Merge remote branch 'tip/auto-latest'

Conflicts:
	arch/x86/kernel/module.c
	include/linux/percpu.h
	net/core/dev.c

306 files changed, 9273 insertions, 7321 deletions

diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index f1c5c4bccd3e..902d3151f527 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -14,25 +14,39 @@ to /proc/cpuinfo.
 	identifier (rather than the kernel's).  The actual value is
 	architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+3) /sys/devices/system/cpu/cpuX/topology/book_id:
+
+	the book ID of cpuX. Typically it is the hardware platform's
+	identifier (rather than the kernel's).	The actual value is
+	architecture and platform dependent.
+
+4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
 	internel kernel map of cpuX's hardware threads within the same
 	core as cpuX
 
-4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
+6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+
+	internal kernel map of cpuX's hardware threads within the same
+	book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 attributes.
+drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
+#define topology_book_id(cpu)
 #define topology_thread_cpumask(cpu)
 #define topology_core_cpumask(cpu)
+#define topology_book_cpumask(cpu)
 
 The type of **_id is int.
 The type of siblings is (const) struct cpumask *.
@@ -45,6 +59,9 @@ not defined by include/asm-XXX/topology.h:
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
 
+For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
+default definitions for topology_book_id() and topology_book_cpumask().
+
 Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 076a2c02adaf..b32911be043f 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -386,34 +386,6 @@ Who:	Tejun Heo <tj@kernel.org>
 
 ----------------------------
 
-What:	Support for VMware's guest paravirtuliazation technique [VMI] will be
-	dropped.
-When:	2.6.37 or earlier.
-Why:	With the recent innovations in CPU hardware acceleration technologies
-	from Intel and AMD, VMware ran a few experiments to compare these
-	techniques to guest paravirtualization technique on VMware's platform.
-	These hardware assisted virtualization techniques have outperformed the
-	performance benefits provided by VMI in most of the workloads. VMware
-	expects that these hardware features will be ubiquitous in a couple of
-	years, as a result, VMware has started a phased retirement of this
-	feature from the hypervisor. We will be removing this feature from the
-	Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
-	technical reasons (read opportunity to remove major chunk of pvops)
-	arise.
-
-	Please note that VMI has always been an optimization and non-VMI kernels
-	still work fine on VMware's platform.
-	Latest versions of VMware's product which support VMI are,
-	Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
-	releases for these products will continue supporting VMI.
-
-	For more details about VMI retirement take a look at this,
-	http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
-
-Who:	Alok N Kataria <akataria@vmware.com>
-
-----------------------------
-
 What:	Support for lcd_switch and display_get in asus-laptop driver
 When:	March 2010
 Why:	These two features use non-standard interfaces. There are the
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b0d65f573ce4..32667b57cb0b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -455,7 +455,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			[ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
 				pxa_timer,timer3,32k_counter,timer0_1
 			[AVR32] avr32
-			[X86-32] pit,hpet,tsc,vmi-timer;
+			[X86-32] pit,hpet,tsc;
 				scx200_hrt on Geode; cyclone on IBM x440
 			[MIPS] MIPS
 			[PARISC] cr16
@@ -2158,6 +2158,11 @@ and is between 256 and 4096 characters. It is defined in the file
 			Reserves a hole at the top of the kernel virtual
 			address space.
 
+	reservelow=	[X86]
+			Format: nn[K]
+			Set the amount of memory to reserve for BIOS at
+			the bottom of the address space.
+
 	reset_devices	[KNL] Force drivers to reset the underlying device
 			during initialization.
 
diff --git a/Documentation/x86/x86_64/kernel-stacks b/Documentation/x86/x86_64/kernel-stacks
index 5ad65d51fb95..a01eec5d1d0b 100644
--- a/Documentation/x86/x86_64/kernel-stacks
+++ b/Documentation/x86/x86_64/kernel-stacks
@@ -18,9 +18,9 @@ specialized stacks contain no useful data.  The main CPU stacks are:
   Used for external hardware interrupts.  If this is the first external
   hardware interrupt (i.e. not a nested hardware interrupt) then the
   kernel switches from the current task to the interrupt stack.  Like
-  the split thread and interrupt stacks on i386 (with CONFIG_4KSTACKS),
-  this gives more room for kernel interrupt processing without having
-  to increase the size of every per thread stack.
+  the split thread and interrupt stacks on i386, this gives more room
+  for kernel interrupt processing without having to increase the size
+  of every per thread stack.
 
   The interrupt stack is also used when processing a softirq.
 
diff --git a/MAINTAINERS b/MAINTAINERS
index ed5e047a7bad..f3fc34a901e0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3280,6 +3280,12 @@ F:	drivers/net/irda/
 F:	include/net/irda/
 F:	net/irda/
 
+IRQ SUBSYSTEM
+M:	Thomas Gleixner <tglx@linutronix.de>
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git irq/core
+F:	kernel/irq/
+
 ISAPNP
 M:	Jaroslav Kysela <perex@perex.cz>
 S:	Maintained
diff --git a/Makefile b/Makefile
index 5288e3ed6e43..3ece0e3ee56a 100644
--- a/Makefile
+++ b/Makefile
@@ -598,6 +598,11 @@ KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 # conserve stack if available
 KBUILD_CFLAGS   += $(call cc-option,-fconserve-stack)
 
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
+	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
 # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
 # But warn user when we do so
 warn-assign = \
diff --git a/arch/Kconfig b/arch/Kconfig
index fe48fc7a3eba..53d7f619a1b9 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -158,4 +158,7 @@ config HAVE_PERF_EVENTS_NMI
 	  subsystem.  Also has support for calculating CPU cycle events
 	  to determine how many clock cycles in a given period.
 
+config HAVE_ARCH_JUMP_LABEL
+	bool
+
 source "kernel/gcov/Kconfig"
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 85d8e4f58c83..1cc49683fb69 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -307,7 +307,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	delta = (new_raw_count  - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
+	delta = (new_raw_count - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
 
 	/* It is possible on very rare occasions that the PMC has overflowed
 	 * but the interrupt is yet to come.  Detect and fix this situation.
@@ -402,14 +402,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
 		struct hw_perf_event *hwc = &pe->hw;
 		int idx = hwc->idx;
 
-		if (cpuc->current_idx[j] != PMC_NO_INDEX) {
-			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
-			continue;
+		if (cpuc->current_idx[j] == PMC_NO_INDEX) {
+			alpha_perf_event_set_period(pe, hwc, idx);
+			cpuc->current_idx[j] = idx;
 		}
 
-		alpha_perf_event_set_period(pe, hwc, idx);
-		cpuc->current_idx[j] = idx;
-		cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
+		if (!(hwc->state & PERF_HES_STOPPED))
+			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
 	}
 	cpuc->config = cpuc->event[0]->hw.config_base;
 }
@@ -420,12 +419,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static int alpha_pmu_enable(struct perf_event *event)
+static int alpha_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	int n0;
 	int ret;
-	unsigned long flags;
+	unsigned long irq_flags;
 
 	/*
 	 * The Sparc code has the IRQ disable first followed by the perf
@@ -435,8 +435,8 @@ static int alpha_pmu_enable(struct perf_event *event)
 	 * nevertheless we disable the PMCs first to enable a potential
 	 * final PMI to occur before we disable interrupts.
 	 */
-	perf_disable();
-	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+	local_irq_save(irq_flags);
 
 	/* Default to error to be returned */
 	ret = -EAGAIN;
@@ -455,8 +455,12 @@ static int alpha_pmu_enable(struct perf_event *event)
 		}
 	}
 
-	local_irq_restore(flags);
-	perf_enable();
+	hwc->state = PERF_HES_UPTODATE;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_STOPPED;
+
+	local_irq_restore(irq_flags);
+	perf_pmu_enable(event->pmu);
 
 	return ret;
 }
@@ -467,15 +471,15 @@ static int alpha_pmu_enable(struct perf_event *event)
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static void alpha_pmu_disable(struct perf_event *event)
+static void alpha_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	unsigned long flags;
+	unsigned long irq_flags;
 	int j;
 
-	perf_disable();
-	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+	local_irq_save(irq_flags);
 
 	for (j = 0; j < cpuc->n_events; j++) {
 		if (event == cpuc->event[j]) {
@@ -501,8 +505,8 @@ static void alpha_pmu_disable(struct perf_event *event)
 		}
 	}
 
-	local_irq_restore(flags);
-	perf_enable();
+	local_irq_restore(irq_flags);
+	perf_pmu_enable(event->pmu);
 }
 
 
@@ -514,13 +518,44 @@ static void alpha_pmu_read(struct perf_event *event)
 }
 
 
-static void alpha_pmu_unthrottle(struct perf_event *event)
+static void alpha_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		cpuc->idx_mask &= ~(1UL<<hwc->idx);
+		hwc->state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		alpha_perf_event_update(event, hwc, hwc->idx, 0);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_DISABLE, (1UL<<hwc->idx));
+}
+
+
+static void alpha_pmu_start(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+		alpha_perf_event_set_period(event, hwc, hwc->idx);
+	}
+
+	hwc->state = 0;
+
 	cpuc->idx_mask |= 1UL<<hwc->idx;
-	wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
 }
 
 
@@ -642,39 +677,36 @@ static int __hw_perf_event_init(struct perf_event *event)
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= alpha_pmu_enable,
-	.disable	= alpha_pmu_disable,
-	.read		= alpha_pmu_read,
-	.unthrottle	= alpha_pmu_unthrottle,
-};
-
-
 /*
  * Main entry point to initialise a HW performance event.
  */
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int alpha_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (!alpha_pmu)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	/* Do the real initialisation work. */
 	err = __hw_perf_event_init(event);
 
-	if (err)
-		return ERR_PTR(err);
-
-	return &pmu;
+	return err;
 }
 
-
-
 /*
  * Main entry point - enable HW performance counters.
  */
-void hw_perf_enable(void)
+static void alpha_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -700,7 +732,7 @@ void hw_perf_enable(void)
  * Main entry point - disable HW performance counters.
  */
 
-void hw_perf_disable(void)
+static void alpha_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -713,6 +745,17 @@ void hw_perf_disable(void)
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= alpha_pmu_enable,
+	.pmu_disable	= alpha_pmu_disable,
+	.event_init	= alpha_pmu_event_init,
+	.add		= alpha_pmu_add,
+	.del		= alpha_pmu_del,
+	.start		= alpha_pmu_start,
+	.stop		= alpha_pmu_stop,
+	.read		= alpha_pmu_read,
+};
+
 
 /*
  * Main entry point - don't know when this is called but it
@@ -766,7 +809,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 
 	/* la_ptr is the counter that overflowed. */
-	if (unlikely(la_ptr >= perf_max_events)) {
+	if (unlikely(la_ptr >= alpha_pmu->num_pmcs)) {
 		/* This should never occur! */
 		irq_err_count++;
 		pr_warning("PMI: silly index %ld\n", la_ptr);
@@ -807,7 +850,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 			/* Interrupts coming too quickly; "throttle" the
 			 * counter, i.e., disable it for a little while.
 			 */
-			cpuc->idx_mask &= ~(1UL<<idx);
+			alpha_pmu_stop(event, 0);
 		}
 	}
 	wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
@@ -837,6 +880,7 @@ void __init init_hw_perf_events(void)
 
 	/* And set up PMU specification */
 	alpha_pmu = &ev67_pmu;
-	perf_max_events = alpha_pmu->num_pmcs;
+
+	perf_pmu_register(&pmu);
 }
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index ecbb0288e5dd..ad19c276b10f 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -221,46 +221,56 @@ again:
 }
 
 static void
-armpmu_disable(struct perf_event *event)
+armpmu_read(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-
-	WARN_ON(idx < 0);
-
-	clear_bit(idx, cpuc->active_mask);
-	armpmu->disable(hwc, idx);
-
-	barrier();
 
-	armpmu_event_update(event, hwc, idx);
-	cpuc->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
+	/* Don't read disabled counters! */
+	if (hwc->idx < 0)
+		return;
 
-	perf_event_update_userpage(event);
+	armpmu_event_update(event, hwc, hwc->idx);
 }
 
 static void
-armpmu_read(struct perf_event *event)
+armpmu_stop(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	/* Don't read disabled counters! */
-	if (hwc->idx < 0)
+	if (!armpmu)
 		return;
 
-	armpmu_event_update(event, hwc, hwc->idx);
+	/*
+	 * ARM pmu always has to update the counter, so ignore
+	 * PERF_EF_UPDATE, see comments in armpmu_start().
+	 */
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		armpmu->disable(hwc, hwc->idx);
+		barrier(); /* why? */
+		armpmu_event_update(event, hwc, hwc->idx);
+		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	}
 }
 
 static void
-armpmu_unthrottle(struct perf_event *event)
+armpmu_start(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!armpmu)
+		return;
+
+	/*
+	 * ARM pmu always has to reprogram the period, so ignore
+	 * PERF_EF_RELOAD, see the comment below.
+	 */
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
 	/*
 	 * Set the period again. Some counters can't be stopped, so when we
-	 * were throttled we simply disabled the IRQ source and the counter
+	 * were stopped we simply disabled the IRQ source and the counter
 	 * may have been left counting. If we don't do this step then we may
 	 * get an interrupt too soon or *way* too late if the overflow has
 	 * happened since disabling.
@@ -269,14 +279,33 @@ armpmu_unthrottle(struct perf_event *event)
 	armpmu->enable(hwc, hwc->idx);
 }
 
+static void
+armpmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	WARN_ON(idx < 0);
+
+	clear_bit(idx, cpuc->active_mask);
+	armpmu_stop(event, PERF_EF_UPDATE);
+	cpuc->events[idx] = NULL;
+	clear_bit(idx, cpuc->used_mask);
+
+	perf_event_update_userpage(event);
+}
+
 static int
-armpmu_enable(struct perf_event *event)
+armpmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
 
+	perf_pmu_disable(event->pmu);
+
 	/* If we don't have a space for the counter then finish early. */
 	idx = armpmu->get_event_idx(cpuc, hwc);
 	if (idx < 0) {
@@ -293,25 +322,19 @@ armpmu_enable(struct perf_event *event)
 	cpuc->events[idx] = event;
 	set_bit(idx, cpuc->active_mask);
 
-	/* Set the period for the event. */
-	armpmu_event_set_period(event, hwc, idx);
-
-	/* Enable the event. */
-	armpmu->enable(hwc, idx);
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	if (flags & PERF_EF_START)
+		armpmu_start(event, PERF_EF_RELOAD);
 
 	/* Propagate our changes to the userspace mapping. */
 	perf_event_update_userpage(event);
 
 out:
+	perf_pmu_enable(event->pmu);
 	return err;
 }
 
-static struct pmu pmu = {
-	.enable	    = armpmu_enable,
-	.disable    = armpmu_disable,
-	.unthrottle = armpmu_unthrottle,
-	.read	    = armpmu_read,
-};
+static struct pmu pmu;
 
 static int
 validate_event(struct cpu_hw_events *cpuc,
@@ -491,20 +514,29 @@ __hw_perf_event_init(struct perf_event *event)
 	return err;
 }
 
-const struct pmu *
-hw_perf_event_init(struct perf_event *event)
+static int armpmu_event_init(struct perf_event *event)
 {
 	int err = 0;
 
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (!armpmu)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	event->destroy = hw_perf_event_destroy;
 
 	if (!atomic_inc_not_zero(&active_events)) {
-		if (atomic_read(&active_events) > perf_max_events) {
+		if (atomic_read(&active_events) > armpmu.num_events) {
 			atomic_dec(&active_events);
-			return ERR_PTR(-ENOSPC);
+			return -ENOSPC;
 		}
 
 		mutex_lock(&pmu_reserve_mutex);
@@ -518,17 +550,16 @@ hw_perf_event_init(struct perf_event *event)
 	}
 
 	if (err)
-		return ERR_PTR(err);
+		return err;
 
 	err = __hw_perf_event_init(event);
 	if (err)
 		hw_perf_event_destroy(event);
 
-	return err ? ERR_PTR(err) : &pmu;
+	return err;
 }
 
-void
-hw_perf_enable(void)
+static void armpmu_enable(struct pmu *pmu)
 {
 	/* Enable all of the perf events on hardware. */
 	int idx;
@@ -549,13 +580,23 @@ hw_perf_enable(void)
 	armpmu->start();
 }
 
-void
-hw_perf_disable(void)
+static void armpmu_disable(struct pmu *pmu)
 {
 	if (armpmu)
 		armpmu->stop();
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= armpmu_enable,
+	.pmu_disable	= armpmu_disable,
+	.event_init	= armpmu_event_init,
+	.add		= armpmu_add,
+	.del		= armpmu_del,
+	.start		= armpmu_start,
+	.stop		= armpmu_stop,
+	.read		= armpmu_read,
+};
+
 /*
  * ARMv6 Performance counter handling code.
  *
@@ -2933,14 +2974,12 @@ init_hw_perf_events(void)
 			armpmu = &armv6pmu;
 			memcpy(armpmu_perf_cache_map, armv6_perf_cache_map,
 					sizeof(armv6_perf_cache_map));
-			perf_max_events	= armv6pmu.num_events;
 			break;
 		case 0xB020:	/* ARM11mpcore */
 			armpmu = &armv6mpcore_pmu;
 			memcpy(armpmu_perf_cache_map,
 			       armv6mpcore_perf_cache_map,
 			       sizeof(armv6mpcore_perf_cache_map));
-			perf_max_events = armv6mpcore_pmu.num_events;
 			break;
 		case 0xC080:	/* Cortex-A8 */
 			armv7pmu.id = ARM_PERF_PMU_ID_CA8;
@@ -2952,7 +2991,6 @@ init_hw_perf_events(void)
 			/* Reset PMNC and read the nb of CNTx counters
 			    supported */
 			armv7pmu.num_events = armv7_reset_read_pmnc();
-			perf_max_events = armv7pmu.num_events;
 			break;
 		case 0xC090:	/* Cortex-A9 */
 			armv7pmu.id = ARM_PERF_PMU_ID_CA9;
@@ -2964,7 +3002,6 @@ init_hw_perf_events(void)
 			/* Reset PMNC and read the nb of CNTx counters
 			    supported */
 			armv7pmu.num_events = armv7_reset_read_pmnc();
-			perf_max_events = armv7pmu.num_events;
 			break;
 		}
 	/* Intel CPUs [xscale]. */
@@ -2975,13 +3012,11 @@ init_hw_perf_events(void)
 			armpmu = &xscale1pmu;
 			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
 					sizeof(xscale_perf_cache_map));
-			perf_max_events	= xscale1pmu.num_events;
 			break;
 		case 2:
 			armpmu = &xscale2pmu;
 			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
 					sizeof(xscale_perf_cache_map));
-			perf_max_events	= xscale2pmu.num_events;
 			break;
 		}
 	}
@@ -2991,9 +3026,10 @@ init_hw_perf_events(void)
 				arm_pmu_names[armpmu->id], armpmu->num_events);
 	} else {
 		pr_info("no hardware support available\n");
-		perf_max_events = -1;
 	}
 
+	perf_pmu_register(&pmu);
+
 	return 0;
 }
 arch_initcall(init_hw_perf_events);
@@ -3001,13 +3037,6 @@ arch_initcall(init_hw_perf_events);
 /*
  * Callchain handling code.
  */
-static inline void
-callchain_store(struct perf_callchain_entry *entry,
-		u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
 
 /*
  * The registers we're interested in are at the end of the variable
@@ -3039,7 +3068,7 @@ user_backtrace(struct frame_tail *tail,
 	if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail)))
 		return NULL;
 
-	callchain_store(entry, buftail.lr);
+	perf_callchain_store(entry, buftail.lr);
 
 	/*
 	 * Frame pointers should strictly progress back up the stack
@@ -3051,16 +3080,11 @@ user_backtrace(struct frame_tail *tail,
 	return buftail.fp - 1;
 }
 
-static void
-perf_callchain_user(struct pt_regs *regs,
-		    struct perf_callchain_entry *entry)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct frame_tail *tail;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-
-	if (!user_mode(regs))
-		regs = task_pt_regs(current);
 
 	tail = (struct frame_tail *)regs->ARM_fp - 1;
 
@@ -3078,56 +3102,18 @@ callchain_trace(struct stackframe *fr,
 		void *data)
 {
 	struct perf_callchain_entry *entry = data;
-	callchain_store(entry, fr->pc);
+	perf_callchain_store(entry, fr->pc);
 	return 0;
 }
 
-static void
-perf_callchain_kernel(struct pt_regs *regs,
-		      struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct stackframe fr;
 
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
 	fr.fp = regs->ARM_fp;
 	fr.sp = regs->ARM_sp;
 	fr.lr = regs->ARM_lr;
 	fr.pc = regs->ARM_pc;
 	walk_stackframe(&fr, callchain_trace, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs,
-		  struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (!current || !current->pid)
-		return;
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-
-	if (current->mm)
-		perf_callchain_user(regs, entry);
-}
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-
-struct perf_callchain_entry *
-perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry);
-
-	entry->nr = 0;
-	perf_do_callchain(regs, entry);
-	return entry;
-}
diff --git a/arch/arm/mach-bcmring/irq.c b/arch/arm/mach-bcmring/irq.c
index dc1c4939b0ce..e3152631eb37 100644
--- a/arch/arm/mach-bcmring/irq.c
+++ b/arch/arm/mach-bcmring/irq.c
@@ -67,21 +67,21 @@ static void bcmring_unmask_irq2(unsigned int irq)
 }
 
 static struct irq_chip bcmring_irq0_chip = {
-	.typename = "ARM-INTC0",
+	.name = "ARM-INTC0",
 	.ack = bcmring_mask_irq0,
 	.mask = bcmring_mask_irq0,	/* mask a specific interrupt, blocking its delivery. */
 	.unmask = bcmring_unmask_irq0,	/* unmaks an interrupt */
 };
 
 static struct irq_chip bcmring_irq1_chip = {
-	.typename = "ARM-INTC1",
+	.name = "ARM-INTC1",
 	.ack = bcmring_mask_irq1,
 	.mask = bcmring_mask_irq1,
 	.unmask = bcmring_unmask_irq1,
 };
 
 static struct irq_chip bcmring_irq2_chip = {
-	.typename = "ARM-SINTC",
+	.name = "ARM-SINTC",
 	.ack = bcmring_mask_irq2,
 	.mask = bcmring_mask_irq2,
 	.unmask = bcmring_unmask_irq2,
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 36c4553ffcce..22cbf9bad48b 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -150,6 +150,7 @@ static void __init find_limits(struct meminfo *mi,
 static void __init arm_bootmem_init(struct meminfo *mi,
 	unsigned long start_pfn, unsigned long end_pfn)
 {
+	struct memblock_region *reg;
 	unsigned int boot_pages;
 	phys_addr_t bitmap;
 	pg_data_t *pgdat;
@@ -180,13 +181,13 @@ static void __init arm_bootmem_init(struct meminfo *mi,
 	/*
 	 * Reserve the memblock reserved regions in bootmem.
 	 */
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		phys_addr_t start = memblock_start_pfn(&memblock.reserved, i);
-		if (start >= start_pfn &&
-		    memblock_end_pfn(&memblock.reserved, i) <= end_pfn)
+	for_each_memblock(reserved, reg) {
+		phys_addr_t start = memblock_region_base_pfn(reg);
+		phys_addr_t end = memblock_region_end_pfn(reg);
+		if (start >= start_pfn && end <= end_pfn)
 			reserve_bootmem_node(pgdat, __pfn_to_phys(start),
-				memblock_size_bytes(&memblock.reserved, i),
-				BOOTMEM_DEFAULT);
+					     (end - start) << PAGE_SHIFT,
+					     BOOTMEM_DEFAULT);
 	}
 }
 
@@ -237,20 +238,7 @@ static void __init arm_bootmem_free(struct meminfo *mi, unsigned long min,
 #ifndef CONFIG_SPARSEMEM
 int pfn_valid(unsigned long pfn)
 {
-	struct memblock_region *mem = &memblock.memory;
-	unsigned int left = 0, right = mem->cnt;
-
-	do {
-		unsigned int mid = (right + left) / 2;
-
-		if (pfn < memblock_start_pfn(mem, mid))
-			right = mid;
-		else if (pfn >= memblock_end_pfn(mem, mid))
-			left = mid + 1;
-		else
-			return 1;
-	} while (left < right);
-	return 0;
+	return memblock_is_memory(pfn << PAGE_SHIFT);
 }
 EXPORT_SYMBOL(pfn_valid);
 
@@ -260,10 +248,11 @@ static void arm_memory_present(void)
 #else
 static void arm_memory_present(void)
 {
-	int i;
-	for (i = 0; i < memblock.memory.cnt; i++)
-		memory_present(0, memblock_start_pfn(&memblock.memory, i),
-				  memblock_end_pfn(&memblock.memory, i));
+	struct memblock_region *reg;
+
+	for_each_memblock(memory, reg)
+		memory_present(0, memblock_region_base_pfn(reg),
+			       memblock_region_end_pfn(reg));
 }
 #endif
 
diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index 72e09eb642dd..d1fb5b2f5218 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -96,7 +96,7 @@ static int op_create_counter(int cpu, int event)
 		return ret;
 
 	pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
-						  cpu, -1,
+						  cpu, NULL,
 						  op_overflow_handler);
 
 	if (IS_ERR(pevent)) {
diff --git a/arch/arm/plat-omap/fb.c b/arch/arm/plat-omap/fb.c
index 9df58fec094c..928ef3919984 100644
--- a/arch/arm/plat-omap/fb.c
+++ b/arch/arm/plat-omap/fb.c
@@ -175,11 +175,7 @@ static int check_fbmem_region(int region_idx, struct omapfb_mem_region *rg,
 
 static int valid_sdram(unsigned long addr, unsigned long size)
 {
-	struct memblock_property res;
-
-	res.base = addr;
-	res.size = size;
-	return !memblock_find(&res) && res.base == addr && res.size == size;
+	return memblock_region_is_memory(addr, size);
 }
 
 static int reserve_sdram(unsigned long addr, unsigned long size)
diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c
index 3c71f776872c..7db26f1f082d 100644
--- a/arch/m32r/kernel/irq.c
+++ b/arch/m32r/kernel/irq.c
@@ -51,7 +51,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)
diff --git a/arch/m32r/platforms/m32104ut/setup.c b/arch/m32r/platforms/m32104ut/setup.c
index 922fdfdadeaa..402a59d7219b 100644
--- a/arch/m32r/platforms/m32104ut/setup.c
+++ b/arch/m32r/platforms/m32104ut/setup.c
@@ -65,7 +65,7 @@ static void shutdown_m32104ut_irq(unsigned int irq)
 
 static struct irq_chip m32104ut_irq_type =
 {
-	.typename = "M32104UT-IRQ",
+	.name = "M32104UT-IRQ",
 	.startup = startup_m32104ut_irq,
 	.shutdown = shutdown_m32104ut_irq,
 	.enable = enable_m32104ut_irq,
diff --git a/arch/m32r/platforms/m32700ut/setup.c b/arch/m32r/platforms/m32700ut/setup.c
index 9c1bc7487c1e..80b1a026795a 100644
--- a/arch/m32r/platforms/m32700ut/setup.c
+++ b/arch/m32r/platforms/m32700ut/setup.c
@@ -71,7 +71,7 @@ static void shutdown_m32700ut_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_irq_type =
 {
-	.typename = "M32700UT-IRQ",
+	.name = "M32700UT-IRQ",
 	.startup = startup_m32700ut_irq,
 	.shutdown = shutdown_m32700ut_irq,
 	.enable = enable_m32700ut_irq,
@@ -148,7 +148,7 @@ static void shutdown_m32700ut_pld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_pld_irq_type =
 {
-	.typename = "M32700UT-PLD-IRQ",
+	.name = "M32700UT-PLD-IRQ",
 	.startup = startup_m32700ut_pld_irq,
 	.shutdown = shutdown_m32700ut_pld_irq,
 	.enable = enable_m32700ut_pld_irq,
@@ -217,7 +217,7 @@ static void shutdown_m32700ut_lanpld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_lanpld_irq_type =
 {
-	.typename = "M32700UT-PLD-LAN-IRQ",
+	.name = "M32700UT-PLD-LAN-IRQ",
 	.startup = startup_m32700ut_lanpld_irq,
 	.shutdown = shutdown_m32700ut_lanpld_irq,
 	.enable = enable_m32700ut_lanpld_irq,
@@ -286,7 +286,7 @@ static void shutdown_m32700ut_lcdpld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_lcdpld_irq_type =
 {
-	.typename = "M32700UT-PLD-LCD-IRQ",
+	.name = "M32700UT-PLD-LCD-IRQ",
 	.startup = startup_m32700ut_lcdpld_irq,
 	.shutdown = shutdown_m32700ut_lcdpld_irq,
 	.enable = enable_m32700ut_lcdpld_irq,
diff --git a/arch/m32r/platforms/mappi/setup.c b/arch/m32r/platforms/mappi/setup.c
index fb4b17799b66..ea00c84d6b1b 100644
--- a/arch/m32r/platforms/mappi/setup.c
+++ b/arch/m32r/platforms/mappi/setup.c
@@ -65,7 +65,7 @@ static void shutdown_mappi_irq(unsigned int irq)
 
 static struct irq_chip mappi_irq_type =
 {
-	.typename = "MAPPI-IRQ",
+	.name = "MAPPI-IRQ",
 	.startup = startup_mappi_irq,
 	.shutdown = shutdown_mappi_irq,
 	.enable = enable_mappi_irq,
diff --git a/arch/m32r/platforms/mappi2/setup.c b/arch/m32r/platforms/mappi2/setup.c
index 6a65eda0a056..c049376d0270 100644
--- a/arch/m32r/platforms/mappi2/setup.c
+++ b/arch/m32r/platforms/mappi2/setup.c
@@ -72,7 +72,7 @@ static void shutdown_mappi2_irq(unsigned int irq)
 
 static struct irq_chip mappi2_irq_type =
 {
-	.typename = "MAPPI2-IRQ",
+	.name = "MAPPI2-IRQ",
 	.startup = startup_mappi2_irq,
 	.shutdown = shutdown_mappi2_irq,
 	.enable = enable_mappi2_irq,
diff --git a/arch/m32r/platforms/mappi3/setup.c b/arch/m32r/platforms/mappi3/setup.c
index 9c337aeac94b..882de25c6e8c 100644
--- a/arch/m32r/platforms/mappi3/setup.c
+++ b/arch/m32r/platforms/mappi3/setup.c
@@ -72,7 +72,7 @@ static void shutdown_mappi3_irq(unsigned int irq)
 
 static struct irq_chip mappi3_irq_type =
 {
-	.typename = "MAPPI3-IRQ",
+	.name = "MAPPI3-IRQ",
 	.startup = startup_mappi3_irq,
 	.shutdown = shutdown_mappi3_irq,
 	.enable = enable_mappi3_irq,
diff --git a/arch/m32r/platforms/oaks32r/setup.c b/arch/m32r/platforms/oaks32r/setup.c
index ed865741c38d..d11d93bf74f5 100644
--- a/arch/m32r/platforms/oaks32r/setup.c
+++ b/arch/m32r/platforms/oaks32r/setup.c
@@ -63,7 +63,7 @@ static void shutdown_oaks32r_irq(unsigned int irq)
 
 static struct irq_chip oaks32r_irq_type =
 {
-	.typename = "OAKS32R-IRQ",
+	.name = "OAKS32R-IRQ",
 	.startup = startup_oaks32r_irq,
 	.shutdown = shutdown_oaks32r_irq,
 	.enable = enable_oaks32r_irq,
diff --git a/arch/m32r/platforms/opsput/setup.c b/arch/m32r/platforms/opsput/setup.c
index 80d680657019..5f3402a2fbaf 100644
--- a/arch/m32r/platforms/opsput/setup.c
+++ b/arch/m32r/platforms/opsput/setup.c
@@ -72,7 +72,7 @@ static void shutdown_opsput_irq(unsigned int irq)
 
 static struct irq_chip opsput_irq_type =
 {
-	.typename = "OPSPUT-IRQ",
+	.name = "OPSPUT-IRQ",
 	.startup = startup_opsput_irq,
 	.shutdown = shutdown_opsput_irq,
 	.enable = enable_opsput_irq,
@@ -149,7 +149,7 @@ static void shutdown_opsput_pld_irq(unsigned int irq)
 
 static struct irq_chip opsput_pld_irq_type =
 {
-	.typename = "OPSPUT-PLD-IRQ",
+	.name = "OPSPUT-PLD-IRQ",
 	.startup = startup_opsput_pld_irq,
 	.shutdown = shutdown_opsput_pld_irq,
 	.enable = enable_opsput_pld_irq,
@@ -218,7 +218,7 @@ static void shutdown_opsput_lanpld_irq(unsigned int irq)
 
 static struct irq_chip opsput_lanpld_irq_type =
 {
-	.typename = "OPSPUT-PLD-LAN-IRQ",
+	.name = "OPSPUT-PLD-LAN-IRQ",
 	.startup = startup_opsput_lanpld_irq,
 	.shutdown = shutdown_opsput_lanpld_irq,
 	.enable = enable_opsput_lanpld_irq,
diff --git a/arch/m32r/platforms/usrv/setup.c b/arch/m32r/platforms/usrv/setup.c
index 757302660af8..1beac7a51ed4 100644
--- a/arch/m32r/platforms/usrv/setup.c
+++ b/arch/m32r/platforms/usrv/setup.c
@@ -63,7 +63,7 @@ static void shutdown_mappi_irq(unsigned int irq)
 
 static struct irq_chip mappi_irq_type =
 {
-	.typename = "M32700-IRQ",
+	.name = "M32700-IRQ",
 	.startup = startup_mappi_irq,
 	.shutdown = shutdown_mappi_irq,
 	.enable = enable_mappi_irq,
@@ -136,7 +136,7 @@ static void shutdown_m32700ut_pld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_pld_irq_type =
 {
-	.typename = "USRV-PLD-IRQ",
+	.name = "USRV-PLD-IRQ",
 	.startup = startup_m32700ut_pld_irq,
 	.shutdown = shutdown_m32700ut_pld_irq,
 	.enable = enable_m32700ut_pld_irq,
diff --git a/arch/microblaze/include/asm/memblock.h b/arch/microblaze/include/asm/memblock.h
index f9c2fa331d2a..20a8e257c77f 100644
--- a/arch/microblaze/include/asm/memblock.h
+++ b/arch/microblaze/include/asm/memblock.h
@@ -9,9 +9,6 @@
 #ifndef _ASM_MICROBLAZE_MEMBLOCK_H
 #define _ASM_MICROBLAZE_MEMBLOCK_H
 
-/* MEMBLOCK limit is OFF */
-#define MEMBLOCK_REAL_LIMIT	0xFFFFFFFF
-
 #endif /* _ASM_MICROBLAZE_MEMBLOCK_H */
 
 
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 65eb00419d19..c8437866d3b7 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -70,16 +70,16 @@ static void __init paging_init(void)
 
 void __init setup_memory(void)
 {
-	int i;
 	unsigned long map_size;
+	struct memblock_region *reg;
+
 #ifndef CONFIG_MMU
 	u32 kernel_align_start, kernel_align_size;
 
 	/* Find main memory where is the kernel */
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		memory_start = (u32) memblock.memory.region[i].base;
-		memory_end = (u32) memblock.memory.region[i].base
-				+ (u32) memblock.memory.region[i].size;
+	for_each_memblock(memory, reg) {
+		memory_start = (u32)reg->base;
+		memory_end = (u32) reg->base + reg->size;
 		if ((memory_start <= (u32)_text) &&
 					((u32)_text <= memory_end)) {
 			memory_size = memory_end - memory_start;
@@ -142,12 +142,10 @@ void __init setup_memory(void)
 	free_bootmem(memory_start, memory_size);
 
 	/* reserve allocate blocks */
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		pr_debug("reserved %d - 0x%08x-0x%08x\n", i,
-			(u32) memblock.reserved.region[i].base,
-			(u32) memblock_size_bytes(&memblock.reserved, i));
-		reserve_bootmem(memblock.reserved.region[i].base,
-			memblock_size_bytes(&memblock.reserved, i) - 1, BOOTMEM_DEFAULT);
+	for_each_memblock(reserved, reg) {
+		pr_debug("reserved - 0x%08x-0x%08x\n",
+			 (u32) reg->base, (u32) reg->size);
+		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
 	}
 #ifdef CONFIG_MMU
 	init_bootmem_done = 1;
@@ -230,7 +228,7 @@ static void mm_cmdline_setup(void)
 		if (maxmem && memory_size > maxmem) {
 			memory_size = maxmem;
 			memory_end = memory_start + memory_size;
-			memblock.memory.region[0].size = memory_size;
+			memblock.memory.regions[0].size = memory_size;
 		}
 	}
 }
@@ -273,14 +271,14 @@ asmlinkage void __init mmu_init(void)
 		machine_restart(NULL);
 	}
 
-	if ((u32) memblock.memory.region[0].size < 0x1000000) {
+	if ((u32) memblock.memory.regions[0].size < 0x1000000) {
 		printk(KERN_EMERG "Memory must be greater than 16MB\n");
 		machine_restart(NULL);
 	}
 	/* Find main memory where the kernel is */
-	memory_start = (u32) memblock.memory.region[0].base;
-	memory_end = (u32) memblock.memory.region[0].base +
-				(u32) memblock.memory.region[0].size;
+	memory_start = (u32) memblock.memory.regions[0].base;
+	memory_end = (u32) memblock.memory.regions[0].base +
+				(u32) memblock.memory.regions[0].size;
 	memory_size = memory_end - memory_start;
 
 	mm_cmdline_setup(); /* FIXME parse args from command line - not used */
diff --git a/arch/powerpc/include/asm/memblock.h b/arch/powerpc/include/asm/memblock.h
index 3c29728b56b1..43efc345065e 100644
--- a/arch/powerpc/include/asm/memblock.h
+++ b/arch/powerpc/include/asm/memblock.h
@@ -5,11 +5,4 @@
 
