
-		if (channel->work_pending)
-			efx_process_channel_now(channel);
-
-		if (channel->magic_count != magic_count)
+		if (ACCESS_ONCE(channel->eventq_read_ptr) != read_ptr)
 			goto eventq_ok;
 	} while (++count < 2);
 
@@ -211,8 +197,7 @@
 	}
 
 	/* Check to see if event was received even if interrupt wasn't */
-	efx_process_channel_now(channel);
-	if (channel->magic_count != magic_count) {
+	if (efx_nic_event_present(channel)) {
 		netif_err(efx, drv, efx->net_dev,
 			  "channel %d event was generated, but "
 			  "failed to trigger an interrupt\n", channel->channel);
@@ -770,6 +755,8 @@
 	__efx_reconfigure_port(efx);
 	mutex_unlock(&efx->mac_lock);
 
+	netif_tx_wake_all_queues(efx->net_dev);
+
 	return rc_test;
 }
 
diff --git a/drivers/net/sfc/tx.c b/drivers/net/sfc/tx.c
index 1398019..d2c85df 100644
--- a/drivers/net/sfc/tx.c
+++ b/drivers/net/sfc/tx.c
@@ -435,7 +435,8 @@
 	 * queue state. */
 	smp_mb();
 	if (unlikely(netif_tx_queue_stopped(tx_queue->core_txq)) &&
-	    likely(efx->port_enabled)) {
+	    likely(efx->port_enabled) &&
+	    likely(!efx->port_inhibited)) {
 		fill_level = tx_queue->insert_count - tx_queue->read_count;
 		if (fill_level < EFX_TXQ_THRESHOLD(efx)) {
 			EFX_BUG_ON_PARANOID(!efx_dev_registered(efx));
diff --git a/drivers/net/sis900.c b/drivers/net/sis900.c
index cb317cd..484f795 100644
--- a/drivers/net/sis900.c
+++ b/drivers/net/sis900.c
@@ -240,7 +240,8 @@
  *	@net_dev: the net device to get address for
  *
  *	Older SiS900 and friends, use EEPROM to store MAC address.
- *	MAC address is read from read_eeprom() into @net_dev->dev_addr.
+ *	MAC address is read from read_eeprom() into @net_dev->dev_addr and
+ *	@net_dev->perm_addr.
  */
 
 static int __devinit sis900_get_mac_addr(struct pci_dev * pci_dev, struct net_device *net_dev)
@@ -261,6 +262,9 @@
 	for (i = 0; i < 3; i++)
 	        ((u16 *)(net_dev->dev_addr))[i] = read_eeprom(ioaddr, i+EEPROMMACAddr);
 
+	/* Store MAC Address in perm_addr */
+	memcpy(net_dev->perm_addr, net_dev->dev_addr, ETH_ALEN);
+
 	return 1;
 }
 
@@ -271,7 +275,8 @@
  *
  *	SiS630E model, use APC CMOS RAM to store MAC address.
  *	APC CMOS RAM is accessed through ISA bridge.
- *	MAC address is read into @net_dev->dev_addr.
+ *	MAC address is read into @net_dev->dev_addr and
+ *	@net_dev->perm_addr.
  */
 
 static int __devinit sis630e_get_mac_addr(struct pci_dev * pci_dev,
@@ -296,6 +301,10 @@
 		outb(0x09 + i, 0x70);
 		((u8 *)(net_dev->dev_addr))[i] = inb(0x71);
 	}
+
+	/* Store MAC Address in perm_addr */
+	memcpy(net_dev->perm_addr, net_dev->dev_addr, ETH_ALEN);
+
 	pci_write_config_byte(isa_bridge, 0x48, reg & ~0x40);
 	pci_dev_put(isa_bridge);
 
@@ -310,7 +319,7 @@
  *
  *	SiS635 model, set MAC Reload Bit to load Mac address from APC
  *	to rfdr. rfdr is accessed through rfcr. MAC address is read into
- *	@net_dev->dev_addr.
+ *	@net_dev->dev_addr and @net_dev->perm_addr.
  */
 
 static int __devinit sis635_get_mac_addr(struct pci_dev * pci_dev,
@@ -334,6 +343,9 @@
 		*( ((u16 *)net_dev->dev_addr) + i) = inw(ioaddr + rfdr);
 	}
 
+	/* Store MAC Address in perm_addr */
+	memcpy(net_dev->perm_addr, net_dev->dev_addr, ETH_ALEN);
+
 	/* enable packet filtering */
 	outl(rfcrSave | RFEN, rfcr + ioaddr);
 
@@ -353,7 +365,7 @@
  *	EEDONE signal to refuse EEPROM access by LAN.
  *	The EEPROM map of SiS962 or SiS963 is different to SiS900.
  *	The signature field in SiS962 or SiS963 spec is meaningless.
- *	MAC address is read into @net_dev->dev_addr.
+ *	MAC address is read into @net_dev->dev_addr and @net_dev->perm_addr.
  */
 
 static int __devinit sis96x_get_mac_addr(struct pci_dev * pci_dev,
@@ -372,6 +384,9 @@
 			for (i = 0; i < 3; i++)
 			        ((u16 *)(net_dev->dev_addr))[i] = read_eeprom(ioaddr, i+EEPROMMACAddr);
 
+			/* Store MAC Address in perm_addr */
+			memcpy(net_dev->perm_addr, net_dev->dev_addr, ETH_ALEN);
+
 			outl(EEDONE, ee_addr);
 			return 1;
 		} else {
diff --git a/drivers/net/stmmac/dwmac_lib.c b/drivers/net/stmmac/dwmac_lib.c
index d65fab1..e250935 100644
--- a/drivers/net/stmmac/dwmac_lib.c
+++ b/drivers/net/stmmac/dwmac_lib.c
@@ -26,9 +26,9 @@
 
 #undef DWMAC_DMA_DEBUG
 #ifdef DWMAC_DMA_DEBUG
-#define DBG(fmt, args...)  printk(fmt, ## args)
+#define DWMAC_LIB_DBG(fmt, args...)  printk(fmt, ## args)
 #else
-#define DBG(fmt, args...)  do { } while (0)
+#define DWMAC_LIB_DBG(fmt, args...)  do { } while (0)
 #endif
 
 /* CSR1 enables the transmit DMA to check for new descriptor */
@@ -152,7 +152,7 @@
 	/* read the status register (CSR5) */
 	u32 intr_status = readl(ioaddr + DMA_STATUS);
 
-	DBG(INFO, "%s: [CSR5: 0x%08x]\n", __func__, intr_status);
+	DWMAC_LIB_DBG(KERN_INFO "%s: [CSR5: 0x%08x]\n", __func__, intr_status);
 #ifdef DWMAC_DMA_DEBUG
 	/* It displays the DMA process states (CSR5 register) */
 	show_tx_process_state(intr_status);
@@ -160,43 +160,43 @@
 #endif
 	/* ABNORMAL interrupts */
 	if (unlikely(intr_status & DMA_STATUS_AIS)) {
-		DBG(INFO, "CSR5[15] DMA ABNORMAL IRQ: ");
+		DWMAC_LIB_DBG(KERN_INFO "CSR5[15] DMA ABNORMAL IRQ: ");
 		if (unlikely(intr_status & DMA_STATUS_UNF)) {
-			DBG(INFO, "transmit underflow\n");
+			DWMAC_LIB_DBG(KERN_INFO "transmit underflow\n");
 			ret = tx_hard_error_bump_tc;
 			x->tx_undeflow_irq++;
 		}
 		if (unlikely(intr_status & DMA_STATUS_TJT)) {
-			DBG(INFO, "transmit jabber\n");
+			DWMAC_LIB_DBG(KERN_INFO "transmit jabber\n");
 			x->tx_jabber_irq++;
 		}
 		if (unlikely(intr_status & DMA_STATUS_OVF)) {
-			DBG(INFO, "recv overflow\n");
+			DWMAC_LIB_DBG(KERN_INFO "recv overflow\n");
 			x->rx_overflow_irq++;
 		}
 		if (unlikely(intr_status & DMA_STATUS_RU)) {
-			DBG(INFO, "receive buffer unavailable\n");
+			DWMAC_LIB_DBG(KERN_INFO "receive buffer unavailable\n");
 			x->rx_buf_unav_irq++;
 		}
 		if (unlikely(intr_status & DMA_STATUS_RPS)) {
-			DBG(INFO, "receive process stopped\n");
+			DWMAC_LIB_DBG(KERN_INFO "receive process stopped\n");
 			x->rx_process_stopped_irq++;
 		}
 		if (unlikely(intr_status & DMA_STATUS_RWT)) {
-			DBG(INFO, "receive watchdog\n");
+			DWMAC_LIB_DBG(KERN_INFO "receive watchdog\n");
 			x->rx_watchdog_irq++;
 		}
 		if (unlikely(intr_status & DMA_STATUS_ETI)) {
-			DBG(INFO, "transmit early interrupt\n");
+			DWMAC_LIB_DBG(KERN_INFO "transmit early interrupt\n");
 			x->tx_early_irq++;
 		}
 		if (unlikely(intr_status & DMA_STATUS_TPS)) {
-			DBG(INFO, "transmit process stopped\n");
+			DWMAC_LIB_DBG(KERN_INFO "transmit process stopped\n");
 			x->tx_process_stopped_irq++;
 			ret = tx_hard_error;
 		}
 		if (unlikely(intr_status & DMA_STATUS_FBI)) {
-			DBG(INFO, "fatal bus error\n");
+			DWMAC_LIB_DBG(KERN_INFO "fatal bus error\n");
 			x->fatal_bus_error_irq++;
 			ret = tx_hard_error;
 		}
@@ -215,7 +215,7 @@
 	/* Clear the interrupt by writing a logic 1 to the CSR5[15-0] */
 	writel((intr_status & 0x1ffff), ioaddr + DMA_STATUS);
 
-	DBG(INFO, "\n\n");
+	DWMAC_LIB_DBG(KERN_INFO "\n\n");
 	return ret;
 }
 
diff --git a/drivers/net/stmmac/stmmac_main.c b/drivers/net/stmmac/stmmac_main.c
index 0e5f031..cc973fc 100644
--- a/drivers/net/stmmac/stmmac_main.c
+++ b/drivers/net/stmmac/stmmac_main.c
@@ -750,7 +750,6 @@
 			priv->hw->dma->dma_mode(priv->ioaddr, tc, SF_DMA_MODE);
 			priv->xstats.threshold = tc;
 		}
-		stmmac_tx_err(priv);
 	} else if (unlikely(status == tx_hard_error))
 		stmmac_tx_err(priv);
 }
@@ -781,21 +780,6 @@
 
 	stmmac_verify_args();
 
-	ret = stmmac_init_phy(dev);
-	if (unlikely(ret)) {
-		pr_err("%s: Cannot attach to PHY (error: %d)\n", __func__, ret);
-		return ret;
-	}
-
-	/* Request the IRQ lines */
-	ret = request_irq(dev->irq, stmmac_interrupt,
-			  IRQF_SHARED, dev->name, dev);
-	if (unlikely(ret < 0)) {
-		pr_err("%s: ERROR: allocating the IRQ %d (error: %d)\n",
-		       __func__, dev->irq, ret);
-		return ret;
-	}
-
 #ifdef CONFIG_STMMAC_TIMER
 	priv->tm = kzalloc(sizeof(struct stmmac_timer *), GFP_KERNEL);
 	if (unlikely(priv->tm == NULL)) {
@@ -814,6 +798,11 @@
 	} else
 		priv->tm->enable = 1;
 #endif
+	ret = stmmac_init_phy(dev);
+	if (unlikely(ret)) {
+		pr_err("%s: Cannot attach to PHY (error: %d)\n", __func__, ret);
+		goto open_error;
+	}
 
 	/* Create and initialize the TX/RX descriptors chains. */
 	priv->dma_tx_size = STMMAC_ALIGN(dma_txsize);
@@ -822,12 +811,11 @@
 	init_dma_desc_rings(dev);
 
 	/* DMA initialization and SW reset */
-	if (unlikely(priv->hw->dma->init(priv->ioaddr, priv->plat->pbl,
-					 priv->dma_tx_phy,
-					 priv->dma_rx_phy) < 0)) {
-
+	ret = priv->hw->dma->init(priv->ioaddr, priv->plat->pbl,
+				  priv->dma_tx_phy, priv->dma_rx_phy);
+	if (ret < 0) {
 		pr_err("%s: DMA initialization failed\n", __func__);
-		return -1;
+		goto open_error;
 	}
 
 	/* Copy the MAC addr into the HW  */
@@ -848,6 +836,15 @@
 	writel(0xffffffff, priv->ioaddr + MMC_HIGH_INTR_MASK);
 	writel(0xffffffff, priv->ioaddr + MMC_LOW_INTR_MASK);
 
+	/* Request the IRQ lines */
+	ret = request_irq(dev->irq, stmmac_interrupt,
+			 IRQF_SHARED, dev->name, dev);
+	if (unlikely(ret < 0)) {
+		pr_err("%s: ERROR: allocating the IRQ %d (error: %d)\n",
+		       __func__, dev->irq, ret);
+		goto open_error;
+	}
+
 	/* Enable the MAC Rx/Tx */
 	stmmac_enable_mac(priv->ioaddr);
 
@@ -878,7 +875,17 @@
 	napi_enable(&priv->napi);
 	skb_queue_head_init(&priv->rx_recycle);
 	netif_start_queue(dev);
+
 	return 0;
+
+open_error:
+#ifdef CONFIG_STMMAC_TIMER
+	kfree(priv->tm);
+#endif
+	if (priv->phydev)
+		phy_disconnect(priv->phydev);
+
+	return ret;
 }
 
 /**
diff --git a/drivers/net/tokenring/3c359.c b/drivers/net/tokenring/3c359.c
index 8a3b191..ff32bef 100644
--- a/drivers/net/tokenring/3c359.c
+++ b/drivers/net/tokenring/3c359.c
@@ -1251,7 +1251,7 @@
 /* 
  * The NIC has told us that a packet has been downloaded onto the card, we must
  * find out which packet it has done, clear the skb and information for the packet
- * then advance around the ring for all tranmitted packets
+ * then advance around the ring for all transmitted packets
  */
 
 static void xl_dn_comp(struct net_device *dev) 
@@ -1568,7 +1568,7 @@
 			if (lan_status_diff & LSC_SOFT_ERR)
 					printk(KERN_WARNING "%s: Adapter transmitted Soft Error Report Mac Frame\n",dev->name);
 			if (lan_status_diff & LSC_TRAN_BCN) 
-					printk(KERN_INFO "%s: We are tranmitting the beacon, aaah\n",dev->name);
+					printk(KERN_INFO "%s: We are transmitting the beacon, aaah\n",dev->name);
 			if (lan_status_diff & LSC_SS) 
 					printk(KERN_INFO "%s: Single Station on the ring\n", dev->name);
 			if (lan_status_diff & LSC_RING_REC)
diff --git a/drivers/net/tokenring/lanstreamer.c b/drivers/net/tokenring/lanstreamer.c
index 5bd1407..9354ca9 100644
--- a/drivers/net/tokenring/lanstreamer.c
+++ b/drivers/net/tokenring/lanstreamer.c
@@ -1675,7 +1675,7 @@
 			if (lan_status_diff & LSC_SOFT_ERR)
 				printk(KERN_WARNING "%s: Adapter transmitted Soft Error Report Mac Frame\n", dev->name);
 			if (lan_status_diff & LSC_TRAN_BCN)
-				printk(KERN_INFO "%s: We are tranmitting the beacon, aaah\n", dev->name);
+				printk(KERN_INFO "%s: We are transmitting the beacon, aaah\n", dev->name);
 			if (lan_status_diff & LSC_SS)
 				printk(KERN_INFO "%s: Single Station on the ring\n", dev->name);
 			if (lan_status_diff & LSC_RING_REC)
diff --git a/drivers/net/tokenring/olympic.c b/drivers/net/tokenring/olympic.c
index 3d2fbe6..2684003 100644
--- a/drivers/net/tokenring/olympic.c
+++ b/drivers/net/tokenring/olympic.c
@@ -1500,7 +1500,7 @@
 			if (lan_status_diff & LSC_SOFT_ERR)
 					printk(KERN_WARNING "%s: Adapter transmitted Soft Error Report Mac Frame\n",dev->name);
 			if (lan_status_diff & LSC_TRAN_BCN) 
-					printk(KERN_INFO "%s: We are tranmitting the beacon, aaah\n",dev->name);
+					printk(KERN_INFO "%s: We are transmitting the beacon, aaah\n",dev->name);
 			if (lan_status_diff & LSC_SS) 
 					printk(KERN_INFO "%s: Single Station on the ring\n", dev->name);
 			if (lan_status_diff & LSC_RING_REC)
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index f1b8af6..2d10239 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -1040,7 +1040,7 @@
 	}
 
 	ret = ath9k_htc_hw_init(hif_dev->htc_handle,
-				&hif_dev->udev->dev, hif_dev->device_id,
+				&interface->dev, hif_dev->device_id,
 				hif_dev->udev->product, id->driver_info);
 	if (ret) {
 		ret = -EINVAL;
@@ -1158,7 +1158,7 @@
 #endif
 
 static struct usb_driver ath9k_hif_usb_driver = {
-	.name = "ath9k_hif_usb",
+	.name = KBUILD_MODNAME,
 	.probe = ath9k_hif_usb_probe,
 	.disconnect = ath9k_hif_usb_disconnect,
 #ifdef CONFIG_PM
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 1ec9bcd..c95bc5c 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1254,15 +1254,6 @@
 	ah->txchainmask = common->tx_chainmask;
 	ah->rxchainmask = common->rx_chainmask;
 
-	if ((common->bus_ops->ath_bus_type != ATH_USB) && !ah->chip_fullsleep) {
-		ath9k_hw_abortpcurecv(ah);
-		if (!ath9k_hw_stopdmarecv(ah)) {
-			ath_dbg(common, ATH_DBG_XMIT,
-				"Failed to stop receive dma\n");
-			bChannelChange = false;
-		}
-	}
-
 	if (!ath9k_hw_setpower(ah, ATH9K_PM_AWAKE))
 		return -EIO;
 
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index 562257a..edc1cbb 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -751,28 +751,47 @@
 }
 EXPORT_SYMBOL(ath9k_hw_abortpcurecv);
 
-bool ath9k_hw_stopdmarecv(struct ath_hw *ah)
+bool ath9k_hw_stopdmarecv(struct ath_hw *ah, bool *reset)
 {
 #define AH_RX_STOP_DMA_TIMEOUT 10000   /* usec */
 #define AH_RX_TIME_QUANTUM     100     /* usec */
 	struct ath_common *common = ath9k_hw_common(ah);
+	u32 mac_status, last_mac_status = 0;
 	int i;
 
+	/* Enable access to the DMA observation bus */
+	REG_WRITE(ah, AR_MACMISC,
+		  ((AR_MACMISC_DMA_OBS_LINE_8 << AR_MACMISC_DMA_OBS_S) |
+		   (AR_MACMISC_MISC_OBS_BUS_1 <<
+		    AR_MACMISC_MISC_OBS_BUS_MSB_S)));
+
 	REG_WRITE(ah, AR_CR, AR_CR_RXD);
 
 	/* Wait for rx enable bit to go low */
 	for (i = AH_RX_STOP_DMA_TIMEOUT / AH_TIME_QUANTUM; i != 0; i--) {
 		if ((REG_READ(ah, AR_CR) & AR_CR_RXE) == 0)
 			break;
+
+		if (!AR_SREV_9300_20_OR_LATER(ah)) {
+			mac_status = REG_READ(ah, AR_DMADBG_7) & 0x7f0;
+			if (mac_status == 0x1c0 && mac_status == last_mac_status) {
+				*reset = true;
+				break;
+			}
+
+			last_mac_status = mac_status;
+		}
+
 		udelay(AH_TIME_QUANTUM);
 	}
 
 	if (i == 0) {
 		ath_err(common,
-			"DMA failed to stop in %d ms AR_CR=0x%08x AR_DIAG_SW=0x%08x\n",
+			"DMA failed to stop in %d ms AR_CR=0x%08x AR_DIAG_SW=0x%08x DMADBG_7=0x%08x\n",
 			AH_RX_STOP_DMA_TIMEOUT / 1000,
 			REG_READ(ah, AR_CR),
-			REG_READ(ah, AR_DIAG_SW));
+			REG_READ(ah, AR_DIAG_SW),
+			REG_READ(ah, AR_DMADBG_7));
 		return false;
 	} else {
 		return true;
diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h
index b2b2ff8..c2a5938 100644
--- a/drivers/net/wireless/ath/ath9k/mac.h
+++ b/drivers/net/wireless/ath/ath9k/mac.h
@@ -695,7 +695,7 @@
 void ath9k_hw_putrxbuf(struct ath_hw *ah, u32 rxdp);
 void ath9k_hw_startpcureceive(struct ath_hw *ah, bool is_scanning);
 void ath9k_hw_abortpcurecv(struct ath_hw *ah);
-bool ath9k_hw_stopdmarecv(struct ath_hw *ah);
+bool ath9k_hw_stopdmarecv(struct ath_hw *ah, bool *reset);
 int ath9k_hw_beaconq_setup(struct ath_hw *ah);
 
 /* Interrupt Handling */
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index dddb85d..17d04ff 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -1376,7 +1376,6 @@
 
 	ath9k_calculate_iter_data(hw, vif, &iter_data);
 
-	ath9k_ps_wakeup(sc);
 	/* Set BSSID mask. */
 	memcpy(common->bssidmask, iter_data.mask, ETH_ALEN);
 	ath_hw_setbssidmask(common);
@@ -1411,7 +1410,6 @@
 	}
 
 	ath9k_hw_set_interrupts(ah, ah->imask);
-	ath9k_ps_restore(sc);
 
 	/* Set up ANI */
 	if ((iter_data.naps + iter_data.nadhocs) > 0) {
@@ -1457,6 +1455,7 @@
 	struct ath_vif *avp = (void *)vif->drv_priv;
 	int ret = 0;
 
+	ath9k_ps_wakeup(sc);
 	mutex_lock(&sc->mutex);
 
 	switch (vif->type) {
@@ -1503,6 +1502,7 @@
 	ath9k_do_vif_add_setup(hw, vif);
 out:
 	mutex_unlock(&sc->mutex);
+	ath9k_ps_restore(sc);
 	return ret;
 }
 
@@ -1517,6 +1517,7 @@
 
 	ath_dbg(common, ATH_DBG_CONFIG, "Change Interface\n");
 	mutex_lock(&sc->mutex);
+	ath9k_ps_wakeup(sc);
 
 	/* See if new interface type is valid. */
 	if ((new_type == NL80211_IFTYPE_ADHOC) &&
@@ -1546,6 +1547,7 @@
 
 	ath9k_do_vif_add_setup(hw, vif);
 out:
+	ath9k_ps_restore(sc);
 	mutex_unlock(&sc->mutex);
 	return ret;
 }
@@ -1558,6 +1560,7 @@
 
 	ath_dbg(common, ATH_DBG_CONFIG, "Detach Interface\n");
 
+	ath9k_ps_wakeup(sc);
 	mutex_lock(&sc->mutex);
 
 	sc->nvifs--;
@@ -1569,6 +1572,7 @@
 	ath9k_calculate_summary_state(hw, NULL);
 
 	mutex_unlock(&sc->mutex);
+	ath9k_ps_restore(sc);
 }
 
 static void ath9k_enable_ps(struct ath_softc *sc)
@@ -1809,6 +1813,7 @@
 
 	txq = sc->tx.txq_map[queue];
 
+	ath9k_ps_wakeup(sc);
 	mutex_lock(&sc->mutex);
 
 	memset(&qi, 0, sizeof(struct ath9k_tx_queue_info));
@@ -1832,6 +1837,7 @@
 			ath_beaconq_config(sc);
 
 	mutex_unlock(&sc->mutex);
+	ath9k_ps_restore(sc);
 
 	return ret;
 }
@@ -1894,6 +1900,7 @@
 	int slottime;
 	int error;
 
+	ath9k_ps_wakeup(sc);
 	mutex_lock(&sc->mutex);
 
 	if (changed & BSS_CHANGED_BSSID) {
@@ -1994,6 +2001,7 @@
 	}
 
 	mutex_unlock(&sc->mutex);
+	ath9k_ps_restore(sc);
 }
 
 static u64 ath9k_get_tsf(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index a9c3f46..dcd19bc 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -486,12 +486,12 @@
 bool ath_stoprecv(struct ath_softc *sc)
 {
 	struct ath_hw *ah = sc->sc_ah;
-	bool stopped;
+	bool stopped, reset = false;
 
 	spin_lock_bh(&sc->rx.rxbuflock);
 	ath9k_hw_abortpcurecv(ah);
 	ath9k_hw_setrxfilter(ah, 0);
-	stopped = ath9k_hw_stopdmarecv(ah);
+	stopped = ath9k_hw_stopdmarecv(ah, &reset);
 
 	if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA)
 		ath_edma_stop_recv(sc);
@@ -506,7 +506,7 @@
 			"confusing the DMA engine when we start RX up\n");
 		ATH_DBG_WARN_ON_ONCE(!stopped);
 	}
-	return stopped;
+	return stopped || reset;
 }
 
 void ath_flushrecv(struct ath_softc *sc)
diff --git a/drivers/net/wireless/ath/regd_common.h b/drivers/net/wireless/ath/regd_common.h
index 248c670..5c2cfe6 100644
--- a/drivers/net/wireless/ath/regd_common.h
+++ b/drivers/net/wireless/ath/regd_common.h
@@ -195,6 +195,7 @@
 	{APL9_WORLD, CTL_ETSI, CTL_ETSI},
 
 	{APL3_FCCA, CTL_FCC, CTL_FCC},
+	{APL7_FCCA, CTL_FCC, CTL_FCC},
 	{APL1_ETSIC, CTL_FCC, CTL_ETSI},
 	{APL2_ETSIC, CTL_FCC, CTL_ETSI},
 	{APL2_APLD, CTL_FCC, NO_CTL},
diff --git a/drivers/net/wireless/iwlegacy/Kconfig b/drivers/net/wireless/iwlegacy/Kconfig
index 2a45dd4..aef65cd 100644
--- a/drivers/net/wireless/iwlegacy/Kconfig
+++ b/drivers/net/wireless/iwlegacy/Kconfig
@@ -1,6 +1,5 @@
 config IWLWIFI_LEGACY
-	tristate "Intel Wireless Wifi legacy devices"
-	depends on PCI && MAC80211
+	tristate
 	select FW_LOADER
 	select NEW_LEDS
 	select LEDS_CLASS
@@ -65,7 +64,8 @@
 
 config IWL4965
 	tristate "Intel Wireless WiFi 4965AGN (iwl4965)"
-	depends on IWLWIFI_LEGACY
+	depends on PCI && MAC80211
+	select IWLWIFI_LEGACY
 	---help---
 	  This option enables support for
 
@@ -92,7 +92,8 @@
 
 config IWL3945
 	tristate "Intel PRO/Wireless 3945ABG/BG Network Connection (iwl3945)"
-	depends on IWLWIFI_LEGACY
+	depends on PCI && MAC80211
+	select IWLWIFI_LEGACY
 	---help---
 	  Select to build the driver supporting the:
 
diff --git a/drivers/net/wireless/iwlegacy/iwl-3945-hw.h b/drivers/net/wireless/iwlegacy/iwl-3945-hw.h
index 779d3cb..5c3a68d 100644
--- a/drivers/net/wireless/iwlegacy/iwl-3945-hw.h
+++ b/drivers/net/wireless/iwlegacy/iwl-3945-hw.h
@@ -74,8 +74,6 @@
 /* RSSI to dBm */
 #define IWL39_RSSI_OFFSET	95
 
-#define IWL_DEFAULT_TX_POWER	0x0F
-
 /*
  * EEPROM related constants, enums, and structures.
  */
diff --git a/drivers/net/wireless/iwlegacy/iwl-4965-hw.h b/drivers/net/wireless/iwlegacy/iwl-4965-hw.h
index 08b189c..fc6fa28 100644
--- a/drivers/net/wireless/iwlegacy/iwl-4965-hw.h
+++ b/drivers/net/wireless/iwlegacy/iwl-4965-hw.h
@@ -804,9 +804,6 @@
 
 #define IWL4965_DEFAULT_TX_RETRY  15
 
-/* Limit range of txpower output target to be between these values */
-#define IWL4965_TX_POWER_TARGET_POWER_MIN	(0)	/* 0 dBm: 1 milliwatt */
-
 /* EEPROM */
 #define IWL4965_FIRST_AMPDU_QUEUE	10
 
diff --git a/drivers/net/wireless/iwlegacy/iwl-core.c b/drivers/net/wireless/iwlegacy/iwl-core.c
index 7007d61..c1511b1 100644
--- a/drivers/net/wireless/iwlegacy/iwl-core.c
+++ b/drivers/net/wireless/iwlegacy/iwl-core.c
@@ -160,6 +160,7 @@
 	struct ieee80211_channel *geo_ch;
 	struct ieee80211_rate *rates;
 	int i = 0;
+	s8 max_tx_power = 0;
 
 	if (priv->bands[IEEE80211_BAND_2GHZ].n_bitrates ||
 	    priv->bands[IEEE80211_BAND_5GHZ].n_bitrates) {
@@ -235,8 +236,8 @@
 
 			geo_ch->flags |= ch->ht40_extension_channel;
 
-			if (ch->max_power_avg > priv->tx_power_device_lmt)
-				priv->tx_power_device_lmt = ch->max_power_avg;
+			if (ch->max_power_avg > max_tx_power)
+				max_tx_power = ch->max_power_avg;
 		} else {
 			geo_ch->flags |= IEEE80211_CHAN_DISABLED;
 		}
@@ -249,6 +250,10 @@
 				 geo_ch->flags);
 	}
 
+	priv->tx_power_device_lmt = max_tx_power;
+	priv->tx_power_user_lmt = max_tx_power;
+	priv->tx_power_next = max_tx_power;
+
 	if ((priv->bands[IEEE80211_BAND_5GHZ].n_channels == 0) &&
 	     priv->cfg->sku & IWL_SKU_A) {
 		IWL_INFO(priv, "Incorrectly detected BG card as ABG. "
@@ -1124,11 +1129,11 @@
 	if (!priv->cfg->ops->lib->send_tx_power)
 		return -EOPNOTSUPP;
 
-	if (tx_power < IWL4965_TX_POWER_TARGET_POWER_MIN) {
+	/* 0 dBm mean 1 milliwatt */
+	if (tx_power < 0) {
 		IWL_WARN(priv,
-			 "Requested user TXPOWER %d below lower limit %d.\n",
-			 tx_power,
-			 IWL4965_TX_POWER_TARGET_POWER_MIN);
+			 "Requested user TXPOWER %d below 1 mW.\n",
+			 tx_power);
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/wireless/iwlegacy/iwl-eeprom.c b/drivers/net/wireless/iwlegacy/iwl-eeprom.c
index 04c5648..cb346d1 100644
--- a/drivers/net/wireless/iwlegacy/iwl-eeprom.c
+++ b/drivers/net/wireless/iwlegacy/iwl-eeprom.c
@@ -471,13 +471,6 @@
 					     flags & EEPROM_CHANNEL_RADAR))
 				       ? "" : "not ");
 
-			/* Set the tx_power_user_lmt to the highest power
-			 * supported by any channel */
-			if (eeprom_ch_info[ch].max_power_avg >
-						priv->tx_power_user_lmt)
-				priv->tx_power_user_lmt =
-				    eeprom_ch_info[ch].max_power_avg;
-
 			ch_info++;
 		}
 	}
diff --git a/drivers/net/wireless/iwlegacy/iwl3945-base.c b/drivers/net/wireless/iwlegacy/iwl3945-base.c
index 28eb3d8..cc7ebce 100644
--- a/drivers/net/wireless/iwlegacy/iwl3945-base.c
+++ b/drivers/net/wireless/iwlegacy/iwl3945-base.c
@@ -3825,10 +3825,6 @@
 	priv->force_reset[IWL_FW_RESET].reset_duration =
 		IWL_DELAY_NEXT_FORCE_FW_RELOAD;
 