 #define MEMBLOCK_DBG(fmt...) udbg_printf(fmt)
 
-#ifdef CONFIG_PPC32
-extern phys_addr_t lowmem_end_addr;
-#define MEMBLOCK_REAL_LIMIT	lowmem_end_addr
-#else
-#define MEMBLOCK_REAL_LIMIT	0
-#endif
-
 #endif /* _ASM_POWERPC_MEMBLOCK_H */
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 7ebf42ed84a2..bb40a06d3b77 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -2,6 +2,8 @@
 #define _ASM_POWERPC_MMU_H_
 #ifdef __KERNEL__
 
+#include <linux/types.h>
+
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
@@ -82,6 +84,16 @@ extern unsigned int __start___mmu_ftr_fixup, __stop___mmu_ftr_fixup;
 extern void early_init_mmu(void);
 extern void early_init_mmu_secondary(void);
 
+extern void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				       phys_addr_t first_memblock_size);
+
+#ifdef CONFIG_PPC64
+/* This is our real memory area size on ppc64 server, on embedded, we
+ * make it match the size our of bolted TLB area
+ */
+extern u64 ppc64_rma_size;
+#endif /* CONFIG_PPC64 */
+
 #endif /* !__ASSEMBLY__ */
 
 /* The kernel use the constants below to index in the page sizes array.
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index a90625f9b485..8278e8bad5a0 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -923,11 +923,7 @@ initial_mmu:
 	mtspr	SPRN_PID,r0
 	sync
 
-	/* Configure and load two entries into TLB slots 62 and 63.
-	 * In case we are pinning TLBs, these are reserved in by the
-	 * other TLB functions.  If not reserving, then it doesn't
-	 * matter where they are loaded.
-	 */
+	/* Configure and load one entry into TLB slots 63 */
 	clrrwi	r4,r4,10		/* Mask off the real page number */
 	ori	r4,r4,(TLB_WR | TLB_EX)	/* Set the write and execute bits */
 
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 1e068a46e6c3..81e4438f6aa7 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -189,7 +189,7 @@ void __init allocate_pacas(void)
 	 * the first segment. On iSeries they must be within the area mapped
 	 * by the HV, which is HvPagesToMap * HVPAGESIZE bytes.
 	 */
-	limit = min(0x10000000ULL, memblock.rmo_size);
+	limit = min(0x10000000ULL, ppc64_rma_size);
 	if (firmware_has_feature(FW_FEATURE_ISERIES))
 		limit = min(limit, HvPagesToMap * HVPAGESIZE);
 
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index 95ad9dad298e..d05ae4204bbf 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -23,18 +23,6 @@
 #include "ppc32.h"
 #endif
 
-/*
- * Store another value in a callchain_entry.
- */
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	unsigned int nr = entry->nr;
-
-	if (nr < PERF_MAX_STACK_DEPTH) {
-		entry->ip[nr] = ip;
-		entry->nr = nr + 1;
-	}
-}
 
 /*
  * Is sp valid as the address of the next kernel stack frame after prev_sp?
@@ -58,8 +46,8 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
 	return 0;
 }
 
-static void perf_callchain_kernel(struct pt_regs *regs,
-				  struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -69,8 +57,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->nip);
+	perf_callchain_store(entry, regs->nip);
 
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
 		return;
@@ -89,7 +76,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			next_ip = regs->nip;
 			lr = regs->link;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_KERNEL);
+			perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 
 		} else {
 			if (level == 0)
@@ -111,7 +98,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			++level;
 		}
 
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		if (!valid_next_sp(next_sp, sp))
 			return;
 		sp = next_sp;
@@ -233,8 +220,8 @@ static int sane_signal_64_frame(unsigned long sp)
 		puc == (unsigned long) &sf->uc;
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -246,8 +233,7 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, next_ip);
+	perf_callchain_store(entry, next_ip);
 
 	for (;;) {
 		fp = (unsigned long __user *) sp;
@@ -276,14 +262,14 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 			    read_user_stack_64(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
@@ -315,8 +301,8 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	return __get_user_inatomic(*ret, ptr);
 }
 
-static inline void perf_callchain_user_64(struct pt_regs *regs,
-					  struct perf_callchain_entry *entry)
+static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
+					  struct pt_regs *regs)
 {
 }
 
@@ -435,8 +421,8 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp,
 	return mctx->mc_gregs;
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned int sp, next_sp;
 	unsigned int next_ip;
@@ -447,8 +433,7 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, next_ip);
+	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		fp = (unsigned int __user *) (unsigned long) sp;
@@ -470,45 +455,24 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 			    read_user_stack_32(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
 }
 
-/*
- * Since we can't get PMU interrupts inside a PMU interrupt handler,
- * we don't need separate irq and nmi entries here.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain);
-
-	entry->nr = 0;
-
-	if (!user_mode(regs)) {
-		perf_callchain_kernel(regs, entry);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-
-	if (regs) {
-		if (current_is_64bit())
-			perf_callchain_user_64(regs, entry);
-		else
-			perf_callchain_user_32(regs, entry);
-	}
-
-	return entry;
+	if (current_is_64bit())
+		perf_callchain_user_64(entry, regs);
+	else
+		perf_callchain_user_32(entry, regs);
 }
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index d301a30445e0..9cb4924b6c07 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -402,6 +402,9 @@ static void power_pmu_read(struct perf_event *event)
 {
 	s64 val, delta, prev;
 
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	if (!event->hw.idx)
 		return;
 	/*
@@ -517,7 +520,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0)
  * Disable all events to prevent PMU interrupts and to allow
  * events to be added or removed.
  */
-void hw_perf_disable(void)
+static void power_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -565,7 +568,7 @@ void hw_perf_disable(void)
  * If we were previously disabled and events were added, then
  * put the new config on the PMU.
  */
-void hw_perf_enable(void)
+static void power_pmu_enable(struct pmu *pmu)
 {
 	struct perf_event *event;
 	struct cpu_hw_events *cpuhw;
@@ -672,6 +675,8 @@ void hw_perf_enable(void)
 		}
 		local64_set(&event->hw.prev_count, val);
 		event->hw.idx = idx;
+		if (event->hw.state & PERF_HES_STOPPED)
+			val = 0;
 		write_pmc(idx, val);
 		perf_event_update_userpage(event);
 	}
@@ -727,7 +732,7 @@ static int collect_events(struct perf_event *group, int max_count,
  * re-enable the PMU in order to get hw_perf_enable to do the
  * actual work of reconfiguring the PMU.
  */
-static int power_pmu_enable(struct perf_event *event)
+static int power_pmu_add(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -735,7 +740,7 @@ static int power_pmu_enable(struct perf_event *event)
 	int ret = -EAGAIN;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	/*
 	 * Add the event to the list (if there is room)
@@ -749,6 +754,9 @@ static int power_pmu_enable(struct perf_event *event)
 	cpuhw->events[n0] = event->hw.config;
 	cpuhw->flags[n0] = event->hw.event_base;
 
+	if (!(ef_flags & PERF_EF_START))
+		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
@@ -769,7 +777,7 @@ nocheck:
 
 	ret = 0;
  out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
@@ -777,14 +785,14 @@ nocheck:
 /*
  * Remove a event from the PMU.
  */
-static void power_pmu_disable(struct perf_event *event)
+static void power_pmu_del(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuhw;
 	long i;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	power_pmu_read(event);
 
@@ -821,34 +829,60 @@ static void power_pmu_disable(struct perf_event *event)
 		cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE);
 	}
 
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
 /*
- * Re-enable interrupts on a event after they were throttled
- * because they were coming too fast.
+ * POWER-PMU does not support disabling individual counters, hence
+ * program their cycle counter to their max value and ignore the interrupts.
  */
-static void power_pmu_unthrottle(struct perf_event *event)
+
+static void power_pmu_start(struct perf_event *event, int ef_flags)
+{
+	unsigned long flags;
+	s64 left;
+
+	if (!event->hw.idx || !event->hw.sample_period)
+		return;
+
+	if (!(event->hw.state & PERF_HES_STOPPED))
+		return;
+
+	if (ef_flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = 0;
+	left = local64_read(&event->hw.period_left);
+	write_pmc(event->hw.idx, left);
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
+
+static void power_pmu_stop(struct perf_event *event, int ef_flags)
 {
-	s64 val, left;
 	unsigned long flags;
 
 	if (!event->hw.idx || !event->hw.sample_period)
 		return;
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
+
 	power_pmu_read(event);
-	left = event->hw.sample_period;
-	event->hw.last_period = left;
-	val = 0;
-	if (left < 0x80000000L)
-		val = 0x80000000L - left;
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
+	event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	write_pmc(event->hw.idx, 0);
+
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
@@ -857,10 +891,11 @@ static void power_pmu_unthrottle(struct perf_event *event)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-void power_pmu_start_txn(const struct pmu *pmu)
+void power_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 	cpuhw->n_txn_start = cpuhw->n_events;
 }
@@ -870,11 +905,12 @@ void power_pmu_start_txn(const struct pmu *pmu)
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-void power_pmu_cancel_txn(const struct pmu *pmu)
+void power_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -882,7 +918,7 @@ void power_pmu_cancel_txn(const struct pmu *pmu)
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-int power_pmu_commit_txn(const struct pmu *pmu)
+int power_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	long i, n;
@@ -901,19 +937,10 @@ int power_pmu_commit_txn(const struct pmu *pmu)
 		cpuhw->event[i]->hw.config = cpuhw->events[i];
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-struct pmu power_pmu = {
-	.enable		= power_pmu_enable,
-	.disable	= power_pmu_disable,
-	.read		= power_pmu_read,
-	.unthrottle	= power_pmu_unthrottle,
-	.start_txn	= power_pmu_start_txn,
-	.cancel_txn	= power_pmu_cancel_txn,
-	.commit_txn	= power_pmu_commit_txn,
-};
-
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
@@ -1014,7 +1041,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp)
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int power_pmu_event_init(struct perf_event *event)
 {
 	u64 ev;
 	unsigned long flags;
@@ -1026,25 +1053,27 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	struct cpu_hw_events *cpuhw;
 
 	if (!ppmu)
-		return ERR_PTR(-ENXIO);
+		return -ENOENT;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
 		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
-			return ERR_PTR(-EOPNOTSUPP);
+			return -EOPNOTSUPP;
 		ev = ppmu->generic_events[ev];
 		break;
 	case PERF_TYPE_HW_CACHE:
 		err = hw_perf_cache_event(event->attr.config, &ev);
 		if (err)
-			return ERR_PTR(err);
+			return err;
 		break;
 	case PERF_TYPE_RAW:
 		ev = event->attr.config;
 		break;
 	default:
-		return ERR_PTR(-EINVAL);
+		return -ENOENT;
 	}
+
 	event->hw.config_base = ev;
 	event->hw.idx = 0;
 
@@ -1081,7 +1110,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 			 */
 			ev = normal_pmc_alternative(ev, flags);
 			if (!ev)
-				return ERR_PTR(-EINVAL);
+				return -EINVAL;
 		}
 	}
 
@@ -1095,19 +1124,19 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		n = collect_events(event->group_leader, ppmu->n_counter - 1,
 				   ctrs, events, cflags);
 		if (n < 0)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 	events[n] = ev;
 	ctrs[n] = event;
 	cflags[n] = flags;
 	if (check_excludes(ctrs, cflags, n, 1))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	cpuhw = &get_cpu_var(cpu_hw_events);
 	err = power_check_constraints(cpuhw, events, cflags, n + 1);
 	put_cpu_var(cpu_hw_events);
 	if (err)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	event->hw.config = events[n];
 	event->hw.event_base = cflags[n];
@@ -1132,11 +1161,23 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	}
 	event->destroy = hw_perf_event_destroy;
 
-	if (err)
-		return ERR_PTR(err);
-	return &power_pmu;
+	return err;
 }
 
+struct pmu power_pmu = {
+	.pmu_enable	= power_pmu_enable,
+	.pmu_disable	= power_pmu_disable,
+	.event_init	= power_pmu_event_init,
+	.add		= power_pmu_add,
+	.del		= power_pmu_del,
+	.start		= power_pmu_start,
+	.stop		= power_pmu_stop,
+	.read		= power_pmu_read,
+	.start_txn	= power_pmu_start_txn,
+	.cancel_txn	= power_pmu_cancel_txn,
+	.commit_txn	= power_pmu_commit_txn,
+};
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -1149,6 +1190,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	s64 prev, delta, left;
 	int record = 0;
 
+	if (event->hw.state & PERF_HES_STOPPED) {
+		write_pmc(event->hw.idx, 0);
+		return;
+	}
+
 	/* we don't have to worry about interrupts here */
 	prev = local64_read(&event->hw.prev_count);
 	delta = (val - prev) & 0xfffffffful;
@@ -1171,6 +1217,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			val = 0x80000000LL - left;
 	}
 
+	write_pmc(event->hw.idx, val);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+
 	/*
 	 * Finally record data if requested.
 	 */
@@ -1183,23 +1234,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR)
 			perf_get_data_addr(regs, &data.addr);
 
-		if (perf_event_overflow(event, nmi, &data, regs)) {
-			/*
-			 * Interrupts are coming too fast - throttle them
-			 * by setting the event to 0, so it will be
-			 * at least 2^30 cycles until the next interrupt
-			 * (assuming each event counts at most 2 counts
-			 * per cycle).
-			 */
-			val = 0;
-			left = ~0ULL >> 1;
-		}
+		if (perf_event_overflow(event, nmi, &data, regs))
+			power_pmu_stop(event, 0);
 	}
-
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
-	perf_event_update_userpage(event);
 }
 
 /*
@@ -1342,6 +1379,7 @@ int register_power_pmu(struct power_pmu *pmu)
 		freeze_events_kernel = MMCR0_FCHV;
 #endif /* CONFIG_PPC64 */
 
+	perf_pmu_register(&power_pmu);
 	perf_cpu_notifier(power_pmu_notifier);
 
 	return 0;
diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c
index 1ba45471ae43..7ecca59ddf77 100644
--- a/arch/powerpc/kernel/perf_event_fsl_emb.c
+++ b/arch/powerpc/kernel/perf_event_fsl_emb.c
@@ -156,6 +156,9 @@ static void fsl_emb_pmu_read(struct perf_event *event)
 {
 	s64 val, delta, prev;
 
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	/*
 	 * Performance monitor interrupts come even when interrupts
 	 * are soft-disabled, as long as interrupts are hard-enabled.
@@ -177,7 +180,7 @@ static void fsl_emb_pmu_read(struct perf_event *event)
  * Disable all events to prevent PMU interrupts and to allow
  * events to be added or removed.
  */
-void hw_perf_disable(void)
+static void fsl_emb_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -216,7 +219,7 @@ void hw_perf_disable(void)
  * If we were previously disabled and events were added, then
  * put the new config on the PMU.
  */
-void hw_perf_enable(void)
+static void fsl_emb_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -262,8 +265,8 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-/* perf must be disabled, context locked on entry */
-static int fsl_emb_pmu_enable(struct perf_event *event)
+/* context locked on entry */
+static int fsl_emb_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuhw;
 	int ret = -EAGAIN;
@@ -271,6 +274,7 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
 	u64 val;
 	int i;
 
+	perf_pmu_disable(event->pmu);
 	cpuhw = &get_cpu_var(cpu_hw_events);
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED)
@@ -301,6 +305,12 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
 			val = 0x80000000L - left;
 	}
 	local64_set(&event->hw.prev_count, val);
+
+	if (!(flags & PERF_EF_START)) {
+		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+		val = 0;
+	}
+
 	write_pmc(i, val);
 	perf_event_update_userpage(event);
 
@@ -310,15 +320,17 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
 	ret = 0;
  out:
 	put_cpu_var(cpu_hw_events);
+	perf_pmu_enable(event->pmu);
 	return ret;
 }
 
-/* perf must be disabled, context locked on entry */
-static void fsl_emb_pmu_disable(struct perf_event *event)
+/* context locked on entry */
+static void fsl_emb_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuhw;
 	int i = event->hw.idx;
 
+	perf_pmu_disable(event->pmu);
 	if (i < 0)
 		goto out;
 
@@ -346,44 +358,57 @@ static void fsl_emb_pmu_disable(struct perf_event *event)
 	cpuhw->n_events--;
 
  out:
+	perf_pmu_enable(event->pmu);
 	put_cpu_var(cpu_hw_events);
 }
 
-/*
- * Re-enable interrupts on a event after they were throttled
- * because they were coming too fast.
- *
- * Context is locked on entry, but perf is not disabled.
- */
-static void fsl_emb_pmu_unthrottle(struct perf_event *event)
+static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags)
 {
-	s64 val, left;
 	unsigned long flags;
+	s64 left;
 
 	if (event->hw.idx < 0 || !event->hw.sample_period)
 		return;
+
+	if (!(event->hw.state & PERF_HES_STOPPED))
+		return;
+
+	if (ef_flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
 	local_irq_save(flags);
-	perf_disable();
-	fsl_emb_pmu_read(event);
-	left = event->hw.sample_period;
-	event->hw.last_period = left;
-	val = 0;
-	if (left < 0x80000000L)
-		val = 0x80000000L - left;
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = 0;
+	left = local64_read(&event->hw.period_left);
+	write_pmc(event->hw.idx, left);
+
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
-static struct pmu fsl_emb_pmu = {
-	.enable		= fsl_emb_pmu_enable,
-	.disable	= fsl_emb_pmu_disable,
-	.read		= fsl_emb_pmu_read,
-	.unthrottle	= fsl_emb_pmu_unthrottle,
-};
+static void fsl_emb_pmu_stop(struct perf_event *event, int ef_flags)
+{
+	unsigned long flags;
+
+	if (event->hw.idx < 0 || !event->hw.sample_period)
+		return;
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	fsl_emb_pmu_read(event);
+	event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	write_pmc(event->hw.idx, 0);
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
 
 /*
  * Release the PMU if this is the last perf_event.
@@ -428,7 +453,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp)
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int fsl_emb_pmu_event_init(struct perf_event *event)
 {
 	u64 ev;
 	struct perf_event *events[MAX_HWEVENTS];
@@ -441,14 +466,14 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
 		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
-			return ERR_PTR(-EOPNOTSUPP);
+			return -EOPNOTSUPP;
 		ev = ppmu->generic_events[ev];
 		break;
 
 	case PERF_TYPE_HW_CACHE:
 		err = hw_perf_cache_event(event->attr.config, &ev);
 		if (err)
-			return ERR_PTR(err);
+			return err;
 		break;
 
 	case PERF_TYPE_RAW:
@@ -456,12 +481,12 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		break;
 
 	default:
-		return ERR_PTR(-EINVAL);
+		return -ENOENT;
 	}
 
 	event->hw.config = ppmu->xlate_event(ev);
 	if (!(event->hw.config & FSL_EMB_EVENT_VALID))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	/*
 	 * If this is in a group, check if it can go on with all the
@@ -473,7 +498,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		n = collect_events(event->group_leader,
 		                   ppmu->n_counter - 1, events);
 		if (n < 0)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) {
@@ -484,7 +509,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		}
 
 		if (num_restricted >= ppmu->n_restricted)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 
 	event->hw.idx = -1;
@@ -497,7 +522,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	if (event->attr.exclude_kernel)
 		event->hw.config_base |= PMLCA_FCS;
 	if (event->attr.exclude_idle)
-		return ERR_PTR(-ENOTSUPP);
+		return -ENOTSUPP;
 
 	event->hw.last_period = event->hw.sample_period;
 	local64_set(&event->hw.period_left, event->hw.last_period);
@@ -523,11 +548,20 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	}
 	event->destroy = hw_perf_event_destroy;
 
-	if (err)
-		return ERR_PTR(err);
-	return &fsl_emb_pmu;
+	return err;
 }
 
+static struct pmu fsl_emb_pmu = {
+	.pmu_enable	= fsl_emb_pmu_enable,
+	.pmu_disable	= fsl_emb_pmu_disable,
+	.event_init	= fsl_emb_pmu_event_init,
+	.add		= fsl_emb_pmu_add,
+	.del		= fsl_emb_pmu_del,
+	.start		= fsl_emb_pmu_start,
+	.stop		= fsl_emb_pmu_stop,
+	.read		= fsl_emb_pmu_read,
+};
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -540,6 +574,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	s64 prev, delta, left;
 	int record = 0;
 
+	if (event->hw.state & PERF_HES_STOPPED) {
+		write_pmc(event->hw.idx, 0);
+		return;
+	}
+
 	/* we don't have to worry about interrupts here */
 	prev = local64_read(&event->hw.prev_count);
 	delta = (val - prev) & 0xfffffffful;
@@ -562,6 +601,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			val = 0x80000000LL - left;
 	}
 
+	write_pmc(event->hw.idx, val);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+
 	/*
 	 * Finally record data if requested.
 	 */
@@ -571,23 +615,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		perf_sample_data_init(&data, 0);
 		data.period = event->hw.last_period;
 
-		if (perf_event_overflow(event, nmi, &data, regs)) {
-			/*
-			 * Interrupts are coming too fast - throttle them
-			 * by setting the event to 0, so it will be
-			 * at least 2^30 cycles until the next interrupt
-			 * (assuming each event counts at most 2 counts
-			 * per cycle).
-			 */
-			val = 0;
-			left = ~0ULL >> 1;
-		}
+		if (perf_event_overflow(event, nmi, &data, regs))
+			fsl_emb_pmu_stop(event, 0);
 	}
-
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
-	perf_event_update_userpage(event);
 }
 
 static void perf_event_interrupt(struct pt_regs *regs)
@@ -651,5 +681,7 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu)
 	pr_info("%s performance monitor hardware support registered\n",
 		pmu->name);
 
+	perf_pmu_register(&fsl_emb_pmu);
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index fed9bf6187d1..c3c6a8857544 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -66,6 +66,7 @@
 int __initdata iommu_is_off;
 int __initdata iommu_force_on;
 unsigned long tce_alloc_start, tce_alloc_end;
+u64 ppc64_rma_size;
 #endif
 
 static int __init early_parse_mem(char *p)
@@ -98,7 +99,7 @@ static void __init move_device_tree(void)
 
 	if ((memory_limit && (start + size) > memory_limit) ||
 			overlaps_crashkernel(start, size)) {
-		p = __va(memblock_alloc_base(size, PAGE_SIZE, memblock.rmo_size));
+		p = __va(memblock_alloc(size, PAGE_SIZE));
 		memcpy(p, initial_boot_params, size);
 		initial_boot_params = (struct boot_param_header *)p;
 		DBG("Moved device tree to 0x%p\n", p);
@@ -492,7 +493,7 @@ static int __init early_init_dt_scan_memory_ppc(unsigned long node,
 
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
-#if defined(CONFIG_PPC64)
+#ifdef CONFIG_PPC64
 	if (iommu_is_off) {
 		if (base >= 0x80000000ul)
 			return;
@@ -501,9 +502,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	}
 #endif
 
-	memblock_add(base, size);
-
+	/* First MEMBLOCK added, do some special initializations */
+	if (memstart_addr == ~(phys_addr_t)0)
+		setup_initial_memory_limit(base, size);
 	memstart_addr = min((u64)memstart_addr, base);
+
+	/* Add the chunk to the MEMBLOCK list */
+	memblock_add(base, size);
 }
 
 u64 __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
@@ -655,7 +660,6 @@ static void __init phyp_dump_reserve_mem(void)
 static inline void __init phyp_dump_reserve_mem(void) {}
 #endif /* CONFIG_PHYP_DUMP  && CONFIG_PPC_RTAS */
 
-
 void __init early_init_devtree(void *params)
 {
 	phys_addr_t limit;
@@ -683,6 +687,7 @@ void __init early_init_devtree(void *params)
 
 	/* Scan memory nodes and rebuild MEMBLOCKs */
 	memblock_init();
+
 	of_scan_flat_dt(early_init_dt_scan_root, NULL);
 	of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
 
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 41048de3c6c3..7333fdbf857b 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -969,7 +969,7 @@ void __init rtas_initialize(void)
 	 */
 #ifdef CONFIG_PPC64
 	if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR)) {
-		rtas_region = min(memblock.rmo_size, RTAS_INSTANTIATE_MAX);
+		rtas_region = min(ppc64_rma_size, RTAS_INSTANTIATE_MAX);
 		ibm_suspend_me_token = rtas_token("ibm,suspend-me");
 	}
 #endif
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 93666f9cabf1..b86111fe9257 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -246,7 +246,7 @@ static void __init irqstack_early_init(void)
 	unsigned int i;
 
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
-	 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
+	 * as the memblock is limited to lowmem by default */
 	for_each_possible_cpu(i) {
 		softirq_ctx[i] = (struct thread_info *)
 			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index e72690ec9b87..2a178b0ebcdf 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -486,7 +486,7 @@ static void __init emergency_stack_init(void)
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
 	 */
-	limit = min(slb0_limit(), memblock.rmo_size);
+	limit = min(slb0_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		unsigned long sp;
diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c
index 1dc2fa5ce1bd..5810967511d4 100644
--- a/arch/powerpc/mm/40x_mmu.c
+++ b/arch/powerpc/mm/40x_mmu.c
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -47,6 +48,7 @@
 #include <asm/bootx.h>
 #include <asm/machdep.h>
 #include <asm/setup.h>
+
 #include "mmu_decl.h"
 
 extern int __map_without_ltlbs;
@@ -139,8 +141,19 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
 	 * coverage with normal-sized pages (or other reasons) do not
 	 * attempt to allocate outside the allowed range.
 	 */
-
-	__initial_memory_limit_addr = memstart_addr + mapped;
+	memblock_set_current_limit(mapped);
 
 	return mapped;
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 40x can only access 16MB at the moment (see head_40x.S) */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
+}
diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c
index d8c6efb32bc6..024acab588fd 100644
--- a/arch/powerpc/mm/44x_mmu.c
+++ b/arch/powerpc/mm/44x_mmu.c
@@ -24,6 +24,8 @@
  */
 
 #include <linux/init.h>
+#include <linux/memblock.h>
+
 #include <asm/mmu.h>
 #include <asm/system.h>
 #include <asm/page.h>
@@ -213,6 +215,18 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
 	return total_lowmem;
 }
 
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 44x has a 256M TLB entry pinned at boot */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, PPC_PIN_SIZE));
+}
+
 #ifdef CONFIG_SMP
 void __cpuinit mmu_init_secondary(int cpu)
 {
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 4b66a1ece6d8..cde270847e7c 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -40,6 +40,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -213,5 +214,14 @@ void __init adjust_total_lowmem(void)
 	pr_cont("%lu Mb, residual: %dMb\n", tlbcam_sz(tlbcam_index - 1) >> 20,
 	        (unsigned int)((total_lowmem - __max_low_memory) >> 20));
 
-	__initial_memory_limit_addr = memstart_addr + __max_low_memory;
+	memblock_set_current_limit(memstart_addr + __max_low_memory);
+}
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	phys_addr_t limit = first_memblock_base + first_memblock_size;
+
+	/* 64M mapped initially according to head_fsl_booke.S */
+	memblock_set_current_limit(min_t(u64, limit, 0x04000000));
 }
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 09dffe6efa46..83f534d862db 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -588,7 +588,7 @@ static void __init htab_initialize(void)
 	unsigned long pteg_count;
 	unsigned long prot;
 	unsigned long base = 0, size = 0, limit;
-	int i;
+	struct memblock_region *reg;
 
 	DBG(" -> htab_initialize()\n");
 
@@ -625,7 +625,7 @@ static void __init htab_initialize(void)
 		if (machine_is(cell))
 			limit = 0x80000000;
 		else
-			limit = 0;
+			limit = MEMBLOCK_ALLOC_ANYWHERE;
 
 		table = memblock_alloc_base(htab_size_bytes, htab_size_bytes, limit);
 
@@ -649,7 +649,7 @@ static void __init htab_initialize(void)
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	linear_map_hash_slots = __va(memblock_alloc_base(linear_map_hash_count,
-						    1, memblock.rmo_size));
+						    1, ppc64_rma_size));
 	memset(linear_map_hash_slots, 0, linear_map_hash_count);
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
@@ -659,9 +659,9 @@ static void __init htab_initialize(void)
 	 */
 
 	/* create bolted the linear mapping in the hash table */
-	for (i=0; i < memblock.memory.cnt; i++) {
-		base = (unsigned long)__va(memblock.memory.region[i].base);
-		size = memblock.memory.region[i].size;
+	for_each_memblock(memory, reg) {
+		base = (unsigned long)__va(reg->base);
+		size = reg->size;
 
 		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
 		    base, size, prot);
@@ -696,7 +696,8 @@ static void __init htab_initialize(void)
 #endif /* CONFIG_U3_DART */
 		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
 				prot, mmu_linear_psize, mmu_kernel_ssize));
-       }
+	}
+	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 
 	/*
 	 * If we have a memory_limit and we've allocated TCEs then we need to
@@ -1247,3 +1248,23 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 	local_irq_restore(flags);
 }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* On LPAR systems, the first entry is our RMA region,
+	 * non-LPAR 64-bit hash MMU systems don't have a limitation
+	 * on real mode access, but using the first entry works well
+	 * enough. We also clamp it to 1G to avoid some funky things
+	 * such as RTAS bugs etc...
+	 */
+	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+
+	/* Finally limit subsequent allocations */
+	memblock_set_current_limit(ppc64_rma_size);
+}
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 6a6975dc2654..742da43b4ab6 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -92,12 +92,6 @@ int __allow_ioremap_reserved;
 unsigned long __max_low_memory = MAX_LOW_MEM;
 
 /*
- * address of the limit of what is accessible with initial MMU setup -
- * 256MB usually, but only 16MB on 601.
- */
-phys_addr_t __initial_memory_limit_addr = (phys_addr_t)0x10000000;
-
-/*
  * Check for command-line options that affect what MMU_init will do.
  */
 void MMU_setup(void)
@@ -126,13 +120,6 @@ void __init MMU_init(void)
 	if (ppc_md.progress)
 		ppc_md.progress("MMU:enter", 0x111);
 
-	/* 601 can only access 16MB at the moment */
-	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
-		__initial_memory_limit_addr = 0x01000000;
-	/* 8xx can only access 8MB at the moment */
-	if (PVR_VER(mfspr(SPRN_PVR)) == 0x50)
-		__initial_memory_limit_addr = 0x00800000;
-
 	/* parse args from command line */
 	MMU_setup();
 
@@ -190,20 +177,18 @@ void __init MMU_init(void)
 #ifdef CONFIG_BOOTX_TEXT
 	btext_unmap();
 #endif
+
+	/* Shortly after that, the entire linear mapping will be available */
+	memblock_set_current_limit(lowmem_end_addr);
 }
 
 /* This is only called until mem_init is done. */
 void __init *early_get_page(void)
 {
-	void *p;
-
-	if (init_bootmem_done) {
-		p = alloc_bootmem_pages(PAGE_SIZE);
-	} else {
-		p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
-					__initial_memory_limit_addr));
-	}
-	return p;
+	if (init_bootmem_done)
+		return alloc_bootmem_pages(PAGE_SIZE);
+	else
+		return __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 }
 
 /* Free up now-unused memory */
@@ -252,3 +237,17 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
+
+#ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 8xx can only access 8MB at the moment */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
+}
+#endif /* CONFIG_8xx */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index ace85fa74b29..6374b2196a17 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -330,3 +330,4 @@ int __meminit vmemmap_populate(struct page *start_page,
 	return 0;
 }
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1a84a8d00005..f661f6c527da 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -82,18 +82,11 @@ int page_is_ram(unsigned long pfn)
 	return pfn < max_pfn;
 #else
 	unsigned long paddr = (pfn << PAGE_SHIFT);
-	int i;
-	for (i=0; i < memblock.memory.cnt; i++) {
-		unsigned long base;
+	struct memblock_region *reg;
 
-		base = memblock.memory.region[i].base;
-
-		if ((paddr >= base) &&
-			(paddr < (base + memblock.memory.region[i].size))) {
+	for_each_memblock(memory, reg)
+		if (paddr >= reg->base && paddr < (reg->base + reg->size))
 			return 1;
-		}
-	}
-
 	return 0;
 #endif
 }
@@ -149,23 +142,19 @@ int
 walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 		void *arg, int (*func)(unsigned long, unsigned long, void *))
 {
-	struct memblock_property res;
-	unsigned long pfn, len;
-	u64 end;
+	struct memblock_region *reg;
+	unsigned long end_pfn = start_pfn + nr_pages;
+	unsigned long tstart, tend;
 	int ret = -1;
 
-	res.base = (u64) start_pfn << PAGE_SHIFT;
-	res.size = (u64) nr_pages << PAGE_SHIFT;
-
-	end = res.base + res.size - 1;
-	while ((res.base < end) && (memblock_find(&res) >= 0)) {
-		pfn = (unsigned long)(res.base >> PAGE_SHIFT);
-		len = (unsigned long)(res.size >> PAGE_SHIFT);
-		ret = (*func)(pfn, len, arg);
+	for_each_memblock(memory, reg) {
+		tstart = max(start_pfn, memblock_region_base_pfn(reg));
+		tend = min(end_pfn, memblock_region_end_pfn(reg));
+		if (tstart >= tend)
+			continue;
+		ret = (*func)(tstart, tend - tstart, arg);
 		if (ret)
 			break;
-		res.base += (res.size + 1);
-		res.size = (end - res.base + 1);
 	}
 	return ret;
 }
@@ -179,9 +168,9 @@ EXPORT_SYMBOL_GPL(walk_system_ram_range);
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 void __init do_init_bootmem(void)
 {
-	unsigned long i;
 	unsigned long start, bootmap_pages;
 	unsigned long total_pages;
+	struct memblock_region *reg;
 	int boot_mapsize;
 
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
@@ -204,10 +193,10 @@ void __init do_init_bootmem(void)
 	boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn);
 
 	/* Add active regions with valid PFNs */
-	for (i = 0; i < memblock.memory.cnt; i++) {
+	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+		start_pfn = memblock_region_base_pfn(reg);
+		end_pfn = memblock_region_end_pfn(reg);
 		add_active_range(0, start_pfn, end_pfn);
 	}
 
@@ -218,29 +207,21 @@ void __init do_init_bootmem(void)
 	free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT);
 
 	/* reserve the sections we're already using */
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long addr = memblock.reserved.region[i].base +
-				     memblock_size_bytes(&memblock.reserved, i) - 1;
-		if (addr < lowmem_end_addr)
-			reserve_bootmem(memblock.reserved.region[i].base,
-					memblock_size_bytes(&memblock.reserved, i),
-					BOOTMEM_DEFAULT);
-		else if (memblock.reserved.region[i].base < lowmem_end_addr) {
-			unsigned long adjusted_size = lowmem_end_addr -
-				      memblock.reserved.region[i].base;
-			reserve_bootmem(memblock.reserved.region[i].base,
-					adjusted_size, BOOTMEM_DEFAULT);
+	for_each_memblock(reserved, reg) {
+		unsigned long top = reg->base + reg->size - 1;
+		if (top < lowmem_end_addr)
+			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+		else if (reg->base < lowmem_end_addr) {
+			unsigned long trunc_size = lowmem_end_addr - reg->base;
+			reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
 		}
 	}
 #else
 	free_bootmem_with_active_regions(0, max_pfn);
 
 	/* reserve the sections we're already using */
-	for (i = 0; i < memblock.reserved.cnt; i++)
-		reserve_bootmem(memblock.reserved.region[i].base,
-				memblock_size_bytes(&memblock.reserved, i),
-				BOOTMEM_DEFAULT);
-
+	for_each_memblock(reserved, reg)
+		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
 #endif
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
@@ -251,22 +232,15 @@ void __init do_init_bootmem(void)
 /* mark pages that don't exist as nosave */
 static int __init mark_nonram_nosave(void)
 {
-	unsigned long memblock_next_region_start_pfn,
-		      memblock_region_max_pfn;
-	int i;
-
-	for (i = 0; i < memblock.memory.cnt - 1; i++) {
-		memblock_region_max_pfn =
-			(memblock.memory.region[i].base >> PAGE_SHIFT) +
-			(memblock.memory.region[i].size >> PAGE_SHIFT);
-		memblock_next_region_start_pfn =
-			memblock.memory.region[i+1].base >> PAGE_SHIFT;
-
-		if (memblock_region_max_pfn < memblock_next_region_start_pfn)
-			register_nosave_region(memblock_region_max_pfn,
-					       memblock_next_region_start_pfn);
+	struct memblock_region *reg, *prev = NULL;
+
+	for_each_memblock(memory, reg) {
+		if (prev &&
+		    memblock_region_end_pfn(prev) < memblock_region_base_pfn(reg))
+			register_nosave_region(memblock_region_end_pfn(prev),
+					       memblock_region_base_pfn(reg));
+		prev = reg;
 	}
-
 	return 0;
 }
 
@@ -327,7 +301,7 @@ void __init mem_init(void)
 		swiotlb_init(1);
 #endif
 
-	num_physpages = memblock.memory.size >> PAGE_SHIFT;
+	num_physpages = memblock_phys_mem_size() >> PAGE_SHIFT;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 002878ccf90b..066fb443ba5a 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -802,16 +802,17 @@ static void __init setup_nonnuma(void)
 	unsigned long top_of_ram = memblock_end_of_DRAM();
 	unsigned long total_ram = memblock_phys_mem_size();
 	unsigned long start_pfn, end_pfn;
-	unsigned int i, nid = 0;
+	unsigned int nid = 0;
+	struct memblock_region *reg;
 
 	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
 	       top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
 
-	for (i = 0; i < memblock.memory.cnt; ++i) {
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+	for_each_memblock(memory, reg) {
+		start_pfn = memblock_region_base_pfn(reg);
+		end_pfn = memblock_region_end_pfn(reg);
 
 		fake_numa_create_new_node(end_pfn, &nid);
 		add_active_range(nid, start_pfn, end_pfn);
@@ -947,11 +948,11 @@ static struct notifier_block __cpuinitdata ppc64_numa_nb = {
 static void mark_reserved_regions_for_nid(int nid)
 {
 	struct pglist_data *node = NODE_DATA(nid);
-	int i;
+	struct memblock_region *reg;
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long physbase = memblock.reserved.region[i].base;
-		unsigned long size = memblock.reserved.region[i].size;
+	for_each_memblock(reserved, reg) {
+		unsigned long physbase = reg->base;
+		unsigned long size = reg->size;
 		unsigned long start_pfn = physbase >> PAGE_SHIFT;
 		unsigned long end_pfn = PFN_UP(physbase + size);
 		struct node_active_region node_ar;
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index f8a01829d64f..11571e118831 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -223,8 +223,7 @@ void __init MMU_init_hw(void)
 	 * Find some memory for the hash table.
 	 */
 	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
-	Hash = __va(memblock_alloc_base(Hash_size, Hash_size,
-				   __initial_memory_limit_addr));
+	Hash = __va(memblock_alloc(Hash_size, Hash_size));
 	cacheable_memzero(Hash, Hash_size);
 	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
 
@@ -272,3 +271,18 @@ void __init MMU_init_hw(void)
 
 	if ( ppc_md.progress ) ppc_md.progress("hash:done", 0x205);
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 601 can only access 16MB at the moment */
+	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000));
+	else /* Anything else has 256M mapped */
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000));
+}
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 264d0eaa66a2..fecd1cbcf97c 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -529,6 +529,8 @@ static void __early_init_mmu(int boot_cpu)
 	 * the MMU configuration
 	 */
 	mb();
+
+	memblock_set_current_limit(linear_map_top);
 }
 
 void __init early_init_mmu(void)
@@ -541,4 +543,18 @@ void __cpuinit early_init_mmu_secondary(void)
 	__early_init_mmu(0);
 }
 
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* On Embedded 64-bit, we adjust the RMA size to match
+	 * the bolted TLB entry. We know for now that only 1G
+	 * entries are supported though that may eventually
+	 * change. We crop it to the size of the first MEMBLOCK to
+	 * avoid going over total available memory just in case...
+	 */
+	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+
+	/* Finally limit subsequent allocations */
+	memblock_set_current_limit(ppc64_memblock_base + ppc64_rma_size);
+}
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 5cdcc7c8d973..649473a729b8 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -65,7 +65,7 @@ static int __init page_aligned(unsigned long x)
 
 void __init wii_memory_fixups(void)
 {
-	struct memblock_property *p = memblock.memory.region;
+	struct memblock_region *p = memblock.memory.regions;
 
 	/*
 	 * This is part of a workaround to allow the use of two
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 0973aa9237a4..409abfb9541d 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -192,6 +192,13 @@ config HOTPLUG_CPU
 	  can be controlled through /sys/devices/system/cpu/cpu#.
 	  Say N if you want to disable CPU hotplug.
 
+config SCHED_BOOK
+	bool "Book scheduler support"
+	depends on SMP
+	help
+	  Book scheduler support improves the CPU scheduler's decision making
+	  when dealing with machines that have several books.
+
 config MATHEMU
 	bool "IEEE FPU emulation"
 	depends on MARCH_G5
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 831bd033ea77..051107a2c5e2 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -3,15 +3,32 @@
 
 #include <linux/cpumask.h>
 
-#define mc_capable()	(1)
-
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
-
 extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
+static inline const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+	return &cpu_core_map[cpu];
+}
+
 #define topology_core_id(cpu)		(cpu_core_id[cpu])
 #define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
+#define mc_capable()			(1)
+
+#ifdef CONFIG_SCHED_BOOK
+
+extern unsigned char cpu_book_id[NR_CPUS];
+extern cpumask_t cpu_book_map[NR_CPUS];
+
+static inline const struct cpumask *cpu_book_mask(unsigned int cpu)
+{
+	return &cpu_book_map[cpu];
+}
+
+#define topology_book_id(cpu)		(cpu_book_id[cpu])
+#define topology_book_cpumask(cpu)	(&cpu_book_map[cpu])
+
+#endif /* CONFIG_SCHED_BOOK */
 
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
@@ -30,6 +47,8 @@ static inline void s390_init_cpu_topology(void)
 };
 #endif
 
+#define SD_BOOK_INIT	SD_CPU_INIT
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_S390_TOPOLOGY_H */
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index bcef00766a64..13559c993847 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -57,8 +57,8 @@ struct tl_info {
 	union tl_entry tle[0];
 };
 
-struct core_info {
-	struct core_info *next;
+struct mask_info {
+	struct mask_info *next;
 	unsigned char id;
 	cpumask_t mask;
 };
@@ -66,7 +66,6 @@ struct core_info {
 static int topology_enabled;
 static void topology_work_fn(struct work_struct *work);
 static struct tl_info *tl_info;
-static struct core_info core_info;
 static int machine_has_topology;
 static struct timer_list topology_timer;
 static void set_topology_timer(void);
@@ -74,38 +73,37 @@ static DECLARE_WORK(topology_work, topology_work_fn);
 /* topology_lock protects the core linked list */
 static DEFINE_SPINLOCK(topology_lock);
 
+static struct mask_info core_info;
 cpumask_t cpu_core_map[NR_CPUS];
 unsigned char cpu_core_id[NR_CPUS];
 
-static cpumask_t cpu_coregroup_map(unsigned int cpu)
+#ifdef CONFIG_SCHED_BOOK
+static struct mask_info book_info;
+cpumask_t cpu_book_map[NR_CPUS];
+unsigned char cpu_book_id[NR_CPUS];
+#endif
+
+static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
-	struct core_info *core = &core_info;
-	unsigned long flags;
 	cpumask_t mask;
 
 	cpus_clear(mask);
 	if (!topology_enabled || !machine_has_topology)
 		return cpu_possible_map;
-	spin_lock_irqsave(&topology_lock, flags);
-	while (core) {
-		if (cpu_isset(cpu, core->mask)) {
-			mask = core->mask;
+	while (info) {
+		if (cpu_isset(cpu, info->mask)) {
+			mask = info->mask;
 			break;
 		}
-		core = core->next;
+		info = info->next;
 	}
-	spin_unlock_irqrestore(&topology_lock, flags);
 	if (cpus_empty(mask))
 		mask = cpumask_of_cpu(cpu);
 	return mask;
 }
 
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
-{
-	return &cpu_core_map[cpu];
-}
-
-static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
+static void add_cpus_to_mask(struct tl_cpu *tl_cpu, struct mask_info *book,
+			     struct mask_info *core)
 {
 	unsigned int cpu;
 
@@ -117,23 +115,35 @@ static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
 
 		rcpu = CPU_BITS - 1 - cpu + tl_cpu->origin;
 		for_each_present_cpu(lcpu) {
-			if (cpu_logical_map(lcpu) == rcpu) {
-				cpu_set(lcpu, core->mask);
-				cpu_core_id[lcpu] = core->id;
-				smp_cpu_polarization[lcpu] = tl_cpu->pp;
-			}
+			if (cpu_logical_map(lcpu) != rcpu)
+				continue;
+#ifdef CONFIG_SCHED_BOOK
+			cpu_set(lcpu, book->mask);
+			cpu_book_id[lcpu] = book->id;
+#endif
+			cpu_set(lcpu, core->mask);
+			cpu_core_id[lcpu] = core->id;
+			smp_cpu_polarization[lcpu] = tl_cpu->pp;
 		}
 	}
 }
 
-static void clear_cores(void)
+static void clear_masks(void)
 {
-	struct core_info *core = &core_info;
+	struct mask_info *info;
 
-	while (core) {
-		cpus_clear(core->mask);
-		core = core->next;
+	info = &core_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
+	}
+#ifdef CONFIG_SCHED_BOOK
+	info = &book_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
 	}
+#endif
 }
 
 static union tl_entry *next_tle(union tl_entry *tle)
@@ -146,29 +156,36 @@ static union tl_entry *next_tle(union tl_entry *tle)
 
 static void tl_to_cores(struct tl_info *info)
 {
+#ifdef CONFIG_SCHED_BOOK
+	struct mask_info *book = &book_info;
+#else
+	struct mask_info *book = NULL;
+#endif
+	struct mask_info *core = &core_info;
 	union tl_entry *tle, *end;
-	struct core_info *core = &core_info;
+
 
 	spin_lock_irq(&topology_lock);
-	clear_cores();
+	clear_masks();
 	tle = info->tle;
 	end = (union tl_entry *)((unsigned long)info + info->length);
 	while (tle < end) {
 		switch (tle->nl) {
-		case 5:
-		case 4:
-		case 3:
+#ifdef CONFIG_SCHED_BOOK
 		case 2:
+			book = book->next;
+			book->id = tle->container.id;
 			break;
+#endif
 		case 1:
 			core = core->next;
 			core->id = tle->container.id;
 			break;
 		case 0:
-			add_cpus_to_core(&tle->cpu, core);
+			add_cpus_to_mask(&tle->cpu, book, core);
 			break;
 		default:
-			clear_cores();
+			clear_masks();
 			machine_has_topology = 0;
 			goto out;
 		}
@@ -221,10 +238,29 @@ int topology_set_cpu_management(int fc)
 
 static void update_cpu_core_map(void)
 {
+	unsigned long flags;
 	int cpu;
 
-	for_each_possible_cpu(cpu)
-		cpu_core_map[cpu] = cpu_coregroup_map(cpu);
+	spin_lock_irqsave(&topology_lock, flags);
+	for_each_possible_cpu(cpu) {
+		cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
+#ifdef CONFIG_SCHED_BOOK
+		cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
+#endif
+	}
+	spin_unlock_irqrestore(&topology_lock, flags);
+}
+
+static void store_topology(struct tl_info *info)
+{
+#ifdef CONFIG_SCHED_BOOK
+	int rc;
+
+	rc = stsi(info, 15, 1, 3);
+	if (rc != -ENOSYS)
+		return;
+#endif
+	stsi(info, 15, 1, 2);
 }
 
 int arch_update_cpu_topology(void)
@@ -238,7 +274,7 @@ int arch_update_cpu_topology(void)
 		topology_update_polarization_simple();
 		return 0;
 	}
-	stsi(info, 15, 1, 2);
+	store_topology(info);
 	tl_to_cores(info);
 	update_cpu_core_map();
 	for_each_online_cpu(cpu) {
@@ -299,12 +335,24 @@ out:
 }
 __initcall(init_topology_update);
 
+static void alloc_masks(struct tl_info *info, struct mask_info *mask, int offset)
+{
+	int i, nr_masks;
+
+	nr_masks = info->mag[NR_MAG - offset];
+	for (i = 0; i < info->mnest - offset; i++)
+		nr_masks *= info->mag[NR_MAG - offset - 1 - i];
+	nr_masks = max(nr_masks, 1);
+	for (i = 0; i < nr_masks; i++) {
+		mask->next = alloc_bootmem(sizeof(struct mask_info));
+		mask = mask->next;
+	}
+}
+
 void __init s390_init_cpu_topology(void)
 {
 	unsigned long long facility_bits;
 	struct tl_info *info;
-	struct core_info *core;
-	int nr_cores;
 	int i;
 
 	if (stfle(&facility_bits, 1) <= 0)
@@ -315,25 +363,13 @@ void __init s390_init_cpu_topology(void)
 
 	tl_info = alloc_bootmem_pages(PAGE_SIZE);
 	info = tl_info;
-	stsi(info, 15, 1, 2);
-
-	nr_cores = info->mag[NR_MAG - 2];
-	for (i = 0; i < info->mnest - 2; i++)
-		nr_cores *= info->mag[NR_MAG - 3 - i];
-
+	store_topology(info);
 	pr_info("The CPU configuration topology of the machine is:");
 	for (i = 0; i < NR_MAG; i++)
 		printk(" %d", info->mag[i]);
 	printk(" / %d\n", info->mnest);
-
-	core = &core_info;
-	for (i = 0; i < nr_cores; i++) {
-		core->next = alloc_bootmem(sizeof(struct core_info));
-		core = core->next;
-		if (!core)
-			goto error;
-	}
-	return;
-error:
-	machine_has_topology = 0;
+	alloc_masks(info, &core_info, 2);
+#ifdef CONFIG_SCHED_BOOK
+	alloc_masks(info, &book_info, 3);
+#endif
 }
diff --git a/arch/sh/include/asm/memblock.h b/arch/sh/include/asm/memblock.h
index dfe683b88075..e87063fad2ea 100644
--- a/arch/sh/include/asm/memblock.h
+++ b/arch/sh/include/asm/memblock.h
@@ -1,6 +1,4 @@
 #ifndef __ASM_SH_MEMBLOCK_H
 #define __ASM_SH_MEMBLOCK_H
 
-#define MEMBLOCK_REAL_LIMIT	0
-
 #endif /* __ASM_SH_MEMBLOCK_H */
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index a9dd3abde28e..d5ca1ef50fa9 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -14,11 +14,6 @@
 #include <asm/unwinder.h>
 #include <asm/ptrace.h>
 
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
 
 static void callchain_warning(void *data, char *msg)
 {
@@ -39,7 +34,7 @@ static void callchain_address(void *data, unsigned long addr, int reliable)
 	struct perf_callchain_entry *entry = data;
 
 	if (reliable)
-		callchain_store(entry, addr);
+		perf_callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops callchain_ops = {
@@ -49,47 +44,10 @@ static const struct stacktrace_ops callchain_ops = {
 	.address	= callchain_address,
 };
 
-static void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->pc);
+	perf_callchain_store(entry, regs->pc);
 
 	unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	/*
-	 * Only the kernel side is implemented for now.
-	 */
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-}
-
-/*
- * No need for separate IRQ and NMI entries.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-	entry->nr = 0;
-
-	perf_do_callchain(regs, entry);
-
-	return entry;
-}
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7a3dc3567258..036f7a9296fa 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -206,50 +206,80 @@ again:
 	local64_add(delta, &event->count);
 }
 
-static void sh_pmu_disable(struct perf_event *event)
+static void sh_pmu_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	clear_bit(idx, cpuc->active_mask);
-	sh_pmu->disable(hwc, idx);
+	if (!(event->hw.state & PERF_HES_STOPPED)) {
+		sh_pmu->disable(hwc, idx);
+		cpuc->events[idx] = NULL;
+		event->hw.state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
+		sh_perf_event_update(event, &event->hw, idx);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
 
-	barrier();
+static void sh_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
 
-	sh_perf_event_update(event, &event->hw, idx);
+	if (WARN_ON_ONCE(idx == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	cpuc->events[idx] = event;
+	event->hw.state = 0;
+	sh_pmu->enable(hwc, idx);
+}
+
+static void sh_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
-	cpuc->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
+	sh_pmu_stop(event, PERF_EF_UPDATE);
+	__clear_bit(event->hw.idx, cpuc->used_mask);
 
 	perf_event_update_userpage(event);
 }
 
-static int sh_pmu_enable(struct perf_event *event)
+static int sh_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
+	int ret = -EAGAIN;
+
+	perf_pmu_disable(event->pmu);
 
-	if (test_and_set_bit(idx, cpuc->used_mask)) {
+	if (__test_and_set_bit(idx, cpuc->used_mask)) {
 		idx = find_first_zero_bit(cpuc->used_mask, sh_pmu->num_events);
 		if (idx == sh_pmu->num_events)
-			return -EAGAIN;
+			goto out;
 
-		set_bit(idx, cpuc->used_mask);
+		__set_bit(idx, cpuc->used_mask);
 		hwc->idx = idx;
 	}
 
 	sh_pmu->disable(hwc, idx);
 
-	cpuc->events[idx] = event;
-	set_bit(idx, cpuc->active_mask);
-
-	sh_pmu->enable(hwc, idx);
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (flags & PERF_EF_START)
+		sh_pmu_start(event, PERF_EF_RELOAD);
 
 	perf_event_update_userpage(event);
-
-	return 0;
+	ret = 0;
+out:
+	perf_pmu_enable(event->pmu);
+	return ret;
 }
 
 static void sh_pmu_read(struct perf_event *event)
@@ -257,24 +287,56 @@ static void sh_pmu_read(struct perf_event *event)
 	sh_perf_event_update(event, &event->hw, event->hw.idx);
 }
 
-static const struct pmu pmu = {
-	.enable		= sh_pmu_enable,
-	.disable	= sh_pmu_disable,
-	.read		= sh_pmu_read,
-};
-
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int sh_pmu_event_init(struct perf_event *event)
 {
-	int err = __hw_perf_event_init(event);
+	int err;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HW_CACHE:
+	case PERF_TYPE_HARDWARE:
+		err = __hw_perf_event_init(event);
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (unlikely(err)) {
 		if (event->destroy)
 			event->destroy(event);
-		return ERR_PTR(err);
 	}
 
-	return &pmu;
+	return err;
+}
+
+static void sh_pmu_enable(struct pmu *pmu)
+{
+	if (!sh_pmu_initialized())
+		return;
+
+	sh_pmu->enable_all();
+}
+
+static void sh_pmu_disable(struct pmu *pmu)
+{
+	if (!sh_pmu_initialized())
+		return;
+
+	sh_pmu->disable_all();
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= sh_pmu_enable,
+	.pmu_disable	= sh_pmu_disable,
+	.event_init	= sh_pmu_event_init,
+	.add		= sh_pmu_add,
+	.del		= sh_pmu_del,
+	.start		= sh_pmu_start,
+	.stop		= sh_pmu_stop,
+	.read		= sh_pmu_read,
+};
+
 static void sh_pmu_setup(int cpu)
 {
 	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
@@ -299,32 +361,17 @@ sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 	return NOTIFY_OK;
 }
 
-void hw_perf_enable(void)
-{
-	if (!sh_pmu_initialized())
-		return;
-
-	sh_pmu->enable_all();
-}
-
-void hw_perf_disable(void)
-{
-	if (!sh_pmu_initialized())
-		return;
-
-	sh_pmu->disable_all();
-}
-
-int __cpuinit register_sh_pmu(struct sh_pmu *pmu)
+int __cpuinit register_sh_pmu(struct sh_pmu *_pmu)
 {
 	if (sh_pmu)
 		return -EBUSY;
-	sh_pmu = pmu;
+	sh_pmu = _pmu;
 
-	pr_info("Performance Events: %s support registered\n", pmu->name);
+	pr_info("Performance Events: %s support registered\n", _pmu->name);
 
-	WARN_ON(pmu->num_events > MAX_HWEVENTS);
+	WARN_ON(_pmu->num_events > MAX_HWEVENTS);
 
+	perf_pmu_register(&pmu);
 	perf_cpu_notifier(sh_pmu_notifier);
 	return 0;
 }
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 105f559d946d..dbffaa75303d 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -224,7 +224,6 @@ static void __init bootmem_init_one_node(unsigned int nid)
 	unsigned long total_pages, paddr;
 	unsigned long end_pfn;
 	struct pglist_data *p;
-	int i;
 
 	p = NODE_DATA(nid);
 
@@ -250,11 +249,12 @@ static void __init bootmem_init_one_node(unsigned int nid)
 	 * reservations in other nodes.
 	 */
 	if (nid == 0) {
+		struct memblock_region *reg;
+
 		/* Reserve the sections we're already using. */
-		for (i = 0; i < memblock.reserved.cnt; i++)
-			reserve_bootmem(memblock.reserved.region[i].base,
-					memblock_size_bytes(&memblock.reserved, i),
-					BOOTMEM_DEFAULT);
+		for_each_memblock(reserved, reg) {
+			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+		}
 	}
 
 	sparse_memory_present_with_active_regions(nid);
@@ -262,13 +262,14 @@ static void __init bootmem_init_one_node(unsigned int nid)
 
 static void __init do_init_bootmem(void)
 {
+	struct memblock_region *reg;
 	int i;
 
 	/* Add active regions with valid PFNs. */
-	for (i = 0; i < memblock.memory.cnt; i++) {
+	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+		start_pfn = memblock_region_base_pfn(reg);
+		end_pfn = memblock_region_end_pfn(reg);
 		__add_active_range(0, start_pfn, end_pfn);
 	}
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 093a6d35e064..13766bbcaa32 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -24,6 +24,7 @@ config SPARC
 	select PERF_USE_VMALLOC
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
+	select HAVE_ARCH_JUMP_LABEL
 
 config SPARC32
 	def_bool !64BIT
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
new file mode 100644
index 000000000000..62e66d7b2fb6
--- /dev/null
+++ b/arch/sparc/include/asm/jump_label.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_SPARC_JUMP_LABEL_H
+#define _ASM_SPARC_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/system.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+#define JUMP_LABEL(key, label)					\
+	do {							\
+		asm goto("1:\n\t"				\
+			 "nop\n\t"				\
+			 "nop\n\t"				\
+			 ".pushsection __jump_table,  \"a\"\n\t"\
+			 ".word 1b, %l[" #label "], %c0\n\t"	\
+			 ".popsection \n\t"			\
+			 : :  "i" (key) :  : label);\
+	} while (0)
+
+#endif /* __KERNEL__ */
+
+typedef u32 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif
diff --git a/arch/sparc/include/asm/memblock.h b/arch/sparc/include/asm/memblock.h
index f12af880649b..c67b047ef85e 100644
--- a/arch/sparc/include/asm/memblock.h
+++ b/arch/sparc/include/asm/memblock.h
@@ -5,6 +5,4 @@
 
 #define MEMBLOCK_DBG(fmt...) prom_printf(fmt)
 
-#define MEMBLOCK_REAL_LIMIT	0
-
 #endif /* !(_SPARC64_MEMBLOCK_H) */
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 0c2dc1f24a9a..599398fbbc7c 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -119,3 +119,5 @@ obj-$(CONFIG_COMPAT)    += $(audit--y)
 
 pc--$(CONFIG_PERF_EVENTS) := perf_event.o
 obj-$(CONFIG_SPARC64)	+= $(pc--y)
+
+obj-$(CONFIG_SPARC64)	+= jump_label.o
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
new file mode 100644
index 000000000000..ea2dafc93d78
--- /dev/null
+++ b/arch/sparc/kernel/jump_label.c
@@ -0,0 +1,47 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	u32 val;
+	u32 *insn = (u32 *) (unsigned long) entry->code;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		s32 off = (s32)entry->target - (s32)entry->code;
+
+#ifdef CONFIG_SPARC64
+		/* ba,pt %xcc, . + (off << 2) */
+		val = 0x10680000 | ((u32) off >> 2);
+#else
+		/* ba . + (off << 2) */
+		val = 0x10800000 | ((u32) off >> 2);
+#endif
+	} else {
+		val = 0x01000000;
+	}
+
+	get_online_cpus();
+	mutex_lock(&text_mutex);
+	*insn = val;
+	flushi(insn);
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+}
+
+void arch_jump_label_text_poke_early(jump_label_t addr)
+{
+	u32 *insn_p = (u32 *) (unsigned long) addr;
+
+	*insn_p = 0x01000000;
+	flushi(insn_p);
+}
+
+#endif
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index f848aadf54dc..ee3c7dde8d9f 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -18,6 +18,9 @@
 #include <asm/spitfire.h>
 
 #ifdef CONFIG_SPARC64
+
+#include <linux/jump_label.h>
+
 static void *module_map(unsigned long size)
 {
 	struct vm_struct *area;
@@ -227,6 +230,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
+	/* make jump label nops */
+	jump_label_apply_nops(me);
+
 	/* Cheetah's I-cache is fully coherent.  */
 	if (tlb_type == spitfire) {
 		unsigned long va;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 6318e622cfb0..0d6deb55a2ae 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -658,13 +658,16 @@ static u64 maybe_change_configuration(struct cpu_hw_events *cpuc, u64 pcr)
 
 		enc = perf_event_get_enc(cpuc->events[i]);
 		pcr &= ~mask_for_index(idx);
-		pcr |= event_encoding(enc, idx);
+		if (hwc->state & PERF_HES_STOPPED)
+			pcr |= nop_for_index(idx);
+		else
+			pcr |= event_encoding(enc, idx);
 	}
 out:
 	return pcr;
 }
 
-void hw_perf_enable(void)
+static void sparc_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	u64 pcr;
@@ -691,7 +694,7 @@ void hw_perf_enable(void)
 	pcr_ops->write(cpuc->pcr);
 }
 
-void hw_perf_disable(void)
+static void sparc_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	u64 val;
@@ -710,19 +713,65 @@ void hw_perf_disable(void)
 	pcr_ops->write(cpuc->pcr);
 }
 
-static void sparc_pmu_disable(struct perf_event *event)
+static int active_event_index(struct cpu_hw_events *cpuc,
+			      struct perf_event *event)
+{
+	int i;
+
+	for (i = 0; i < cpuc->n_events; i++) {
+		if (cpuc->event[i] == event)
+			break;
+	}
+	BUG_ON(i == cpuc->n_events);
+	return cpuc->current_idx[i];
+}
+
+static void sparc_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx = active_event_index(cpuc, event);
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+		sparc_perf_event_set_period(event, &event->hw, idx);
+	}
+
+	event->hw.state = 0;
+
+	sparc_pmu_enable_event(cpuc, &event->hw, idx);
+}
+
+static void sparc_pmu_stop(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx = active_event_index(cpuc, event);
+
+	if (!(event->hw.state & PERF_HES_STOPPED)) {
+		sparc_pmu_disable_event(cpuc, &event->hw, idx);
+		event->hw.state |= PERF_HES_STOPPED;
+	}
+
+	if (!(event->hw.state & PERF_HES_UPTODATE) && (flags & PERF_EF_UPDATE)) {
+		sparc_perf_event_update(event, &event->hw, idx);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
+
+static void sparc_pmu_del(struct perf_event *event, int _flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 	int i;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event[i]) {
-			int idx = cpuc->current_idx[i];
+			/* Absorb the final count and turn off the
+			 * event.
+			 */
+			sparc_pmu_stop(event, PERF_EF_UPDATE);
 
 			/* Shift remaining entries down into
 			 * the existing slot.
@@ -734,13 +783,6 @@ static void sparc_pmu_disable(struct perf_event *event)
 					cpuc->current_idx[i];
 			}
 
-			/* Absorb the final count and turn off the
-			 * event.
-			 */
-			sparc_pmu_disable_event(cpuc, hwc, idx);
-			barrier();
-			sparc_perf_event_update(event, hwc, idx);
-
 			perf_event_update_userpage(event);
 
 			cpuc->n_events--;
@@ -748,23 +790,10 @@ static void sparc_pmu_disable(struct perf_event *event)
 		}
 	}
 
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
-static int active_event_index(struct cpu_hw_events *cpuc,
-			      struct perf_event *event)
-{
-	int i;
-
-	for (i = 0; i < cpuc->n_events; i++) {
-		if (cpuc->event[i] == event)
-			break;
-	}
-	BUG_ON(i == cpuc->n_events);
-	return cpuc->current_idx[i];
-}
-
 static void sparc_pmu_read(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -774,15 +803,6 @@ static void sparc_pmu_read(struct perf_event *event)
 	sparc_perf_event_update(event, hwc, idx);
 }
 
-static void sparc_pmu_unthrottle(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	int idx = active_event_index(cpuc, event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	sparc_pmu_enable_event(cpuc, hwc, idx);
-}
-
 static atomic_t active_events = ATOMIC_INIT(0);
 static DEFINE_MUTEX(pmc_grab_mutex);
 
@@ -877,7 +897,7 @@ static int sparc_check_constraints(struct perf_event **evts,
 	if (!n_ev)
 		return 0;
 
-	if (n_ev > perf_max_events)
+	if (n_ev > MAX_HWEVENTS)
 		return -1;
 
 	msk0 = perf_event_get_msk(events[0]);
@@ -984,23 +1004,27 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-static int sparc_pmu_enable(struct perf_event *event)
+static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int n0, ret = -EAGAIN;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	n0 = cpuc->n_events;
-	if (n0 >= perf_max_events)
+	if (n0 >= MAX_HWEVENTS)
 		goto out;
 
 	cpuc->event[n0] = event;
 	cpuc->events[n0] = event->hw.event_base;
 	cpuc->current_idx[n0] = PIC_NO_INDEX;
 
+	event->hw.state = PERF_HES_UPTODATE;
+	if (!(ef_flags & PERF_EF_START))
+		event->hw.state |= PERF_HES_STOPPED;
+
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
@@ -1020,12 +1044,12 @@ nocheck:
 
 	ret = 0;
 out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int sparc_pmu_event_init(struct perf_event *event)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct perf_event *evts[MAX_HWEVENTS];
@@ -1038,22 +1062,33 @@ static int __hw_perf_event_init(struct perf_event *event)
 	if (atomic_read(&nmi_active) < 0)
 		return -ENODEV;
 
-	pmap = NULL;
-	if (attr->type == PERF_TYPE_HARDWARE) {
+	switch (attr->type) {
+	case PERF_TYPE_HARDWARE:
 		if (attr->config >= sparc_pmu->max_events)
 			return -EINVAL;
 		pmap = sparc_pmu->event_map(attr->config);
-	} else if (attr->type == PERF_TYPE_HW_CACHE) {
+		break;
+
+	case PERF_TYPE_HW_CACHE:
 		pmap = sparc_map_cache_event(attr->config);
 		if (IS_ERR(pmap))
 			return PTR_ERR(pmap);
-	} else if (attr->type != PERF_TYPE_RAW)
-		return -EOPNOTSUPP;
+		break;
+
+	case PERF_TYPE_RAW:
+		pmap = NULL;
+		break;
+
+	default:
+		return -ENOENT;
+
+	}
 
 	if (pmap) {
 		hwc->event_base = perf_event_encode(pmap);
 	} else {
-		/* User gives us "(encoding << 16) | pic_mask" for
+		/*
+		 * User gives us "(encoding << 16) | pic_mask" for
 		 * PERF_TYPE_RAW events.
 		 */
 		hwc->event_base = attr->config;
@@ -1071,7 +1106,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 	n = 0;
 	if (event->group_leader != event) {
 		n = collect_events(event->group_leader,
-				   perf_max_events - 1,
+				   MAX_HWEVENTS - 1,
 				   evts, events, current_idx_dmy);
 		if (n < 0)
 			return -EINVAL;
@@ -1107,10 +1142,11 @@ static int __hw_perf_event_init(struct perf_event *event)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void sparc_pmu_start_txn(const struct pmu *pmu)
+static void sparc_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 }
 
@@ -1119,11 +1155,12 @@ static void sparc_pmu_start_txn(const struct pmu *pmu)
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-static void sparc_pmu_cancel_txn(const struct pmu *pmu)
+static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -1131,7 +1168,7 @@ static void sparc_pmu_cancel_txn(const struct pmu *pmu)
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-static int sparc_pmu_commit_txn(const struct pmu *pmu)
+static int sparc_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int n;
@@ -1147,28 +1184,24 @@ static int sparc_pmu_commit_txn(const struct pmu *pmu)
 		return -EAGAIN;
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= sparc_pmu_enable,
-	.disable	= sparc_pmu_disable,
+static struct pmu pmu = {
+	.pmu_enable	= sparc_pmu_enable,
+	.pmu_disable	= sparc_pmu_disable,
+	.event_init	= sparc_pmu_event_init,
+	.add		= sparc_pmu_add,
+	.del		= sparc_pmu_del,
+	.start		= sparc_pmu_start,
+	.stop		= sparc_pmu_stop,
 	.read		= sparc_pmu_read,
-	.unthrottle	= sparc_pmu_unthrottle,
 	.start_txn	= sparc_pmu_start_txn,
 	.cancel_txn	= sparc_pmu_cancel_txn,
 	.commit_txn	= sparc_pmu_commit_txn,
 };
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
-{
-	int err = __hw_perf_event_init(event);
-
-	if (err)
-		return ERR_PTR(err);
-	return &pmu;
-}
-
 void perf_event_print_debug(void)
 {
 	unsigned long flags;
@@ -1244,7 +1277,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			sparc_pmu_disable_event(cpuc, hwc, idx);
+			sparc_pmu_stop(event, 0);
 	}
 
 	return NOTIFY_STOP;
@@ -1285,28 +1318,21 @@ void __init init_hw_perf_events(void)
 
 	pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type);
 
-	/* All sparc64 PMUs currently have 2 events.  */
-	perf_max_events = 2;
-
+	perf_pmu_register(&pmu);
 	register_die_notifier(&perf_event_nmi_notifier);
 }
 
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
-
-static void perf_callchain_kernel(struct pt_regs *regs,
-				  struct perf_callchain_entry *entry)
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+			   struct pt_regs *regs)
 {
 	unsigned long ksp, fp;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	int graph = 0;
 #endif
 
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->tpc);
+	stack_trace_flush();
+
+	perf_callchain_store(entry, regs->tpc);
 
 	ksp = regs->u_regs[UREG_I6];
 	fp = ksp + STACK_BIAS;
@@ -1330,13 +1356,13 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			pc = sf->callers_pc;
 			fp = (unsigned long)sf->fp + STACK_BIAS;
 		}
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 		if ((pc + 8UL) == (unsigned long) &return_to_handler) {
 			int index = current->curr_ret_stack;
 			if (current->ret_stack && index >= graph) {
 				pc = current->ret_stack[index - graph].ret;
-				callchain_store(entry, pc);
+				perf_callchain_store(entry, pc);
 				graph++;
 			}
 		}
@@ -1344,13 +1370,12 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long ufp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, regs->tpc);
+	perf_callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
 	do {
@@ -1363,17 +1388,16 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp + STACK_BIAS;
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long ufp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, regs->tpc);
+	perf_callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
 	do {
@@ -1386,34 +1410,16 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp;
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-/* Like powerpc we can't get PMU interrupts within the PMU handler,
- * so no need for separate NMI and IRQ chains as on x86.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-	entry->nr = 0;
-	if (!user_mode(regs)) {
-		stack_trace_flush();
-		perf_callchain_kernel(regs, entry);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-	if (regs) {
-		flushw_user();
-		if (test_thread_flag(TIF_32BIT))
-			perf_callchain_user_32(regs, entry);
-		else
-			perf_callchain_user_64(regs, entry);
-	}
-	return entry;
+	flushw_user();
+	if (test_thread_flag(TIF_32BIT))
+		perf_callchain_user_32(entry, regs);
+	else
+		perf_callchain_user_64(entry, regs);
 }
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index f0434513df15..dc584d26d597 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -785,8 +785,7 @@ static int find_node(unsigned long addr)
 	return -1;
 }
 
-static unsigned long long nid_range(unsigned long long start,
-				    unsigned long long end, int *nid)
+u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = find_node(start);
 	start += PAGE_SIZE;
@@ -804,8 +803,7 @@ static unsigned long long nid_range(unsigned long long start,
 	return start;
 }
 #else
-static unsigned long long nid_range(unsigned long long start,
-				    unsigned long long end, int *nid)
+u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = 0;
 	return end;
@@ -822,8 +820,7 @@ static void __init allocate_node_data(int nid)
 	struct pglist_data *p;
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
-	paddr = memblock_alloc_nid(sizeof(struct pglist_data),
-			      SMP_CACHE_BYTES, nid, nid_range);
+	paddr = memblock_alloc_try_nid(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid);
 	if (!paddr) {
 		prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid);
 		prom_halt();
@@ -843,8 +840,7 @@ static void __init allocate_node_data(int nid)
 	if (p->node_spanned_pages) {
 		num_pages = bootmem_bootmap_pages(p->node_spanned_pages);
 
-		paddr = memblock_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid,
-				      nid_range);
+		paddr = memblock_alloc_try_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid);
 		if (!paddr) {
 			prom_printf("Cannot allocate bootmap for nid[%d]\n",
 				  nid);
@@ -972,19 +968,19 @@ int of_node_to_nid(struct device_node *dp)
 
 static void __init add_node_ranges(void)
 {
-	int i;
+	struct memblock_region *reg;
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		unsigned long size = memblock_size_bytes(&memblock.memory, i);
+	for_each_memblock(memory, reg) {
+		unsigned long size = reg->size;
 		unsigned long start, end;
 
-		start = memblock.memory.region[i].base;
+		start = reg->base;
 		end = start + size;
 		while (start < end) {
 			unsigned long this_end;
 			int nid;
 
-			this_end = nid_range(start, end, &nid);
+			this_end = memblock_nid_range(start, end, &nid);
 
 			numadbg("Adding active range nid[%d] "
 				"start[%lx] end[%lx]\n",
@@ -1281,7 +1277,7 @@ static void __init bootmem_init_nonnuma(void)
 {
 	unsigned long top_of_ram = memblock_end_of_DRAM();
 	unsigned long total_ram = memblock_phys_mem_size();
-	unsigned int i;
+	struct memblock_region *reg;
 
 	numadbg("bootmem_init_nonnuma()\n");
 
@@ -1292,15 +1288,14 @@ static void __init bootmem_init_nonnuma(void)
 
 	init_node_masks_nonnuma();
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		unsigned long size = memblock_size_bytes(&memblock.memory, i);
+	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
 
-		if (!size)
+		if (!reg->size)
 			continue;
 
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+		start_pfn = memblock_region_base_pfn(reg);
+		end_pfn = memblock_region_end_pfn(reg);
 		add_active_range(0, start_pfn, end_pfn);
 	}
 
@@ -1318,7 +1313,7 @@ static void __init reserve_range_in_node(int nid, unsigned long start,
 		unsigned long this_end;
 		int n;
 
-		this_end = nid_range(start, end, &n);
+		this_end = memblock_nid_range(start, end, &n);
 		if (n == nid) {
 			numadbg("      MATCH reserving range [%lx:%lx]\n",
 				start, this_end);
@@ -1334,17 +1329,12 @@ static void __init reserve_range_in_node(int nid, unsigned long start,
 
 static void __init trim_reserved_in_node(int nid)
 {
-	int i;
+	struct memblock_region *reg;
 
 	numadbg("  trim_reserved_in_node(%d)\n", nid);
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long start = memblock.reserved.region[i].base;
-		unsigned long size = memblock_size_bytes(&memblock.reserved, i);
-		unsigned long end = start + size;
-
-		reserve_range_in_node(nid, start, end);
-	}
+	for_each_memblock(reserved, reg)
+		reserve_range_in_node(nid, reg->base, reg->base + reg->size);
 }
 
 static void __init bootmem_init_one_node(int nid)
diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c
index 596c60086930..9a27d563fc30 100644
--- a/arch/tile/kernel/irq.c
+++ b/arch/tile/kernel/irq.c
@@ -208,7 +208,7 @@ static void tile_irq_chip_eoi(unsigned int irq)
 }
 
 static struct irq_chip tile_irq_chip = {
-	.typename = "tile_irq_chip",
+	.name = "tile_irq_chip",
 	.ack = tile_irq_chip_ack,
 	.eoi = tile_irq_chip_eoi,
 	.mask = tile_irq_chip_mask,
@@ -288,7 +288,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action = action->next; action; action = action->next)
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index a3f0b04d7101..a746e3037a5b 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -46,7 +46,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)
@@ -369,7 +369,7 @@ static void dummy(unsigned int irq)
 
 /* This is used for everything else than the timer. */
 static struct irq_chip normal_irq_type = {
-	.typename = "SIGIO",
+	.name = "SIGIO",
 	.release = free_irq_by_irq_and_dev,
 	.disable = dummy,
 	.enable = dummy,
@@ -378,7 +378,7 @@ static struct irq_chip normal_irq_type = {
 };
 
 static struct irq_chip SIGVTALRM_irq_type = {
-	.typename = "SIGVTALRM",
+	.name = "SIGVTALRM",
 	.release = free_irq_by_irq_and_dev,
 	.shutdown = dummy, /* never called */
 	.disable = dummy,
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2cf84f58997e..065c18878160 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,6 +24,7 @@ config X86
 	select HAVE_PERF_EVENTS if (!M386 && !M486)
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
+	select HAVE_MEMBLOCK
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_FRAME_POINTERS
 	select HAVE_DMA_ATTRS
@@ -56,6 +57,12 @@ config X86
 	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
+	select HAVE_GENERIC_HARDIRQS
+	select HAVE_SPARSE_IRQ
+	select NUMA_IRQ_DESC if (SPARSE_IRQ && NUMA)
+	select GENERIC_IRQ_PROBE
+	select GENERIC_PENDING_IRQ if SMP
+	select HAVE_ARCH_JUMP_LABEL
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
@@ -190,27 +197,10 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
-config HAVE_EARLY_RES
-	def_bool y
-
 config HAVE_INTEL_TXT
 	def_bool y
 	depends on EXPERIMENTAL && DMAR && ACPI
 
-# Use the generic interrupt handling code in kernel/irq/:
-config GENERIC_HARDIRQS
-	def_bool y
-
-config GENERIC_HARDIRQS_NO__DO_IRQ
-       def_bool y
-
-config GENERIC_IRQ_PROBE
-	def_bool y
-
-config GENERIC_PENDING_IRQ
-	def_bool y
-	depends on GENERIC_HARDIRQS && SMP
-
 config USE_GENERIC_SMP_HELPERS
 	def_bool y
 	depends on SMP
@@ -293,23 +283,6 @@ config X86_X2APIC
 
 	  If you don't know what to do here, say N.
 