-
-	priv->tx_power_user_lmt = IWL_DEFAULT_TX_POWER;
-	priv->tx_power_next = IWL_DEFAULT_TX_POWER;
-
 	if (eeprom->version < EEPROM_3945_EEPROM_VERSION) {
 		IWL_WARN(priv, "Unsupported EEPROM version: 0x%04X\n",
 			 eeprom->version);
diff --git a/drivers/net/wireless/iwlegacy/iwl4965-base.c b/drivers/net/wireless/iwlegacy/iwl4965-base.c
index 91b3d8b..d484c36 100644
--- a/drivers/net/wireless/iwlegacy/iwl4965-base.c
+++ b/drivers/net/wireless/iwlegacy/iwl4965-base.c
@@ -3140,12 +3140,6 @@
 
 	iwl_legacy_init_scan_params(priv);
 
-	/* Set the tx_power_user_lmt to the lowest power level
-	 * this value will get overwritten by channel max power avg
-	 * from eeprom */
-	priv->tx_power_user_lmt = IWL4965_TX_POWER_TARGET_POWER_MIN;
-	priv->tx_power_next = IWL4965_TX_POWER_TARGET_POWER_MIN;
-
 	ret = iwl_legacy_init_channel_map(priv);
 	if (ret) {
 		IWL_ERR(priv, "initializing regulatory failed: %d\n", ret);
diff --git a/drivers/net/wireless/iwlwifi/iwl-5000.c b/drivers/net/wireless/iwlwifi/iwl-5000.c
index 3ea31b6..22e045b 100644
--- a/drivers/net/wireless/iwlwifi/iwl-5000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-5000.c
@@ -530,6 +530,9 @@
 struct iwl_cfg iwl5300_agn_cfg = {
 	.name = "Intel(R) Ultimate N WiFi Link 5300 AGN",
 	IWL_DEVICE_5000,
+	/* at least EEPROM 0x11A has wrong info */
+	.valid_tx_ant = ANT_ABC,	/* .cfg overwrite */
+	.valid_rx_ant = ANT_ABC,	/* .cfg overwrite */
 	.ht_params = &iwl5000_ht_params,
 };
 
diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c
index 3695227..c1ceb4b 100644
--- a/drivers/net/wireless/mwl8k.c
+++ b/drivers/net/wireless/mwl8k.c
@@ -137,6 +137,7 @@
 struct mwl8k_priv {
 	struct ieee80211_hw *hw;
 	struct pci_dev *pdev;
+	int irq;
 
 	struct mwl8k_device_info *device_info;
 
@@ -3761,9 +3762,11 @@
 	rc = request_irq(priv->pdev->irq, mwl8k_interrupt,
 			 IRQF_SHARED, MWL8K_NAME, hw);
 	if (rc) {
+		priv->irq = -1;
 		wiphy_err(hw->wiphy, "failed to register IRQ handler\n");
 		return -EIO;
 	}
+	priv->irq = priv->pdev->irq;
 
 	/* Enable TX reclaim and RX tasklets.  */
 	tasklet_enable(&priv->poll_tx_task);
@@ -3800,6 +3803,7 @@
 	if (rc) {
 		iowrite32(0, priv->regs + MWL8K_HIU_A2H_INTERRUPT_MASK);
 		free_irq(priv->pdev->irq, hw);
+		priv->irq = -1;
 		tasklet_disable(&priv->poll_tx_task);
 		tasklet_disable(&priv->poll_rx_task);
 	}
@@ -3818,7 +3822,10 @@
 
 	/* Disable interrupts */
 	iowrite32(0, priv->regs + MWL8K_HIU_A2H_INTERRUPT_MASK);
-	free_irq(priv->pdev->irq, hw);
+	if (priv->irq != -1) {
+		free_irq(priv->pdev->irq, hw);
+		priv->irq = -1;
+	}
 
 	/* Stop finalize join worker */
 	cancel_work_sync(&priv->finalize_join_worker);
diff --git a/drivers/net/wireless/p54/txrx.c b/drivers/net/wireless/p54/txrx.c
index 7834c26..042842e 100644
--- a/drivers/net/wireless/p54/txrx.c
+++ b/drivers/net/wireless/p54/txrx.c
@@ -703,7 +703,7 @@
 	struct p54_tx_info *p54info;
 	struct p54_hdr *hdr;
 	struct p54_tx_data *txhdr;
-	unsigned int padding, len, extra_len;
+	unsigned int padding, len, extra_len = 0;
 	int i, j, ridx;
 	u16 hdr_flags = 0, aid = 0;
 	u8 rate, queue = 0, crypt_offset = 0;
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index c8ff646..0fa466a 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -88,4 +88,6 @@
 	depends on HOTPLUG
 	default y
 
-select NLS if (DMI || ACPI)
+config PCI_LABEL
+	def_bool y if (DMI || ACPI)
+	select NLS
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 98d61c8..c85f744 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -56,10 +56,10 @@
 # ACPI Related PCI FW Functions
 # ACPI _DSM provided firmware instance and string name
 #
-obj-$(CONFIG_ACPI)    += pci-acpi.o pci-label.o
+obj-$(CONFIG_ACPI)    += pci-acpi.o
 
 # SMBIOS provided firmware instance and labels
-obj-$(CONFIG_DMI)    += pci-label.o
+obj-$(CONFIG_PCI_LABEL) += pci-label.o
 
 # Cardbus & CompactPCI use setup-bus
 obj-$(CONFIG_HOTPLUG) += setup-bus.o
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index de0dd7b..bcae8dd 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -394,7 +394,7 @@
 	return 0;
 
 fail2:
-	free_irq(omap_rtc_timer, NULL);
+	free_irq(omap_rtc_timer, rtc);
 fail1:
 	rtc_device_unregister(rtc);
 fail0:
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index de34bfa..5d505aa 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -178,16 +178,17 @@
 
 	if (value) {
 		acl = posix_acl_from_xattr(value, size);
-		if (acl == NULL) {
-			value = NULL;
-			size = 0;
+		if (acl) {
+			ret = posix_acl_valid(acl);
+			if (ret)
+				goto out;
 		} else if (IS_ERR(acl)) {
 			return PTR_ERR(acl);
 		}
 	}
 
 	ret = btrfs_set_acl(NULL, dentry->d_inode, acl, type);
-
+out:
 	posix_acl_release(acl);
 
 	return ret;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 3458b57..2e61fe1 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -740,8 +740,10 @@
 	 */
 	unsigned long reservation_progress;
 
-	int full;		/* indicates that we cannot allocate any more
+	int full:1;		/* indicates that we cannot allocate any more
 				   chunks for this space */
+	int chunk_alloc:1;	/* set if we are allocating a chunk */
+
 	int force_alloc;	/* set if we need to force a chunk alloc for
 				   this space */
 
@@ -2576,6 +2578,11 @@
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 			      struct inode *inode, u64 start, u64 end);
 int btrfs_release_file(struct inode *inode, struct file *file);
+void btrfs_drop_pages(struct page **pages, size_t num_pages);
+int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
+		      struct page **pages, size_t num_pages,
+		      loff_t pos, size_t write_bytes,
+		      struct extent_state **cached);
 
 /* tree-defrag.c */
 int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8f1d44b..68c84c8 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3057,7 +3057,7 @@
 		btrfs_destroy_pinned_extent(root,
 					    root->fs_info->pinned_extents);
 
-		t->use_count = 0;
+		atomic_set(&t->use_count, 0);
 		list_del_init(&t->list);
 		memset(t, 0, sizeof(*t));
 		kmem_cache_free(btrfs_transaction_cachep, t);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f619c3c..31f33ba 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -33,6 +33,25 @@
 #include "locking.h"
 #include "free-space-cache.h"
 
+/* control flags for do_chunk_alloc's force field
+ * CHUNK_ALLOC_NO_FORCE means to only allocate a chunk
+ * if we really need one.
+ *
+ * CHUNK_ALLOC_FORCE means it must try to allocate one
+ *
+ * CHUNK_ALLOC_LIMITED means to only try and allocate one
+ * if we have very few chunks already allocated.  This is
+ * used as part of the clustering code to help make sure
+ * we have a good pool of storage to cluster in, without
+ * filling the FS with empty chunks
+ *
+ */
+enum {
+	CHUNK_ALLOC_NO_FORCE = 0,
+	CHUNK_ALLOC_FORCE = 1,
+	CHUNK_ALLOC_LIMITED = 2,
+};
+
 static int update_block_group(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      u64 bytenr, u64 num_bytes, int alloc);
@@ -3019,7 +3038,8 @@
 	found->bytes_readonly = 0;
 	found->bytes_may_use = 0;
 	found->full = 0;
-	found->force_alloc = 0;
+	found->force_alloc = CHUNK_ALLOC_NO_FORCE;
+	found->chunk_alloc = 0;
 	*space_info = found;
 	list_add_rcu(&found->list, &info->space_info);
 	atomic_set(&found->caching_threads, 0);
@@ -3150,7 +3170,7 @@
 		if (!data_sinfo->full && alloc_chunk) {
 			u64 alloc_target;
 
-			data_sinfo->force_alloc = 1;
+			data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
 			spin_unlock(&data_sinfo->lock);
 alloc:
 			alloc_target = btrfs_get_alloc_profile(root, 1);
@@ -3160,7 +3180,8 @@
 
 			ret = do_chunk_alloc(trans, root->fs_info->extent_root,
 					     bytes + 2 * 1024 * 1024,
-					     alloc_target, 0);
+					     alloc_target,
+					     CHUNK_ALLOC_NO_FORCE);
 			btrfs_end_transaction(trans, root);
 			if (ret < 0) {
 				if (ret != -ENOSPC)
@@ -3239,31 +3260,56 @@
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
 		if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
-			found->force_alloc = 1;
+			found->force_alloc = CHUNK_ALLOC_FORCE;
 	}
 	rcu_read_unlock();
 }
 
 static int should_alloc_chunk(struct btrfs_root *root,
-			      struct btrfs_space_info *sinfo, u64 alloc_bytes)
+			      struct btrfs_space_info *sinfo, u64 alloc_bytes,
+			      int force)
 {
 	u64 num_bytes = sinfo->total_bytes - sinfo->bytes_readonly;
+	u64 num_allocated = sinfo->bytes_used + sinfo->bytes_reserved;
 	u64 thresh;
 
-	if (sinfo->bytes_used + sinfo->bytes_reserved +
-	    alloc_bytes + 256 * 1024 * 1024 < num_bytes)
+	if (force == CHUNK_ALLOC_FORCE)
+		return 1;
+
+	/*
+	 * in limited mode, we want to have some free space up to
+	 * about 1% of the FS size.
+	 */
+	if (force == CHUNK_ALLOC_LIMITED) {
+		thresh = btrfs_super_total_bytes(&root->fs_info->super_copy);
+		thresh = max_t(u64, 64 * 1024 * 1024,
+			       div_factor_fine(thresh, 1));
+
+		if (num_bytes - num_allocated < thresh)
+			return 1;
+	}
+
+	/*
+	 * we have two similar checks here, one based on percentage
+	 * and once based on a hard number of 256MB.  The idea
+	 * is that if we have a good amount of free
+	 * room, don't allocate a chunk.  A good mount is
+	 * less than 80% utilized of the chunks we have allocated,
+	 * or more than 256MB free
+	 */
+	if (num_allocated + alloc_bytes + 256 * 1024 * 1024 < num_bytes)
 		return 0;
 
-	if (sinfo->bytes_used + sinfo->bytes_reserved +
-	    alloc_bytes < div_factor(num_bytes, 8))
+	if (num_allocated + alloc_bytes < div_factor(num_bytes, 8))
 		return 0;
 
 	thresh = btrfs_super_total_bytes(&root->fs_info->super_copy);
+
+	/* 256MB or 5% of the FS */
 	thresh = max_t(u64, 256 * 1024 * 1024, div_factor_fine(thresh, 5));
 
 	if (num_bytes > thresh && sinfo->bytes_used < div_factor(num_bytes, 3))
 		return 0;
-
 	return 1;
 }
 
@@ -3273,10 +3319,9 @@
 {
 	struct btrfs_space_info *space_info;
 	struct btrfs_fs_info *fs_info = extent_root->fs_info;
+	int wait_for_alloc = 0;
 	int ret = 0;
 
-	mutex_lock(&fs_info->chunk_mutex);
-
 	flags = btrfs_reduce_alloc_profile(extent_root, flags);
 
 	space_info = __find_space_info(extent_root->fs_info, flags);
@@ -3287,21 +3332,40 @@
 	}
 	BUG_ON(!space_info);
 
+again:
 	spin_lock(&space_info->lock);
 	if (space_info->force_alloc)
-		force = 1;
+		force = space_info->force_alloc;
 	if (space_info->full) {
 		spin_unlock(&space_info->lock);
-		goto out;
+		return 0;
 	}
 
-	if (!force && !should_alloc_chunk(extent_root, space_info,
-					  alloc_bytes)) {
+	if (!should_alloc_chunk(extent_root, space_info, alloc_bytes, force)) {
 		spin_unlock(&space_info->lock);
-		goto out;
+		return 0;
+	} else if (space_info->chunk_alloc) {
+		wait_for_alloc = 1;
+	} else {
+		space_info->chunk_alloc = 1;
 	}
+
 	spin_unlock(&space_info->lock);
 
+	mutex_lock(&fs_info->chunk_mutex);
+
+	/*
+	 * The chunk_mutex is held throughout the entirety of a chunk
+	 * allocation, so once we've acquired the chunk_mutex we know that the
+	 * other guy is done and we need to recheck and see if we should
+	 * allocate.
+	 */
+	if (wait_for_alloc) {
+		mutex_unlock(&fs_info->chunk_mutex);
+		wait_for_alloc = 0;
+		goto again;
+	}
+
 	/*
 	 * If we have mixed data/metadata chunks we want to make sure we keep
 	 * allocating mixed chunks instead of individual chunks.
@@ -3327,9 +3391,10 @@
 		space_info->full = 1;
 	else
 		ret = 1;
-	space_info->force_alloc = 0;
+
+	space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
+	space_info->chunk_alloc = 0;
 	spin_unlock(&space_info->lock);
-out:
 	mutex_unlock(&extent_root->fs_info->chunk_mutex);
 	return ret;
 }
@@ -5303,11 +5368,13 @@
 
 		if (allowed_chunk_alloc) {
 			ret = do_chunk_alloc(trans, root, num_bytes +
-					     2 * 1024 * 1024, data, 1);
+					     2 * 1024 * 1024, data,
+					     CHUNK_ALLOC_LIMITED);
 			allowed_chunk_alloc = 0;
 			done_chunk_alloc = 1;
-		} else if (!done_chunk_alloc) {
-			space_info->force_alloc = 1;
+		} else if (!done_chunk_alloc &&
+			   space_info->force_alloc == CHUNK_ALLOC_NO_FORCE) {
+			space_info->force_alloc = CHUNK_ALLOC_LIMITED;
 		}
 
 		if (loop < LOOP_NO_EMPTY_SIZE) {
@@ -5393,7 +5460,8 @@
 	 */
 	if (empty_size || root->ref_cows)
 		ret = do_chunk_alloc(trans, root->fs_info->extent_root,
-				     num_bytes + 2 * 1024 * 1024, data, 0);
+				     num_bytes + 2 * 1024 * 1024, data,
+				     CHUNK_ALLOC_NO_FORCE);
 