-config SPARSE_IRQ
-	bool "Support sparse irq numbering"
-	depends on PCI_MSI || HT_IRQ
-	---help---
-	  This enables support for sparse irqs. This is useful for distro
-	  kernels that want to define a high CONFIG_NR_CPUS value but still
-	  want to have low kernel memory footprint on smaller machines.
-
-	  ( Sparse IRQs can also be beneficial on NUMA boxes, as they spread
-	    out the irq_desc[] array in a more NUMA-friendly way. )
-
-	  If you don't know what to do here, say N.
-
-config NUMA_IRQ_DESC
-	def_bool y
-	depends on SPARSE_IRQ && NUMA
-
 config X86_MPPARSE
 	bool "Enable MPS table" if ACPI
 	default y
@@ -514,25 +487,6 @@ if PARAVIRT_GUEST
 
 source "arch/x86/xen/Kconfig"
 
-config VMI
-	bool "VMI Guest support (DEPRECATED)"
-	select PARAVIRT
-	depends on X86_32
-	---help---
-	  VMI provides a paravirtualized interface to the VMware ESX server
-	  (it could be used by other hypervisors in theory too, but is not
-	  at the moment), by linking the kernel to a GPL-ed ROM module
-	  provided by the hypervisor.
-
-	  As of September 2009, VMware has started a phased retirement
-	  of this feature from VMware's products. Please see
-	  feature-removal-schedule.txt for details.  If you are
-	  planning to enable this option, please note that you cannot
-	  live migrate a VMI enabled VM to a future VMware product,
-	  which doesn't support VMI. So if you expect your kernel to
-	  seamlessly migrate to newer VMware products, keep this
-	  disabled.
-
 config KVM_CLOCK
 	bool "KVM paravirtualized clock"
 	select PARAVIRT
@@ -587,16 +541,7 @@ config PARAVIRT_DEBUG
 	  a paravirt_op is missing when it is called.
 
 config NO_BOOTMEM
-	default y
-	bool "Disable Bootmem code"
-	---help---
-	  Use early_res directly instead of bootmem before slab is ready.
-		- allocator (buddy) [generic]
-		- early allocator (bootmem) [generic]
-		- very early allocator (reserve_early*()) [x86]
-		- very very early allocator (early brk model) [x86]
-	  So reduce one layer between early allocator to final allocator
-
+	def_bool y
 
 config MEMTEST
 	bool "Memtest"
@@ -667,7 +612,7 @@ config GART_IOMMU
 	bool "GART IOMMU support" if EMBEDDED
 	default y
 	select SWIOTLB
-	depends on X86_64 && PCI && K8_NB
+	depends on X86_64 && PCI && AMD_NB
 	---help---
 	  Support for full DMA access of devices with 32bit memory access only
 	  on systems with more than 3GB. This is usually needed for USB,
@@ -1323,25 +1268,34 @@ config X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK
 	  Set whether the default state of memory_corruption_check is
 	  on or off.
 
-config X86_RESERVE_LOW_64K
-	bool "Reserve low 64K of RAM on AMI/Phoenix BIOSen"
-	default y
+config X86_RESERVE_LOW
+	int "Amount of low memory, in kilobytes, to reserve for the BIOS"
+	default 64
+	range 4 640
 	---help---
-	  Reserve the first 64K of physical RAM on BIOSes that are known
-	  to potentially corrupt that memory range. A numbers of BIOSes are
-	  known to utilize this area during suspend/resume, so it must not
-	  be used by the kernel.
+	  Specify the amount of low memory to reserve for the BIOS.
+
+	  The first page contains BIOS data structures that the kernel
+	  must not use, so that page must always be reserved.
+
+	  By default we reserve the first 64K of physical RAM, as a
+	  number of BIOSes are known to corrupt that memory range
+	  during events such as suspend/resume or monitor cable
+	  insertion, so it must not be used by the kernel.
 
-	  Set this to N if you are absolutely sure that you trust the BIOS
-	  to get all its memory reservations and usages right.
+	  You can set this to 4 if you are absolutely sure that you
+	  trust the BIOS to get all its memory reservations and usages
+	  right.  If you know your BIOS have problems beyond the
+	  default 64K area, you can set this to 640 to avoid using the
+	  entire low memory range.
 
-	  If you have doubts about the BIOS (e.g. suspend/resume does not
-	  work or there's kernel crashes after certain hardware hotplug
-	  events) and it's not AMI or Phoenix, then you might want to enable
-	  X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check typical
-	  corruption patterns.
+	  If you have doubts about the BIOS (e.g. suspend/resume does
+	  not work or there's kernel crashes after certain hardware
+	  hotplug events) then you might want to enable
+	  X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check
+	  typical corruption patterns.
 
-	  Say Y if unsure.
+	  Leave this to the default value of 64 if you are unsure.
 
 config MATH_EMULATION
 	bool
@@ -2058,6 +2012,7 @@ config SCx200HR_TIMER
 config OLPC
 	bool "One Laptop Per Child support"
 	select GPIOLIB
+	select OLPC_OPENFIRMWARE
 	---help---
 	  Add support for detecting the unique features of the OLPC
 	  XO hardware.
@@ -2065,7 +2020,7 @@ config OLPC
 config OLPC_OPENFIRMWARE
 	bool "Support for OLPC's Open Firmware"
 	depends on !X86_64 && !X86_PAE
-	default y if OLPC
+	default n
 	help
 	  This option adds support for the implementation of Open Firmware
 	  that is used on the OLPC XO-1 Children's Machine.
@@ -2073,7 +2028,7 @@ config OLPC_OPENFIRMWARE
 
 endif # X86_32
 
-config K8_NB
+config AMD_NB
 	def_bool y
 	depends on CPU_SUP_AMD && PCI
 
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 75085080b63e..7f1530838bc8 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -121,16 +121,6 @@ config DEBUG_NX_TEST
 	  and the software setup of this feature.
 	  If in doubt, say "N"
 
-config 4KSTACKS
-	bool "Use 4Kb for kernel stacks instead of 8Kb"
-	depends on X86_32
-	---help---
-	  If you say Y here the kernel will use a 4Kb stacksize for the
-	  kernel stack attached to each process/thread. This facilitates
-	  running more threads on a system and also reduces the pressure
-	  on the VM subsystem for higher order allocations. This option
-	  will also use IRQ stacks to compensate for the reduced stackspace.
-
 config DOUBLEFAULT
 	default y
 	bool "Enable doublefault exception handler" if EMBEDDED
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index bc6abb7bc7ee..76561d20ea2f 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
+#include <linux/jump_label.h>
 #include <asm/asm.h>
 
 /*
@@ -160,6 +161,8 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end	NULL
 #endif
 
+extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.
  * Allows the kernel to edit read-only pages.
@@ -180,4 +183,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
 
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
+#define IDEAL_NOP_SIZE_5 5
+extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+extern void arch_init_ideal_nop5(void);
+#else
+static inline void arch_init_ideal_nop5(void) {}
+#endif
+
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index 5af2982133b5..2798142cdb49 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -24,11 +24,11 @@
 
 #ifdef CONFIG_AMD_IOMMU
 
-extern void amd_iommu_detect(void);
+extern int amd_iommu_detect(void);
 
 #else
 
-static inline void amd_iommu_detect(void) { }
+static inline int amd_iommu_detect(void) { return -ENODEV; }
 
 #endif
 
diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/amd_nb.h
index af00bd1d2089..c8517f81b21e 100644
--- a/arch/x86/include/asm/k8.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_K8_H
-#define _ASM_X86_K8_H
+#ifndef _ASM_X86_AMD_NB_H
+#define _ASM_X86_AMD_NB_H
 
 #include <linux/pci.h>
 
@@ -7,24 +7,27 @@ extern struct pci_device_id k8_nb_ids[];
 struct bootnode;
 
 extern int early_is_k8_nb(u32 value);
-extern struct pci_dev **k8_northbridges;
-extern int num_k8_northbridges;
 extern int cache_k8_northbridges(void);
 extern void k8_flush_garts(void);
 extern int k8_get_nodes(struct bootnode *nodes);
 extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn);
 extern int k8_scan_nodes(void);
 
-#ifdef CONFIG_K8_NB
-extern int num_k8_northbridges;
+struct k8_northbridge_info {
+	u16 num;
+	u8 gart_supported;
+	struct pci_dev **nb_misc;
+};
+extern struct k8_northbridge_info k8_northbridges;
+
+#ifdef CONFIG_AMD_NB
 
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
-	return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL;
+	return (node < k8_northbridges.num) ? k8_northbridges.nb_misc[node] : NULL;
 }
 
 #else
-#define num_k8_northbridges 0
 
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
@@ -33,4 +36,4 @@ static inline struct pci_dev *node_to_k8_nb_misc(int node)
 #endif
 
 
-#endif /* _ASM_X86_K8_H */
+#endif /* _ASM_X86_AMD_NB_H */
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index a69b1ac9eaf8..2fefa501d3ba 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -54,7 +54,6 @@ extern struct clock_event_device *global_clock_event;
 extern unsigned long apbt_quick_calibrate(void);
 extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
 extern void apbt_setup_secondary_clock(void);
-extern unsigned int boot_cpu_id;
 
 extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
 extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr);
diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h
index 0918654305af..0d467b338835 100644
--- a/arch/x86/include/asm/calgary.h
+++ b/arch/x86/include/asm/calgary.h
@@ -62,9 +62,9 @@ struct cal_chipset_ops {
 extern int use_calgary;
 
 #ifdef CONFIG_CALGARY_IOMMU
-extern void detect_calgary(void);
+extern int detect_calgary(void);
 #else
-static inline void detect_calgary(void) { return; }
+static inline int detect_calgary(void) { return -ENODEV; }
 #endif
 
 #endif /* _ASM_X86_CALGARY_H */
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index b185091bf19c..4fab24de26b1 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -32,6 +32,5 @@ extern void arch_unregister_cpu(int);
 
 DECLARE_PER_CPU(int, cpu_state);
 
-extern unsigned int boot_cpu_id;
 
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3f76523589af..220e2ea08e80 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -152,10 +152,14 @@
 #define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
 #define X86_FEATURE_OSVW	(6*32+ 9) /* OS Visible Workaround */
 #define X86_FEATURE_IBS		(6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_SSE5	(6*32+11) /* SSE-5 */
+#define X86_FEATURE_XOP		(6*32+11) /* extended AVX instructions */
 #define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
 #define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP		(6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4	(6*32+16) /* 4 operands MAC instructions */
 #define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -180,6 +184,13 @@
 #define X86_FEATURE_LBRV	(8*32+ 6) /* AMD LBR Virtualization support */
 #define X86_FEATURE_SVML	(8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
 #define X86_FEATURE_NRIPS	(8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */
+
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 733f7e91e7a9..326099199318 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -89,6 +89,16 @@
 	CFI_ADJUST_CFA_OFFSET -8
 	.endm
 
+	.macro pushfq_cfi
+	pushfq
+	CFI_ADJUST_CFA_OFFSET 8
+	.endm
+
+	.macro popfq_cfi
+	popfq
+	CFI_ADJUST_CFA_OFFSET -8
+	.endm
+
 	.macro movq_cfi reg offset=0
 	movq %\reg, \offset(%rsp)
 	CFI_REL_OFFSET \reg, \offset
@@ -109,6 +119,16 @@
 	CFI_ADJUST_CFA_OFFSET -4
 	.endm
 
+	.macro pushfl_cfi
+	pushfl
+	CFI_ADJUST_CFA_OFFSET 4
+	.endm
+
+	.macro popfl_cfi
+	popfl
+	CFI_ADJUST_CFA_OFFSET -4
+	.endm
+
 	.macro movl_cfi reg offset=0
 	movl %\reg, \offset(%esp)
 	CFI_REL_OFFSET \reg, \offset
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index ec8a52d14ab1..5be1542fbfaf 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -112,23 +112,13 @@ static inline void early_memtest(unsigned long start, unsigned long end)
 }
 #endif
 
-extern unsigned long end_user_pfn;
-
-extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
-extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
-extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-#include <linux/early_res.h>
-
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
-extern int e820_find_active_region(const struct e820entry *ei,
-				  unsigned long start_pfn,
-				  unsigned long last_pfn,
-				  unsigned long *ei_startpfn,
-				  unsigned long *ei_endpfn);
-extern void e820_register_active_regions(int nid, unsigned long start_pfn,
-					 unsigned long end_pfn);
-extern u64 e820_hole_size(u64 start, u64 end);
+extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+
+void memblock_x86_fill(void);
+void memblock_find_dma_reserve(void);
+
 extern void finish_e820_parsing(void);
 extern void e820_reserve_resources(void);
 extern void e820_reserve_resources_late(void);
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 8406ed7f9926..8e4a16508d4e 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -90,7 +90,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
-extern void efi_reserve_early(void);
+extern void efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 4ac5b0f33fc1..43085bfc99c3 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -17,6 +17,7 @@ extern int fix_aperture;
 #define GARTEN		(1<<0)
 #define DISGARTCPU	(1<<4)
 #define DISGARTIO	(1<<5)
+#define DISTLBWALKPRB	(1<<6)
 
 /* GART cache control register bits. */
 #define INVGART		(1<<0)
@@ -27,7 +28,6 @@ extern int fix_aperture;
 #define AMD64_GARTAPERTUREBASE	0x94
 #define AMD64_GARTTABLEBASE	0x98
 #define AMD64_GARTCACHECTL	0x9c
-#define AMD64_GARTEN		(1<<0)
 
 #ifdef CONFIG_GART_IOMMU
 extern int gart_iommu_aperture;
@@ -37,7 +37,7 @@ extern int gart_iommu_aperture_disabled;
 extern void early_gart_iommu_check(void);
 extern int gart_iommu_init(void);
 extern void __init gart_parse_options(char *);
-extern void gart_iommu_hole_init(void);
+extern int gart_iommu_hole_init(void);
 
 #else
 #define gart_iommu_aperture            0
@@ -50,13 +50,27 @@ static inline void early_gart_iommu_check(void)
 static inline void gart_parse_options(char *options)
 {
 }
-static inline void gart_iommu_hole_init(void)
+static inline int gart_iommu_hole_init(void)
 {
+	return -ENODEV;
 }
 #endif
 
 extern int agp_amd64_init(void);
 
+static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order)
+{
+	u32 ctl;
+
+	/*
+	 * Don't enable translation but enable GART IO and CPU accesses.
+	 * Also, set DISTLBWALKPRB since GART tables memory is UC.
+	 */
+	ctl = DISTLBWALKPRB | order << 1;
+
+	pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+}
+
 static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
 {
 	u32 tmp, ctl;
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index a73a8d5a5e69..70626ed96cb5 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -55,6 +55,12 @@ extern int save_i387_xstate_ia32(void __user *buf);
 extern int restore_i387_xstate_ia32(void __user *buf);
 #endif
 
+#ifdef CONFIG_MATH_EMULATION
+extern void finit_soft_fpu(struct i387_soft_struct *soft);
+#else
+static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
+#endif
+
 #define X87_FSW_ES (1 << 7)	/* Exception Summary */
 
 static __always_inline __pure bool use_xsaveopt(void)
@@ -67,6 +73,11 @@ static __always_inline __pure bool use_xsave(void)
 	return static_cpu_has(X86_FEATURE_XSAVE);
 }
 
+static __always_inline __pure bool use_fxsr(void)
+{
+        return static_cpu_has(X86_FEATURE_FXSR);
+}
+
 extern void __sanitize_i387_state(struct task_struct *);
 
 static inline void sanitize_i387_state(struct task_struct *tsk)
@@ -77,19 +88,11 @@ static inline void sanitize_i387_state(struct task_struct *tsk)
 }
 
 #ifdef CONFIG_X86_64
-
-/* Ignore delayed exceptions from user space */
-static inline void tolerant_fwait(void)
-{
-	asm volatile("1: fwait\n"
-		     "2:\n"
-		     _ASM_EXTABLE(1b, 2b));
-}
-
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
 	int err;
 
+	/* See comment in fxsave() below. */
 	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
@@ -98,44 +101,10 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 		     ".previous\n"
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err)
-#if 0 /* See comment in fxsave() below. */
-		     : [fx] "r" (fx), "m" (*fx), "0" (0));
-#else
-		     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
-#endif
+		     : [fx] "R" (fx), "m" (*fx), "0" (0));
 	return err;
 }
 
-/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
-   is pending. Clear the x87 state here by setting it to fixed
-   values. The kernel data segment can be sometimes 0 and sometimes
-   new user value. Both should be ok.
-   Use the PDA as safe address because it should be already in L1. */
-static inline void fpu_clear(struct fpu *fpu)
-{
-	struct xsave_struct *xstate = &fpu->state->xsave;
-	struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
-	/*
-	 * xsave header may indicate the init state of the FP.
-	 */
-	if (use_xsave() &&
-	    !(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-		return;
-
-	if (unlikely(fx->swd & X87_FSW_ES))
-		asm volatile("fnclex");
-	alternative_input(ASM_NOP8 ASM_NOP2,
-			  "    emms\n"		/* clear stack tags */
-			  "    fildl %%gs:0",	/* load to clear state */
-			  X86_FEATURE_FXSAVE_LEAK);
-}
-
-static inline void clear_fpu_state(struct task_struct *tsk)
-{
-	fpu_clear(&tsk->thread.fpu);
-}
-
 static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
 	int err;
@@ -149,6 +118,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 	if (unlikely(err))
 		return -EFAULT;
 
+	/* See comment in fxsave() below. */
 	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
@@ -157,11 +127,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 		     ".previous\n"
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err), "=m" (*fx)
-#if 0 /* See comment in fxsave() below. */
-		     : [fx] "r" (fx), "0" (0));
-#else
-		     : [fx] "cdaSDb" (fx), "0" (0));
-#endif
+		     : [fx] "R" (fx), "0" (0));
 	if (unlikely(err) &&
 	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
 		err = -EFAULT;
@@ -174,57 +140,26 @@ static inline void fpu_fxsave(struct fpu *fpu)
 	/* Using "rex64; fxsave %0" is broken because, if the memory operand
 	   uses any extended registers for addressing, a second REX prefix
 	   will be generated (to the assembler, rex64 followed by semicolon
-	   is a separate instruction), and hence the 64-bitness is lost. */
-#if 0
-	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
-	   starting with gas 2.16. */
-	__asm__ __volatile__("fxsaveq %0"
-			     : "=m" (fpu->state->fxsave));
-#elif 0
-	/* Using, as a workaround, the properly prefixed form below isn't
+	   is a separate instruction), and hence the 64-bitness is lost.
+	   Using "fxsaveq %0" would be the ideal choice, but is only supported
+	   starting with gas 2.16.
+	asm volatile("fxsaveq %0"
+		     : "=m" (fpu->state->fxsave));
+	   Using, as a workaround, the properly prefixed form below isn't
 	   accepted by any binutils version so far released, complaining that
 	   the same type of prefix is used twice if an extended register is
-	   needed for addressing (fix submitted to mainline 2005-11-21). */
-	__asm__ __volatile__("rex64/fxsave %0"
-			     : "=m" (fpu->state->fxsave));
-#else
-	/* This, however, we can work around by forcing the compiler to select
+	   needed for addressing (fix submitted to mainline 2005-11-21).
+	asm volatile("rex64/fxsave %0"
+		     : "=m" (fpu->state->fxsave));
+	   This, however, we can work around by forcing the compiler to select
 	   an addressing mode that doesn't require extended registers. */
-	__asm__ __volatile__("rex64/fxsave (%1)"
-			     : "=m" (fpu->state->fxsave)
-			     : "cdaSDb" (&fpu->state->fxsave));
-#endif
-}
-
-static inline void fpu_save_init(struct fpu *fpu)
-{
-	if (use_xsave())
-		fpu_xsave(fpu);
-	else
-		fpu_fxsave(fpu);
-
-	fpu_clear(fpu);
-}
-
-static inline void __save_init_fpu(struct task_struct *tsk)
-{
-	fpu_save_init(&tsk->thread.fpu);
-	task_thread_info(tsk)->status &= ~TS_USEDFPU;
+	asm volatile("rex64/fxsave (%[fx])"
+		     : "=m" (fpu->state->fxsave)
+		     : [fx] "R" (&fpu->state->fxsave));
 }
 
 #else  /* CONFIG_X86_32 */
 
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-static inline void tolerant_fwait(void)
-{
-	asm volatile("fnclex ; fwait");
-}
-
 /* perform fxrstor iff the processor has extended states, otherwise frstor */
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
@@ -241,6 +176,14 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 	return 0;
 }
 
+static inline void fpu_fxsave(struct fpu *fpu)
+{
+	asm volatile("fxsave %[fx]"
+		     : [fx] "=m" (fpu->state->fxsave));
+}
+
+#endif	/* CONFIG_X86_64 */
+
 /* We need a safe address that is cheap to find and that is already
    in L1 during context switch. The best choices are unfortunately
    different for UP and SMP */
@@ -256,47 +199,33 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 static inline void fpu_save_init(struct fpu *fpu)
 {
 	if (use_xsave()) {
-		struct xsave_struct *xstate = &fpu->state->xsave;
-		struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
 		fpu_xsave(fpu);
 
 		/*
 		 * xsave header may indicate the init state of the FP.
 		 */
-		if (!(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-			goto end;
-
-		if (unlikely(fx->swd & X87_FSW_ES))
-			asm volatile("fnclex");
-
-		/*
-		 * we can do a simple return here or be paranoid :)
-		 */
-		goto clear_state;
+		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
+			return;
+	} else if (use_fxsr()) {
+		fpu_fxsave(fpu);
+	} else {
+		asm volatile("fsave %[fx]; fwait"
+			     : [fx] "=m" (fpu->state->fsave));
+		return;
 	}
 
-	/* Use more nops than strictly needed in case the compiler
-	   varies code */
-	alternative_input(
-		"fnsave %[fx] ;fwait;" GENERIC_NOP8 GENERIC_NOP4,
-		"fxsave %[fx]\n"
-		"bt $7,%[fsw] ; jnc 1f ; fnclex\n1:",
-		X86_FEATURE_FXSR,
-		[fx] "m" (fpu->state->fxsave),
-		[fsw] "m" (fpu->state->fxsave.swd) : "memory");
-clear_state:
+	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+		asm volatile("fnclex");
+
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
 	   values. safe_address is a random variable that should be in L1 */
 	alternative_input(
-		GENERIC_NOP8 GENERIC_NOP2,
+		ASM_NOP8 ASM_NOP2,
 		"emms\n\t"	  	/* clear stack tags */
-		"fildl %[addr]", 	/* set F?P to defined value */
+		"fildl %P[addr]",	/* set F?P to defined value */
 		X86_FEATURE_FXSAVE_LEAK,
 		[addr] "m" (safe_address));
-end:
-	;
 }
 
 static inline void __save_init_fpu(struct task_struct *tsk)
@@ -305,9 +234,6 @@ static inline void __save_init_fpu(struct task_struct *tsk)
 	task_thread_info(tsk)->status &= ~TS_USEDFPU;
 }
 
-
-#endif	/* CONFIG_X86_64 */
-
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
 {
 	return fxrstor_checking(&fpu->state->fxsave);
@@ -344,7 +270,10 @@ static inline void __unlazy_fpu(struct task_struct *tsk)
 static inline void __clear_fpu(struct task_struct *tsk)
 {
 	if (task_thread_info(tsk)->status & TS_USEDFPU) {
-		tolerant_fwait();
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
 		task_thread_info(tsk)->status &= ~TS_USEDFPU;
 		stts();
 	}
@@ -405,19 +334,6 @@ static inline void irq_ts_restore(int TS_state)
 		stts();
 }
 
-#ifdef CONFIG_X86_64
-
-static inline void save_init_fpu(struct task_struct *tsk)
-{
-	__save_init_fpu(tsk);
-	stts();
-}
-
-#define unlazy_fpu	__unlazy_fpu
-#define clear_fpu	__clear_fpu
-
-#else  /* CONFIG_X86_32 */
-
 /*
  * These disable preemption on their own and are safe
  */
@@ -443,8 +359,6 @@ static inline void clear_fpu(struct task_struct *tsk)
 	preempt_enable();
 }
 
-#endif	/* CONFIG_X86_64 */
-
 /*
  * i387 state interaction
  */
@@ -508,7 +422,4 @@ extern void fpu_finit(struct fpu *fpu);
 
 #endif /* __ASSEMBLY__ */
 
-#define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5
-#define PSHUFB_XMM5_XMM6 .byte 0x66, 0x0f, 0x38, 0x00, 0xf5
-
 #endif /* _ASM_X86_I387_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 30a3e9776123..6a45ec41ec26 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -206,6 +206,7 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
 
 extern void iounmap(volatile void __iomem *addr);
 
+extern void set_iounmap_nonlazy(void);
 
 #ifdef __KERNEL__
 
diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h
new file mode 100644
index 000000000000..df55a78888e3
--- /dev/null
+++ b/arch/x86/include/asm/iommu_table.h
@@ -0,0 +1,101 @@
+
+#ifndef _ASM_X86_IOMMU_TABLE_H
+#define _ASM_X86_IOMMU_TABLE_H
+
+#include <asm/swiotlb.h>
+
+/*
+ * History lesson:
+ * The execution chain of IOMMUs in 2.6.36 looks as so:
+ *
+ *            [xen-swiotlb]
+ *                 |
+ *         +----[swiotlb *]--+
+ *        /         |         \
+ *       /          |          \
+ *    [GART]     [Calgary]  [Intel VT-d]
+ *     /
+ *    /
+ * [AMD-Vi]
+ *
+ * *: if SWIOTLB detected 'iommu=soft'/'swiotlb=force' it would skip
+ * over the rest of IOMMUs and unconditionally initialize the SWIOTLB.
+ * Also it would surreptitiously initialize set the swiotlb=1 if there were
+ * more than 4GB and if the user did not pass in 'iommu=off'. The swiotlb
+ * flag would be turned off by all IOMMUs except the Calgary one.
+ *
+ * The IOMMU_INIT* macros allow a similar tree (or more complex if desired)
+ * to be built by defining who we depend on.
+ *
+ * And all that needs to be done is to use one of the macros in the IOMMU
+ * and the pci-dma.c will take care of the rest.
+ */
+
+struct iommu_table_entry {
+	initcall_t	detect;
+	initcall_t	depend;
+	void		(*early_init)(void); /* No memory allocate available. */
+	void		(*late_init)(void); /* Yes, can allocate memory. */
+#define IOMMU_FINISH_IF_DETECTED (1<<0)
+#define IOMMU_DETECTED		 (1<<1)
+	int		flags;
+};
+/*
+ * Macro fills out an entry in the .iommu_table that is equivalent
+ * to the fields that 'struct iommu_table_entry' has. The entries
+ * that are put in the .iommu_table section are not put in any order
+ * hence during boot-time we will have to resort them based on
+ * dependency. */
+
+
+#define __IOMMU_INIT(_detect, _depend, _early_init, _late_init, _finish)\
+	static const struct iommu_table_entry const			\
+		__iommu_entry_##_detect __used				\
+	__attribute__ ((unused, __section__(".iommu_table"),		\
+			aligned((sizeof(void *)))))	\
+	= {_detect, _depend, _early_init, _late_init,			\
+	   _finish ? IOMMU_FINISH_IF_DETECTED : 0}
+/*
+ * The simplest IOMMU definition. Provide the detection routine
+ * and it will be run after the SWIOTLB and the other IOMMUs
+ * that utilize this macro. If the IOMMU is detected (ie, the
+ * detect routine returns a positive value), the other IOMMUs
+ * are also checked. You can use IOMMU_INIT_FINISH if you prefer
+ * to stop detecting the other IOMMUs after yours has been detected.
+ */
+#define IOMMU_INIT_POST(_detect)					\
+	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  0, 0, 0)
+
+#define IOMMU_INIT_POST_FINISH(detect)					\
+	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  0, 0, 1)
+
+/*
+ * A more sophisticated version of IOMMU_INIT. This variant requires:
+ *  a). A detection routine function.
+ *  b). The name of the detection routine we depend on to get called
+ *      before us.
+ *  c). The init routine which gets called if the detection routine
+ *      returns a positive value from the pci_iommu_alloc. This means
+ *      no presence of a memory allocator.
+ *  d). Similar to the 'init', except that this gets called from pci_iommu_init
+ *      where we do have a memory allocator.
+ *
+ * The _CONT vs the _EXIT differs in that the _CONT variant will
+ * continue detecting other IOMMUs in the call list after the
+ * the detection routine returns a positive number. The _EXIT will
+ * stop the execution chain. Both will still call the 'init' and
+ * 'late_init' functions if they are set.
+ */
+#define IOMMU_INIT_FINISH(_detect, _depend, _init, _late_init)		\
+	__IOMMU_INIT(_detect, _depend, _init, _late_init, 1)
+
+#define IOMMU_INIT(_detect, _depend, _init, _late_init)			\
+	__IOMMU_INIT(_detect, _depend, _init, _late_init, 0)
+
+void sort_iommu_table(struct iommu_table_entry *start,
+		      struct iommu_table_entry *finish);
+
+void check_iommu_entries(struct iommu_table_entry *start,
+			 struct iommu_table_entry *finish);
+
+#endif /* _ASM_X86_IOMMU_TABLE_H */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 5458380b6ef8..0bf5b0083650 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -19,18 +19,16 @@ static inline int irq_canonicalize(int irq)
 # define ARCH_HAS_NMI_WATCHDOG
 #endif
 
-#ifdef CONFIG_4KSTACKS
-  extern void irq_ctx_init(int cpu);
-  extern void irq_ctx_exit(int cpu);
-# define __ARCH_HAS_DO_SOFTIRQ
+#ifdef CONFIG_X86_32
+extern void irq_ctx_init(int cpu);
+extern void irq_ctx_exit(int cpu);
 #else
 # define irq_ctx_init(cpu) do { } while (0)
 # define irq_ctx_exit(cpu) do { } while (0)
-# ifdef CONFIG_X86_64
-#  define __ARCH_HAS_DO_SOFTIRQ
-# endif
 #endif
 
+#define __ARCH_HAS_DO_SOFTIRQ
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(void);
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index f275e2244505..8d841505344e 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -3,4 +3,31 @@
 
 #define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
 
+#ifdef CONFIG_INTR_REMAP
+static inline void prepare_irte(struct irte *irte, int vector,
+			        unsigned int dest)
+{
+	memset(irte, 0, sizeof(*irte));
+
+	irte->present = 1;
+	irte->dst_mode = apic->irq_dest_mode;
+	/*
+	 * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
+	 * actual level or edge trigger will be setup in the IO-APIC
+	 * RTE. This will help simplify level triggered irq migration.
+	 * For more details, see the comments (in io_apic.c) explainig IO-APIC
+	 * irq migration in the presence of interrupt-remapping.
+	*/
+	irte->trigger_mode = 0;
+	irte->dlvry_mode = apic->irq_delivery_mode;
+	irte->vector = vector;
+	irte->dest_id = IRTE_DEST(dest);
+	irte->redir_hint = 1;
+}
+#else
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
+{
+}
+#endif
+
 #endif	/* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
new file mode 100644
index 000000000000..f52d42e80585
--- /dev/null
+++ b/arch/x86/include/asm/jump_label.h
@@ -0,0 +1,37 @@
+#ifndef _ASM_X86_JUMP_LABEL_H
+#define _ASM_X86_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/nops.h>
+
+#define JUMP_LABEL_NOP_SIZE 5
+
+# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+
+# define JUMP_LABEL(key, label)					\
+	do {							\
+		asm goto("1:"					\
+			JUMP_LABEL_INITIAL_NOP			\
+			".pushsection __jump_table,  \"a\" \n\t"\
+			_ASM_PTR "1b, %l[" #label "], %c0 \n\t" \
+			".popsection \n\t"			\
+			: :  "i" (key) :  : label);		\
+	} while (0)
+
+#endif /* __KERNEL__ */
+
+#ifdef CONFIG_X86_64
+typedef u64 jump_label_t;
+#else
+typedef u32 jump_label_t;
+#endif
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif
diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h
new file mode 100644
index 000000000000..2c304bb6e072
--- /dev/null
+++ b/arch/x86/include/asm/memblock.h
@@ -0,0 +1,21 @@
+#ifndef _X86_MEMBLOCK_H
+#define _X86_MEMBLOCK_H
+
+#define ARCH_DISCARD_MEMBLOCK
+
+u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align);
+void memblock_x86_to_bootmem(u64 start, u64 end);
+
+void memblock_x86_reserve_range(u64 start, u64 end, char *name);
+void memblock_x86_free_range(u64 start, u64 end);
+struct range;
+int get_free_all_memory_range(struct range **rangep, int nodeid);
+
+void memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long last_pfn);
+u64 memblock_x86_hole_size(u64 start, u64 end);
+u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
+u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
+u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
+
+#endif
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 3e2ce58a31a3..67763c5d8b4e 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -60,12 +60,7 @@
 #endif
 
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_4KSTACKS
-#  define MODULE_STACKSIZE "4KSTACKS "
-# else
-#  define MODULE_STACKSIZE ""
-# endif
-# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
+# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
 #endif
 
 #endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
new file mode 100644
index 000000000000..bcdff997668c
--- /dev/null
+++ b/arch/x86/include/asm/mwait.h
@@ -0,0 +1,15 @@
+#ifndef _ASM_X86_MWAIT_H
+#define _ASM_X86_MWAIT_H
+
+#define MWAIT_SUBSTATE_MASK		0xf
+#define MWAIT_CSTATE_MASK		0xf
+#define MWAIT_SUBSTATE_SIZE		4
+#define MWAIT_MAX_NUM_CSTATES		8
+
+#define CPUID_MWAIT_LEAF		5
+#define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1
+#define CPUID5_ECX_INTERRUPT_BREAK	0x2
+
+#define MWAIT_ECX_INTERRUPT_BREAK	0x1
+
+#endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h
index 08fde475cb3b..2a8478140bb3 100644
--- a/arch/x86/include/asm/olpc_ofw.h
+++ b/arch/x86/include/asm/olpc_ofw.h
@@ -21,10 +21,14 @@ extern void olpc_ofw_detect(void);
 /* install OFW's pde permanently into the kernel's pgtable */
 extern void setup_olpc_ofw_pgd(void);
 
+/* check if OFW was detected during boot */
+extern bool olpc_ofw_present(void);
+
 #else /* !CONFIG_OLPC_OPENFIRMWARE */
 
 static inline void olpc_ofw_detect(void) { }
 static inline void setup_olpc_ofw_pgd(void) { }
+static inline bool olpc_ofw_present(void) { return false; }
 
 #endif /* !CONFIG_OLPC_OPENFIRMWARE */
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 6f1b7331313f..ade619ff9e2a 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -15,11 +15,7 @@
  */
 #define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 
-#ifdef CONFIG_4KSTACKS
-#define THREAD_ORDER	0
-#else
 #define THREAD_ORDER	1
-#endif
 #define THREAD_SIZE 	(PAGE_SIZE << THREAD_ORDER)
 
 #define STACKFAULT_STACK 0
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5653f43d90e5..edecb4ed2210 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -416,11 +416,6 @@ static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
 	PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
 }
 
-static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
-					    unsigned long start, unsigned long count)
-{
-	PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count);
-}
 static inline void paravirt_release_pmd(unsigned long pfn)
 {
 	PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index db9ef5532341..b82bac975250 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -255,7 +255,6 @@ struct pv_mmu_ops {
 	 */
 	void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
 	void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
-	void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
 	void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
 	void (*release_pte)(unsigned long pfn);
 	void (*release_pmd)(unsigned long pfn);
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index def500776b16..a70cd216be5d 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -36,19 +36,6 @@
 #define P4_ESCR_EMASK(v)	((v) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_TAG(v)		((v) << P4_ESCR_TAG_SHIFT)
 
-/* Non HT mask */
-#define P4_ESCR_MASK			\
-	(P4_ESCR_EVENT_MASK	|	\
-	P4_ESCR_EVENTMASK_MASK	|	\
-	P4_ESCR_TAG_MASK	|	\
-	P4_ESCR_TAG_ENABLE	|	\
-	P4_ESCR_T0_OS		|	\
-	P4_ESCR_T0_USR)
-
-/* HT mask */
-#define P4_ESCR_MASK_HT			\
-	(P4_ESCR_MASK |	P4_ESCR_T1_OS | P4_ESCR_T1_USR)
-
 #define P4_CCCR_OVF			0x80000000U
 #define P4_CCCR_CASCADE			0x40000000U
 #define P4_CCCR_OVF_PMI_T0		0x04000000U
@@ -70,23 +57,6 @@
 #define P4_CCCR_THRESHOLD(v)		((v) << P4_CCCR_THRESHOLD_SHIFT)
 #define P4_CCCR_ESEL(v)			((v) << P4_CCCR_ESCR_SELECT_SHIFT)
 
-/* Non HT mask */
-#define P4_CCCR_MASK				\
-	(P4_CCCR_OVF			|	\
-	P4_CCCR_CASCADE			|	\
-	P4_CCCR_OVF_PMI_T0		|	\
-	P4_CCCR_FORCE_OVF		|	\
-	P4_CCCR_EDGE			|	\
-	P4_CCCR_THRESHOLD_MASK		|	\
-	P4_CCCR_COMPLEMENT		|	\
-	P4_CCCR_COMPARE			|	\
-	P4_CCCR_ESCR_SELECT_MASK	|	\
-	P4_CCCR_ENABLE)
-
-/* HT mask */
-#define P4_CCCR_MASK_HT				\
-	(P4_CCCR_MASK | P4_CCCR_OVF_PMI_T1 | P4_CCCR_THREAD_ANY)
-
 #define P4_GEN_ESCR_EMASK(class, name, bit)	\
 	class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_EMASK_BIT(class, name)		class##__##name
@@ -127,6 +97,28 @@
 #define P4_CONFIG_HT_SHIFT		63
 #define P4_CONFIG_HT			(1ULL << P4_CONFIG_HT_SHIFT)
 
+/*
+ * The bits we allow to pass for RAW events
+ */
+#define P4_CONFIG_MASK_ESCR		\
+	P4_ESCR_EVENT_MASK	|	\
+	P4_ESCR_EVENTMASK_MASK	|	\
+	P4_ESCR_TAG_MASK	|	\
+	P4_ESCR_TAG_ENABLE
+
+#define P4_CONFIG_MASK_CCCR		\
+	P4_CCCR_EDGE		|	\
+	P4_CCCR_THRESHOLD_MASK	|	\
+	P4_CCCR_COMPLEMENT	|	\
+	P4_CCCR_COMPARE		|	\
+	P4_CCCR_THREAD_ANY	|	\
+	P4_CCCR_RESERVED
+
+/* some dangerous bits are reserved for kernel internals */
+#define P4_CONFIG_MASK				  	  \
+	(p4_config_pack_escr(P4_CONFIG_MASK_ESCR))	| \
+	(p4_config_pack_cccr(P4_CONFIG_MASK_CCCR))
+
 static inline bool p4_is_event_cascaded(u64 config)
 {
 	u32 cccr = p4_config_unpack_cccr(config);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index a34c785c5a63..2d0a33bd2971 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -603,6 +603,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
 	pte_update(mm, addr, ptep);
 }
 
+#define flush_tlb_fix_spurious_fault(vma, address)
+
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
  *
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 076052cd62be..f96ac9bedf75 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -102,6 +102,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
 	native_set_pgd(pgd, native_make_pgd(0));
 }
 
+extern void sync_global_pgds(unsigned long start, unsigned long end);
+
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 325b7bdbebaa..cae9c3cb95cf 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -110,6 +110,8 @@ struct cpuinfo_x86 {
 	u16			phys_proc_id;
 	/* Core id: */
 	u16			cpu_core_id;
+	/* Compute unit id */
+	u8			compute_unit_id;
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 #endif
@@ -602,7 +604,7 @@ extern unsigned long		mmu_cr4_features;
 
 static inline void set_in_cr4(unsigned long mask)
 {
-	unsigned cr4;
+	unsigned long cr4;
 
 	mmu_cr4_features |= mask;
 	cr4 = read_cr4();
@@ -612,7 +614,7 @@ static inline void set_in_cr4(unsigned long mask)
 
 static inline void clear_in_cr4(unsigned long mask)
 {
-	unsigned cr4;
+	unsigned long cr4;
 
 	mmu_cr4_features &= ~mask;
 	cr4 = read_cr4();
@@ -764,29 +766,6 @@ extern unsigned long		idle_halt;
 extern unsigned long		idle_nomwait;
 extern bool			c1e_detected;
 
-/*
- * on systems with caches, caches must be flashed as the absolute
- * last instruction before going into a suspended halt.  Otherwise,
- * dirty data can linger in the cache and become stale on resume,
- * leading to strange errors.
- *
- * perform a variety of operations to guarantee that the compiler
- * will not reorder instructions.  wbinvd itself is serializing
- * so the processor will not reorder.
- *
- * Systems without cache can just go into halt.
- */
-static inline void wbinvd_halt(void)
-{
-	mb();
-	/* check for clflush to determine if wbinvd is legal */
-	if (cpu_has_clflush)
-		asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory");
-	else
-		while (1)
-			halt();
-}
-
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index 8085277e1b8b..977f1761a25d 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -5,17 +5,26 @@
 
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
-extern int __init pci_swiotlb_detect(void);
+extern int __init pci_swiotlb_detect_override(void);
+extern int __init pci_swiotlb_detect_4gb(void);
 extern void __init pci_swiotlb_init(void);
+extern void __init pci_swiotlb_late_init(void);
 #else
 #define swiotlb 0
-static inline int pci_swiotlb_detect(void)
+static inline int pci_swiotlb_detect_override(void)
+{
+	return 0;
+}
+static inline int pci_swiotlb_detect_4gb(void)
 {
 	return 0;
 }
 static inline void pci_swiotlb_init(void)
 {
 }
+static inline void pci_swiotlb_late_init(void)
+{
+}
 #endif
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
diff --git a/arch/x86/include/asm/vmi.h b/arch/x86/include/asm/vmi.h
deleted file mode 100644
index 61e08c0a2907..000000000000
--- a/arch/x86/include/asm/vmi.h
+++ /dev/null
@@ -1,269 +0,0 @@
-/*
- * VMI interface definition
- *
- * Copyright (C) 2005, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Maintained by: Zachary Amsden zach@vmware.com
- *
- */
-#include <linux/types.h>
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI Option ROM API
- *
- *---------------------------------------------------------------------
- */
-#define VMI_SIGNATURE 0x696d5663   /* "cVmi" */
-
-#define PCI_VENDOR_ID_VMWARE            0x15AD
-#define PCI_DEVICE_ID_VMWARE_VMI        0x0801
-
-/*
- * We use two version numbers for compatibility, with the major
- * number signifying interface breakages, and the minor number
- * interface extensions.
- */
-#define VMI_API_REV_MAJOR       3
-#define VMI_API_REV_MINOR       0
-
-#define VMI_CALL_CPUID			0
-#define VMI_CALL_WRMSR			1
-#define VMI_CALL_RDMSR			2
-#define VMI_CALL_SetGDT			3
-#define VMI_CALL_SetLDT			4
-#define VMI_CALL_SetIDT			5
-#define VMI_CALL_SetTR			6
-#define VMI_CALL_GetGDT			7
-#define VMI_CALL_GetLDT			8
-#define VMI_CALL_GetIDT			9
-#define VMI_CALL_GetTR			10
-#define VMI_CALL_WriteGDTEntry		11
-#define VMI_CALL_WriteLDTEntry		12
-#define VMI_CALL_WriteIDTEntry		13
-#define VMI_CALL_UpdateKernelStack	14
-#define VMI_CALL_SetCR0			15
-#define VMI_CALL_SetCR2			16
-#define VMI_CALL_SetCR3			17
-#define VMI_CALL_SetCR4			18
-#define VMI_CALL_GetCR0			19
-#define VMI_CALL_GetCR2			20
-#define VMI_CALL_GetCR3			21
-#define VMI_CALL_GetCR4			22
-#define VMI_CALL_WBINVD			23
-#define VMI_CALL_SetDR			24
-#define VMI_CALL_GetDR			25
-#define VMI_CALL_RDPMC			26
-#define VMI_CALL_RDTSC			27
-#define VMI_CALL_CLTS			28
-#define VMI_CALL_EnableInterrupts	29
-#define VMI_CALL_DisableInterrupts	30
-#define VMI_CALL_GetInterruptMask	31
-#define VMI_CALL_SetInterruptMask	32
-#define VMI_CALL_IRET			33
-#define VMI_CALL_SYSEXIT		34
-#define VMI_CALL_Halt			35
-#define VMI_CALL_Reboot			36
-#define VMI_CALL_Shutdown		37
-#define VMI_CALL_SetPxE			38
-#define VMI_CALL_SetPxELong		39
-#define VMI_CALL_UpdatePxE		40
-#define VMI_CALL_UpdatePxELong		41
-#define VMI_CALL_MachineToPhysical	42
-#define VMI_CALL_PhysicalToMachine	43
-#define VMI_CALL_AllocatePage		44
-#define VMI_CALL_ReleasePage		45
-#define VMI_CALL_InvalPage		46
-#define VMI_CALL_FlushTLB		47
-#define VMI_CALL_SetLinearMapping	48
-
-#define VMI_CALL_SetIOPLMask		61
-#define VMI_CALL_SetInitialAPState	62
-#define VMI_CALL_APICWrite		63
-#define VMI_CALL_APICRead		64
-#define VMI_CALL_IODelay		65
-#define VMI_CALL_SetLazyMode		73
-
-/*
- *---------------------------------------------------------------------
- *
- * MMU operation flags
- *
- *---------------------------------------------------------------------
- */
-
-/* Flags used by VMI_{Allocate|Release}Page call */
-#define VMI_PAGE_PAE             0x10  /* Allocate PAE shadow */
-#define VMI_PAGE_CLONE           0x20  /* Clone from another shadow */
-#define VMI_PAGE_ZEROED          0x40  /* Page is pre-zeroed */
-
-
-/* Flags shared by Allocate|Release Page and PTE updates */
-#define VMI_PAGE_PT              0x01
-#define VMI_PAGE_PD              0x02
-#define VMI_PAGE_PDP             0x04
-#define VMI_PAGE_PML4            0x08
-
-#define VMI_PAGE_NORMAL          0x00 /* for debugging */
-
-/* Flags used by PTE updates */
-#define VMI_PAGE_CURRENT_AS      0x10 /* implies VMI_PAGE_VA_MASK is valid */
-#define VMI_PAGE_DEFER           0x20 /* may queue update until TLB inval */
-#define VMI_PAGE_VA_MASK         0xfffff000
-
-#ifdef CONFIG_X86_PAE
-#define VMI_PAGE_L1		(VMI_PAGE_PT | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2		(VMI_PAGE_PD | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#else
-#define VMI_PAGE_L1		(VMI_PAGE_PT | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2		(VMI_PAGE_PD | VMI_PAGE_ZEROED)
-#endif
-
-/* Flags used by VMI_FlushTLB call */
-#define VMI_FLUSH_TLB            0x01
-#define VMI_FLUSH_GLOBAL         0x02
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI relocation definitions for ROM call get_reloc
- *
- *---------------------------------------------------------------------
- */
-
-/* VMI Relocation types */
-#define VMI_RELOCATION_NONE     0
-#define VMI_RELOCATION_CALL_REL 1
-#define VMI_RELOCATION_JUMP_REL 2
-#define VMI_RELOCATION_NOP	3
-
-#ifndef __ASSEMBLY__
-struct vmi_relocation_info {
-	unsigned char           *eip;
-	unsigned char           type;
-	unsigned char           reserved[3];
-};
-#endif
-
-
-/*
- *---------------------------------------------------------------------
- *
- *  Generic ROM structures and definitions
- *
- *---------------------------------------------------------------------
- */
-
-#ifndef __ASSEMBLY__
-
-struct vrom_header {
-	u16     rom_signature;  /* option ROM signature */
-	u8      rom_length;     /* ROM length in 512 byte chunks */
-	u8      rom_entry[4];   /* 16-bit code entry point */
-	u8      rom_pad0;       /* 4-byte align pad */
-	u32     vrom_signature; /* VROM identification signature */
-	u8      api_version_min;/* Minor version of API */
-	u8      api_version_maj;/* Major version of API */
-	u8      jump_slots;     /* Number of jump slots */
-	u8      reserved1;      /* Reserved for expansion */
-	u32     virtual_top;    /* Hypervisor virtual address start */
-	u16     reserved2;      /* Reserved for expansion */
-	u16	license_offs;	/* Offset to License string */
-	u16     pci_header_offs;/* Offset to PCI OPROM header */
-	u16     pnp_header_offs;/* Offset to PnP OPROM header */
-	u32     rom_pad3;       /* PnP reserverd / VMI reserved */
-	u8      reserved[96];   /* Reserved for headers */
-	char    vmi_init[8];    /* VMI_Init jump point */
-	char    get_reloc[8];   /* VMI_GetRelocationInfo jump point */
-} __attribute__((packed));
-
-struct pnp_header {
-	char sig[4];
-	char rev;
-	char size;
-	short next;
-	short res;
-	long devID;
-	unsigned short manufacturer_offset;
-	unsigned short product_offset;
-} __attribute__((packed));
-
-struct pci_header {
-	char sig[4];
-	short vendorID;
-	short deviceID;
-	short vpdData;
-	short size;
-	char rev;
-	char class;
-	char subclass;
-	char interface;
-	short chunks;
-	char rom_version_min;
-	char rom_version_maj;
-	char codetype;
-	char lastRom;
-	short reserved;
-} __attribute__((packed));
-
-/* Function prototypes for bootstrapping */
-#ifdef CONFIG_VMI
-extern void vmi_init(void);
-extern void vmi_activate(void);
-extern void vmi_bringup(void);
-#else
-static inline void vmi_init(void) {}
-static inline void vmi_activate(void) {}
-static inline void vmi_bringup(void) {}
-#endif
-
-/* State needed to start an application processor in an SMP system. */
-struct vmi_ap_state {
-	u32 cr0;
-	u32 cr2;
-	u32 cr3;
-	u32 cr4;
-
-	u64 efer;
-
-	u32 eip;
-	u32 eflags;
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-	u32 esp;
-	u32 ebp;
-	u32 esi;
-	u32 edi;
-	u16 cs;
-	u16 ss;
-	u16 ds;
-	u16 es;
-	u16 fs;
-	u16 gs;
-	u16 ldtr;
-
-	u16 gdtr_limit;
-	u32 gdtr_base;
-	u32 idtr_base;
-	u16 idtr_limit;
-};
-
-#endif
diff --git a/arch/x86/include/asm/vmi_time.h b/arch/x86/include/asm/vmi_time.h
deleted file mode 100644
index c6e0bee93e3c..000000000000
--- a/arch/x86/include/asm/vmi_time.h
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * VMI Time wrappers
- *
- * Copyright (C) 2006, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to dhecht@vmware.com
- *
- */
-
-#ifndef _ASM_X86_VMI_TIME_H
-#define _ASM_X86_VMI_TIME_H
-
-/*
- * Raw VMI call indices for timer functions
- */
-#define VMI_CALL_GetCycleFrequency	66
-#define VMI_CALL_GetCycleCounter	67
-#define VMI_CALL_SetAlarm		68
-#define VMI_CALL_CancelAlarm		69
-#define VMI_CALL_GetWallclockTime	70
-#define VMI_CALL_WallclockUpdated	71
-
-/* Cached VMI timer operations */
-extern struct vmi_timer_ops {
-	u64 (*get_cycle_frequency)(void);
-	u64 (*get_cycle_counter)(int);
-	u64 (*get_wallclock)(void);
-	int (*wallclock_updated)(void);
-	void (*set_alarm)(u32 flags, u64 expiry, u64 period);
-	void (*cancel_alarm)(u32 flags);
-} vmi_timer_ops;
-
-/* Prototypes */
-extern void __init vmi_time_init(void);
-extern unsigned long vmi_get_wallclock(void);
-extern int vmi_set_wallclock(unsigned long now);
-extern unsigned long long vmi_sched_clock(void);
-extern unsigned long vmi_tsc_khz(void);
-
-#ifdef CONFIG_X86_LOCAL_APIC
-extern void __devinit vmi_time_bsp_init(void);
-extern void __devinit vmi_time_ap_init(void);
-#endif
-
-/*
- * When run under a hypervisor, a vcpu is always in one of three states:
- * running, halted, or ready.  The vcpu is in the 'running' state if it
- * is executing.  When the vcpu executes the halt interface, the vcpu
- * enters the 'halted' state and remains halted until there is some work
- * pending for the vcpu (e.g. an alarm expires, host I/O completes on
- * behalf of virtual I/O).  At this point, the vcpu enters the 'ready'
- * state (waiting for the hypervisor to reschedule it).  Finally, at any
- * time when the vcpu is not in the 'running' state nor the 'halted'
- * state, it is in the 'ready' state.
- *
- * Real time is advances while the vcpu is 'running', 'ready', or
- * 'halted'.  Stolen time is the time in which the vcpu is in the
- * 'ready' state.  Available time is the remaining time -- the vcpu is
- * either 'running' or 'halted'.
- *
- * All three views of time are accessible through the VMI cycle
- * counters.
- */
-
-/* The cycle counters. */
-#define VMI_CYCLES_REAL         0
-#define VMI_CYCLES_AVAILABLE    1
-#define VMI_CYCLES_STOLEN       2
-
-/* The alarm interface 'flags' bits */
-#define VMI_ALARM_COUNTERS      2
-
-#define VMI_ALARM_COUNTER_MASK  0x000000ff
-
-#define VMI_ALARM_WIRED_IRQ0    0x00000000
-#define VMI_ALARM_WIRED_LVTT    0x00010000
-
-#define VMI_ALARM_IS_ONESHOT    0x00000000
-#define VMI_ALARM_IS_PERIODIC   0x00000100
-
-#define CONFIG_VMI_ALARM_HZ	100
-
-#endif /* _ASM_X86_VMI_TIME_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index fedf32a8c3ec..c0cc701dc225 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -34,7 +34,7 @@ GCOV_PROFILE_paravirt.o		:= n
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o x86_init.o i8259.o irqinit.o
+obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
@@ -44,6 +44,7 @@ obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
+obj-y			+= pci-iommu_table.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o
@@ -89,11 +90,10 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_APB_TIMER)		+= apb_timer.o
 
-obj-$(CONFIG_K8_NB)		+= k8.o
+obj-$(CONFIG_AMD_NB)		+= amd_nb.o
 obj-$(CONFIG_DEBUG_RODATA_TEST)	+= test_rodata.o
 obj-$(CONFIG_DEBUG_NX_TEST)	+= test_nx.o
 
-obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o
 obj-$(CONFIG_KVM_CLOCK)		+= kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index fb16f17e59be..5812404a0d4c 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -13,6 +13,7 @@
 
 #include <acpi/processor.h>
 #include <asm/acpi.h>
+#include <asm/mwait.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
@@ -65,16 +66,6 @@ static struct cstate_entry __percpu *cpu_cstate_entry;	/* per CPU ptr */
 
 static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
 
-#define MWAIT_SUBSTATE_MASK	(0xf)
-#define MWAIT_CSTATE_MASK	(0xf)
-#define MWAIT_SUBSTATE_SIZE	(4)
-
-#define CPUID_MWAIT_LEAF (5)
-#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
-#define CPUID5_ECX_INTERRUPT_BREAK	(0x2)
-
-#define MWAIT_ECX_INTERRUPT_BREAK	(0x1)
-
 #define NATIVE_CSTATE_BEYOND_HALT	(2)
 
 static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 33cec152070d..e1252074ea40 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -7,6 +7,7 @@
 
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/dmi.h>
 #include <linux/cpumask.h>
 #include <asm/segment.h>
@@ -125,7 +126,7 @@ void acpi_restore_state_mem(void)
  */
 void __init acpi_reserve_wakeup_memory(void)
 {
-	unsigned long mem;
+	phys_addr_t mem;
 
 	if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) {
 		printk(KERN_ERR
@@ -133,15 +134,15 @@ void __init acpi_reserve_wakeup_memory(void)
 		return;
 	}
 
-	mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
+	mem = memblock_find_in_range(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
 
-	if (mem == -1L) {
+	if (mem == MEMBLOCK_ERROR) {
 		printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
 		return;
 	}
 	acpi_realmode = (unsigned long) phys_to_virt(mem);
 	acpi_wakeup_address = mem;
-	reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
+	memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
 }
 
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index f65ab8b014c4..cb0e6d385f6d 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -195,7 +195,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
-static void *text_poke_early(void *addr, const void *opcode, size_t len);
+void *text_poke_early(void *addr, const void *opcode, size_t len);
 
 /* Replace instructions with better alternatives for this CPU type.
    This runs before SMP is initialized to avoid SMP problems with
@@ -522,7 +522,7 @@ void __init alternative_instructions(void)
  * instructions. And on the local CPU you need to be protected again NMI or MCE
  * handlers seeing an inconsistent instruction while you patch.
  */
-static void *__init_or_module text_poke_early(void *addr, const void *opcode,
+void *__init_or_module text_poke_early(void *addr, const void *opcode,
 					      size_t len)
 {
 	unsigned long flags;
@@ -641,3 +641,67 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
 	return addr;
 }
 
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
+
+unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+
+void __init arch_init_ideal_nop5(void)
+{
+	extern const unsigned char ftrace_test_p6nop[];
+	extern const unsigned char ftrace_test_nop5[];
+	extern const unsigned char ftrace_test_jmp[];
+	int faulted = 0;
+
+	/*
+	 * There is no good nop for all x86 archs.
+	 * We will default to using the P6_NOP5, but first we
+	 * will test to make sure that the nop will actually
+	 * work on this CPU. If it faults, we will then
+	 * go to a lesser efficient 5 byte nop. If that fails
+	 * we then just use a jmp as our nop. This isn't the most
+	 * efficient nop, but we can not use a multi part nop
+	 * since we would then risk being preempted in the middle
+	 * of that nop, and if we enabled tracing then, it might
+	 * cause a system crash.
+	 *
+	 * TODO: check the cpuid to determine the best nop.
+	 */
+	asm volatile (
+		"ftrace_test_jmp:"
+		"jmp ftrace_test_p6nop\n"
+		"nop\n"
+		"nop\n"
+		"nop\n"  /* 2 byte jmp + 3 bytes */
+		"ftrace_test_p6nop:"
+		P6_NOP5
+		"jmp 1f\n"
+		"ftrace_test_nop5:"
+		".byte 0x66,0x66,0x66,0x66,0x90\n"
+		"1:"
+		".section .fixup, \"ax\"\n"
+		"2:	movl $1, %0\n"
+		"	jmp ftrace_test_nop5\n"
+		"3:	movl $2, %0\n"
+		"	jmp 1b\n"
+		".previous\n"
+		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
+		_ASM_EXTABLE(ftrace_test_nop5, 3b)
+		: "=r"(faulted) : "0" (faulted));
+
+	switch (faulted) {
+	case 0:
+		pr_info("converting mcount calls to 0f 1f 44 00 00\n");
+		memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5);
+		break;
+	case 1:
+		pr_info("converting mcount calls to 66 66 66 66 90\n");
+		memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5);
+		break;
+	case 2:
+		pr_info("converting mcount calls to jmp . + 5\n");
+		memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5);
+		break;
+	}
+
+}
+#endif
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 5a170cbbbed8..aaf4b99c1c7d 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -31,7 +31,7 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/x86_init.h>
-
+#include <asm/iommu_table.h>
 /*
  * definitions for the ACPI scanning code
  */
@@ -1405,13 +1405,13 @@ static int __init early_amd_iommu_detect(struct acpi_table_header *table)
 	return 0;
 }
 
-void __init amd_iommu_detect(void)
+int __init amd_iommu_detect(void)
 {
 	if (no_iommu || (iommu_detected && !gart_iommu_aperture))
-		return;
+		return -ENODEV;
 
 	if (amd_iommu_disabled)
-		return;
+		return -ENODEV;
 
 	if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) {
 		iommu_detected = 1;
@@ -1420,7 +1420,9 @@ void __init amd_iommu_detect(void)
 
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
+		return 1;
 	}
+	return -ENODEV;
 }
 
 /****************************************************************************
@@ -1451,3 +1453,8 @@ static int __init parse_amd_iommu_options(char *str)
 
 __setup("amd_iommu_dump", parse_amd_iommu_dump);
 __setup("amd_iommu=", parse_amd_iommu_options);
+
+IOMMU_INIT_FINISH(amd_iommu_detect,
+		  gart_iommu_hole_init,
+		  0,
+		  0);
diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/amd_nb.c
index 0f7bc20cfcde..8f6463d8ed0d 100644
--- a/arch/x86/kernel/k8.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -8,21 +8,19 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <asm/k8.h>
-
-int num_k8_northbridges;
-EXPORT_SYMBOL(num_k8_northbridges);
+#include <asm/amd_nb.h>
 
 static u32 *flush_words;
 
 struct pci_device_id k8_nb_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) },
 	{}
 };
 EXPORT_SYMBOL(k8_nb_ids);
 
-struct pci_dev **k8_northbridges;
+struct k8_northbridge_info k8_northbridges;
 EXPORT_SYMBOL(k8_northbridges);
 
 static struct pci_dev *next_k8_northbridge(struct pci_dev *dev)
@@ -40,36 +38,45 @@ int cache_k8_northbridges(void)
 	int i;
 	struct pci_dev *dev;
 
-	if (num_k8_northbridges)
+	if (k8_northbridges.num)
 		return 0;
 
 	dev = NULL;
 	while ((dev = next_k8_northbridge(dev)) != NULL)
-		num_k8_northbridges++;
+		k8_northbridges.num++;
+
+	/* some CPU families (e.g. family 0x11) do not support GART */
+	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+	    boot_cpu_data.x86 == 0x15)
+		k8_northbridges.gart_supported = 1;
 
-	k8_northbridges = kmalloc((num_k8_northbridges + 1) * sizeof(void *),
-				  GFP_KERNEL);
-	if (!k8_northbridges)
+	k8_northbridges.nb_misc = kmalloc((k8_northbridges.num + 1) *
+					  sizeof(void *), GFP_KERNEL);
+	if (!k8_northbridges.nb_misc)
 		return -ENOMEM;
 
-	if (!num_k8_northbridges) {
-		k8_northbridges[0] = NULL;
+	if (!k8_northbridges.num) {
+		k8_northbridges.nb_misc[0] = NULL;
 		return 0;
 	}
 
-	flush_words = kmalloc(num_k8_northbridges * sizeof(u32), GFP_KERNEL);
-	if (!flush_words) {
-		kfree(k8_northbridges);
-		return -ENOMEM;
+	if (k8_northbridges.gart_supported) {
+		flush_words = kmalloc(k8_northbridges.num * sizeof(u32),
+				      GFP_KERNEL);
+		if (!flush_words) {
+			kfree(k8_northbridges.nb_misc);
+			return -ENOMEM;
+		}
 	}
 
 	dev = NULL;
 	i = 0;
 	while ((dev = next_k8_northbridge(dev)) != NULL) {
-		k8_northbridges[i] = dev;
-		pci_read_config_dword(dev, 0x9c, &flush_words[i++]);
+		k8_northbridges.nb_misc[i] = dev;
+		if (k8_northbridges.gart_supported)
+			pci_read_config_dword(dev, 0x9c, &flush_words[i++]);
 	}
-	k8_northbridges[i] = NULL;
+	k8_northbridges.nb_misc[i] = NULL;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(cache_k8_northbridges);
@@ -93,22 +100,25 @@ void k8_flush_garts(void)
 	unsigned long flags;
 	static DEFINE_SPINLOCK(gart_lock);
 
+	if (!k8_northbridges.gart_supported)
+		return;
+
 	/* Avoid races between AGP and IOMMU. In theory it's not needed
 	   but I'm not sure if the hardware won't lose flush requests
 	   when another is pending. This whole thing is so expensive anyways
 	   that it doesn't matter to serialize more. -AK */
 	spin_lock_irqsave(&gart_lock, flags);
 	flushed = 0;
-	for (i = 0; i < num_k8_northbridges; i++) {
-		pci_write_config_dword(k8_northbridges[i], 0x9c,
+	for (i = 0; i < k8_northbridges.num; i++) {
+		pci_write_config_dword(k8_northbridges.nb_misc[i], 0x9c,
 				       flush_words[i]|1);
 		flushed++;
 	}
-	for (i = 0; i < num_k8_northbridges; i++) {
+	for (i = 0; i < k8_northbridges.num; i++) {
 		u32 w;
 		/* Make sure the hardware actually executed the flush*/
 		for (;;) {
-			pci_read_config_dword(k8_northbridges[i],
+			pci_read_config_dword(k8_northbridges.nb_misc[i],
 					      0x9c, &w);
 			if (!(w & 1))
 				break;
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 8dd77800ff5d..6fe2b5cb4f3c 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -343,7 +343,7 @@ void apbt_setup_secondary_clock(void)
 
 	/* Don't register boot CPU clockevent */
 	cpu = smp_processor_id();
-	if (cpu == boot_cpu_id)
+	if (!cpu)
 		return;
 	/*
 	 * We need to calculate the scaled math multiplication factor for
@@ -398,7 +398,7 @@ static int apbt_cpuhp_notify(struct notifier_block *n,
 		}
 		break;
 	default:
-		pr_debug(KERN_INFO "APBT notified %lu, no action\n", action);
+		pr_debug("APBT notified %lu, no action\n", action);
 	}
 	return NOTIFY_OK;
 }
@@ -552,7 +552,7 @@ bad_count:
 		pr_debug("APB CS going back %lx:%lx:%lx ",
 			 t2, last_read, t2 - last_read);
 bad_count_x3:
-		pr_debug(KERN_INFO "tripple check enforced\n");
+		pr_debug("triple check enforced\n");
 		t0 = apbt_readl(phy_cs_timer_id,
 				APBTMR_N_CURRENT_VALUE);
 		udelay(1);
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index a2e0caf26e17..b3a16e8f0703 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -27,7 +27,7 @@
 #include <asm/gart.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/x86_init.h>
 
 int gart_iommu_aperture;
@@ -307,7 +307,7 @@ void __init early_gart_iommu_check(void)
 				continue;
 
 			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
-			aper_enabled = ctl & AMD64_GARTEN;
+			aper_enabled = ctl & GARTEN;
 			aper_order = (ctl >> 1) & 7;
 			aper_size = (32 * 1024 * 1024) << aper_order;
 			aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
@@ -362,7 +362,7 @@ void __init early_gart_iommu_check(void)
 				continue;
 
 			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
-			ctl &= ~AMD64_GARTEN;
+			ctl &= ~GARTEN;
 			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
 		}
 	}
@@ -371,7 +371,7 @@ void __init early_gart_iommu_check(void)
 
 static int __initdata printed_gart_size_msg;
 
-void __init gart_iommu_hole_init(void)
+int __init gart_iommu_hole_init(void)
 {
 	u32 agp_aper_base = 0, agp_aper_order = 0;
 	u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
@@ -381,7 +381,7 @@ void __init gart_iommu_hole_init(void)
 
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
-		return;
+		return -ENODEV;
 
 	printk(KERN_INFO  "Checking aperture...\n");
 
@@ -463,8 +463,9 @@ out:
 			unsigned long n = (32 * 1024 * 1024) << last_aper_order;
 
 			insert_aperture_resource((u32)last_aper_base, n);
+			return 1;
 		}
-		return;
+		return 0;
 	}
 
 	if (!fallback_aper_force) {
@@ -500,13 +501,18 @@ out:
 			panic("Not enough memory for aperture");
 		}
 	} else {
-		return;
+		return 0;
 	}
 
 	/* Fix up the north bridges */
 	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
-		int bus;
-		int dev_base, dev_limit;
+		int bus, dev_base, dev_limit;
+
+		/*
+		 * 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;
 
 		bus = bus_dev_ranges[i].bus;
 		dev_base = bus_dev_ranges[i].dev_base;
@@ -515,13 +521,12 @@ out:
 			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
-			/* Don't enable translation yet. That is done later.
-			   Assume this BIOS didn't initialise the GART so
-			   just overwrite all previous bits */
-			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, aper_order << 1);
+			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
 			write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25);
 		}
 	}
 
 	set_up_gart_resume(aper_order, aper_alloc);
+
+	return 1;
 }
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e3b534cda49a..8cf86fb3b4e3 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1665,10 +1665,7 @@ int __init APIC_init_uniprocessor(void)
 	}
 #endif
 
-#ifndef CONFIG_SMP
-	enable_IR_x2apic();
 	default_setup_apic_routing();
-#endif
 
 	verify_local_APIC();
 	connect_bsp_APIC();
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 5c5b8f3dddb5..9508811e8448 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -162,7 +162,7 @@ int __init arch_early_irq_init(void)
 
 	cfg = irq_cfgx;
 	count = ARRAY_SIZE(irq_cfgx);
-	node= cpu_to_node(boot_cpu_id);
+	node = cpu_to_node(0);
 
 	for (i = 0; i < count; i++) {
 		desc = irq_to_desc(i);
@@ -1382,21 +1382,7 @@ int setup_ioapic_entry(int apic_id, int irq,
 		if (index < 0)
 			panic("Failed to allocate IRTE for ioapic %d\n", apic_id);
 
-		memset(&irte, 0, sizeof(irte));
-
-		irte.present = 1;
-		irte.dst_mode = apic->irq_dest_mode;
-		/*
-		 * Trigger mode in the IRTE will always be edge, and the
-		 * actual level or edge trigger will be setup in the IO-APIC
-		 * RTE. This will help simplify level triggered irq migration.
-		 * For more details, see the comments above explainig IO-APIC
-		 * irq migration in the presence of interrupt-remapping.
-		 */
-		irte.trigger_mode = 0;
-		irte.dlvry_mode = apic->irq_delivery_mode;
-		irte.vector = vector;
-		irte.dest_id = IRTE_DEST(destination);
+		prepare_irte(&irte, vector, destination);
 
 		/* Set source-id of interrupt request */
 		set_ioapic_sid(&irte, apic_id);
@@ -1488,7 +1474,7 @@ static void __init setup_IO_APIC_irqs(void)
 	int notcon = 0;
 	struct irq_desc *desc;
 	struct irq_cfg *cfg;
-	int node = cpu_to_node(boot_cpu_id);
+	int node = cpu_to_node(0);
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
@@ -1553,7 +1539,7 @@ static void __init setup_IO_APIC_irqs(void)
 void setup_IO_APIC_irq_extra(u32 gsi)
 {
 	int apic_id = 0, pin, idx, irq;
-	int node = cpu_to_node(boot_cpu_id);
+	int node = cpu_to_node(0);
 	struct irq_desc *desc;
 	struct irq_cfg *cfg;
 
@@ -2932,7 +2918,7 @@ static inline void __init check_timer(void)
 {
 	struct irq_desc *desc = irq_to_desc(0);
 	struct irq_cfg *cfg = desc->chip_data;
-	int node = cpu_to_node(boot_cpu_id);
+	int node = cpu_to_node(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
 	int no_pin1 = 0;
@@ -3286,7 +3272,7 @@ unsigned int create_irq_nr(unsigned int irq_want, int node)
 
 int create_irq(void)
 {
-	int node = cpu_to_node(boot_cpu_id);
+	int node = cpu_to_node(0);
 	unsigned int irq_want;
 	int irq;
 
@@ -3340,14 +3326,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 		ir_index = map_irq_to_irte_handle(irq, &sub_handle);
 		BUG_ON(ir_index == -1);
 