 	WARN_ON(num_bytes < root->sectorsize);
 	ret = find_free_extent(trans, root, num_bytes, empty_size,
@@ -5405,7 +5473,7 @@
 		num_bytes = num_bytes & ~(root->sectorsize - 1);
 		num_bytes = max(num_bytes, min_alloc_size);
 		do_chunk_alloc(trans, root->fs_info->extent_root,
-			       num_bytes, data, 1);
+			       num_bytes, data, CHUNK_ALLOC_FORCE);
 		goto again;
 	}
 	if (ret == -ENOSPC && btrfs_test_opt(root, ENOSPC_DEBUG)) {
@@ -8109,13 +8177,15 @@
 
 	alloc_flags = update_block_group_flags(root, cache->flags);
 	if (alloc_flags != cache->flags)
-		do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+		do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+			       CHUNK_ALLOC_FORCE);
 
 	ret = set_block_group_ro(cache);
 	if (!ret)
 		goto out;
 	alloc_flags = get_alloc_profile(root, cache->space_info->flags);
-	ret = do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+	ret = do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+			     CHUNK_ALLOC_FORCE);
 	if (ret < 0)
 		goto out;
 	ret = set_block_group_ro(cache);
@@ -8128,7 +8198,8 @@
 			    struct btrfs_root *root, u64 type)
 {
 	u64 alloc_flags = get_alloc_profile(root, type);
-	return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+	return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+			      CHUNK_ALLOC_FORCE);
 }
 
 /*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 20ddb28..3151386 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -690,6 +690,15 @@
 	}
 }
 
+static void uncache_state(struct extent_state **cached_ptr)
+{
+	if (cached_ptr && (*cached_ptr)) {
+		struct extent_state *state = *cached_ptr;
+		*cached_ptr = NULL;
+		free_extent_state(state);
+	}
+}
+
 /*
  * set some bits on a range in the tree.  This may require allocations or
  * sleeping, so the gfp mask is used to indicate what is allowed.
@@ -940,10 +949,10 @@
 }
 
 int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			gfp_t mask)
+			struct extent_state **cached_state, gfp_t mask)
 {
-	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, NULL,
-			      NULL, mask);
+	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0,
+			      NULL, cached_state, mask);
 }
 
 static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
@@ -1012,8 +1021,7 @@
 				mask);
 }
 
-int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end,
-		  gfp_t mask)
+int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask)
 {
 	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL,
 				mask);
@@ -1735,6 +1743,9 @@
 
 	do {
 		struct page *page = bvec->bv_page;
+		struct extent_state *cached = NULL;
+		struct extent_state *state;
+
 		tree = &BTRFS_I(page->mapping->host)->io_tree;
 
 		start = ((u64)page->index << PAGE_CACHE_SHIFT) +
@@ -1749,9 +1760,20 @@
 		if (++bvec <= bvec_end)
 			prefetchw(&bvec->bv_page->flags);
 
+		spin_lock(&tree->lock);
+		state = find_first_extent_bit_state(tree, start, EXTENT_LOCKED);
+		if (state && state->start == start) {
+			/*
+			 * take a reference on the state, unlock will drop
+			 * the ref
+			 */
+			cache_state(state, &cached);
+		}
+		spin_unlock(&tree->lock);
+
 		if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) {
 			ret = tree->ops->readpage_end_io_hook(page, start, end,
-							      NULL);
+							      state);
 			if (ret)
 				uptodate = 0;
 		}
@@ -1764,15 +1786,16 @@
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
 					uptodate = 0;
+				uncache_state(&cached);
 				continue;
 			}
 		}
 
 		if (uptodate) {
-			set_extent_uptodate(tree, start, end,
+			set_extent_uptodate(tree, start, end, &cached,
 					    GFP_ATOMIC);
 		}
-		unlock_extent(tree, start, end, GFP_ATOMIC);
+		unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
 
 		if (whole_page) {
 			if (uptodate) {
@@ -1811,6 +1834,7 @@
 
 	do {
 		struct page *page = bvec->bv_page;
+		struct extent_state *cached = NULL;
 		tree = &BTRFS_I(page->mapping->host)->io_tree;
 
 		start = ((u64)page->index << PAGE_CACHE_SHIFT) +
@@ -1821,13 +1845,14 @@
 			prefetchw(&bvec->bv_page->flags);
 
 		if (uptodate) {
-			set_extent_uptodate(tree, start, end, GFP_ATOMIC);
+			set_extent_uptodate(tree, start, end, &cached,
+					    GFP_ATOMIC);
 		} else {
 			ClearPageUptodate(page);
 			SetPageError(page);
 		}
 
-		unlock_extent(tree, start, end, GFP_ATOMIC);
+		unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
 
 	} while (bvec >= bio->bi_io_vec);
 
@@ -2016,14 +2041,17 @@
 	while (cur <= end) {
 		if (cur >= last_byte) {
 			char *userpage;
+			struct extent_state *cached = NULL;
+
 			iosize = PAGE_CACHE_SIZE - page_offset;
 			userpage = kmap_atomic(page, KM_USER0);
 			memset(userpage + page_offset, 0, iosize);
 			flush_dcache_page(page);
 			kunmap_atomic(userpage, KM_USER0);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
-					    GFP_NOFS);
-			unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS);
+					    &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur, cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			break;
 		}
 		em = get_extent(inode, page, page_offset, cur,
@@ -2063,14 +2091,17 @@
 		/* we've found a hole, just zero and go on */
 		if (block_start == EXTENT_MAP_HOLE) {
 			char *userpage;
+			struct extent_state *cached = NULL;
+
 			userpage = kmap_atomic(page, KM_USER0);
 			memset(userpage + page_offset, 0, iosize);
 			flush_dcache_page(page);
 			kunmap_atomic(userpage, KM_USER0);
 
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
-					    GFP_NOFS);
-			unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS);
+					    &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur, cur + iosize - 1,
+			                     &cached, GFP_NOFS);
 			cur = cur + iosize;
 			page_offset += iosize;
 			continue;
@@ -2789,9 +2820,12 @@
 			iocount++;
 			block_start = block_start + iosize;
 		} else {
-			set_extent_uptodate(tree, block_start, cur_end,
+			struct extent_state *cached = NULL;
+
+			set_extent_uptodate(tree, block_start, cur_end, &cached,
 					    GFP_NOFS);
-			unlock_extent(tree, block_start, cur_end, GFP_NOFS);
+			unlock_extent_cached(tree, block_start, cur_end,
+					     &cached, GFP_NOFS);
 			block_start = cur_end + 1;
 		}
 		page_offset = block_start & (PAGE_CACHE_SIZE - 1);
@@ -3457,7 +3491,7 @@
 	num_pages = num_extent_pages(eb->start, eb->len);
 
 	set_extent_uptodate(tree, eb->start, eb->start + eb->len - 1,
-			    GFP_NOFS);
+			    NULL, GFP_NOFS);
 	for (i = 0; i < num_pages; i++) {
 		page = extent_buffer_page(eb, i);
 		if ((i == 0 && (eb->start & (PAGE_CACHE_SIZE - 1))) ||
@@ -3885,6 +3919,12 @@
 	kunmap_atomic(dst_kaddr, KM_USER0);
 }
 
+static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned long len)
+{
+	unsigned long distance = (src > dst) ? src - dst : dst - src;
+	return distance < len;
+}
+
 static void copy_pages(struct page *dst_page, struct page *src_page,
 		       unsigned long dst_off, unsigned long src_off,
 		       unsigned long len)
@@ -3892,10 +3932,12 @@
 	char *dst_kaddr = kmap_atomic(dst_page, KM_USER0);
 	char *src_kaddr;
 
-	if (dst_page != src_page)
+	if (dst_page != src_page) {
 		src_kaddr = kmap_atomic(src_page, KM_USER1);
-	else
+	} else {
 		src_kaddr = dst_kaddr;
+		BUG_ON(areas_overlap(src_off, dst_off, len));
+	}
 
 	memcpy(dst_kaddr + dst_off, src_kaddr + src_off, len);
 	kunmap_atomic(dst_kaddr, KM_USER0);
@@ -3970,7 +4012,7 @@
 		       "len %lu len %lu\n", dst_offset, len, dst->len);
 		BUG_ON(1);
 	}
-	if (dst_offset < src_offset) {
+	if (!areas_overlap(src_offset, dst_offset, len)) {
 		memcpy_extent_buffer(dst, dst_offset, src_offset, len);
 		return;
 	}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index f62c5442..af2d717 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -208,7 +208,7 @@
 		   int bits, int exclusive_bits, u64 *failed_start,
 		   struct extent_state **cached_state, gfp_t mask);
 int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			gfp_t mask);
+			struct extent_state **cached_state, gfp_t mask);
 int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end,
 		   gfp_t mask);
 int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e621ea5..75899a0 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -104,7 +104,7 @@
 /*
  * unlocks pages after btrfs_file_write is done with them
  */
-static noinline void btrfs_drop_pages(struct page **pages, size_t num_pages)
+void btrfs_drop_pages(struct page **pages, size_t num_pages)
 {
 	size_t i;
 	for (i = 0; i < num_pages; i++) {
@@ -127,16 +127,13 @@
  * this also makes the decision about creating an inline extent vs
  * doing real data extents, marking pages dirty and delalloc as required.
  */
-static noinline int dirty_and_release_pages(struct btrfs_root *root,
-					    struct file *file,
-					    struct page **pages,
-					    size_t num_pages,
-					    loff_t pos,
-					    size_t write_bytes)
+int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
+		      struct page **pages, size_t num_pages,
+		      loff_t pos, size_t write_bytes,
+		      struct extent_state **cached)
 {
 	int err = 0;
 	int i;
-	struct inode *inode = fdentry(file)->d_inode;
 	u64 num_bytes;
 	u64 start_pos;
 	u64 end_of_last_block;
@@ -149,7 +146,7 @@
 
 	end_of_last_block = start_pos + num_bytes - 1;
 	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
-					NULL);
+					cached);
 	if (err)
 		return err;
 
@@ -992,9 +989,9 @@
 		}
 
 		if (copied > 0) {
-			ret = dirty_and_release_pages(root, file, pages,
-						      dirty_pages, pos,
-						      copied);
+			ret = btrfs_dirty_pages(root, inode, pages,
+						dirty_pages, pos, copied,
+						NULL);
 			if (ret) {
 				btrfs_delalloc_release_space(inode,
 					dirty_pages << PAGE_CACHE_SHIFT);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index f561c95..11d2e9c 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -508,6 +508,7 @@
 	struct inode *inode;
 	struct rb_node *node;
 	struct list_head *pos, *n;
+	struct page **pages;
 	struct page *page;
 	struct extent_state *cached_state = NULL;
 	struct btrfs_free_cluster *cluster = NULL;
@@ -517,13 +518,13 @@
 	u64 start, end, len;
 	u64 bytes = 0;
 	u32 *crc, *checksums;
-	pgoff_t index = 0, last_index = 0;
 	unsigned long first_page_offset;
-	int num_checksums;
+	int index = 0, num_pages = 0;
 	int entries = 0;
 	int bitmaps = 0;
 	int ret = 0;
 	bool next_page = false;
+	bool out_of_space = false;
 
 	root = root->fs_info->tree_root;
 
@@ -551,24 +552,31 @@
 		return 0;
 	}
 
-	last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
+	num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+		PAGE_CACHE_SHIFT;
 	filemap_write_and_wait(inode->i_mapping);
 	btrfs_wait_ordered_range(inode, inode->i_size &
 				 ~(root->sectorsize - 1), (u64)-1);
 
 	/* We need a checksum per page. */
-	num_checksums = i_size_read(inode) / PAGE_CACHE_SIZE;
-	crc = checksums  = kzalloc(sizeof(u32) * num_checksums, GFP_NOFS);
+	crc = checksums = kzalloc(sizeof(u32) * num_pages, GFP_NOFS);
 	if (!crc) {
 		iput(inode);
 		return 0;
 	}
 
+	pages = kzalloc(sizeof(struct page *) * num_pages, GFP_NOFS);
+	if (!pages) {
+		kfree(crc);
+		iput(inode);
+		return 0;
+	}
+
 	/* Since the first page has all of our checksums and our generation we
 	 * need to calculate the offset into the page that we can start writing
 	 * our entries.
 	 */
-	first_page_offset = (sizeof(u32) * num_checksums) + sizeof(u64);
+	first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
 
 	/* Get the cluster for this block_group if it exists */
 	if (!list_empty(&block_group->cluster_list))
@@ -590,20 +598,18 @@
 	 * after find_get_page at this point.  Just putting this here so people
 	 * know and don't freak out.
 	 */
-	while (index <= last_index) {
+	while (index < num_pages) {
 		page = grab_cache_page(inode->i_mapping, index);
 		if (!page) {
-			pgoff_t i = 0;
+			int i;
 
-			while (i < index) {
-				page = find_get_page(inode->i_mapping, i);
-				unlock_page(page);
-				page_cache_release(page);
-				page_cache_release(page);
-				i++;
+			for (i = 0; i < num_pages; i++) {
+				unlock_page(pages[i]);
+				page_cache_release(pages[i]);
 			}
 			goto out_free;
 		}
+		pages[index] = page;
 		index++;
 	}
 
@@ -631,7 +637,12 @@
 			offset = start_offset;
 		}
 
-		page = find_get_page(inode->i_mapping, index);
+		if (index >= num_pages) {
+			out_of_space = true;
+			break;
+		}
+
+		page = pages[index];
 
 		addr = kmap(page);
 		entry = addr + start_offset;
@@ -708,23 +719,6 @@
 
 		bytes += PAGE_CACHE_SIZE;
 
-		ClearPageChecked(page);
-		set_page_extent_mapped(page);
-		SetPageUptodate(page);
-		set_page_dirty(page);
-
-		/*
-		 * We need to release our reference we got for grab_cache_page,
-		 * except for the first page which will hold our checksums, we
-		 * do that below.
-		 */
-		if (index != 0) {
-			unlock_page(page);
-			page_cache_release(page);
-		}
-
-		page_cache_release(page);
-
 		index++;
 	} while (node || next_page);
 
@@ -734,7 +728,11 @@
 		struct btrfs_free_space *entry =
 			list_entry(pos, struct btrfs_free_space, list);
 
-		page = find_get_page(inode->i_mapping, index);
+		if (index >= num_pages) {
+			out_of_space = true;
+			break;
+		}
+		page = pages[index];
 
 		addr = kmap(page);
 		memcpy(addr, entry->bitmap, PAGE_CACHE_SIZE);
@@ -745,64 +743,58 @@
 		crc++;
 		bytes += PAGE_CACHE_SIZE;
 
-		ClearPageChecked(page);
-		set_page_extent_mapped(page);
-		SetPageUptodate(page);
-		set_page_dirty(page);
-		unlock_page(page);
-		page_cache_release(page);
-		page_cache_release(page);
 		list_del_init(&entry->list);
 		index++;
 	}
 
+	if (out_of_space) {
+		btrfs_drop_pages(pages, num_pages);
+		unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
+				     i_size_read(inode) - 1, &cached_state,
+				     GFP_NOFS);
+		ret = 0;
+		goto out_free;
+	}
+
 	/* Zero out the rest of the pages just to make sure */
-	while (index <= last_index) {
+	while (index < num_pages) {
 		void *addr;
 
-		page = find_get_page(inode->i_mapping, index);
-
+		page = pages[index];
 		addr = kmap(page);
 		memset(addr, 0, PAGE_CACHE_SIZE);
 		kunmap(page);
-		ClearPageChecked(page);
-		set_page_extent_mapped(page);
-		SetPageUptodate(page);
-		set_page_dirty(page);
-		unlock_page(page);
-		page_cache_release(page);
-		page_cache_release(page);
 		bytes += PAGE_CACHE_SIZE;
 		index++;
 	}
 
-	btrfs_set_extent_delalloc(inode, 0, bytes - 1, &cached_state);
-
 	/* Write the checksums and trans id to the first page */
 	{
 		void *addr;
 		u64 *gen;
 
-		page = find_get_page(inode->i_mapping, 0);
+		page = pages[0];
 
 		addr = kmap(page);
-		memcpy(addr, checksums, sizeof(u32) * num_checksums);
-		gen = addr + (sizeof(u32) * num_checksums);
+		memcpy(addr, checksums, sizeof(u32) * num_pages);
+		gen = addr + (sizeof(u32) * num_pages);
 		*gen = trans->transid;
 		kunmap(page);
-		ClearPageChecked(page);
-		set_page_extent_mapped(page);
-		SetPageUptodate(page);
-		set_page_dirty(page);
-		unlock_page(page);
-		page_cache_release(page);
-		page_cache_release(page);
 	}
-	BTRFS_I(inode)->generation = trans->transid;
 
+	ret = btrfs_dirty_pages(root, inode, pages, num_pages, 0,
+					    bytes, &cached_state);
+	btrfs_drop_pages(pages, num_pages);
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
 			     i_size_read(inode) - 1, &cached_state, GFP_NOFS);
 
+	if (ret) {
+		ret = 0;
+		goto out_free;
+	}
+
+	BTRFS_I(inode)->generation = trans->transid;
+
 	filemap_write_and_wait(inode->i_mapping);
 
 	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
@@ -853,6 +845,7 @@
 		BTRFS_I(inode)->generation = 0;
 	}
 	kfree(checksums);
+	kfree(pages);
 	btrfs_update_inode(trans, root, inode);
 	iput(inode);
 	return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5cc64ab..fcd66b6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1770,9 +1770,12 @@
 	add_pending_csums(trans, inode, ordered_extent->file_offset,
 			  &ordered_extent->list);
 
-	btrfs_ordered_update_i_size(inode, 0, ordered_extent);
-	ret = btrfs_update_inode(trans, root, inode);
-	BUG_ON(ret);
+	ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
+	if (!ret) {
+		ret = btrfs_update_inode(trans, root, inode);
+		BUG_ON(ret);
+	}
+	ret = 0;
 out:
 	if (nolock) {
 		if (trans)
@@ -2590,6 +2593,13 @@
 			    struct btrfs_inode_item *item,
 			    struct inode *inode)
 {
+	if (!leaf->map_token)
+		map_private_extent_buffer(leaf, (unsigned long)item,
+					  sizeof(struct btrfs_inode_item),
+					  &leaf->map_token, &leaf->kaddr,
+					  &leaf->map_start, &leaf->map_len,
+					  KM_USER1);
+
 	btrfs_set_inode_uid(leaf, item, inode->i_uid);
 	btrfs_set_inode_gid(leaf, item, inode->i_gid);
 	btrfs_set_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size);
@@ -2618,6 +2628,11 @@
 	btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
 	btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
 	btrfs_set_inode_block_group(leaf, item, BTRFS_I(inode)->block_group);
+
+	if (leaf->map_token) {
+		unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
+		leaf->map_token = NULL;
+	}
 }
 
 /*
@@ -4207,10 +4222,8 @@
 	struct btrfs_key found_key;
 	struct btrfs_path *path;
 	int ret;
-	u32 nritems;
 	struct extent_buffer *leaf;
 	int slot;
-	int advance;
 	unsigned char d_type;
 	int over = 0;
 	u32 di_cur;
@@ -4253,27 +4266,19 @@
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		goto err;
-	advance = 0;
 
 	while (1) {
 		leaf = path->nodes[0];
-		nritems = btrfs_header_nritems(leaf);
 		slot = path->slots[0];
-		if (advance || slot >= nritems) {
-			if (slot >= nritems - 1) {
-				ret = btrfs_next_leaf(root, path);
-				if (ret)
-					break;
-				leaf = path->nodes[0];
-				nritems = btrfs_header_nritems(leaf);
-				slot = path->slots[0];
-			} else {
-				slot++;
-				path->slots[0]++;
-			}
+		if (slot >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto err;
+			else if (ret > 0)
+				break;
+			continue;
 		}
 
-		advance = 1;
 		item = btrfs_item_nr(leaf, slot);
 		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
@@ -4282,7 +4287,7 @@
 		if (btrfs_key_type(&found_key) != key_type)
 			break;
 		if (found_key.offset < filp->f_pos)
-			continue;
+			goto next;
 
 		filp->f_pos = found_key.offset;
 
@@ -4335,6 +4340,8 @@
 			di_cur += di_len;
 			di = (struct btrfs_dir_item *)((char *)di + di_len);
 		}
+next:
+		path->slots[0]++;
 	}
 
 	/* Reached end of directory/root. Bump pos past the last item. */
@@ -4527,14 +4534,17 @@
 	BUG_ON(!path);
 
 	inode = new_inode(root->fs_info->sb);
-	if (!inode)
+	if (!inode) {
+		btrfs_free_path(path);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	if (dir) {
 		trace_btrfs_inode_request(dir);
 
 		ret = btrfs_set_inode_index(dir, index);
 		if (ret) {
+			btrfs_free_path(path);
 			iput(inode);
 			return ERR_PTR(ret);
 		}
@@ -4834,9 +4844,6 @@
 	if (inode->i_nlink == ~0U)
 		return -EMLINK;
 
-	btrfs_inc_nlink(inode);
-	inode->i_ctime = CURRENT_TIME;
-
 	err = btrfs_set_inode_index(dir, &index);
 	if (err)
 		goto fail;
@@ -4852,6 +4859,9 @@
 		goto fail;
 	}
 
+	btrfs_inc_nlink(inode);
+	inode->i_ctime = CURRENT_TIME;
+
 	btrfs_set_trans_block_group(trans, dir);
 	ihold(inode);
 
@@ -5221,7 +5231,7 @@
 			btrfs_mark_buffer_dirty(leaf);
 		}
 		set_extent_uptodate(io_tree, em->start,
-				    extent_map_end(em) - 1, GFP_NOFS);
+				    extent_map_end(em) - 1, NULL, GFP_NOFS);
 		goto insert;
 	} else {
 		printk(KERN_ERR "btrfs unknown found_type %d\n", found_type);
@@ -5428,17 +5438,30 @@
 }
 
 static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
+						  struct extent_map *em,
 						  u64 start, u64 len)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
-	struct extent_map *em;
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct btrfs_key ins;
 	u64 alloc_hint;
 	int ret;
+	bool insert = false;
 
-	btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
+	/*
+	 * Ok if the extent map we looked up is a hole and is for the exact
+	 * range we want, there is no reason to allocate a new one, however if
+	 * it is not right then we need to free this one and drop the cache for
+	 * our range.
+	 */
+	if (em->block_start != EXTENT_MAP_HOLE || em->start != start ||
+	    em->len != len) {
+		free_extent_map(em);
+		em = NULL;
+		insert = true;
+		btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
+	}
 
 	trans = btrfs_join_transaction(root, 0);
 	if (IS_ERR(trans))
@@ -5454,10 +5477,12 @@
 		goto out;
 	}
 
-	em = alloc_extent_map(GFP_NOFS);
 	if (!em) {
-		em = ERR_PTR(-ENOMEM);
-		goto out;
+		em = alloc_extent_map(GFP_NOFS);
+		if (!em) {
+			em = ERR_PTR(-ENOMEM);
+			goto out;
+		}
 	}
 
 	em->start = start;
@@ -5467,9 +5492,15 @@
 	em->block_start = ins.objectid;
 	em->block_len = ins.offset;
 	em->bdev = root->fs_info->fs_devices->latest_bdev;
+
+	/*
+	 * We need to do this because if we're using the original em we searched
+	 * for, we could have EXTENT_FLAG_VACANCY set, and we don't want that.
+	 */
+	em->flags = 0;
 	set_bit(EXTENT_FLAG_PINNED, &em->flags);
 
-	while (1) {
+	while (insert) {
 		write_lock(&em_tree->lock);
 		ret = add_extent_mapping(em_tree, em);
 		write_unlock(&em_tree->lock);
@@ -5687,8 +5718,7 @@
 	 * it above
 	 */
 	len = bh_result->b_size;
-	free_extent_map(em);
-	em = btrfs_new_extent_direct(inode, start, len);
+	em = btrfs_new_extent_direct(inode, em, start, len);
 	if (IS_ERR(em))
 		return PTR_ERR(em);
 	len = min(len, em->len - (start - em->start));
@@ -5851,8 +5881,10 @@
 	}
 
 	add_pending_csums(trans, inode, ordered->file_offset, &ordered->list);
-	btrfs_ordered_update_i_size(inode, 0, ordered);
-	btrfs_update_inode(trans, root, inode);
+	ret = btrfs_ordered_update_i_size(inode, 0, ordered);
+	if (!ret)
+		btrfs_update_inode(trans, root, inode);
+	ret = 0;
 out_unlock:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, ordered->file_offset,
 			     ordered->file_offset + ordered->len - 1,
@@ -5938,7 +5970,7 @@
 
 static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 					 int rw, u64 file_offset, int skip_sum,
-					 u32 *csums)
+					 u32 *csums, int async_submit)
 {
 	int write = rw & REQ_WRITE;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -5949,13 +5981,24 @@
 	if (ret)
 		goto err;
 
-	if (write && !skip_sum) {
+	if (skip_sum)
+		goto map;
+
+	if (write && async_submit) {
 		ret = btrfs_wq_submit_bio(root->fs_info,
 				   inode, rw, bio, 0, 0,
 				   file_offset,
 				   __btrfs_submit_bio_start_direct_io,
 				   __btrfs_submit_bio_done);
 		goto err;
+	} else if (write) {
+		/*
+		 * If we aren't doing async submit, calculate the csum of the
+		 * bio now.
+		 */
+		ret = btrfs_csum_one_bio(root, inode, bio, file_offset, 1);
+		if (ret)
+			goto err;
 	} else if (!skip_sum) {
 		ret = btrfs_lookup_bio_sums_dio(root, inode, bio,
 					  file_offset, csums);
@@ -5963,7 +6006,8 @@
 			goto err;
 	}
 
-	ret = btrfs_map_bio(root, rw, bio, 0, 1);
+map:
+	ret = btrfs_map_bio(root, rw, bio, 0, async_submit);
 err:
 	bio_put(bio);
 	return ret;
@@ -5985,15 +6029,9 @@
 	int nr_pages = 0;
 	u32 *csums = dip->csums;
 	int ret = 0;
+	int async_submit = 0;
 	int write = rw & REQ_WRITE;
 
-	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
-	if (!bio)
-		return -ENOMEM;
-	bio->bi_private = dip;
-	bio->bi_end_io = btrfs_end_dio_bio;
-	atomic_inc(&dip->pending_bios);
-
 	map_length = orig_bio->bi_size;
 	ret = btrfs_map_block(map_tree, READ, start_sector << 9,
 			      &map_length, NULL, 0);
@@ -6002,6 +6040,19 @@
 		return -EIO;
 	}
 
+	if (map_length >= orig_bio->bi_size) {
+		bio = orig_bio;
+		goto submit;
+	}
+
+	async_submit = 1;
+	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
+	if (!bio)
+		return -ENOMEM;
+	bio->bi_private = dip;
+	bio->bi_end_io = btrfs_end_dio_bio;
+	atomic_inc(&dip->pending_bios);
+
 	while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
 		if (unlikely(map_length < submit_len + bvec->bv_len ||
 		    bio_add_page(bio, bvec->bv_page, bvec->bv_len,
@@ -6015,7 +6066,7 @@
 			atomic_inc(&dip->pending_bios);
 			ret = __btrfs_submit_dio_bio(bio, inode, rw,
 						     file_offset, skip_sum,
-						     csums);
+						     csums, async_submit);
 			if (ret) {
 				bio_put(bio);
 				atomic_dec(&dip->pending_bios);
@@ -6052,8 +6103,9 @@
 		}
 	}
 
+submit:
 	ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum,
-				     csums);
+				     csums, async_submit);
 	if (!ret)
 		return 0;
 
@@ -6148,6 +6200,7 @@
 			unsigned long nr_segs)
 {
 	int seg;
+	int i;
 	size_t size;
 	unsigned long addr;
 	unsigned blocksize_mask = root->sectorsize - 1;
@@ -6162,8 +6215,22 @@
 		addr = (unsigned long)iov[seg].iov_base;
 		size = iov[seg].iov_len;
 		end += size;
-		if ((addr & blocksize_mask) || (size & blocksize_mask)) 
+		if ((addr & blocksize_mask) || (size & blocksize_mask))
 			goto out;
+
+		/* If this is a write we don't need to check anymore */
+		if (rw & WRITE)
+			continue;
+
+		/*
+		 * Check to make sure we don't have duplicate iov_base's in this
+		 * iovec, if so return EINVAL, otherwise we'll get csum errors
+		 * when reading back.
+		 */
+		for (i = seg + 1; i < nr_segs; i++) {
+			if (iov[seg].iov_base == iov[i].iov_base)
+				goto out;
+		}
 	}
 	retval = 0;
 out:
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index cfc264f..ffb48d6c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2287,7 +2287,7 @@
 	struct btrfs_ioctl_space_info space;
 	struct btrfs_ioctl_space_info *dest;
 	struct btrfs_ioctl_space_info *dest_orig;
-	struct btrfs_ioctl_space_info *user_dest;
+	struct btrfs_ioctl_space_info __user *user_dest;
 	struct btrfs_space_info *info;
 	u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
 		       BTRFS_BLOCK_GROUP_SYSTEM,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 58e7de9..0ac712e 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -159,7 +159,7 @@
 	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
 	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
 	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
-	Opt_enospc_debug, Opt_err,
+	Opt_enospc_debug, Opt_subvolrootid, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -189,6 +189,7 @@
 	{Opt_clear_cache, "clear_cache"},
 	{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
 	{Opt_enospc_debug, "enospc_debug"},
+	{Opt_subvolrootid, "subvolrootid=%d"},
 	{Opt_err, NULL},
 };
 
@@ -232,6 +233,7 @@
 			break;
 		case Opt_subvol:
 		case Opt_subvolid:
+		case Opt_subvolrootid:
 		case Opt_device:
 			/*
 			 * These are parsed by btrfs_parse_early_options
@@ -388,7 +390,7 @@
  */
 static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		void *holder, char **subvol_name, u64 *subvol_objectid,
-		struct btrfs_fs_devices **fs_devices)
+		u64 *subvol_rootid, struct btrfs_fs_devices **fs_devices)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *opts, *orig, *p;
@@ -429,6 +431,18 @@
 					*subvol_objectid = intarg;
 			}
 			break;
+		case Opt_subvolrootid:
+			intarg = 0;
+			error = match_int(&args[0], &intarg);
+			if (!error) {
+				/* we want the original fs_tree */
+				if (!intarg)
+					*subvol_rootid =
+						BTRFS_FS_TREE_OBJECTID;
+				else
+					*subvol_rootid = intarg;
+			}
+			break;
 		case Opt_device:
 			error = btrfs_scan_one_device(match_strdup(&args[0]),
 					flags, holder, fs_devices);
@@ -736,6 +750,7 @@
 	fmode_t mode = FMODE_READ;
 	char *subvol_name = NULL;
 	u64 subvol_objectid = 0;
+	u64 subvol_rootid = 0;
 	int error = 0;
 
 	if (!(flags & MS_RDONLY))
@@ -743,7 +758,7 @@
 
 	error = btrfs_parse_early_options(data, mode, fs_type,
 					  &subvol_name, &subvol_objectid,
-					  &fs_devices);
+					  &subvol_rootid, &fs_devices);
 	if (error)
 		return ERR_PTR(error);
 