-		memset (&irte, 0, sizeof(irte));
-
-		irte.present = 1;
-		irte.dst_mode = apic->irq_dest_mode;
-		irte.trigger_mode = 0; /* edge */
-		irte.dlvry_mode = apic->irq_delivery_mode;
-		irte.vector = cfg->vector;
-		irte.dest_id = IRTE_DEST(dest);
+		prepare_irte(&irte, cfg->vector, dest);
 
 		/* Set source-id of interrupt request */
 		if (pdev)
@@ -3908,7 +3887,7 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
 	if (dev)
 		node = dev_to_node(dev);
 	else
-		node = cpu_to_node(boot_cpu_id);
+		node = cpu_to_node(0);
 
 	desc = irq_to_desc_alloc_node(irq, node);
 	if (!desc) {
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 3e28401f161c..960f26ab5c9f 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -26,6 +26,7 @@
 #include <linux/nodemask.h>
 #include <linux/topology.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/kernel.h>
@@ -88,7 +89,7 @@ static inline void numaq_register_node(int node, struct sys_cfg_data *scd)
 	node_end_pfn[node] =
 		 MB_TO_PAGES(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
 
-	e820_register_active_regions(node, node_start_pfn[node],
+	memblock_x86_register_active_regions(node, node_start_pfn[node],
 						node_end_pfn[node]);
 
 	memory_present(node, node_start_pfn[node], node_end_pfn[node]);
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 83e9be4778e2..f9e4e6a54073 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -54,6 +54,9 @@ static int apicid_phys_pkg_id(int initial_apic_id, int index_msb)
  */
 void __init default_setup_apic_routing(void)
 {
+
+	enable_IR_x2apic();
+
 #ifdef CONFIG_X86_X2APIC
 	if (x2apic_mode
 #ifdef CONFIG_X86_UV
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index fc999e6fc46a..13a389179514 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -2,7 +2,8 @@
 #include <linux/sched.h>
 #include <linux/kthread.h>
 #include <linux/workqueue.h>
-#include <asm/e820.h>
+#include <linux/memblock.h>
+
 #include <asm/proto.h>
 
 /*
@@ -18,10 +19,12 @@ static int __read_mostly memory_corruption_check = -1;
 static unsigned __read_mostly corruption_check_size = 64*1024;
 static unsigned __read_mostly corruption_check_period = 60; /* seconds */
 
-static struct e820entry scan_areas[MAX_SCAN_AREAS];
+static struct scan_area {
+	u64 addr;
+	u64 size;
+} scan_areas[MAX_SCAN_AREAS];
 static int num_scan_areas;
 
-
 static __init int set_corruption_check(char *arg)
 {
 	char *end;
@@ -81,9 +84,9 @@ void __init setup_bios_corruption_check(void)
 
 	while (addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) {
 		u64 size;
-		addr = find_e820_area_size(addr, &size, PAGE_SIZE);
+		addr = memblock_x86_find_in_range_size(addr, &size, PAGE_SIZE);
 
-		if (!(addr + 1))
+		if (addr == MEMBLOCK_ERROR)
 			break;
 
 		if (addr >= corruption_check_size)
@@ -92,7 +95,7 @@ void __init setup_bios_corruption_check(void)
 		if ((addr + size) > corruption_check_size)
 			size = corruption_check_size - addr;
 
-		e820_update_range(addr, size, E820_RAM, E820_RESERVED);
+		memblock_x86_reserve_range(addr, addr + size, "SCAN RAM");
 		scan_areas[num_scan_areas].addr = addr;
 		scan_areas[num_scan_areas].size = size;
 		num_scan_areas++;
@@ -105,7 +108,6 @@ void __init setup_bios_corruption_check(void)
 
 	printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
 	       num_scan_areas);
-	update_e820();
 }
 
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ba5f62f45f01..9e093f8fe78c 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -148,7 +148,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	/* calling is from identify_secondary_cpu() ? */
-	if (c->cpu_index == boot_cpu_id)
+	if (!c->cpu_index)
 		return;
 
 	/*
@@ -253,37 +253,51 @@ static int __cpuinit nearby_node(int apicid)
 #endif
 
 /*
- * Fixup core topology information for AMD multi-node processors.
- * Assumption: Number of cores in each internal node is the same.
+ * Fixup core topology information for
+ * (1) AMD multi-node processors
+ *     Assumption: Number of cores in each internal node is the same.
+ * (2) AMD processors supporting compute units
  */
 #ifdef CONFIG_X86_HT
-static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
+static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
 {
-	unsigned long long value;
-	u32 nodes, cores_per_node;
+	u32 nodes;
+	u8 node_id;
 	int cpu = smp_processor_id();
 
-	if (!cpu_has(c, X86_FEATURE_NODEID_MSR))
-		return;
+	/* get information required for multi-node processors */
+	if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+		u32 eax, ebx, ecx, edx;
 
-	/* fixup topology information only once for a core */
-	if (cpu_has(c, X86_FEATURE_AMD_DCM))
-		return;
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+		nodes = ((ecx >> 8) & 7) + 1;
+		node_id = ecx & 7;
 
-	rdmsrl(MSR_FAM10H_NODE_ID, value);
+		/* get compute unit information */
+		smp_num_siblings = ((ebx >> 8) & 3) + 1;
+		c->compute_unit_id = ebx & 0xff;
+	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
+		u64 value;
 
-	nodes = ((value >> 3) & 7) + 1;
-	if (nodes == 1)
+		rdmsrl(MSR_FAM10H_NODE_ID, value);
+		nodes = ((value >> 3) & 7) + 1;
+		node_id = value & 7;
+	} else
 		return;
 
-	set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-	cores_per_node = c->x86_max_cores / nodes;
+	/* fixup multi-node processor information */
+	if (nodes > 1) {
+		u32 cores_per_node;
+
+		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+		cores_per_node = c->x86_max_cores / nodes;
 
-	/* store NodeID, use llc_shared_map to store sibling info */
-	per_cpu(cpu_llc_id, cpu) = value & 7;
+		/* store NodeID, use llc_shared_map to store sibling info */
+		per_cpu(cpu_llc_id, cpu) = node_id;
 
-	/* fixup core id to be in range from 0 to (cores_per_node - 1) */
-	c->cpu_core_id = c->cpu_core_id % cores_per_node;
+		/* core id to be in range from 0 to (cores_per_node - 1) */
+		c->cpu_core_id = c->cpu_core_id % cores_per_node;
+	}
 }
 #endif
 
@@ -304,9 +318,7 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
 	c->phys_proc_id = c->initial_apicid >> bits;
 	/* use socket ID also for last level cache */
 	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
-	/* fixup topology information on multi-node processors */
-	if ((c->x86 == 0x10) && (c->x86_model == 9))
-		amd_fixup_dcm(c);
+	amd_get_topology(c);
 #endif
 }
 
@@ -412,6 +424,23 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
 	}
 #endif
+
+	/* We need to do the following only once */
+	if (c != &boot_cpu_data)
+		return;
+
+	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
+
+		if (c->x86 > 0x10 ||
+		    (c->x86 == 0x10 && c->x86_model >= 0x2)) {
+			u64 val;
+
+			rdmsrl(MSR_K7_HWCR, val);
+			if (!(val & BIT(24)))
+				printk(KERN_WARNING FW_BUG "TSC doesn't count "
+					"with P0 frequency!\n");
+		}
+	}
 }
 
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
@@ -523,7 +552,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 #endif
 
 	if (c->extended_cpuid_level >= 0x80000006) {
-		if ((c->x86 >= 0x0f) && (cpuid_edx(0x80000006) & 0xf000))
+		if (cpuid_edx(0x80000006) & 0xf000)
 			num_cache_leaves = 4;
 		else
 			num_cache_leaves = 3;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f2f9ac7da25c..4b68bda30938 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -665,7 +665,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		this_cpu->c_early_init(c);
 
 #ifdef CONFIG_SMP
-	c->cpu_index = boot_cpu_id;
+	c->cpu_index = 0;
 #endif
 	filter_cpuid_features(c, false);
 }
@@ -704,16 +704,21 @@ void __init early_cpu_init(void)
 }
 
 /*
- * The NOPL instruction is supposed to exist on all CPUs with
- * family >= 6; unfortunately, that's not true in practice because
- * of early VIA chips and (more importantly) broken virtualizers that
- * are not easy to detect.  In the latter case it doesn't even *fail*
- * reliably, so probing for it doesn't even work.  Disable it completely
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
  * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
  */
 static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_32
 	clear_cpu_cap(c, X86_FEATURE_NOPL);
+#else
+	set_cpu_cap(c, X86_FEATURE_NOPL);
+#endif
 }
 
 static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
@@ -1264,13 +1269,6 @@ void __cpuinit cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	/*
-	 * Force FPU initialization:
-	 */
-	current_thread_info()->status = 0;
-	clear_used_math();
-	mxcsr_feature_mask_init();
-
 	fpu_init();
 	xsave_init();
 }
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index f668bb1f7d43..e765633f210e 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -32,6 +32,7 @@ struct cpu_dev {
 extern const struct cpu_dev *const __x86_cpu_dev_start[],
 			    *const __x86_cpu_dev_end[];
 
+extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b4389441efbb..695f17731e23 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -170,7 +170,7 @@ static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	/* calling is from identify_secondary_cpu() ? */
-	if (c->cpu_index == boot_cpu_id)
+	if (!c->cpu_index)
 		return;
 
 	/*
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 898c2f4eab88..12cd823c8d03 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -17,7 +17,7 @@
 
 #include <asm/processor.h>
 #include <linux/smp.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/smp.h>
 
 #define LVL_1_INST	1
@@ -306,7 +306,7 @@ struct _cache_attr {
 	ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
 };
 
-#ifdef CONFIG_CPU_SUP_AMD
+#ifdef CONFIG_AMD_NB
 
 /*
  * L3 cache descriptors
@@ -369,7 +369,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
 			return;
 
 	/* not in virtualized environments */
-	if (num_k8_northbridges == 0)
+	if (k8_northbridges.num == 0)
 		return;
 
 	/*
@@ -377,7 +377,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
 	 * never freed but this is done only on shutdown so it doesn't matter.
 	 */
 	if (!l3_caches) {
-		int size = num_k8_northbridges * sizeof(struct amd_l3_cache *);
+		int size = k8_northbridges.num * sizeof(struct amd_l3_cache *);
 
 		l3_caches = kzalloc(size, GFP_ATOMIC);
 		if (!l3_caches)
@@ -556,12 +556,12 @@ static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
 static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
 		show_cache_disable_1, store_cache_disable_1);
 
-#else	/* CONFIG_CPU_SUP_AMD */
+#else	/* CONFIG_AMD_NB */
 static void __cpuinit
 amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index)
 {
 };
-#endif /* CONFIG_CPU_SUP_AMD */
+#endif /* CONFIG_AMD_NB */
 
 static int
 __cpuinit cpuid4_cache_lookup_regs(int index,
@@ -1000,7 +1000,7 @@ static struct attribute *default_attrs[] = {
 
 static struct attribute *default_l3_attrs[] = {
 	DEFAULT_SYSFS_CACHE_ATTRS,
-#ifdef CONFIG_CPU_SUP_AMD
+#ifdef CONFIG_AMD_NB
 	&cache_disable_0.attr,
 	&cache_disable_1.attr,
 #endif
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index d9368eeda309..ba52598e14eb 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -349,7 +349,7 @@ static void intel_thermal_interrupt(void)
 
 static void unexpected_thermal_interrupt(void)
 {
-	printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
+	printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
 			smp_processor_id());
 	add_taint(TAINT_MACHINE_CHECK);
 }
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index c5f59d071425..ac140c7be396 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -827,7 +827,7 @@ int __init amd_special_default_mtrr(void)
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		return 0;
-	if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
+	if (boot_cpu_data.x86 < 0xf)
 		return 0;
 	/* In case some hypervisor doesn't pass SYSCFG through: */
 	if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0)
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 7d28d7d03885..9f27228ceffd 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -64,18 +64,59 @@ static inline void k8_check_syscfg_dram_mod_en(void)
 	}
 }
 
+/* Get the size of contiguous MTRR range */
+static u64 get_mtrr_size(u64 mask)
+{
+	u64 size;
+
+	mask >>= PAGE_SHIFT;
+	mask |= size_or_mask;
+	size = -mask;
+	size <<= PAGE_SHIFT;
+	return size;
+}
+
 /*
- * Returns the effective MTRR type for the region
- * Error returns:
- * - 0xFE - when the range is "not entirely covered" by _any_ var range MTRR
- * - 0xFF - when MTRR is not enabled
+ * Check and return the effective type for MTRR-MTRR type overlap.
+ * Returns 1 if the effective type is UNCACHEABLE, else returns 0
  */
-u8 mtrr_type_lookup(u64 start, u64 end)
+static int check_type_overlap(u8 *prev, u8 *curr)
+{
+	if (*prev == MTRR_TYPE_UNCACHABLE || *curr == MTRR_TYPE_UNCACHABLE) {
+		*prev = MTRR_TYPE_UNCACHABLE;
+		*curr = MTRR_TYPE_UNCACHABLE;
+		return 1;
+	}
+
+	if ((*prev == MTRR_TYPE_WRBACK && *curr == MTRR_TYPE_WRTHROUGH) ||
+	    (*prev == MTRR_TYPE_WRTHROUGH && *curr == MTRR_TYPE_WRBACK)) {
+		*prev = MTRR_TYPE_WRTHROUGH;
+		*curr = MTRR_TYPE_WRTHROUGH;
+	}
+
+	if (*prev != *curr) {
+		*prev = MTRR_TYPE_UNCACHABLE;
+		*curr = MTRR_TYPE_UNCACHABLE;
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Error/Semi-error returns:
+ * 0xFF - when MTRR is not enabled
+ * *repeat == 1 implies [start:end] spanned across MTRR range and type returned
+ *		corresponds only to [start:*partial_end].
+ *		Caller has to lookup again for [*partial_end:end].
+ */
+static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 {
 	int i;
 	u64 base, mask;
 	u8 prev_match, curr_match;
 
+	*repeat = 0;
 	if (!mtrr_state_set)
 		return 0xFF;
 
@@ -126,8 +167,34 @@ u8 mtrr_type_lookup(u64 start, u64 end)
 
 		start_state = ((start & mask) == (base & mask));
 		end_state = ((end & mask) == (base & mask));
-		if (start_state != end_state)
-			return 0xFE;
+
+		if (start_state != end_state) {
+			/*
+			 * We have start:end spanning across an MTRR.
+			 * We split the region into
+			 * either
+			 * (start:mtrr_end) (mtrr_end:end)
+			 * or
+			 * (start:mtrr_start) (mtrr_start:end)
+			 * depending on kind of overlap.
+			 * Return the type for first region and a pointer to
+			 * the start of second region so that caller will
+			 * lookup again on the second region.
+			 * Note: This way we handle multiple overlaps as well.
+			 */
+			if (start_state)
+				*partial_end = base + get_mtrr_size(mask);
+			else
+				*partial_end = base;
+
+			if (unlikely(*partial_end <= start)) {
+				WARN_ON(1);
+				*partial_end = start + PAGE_SIZE;
+			}
+
+			end = *partial_end - 1; /* end is inclusive */
+			*repeat = 1;
+		}
 
 		if ((start & mask) != (base & mask))
 			continue;
@@ -138,21 +205,8 @@ u8 mtrr_type_lookup(u64 start, u64 end)
 			continue;
 		}
 
-		if (prev_match == MTRR_TYPE_UNCACHABLE ||
-		    curr_match == MTRR_TYPE_UNCACHABLE) {
-			return MTRR_TYPE_UNCACHABLE;
-		}
-
-		if ((prev_match == MTRR_TYPE_WRBACK &&
-		     curr_match == MTRR_TYPE_WRTHROUGH) ||
-		    (prev_match == MTRR_TYPE_WRTHROUGH &&
-		     curr_match == MTRR_TYPE_WRBACK)) {
-			prev_match = MTRR_TYPE_WRTHROUGH;
-			curr_match = MTRR_TYPE_WRTHROUGH;
-		}
-
-		if (prev_match != curr_match)
-			return MTRR_TYPE_UNCACHABLE;
+		if (check_type_overlap(&prev_match, &curr_match))
+			return curr_match;
 	}
 
 	if (mtrr_tom2) {
@@ -166,6 +220,36 @@ u8 mtrr_type_lookup(u64 start, u64 end)
 	return mtrr_state.def_type;
 }
 
+/*
+ * Returns the effective MTRR type for the region
+ * Error return:
+ * 0xFF - when MTRR is not enabled
+ */
+u8 mtrr_type_lookup(u64 start, u64 end)
+{
+	u8 type, prev_type;
+	int repeat;
+	u64 partial_end;
+
+	type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+
+	/*
+	 * Common path is with repeat = 0.
+	 * However, we can have cases where [start:end] spans across some
+	 * MTRR range. Do repeated lookups for that case here.
+	 */
+	while (repeat) {
+		prev_type = type;
+		start = partial_end;
+		type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+
+		if (check_type_overlap(&prev_type, &type))
+			return type;
+	}
+
+	return type;
+}
+
 /* Get the MSR pair relating to a var range */
 static void
 get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 03a5b0385ad6..e2513f26ba8b 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -531,7 +531,7 @@ static int x86_pmu_hw_config(struct perf_event *event)
 /*
  * Setup the hardware configuration for a given attr_type
  */
-static int __hw_perf_event_init(struct perf_event *event)
+static int __x86_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
@@ -584,7 +584,7 @@ static void x86_pmu_disable_all(void)
 	}
 }
 
-void hw_perf_disable(void)
+static void x86_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -619,7 +619,7 @@ static void x86_pmu_enable_all(int added)
 	}
 }
 
-static const struct pmu pmu;
+static struct pmu pmu;
 
 static inline int is_x86_event(struct perf_event *event)
 {
@@ -801,10 +801,10 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc,
 		hwc->last_tag == cpuc->tags[i];
 }
 
-static int x86_pmu_start(struct perf_event *event);
-static void x86_pmu_stop(struct perf_event *event);
+static void x86_pmu_start(struct perf_event *event, int flags);
+static void x86_pmu_stop(struct perf_event *event, int flags);
 
-void hw_perf_enable(void)
+static void x86_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct perf_event *event;
@@ -840,7 +840,14 @@ void hw_perf_enable(void)
 			    match_prev_assignment(hwc, cpuc, i))
 				continue;
 
-			x86_pmu_stop(event);
+			/*
+			 * Ensure we don't accidentally enable a stopped
+			 * counter simply because we rescheduled.
+			 */
+			if (hwc->state & PERF_HES_STOPPED)
+				hwc->state |= PERF_HES_ARCH;
+
+			x86_pmu_stop(event, PERF_EF_UPDATE);
 		}
 
 		for (i = 0; i < cpuc->n_events; i++) {
@@ -852,7 +859,10 @@ void hw_perf_enable(void)
 			else if (i < n_running)
 				continue;
 
-			x86_pmu_start(event);
+			if (hwc->state & PERF_HES_ARCH)
+				continue;
+
+			x86_pmu_start(event, PERF_EF_RELOAD);
 		}
 		cpuc->n_added = 0;
 		perf_events_lapic_init();
@@ -953,15 +963,12 @@ static void x86_pmu_enable_event(struct perf_event *event)
 }
 
 /*
- * activate a single event
+ * Add a single event to the PMU.
  *
  * The event is added to the group of enabled events
  * but only if it can be scehduled with existing events.
- *
- * Called with PMU disabled. If successful and return value 1,
- * then guaranteed to call perf_enable() and hw_perf_enable()
  */
-static int x86_pmu_enable(struct perf_event *event)
+static int x86_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc;
@@ -970,58 +977,67 @@ static int x86_pmu_enable(struct perf_event *event)
 
 	hwc = &event->hw;
 
+	perf_pmu_disable(event->pmu);
 	n0 = cpuc->n_events;
-	n = collect_events(cpuc, event, false);
-	if (n < 0)
-		return n;
+	ret = n = collect_events(cpuc, event, false);
+	if (ret < 0)
+		goto out;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_ARCH;
 
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
-	 * at commit time(->commit_txn) as a whole
+	 * at commit time (->commit_txn) as a whole
 	 */
 	if (cpuc->group_flag & PERF_EVENT_TXN)
-		goto out;
+		goto done_collect;
 
 	ret = x86_pmu.schedule_events(cpuc, n, assign);
 	if (ret)
-		return ret;
+		goto out;
 	/*
 	 * copy new assignment, now we know it is possible
 	 * will be used by hw_perf_enable()
 	 */
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
-out:
+done_collect:
 	cpuc->n_events = n;
 	cpuc->n_added += n - n0;
 	cpuc->n_txn += n - n0;
 
-	return 0;
+	ret = 0;
+out:
+	perf_pmu_enable(event->pmu);
+	return ret;
 }
 
-static int x86_pmu_start(struct perf_event *event)
+static void x86_pmu_start(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx = event->hw.idx;
 
-	if (idx == -1)
-		return -EAGAIN;
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	if (WARN_ON_ONCE(idx == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+		x86_perf_event_set_period(event);
+	}
+
+	event->hw.state = 0;
 
-	x86_perf_event_set_period(event);
 	cpuc->events[idx] = event;
 	__set_bit(idx, cpuc->active_mask);
 	__set_bit(idx, cpuc->running);
 	x86_pmu.enable(event);
 	perf_event_update_userpage(event);
-
-	return 0;
-}
-
-static void x86_pmu_unthrottle(struct perf_event *event)
-{
-	int ret = x86_pmu_start(event);
-	WARN_ON_ONCE(ret);
 }
 
 void perf_event_print_debug(void)
@@ -1078,27 +1094,29 @@ void perf_event_print_debug(void)
 	local_irq_restore(flags);
 }
 
-static void x86_pmu_stop(struct perf_event *event)
+static void x86_pmu_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
 
-	if (!__test_and_clear_bit(idx, cpuc->active_mask))
-		return;
-
-	x86_pmu.disable(event);
-
-	/*
-	 * Drain the remaining delta count out of a event
-	 * that we are disabling:
-	 */
-	x86_perf_event_update(event);
+	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+		x86_pmu.disable(event);
+		cpuc->events[hwc->idx] = NULL;
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+	}
 
-	cpuc->events[idx] = NULL;
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		/*
+		 * Drain the remaining delta count out of a event
+		 * that we are disabling:
+		 */
+		x86_perf_event_update(event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
 }
 
-static void x86_pmu_disable(struct perf_event *event)
+static void x86_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int i;
@@ -1111,7 +1129,7 @@ static void x86_pmu_disable(struct perf_event *event)
 	if (cpuc->group_flag & PERF_EVENT_TXN)
 		return;
 
-	x86_pmu_stop(event);
+	x86_pmu_stop(event, PERF_EF_UPDATE);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event_list[i]) {
@@ -1134,7 +1152,6 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc;
 	struct perf_event *event;
-	struct hw_perf_event *hwc;
 	int idx, handled = 0;
 	u64 val;
 
@@ -1155,7 +1172,6 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		}
 
 		event = cpuc->events[idx];
-		hwc = &event->hw;
 
 		val = x86_perf_event_update(event);
 		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
@@ -1171,7 +1187,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu_stop(event);
+			x86_pmu_stop(event, 0);
 	}
 
 	if (handled)
@@ -1388,7 +1404,6 @@ void __init init_hw_perf_events(void)
 		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
 	}
 	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
-	perf_max_events = x86_pmu.num_counters;
 
 	if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
@@ -1424,6 +1439,7 @@ void __init init_hw_perf_events(void)
 	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
 	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
+	perf_pmu_register(&pmu);
 	perf_cpu_notifier(x86_pmu_notifier);
 }
 
@@ -1437,10 +1453,11 @@ static inline void x86_pmu_read(struct perf_event *event)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void x86_pmu_start_txn(const struct pmu *pmu)
+static void x86_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuc->group_flag |= PERF_EVENT_TXN;
 	cpuc->n_txn = 0;
 }
@@ -1450,7 +1467,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu)
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-static void x86_pmu_cancel_txn(const struct pmu *pmu)
+static void x86_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -1460,6 +1477,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
 	 */
 	cpuc->n_added -= cpuc->n_txn;
 	cpuc->n_events -= cpuc->n_txn;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -1467,7 +1485,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-static int x86_pmu_commit_txn(const struct pmu *pmu)
+static int x86_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int assign[X86_PMC_IDX_MAX];
@@ -1489,22 +1507,10 @@ static int x86_pmu_commit_txn(const struct pmu *pmu)
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
-
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= x86_pmu_enable,
-	.disable	= x86_pmu_disable,
-	.start		= x86_pmu_start,
-	.stop		= x86_pmu_stop,
-	.read		= x86_pmu_read,
-	.unthrottle	= x86_pmu_unthrottle,
-	.start_txn	= x86_pmu_start_txn,
-	.cancel_txn	= x86_pmu_cancel_txn,
-	.commit_txn	= x86_pmu_commit_txn,
-};
-
 /*
  * validate that we can schedule this event
  */
@@ -1579,12 +1585,22 @@ out:
 	return ret;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+int x86_pmu_event_init(struct perf_event *event)
 {
-	const struct pmu *tmp;
+	struct pmu *tmp;
 	int err;
 
-	err = __hw_perf_event_init(event);
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
+	err = __x86_pmu_event_init(event);
 	if (!err) {
 		/*
 		 * we temporarily connect event to its pmu
@@ -1604,26 +1620,31 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	if (err) {
 		if (event->destroy)
 			event->destroy(event);
-		return ERR_PTR(err);
 	}
 
-	return &pmu;
+	return err;
 }
 
-/*
- * callchain support
- */
+static struct pmu pmu = {
+	.pmu_enable	= x86_pmu_enable,
+	.pmu_disable	= x86_pmu_disable,
 
-static inline
-void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
+	.event_init	= x86_pmu_event_init,
 
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
+	.add		= x86_pmu_add,
+	.del		= x86_pmu_del,
+	.start		= x86_pmu_start,
+	.stop		= x86_pmu_stop,
+	.read		= x86_pmu_read,
 
+	.start_txn	= x86_pmu_start_txn,
+	.cancel_txn	= x86_pmu_cancel_txn,
+	.commit_txn	= x86_pmu_commit_txn,
+};
+
+/*
+ * callchain support
+ */
 
 static void
 backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
@@ -1645,7 +1666,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
 	struct perf_callchain_entry *entry = data;
 
-	callchain_store(entry, addr);
+	perf_callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops backtrace_ops = {
@@ -1656,11 +1677,15 @@ static const struct stacktrace_ops backtrace_ops = {
 	.walk_stack		= print_context_stack_bp,
 };
 
-static void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->ip);
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* TODO: We don't support guest os callchain now */
+		return;
+	}
+
+	perf_callchain_store(entry, regs->ip);
 
 	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
 }
@@ -1689,7 +1714,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if (fp < compat_ptr(regs->sp))
 			break;
 
-		callchain_store(entry, frame.return_address);
+		perf_callchain_store(entry, frame.return_address);
 		fp = compat_ptr(frame.next_frame);
 	}
 	return 1;
@@ -1702,19 +1727,20 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 }
 #endif
 
-static void
-perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
 	const void __user *fp;
 
-	if (!user_mode(regs))
-		regs = task_pt_regs(current);
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* TODO: We don't support guest os callchain now */
+		return;
+	}
 
 	fp = (void __user *)regs->bp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, regs->ip);
+	perf_callchain_store(entry, regs->ip);
 
 	if (perf_callchain_user32(regs, entry))
 		return;
@@ -1731,52 +1757,11 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if ((unsigned long)fp < regs->sp)
 			break;
 
-		callchain_store(entry, frame.return_address);
+		perf_callchain_store(entry, frame.return_address);
 		fp = frame.next_frame;
 	}
 }
 
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-
-	if (current->mm)
-		perf_callchain_user(regs, entry);
-}
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* TODO: We don't support guest os callchain now */
-		return NULL;
-	}
-
-	if (in_nmi())
-		entry = &__get_cpu_var(pmc_nmi_entry);
-	else
-		entry = &__get_cpu_var(pmc_irq_entry);
-
-	entry->nr = 0;
-
-	perf_do_callchain(regs, entry);
-
-	return entry;
-}
-
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long ip;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index ee05c90012d2..c8f5c088cad1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -713,18 +713,18 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	struct cpu_hw_events *cpuc;
 	int bit, loops;
 	u64 status;
-	int handled = 0;
+	int handled;
 
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	intel_pmu_disable_all();
-	intel_pmu_drain_bts_buffer();
+	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
 	if (!status) {
 		intel_pmu_enable_all(0);
-		return 0;
+		return handled;
 	}
 
 	loops = 0;
@@ -763,7 +763,7 @@ again:
 		data.period = event->hw.last_period;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu_stop(event);
+			x86_pmu_stop(event, 0);
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 18018d1311cd..4977f9c400e5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -214,7 +214,7 @@ static void intel_pmu_disable_bts(void)
 	update_debugctlmsr(debugctlmsr);
 }
 
-static void intel_pmu_drain_bts_buffer(void)
+static int intel_pmu_drain_bts_buffer(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
@@ -231,16 +231,16 @@ static void intel_pmu_drain_bts_buffer(void)
 	struct pt_regs regs;
 
 	if (!event)
-		return;
+		return 0;
 
 	if (!ds)
-		return;
+		return 0;
 
 	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
 	top = (struct bts_record *)(unsigned long)ds->bts_index;
 
 	if (top <= at)
-		return;
+		return 0;
 
 	ds->bts_index = ds->bts_buffer_base;
 
@@ -256,7 +256,7 @@ static void intel_pmu_drain_bts_buffer(void)
 	perf_prepare_sample(&header, &data, event, &regs);
 
 	if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1))
-		return;
+		return 1;
 
 	for (; at < top; at++) {
 		data.ip		= at->from;
@@ -270,6 +270,7 @@ static void intel_pmu_drain_bts_buffer(void)
 	/* There's new data available. */
 	event->hw.interrupts++;
 	event->pending_kill = POLL_IN;
+	return 1;
 }
 
 /*
@@ -491,7 +492,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
 	if (perf_event_overflow(event, 1, &data, &regs))
-		x86_pmu_stop(event);
+		x86_pmu_stop(event, 0);
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 249015173992..81400b93e694 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -18,6 +18,8 @@
 struct p4_event_bind {
 	unsigned int opcode;			/* Event code and ESCR selector */
 	unsigned int escr_msr[2];		/* ESCR MSR for this event */
+	unsigned int escr_emask;		/* valid ESCR EventMask bits */
+	unsigned int shared;			/* event is shared across threads */
 	char cntr[2][P4_CNTR_LIMIT];		/* counter index (offset), -1 on abscence */
 };
 
@@ -66,231 +68,435 @@ static struct p4_event_bind p4_event_bind_map[] = {
 	[P4_EVENT_TC_DELIVER_MODE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_TC_DELIVER_MODE),
 		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DB)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DI)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BD)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BB)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BI)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, ID),
+		.shared		= 1,
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_BPU_FETCH_REQUEST] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST),
 		.escr_msr	= { MSR_P4_BPU_ESCR0, MSR_P4_BPU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BPU_FETCH_REQUEST, TCMISS),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_ITLB_REFERENCE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_ITLB_REFERENCE),
 		.escr_msr	= { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, HIT)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, MISS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, HIT_UK),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_MEMORY_CANCEL] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_CANCEL),
 		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_CANCEL, 64K_CONF),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_MEMORY_COMPLETE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_COMPLETE),
 		.escr_msr	= { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_COMPLETE, LSC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_COMPLETE, SSC),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_LOAD_PORT_REPLAY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY),
 		.escr_msr	= { MSR_P4_SAAT_ESCR0, MSR_P4_SAAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_STORE_PORT_REPLAY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY),
 		.escr_msr	= { MSR_P4_SAAT_ESCR0 ,  MSR_P4_SAAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_MOB_LOAD_REPLAY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY),
 		.escr_msr	= { MSR_P4_MOB_ESCR0, MSR_P4_MOB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, NO_STA)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, NO_STD)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_PAGE_WALK_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE),
 		.escr_msr	= { MSR_P4_PMH_ESCR0, MSR_P4_PMH_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_PAGE_WALK_TYPE, DTMISS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_PAGE_WALK_TYPE, ITMISS),
+		.shared		= 1,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_BSQ_CACHE_REFERENCE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE),
 		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_IOQ_ALLOCATION] = {
 		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ALLOCATION),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, DEFAULT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, ALL_READ)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_UC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WB)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, OWN)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, OTHER)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, PREFETCH),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_IOQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
 		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES),
 		.escr_msr	= { MSR_P4_FSB_ESCR1,  MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH),
 		.cntr		= { {2, -1, -1}, {3, -1, -1} },
 	},
 	[P4_EVENT_FSB_DATA_ACTIVITY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER),
+		.shared		= 1,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_BSQ_ALLOCATION] = {		/* shared ESCR, broken CCCR1 */
 		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ALLOCATION),
 		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR0 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2),
 		.cntr		= { {0, -1, -1}, {1, -1, -1} },
 	},
 	[P4_EVENT_BSQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
 		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES),
 		.escr_msr	= { MSR_P4_BSU_ESCR1 , MSR_P4_BSU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2),
 		.cntr		= { {2, -1, -1}, {3, -1, -1} },
 	},
 	[P4_EVENT_SSE_INPUT_ASSIST] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_SSE_INPUT_ASSIST, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_PACKED_SP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_PACKED_SP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_PACKED_SP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_PACKED_DP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_PACKED_DP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_PACKED_DP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_SCALAR_SP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_SP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_SCALAR_SP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_SCALAR_DP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_DP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_SCALAR_DP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_64BIT_MMX_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_64BIT_MMX_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_64BIT_MMX_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_128BIT_MMX_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_128BIT_MMX_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_128BIT_MMX_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_X87_FP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_X87_FP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_FP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_TC_MISC] = {
 		.opcode		= P4_OPCODE(P4_EVENT_TC_MISC),
 		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_MISC, FLUSH),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_GLOBAL_POWER_EVENTS] = {
 		.opcode		= P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_TC_MS_XFER] = {
 		.opcode		= P4_OPCODE(P4_EVENT_TC_MS_XFER),
 		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_MS_XFER, CISC),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_UOP_QUEUE_WRITES] = {
 		.opcode		= P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES),
 		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE),
 		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR0 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_RETIRED_BRANCH_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE),
 		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CALL)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_RESOURCE_STALL] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RESOURCE_STALL),
 		.escr_msr	= { MSR_P4_ALF_ESCR0, MSR_P4_ALF_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_RESOURCE_STALL, SBFULL),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_WC_BUFFER] = {
 		.opcode		= P4_OPCODE(P4_EVENT_WC_BUFFER),
 		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_WC_BUFFER, WCB_EVICTS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_B2B_CYCLES] = {
 		.opcode		= P4_OPCODE(P4_EVENT_B2B_CYCLES),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_BNR] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BNR),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_SNOOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SNOOP),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_RESPONSE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RESPONSE),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_FRONT_END_EVENT] = {
 		.opcode		= P4_OPCODE(P4_EVENT_FRONT_END_EVENT),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_FRONT_END_EVENT, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FRONT_END_EVENT, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_EXECUTION_EVENT] = {
 		.opcode		= P4_OPCODE(P4_EVENT_EXECUTION_EVENT),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS2)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS3)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS2)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS3),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_REPLAY_EVENT] = {
 		.opcode		= P4_OPCODE(P4_EVENT_REPLAY_EVENT),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_REPLAY_EVENT, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_REPLAY_EVENT, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_INSTR_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_INSTR_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSTAG)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSNTAG)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSTAG),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_UOPS_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_UOPS_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOPS_RETIRED, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOPS_RETIRED, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_UOP_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_UOP_TYPE),
 		.escr_msr	= { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_TYPE, TAGLOADS)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_TYPE, TAGSTORES),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_BRANCH_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BRANCH_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMNP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMNM)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMTP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMTM),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_MISPRED_BRANCH_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+		P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_X87_ASSIST] = {
 		.opcode		= P4_OPCODE(P4_EVENT_X87_ASSIST),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, FPSU)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, FPSO)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, POAO)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, POAU)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, PREA),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_MACHINE_CLEAR] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MACHINE_CLEAR),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, CLEAR)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, MOCLEAR)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, SMCLEAR),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_INSTR_COMPLETED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_INSTR_COMPLETED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_COMPLETED, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_COMPLETED, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 };
@@ -428,29 +634,73 @@ static u64 p4_pmu_event_map(int hw_event)
 	return config;
 }
 
+/* check cpu model specifics */
+static bool p4_event_match_cpu_model(unsigned int event_idx)
+{
+	/* INSTR_COMPLETED event only exist for model 3, 4, 6 (Prescott) */
+	if (event_idx == P4_EVENT_INSTR_COMPLETED) {
+		if (boot_cpu_data.x86_model != 3 &&
+			boot_cpu_data.x86_model != 4 &&
+			boot_cpu_data.x86_model != 6)
+			return false;
+	}
+
+	/*
+	 * For info
+	 * - IQ_ESCR0, IQ_ESCR1 only for models 1 and 2
+	 */
+
+	return true;
+}
+
 static int p4_validate_raw_event(struct perf_event *event)
 {
-	unsigned int v;
+	unsigned int v, emask;
 