@@ -807,15 +822,17 @@
 		s->s_flags |= MS_ACTIVE;
 	}
 
-	root = get_default_root(s, subvol_objectid);
-	if (IS_ERR(root)) {
-		error = PTR_ERR(root);
-		deactivate_locked_super(s);
-		goto error_free_subvol_name;
-	}
 	/* if they gave us a subvolume name bind mount into that */
 	if (strcmp(subvol_name, ".")) {
 		struct dentry *new_root;
+
+		root = get_default_root(s, subvol_rootid);
+		if (IS_ERR(root)) {
+			error = PTR_ERR(root);
+			deactivate_locked_super(s);
+			goto error_free_subvol_name;
+		}
+
 		mutex_lock(&root->d_inode->i_mutex);
 		new_root = lookup_one_len(subvol_name, root,
 				      strlen(subvol_name));
@@ -836,6 +853,13 @@
 		}
 		dput(root);
 		root = new_root;
+	} else {
+		root = get_default_root(s, subvol_objectid);
+		if (IS_ERR(root)) {
+			error = PTR_ERR(root);
+			deactivate_locked_super(s);
+			goto error_free_subvol_name;
+		}
 	}
 
 	kfree(subvol_name);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5b158da..c571734 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -32,10 +32,8 @@
 
 static noinline void put_transaction(struct btrfs_transaction *transaction)
 {
-	WARN_ON(transaction->use_count == 0);
-	transaction->use_count--;
-	if (transaction->use_count == 0) {
-		list_del_init(&transaction->list);
+	WARN_ON(atomic_read(&transaction->use_count) == 0);
+	if (atomic_dec_and_test(&transaction->use_count)) {
 		memset(transaction, 0, sizeof(*transaction));
 		kmem_cache_free(btrfs_transaction_cachep, transaction);
 	}
@@ -60,14 +58,14 @@
 		if (!cur_trans)
 			return -ENOMEM;
 		root->fs_info->generation++;
-		cur_trans->num_writers = 1;
+		atomic_set(&cur_trans->num_writers, 1);
 		cur_trans->num_joined = 0;
 		cur_trans->transid = root->fs_info->generation;
 		init_waitqueue_head(&cur_trans->writer_wait);
 		init_waitqueue_head(&cur_trans->commit_wait);
 		cur_trans->in_commit = 0;
 		cur_trans->blocked = 0;
-		cur_trans->use_count = 1;
+		atomic_set(&cur_trans->use_count, 1);
 		cur_trans->commit_done = 0;
 		cur_trans->start_time = get_seconds();
 
@@ -88,7 +86,7 @@
 		root->fs_info->running_transaction = cur_trans;
 		spin_unlock(&root->fs_info->new_trans_lock);
 	} else {
-		cur_trans->num_writers++;
+		atomic_inc(&cur_trans->num_writers);
 		cur_trans->num_joined++;
 	}
 
@@ -145,7 +143,7 @@
 	cur_trans = root->fs_info->running_transaction;
 	if (cur_trans && cur_trans->blocked) {
 		DEFINE_WAIT(wait);
-		cur_trans->use_count++;
+		atomic_inc(&cur_trans->use_count);
 		while (1) {
 			prepare_to_wait(&root->fs_info->transaction_wait, &wait,
 					TASK_UNINTERRUPTIBLE);
@@ -181,6 +179,7 @@
 {
 	struct btrfs_trans_handle *h;
 	struct btrfs_transaction *cur_trans;
+	int retries = 0;
 	int ret;
 
 	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
@@ -204,7 +203,7 @@
 	}
 
 	cur_trans = root->fs_info->running_transaction;
-	cur_trans->use_count++;
+	atomic_inc(&cur_trans->use_count);
 	if (type != TRANS_JOIN_NOLOCK)
 		mutex_unlock(&root->fs_info->trans_mutex);
 
@@ -224,10 +223,18 @@
 
 	if (num_items > 0) {
 		ret = btrfs_trans_reserve_metadata(h, root, num_items);
-		if (ret == -EAGAIN) {
+		if (ret == -EAGAIN && !retries) {
+			retries++;
 			btrfs_commit_transaction(h, root);
 			goto again;
+		} else if (ret == -EAGAIN) {
+			/*
+			 * We have already retried and got EAGAIN, so really we
+			 * don't have space, so set ret to -ENOSPC.
+			 */
+			ret = -ENOSPC;
 		}
+
 		if (ret < 0) {
 			btrfs_end_transaction(h, root);
 			return ERR_PTR(ret);
@@ -327,7 +334,7 @@
 			goto out_unlock;  /* nothing committing|committed */
 	}
 
-	cur_trans->use_count++;
+	atomic_inc(&cur_trans->use_count);
 	mutex_unlock(&root->fs_info->trans_mutex);
 
 	wait_for_commit(root, cur_trans);
@@ -457,18 +464,14 @@
 			wake_up_process(info->transaction_kthread);
 	}
 
-	if (lock)
-		mutex_lock(&info->trans_mutex);
 	WARN_ON(cur_trans != info->running_transaction);
-	WARN_ON(cur_trans->num_writers < 1);
-	cur_trans->num_writers--;
+	WARN_ON(atomic_read(&cur_trans->num_writers) < 1);
+	atomic_dec(&cur_trans->num_writers);
 
 	smp_mb();
 	if (waitqueue_active(&cur_trans->writer_wait))
 		wake_up(&cur_trans->writer_wait);
 	put_transaction(cur_trans);
-	if (lock)
-		mutex_unlock(&info->trans_mutex);
 
 	if (current->journal_info == trans)
 		current->journal_info = NULL;
@@ -1178,7 +1181,7 @@
 	/* take transaction reference */
 	mutex_lock(&root->fs_info->trans_mutex);
 	cur_trans = trans->transaction;
-	cur_trans->use_count++;
+	atomic_inc(&cur_trans->use_count);
 	mutex_unlock(&root->fs_info->trans_mutex);
 
 	btrfs_end_transaction(trans, root);
@@ -1237,7 +1240,7 @@
 
 	mutex_lock(&root->fs_info->trans_mutex);
 	if (cur_trans->in_commit) {
-		cur_trans->use_count++;
+		atomic_inc(&cur_trans->use_count);
 		mutex_unlock(&root->fs_info->trans_mutex);
 		btrfs_end_transaction(trans, root);
 
@@ -1259,7 +1262,7 @@
 		prev_trans = list_entry(cur_trans->list.prev,
 					struct btrfs_transaction, list);
 		if (!prev_trans->commit_done) {
-			prev_trans->use_count++;
+			atomic_inc(&prev_trans->use_count);
 			mutex_unlock(&root->fs_info->trans_mutex);
 
 			wait_for_commit(root, prev_trans);
@@ -1300,14 +1303,14 @@
 				TASK_UNINTERRUPTIBLE);
 
 		smp_mb();
-		if (cur_trans->num_writers > 1)
+		if (atomic_read(&cur_trans->num_writers) > 1)
 			schedule_timeout(MAX_SCHEDULE_TIMEOUT);
 		else if (should_grow)
 			schedule_timeout(1);
 
 		mutex_lock(&root->fs_info->trans_mutex);
 		finish_wait(&cur_trans->writer_wait, &wait);
-	} while (cur_trans->num_writers > 1 ||
+	} while (atomic_read(&cur_trans->num_writers) > 1 ||
 		 (should_grow && cur_trans->num_joined != joined));
 
 	ret = create_pending_snapshots(trans, root->fs_info);
@@ -1394,6 +1397,7 @@
 
 	wake_up(&cur_trans->commit_wait);
 
+	list_del_init(&cur_trans->list);
 	put_transaction(cur_trans);
 	put_transaction(cur_trans);
 
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 229a594..e441acc 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -27,11 +27,11 @@
 	 * total writers in this transaction, it must be zero before the
 	 * transaction can end
 	 */
-	unsigned long num_writers;
+	atomic_t num_writers;
 
 	unsigned long num_joined;
 	int in_commit;
-	int use_count;
+	atomic_t use_count;
 	int commit_done;
 	int blocked;
 	struct list_head list;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index a5303b8..cfd6605 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -180,11 +180,10 @@
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_dir_item *di;
-	int ret = 0, slot, advance;
+	int ret = 0, slot;
 	size_t total_size = 0, size_left = size;
 	unsigned long name_ptr;
 	size_t name_len;
-	u32 nritems;
 
 	/*
 	 * ok we want all objects associated with this id.
@@ -204,34 +203,24 @@
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		goto err;
-	advance = 0;
+
 	while (1) {
 		leaf = path->nodes[0];
-		nritems = btrfs_header_nritems(leaf);
 		slot = path->slots[0];
 
 		/* this is where we start walking through the path */
-		if (advance || slot >= nritems) {
+		if (slot >= btrfs_header_nritems(leaf)) {
 			/*
 			 * if we've reached the last slot in this leaf we need
 			 * to go to the next leaf and reset everything
 			 */
-			if (slot >= nritems-1) {
-				ret = btrfs_next_leaf(root, path);
-				if (ret)
-					break;
-				leaf = path->nodes[0];
-				nritems = btrfs_header_nritems(leaf);
-				slot = path->slots[0];
-			} else {
-				/*
-				 * just walking through the slots on this leaf
-				 */
-				slot++;
-				path->slots[0]++;
-			}
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto err;
+			else if (ret > 0)
+				break;
+			continue;
 		}
-		advance = 1;
 
 		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
@@ -250,7 +239,7 @@
 
 		/* we are just looking for how big our buffer needs to be */
 		if (!size)
-			continue;
+			goto next;
 
 		if (!buffer || (name_len + 1) > size_left) {
 			ret = -ERANGE;
@@ -263,6 +252,8 @@
 
 		size_left -= name_len + 1;
 		buffer += name_len + 1;
+next:
+		path->slots[0]++;
 	}
 	ret = total_size;
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index c71995b..0f5c4f9 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -884,8 +884,8 @@
 	}
 
 	brelse(dibh);
-	gfs2_trans_end(sdp);
 failed:
+	gfs2_trans_end(sdp);
 	if (al) {
 		gfs2_inplace_release(ip);
 		gfs2_quota_unlock(ip);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 5c356d0..f789c57 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1506,7 +1506,7 @@
 		inode = gfs2_inode_lookup(dir->i_sb, 
 				be16_to_cpu(dent->de_type),
 				be64_to_cpu(dent->de_inum.no_addr),
-				be64_to_cpu(dent->de_inum.no_formal_ino));
+				be64_to_cpu(dent->de_inum.no_formal_ino), 0);
 		brelse(bh);
 		return inode;
 	}
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index b2682e0..e483108 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -617,18 +617,51 @@
 	return generic_file_aio_write(iocb, iov, nr_segs, pos);
 }
 
-static void empty_write_end(struct page *page, unsigned from,
-			   unsigned to)
+static int empty_write_end(struct page *page, unsigned from,
+			   unsigned to, int mode)
 {
-	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct buffer_head *bh;
+	unsigned offset, blksize = 1 << inode->i_blkbits;
+	pgoff_t end_index = i_size_read(inode) >> PAGE_CACHE_SHIFT;
 
 	zero_user(page, from, to-from);
 	mark_page_accessed(page);
 
-	if (!gfs2_is_writeback(ip))
-		gfs2_page_add_databufs(ip, page, from, to);
+	if (page->index < end_index || !(mode & FALLOC_FL_KEEP_SIZE)) {
+		if (!gfs2_is_writeback(ip))
+			gfs2_page_add_databufs(ip, page, from, to);
 
-	block_commit_write(page, from, to);
+		block_commit_write(page, from, to);
+		return 0;
+	}
+
+	offset = 0;
+	bh = page_buffers(page);
+	while (offset < to) {
+		if (offset >= from) {
+			set_buffer_uptodate(bh);
+			mark_buffer_dirty(bh);
+			clear_buffer_new(bh);
+			write_dirty_buffer(bh, WRITE);
+		}
+		offset += blksize;
+		bh = bh->b_this_page;
+	}
+
+	offset = 0;
+	bh = page_buffers(page);
+	while (offset < to) {
+		if (offset >= from) {
+			wait_on_buffer(bh);
+			if (!buffer_uptodate(bh))
+				return -EIO;
+		}
+		offset += blksize;
+		bh = bh->b_this_page;
+	}
+	return 0;
 }
 
 static int needs_empty_write(sector_t block, struct inode *inode)
@@ -643,7 +676,8 @@
 	return !buffer_mapped(&bh_map);
 }
 
-static int write_empty_blocks(struct page *page, unsigned from, unsigned to)
+static int write_empty_blocks(struct page *page, unsigned from, unsigned to,
+			      int mode)
 {
 	struct inode *inode = page->mapping->host;
 	unsigned start, end, next, blksize;
@@ -668,7 +702,9 @@
 							  gfs2_block_map);
 				if (unlikely(ret))
 					return ret;
-				empty_write_end(page, start, end);
+				ret = empty_write_end(page, start, end, mode);
+				if (unlikely(ret))
+					return ret;
 				end = 0;
 			}
 			start = next;
@@ -682,7 +718,9 @@
 		ret = __block_write_begin(page, start, end - start, gfs2_block_map);
 		if (unlikely(ret))
 			return ret;
-		empty_write_end(page, start, end);
+		ret = empty_write_end(page, start, end, mode);
+		if (unlikely(ret))
+			return ret;
 	}
 
 	return 0;
@@ -731,7 +769,7 @@
 
 		if (curr == end)
 			to = end_offset;
-		error = write_empty_blocks(page, from, to);
+		error = write_empty_blocks(page, from, to, mode);
 		if (!error && offset + to > inode->i_size &&
 		    !(mode & FALLOC_FL_KEEP_SIZE)) {
 			i_size_write(inode, offset + to);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 3754e3c..25eeb2b 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -385,6 +385,10 @@
 static void iopen_go_callback(struct gfs2_glock *gl)
 {
 	struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (sdp->sd_vfs->s_flags & MS_RDONLY)
+		return;
 
 	if (gl->gl_demote_state == LM_ST_UNLOCKED &&
 	    gl->gl_state == LM_ST_SHARED && ip) {
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 97d54a2..9134dcb 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -40,37 +40,61 @@
 	u64 ir_length;
 };
 
+struct gfs2_skip_data {
+	u64 no_addr;
+	int skipped;
+	int non_block;
+};
+
 static int iget_test(struct inode *inode, void *opaque)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
-	u64 *no_addr = opaque;
+	struct gfs2_skip_data *data = opaque;
 
-	if (ip->i_no_addr == *no_addr)
+	if (ip->i_no_addr == data->no_addr) {
+		if (data->non_block &&
+		    inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
+			data->skipped = 1;
+			return 0;
+		}
 		return 1;
-
+	}
 	return 0;
 }
 
 static int iget_set(struct inode *inode, void *opaque)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
-	u64 *no_addr = opaque;
+	struct gfs2_skip_data *data = opaque;
 
-	inode->i_ino = (unsigned long)*no_addr;
-	ip->i_no_addr = *no_addr;
+	if (data->skipped)
+		return -ENOENT;
+	inode->i_ino = (unsigned long)(data->no_addr);
+	ip->i_no_addr = data->no_addr;
 	return 0;
 }
 
 struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr)
 {
 	unsigned long hash = (unsigned long)no_addr;
-	return ilookup5(sb, hash, iget_test, &no_addr);
+	struct gfs2_skip_data data;
+
+	data.no_addr = no_addr;
+	data.skipped = 0;
+	data.non_block = 0;
+	return ilookup5(sb, hash, iget_test, &data);
 }
 
-static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr)
+static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr,
+			       int non_block)
 {
+	struct gfs2_skip_data data;
 	unsigned long hash = (unsigned long)no_addr;
-	return iget5_locked(sb, hash, iget_test, iget_set, &no_addr);
+
+	data.no_addr = no_addr;
+	data.skipped = 0;
+	data.non_block = non_block;
+	return iget5_locked(sb, hash, iget_test, iget_set, &data);
 }
 
 /**
@@ -111,19 +135,20 @@
  * @sb: The super block
  * @no_addr: The inode number
  * @type: The type of the inode
+ * non_block: Can we block on inodes that are being freed?
  *
  * Returns: A VFS inode, or an error
  */
 
 struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
-				u64 no_addr, u64 no_formal_ino)
+				u64 no_addr, u64 no_formal_ino, int non_block)
 {
 	struct inode *inode;
 	struct gfs2_inode *ip;
 	struct gfs2_glock *io_gl = NULL;
 	int error;
 
-	inode = gfs2_iget(sb, no_addr);
+	inode = gfs2_iget(sb, no_addr, non_block);
 	ip = GFS2_I(inode);
 
 	if (!inode)
@@ -185,11 +210,12 @@
 {
 	struct super_block *sb = sdp->sd_vfs;
 	struct gfs2_holder i_gh;
-	struct inode *inode;
+	struct inode *inode = NULL;
 	int error;
 
+	/* Must not read in block until block type is verified */
 	error = gfs2_glock_nq_num(sdp, no_addr, &gfs2_inode_glops,
-				  LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+				  LM_ST_EXCLUSIVE, GL_SKIP, &i_gh);
 	if (error)
 		return ERR_PTR(error);
 
@@ -197,7 +223,7 @@
 	if (error)
 		goto fail;
 
-	inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0);
+	inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0, 1);
 	if (IS_ERR(inode))
 		goto fail;
 
@@ -843,7 +869,7 @@
 		goto fail_gunlock2;
 
 	inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode), inum.no_addr,
-				  inum.no_formal_ino);
+				  inum.no_formal_ino, 0);
 	if (IS_ERR(inode))
 		goto fail_gunlock2;
 
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 3e00a66..099ca30 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -97,7 +97,8 @@
 }
 
 extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
-				       u64 no_addr, u64 no_formal_ino);
+				       u64 no_addr, u64 no_formal_ino,
+				       int non_block);
 extern struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
 					 u64 *no_formal_ino,
 					 unsigned int blktype);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 42ef243..d3c69eb 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -430,7 +430,7 @@
 	struct dentry *dentry;
 	struct inode *inode;
 
-	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0);
+	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
 	if (IS_ERR(inode)) {
 		fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
 		return PTR_ERR(inode);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index cf930cd..6fcae84 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -945,7 +945,7 @@
 		/* rgblk_search can return a block < goal, so we need to
 		   keep it marching forward. */
 		no_addr = block + rgd->rd_data0;
-		goal++;
+		goal = max(block + 1, goal + 1);
 		if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
 			continue;
 		if (no_addr == skip)
@@ -971,7 +971,7 @@
 			found++;
 
 		/* Limit reclaim to sensible number of tasks */
-		if (found > 2*NR_CPUS)
+		if (found > NR_CPUS)
 			return;
 	}
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index a4e23d6..b9f28e6 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1318,15 +1318,17 @@
 
 static void gfs2_evict_inode(struct inode *inode)
 {
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int error;
 
-	if (inode->i_nlink)
+	if (inode->i_nlink || (sb->s_flags & MS_RDONLY))
 		goto out;
 
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	/* Must not read inode block until block type has been verified */
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
 	if (unlikely(error)) {
 		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 		goto out;
@@ -1336,6 +1338,12 @@
 	if (error)
 		goto out_truncate;
 
+	if (test_bit(GIF_INVALID, &ip->i_flags)) {
+		error = gfs2_inode_refresh(ip);
+		if (error)
+			goto out_truncate;
+	}
+
 	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 	gfs2_glock_dq_wait(&ip->i_iopen_gh);
 	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index dd6628d..dfa5327 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3124,11 +3124,16 @@
 /* for the /proc/ directory itself, after non-process stuff has been done */
 int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
 {
-	unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY;
-	struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode);
+	unsigned int nr;
+	struct task_struct *reaper;
 	struct tgid_iter iter;
 	struct pid_namespace *ns;
 
+	if (filp->f_pos >= PID_MAX_LIMIT + TGID_OFFSET)
+		goto out_no_task;
+	nr = filp->f_pos - FIRST_PROCESS_ENTRY;
+
+	reaper = get_proc_task(filp->f_path.dentry->d_inode);
 	if (!reaper)
 		goto out_no_task;
 
diff --git a/include/linux/input.h b/include/linux/input.h
index f3a7794..771d6d8 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -167,6 +167,7 @@
 #define SYN_REPORT		0
 #define SYN_CONFIG		1
 #define SYN_MT_REPORT		2
+#define SYN_DROPPED		3
 
 /*
  * Keys and buttons
@@ -553,8 +554,8 @@
 #define KEY_DVD			0x185	/* Media Select DVD */
 #define KEY_AUX			0x186
 #define KEY_MP3			0x187
-#define KEY_AUDIO		0x188
-#define KEY_VIDEO		0x189
+#define KEY_AUDIO		0x188	/* AL Audio Browser */
+#define KEY_VIDEO		0x189	/* AL Movie Browser */
 #define KEY_DIRECTORY		0x18a
 #define KEY_LIST		0x18b
 #define KEY_MEMO		0x18c	/* Media Select Messages */
@@ -603,8 +604,9 @@
 #define KEY_FRAMEFORWARD	0x1b5
 #define KEY_CONTEXT_MENU	0x1b6	/* GenDesc - system context menu */
 #define KEY_MEDIA_REPEAT	0x1b7	/* Consumer - transport control */
-#define KEY_10CHANNELSUP        0x1b8   /* 10 channels up (10+) */
-#define KEY_10CHANNELSDOWN      0x1b9   /* 10 channels down (10-) */
+#define KEY_10CHANNELSUP	0x1b8	/* 10 channels up (10+) */
+#define KEY_10CHANNELSDOWN	0x1b9	/* 10 channels down (10-) */
+#define KEY_IMAGES		0x1ba	/* AL Image Browser */
 
 #define KEY_DEL_EOL		0x1c0
 #define KEY_DEL_EOS		0x1c1
diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h
index b3ac06a..318bb82 100644
--- a/include/linux/input/mt.h
+++ b/include/linux/input/mt.h
@@ -48,6 +48,12 @@
 	input_event(dev, EV_ABS, ABS_MT_SLOT, slot);
 }
 
+static inline bool input_is_mt_axis(int axis)
+{
+	return axis == ABS_MT_SLOT ||
+		(axis >= ABS_MT_FIRST && axis <= ABS_MT_LAST);
+}
+
 void input_mt_report_slot_state(struct input_dev *dev,
 				unsigned int tool_type, bool active);
 
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 31afb7e..cdced84 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -117,7 +117,7 @@
  */
 extern struct pid *find_get_pid(int nr);
 extern struct pid *find_ge_pid(int nr, struct pid_namespace *);
-int next_pidmap(struct pid_namespace *pid_ns, int last);
+int next_pidmap(struct pid_namespace *pid_ns, unsigned int last);
 
 extern struct pid *alloc_pid(struct pid_namespace *ns);
 extern void free_pid(struct pid *pid);
diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h
index 369e19d..7f1183dc 100644
--- a/include/linux/posix-clock.h
+++ b/include/linux/posix-clock.h
@@ -24,6 +24,7 @@
 #include <linux/fs.h>
 #include <linux/poll.h>
 #include <linux/posix-timers.h>
+#include <linux/rwsem.h>
 
 struct posix_clock;
 
@@ -104,7 +105,7 @@
  * @ops:     Functional interface to the clock
  * @cdev:    Character device instance for this clock
  * @kref:    Reference count.
- * @mutex:   Protects the 'zombie' field from concurrent access.
+ * @rwsem:   Protects the 'zombie' field from concurrent access.
  * @zombie:  If 'zombie' is true, then the hardware has disappeared.
  * @release: A function to free the structure when the reference count reaches
  *           zero. May be NULL if structure is statically allocated.
@@ -117,7 +118,7 @@
 	struct posix_clock_operations ops;
 	struct cdev cdev;
 	struct kref kref;
-	struct mutex mutex;
+	struct rw_semaphore rwsem;
 	bool zombie;
 	void (*release)(struct posix_clock *clk);
 };
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 3c7329b..0e18550 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -103,8 +103,8 @@
  * Indicates to usbnet, that USB driver accumulates multiple IP packets.
  * Affects statistic (counters) and short packet handling.
  */
-#define FLAG_MULTI_PACKET	0x1000
-#define FLAG_RX_ASSEMBLE	0x2000	/* rx packets may span >1 frames */
+#define FLAG_MULTI_PACKET	0x2000
+#define FLAG_RX_ASSEMBLE	0x4000	/* rx packets may span >1 frames */
 
 	/* init device ... can sleep, or cause probe() failure */
 	int	(*bind)(struct usbnet *, struct usb_interface *);
diff --git a/kernel/pid.c b/kernel/pid.c
index 02f2212..57a8346 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -217,11 +217,14 @@
 	return -1;
 }
 
-int next_pidmap(struct pid_namespace *pid_ns, int last)
+int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
 {
 	int offset;
 	struct pidmap *map, *end;
 
+	if (last >= PID_MAX_LIMIT)
+		return -1;
+
 	offset = (last + 1) & BITS_PER_PAGE_MASK;
 	map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE];
 	end = &pid_ns->pidmap[PIDMAP_ENTRIES];
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 25028dd..c340ca6 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -19,7 +19,6 @@
  */
 #include <linux/device.h>
 #include <linux/file.h>
-#include <linux/mutex.h>
 #include <linux/posix-clock.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
@@ -34,19 +33,19 @@
 {
 	struct posix_clock *clk = fp->private_data;
 
-	mutex_lock(&clk->mutex);
+	down_read(&clk->rwsem);
 
 	if (!clk->zombie)
 		return clk;
 
-	mutex_unlock(&clk->mutex);
+	up_read(&clk->rwsem);
 
 	return NULL;
 }
 
 static void put_posix_clock(struct posix_clock *clk)
 {
-	mutex_unlock(&clk->mutex);
+	up_read(&clk->rwsem);
 }
 
 static ssize_t posix_clock_read(struct file *fp, char __user *buf,
@@ -156,7 +155,7 @@
 	struct posix_clock *clk =
 		container_of(inode->i_cdev, struct posix_clock, cdev);
 
-	mutex_lock(&clk->mutex);
+	down_read(&clk->rwsem);
 
 	if (clk->zombie) {
 		err = -ENODEV;
@@ -172,7 +171,7 @@
 		fp->private_data = clk;
 	}
 out:
-	mutex_unlock(&clk->mutex);
+	up_read(&clk->rwsem);
 	return err;
 }
 
@@ -211,25 +210,20 @@
 	int err;
 
 	kref_init(&clk->kref);
-	mutex_init(&clk->mutex);
+	init_rwsem(&clk->rwsem);
 
 	cdev_init(&clk->cdev, &posix_clock_file_operations);
 	clk->cdev.owner = clk->ops.owner;
 	err = cdev_add(&clk->cdev, devid, 1);
-	if (err)
-		goto no_cdev;
 
 	return err;
-no_cdev:
-	mutex_destroy(&clk->mutex);
-	return err;
 }
 EXPORT_SYMBOL_GPL(posix_clock_register);
 
 static void delete_clock(struct kref *kref)
 {
 	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
-	mutex_destroy(&clk->mutex);
+
 	if (clk->release)
 		clk->release(clk);
 }
@@ -238,9 +232,9 @@
 {
 	cdev_del(&clk->cdev);
 
-	mutex_lock(&clk->mutex);
+	down_write(&clk->rwsem);
 	clk->zombie = true;
-	mutex_unlock(&clk->mutex);
+	up_write(&clk->rwsem);
 
 	kref_put(&clk->kref, delete_clock);
 }
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 008ff6c..f3bc322 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -249,11 +249,9 @@
 		goto drop;
 	}
 
-	/* Zero out the CB buffer if no options present */
-	if (iph->ihl == 5) {
-		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+	if (iph->ihl == 5)
 		return 0;
-	}
 
 	opt->optlen = iph->ihl*4 - sizeof(struct iphdr);
 	if (ip_options_compile(dev_net(dev), opt, skb))
diff --git a/net/caif/cfdgml.c b/net/caif/cfdgml.c
index 27dab26..054fdb5 100644
--- a/net/caif/cfdgml.c
+++ b/net/caif/cfdgml.c
@@ -13,6 +13,7 @@
 #include <net/caif/cfsrvl.h>
 #include <net/caif/cfpkt.h>
 
+
 #define container_obj(layr) ((struct cfsrvl *) layr)
 
 #define DGM_CMD_BIT  0x80
@@ -83,6 +84,7 @@
 
 static int cfdgml_transmit(struct cflayer *layr, struct cfpkt *pkt)
 {
+	u8 packet_type;
 	u32 zero = 0;
 	struct caif_payload_info *info;
 	struct cfsrvl *service = container_obj(layr);
@@ -94,7 +96,9 @@
 	if (cfpkt_getlen(pkt) > DGM_MTU)
 		return -EMSGSIZE;
 
-	cfpkt_add_head(pkt, &zero, 4);
+	cfpkt_add_head(pkt, &zero, 3);
+	packet_type = 0x08; /* B9 set - UNCLASSIFIED */
+	cfpkt_add_head(pkt, &packet_type, 1);
 
 	/* Add info for MUX-layer to route the packet out. */
 	info = cfpkt_info(pkt);
diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c
index 46f34b2..24f1ffa 100644
--- a/net/caif/cfmuxl.c
+++ b/net/caif/cfmuxl.c
@@ -244,9 +244,9 @@
 				int phyid)
 {
 	struct cfmuxl *muxl = container_obj(layr);
-	struct list_head *node;
+	struct list_head *node, *next;
 	struct cflayer *layer;
-	list_for_each(node, &muxl->srvl_list) {
+	list_for_each_safe(node, next, &muxl->srvl_list) {
 		layer = list_entry(node, struct cflayer, node);
 		if (cfsrvl_phyid_match(layer, phyid))
 			layer->ctrlcmd(layer, ctrl, phyid);
diff --git a/net/core/dev.c b/net/core/dev.c
index 956d3b0..c2ac599 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5203,11 +5203,15 @@
 	}
 
 	/* TSO requires that SG is present as well. */
-	if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) {
-		netdev_info(dev, "Dropping NETIF_F_TSO since no SG feature.\n");
-		features &= ~NETIF_F_TSO;
+	if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) {
+		netdev_info(dev, "Dropping TSO features since no SG feature.\n");
+		features &= ~NETIF_F_ALL_TSO;
 	}
 
+	/* TSO ECN requires that TSO is present as well. */
+	if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN)
+		features &= ~NETIF_F_TSO_ECN;
+
 	/* Software GSO depends on SG. */
 	if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) {
 		netdev_info(dev, "Dropping NETIF_F_GSO since no SG feature.\n");
diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile
index ce2d335..5761185 100644
--- a/net/ieee802154/Makefile
+++ b/net/ieee802154/Makefile
@@ -1,5 +1,3 @@
 obj-$(CONFIG_IEEE802154) +=	ieee802154.o af_802154.o
 ieee802154-y		:= netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o
 af_802154-y		:= af_ieee802154.o raw.o dgram.o
-
-ccflags-y += -Wall -DDEBUG
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6c0b7f4..38f23e7 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -73,7 +73,7 @@
 		     !sk2->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
 			if (!reuse || !sk2->sk_reuse ||
-			    ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) {
+			    sk2->sk_state == TCP_LISTEN) {
 				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
 				if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
 				    sk2_rcv_saddr == sk_rcv_saddr(sk))
@@ -122,8 +122,7 @@
 					    (tb->num_owners < smallest_size || smallest_size == -1)) {
 						smallest_size = tb->num_owners;
 						smallest_rover = rover;
-						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 &&
-						    !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
 							spin_unlock(&head->lock);
 							snum = smallest_rover;
 							goto have_snum;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index dd1b20e..9df4e63 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -354,7 +354,8 @@
 }
 
 /* May be called with local BH enabled. */
-static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base)
+static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base,
+			     struct inet_peer __rcu **stack[PEER_MAXDEPTH])
 {
 	int do_free;
 
@@ -368,7 +369,6 @@
 	 * We use refcnt=-1 to alert lockless readers this entry is deleted.
 	 */
 	if (atomic_cmpxchg(&p->refcnt, 1, -1) == 1) {
-		struct inet_peer __rcu **stack[PEER_MAXDEPTH];
 		struct inet_peer __rcu ***stackptr, ***delp;
 		if (lookup(&p->daddr, stack, base) != p)
 			BUG();
@@ -422,7 +422,7 @@
 }
 
 /* May be called with local BH enabled. */
-static int cleanup_once(unsigned long ttl)
+static int cleanup_once(unsigned long ttl, struct inet_peer __rcu **stack[PEER_MAXDEPTH])
 {
 	struct inet_peer *p = NULL;
 