-	/* user data may have out-of-bound event index */
+	/* User data may have out-of-bound event index */
 	v = p4_config_unpack_event(event->attr.config);
-	if (v >= ARRAY_SIZE(p4_event_bind_map)) {
-		pr_warning("P4 PMU: Unknown event code: %d\n", v);
+	if (v >= ARRAY_SIZE(p4_event_bind_map))
+		return -EINVAL;
+
+	/* It may be unsupported: */
+	if (!p4_event_match_cpu_model(v))
 		return -EINVAL;
+
+	/*
+	 * NOTE: P4_CCCR_THREAD_ANY has not the same meaning as
+	 * in Architectural Performance Monitoring, it means not
+	 * on _which_ logical cpu to count but rather _when_, ie it
+	 * depends on logical cpu state -- count event if one cpu active,
+	 * none, both or any, so we just allow user to pass any value
+	 * desired.
+	 *
+	 * In turn we always set Tx_OS/Tx_USR bits bound to logical
+	 * cpu without their propagation to another cpu
+	 */
+
+	/*
+	 * if an event is shared accross the logical threads
+	 * the user needs special permissions to be able to use it
+	 */
+	if (p4_event_bind_map[v].shared) {
+		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
 	}
 
+	/* ESCR EventMask bits may be invalid */
+	emask = p4_config_unpack_escr(event->attr.config) & P4_ESCR_EVENTMASK_MASK;
+	if (emask & ~p4_event_bind_map[v].escr_emask)
+		return -EINVAL;
+
 	/*
-	 * it may have some screwed PEBS bits
+	 * it may have some invalid PEBS bits
 	 */
-	if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE)) {
-		pr_warning("P4 PMU: PEBS are not supported yet\n");
+	if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE))
 		return -EINVAL;
-	}
+
 	v = p4_config_unpack_metric(event->attr.config);
-	if (v >= ARRAY_SIZE(p4_pebs_bind_map)) {
-		pr_warning("P4 PMU: Unknown metric code: %d\n", v);
+	if (v >= ARRAY_SIZE(p4_pebs_bind_map))
 		return -EINVAL;
-	}
 
 	return 0;
 }
@@ -478,27 +728,21 @@ static int p4_hw_config(struct perf_event *event)
 
 	if (event->attr.type == PERF_TYPE_RAW) {
 
+		/*
+		 * Clear bits we reserve to be managed by kernel itself
+		 * and never allowed from a user space
+		 */
+		 event->attr.config &= P4_CONFIG_MASK;
+
 		rc = p4_validate_raw_event(event);
 		if (rc)
 			goto out;
 
 		/*
-		 * We don't control raw events so it's up to the caller
-		 * to pass sane values (and we don't count the thread number
-		 * on HT machine but allow HT-compatible specifics to be
-		 * passed on)
-		 *
 		 * Note that for RAW events we allow user to use P4_CCCR_RESERVED
 		 * bits since we keep additional info here (for cache events and etc)
-		 *
-		 * XXX: HT wide things should check perf_paranoid_cpu() &&
-		 *      CAP_SYS_ADMIN
 		 */
-		event->hw.config |= event->attr.config &
-			(p4_config_pack_escr(P4_ESCR_MASK_HT) |
-			 p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED));
-
-		event->hw.config &= ~P4_CCCR_FORCE_OVF;
+		event->hw.config |= event->attr.config;
 	}
 
 	rc = x86_setup_perfctr(event);
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index fb329e9f8494..d9f4ff8fcd69 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -700,11 +700,10 @@ static void probe_nmi_watchdog(void)
 {
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
-		if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 &&
-		    boot_cpu_data.x86 != 16 && boot_cpu_data.x86 != 17)
-			return;
-		wd_ops = &k7_wd_ops;
-		break;
+		if (boot_cpu_data.x86 == 6 ||
+		    (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15))
+			wd_ops = &k7_wd_ops;
+		return;
 	case X86_VENDOR_INTEL:
 		/* Work around where perfctr1 doesn't have a working enable
 		 * bit as described in the following errata:
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index d49079515122..c7f64e6f537a 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -44,6 +44,12 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		{ X86_FEATURE_LBRV,		CR_EDX, 1, 0x8000000a, 0 },
 		{ X86_FEATURE_SVML,		CR_EDX, 2, 0x8000000a, 0 },
 		{ X86_FEATURE_NRIPS,		CR_EDX, 3, 0x8000000a, 0 },
+		{ X86_FEATURE_TSCRATEMSR,	CR_EDX, 4, 0x8000000a, 0 },
+		{ X86_FEATURE_VMCBCLEAN,	CR_EDX, 5, 0x8000000a, 0 },
+		{ X86_FEATURE_FLUSHBYASID,	CR_EDX, 6, 0x8000000a, 0 },
+		{ X86_FEATURE_DECODEASSISTS,	CR_EDX, 7, 0x8000000a, 0 },
+		{ X86_FEATURE_PAUSEFILTER,	CR_EDX,10, 0x8000000a, 0 },
+		{ X86_FEATURE_PFTHRESHOLD,	CR_EDX,12, 0x8000000a, 0 },
 		{ 0, 0, 0, 0, 0 }
 	};
 
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 045b36cada65..994828899e09 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -34,7 +34,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	if (!csize)
 		return 0;
 
-	vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+	vaddr = ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE);
 	if (!vaddr)
 		return -ENOMEM;
 
@@ -46,6 +46,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	} else
 		memcpy(buf, vaddr + offset, csize);
 
+	set_iounmap_nonlazy();
 	iounmap(vaddr);
 	return csize;
 }
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 0d6fc71bedb1..0c2b7ef7a34d 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -15,6 +15,7 @@
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/firmware-map.h>
+#include <linux/memblock.h>
 
 #include <asm/e820.h>
 #include <asm/proto.h>
@@ -738,73 +739,7 @@ core_initcall(e820_mark_nvs_memory);
 #endif
 
 /*
- * Find a free area with specified alignment in a specific range.
- */
-u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-
-		ei_last = ei->addr + ei->size;
-		ei_start = ei->addr;
-		addr = find_early_area(ei_start, ei_last, start, end,
-					 size, align);
-
-		if (addr != -1ULL)
-			return addr;
-	}
-	return -1ULL;
-}
-
-u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
-{
-	return find_e820_area(start, end, size, align);
-}
-
-u64 __init get_max_mapped(void)
-{
-	u64 end = max_pfn_mapped;
-
-	end <<= PAGE_SHIFT;
-
-	return end;
-}
-/*
- * Find next free range after *start
- */
-u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-
-		ei_last = ei->addr + ei->size;
-		ei_start = ei->addr;
-		addr = find_early_area_size(ei_start, ei_last, start,
-					 sizep, align);
-
-		if (addr != -1ULL)
-			return addr;
-	}
-
-	return -1ULL;
-}
-
-/*
- * pre allocated 4k and reserved it in e820
+ * pre allocated 4k and reserved it in memblock and e820_saved
  */
 u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 {
@@ -813,8 +748,8 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 	u64 start;
 
 	for (start = startt; ; start += size) {
-		start = find_e820_area_size(start, &size, align);
-		if (!(start + 1))
+		start = memblock_x86_find_in_range_size(start, &size, align);
+		if (start == MEMBLOCK_ERROR)
 			return 0;
 		if (size >= sizet)
 			break;
@@ -830,10 +765,9 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 	addr = round_down(start + size - sizet, align);
 	if (addr < start)
 		return 0;
-	e820_update_range(addr, sizet, E820_RAM, E820_RESERVED);
+	memblock_x86_reserve_range(addr, addr + sizet, "new next");
 	e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED);
-	printk(KERN_INFO "update e820 for early_reserve_e820\n");
-	update_e820();
+	printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
 	update_e820_saved();
 
 	return addr;
@@ -895,74 +829,6 @@ unsigned long __init e820_end_of_low_ram_pfn(void)
 {
 	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
 }
-/*
- * Finds an active region in the address range from start_pfn to last_pfn and
- * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
- */
-int __init e820_find_active_region(const struct e820entry *ei,
-				  unsigned long start_pfn,
-				  unsigned long last_pfn,
-				  unsigned long *ei_startpfn,
-				  unsigned long *ei_endpfn)
-{
-	u64 align = PAGE_SIZE;
-
-	*ei_startpfn = round_up(ei->addr, align) >> PAGE_SHIFT;
-	*ei_endpfn = round_down(ei->addr + ei->size, align) >> PAGE_SHIFT;
-
-	/* Skip map entries smaller than a page */
-	if (*ei_startpfn >= *ei_endpfn)
-		return 0;
-
-	/* Skip if map is outside the node */
-	if (ei->type != E820_RAM || *ei_endpfn <= start_pfn ||
-				    *ei_startpfn >= last_pfn)
-		return 0;
-
-	/* Check for overlaps */
-	if (*ei_startpfn < start_pfn)
-		*ei_startpfn = start_pfn;
-	if (*ei_endpfn > last_pfn)
-		*ei_endpfn = last_pfn;
-
-	return 1;
-}
-
-/* Walk the e820 map and register active regions within a node */
-void __init e820_register_active_regions(int nid, unsigned long start_pfn,
-					 unsigned long last_pfn)
-{
-	unsigned long ei_startpfn;
-	unsigned long ei_endpfn;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++)
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, last_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			add_active_range(nid, ei_startpfn, ei_endpfn);
-}
-
-/*
- * Find the hole size (in bytes) in the memory range.
- * @start: starting address of the memory range to scan
- * @end: ending address of the memory range to scan
- */
-u64 __init e820_hole_size(u64 start, u64 end)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long last_pfn = end >> PAGE_SHIFT;
-	unsigned long ei_startpfn, ei_endpfn, ram = 0;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, last_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			ram += ei_endpfn - ei_startpfn;
-	}
-	return end - start - ((u64)ram << PAGE_SHIFT);
-}
 
 static void early_panic(char *msg)
 {
@@ -1210,3 +1076,48 @@ void __init setup_memory_map(void)
 	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
 	e820_print_map(who);
 }
+
+void __init memblock_x86_fill(void)
+{
+	int i;
+	u64 end;
+
+	/*
+	 * EFI may have more than 128 entries
+	 * We are safe to enable resizing, beause memblock_x86_fill()
+	 * is rather later for x86
+	 */
+	memblock_can_resize = 1;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		end = ei->addr + ei->size;
+		if (end != (resource_size_t)end)
+			continue;
+
+		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
+			continue;
+
+		memblock_add(ei->addr, ei->size);
+	}
+
+	memblock_analyze();
+	memblock_dump_all();
+}
+
+void __init memblock_find_dma_reserve(void)
+{
+#ifdef CONFIG_X86_64
+	u64 free_size_pfn;
+	u64 mem_size_pfn;
+	/*
+	 * need to find out used area below MAX_DMA_PFN
+	 * need to use memblock to get free size in [0, MAX_DMA_PFN]
+	 * at first, and assume boot_mem will not take below MAX_DMA_PFN
+	 */
+	mem_size_pfn = memblock_x86_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT;
+	free_size_pfn = memblock_x86_free_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT;
+	set_dma_reserve(mem_size_pfn - free_size_pfn);
+#endif
+}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index ebdb85cf2686..76b8cd953dee 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -97,7 +97,6 @@ static void __init nvidia_bugs(int num, int slot, int func)
 }
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
-#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
 static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 {
 	u32 d;
@@ -115,7 +114,6 @@ static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 	d &= 0xff;
 	return d;
 }
-#endif
 
 static void __init ati_bugs(int num, int slot, int func)
 {
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index c2fa9b8b497e..0fe27d7c6258 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -30,6 +30,7 @@
 #include <linux/init.h>
 #include <linux/efi.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 #include <linux/time.h>
@@ -275,7 +276,7 @@ static void __init do_add_efi_memmap(void)
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
-void __init efi_reserve_early(void)
+void __init efi_memblock_x86_reserve_range(void)
 {
 	unsigned long pmap;
 
@@ -290,7 +291,7 @@ void __init efi_reserve_early(void)
 		boot_params.efi_info.efi_memdesc_size;
 	memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
 	memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
-	reserve_early(pmap, pmap + memmap.nr_map * memmap.desc_size,
+	memblock_x86_reserve_range(pmap, pmap + memmap.nr_map * memmap.desc_size,
 		      "EFI memmap");
 }
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 227d00920d2f..9fb188d7bc76 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -115,8 +115,7 @@
 
  /* unfortunately push/pop can't be no-op */
 .macro PUSH_GS
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
 .endm
 .macro POP_GS pop=0
 	addl $(4 + \pop), %esp
@@ -140,14 +139,12 @@
 #else	/* CONFIG_X86_32_LAZY_GS */
 
 .macro PUSH_GS
-	pushl %gs
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %gs
 	/*CFI_REL_OFFSET gs, 0*/
 .endm
 
 .macro POP_GS pop=0
-98:	popl %gs
-	CFI_ADJUST_CFA_OFFSET -4
+98:	popl_cfi %gs
 	/*CFI_RESTORE gs*/
   .if \pop <> 0
 	add $\pop, %esp
@@ -195,35 +192,25 @@
 .macro SAVE_ALL
 	cld
 	PUSH_GS
-	pushl %fs
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %fs
 	/*CFI_REL_OFFSET fs, 0;*/
-	pushl %es
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %es
 	/*CFI_REL_OFFSET es, 0;*/
-	pushl %ds
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ds
 	/*CFI_REL_OFFSET ds, 0;*/
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	CFI_REL_OFFSET eax, 0
-	pushl %ebp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebp
 	CFI_REL_OFFSET ebp, 0
-	pushl %edi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edi
 	CFI_REL_OFFSET edi, 0
-	pushl %esi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %esi
 	CFI_REL_OFFSET esi, 0
-	pushl %edx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edx
 	CFI_REL_OFFSET edx, 0
-	pushl %ecx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx
 	CFI_REL_OFFSET ecx, 0
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	CFI_REL_OFFSET ebx, 0
 	movl $(__USER_DS), %edx
 	movl %edx, %ds
@@ -234,39 +221,29 @@
 .endm
 
 .macro RESTORE_INT_REGS
-	popl %ebx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ebx
 	CFI_RESTORE ebx
-	popl %ecx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ecx
 	CFI_RESTORE ecx
-	popl %edx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %edx
 	CFI_RESTORE edx
-	popl %esi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %esi
 	CFI_RESTORE esi
-	popl %edi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %edi
 	CFI_RESTORE edi
-	popl %ebp
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ebp
 	CFI_RESTORE ebp
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
 	CFI_RESTORE eax
 .endm
 
 .macro RESTORE_REGS pop=0
 	RESTORE_INT_REGS
-1:	popl %ds
-	CFI_ADJUST_CFA_OFFSET -4
+1:	popl_cfi %ds
 	/*CFI_RESTORE ds;*/
-2:	popl %es
-	CFI_ADJUST_CFA_OFFSET -4
+2:	popl_cfi %es
 	/*CFI_RESTORE es;*/
-3:	popl %fs
-	CFI_ADJUST_CFA_OFFSET -4
+3:	popl_cfi %fs
 	/*CFI_RESTORE fs;*/
 	POP_GS \pop
 .pushsection .fixup, "ax"
@@ -320,16 +297,12 @@
 
 ENTRY(ret_from_fork)
 	CFI_STARTPROC
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	call schedule_tail
 	GET_THREAD_INFO(%ebp)
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
-	pushl $0x0202			# Reset kernel eflags
-	CFI_ADJUST_CFA_OFFSET 4
-	popfl
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
+	pushl_cfi $0x0202		# Reset kernel eflags
+	popfl_cfi
 	jmp syscall_exit
 	CFI_ENDPROC
 END(ret_from_fork)
@@ -409,29 +382,23 @@ sysenter_past_esp:
 	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
 	 * we immediately enable interrupts at that point anyway.
 	 */
-	pushl $(__USER_DS)
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $(__USER_DS)
 	/*CFI_REL_OFFSET ss, 0*/
-	pushl %ebp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebp
 	CFI_REL_OFFSET esp, 0
-	pushfl
+	pushfl_cfi
 	orl $X86_EFLAGS_IF, (%esp)
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $(__USER_CS)
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $(__USER_CS)
 	/*CFI_REL_OFFSET cs, 0*/
 	/*
 	 * Push current_thread_info()->sysenter_return to the stack.
 	 * A tiny bit of offset fixup is necessary - 4*4 means the 4 words
 	 * pushed above; +8 corresponds to copy_thread's esp0 setting.
 	 */
-	pushl (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
 	CFI_REL_OFFSET eip, 0
 
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	SAVE_ALL
 	ENABLE_INTERRUPTS(CLBR_NONE)
 
@@ -486,8 +453,7 @@ sysenter_audit:
 	movl %eax,%edx			/* 2nd arg: syscall number */
 	movl $AUDIT_ARCH_I386,%eax	/* 1st arg: audit arch */
 	call audit_syscall_entry
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	movl PT_EAX(%esp),%eax		/* reload syscall number */
 	jmp sysenter_do_call
 
@@ -529,8 +495,7 @@ ENDPROC(ia32_sysenter_target)
 	# system call handler stub
 ENTRY(system_call)
 	RING0_INT_FRAME			# can't unwind into user space anyway
-	pushl %eax			# save orig_eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax			# save orig_eax
 	SAVE_ALL
 	GET_THREAD_INFO(%ebp)
 					# system call tracing in operation / emulation
@@ -566,7 +531,6 @@ restore_all_notrace:
 	je ldt_ss			# returning to user-space with LDT SS
 restore_nocheck:
 	RESTORE_REGS 4			# skip orig_eax/error_code
-	CFI_ADJUST_CFA_OFFSET -4
 irq_return:
 	INTERRUPT_RETURN
 .section .fixup,"ax"
@@ -619,10 +583,8 @@ ldt_ss:
 	shr $16, %edx
 	mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
 	mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
-	pushl $__ESPFIX_SS
-	CFI_ADJUST_CFA_OFFSET 4
-	push %eax			/* new kernel esp */
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $__ESPFIX_SS
+	pushl_cfi %eax			/* new kernel esp */
 	/* Disable interrupts, but do not irqtrace this section: we
 	 * will soon execute iret and the tracer was already set to
 	 * the irqstate after the iret */
@@ -666,11 +628,9 @@ work_notifysig:				# deal with pending signals and
 
 	ALIGN
 work_notifysig_v86:
-	pushl %ecx			# save ti_flags for do_notify_resume
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx			# save ti_flags for do_notify_resume
 	call save_v86_state		# %eax contains pt_regs pointer
-	popl %ecx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ecx
 	movl %eax, %esp
 #else
 	movl %esp, %eax
@@ -750,14 +710,18 @@ ptregs_##name: \
 #define PTREGSCALL3(name) \
 	ALIGN; \
 ptregs_##name: \
+	CFI_STARTPROC; \
 	leal 4(%esp),%eax; \
-	pushl %eax; \
+	pushl_cfi %eax; \
 	movl PT_EDX(%eax),%ecx; \
 	movl PT_ECX(%eax),%edx; \
 	movl PT_EBX(%eax),%eax; \
 	call sys_##name; \
 	addl $4,%esp; \
-	ret
+	CFI_ADJUST_CFA_OFFSET -4; \
+	ret; \
+	CFI_ENDPROC; \
+ENDPROC(ptregs_##name)
 
 PTREGSCALL1(iopl)
 PTREGSCALL0(fork)
@@ -772,15 +736,19 @@ PTREGSCALL1(vm86old)
 /* Clone is an oddball.  The 4th arg is in %edi */
 	ALIGN;
 ptregs_clone:
+	CFI_STARTPROC
 	leal 4(%esp),%eax
-	pushl %eax
-	pushl PT_EDI(%eax)
+	pushl_cfi %eax
+	pushl_cfi PT_EDI(%eax)
 	movl PT_EDX(%eax),%ecx
 	movl PT_ECX(%eax),%edx
 	movl PT_EBX(%eax),%eax
 	call sys_clone
 	addl $8,%esp
+	CFI_ADJUST_CFA_OFFSET -8
 	ret
+	CFI_ENDPROC
+ENDPROC(ptregs_clone)
 
 .macro FIXUP_ESPFIX_STACK
 /*
@@ -795,10 +763,8 @@ ptregs_clone:
 	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
 	shl $16, %eax
 	addl %esp, %eax			/* the adjusted stack pointer */
-	pushl $__KERNEL_DS
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $__KERNEL_DS
+	pushl_cfi %eax
 	lss (%esp), %esp		/* switch to the normal stack segment */
 	CFI_ADJUST_CFA_OFFSET -8
 .endm
@@ -835,8 +801,7 @@ vector=FIRST_EXTERNAL_VECTOR
       .if vector <> FIRST_EXTERNAL_VECTOR
 	CFI_ADJUST_CFA_OFFSET -4
       .endif
-1:	pushl $(~vector+0x80)	/* Note: always in signed byte range */
-	CFI_ADJUST_CFA_OFFSET 4
+1:	pushl_cfi $(~vector+0x80)	/* Note: always in signed byte range */
       .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
 	jmp 2f
       .endif
@@ -876,8 +841,7 @@ ENDPROC(common_interrupt)
 #define BUILD_INTERRUPT3(name, nr, fn)	\
 ENTRY(name)				\
 	RING0_INT_FRAME;		\
-	pushl $~(nr);			\
-	CFI_ADJUST_CFA_OFFSET 4;	\
+	pushl_cfi $~(nr);		\
 	SAVE_ALL;			\
 	TRACE_IRQS_OFF			\
 	movl %esp,%eax;			\
@@ -893,21 +857,18 @@ ENDPROC(name)
 
 ENTRY(coprocessor_error)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_coprocessor_error
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_coprocessor_error
 	jmp error_code
 	CFI_ENDPROC
 END(coprocessor_error)
 
 ENTRY(simd_coprocessor_error)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
 #ifdef CONFIG_X86_INVD_BUG
 	/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
-661:	pushl $do_general_protection
+661:	pushl_cfi $do_general_protection
 662:
 .section .altinstructions,"a"
 	.balign 4
@@ -922,19 +883,16 @@ ENTRY(simd_coprocessor_error)
 664:
 .previous
 #else
-	pushl $do_simd_coprocessor_error
+	pushl_cfi $do_simd_coprocessor_error
 #endif
-	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
 END(simd_coprocessor_error)
 
 ENTRY(device_not_available)
 	RING0_INT_FRAME
-	pushl $-1			# mark this as an int
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_device_not_available
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $-1			# mark this as an int
+	pushl_cfi $do_device_not_available
 	jmp error_code
 	CFI_ENDPROC
 END(device_not_available)
@@ -956,82 +914,68 @@ END(native_irq_enable_sysexit)
 
 ENTRY(overflow)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_overflow
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_overflow
 	jmp error_code
 	CFI_ENDPROC
 END(overflow)
 
 ENTRY(bounds)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_bounds
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_bounds
 	jmp error_code
 	CFI_ENDPROC
 END(bounds)
 
 ENTRY(invalid_op)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_invalid_op
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_invalid_op
 	jmp error_code
 	CFI_ENDPROC
 END(invalid_op)
 
 ENTRY(coprocessor_segment_overrun)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_coprocessor_segment_overrun
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_coprocessor_segment_overrun
 	jmp error_code
 	CFI_ENDPROC
 END(coprocessor_segment_overrun)
 
 ENTRY(invalid_TSS)
 	RING0_EC_FRAME
-	pushl $do_invalid_TSS
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_invalid_TSS
 	jmp error_code
 	CFI_ENDPROC
 END(invalid_TSS)
 
 ENTRY(segment_not_present)
 	RING0_EC_FRAME
-	pushl $do_segment_not_present
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_segment_not_present
 	jmp error_code
 	CFI_ENDPROC
 END(segment_not_present)
 
 ENTRY(stack_segment)
 	RING0_EC_FRAME
-	pushl $do_stack_segment
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_stack_segment
 	jmp error_code
 	CFI_ENDPROC
 END(stack_segment)
 
 ENTRY(alignment_check)
 	RING0_EC_FRAME
-	pushl $do_alignment_check
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_alignment_check
 	jmp error_code
 	CFI_ENDPROC
 END(alignment_check)
 
 ENTRY(divide_error)
 	RING0_INT_FRAME
-	pushl $0			# no error code
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_divide_error
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0			# no error code
+	pushl_cfi $do_divide_error
 	jmp error_code
 	CFI_ENDPROC
 END(divide_error)
@@ -1039,10 +983,8 @@ END(divide_error)
 #ifdef CONFIG_X86_MCE
 ENTRY(machine_check)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl machine_check_vector
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi machine_check_vector
 	jmp error_code
 	CFI_ENDPROC
 END(machine_check)
@@ -1050,10 +992,8 @@ END(machine_check)
 
 ENTRY(spurious_interrupt_bug)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_spurious_interrupt_bug
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_spurious_interrupt_bug
 	jmp error_code
 	CFI_ENDPROC
 END(spurious_interrupt_bug)
@@ -1084,8 +1024,7 @@ ENTRY(xen_sysenter_target)
 
 ENTRY(xen_hypervisor_callback)
 	CFI_STARTPROC
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
 	SAVE_ALL
 	TRACE_IRQS_OFF
 
@@ -1121,23 +1060,20 @@ ENDPROC(xen_hypervisor_callback)
 # We distinguish between categories by maintaining a status value in EAX.
 ENTRY(xen_failsafe_callback)
 	CFI_STARTPROC
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	movl $1,%eax
 1:	mov 4(%esp),%ds
 2:	mov 8(%esp),%es
 3:	mov 12(%esp),%fs
 4:	mov 16(%esp),%gs
 	testl %eax,%eax
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
 	lea 16(%esp),%esp
 	CFI_ADJUST_CFA_OFFSET -16
 	jz 5f
 	addl $16,%esp
 	jmp iret_exc		# EAX != 0 => Category 2 (Bad IRET)
-5:	pushl $0		# EAX == 0 => Category 1 (Bad segment)
-	CFI_ADJUST_CFA_OFFSET 4
+5:	pushl_cfi $0		# EAX == 0 => Category 1 (Bad segment)
 	SAVE_ALL
 	jmp ret_from_exception
 	CFI_ENDPROC
@@ -1287,40 +1223,29 @@ syscall_table_size=(.-sys_call_table)
 
 ENTRY(page_fault)
 	RING0_EC_FRAME
-	pushl $do_page_fault
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_page_fault
 	ALIGN
 error_code:
 	/* the function address is in %gs's slot on the stack */
-	pushl %fs
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %fs
 	/*CFI_REL_OFFSET fs, 0*/
-	pushl %es
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %es
 	/*CFI_REL_OFFSET es, 0*/
-	pushl %ds
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ds
 	/*CFI_REL_OFFSET ds, 0*/
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	CFI_REL_OFFSET eax, 0
-	pushl %ebp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebp
 	CFI_REL_OFFSET ebp, 0
-	pushl %edi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edi
 	CFI_REL_OFFSET edi, 0
-	pushl %esi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %esi
 	CFI_REL_OFFSET esi, 0
-	pushl %edx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edx
 	CFI_REL_OFFSET edx, 0
-	pushl %ecx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx
 	CFI_REL_OFFSET ecx, 0
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	CFI_REL_OFFSET ebx, 0
 	cld
 	movl $(__KERNEL_PERCPU), %ecx
@@ -1362,12 +1287,9 @@ END(page_fault)
 	movl TSS_sysenter_sp0 + \offset(%esp), %esp
 	CFI_DEF_CFA esp, 0
 	CFI_UNDEFINED eip
-	pushfl
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $__KERNEL_CS
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $sysenter_past_esp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushfl_cfi
+	pushl_cfi $__KERNEL_CS
+	pushl_cfi $sysenter_past_esp
 	CFI_REL_OFFSET eip, 0
 .endm
 
@@ -1377,8 +1299,7 @@ ENTRY(debug)
 	jne debug_stack_correct
 	FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
 debug_stack_correct:
-	pushl $-1			# mark this as an int
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $-1			# mark this as an int
 	SAVE_ALL
 	TRACE_IRQS_OFF
 	xorl %edx,%edx			# error code 0
@@ -1398,32 +1319,27 @@ END(debug)
  */
 ENTRY(nmi)
 	RING0_INT_FRAME
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	movl %ss, %eax
 	cmpw $__ESPFIX_SS, %ax
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
 	je nmi_espfix_stack
 	cmpl $ia32_sysenter_target,(%esp)
 	je nmi_stack_fixup
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	movl %esp,%eax
 	/* Do not access memory above the end of our stack page,
 	 * it might not exist.
 	 */
 	andl $(THREAD_SIZE-1),%eax
 	cmpl $(THREAD_SIZE-20),%eax
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
 	jae nmi_stack_correct
 	cmpl $ia32_sysenter_target,12(%esp)
 	je nmi_debug_stack_check
 nmi_stack_correct:
 	/* We have a RING0_INT_FRAME here */
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	SAVE_ALL
 	xorl %edx,%edx		# zero error code
 	movl %esp,%eax		# pt_regs pointer
@@ -1452,18 +1368,14 @@ nmi_espfix_stack:
 	 *
 	 * create the pointer to lss back
 	 */
-	pushl %ss
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl %esp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ss
+	pushl_cfi %esp
 	addl $4, (%esp)
 	/* copy the iret frame of 12 bytes */
 	.rept 3
-	pushl 16(%esp)
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi 16(%esp)
 	.endr
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	SAVE_ALL
 	FIXUP_ESPFIX_STACK		# %eax == %esp
 	xorl %edx,%edx			# zero error code
@@ -1477,8 +1389,7 @@ END(nmi)
 
 ENTRY(int3)
 	RING0_INT_FRAME
-	pushl $-1			# mark this as an int
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $-1			# mark this as an int
 	SAVE_ALL
 	TRACE_IRQS_OFF
 	xorl %edx,%edx		# zero error code
@@ -1490,8 +1401,7 @@ END(int3)
 
 ENTRY(general_protection)
 	RING0_EC_FRAME
-	pushl $do_general_protection
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_general_protection
 	jmp error_code
 	CFI_ENDPROC
 END(general_protection)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 17be5ec7cbba..8851a2bb8c0b 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -213,23 +213,17 @@ ENDPROC(native_usergs_sysret64)
 	.macro FAKE_STACK_FRAME child_rip
 	/* push in order ss, rsp, eflags, cs, rip */
 	xorl %eax, %eax
-	pushq $__KERNEL_DS /* ss */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi $__KERNEL_DS /* ss */
 	/*CFI_REL_OFFSET	ss,0*/
-	pushq %rax /* rsp */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi %rax /* rsp */
 	CFI_REL_OFFSET	rsp,0
-	pushq $X86_EFLAGS_IF /* eflags - interrupts on */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi $X86_EFLAGS_IF /* eflags - interrupts on */
 	/*CFI_REL_OFFSET	rflags,0*/
-	pushq $__KERNEL_CS /* cs */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi $__KERNEL_CS /* cs */
 	/*CFI_REL_OFFSET	cs,0*/
-	pushq \child_rip /* rip */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi \child_rip /* rip */
 	CFI_REL_OFFSET	rip,0
-	pushq	%rax /* orig rax */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi %rax /* orig rax */
 	.endm
 
 	.macro UNFAKE_STACK_FRAME
@@ -398,10 +392,8 @@ ENTRY(ret_from_fork)
 
 	LOCK ; btr $TIF_FORK,TI_flags(%r8)
 
-	push kernel_eflags(%rip)
-	CFI_ADJUST_CFA_OFFSET 8
-	popf					# reset kernel eflags
-	CFI_ADJUST_CFA_OFFSET -8
+	pushq_cfi kernel_eflags(%rip)
+	popfq_cfi				# reset kernel eflags
 
 	call schedule_tail			# rdi: 'prev' task parameter
 
@@ -521,11 +513,9 @@ sysret_careful:
 	jnc sysret_signal
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq %rdi
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %rdi
 	call schedule
-	popq  %rdi
-	CFI_ADJUST_CFA_OFFSET -8
+	popq_cfi %rdi
 	jmp sysret_check
 
 	/* Handle a signal */
@@ -634,11 +624,9 @@ int_careful:
 	jnc  int_very_careful
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq %rdi
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %rdi
 	call schedule
-	popq %rdi
-	CFI_ADJUST_CFA_OFFSET -8
+	popq_cfi %rdi
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	jmp int_with_check
@@ -652,12 +640,10 @@ int_check_syscall_exit_work:
 	/* Check for syscall exit trace */
 	testl $_TIF_WORK_SYSCALL_EXIT,%edx
 	jz int_signal
-	pushq %rdi
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %rdi
 	leaq 8(%rsp),%rdi	# &ptregs -> arg1
 	call syscall_trace_leave
-	popq %rdi
-	CFI_ADJUST_CFA_OFFSET -8
+	popq_cfi %rdi
 	andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
 	jmp int_restore_rest
 
@@ -714,9 +700,8 @@ END(ptregscall_common)
 
 ENTRY(stub_execve)
 	CFI_STARTPROC
-	popq %r11
-	CFI_ADJUST_CFA_OFFSET -8
-	CFI_REGISTER rip, r11
+	addq $8, %rsp
+	PARTIAL_FRAME 0
 	SAVE_REST
 	FIXUP_TOP_OF_STACK %r11
 	movq %rsp, %rcx
@@ -735,7 +720,7 @@ END(stub_execve)
 ENTRY(stub_rt_sigreturn)
 	CFI_STARTPROC
 	addq $8, %rsp
-	CFI_ADJUST_CFA_OFFSET	-8
+	PARTIAL_FRAME 0
 	SAVE_REST
 	movq %rsp,%rdi
 	FIXUP_TOP_OF_STACK %r11
@@ -766,8 +751,7 @@ vector=FIRST_EXTERNAL_VECTOR
       .if vector <> FIRST_EXTERNAL_VECTOR
 	CFI_ADJUST_CFA_OFFSET -8
       .endif
-1:	pushq $(~vector+0x80)	/* Note: always in signed byte range */
-	CFI_ADJUST_CFA_OFFSET 8
+1:	pushq_cfi $(~vector+0x80)	/* Note: always in signed byte range */
       .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
 	jmp 2f
       .endif
@@ -796,8 +780,8 @@ END(interrupt)
 
 /* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
-	subq $10*8, %rsp
-	CFI_ADJUST_CFA_OFFSET 10*8
+	subq $ORIG_RAX-ARGOFFSET+8, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-ARGOFFSET+8
 	call save_args
 	PARTIAL_FRAME 0
 	call \func
@@ -822,6 +806,7 @@ ret_from_intr:
 	TRACE_IRQS_OFF
 	decl PER_CPU_VAR(irq_count)
 	leaveq
+	CFI_RESTORE		rbp
 	CFI_DEF_CFA_REGISTER	rsp
 	CFI_ADJUST_CFA_OFFSET	-8
 exit_intr:
@@ -903,11 +888,9 @@ retint_careful:
 	jnc   retint_signal
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq %rdi
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi %rdi
 	call  schedule
-	popq %rdi
-	CFI_ADJUST_CFA_OFFSET	-8
+	popq_cfi %rdi
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
@@ -956,8 +939,7 @@ END(common_interrupt)
 .macro apicinterrupt num sym do_sym
 ENTRY(\sym)
 	INTR_FRAME
-	pushq $~(\num)
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi $~(\num)
 	interrupt \do_sym
 	jmp ret_from_intr
 	CFI_ENDPROC
@@ -1036,8 +1018,8 @@ ENTRY(\sym)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
-	subq $15*8,%rsp
-	CFI_ADJUST_CFA_OFFSET 15*8
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call error_entry
 	DEFAULT_FRAME 0
 	movq %rsp,%rdi		/* pt_regs pointer */
@@ -1052,9 +1034,9 @@ END(\sym)
 ENTRY(\sym)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $-1		/* ORIG_RAX: no syscall to restart */
-	CFI_ADJUST_CFA_OFFSET 8
-	subq $15*8, %rsp
+	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call save_paranoid
 	TRACE_IRQS_OFF
 	movq %rsp,%rdi		/* pt_regs pointer */
@@ -1070,9 +1052,9 @@ END(\sym)
 ENTRY(\sym)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $-1		/* ORIG_RAX: no syscall to restart */
-	CFI_ADJUST_CFA_OFFSET 8
-	subq $15*8, %rsp
+	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call save_paranoid
 	TRACE_IRQS_OFF
 	movq %rsp,%rdi		/* pt_regs pointer */
@@ -1089,8 +1071,8 @@ END(\sym)
 ENTRY(\sym)
 	XCPT_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	subq $15*8,%rsp
-	CFI_ADJUST_CFA_OFFSET 15*8
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call error_entry
 	DEFAULT_FRAME 0
 	movq %rsp,%rdi			/* pt_regs pointer */
@@ -1107,8 +1089,8 @@ END(\sym)
 ENTRY(\sym)
 	XCPT_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	subq $15*8,%rsp
-	CFI_ADJUST_CFA_OFFSET 15*8
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call save_paranoid
 	DEFAULT_FRAME 0
 	TRACE_IRQS_OFF
@@ -1139,16 +1121,14 @@ zeroentry simd_coprocessor_error do_simd_coprocessor_error
 	/* edi:  new selector */
 ENTRY(native_load_gs_index)
 	CFI_STARTPROC
-	pushf
-	CFI_ADJUST_CFA_OFFSET 8
+	pushfq_cfi
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
 	SWAPGS
 gs_change:
 	movl %edi,%gs
 2:	mfence		/* workaround */
 	SWAPGS
-	popf
-	CFI_ADJUST_CFA_OFFSET -8
+	popfq_cfi
 	ret
 	CFI_ENDPROC
 END(native_load_gs_index)
@@ -1215,8 +1195,7 @@ END(kernel_execve)
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(call_softirq)
 	CFI_STARTPROC
-	push %rbp
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi %rbp
 	CFI_REL_OFFSET rbp,0
 	mov  %rsp,%rbp
 	CFI_DEF_CFA_REGISTER rbp
@@ -1225,6 +1204,7 @@ ENTRY(call_softirq)
 	push  %rbp			# backlink for old unwinder
 	call __do_softirq
 	leaveq
+	CFI_RESTORE		rbp
 	CFI_DEF_CFA_REGISTER	rsp
 	CFI_ADJUST_CFA_OFFSET   -8
 	decl PER_CPU_VAR(irq_count)
@@ -1368,7 +1348,7 @@ paranoidzeroentry machine_check *machine_check_vector(%rip)
 