@@ -454,7 +454,7 @@
 		 * happen because of entry limits in route cache. */
 		return -1;
 
-	unlink_from_pool(p, peer_to_base(p));
+	unlink_from_pool(p, peer_to_base(p), stack);
 	return 0;
 }
 
@@ -524,7 +524,7 @@
 
 	if (base->total >= inet_peer_threshold)
 		/* Remove one less-recently-used entry. */
-		cleanup_once(0);
+		cleanup_once(0, stack);
 
 	return p;
 }
@@ -540,6 +540,7 @@
 {
 	unsigned long now = jiffies;
 	int ttl, total;
+	struct inet_peer __rcu **stack[PEER_MAXDEPTH];
 
 	total = compute_total();
 	if (total >= inet_peer_threshold)
@@ -548,7 +549,7 @@
 		ttl = inet_peer_maxttl
 				- (inet_peer_maxttl - inet_peer_minttl) / HZ *
 					total / inet_peer_threshold * HZ;
-	while (!cleanup_once(ttl)) {
+	while (!cleanup_once(ttl, stack)) {
 		if (jiffies != now)
 			break;
 	}
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 28a736f..2391b24 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -329,7 +329,7 @@
 					pp_ptr = optptr + 2;
 					goto error;
 				}
-				if (skb) {
+				if (rt) {
 					memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
 					opt->is_changed = 1;
 				}
@@ -371,7 +371,7 @@
 						goto error;
 					}
 					opt->ts = optptr - iph;
-					if (skb) {
+					if (rt)  {
 						memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
 						timeptr = (__be32*)&optptr[optptr[2]+3];
 					}
@@ -603,7 +603,7 @@
 	unsigned long orefdst;
 	int err;
 
-	if (!opt->srr)
+	if (!opt->srr || !rt)
 		return 0;
 
 	if (skb->pkt_type != PACKET_HOST)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1a45665..321e6e8 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -311,7 +311,6 @@
 		.mode		= 0644,
 		.proc_handler	= proc_do_large_bitmap,
 	},
-#ifdef CONFIG_IP_MULTICAST
 	{
 		.procname	= "igmp_max_memberships",
 		.data		= &sysctl_igmp_max_memberships,
@@ -319,8 +318,6 @@
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-
-#endif
 	{
 		.procname	= "igmp_max_msf",
 		.data		= &sysctl_igmp_max_msf,
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 1660546..f2c5b0f 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -44,7 +44,7 @@
 		     !sk2->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if) &&
 		    (!sk->sk_reuse || !sk2->sk_reuse ||
-		     ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) &&
+		     sk2->sk_state == TCP_LISTEN) &&
 		     ipv6_rcv_saddr_equal(sk, sk2))
 			break;
 	}
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index c9890e2..cc61697 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1297,8 +1297,7 @@
 	/* Note : socket.c set MSG_EOR on SEQPACKET sockets */
 	if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_EOR | MSG_CMSG_COMPAT |
 			       MSG_NOSIGNAL)) {
-		err = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	lock_sock(sk);
diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c
index 058f1e9..9032421 100644
--- a/net/llc/llc_input.c
+++ b/net/llc/llc_input.c
@@ -121,8 +121,7 @@
 		s32 data_size = ntohs(pdulen) - llc_len;
 
 		if (data_size < 0 ||
-		    ((skb_tail_pointer(skb) -
-		      (u8 *)pdu) - llc_len) < data_size)
+		    !pskb_may_pull(skb, data_size))
 			return 0;
 		if (unlikely(pskb_trim_rcsum(skb, data_size)))
 			return 0;
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 00a3324..a274300 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -343,6 +343,10 @@
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct ipmac data;
 
+	/* MAC can be src only */
+	if (!(flags & IPSET_DIM_TWO_SRC))
+		return 0;
+
 	data.id = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC));
 	if (data.id < map->first_ip || data.id > map->last_ip)
 		return -IPSET_ERR_BITMAP_RANGE;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 9152e69..72d1ac6 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1022,8 +1022,9 @@
 	if (cb->args[1] >= ip_set_max)
 		goto out;
 
-	pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]);
 	max = cb->args[0] == DUMP_ONE ? cb->args[1] + 1 : ip_set_max;
+dump_last:
+	pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]);
 	for (; cb->args[1] < max; cb->args[1]++) {
 		index = (ip_set_id_t) cb->args[1];
 		set = ip_set_list[index];
@@ -1038,8 +1039,8 @@
 		 * so that lists (unions of sets) are dumped last.
 		 */
 		if (cb->args[0] != DUMP_ONE &&
-		    !((cb->args[0] == DUMP_ALL) ^
-		      (set->type->features & IPSET_DUMP_LAST)))
+		    ((cb->args[0] == DUMP_ALL) ==
+		     !!(set->type->features & IPSET_DUMP_LAST)))
 			continue;
 		pr_debug("List set: %s\n", set->name);
 		if (!cb->args[2]) {
@@ -1083,6 +1084,12 @@
 			goto release_refcount;
 		}
 	}
+	/* If we dump all sets, continue with dumping last ones */
+	if (cb->args[0] == DUMP_ALL) {
+		cb->args[0] = DUMP_LAST;
+		cb->args[1] = 0;
+		goto dump_last;
+	}
 	goto out;
 
 nla_put_failure:
@@ -1093,11 +1100,6 @@
 		pr_debug("release set %s\n", ip_set_list[index]->name);
 		ip_set_put_byindex(index);
 	}
-
-	/* If we dump all sets, continue with dumping last ones */
-	if (cb->args[0] == DUMP_ALL && cb->args[1] >= max && !cb->args[2])
-		cb->args[0] = DUMP_LAST;
-
 out:
 	if (nlh) {
 		nlmsg_end(skb, nlh);
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 061d48c..b3babae 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -81,6 +81,7 @@
 	if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) {
 		pr_warning("Protocol error: set match dimension "
 			   "is over the limit!\n");
+		ip_set_nfnl_put(info->match_set.index);
 		return -ERANGE;
 	}
 
@@ -135,6 +136,8 @@
 		if (index == IPSET_INVALID_ID) {
 			pr_warning("Cannot find del_set index %u as target\n",
 				   info->del_set.index);
+			if (info->add_set.index != IPSET_INVALID_ID)
+				ip_set_nfnl_put(info->add_set.index);
 			return -ENOENT;
 		}
 	}
@@ -142,6 +145,10 @@
 	    info->del_set.u.flags[IPSET_DIM_MAX-1] != 0) {
 		pr_warning("Protocol error: SET target dimension "
 			   "is over the limit!\n");
+		if (info->add_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(info->add_set.index);
+		if (info->del_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(info->del_set.index);
 		return -ERANGE;
 	}
 
@@ -192,6 +199,7 @@
 	if (info->match_set.dim > IPSET_DIM_MAX) {
 		pr_warning("Protocol error: set match dimension "
 			   "is over the limit!\n");
+		ip_set_nfnl_put(info->match_set.index);
 		return -ERANGE;
 	}
 
@@ -219,7 +227,7 @@
 	if (info->del_set.index != IPSET_INVALID_ID)
 		ip_set_del(info->del_set.index,
 			   skb, par->family,
-			   info->add_set.dim,
+			   info->del_set.dim,
 			   info->del_set.flags);
 
 	return XT_CONTINUE;
@@ -245,13 +253,19 @@
 		if (index == IPSET_INVALID_ID) {
 			pr_warning("Cannot find del_set index %u as target\n",
 				   info->del_set.index);
+			if (info->add_set.index != IPSET_INVALID_ID)
+				ip_set_nfnl_put(info->add_set.index);
 			return -ENOENT;
 		}
 	}
 	if (info->add_set.dim > IPSET_DIM_MAX ||
-	    info->del_set.flags > IPSET_DIM_MAX) {
+	    info->del_set.dim > IPSET_DIM_MAX) {
 		pr_warning("Protocol error: SET target dimension "
 			   "is over the limit!\n");
+		if (info->add_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(info->add_set.index);
+		if (info->del_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(info->del_set.index);
 		return -ERANGE;
 	}
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 0698cad..1a21c57 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -569,6 +569,8 @@
 		sctp_assoc_set_primary(asoc, transport);
 	if (asoc->peer.active_path == peer)
 		asoc->peer.active_path = transport;
+	if (asoc->peer.retran_path == peer)
+		asoc->peer.retran_path = transport;
 	if (asoc->peer.last_data_from == peer)
 		asoc->peer.last_data_from = transport;
 
@@ -1323,6 +1325,8 @@
 
 	if (t)
 		asoc->peer.retran_path = t;
+	else
+		t = asoc->peer.retran_path;
 
 	SCTP_DEBUG_PRINTK_IPADDR("sctp_assoc_update_retran_path:association"
 				 " %p addr: ",
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 17d1dcb..4165382 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -163,6 +163,7 @@
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
+	attr->inherit		= !no_inherit;
 	attr->read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
 				  PERF_FORMAT_TOTAL_TIME_RUNNING |
 				  PERF_FORMAT_ID;
@@ -251,6 +252,9 @@
 {
 	struct perf_evsel *pos;
 
+	if (evlist->cpus->map[0] < 0)
+		no_inherit = true;
+
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct perf_event_attr *attr = &pos->attr;
 		/*
@@ -271,8 +275,7 @@
 retry_sample_id:
 		attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 try_again:
-		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
-				     !no_inherit) < 0) {
+		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e2109f9..03f0e45 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -167,16 +167,17 @@
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
 				    PERF_FORMAT_TOTAL_TIME_RUNNING;
 
-	if (system_wide)
-		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false, false);
-
 	attr->inherit = !no_inherit;
+
+	if (system_wide)
+		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false);
+
 	if (target_pid == -1 && target_tid == -1) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
 
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false, false);
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false);
 }
 
 /*
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 1b2106c..11e3c84 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -290,7 +290,7 @@
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open_per_thread(evsel, threads, false, false) < 0) {
+	if (perf_evsel__open_per_thread(evsel, threads, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -303,7 +303,7 @@
 	}
 
 	if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
-		pr_debug("perf_evsel__open_read_on_cpu\n");
+		pr_debug("perf_evsel__read_on_cpu\n");
 		goto out_close_fd;
 	}
 
@@ -365,7 +365,7 @@
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open(evsel, cpus, threads, false, false) < 0) {
+	if (perf_evsel__open(evsel, cpus, threads, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -418,7 +418,7 @@
 			continue;
 
 		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
-			pr_debug("perf_evsel__open_read_on_cpu\n");
+			pr_debug("perf_evsel__read_on_cpu\n");
 			err = -1;
 			break;
 		}
@@ -529,7 +529,7 @@
 
 		perf_evlist__add(evlist, evsels[i]);
 
-		if (perf_evsel__open(evsels[i], cpus, threads, false, false) < 0) {
+		if (perf_evsel__open(evsels[i], cpus, threads, false) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 				 strerror(errno));
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index fc1273e..7e3d6e3 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -845,9 +845,10 @@
 		}
 
 		attr->mmap = 1;
+		attr->inherit = inherit;
 try_again:
 		if (perf_evsel__open(counter, top.evlist->cpus,
-				     top.evlist->threads, group, inherit) < 0) {
+				     top.evlist->threads, group) < 0) {
 			int err = errno;
 
 			if (err == EPERM || err == EACCES) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d852cef..45da8d1 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,6 +12,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "util.h"
+#include "debug.h"
 
 #include <sys/mman.h>
 
@@ -250,15 +251,19 @@
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
-			       int mask, int fd)
+static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+			       int cpu, int prot, int mask, int fd)
 {
 	evlist->mmap[cpu].prev = 0;
 	evlist->mmap[cpu].mask = mask;
 	evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[cpu].base == MAP_FAILED)
+	if (evlist->mmap[cpu].base == MAP_FAILED) {
+		if (evlist->cpus->map[cpu] == -1 && evsel->attr.inherit)
+			ui__warning("Inherit is not allowed on per-task "
+				    "events using mmap.\n");
 		return -1;
+	}
 
 	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
@@ -312,7 +317,8 @@
 					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
 						  FD(first_evsel, cpu, 0)) != 0)
 						goto out_unmap;
-				} else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
+				} else if (__perf_evlist__mmap(evlist, evsel, cpu,
+							       prot, mask, fd) < 0)
 					goto out_unmap;
 
 				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 662596a..d6fd59b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -175,7 +175,7 @@
 }
 
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads, bool group, bool inherit)
+			      struct thread_map *threads, bool group)
 {
 	int cpu, thread;
 	unsigned long flags = 0;
@@ -192,19 +192,6 @@
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 		int group_fd = -1;
-		/*
-		 * Don't allow mmap() of inherited per-task counters. This
-		 * would create a performance issue due to all children writing
-		 * to the same buffer.
-		 *
-		 * FIXME:
-		 * Proper fix is not to pass 'inherit' to perf_evsel__open*,
-		 * but a 'flags' parameter, with 'group' folded there as well,
-		 * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
-		 * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
-		 * set. Lets go for the minimal fix first tho.
-		 */
-		evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
 
 		for (thread = 0; thread < threads->nr; thread++) {
 
@@ -253,7 +240,7 @@
 };
 
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit)
+		     struct thread_map *threads, bool group)
 {
 	if (cpus == NULL) {
 		/* Work around old compiler warnings about strict aliasing */
@@ -263,19 +250,19 @@
 	if (threads == NULL)
 		threads = &empty_thread_map.map;
 
-	return __perf_evsel__open(evsel, cpus, threads, group, inherit);
+	return __perf_evsel__open(evsel, cpus, threads, group);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group, bool inherit)
+			     struct cpu_map *cpus, bool group)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit)
+				struct thread_map *threads, bool group)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit);
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6710ab5..f79bb2c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -81,11 +81,11 @@
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group, bool inherit);
+			     struct cpu_map *cpus, bool group);
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit);
+				struct thread_map *threads, bool group);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit);
+		     struct thread_map *threads, bool group);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index a9f2d7e..f5e3845 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -498,11 +498,11 @@
 	struct cpu_map *cpus = NULL;
 	struct thread_map *threads = NULL;
 	PyObject *pcpus = NULL, *pthreads = NULL;
-	int group = 0, overwrite = 0;
-	static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL};
+	int group = 0, inherit = 0;
+	static char *kwlist[] = {"cpus", "threads", "group", "inherit", NULL, NULL};
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
-					 &pcpus, &pthreads, &group, &overwrite))
+					 &pcpus, &pthreads, &group, &inherit))
 		return NULL;
 
 	if (pthreads != NULL)
@@ -511,7 +511,8 @@
 	if (pcpus != NULL)
 		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
 
-	if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) {
+	evsel->attr.inherit = inherit;
+	if (perf_evsel__open(evsel, cpus, threads, group) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 8c17a87..15633d6 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -256,10 +256,9 @@
 			 int refresh)
 {
 	struct objdump_line *pos, *n;
-	struct annotation *notes = symbol__annotation(sym);
+	struct annotation *notes;
 	struct annotate_browser browser = {
 		.b = {
-			.entries = &notes->src->source,
 			.refresh = ui_browser__list_head_refresh,
 			.seek	 = ui_browser__list_head_seek,
 			.write	 = annotate_browser__write,
@@ -281,6 +280,8 @@
 
 	ui_helpline__push("Press <- or ESC to exit");
 
+	notes = symbol__annotation(sym);
+
 	list_for_each_entry(pos, &notes->src->source, node) {
 		struct objdump_line_rb_node *rbpos;
 		size_t line_len = strlen(pos->line);
@@ -291,6 +292,7 @@
 		rbpos->idx = browser.b.nr_entries++;
 	}
 
+	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
 	ret = annotate_browser__run(&browser, evidx, refresh);
 	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 798efdc..5d767c6 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -851,7 +851,7 @@
 			goto out_free_stack;
 		case 'a':
 			if (browser->selection == NULL ||
-			    browser->selection->map == NULL ||
+			    browser->selection->sym == NULL ||
 			    browser->selection->map->dso->annotate_warned)
 				continue;
 			goto do_annotate;