 	/* ebx:	no swapgs flag */
 ENTRY(paranoid_exit)
-	INTR_FRAME
+	DEFAULT_FRAME
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl %ebx,%ebx				/* swapgs needed? */
@@ -1445,7 +1425,6 @@ error_swapgs:
 error_sti:
 	TRACE_IRQS_OFF
 	ret
-	CFI_ENDPROC
 
 /*
  * There are two places in the kernel that can potentially fault with
@@ -1470,6 +1449,7 @@ bstep_iret:
 	/* Fix truncated RIP */
 	movq %rcx,RIP+8(%rsp)
 	jmp error_swapgs
+	CFI_ENDPROC
 END(error_entry)
 
 
@@ -1498,8 +1478,8 @@ ENTRY(nmi)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1
-	subq $15*8, %rsp
-	CFI_ADJUST_CFA_OFFSET 15*8
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call save_paranoid
 	DEFAULT_FRAME 0
 	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index cd37469b54ee..3afb33f14d2d 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -257,14 +257,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	return mod_code_status;
 }
 
-
-
-
-static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
-
 static unsigned char *ftrace_nop_replace(void)
 {
-	return ftrace_nop;
+	return ideal_nop5;
 }
 
 static int
@@ -338,62 +333,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	extern const unsigned char ftrace_test_p6nop[];
-	extern const unsigned char ftrace_test_nop5[];
-	extern const unsigned char ftrace_test_jmp[];
-	int faulted = 0;
-
-	/*
-	 * There is no good nop for all x86 archs.
-	 * We will default to using the P6_NOP5, but first we
-	 * will test to make sure that the nop will actually
-	 * work on this CPU. If it faults, we will then
-	 * go to a lesser efficient 5 byte nop. If that fails
-	 * we then just use a jmp as our nop. This isn't the most
-	 * efficient nop, but we can not use a multi part nop
-	 * since we would then risk being preempted in the middle
-	 * of that nop, and if we enabled tracing then, it might
-	 * cause a system crash.
-	 *
-	 * TODO: check the cpuid to determine the best nop.
-	 */
-	asm volatile (
-		"ftrace_test_jmp:"
-		"jmp ftrace_test_p6nop\n"
-		"nop\n"
-		"nop\n"
-		"nop\n"  /* 2 byte jmp + 3 bytes */
-		"ftrace_test_p6nop:"
-		P6_NOP5
-		"jmp 1f\n"
-		"ftrace_test_nop5:"
-		".byte 0x66,0x66,0x66,0x66,0x90\n"
-		"1:"
-		".section .fixup, \"ax\"\n"
-		"2:	movl $1, %0\n"
-		"	jmp ftrace_test_nop5\n"
-		"3:	movl $2, %0\n"
-		"	jmp 1b\n"
-		".previous\n"
-		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
-		_ASM_EXTABLE(ftrace_test_nop5, 3b)
-		: "=r"(faulted) : "0" (faulted));
-
-	switch (faulted) {
-	case 0:
-		pr_info("converting mcount calls to 0f 1f 44 00 00\n");
-		memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE);
-		break;
-	case 1:
-		pr_info("converting mcount calls to 66 66 66 66 90\n");
-		memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
-		break;
-	case 2:
-		pr_info("converting mcount calls to jmp . + 5\n");
-		memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
-		break;
-	}
-
 	/* The return code is retured via data */
 	*(unsigned long *)data = 0;
 
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index 3e66bd364a9d..af0699ba48cf 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -1,5 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/bios_ebda.h>
@@ -51,5 +52,5 @@ void __init reserve_ebda_region(void)
 		lowmem = 0x9f000;
 
 	/* reserve all memory between lowmem and the 1MB mark */
-	reserve_early_overlap_ok(lowmem, 0x100000, "BIOS reserved");
+	memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved");
 }
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 784360c0625c..9a6ca2392170 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/start_kernel.h>
 #include <linux/mm.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -30,17 +31,18 @@ static void __init i386_default_early_setup(void)
 
 void __init i386_start_kernel(void)
 {
+	memblock_init();
+
 #ifdef CONFIG_X86_TRAMPOLINE
 	/*
 	 * But first pinch a few for the stack/trampoline stuff
 	 * FIXME: Don't need the extra page at 4K, but need to fix
 	 * trampoline before removing it. (see the GDT stuff)
 	 */
-	reserve_early_overlap_ok(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE,
-					 "EX TRAMPOLINE");
+	memblock_x86_reserve_range(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
 #endif
 
-	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+	memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
@@ -49,7 +51,7 @@ void __init i386_start_kernel(void)
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
 		u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+		memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 7147143fd614..97adf9828b95 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -12,6 +12,7 @@
 #include <linux/percpu.h>
 #include <linux/start_kernel.h>
 #include <linux/io.h>
+#include <linux/memblock.h>
 
 #include <asm/processor.h>
 #include <asm/proto.h>
@@ -98,7 +99,9 @@ void __init x86_64_start_reservations(char *real_mode_data)
 {
 	copy_bootdata(__va(real_mode_data));
 
-	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+	memblock_init();
+
+	memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
@@ -107,7 +110,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
 		unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+		memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 7494999141b3..d0eb7b90d12c 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -380,44 +380,35 @@ static int hpet_next_event(unsigned long delta,
 			   struct clock_event_device *evt, int timer)
 {
 	u32 cnt;
+	s32 res;
 
 	cnt = hpet_readl(HPET_COUNTER);
 	cnt += (u32) delta;
 	hpet_writel(cnt, HPET_Tn_CMP(timer));
 
 	/*
-	 * We need to read back the CMP register on certain HPET
-	 * implementations (ATI chipsets) which seem to delay the
-	 * transfer of the compare register into the internal compare
-	 * logic. With small deltas this might actually be too late as
-	 * the counter could already be higher than the compare value
-	 * at that point and we would wait for the next hpet interrupt
-	 * forever. We found out that reading the CMP register back
-	 * forces the transfer so we can rely on the comparison with
-	 * the counter register below. If the read back from the
-	 * compare register does not match the value we programmed
-	 * then we might have a real hardware problem. We can not do
-	 * much about it here, but at least alert the user/admin with
-	 * a prominent warning.
-	 *
-	 * An erratum on some chipsets (ICH9,..), results in
-	 * comparator read immediately following a write returning old
-	 * value. Workaround for this is to read this value second
-	 * time, when first read returns old value.
-	 *
-	 * In fact the write to the comparator register is delayed up
-	 * to two HPET cycles so the workaround we tried to restrict
-	 * the readback to those known to be borked ATI chipsets
-	 * failed miserably. So we give up on optimizations forever
-	 * and penalize all HPET incarnations unconditionally.
+	 * HPETs are a complete disaster. The compare register is
+	 * based on a equal comparison and neither provides a less
+	 * than or equal functionality (which would require to take
+	 * the wraparound into account) nor a simple count down event
+	 * mode. Further the write to the comparator register is
+	 * delayed internally up to two HPET clock cycles in certain
+	 * chipsets (ATI, ICH9,10). We worked around that by reading
+	 * back the compare register, but that required another
+	 * workaround for ICH9,10 chips where the first readout after
+	 * write can return the old stale value. We already have a
+	 * minimum delta of 5us enforced, but a NMI or SMI hitting
+	 * between the counter readout and the comparator write can
+	 * move us behind that point easily. Now instead of reading
+	 * the compare register back several times, we make the ETIME
+	 * decision based on the following: Return ETIME if the
+	 * counter value after the write is less than 8 HPET cycles
+	 * away from the event or if the counter is already ahead of
+	 * the event.
 	 */
-	if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) {
-		if (hpet_readl(HPET_Tn_CMP(timer)) != cnt)
-			printk_once(KERN_WARNING
-				"hpet: compare register read back failed.\n");
-	}
+	res = (s32)(cnt - hpet_readl(HPET_COUNTER));
 
-	return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
+	return res < 8 ? -ETIME : 0;
 }
 
 static void hpet_legacy_set_mode(enum clock_event_mode mode,
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index a46cb3522c0c..58bb239a2fd7 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -68,19 +68,22 @@ static void __cpuinit init_thread_xstate(void)
 	 */
 
 	if (!HAVE_HWFP) {
+		/*
+		 * Disable xsave as we do not support it if i387
+		 * emulation is enabled.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
 		xstate_size = sizeof(struct i387_soft_struct);
 		return;
 	}
 
 	if (cpu_has_fxsr)
 		xstate_size = sizeof(struct i387_fxsave_struct);
-#ifdef CONFIG_X86_32
 	else
 		xstate_size = sizeof(struct i387_fsave_struct);
-#endif
 }
 
-#ifdef CONFIG_X86_64
 /*
  * Called at bootup to set up the initial FPU state that is later cloned
  * into all processes.
@@ -88,12 +91,21 @@ static void __cpuinit init_thread_xstate(void)
 
 void __cpuinit fpu_init(void)
 {
-	unsigned long oldcr0 = read_cr0();
-
-	set_in_cr4(X86_CR4_OSFXSR);
-	set_in_cr4(X86_CR4_OSXMMEXCPT);
+	unsigned long cr0;
+	unsigned long cr4_mask = 0;
 
-	write_cr0(oldcr0 & ~(X86_CR0_TS|X86_CR0_EM)); /* clear TS and EM */
+	if (cpu_has_fxsr)
+		cr4_mask |= X86_CR4_OSFXSR;
+	if (cpu_has_xmm)
+		cr4_mask |= X86_CR4_OSXMMEXCPT;
+	if (cr4_mask)
+		set_in_cr4(cr4_mask);
+
+	cr0 = read_cr0();
+	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
+	if (!HAVE_HWFP)
+		cr0 |= X86_CR0_EM;
+	write_cr0(cr0);
 
 	if (!smp_processor_id())
 		init_thread_xstate();
@@ -104,24 +116,12 @@ void __cpuinit fpu_init(void)
 	clear_used_math();
 }
 
-#else	/* CONFIG_X86_64 */
-
-void __cpuinit fpu_init(void)
-{
-	if (!smp_processor_id())
-		init_thread_xstate();
-}
-
-#endif	/* CONFIG_X86_32 */
-
 void fpu_finit(struct fpu *fpu)
 {
-#ifdef CONFIG_X86_32
 	if (!HAVE_HWFP) {
 		finit_soft_fpu(&fpu->state->soft);
 		return;
 	}
-#endif
 
 	if (cpu_has_fxsr) {
 		struct i387_fxsave_struct *fx = &fpu->state->fxsave;
@@ -386,19 +386,17 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 #ifdef CONFIG_X86_64
 	env->fip = fxsave->rip;
 	env->foo = fxsave->rdp;
+	/*
+	 * should be actually ds/cs at fpu exception time, but
+	 * that information is not available in 64bit mode.
+	 */
+	env->fcs = task_pt_regs(tsk)->cs;
 	if (tsk == current) {
-		/*
-		 * should be actually ds/cs at fpu exception time, but
-		 * that information is not available in 64bit mode.
-		 */
-		asm("mov %%ds, %[fos]" : [fos] "=r" (env->fos));
-		asm("mov %%cs, %[fcs]" : [fcs] "=r" (env->fcs));
+		savesegment(ds, env->fos);
 	} else {
-		struct pt_regs *regs = task_pt_regs(tsk);
-
-		env->fos = 0xffff0000 | tsk->thread.ds;
-		env->fcs = regs->cs;
+		env->fos = tsk->thread.ds;
 	}
+	env->fos |= 0xffff0000;
 #else
 	env->fip = fxsave->fip;
 	env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 10709f29d166..50fbbe60e507 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -49,20 +49,19 @@ static inline int check_stack_overflow(void) { return 0; }
 static inline void print_stack_overflow(void) { }
 #endif
 
-#ifdef CONFIG_4KSTACKS
 /*
  * per-CPU IRQ handling contexts (thread information and stack)
  */
 union irq_ctx {
 	struct thread_info      tinfo;
 	u32                     stack[THREAD_SIZE/sizeof(u32)];
-} __attribute__((aligned(PAGE_SIZE)));
+} __attribute__((aligned(THREAD_SIZE)));
 
 static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
 static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
 
-static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, hardirq_stack);
-static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, softirq_stack);
+static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, hardirq_stack, THREAD_SIZE);
+static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, softirq_stack, THREAD_SIZE);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -187,11 +186,6 @@ asmlinkage void do_softirq(void)
 	local_irq_restore(flags);
 }
 
-#else
-static inline int
-execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; }
-#endif
-
 bool handle_irq(unsigned irq, struct pt_regs *regs)
 {
 	struct irq_desc *desc;
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
new file mode 100644
index 000000000000..961b6b30ba90
--- /dev/null
+++ b/arch/x86/kernel/jump_label.c
@@ -0,0 +1,50 @@
+/*
+ * jump label x86 support
+ *
+ * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
+ *
+ */
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/cpu.h>
+#include <asm/kprobes.h>
+#include <asm/alternative.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+union jump_code_union {
+	char code[JUMP_LABEL_NOP_SIZE];
+	struct {
+		char jump;
+		int offset;
+	} __attribute__((packed));
+};
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	union jump_code_union code;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		code.jump = 0xe9;
+		code.offset = entry->target -
+				(entry->code + JUMP_LABEL_NOP_SIZE);
+	} else
+		memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+	get_online_cpus();
+	mutex_lock(&text_mutex);
+	text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+}
+
+void arch_jump_label_text_poke_early(jump_label_t addr)
+{
+	text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+}
+
+#endif
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 770ebfb349e9..1cbd54c0df99 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -230,9 +230,6 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 	return 0;
 }
 
-/* Dummy buffers for kallsyms_lookup */
-static char __dummy_buf[KSYM_NAME_LEN];
-
 /* Check if paddr is at an instruction boundary */
 static int __kprobes can_probe(unsigned long paddr)
 {
@@ -241,7 +238,7 @@ static int __kprobes can_probe(unsigned long paddr)
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
-	if (!kallsyms_lookup(paddr, NULL, &offset, NULL, __dummy_buf))
+	if (!kallsyms_lookup_size_offset(paddr, NULL, &offset))
 		return 0;
 
 	/* Decode instructions */
@@ -1129,7 +1126,7 @@ static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr,
 	*(unsigned long *)addr = val;
 }
 
-void __kprobes kprobes_optinsn_template_holder(void)
+static void __used __kprobes kprobes_optinsn_template_holder(void)
 {
 	asm volatile (
 			".global optprobe_template_entry\n"
@@ -1221,7 +1218,8 @@ static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
 	}
 	/* Check whether the address range is reserved */
 	if (ftrace_text_reserved(src, src + len - 1) ||
-	    alternatives_text_reserved(src, src + len - 1))
+	    alternatives_text_reserved(src, src + len - 1) ||
+	    jump_label_text_reserved(src, src + len - 1))
 		return -EBUSY;
 
 	return len;
@@ -1269,11 +1267,9 @@ static int __kprobes can_optimize(unsigned long paddr)
 	unsigned long addr, size = 0, offset = 0;
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
-	/* Dummy buffers for lookup_symbol_attrs */
-	static char __dummy_buf[KSYM_NAME_LEN];
 
 	/* Lookup symbol including addr */
-	if (!kallsyms_lookup(paddr, &size, &offset, NULL, __dummy_buf))
+	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
 		return 0;
 
 	/* Check there is enough space for a relative jump. */
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 035c8c529181..b3ea9db39db6 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -36,7 +36,7 @@ static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
 		if (!page)
 			goto out;
 		pud = (pud_t *)page_address(page);
-		memset(pud, 0, PAGE_SIZE);
+		clear_page(pud);
 		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
 	}
 	pud = pud_offset(pgd, addr);
@@ -45,7 +45,7 @@ static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
 		if (!page)
 			goto out;
 		pmd = (pmd_t *)page_address(page);
-		memset(pmd, 0, PAGE_SIZE);
+		clear_page(pmd);
 		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
 	}
 	pmd = pmd_offset(pud, addr);
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 1c355c550960..8f2956091735 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -239,6 +239,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 		apply_paravirt(pseg, pseg + para->sh_size);
 	}
 
+	/* make jump label nops */
+	jump_label_apply_nops(me);
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index d7b6f7fb4fec..9af64d9c4b67 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/bitops.h>
@@ -657,7 +658,7 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
 
-	reserve_early_overlap_ok(mpf->physptr, mpf->physptr+size, "MP-table mpc");
+	memblock_x86_reserve_range(mpf->physptr, mpf->physptr+size, "* MP-table mpc");
 }
 
 static int __init smp_scan_config(unsigned long base, unsigned long length)
@@ -686,7 +687,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 			       mpf, (u64)virt_to_phys(mpf));
 
 			mem = virt_to_phys(mpf);
-			reserve_early_overlap_ok(mem, mem + sizeof(*mpf), "MP-table mpf");
+			memblock_x86_reserve_range(mem, mem + sizeof(*mpf), "* MP-table mpf");
 			if (mpf->physptr)
 				smp_reserve_memory(mpf);
 
diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c
index 635888cf050d..37c49934c785 100644
--- a/arch/x86/kernel/olpc.c
+++ b/arch/x86/kernel/olpc.c
@@ -183,8 +183,21 @@ err:
 }
 EXPORT_SYMBOL_GPL(olpc_ec_cmd);
 
-#ifdef CONFIG_OLPC_OPENFIRMWARE
-static void __init platform_detect(void)
+static bool __init check_ofw_architecture(void)
+{
+	size_t propsize;
+	char olpc_arch[5];
+	const void *args[] = { NULL, "architecture", olpc_arch, (void *)5 };
+	void *res[] = { &propsize };
+
+	if (olpc_ofw("getprop", args, res)) {
+		printk(KERN_ERR "ofw: getprop call failed!\n");
+		return false;
+	}
+	return propsize == 5 && strncmp("OLPC", olpc_arch, 5) == 0;
+}
+
+static u32 __init get_board_revision(void)
 {
 	size_t propsize;
 	__be32 rev;
@@ -193,46 +206,27 @@ static void __init platform_detect(void)
 
 	if (olpc_ofw("getprop", args, res) || propsize != 4) {
 		printk(KERN_ERR "ofw: getprop call failed!\n");
-		rev = cpu_to_be32(0);
+		return cpu_to_be32(0);
 	}
-	olpc_platform_info.boardrev = be32_to_cpu(rev);
+	return be32_to_cpu(rev);
 }
-#else
-static void __init platform_detect(void)
+
+static bool __init platform_detect(void)
 {
-	/* stopgap until OFW support is added to the kernel */
-	olpc_platform_info.boardrev = olpc_board(0xc2);
+	if (!check_ofw_architecture())
+		return false;
+	olpc_platform_info.flags |= OLPC_F_PRESENT;
+	olpc_platform_info.boardrev = get_board_revision();
+	return true;
 }
-#endif
 
 static int __init olpc_init(void)
 {
-	unsigned char *romsig;
-
-	/* The ioremap check is dangerous; limit what we run it on */
-	if (!is_geode() || cs5535_has_vsa2())
+	if (!olpc_ofw_present() || !platform_detect())
 		return 0;
 
 	spin_lock_init(&ec_lock);
 
-	romsig = ioremap(0xffffffc0, 16);
-	if (!romsig)
-		return 0;
-
-	if (strncmp(romsig, "CL1   Q", 7))
-		goto unmap;
-	if (strncmp(romsig+6, romsig+13, 3)) {
-		printk(KERN_INFO "OLPC BIOS signature looks invalid.  "
-				"Assuming not OLPC\n");
-		goto unmap;
-	}
-
-	printk(KERN_INFO "OLPC board with OpenFirmware %.16s\n", romsig);
-	olpc_platform_info.flags |= OLPC_F_PRESENT;
-
-	/* get the platform revision */
-	platform_detect();
-
 	/* assume B1 and above models always have a DCON */
 	if (olpc_board_at_least(olpc_board(0xb1)))
 		olpc_platform_info.flags |= OLPC_F_DCON;
@@ -254,8 +248,6 @@ static int __init olpc_init(void)
 			olpc_platform_info.boardrev >> 4,
 			olpc_platform_info.ecver);
 
-unmap:
-	iounmap(romsig);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/olpc_ofw.c b/arch/x86/kernel/olpc_ofw.c
index 3218aa71ab5e..787320464379 100644
--- a/arch/x86/kernel/olpc_ofw.c
+++ b/arch/x86/kernel/olpc_ofw.c
@@ -74,6 +74,12 @@ int __olpc_ofw(const char *name, int nr_args, const void **args, int nr_res,
 }
 EXPORT_SYMBOL_GPL(__olpc_ofw);
 
+bool olpc_ofw_present(void)
+{
+	return olpc_ofw_cif != NULL;
+}
+EXPORT_SYMBOL_GPL(olpc_ofw_present);
+
 /* OFW cif _should_ be above this address */
 #define OFW_MIN 0xff000000
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1db183ed7c01..c5b250011fd4 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -413,7 +413,6 @@ struct pv_mmu_ops pv_mmu_ops = {
 
 	.alloc_pte = paravirt_nop,
 	.alloc_pmd = paravirt_nop,
-	.alloc_pmd_clone = paravirt_nop,
 	.alloc_pud = paravirt_nop,
 	.release_pte = paravirt_nop,
 	.release_pmd = paravirt_nop,
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 078d4ec1a9d9..f56a117cef68 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -47,6 +47,7 @@
 #include <asm/rio.h>
 #include <asm/bios_ebda.h>
 #include <asm/x86_init.h>
+#include <asm/iommu_table.h>
 
 #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
 int use_calgary __read_mostly = 1;
@@ -1364,7 +1365,7 @@ static int __init calgary_iommu_init(void)
 	return 0;
 }
 
-void __init detect_calgary(void)
+int __init detect_calgary(void)
 {
 	int bus;
 	void *tbl;
@@ -1378,13 +1379,13 @@ void __init detect_calgary(void)
 	 * another HW IOMMU already, bail out.
 	 */
 	if (no_iommu || iommu_detected)
-		return;
+		return -ENODEV;
 
 	if (!use_calgary)
-		return;
+		return -ENODEV;
 
 	if (!early_pci_allowed())
-		return;
+		return -ENODEV;
 
 	printk(KERN_DEBUG "Calgary: detecting Calgary via BIOS EBDA area\n");
 
@@ -1410,13 +1411,13 @@ void __init detect_calgary(void)
 	if (!rio_table_hdr) {
 		printk(KERN_DEBUG "Calgary: Unable to locate Rio Grande table "
 		       "in EBDA - bailing!\n");
-		return;
+		return -ENODEV;
 	}
 
 	ret = build_detail_arrays();
 	if (ret) {
 		printk(KERN_DEBUG "Calgary: build_detail_arrays ret %d\n", ret);
-		return;
+		return -ENOMEM;
 	}
 
 	specified_table_size = determine_tce_table_size((is_kdump_kernel() ?
@@ -1464,7 +1465,7 @@ void __init detect_calgary(void)
 
 		x86_init.iommu.iommu_init = calgary_iommu_init;
 	}
-	return;
+	return calgary_found;
 
 cleanup:
 	for (--bus; bus >= 0; --bus) {
@@ -1473,6 +1474,7 @@ cleanup:
 		if (info->tce_space)
 			free_tce_table(info->tce_space);
 	}
+	return -ENOMEM;
 }
 
 static int __init calgary_parse_options(char *p)
@@ -1594,3 +1596,5 @@ static int __init calgary_fixup_tce_spaces(void)
  * and before device_initcall.
  */
 rootfs_initcall(calgary_fixup_tce_spaces);
+
+IOMMU_INIT_POST(detect_calgary);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 9f07cfcbd3a5..9ea999a4dcc1 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -11,9 +11,8 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/calgary.h>
-#include <asm/amd_iommu.h>
 #include <asm/x86_init.h>
-#include <asm/xen/swiotlb-xen.h>
+#include <asm/iommu_table.h>
 
 static int forbid_dac __read_mostly;
 
@@ -45,6 +44,8 @@ int iommu_detected __read_mostly = 0;
  */
 int iommu_pass_through __read_mostly;
 
+extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
+
 /* Dummy device used for NULL arguments (normally ISA). */
 struct device x86_dma_fallback_dev = {
 	.init_name = "fallback device",
@@ -130,26 +131,24 @@ static void __init dma32_free_bootmem(void)
 
 void __init pci_iommu_alloc(void)
 {
+	struct iommu_table_entry *p;
+
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
 
-	if (pci_xen_swiotlb_detect() || pci_swiotlb_detect())
-		goto out;
-
-	gart_iommu_hole_init();
-
-	detect_calgary();
-
-	detect_intel_iommu();
+	sort_iommu_table(__iommu_table, __iommu_table_end);
+	check_iommu_entries(__iommu_table, __iommu_table_end);
 
-	/* needs to be called after gart_iommu_hole_init */
-	amd_iommu_detect();
-out:
-	pci_xen_swiotlb_init();
-
-	pci_swiotlb_init();
+	for (p = __iommu_table; p < __iommu_table_end; p++) {
+		if (p && p->detect && p->detect() > 0) {
+			p->flags |= IOMMU_DETECTED;
+			if (p->early_init)
+				p->early_init();
+			if (p->flags & IOMMU_FINISH_IF_DETECTED)
+				break;
+		}
+	}
 }
-
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 				 dma_addr_t *dma_addr, gfp_t flag)
 {
@@ -292,6 +291,7 @@ EXPORT_SYMBOL(dma_supported);
 
 static int __init pci_iommu_init(void)
 {
+	struct iommu_table_entry *p;
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 
 #ifdef CONFIG_PCI
@@ -299,12 +299,10 @@ static int __init pci_iommu_init(void)
 #endif
 	x86_init.iommu.iommu_init();
 
-	if (swiotlb || xen_swiotlb) {
-		printk(KERN_INFO "PCI-DMA: "
-		       "Using software bounce buffering for IO (SWIOTLB)\n");
-		swiotlb_print_info();
-	} else
-		swiotlb_free();
+	for (p = __iommu_table; p < __iommu_table_end; p++) {
+		if (p && (p->flags & IOMMU_DETECTED) && p->late_init)
+			p->late_init();
+	}
 
 	return 0;
 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 0f7f130caa67..ba0f0ca9f280 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -39,8 +39,9 @@
 #include <asm/cacheflush.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/x86_init.h>
+#include <asm/iommu_table.h>
 
 static unsigned long iommu_bus_base;	/* GART remapping area (physical) */
 static unsigned long iommu_size;	/* size of remapping area bytes */
@@ -560,8 +561,11 @@ static void enable_gart_translations(void)
 {
 	int i;
 
-	for (i = 0; i < num_k8_northbridges; i++) {
-		struct pci_dev *dev = k8_northbridges[i];
+	if (!k8_northbridges.gart_supported)
+		return;
+
+	for (i = 0; i < k8_northbridges.num; i++) {
+		struct pci_dev *dev = k8_northbridges.nb_misc[i];
 
 		enable_gart_translation(dev, __pa(agp_gatt_table));
 	}
@@ -592,16 +596,19 @@ static void gart_fixup_northbridges(struct sys_device *dev)
 	if (!fix_up_north_bridges)
 		return;
 
+	if (!k8_northbridges.gart_supported)
+		return;
+
 	pr_info("PCI-DMA: Restoring GART aperture settings\n");
 
-	for (i = 0; i < num_k8_northbridges; i++) {
-		struct pci_dev *dev = k8_northbridges[i];
+	for (i = 0; i < k8_northbridges.num; i++) {
+		struct pci_dev *dev = k8_northbridges.nb_misc[i];
 
 		/*
 		 * Don't enable translations just yet.  That is the next
 		 * step.  Restore the pre-suspend aperture settings.
 		 */
-		pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, aperture_order << 1);
+		gart_set_size_and_enable(dev, aperture_order);
 		pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE, aperture_alloc >> 25);
 	}
 }
@@ -649,8 +656,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 	aper_size = aper_base = info->aper_size = 0;
 	dev = NULL;
-	for (i = 0; i < num_k8_northbridges; i++) {
-		dev = k8_northbridges[i];
+	for (i = 0; i < k8_northbridges.num; i++) {
+		dev = k8_northbridges.nb_misc[i];
 		new_aper_base = read_aperture(dev, &new_aper_size);
 		if (!new_aper_base)
 			goto nommu;
@@ -718,10 +725,13 @@ static void gart_iommu_shutdown(void)
 	if (!no_agp)
 		return;
 
-	for (i = 0; i < num_k8_northbridges; i++) {
+	if (!k8_northbridges.gart_supported)
+		return;
+
+	for (i = 0; i < k8_northbridges.num; i++) {
 		u32 ctl;
 
-		dev = k8_northbridges[i];
+		dev = k8_northbridges.nb_misc[i];
 		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
 
 		ctl &= ~GARTEN;
@@ -739,7 +749,7 @@ int __init gart_iommu_init(void)
 	unsigned long scratch;
 	long i;
 
-	if (num_k8_northbridges == 0)
+	if (!k8_northbridges.gart_supported)
 		return 0;
 
 #ifndef CONFIG_AGP_AMD64
@@ -896,3 +906,4 @@ void __init gart_parse_options(char *p)
 		}
 	}
 }
+IOMMU_INIT_POST(gart_iommu_hole_init);
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
new file mode 100644
index 000000000000..55d745ec1181
--- /dev/null
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -0,0 +1,89 @@
+#include <linux/dma-mapping.h>
+#include <asm/iommu_table.h>
+#include <linux/string.h>
+#include <linux/kallsyms.h>
+
+
+#define DEBUG 1
+
+static struct iommu_table_entry * __init
+find_dependents_of(struct iommu_table_entry *start,
+		   struct iommu_table_entry *finish,
+		   struct iommu_table_entry *q)
+{
+	struct iommu_table_entry *p;
+
+	if (!q)
+		return NULL;
+
+	for (p = start; p < finish; p++)
+		if (p->detect == q->depend)
+			return p;
+
+	return NULL;
+}
+
+
+void __init sort_iommu_table(struct iommu_table_entry *start,
+			     struct iommu_table_entry *finish) {
+
+	struct iommu_table_entry *p, *q, tmp;
+
+	for (p = start; p < finish; p++) {
+again:
+		q = find_dependents_of(start, finish, p);
+		/* We are bit sneaky here. We use the memory address to figure
+		 * out if the node we depend on is past our point, if so, swap.
+		 */
+		if (q > p) {
+			tmp = *p;
+			memmove(p, q, sizeof(*p));
+			*q = tmp;
+			goto again;
+		}
+	}
+
+}
+
+#ifdef DEBUG
+void __init check_iommu_entries(struct iommu_table_entry *start,
+				struct iommu_table_entry *finish)
+{
+	struct iommu_table_entry *p, *q, *x;
+	char sym_p[KSYM_SYMBOL_LEN];
+	char sym_q[KSYM_SYMBOL_LEN];
+
+	/* Simple cyclic dependency checker. */
+	for (p = start; p < finish; p++) {
+		q = find_dependents_of(start, finish, p);
+		x = find_dependents_of(start, finish, q);
+		if (p == x) {
+			sprint_symbol(sym_p, (unsigned long)p->detect);
+			sprint_symbol(sym_q, (unsigned long)q->detect);
+
+			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %s depends" \
+					" on %s and vice-versa. BREAKING IT.\n",
+					sym_p, sym_q);
+			/* Heavy handed way..*/
+			x->depend = 0;
+		}
+	}
+
+	for (p = start; p < finish; p++) {
+		q = find_dependents_of(p, finish, p);
+		if (q && q > p) {
+			sprint_symbol(sym_p, (unsigned long)p->detect);
+			sprint_symbol(sym_q, (unsigned long)q->detect);
+
+			printk(KERN_ERR "EXECUTION ORDER INVALID! %s "\
+					"should be called before %s!\n",
+					sym_p, sym_q);
+		}
+	}
+}
+#else
+inline void check_iommu_entries(struct iommu_table_entry *start,
+				       struct iommu_table_entry *finish)
+{
+}
+#endif
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index a5bc528d4328..8f972cbddef0 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -10,7 +10,8 @@
 #include <asm/iommu.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
-
+#include <asm/xen/swiotlb-xen.h>
+#include <asm/iommu_table.h>
 int swiotlb __read_mostly;
 
 static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
@@ -41,25 +42,42 @@ static struct dma_map_ops swiotlb_dma_ops = {
 };
 
 /*
- * pci_swiotlb_detect - set swiotlb to 1 if necessary
+ * pci_swiotlb_detect_override - set swiotlb to 1 if necessary
  *
  * This returns non-zero if we are forced to use swiotlb (by the boot
  * option).
  */
-int __init pci_swiotlb_detect(void)
+int __init pci_swiotlb_detect_override(void)
 {
 	int use_swiotlb = swiotlb | swiotlb_force;
 
+	if (swiotlb_force)
+		swiotlb = 1;
+
+	return use_swiotlb;
+}
+IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
+		  pci_xen_swiotlb_detect,
+		  pci_swiotlb_init,
+		  pci_swiotlb_late_init);
+
+/*
+ * if 4GB or more detected (and iommu=off not set) return 1
+ * and set swiotlb to 1.
+ */
+int __init pci_swiotlb_detect_4gb(void)
+{
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
 #ifdef CONFIG_X86_64
 	if (!no_iommu && max_pfn > MAX_DMA32_PFN)
 		swiotlb = 1;
 #endif
-	if (swiotlb_force)
-		swiotlb = 1;
-
-	return use_swiotlb;
+	return swiotlb;
 }
+IOMMU_INIT(pci_swiotlb_detect_4gb,
+	   pci_swiotlb_detect_override,
+	   pci_swiotlb_init,
+	   pci_swiotlb_late_init);
 
 void __init pci_swiotlb_init(void)
 {
@@ -68,3 +86,15 @@ void __init pci_swiotlb_init(void)
 		dma_ops = &swiotlb_dma_ops;
 	}
 }
+
+void __init pci_swiotlb_late_init(void)
+{
+	/* An IOMMU turned us off. */
+	if (!swiotlb)
+		swiotlb_free();
+	else {
+		printk(KERN_INFO "PCI-DMA: "
+		       "Using software bounce buffering for IO (SWIOTLB)\n");
+		swiotlb_print_info();
+	}
+}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 57d1868a86aa..e8a5ad12d42d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -44,7 +44,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	}
 	return 0;
 }
-
 void free_thread_xstate(struct task_struct *tsk)
 {
 	fpu_free(&tsk->thread.fpu);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3d9ea531ddd1..b3d7a3a04f38 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -424,7 +424,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	load_TLS(next, cpu);
 
 	/* Must be after DS reload */
-	unlazy_fpu(prev_p);
+	__unlazy_fpu(prev_p);
 
 	/* Make sure cpu is ready for new context */
 	if (preload_fpu)
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 939b9e98245f..8bbe8c56916d 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -344,6 +344,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235,
 			 vt8237_force_enable_hpet);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237,
 			 vt8237_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_CX700,
+			 vt8237_force_enable_hpet);
 
 static void ati_force_hpet_resume(void)
 {
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e3af342fe83a..7a4cf14223ba 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -84,7 +84,7 @@ static int __init reboot_setup(char *str)
 			}
 				/* we will leave sorting out the final value
 				   when we are ready to reboot, since we might not
-				   have set up boot_cpu_id or smp_num_cpu */
+				   have detected BSP APIC ID or smp_num_cpu */
 			break;
 #endif /* CONFIG_SMP */
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c3a4fbb2b996..468ccd29a59b 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -31,6 +31,7 @@
 #include <linux/apm_bios.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/seq_file.h>
 #include <linux/console.h>
 #include <linux/mca.h>
@@ -83,7 +84,6 @@
 #include <asm/dmi.h>
 #include <asm/io_apic.h>
 #include <asm/ist.h>
-#include <asm/vmi.h>
 #include <asm/setup_arch.h>
 #include <asm/bios_ebda.h>
 #include <asm/cacheflush.h>
@@ -107,11 +107,12 @@
 #include <asm/percpu.h>
 #include <asm/topology.h>
 #include <asm/apicdef.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #ifdef CONFIG_X86_64
 #include <asm/numa_64.h>
 #endif
 #include <asm/mce.h>
+#include <asm/alternative.h>
 
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -125,7 +126,6 @@ unsigned long max_pfn_mapped;
 RESERVE_BRK(dmi_alloc, 65536);
 #endif
 
-unsigned int boot_cpu_id __read_mostly;
 
 static __initdata unsigned long _brk_start = (unsigned long)__brk_base;
 unsigned long _brk_end = (unsigned long)__brk_base;
@@ -302,7 +302,7 @@ static inline void init_gbpages(void)
 static void __init reserve_brk(void)
 {
 	if (_brk_end > _brk_start)
-		reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK");
+		memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK");
 
 	/* Mark brk area as locked down and no longer taking any
 	   new allocations */
@@ -324,17 +324,16 @@ static void __init relocate_initrd(void)
 	char *p, *q;
 
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, area_size,
+	ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
-	if (ramdisk_here == -1ULL)
+	if (ramdisk_here == MEMBLOCK_ERROR)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
 			 ramdisk_size);
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + area_size,
-			 "NEW RAMDISK");
+	memblock_x86_reserve_range(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
@@ -390,7 +389,7 @@ static void __init reserve_initrd(void)
 	initrd_start = 0;
 
 	if (ramdisk_size >= (end_of_lowmem>>1)) {
-		free_early(ramdisk_image, ramdisk_end);
+		memblock_x86_free_range(ramdisk_image, ramdisk_end);
 		printk(KERN_ERR "initrd too large to handle, "
 		       "disabling initrd\n");
 		return;
@@ -413,7 +412,7 @@ static void __init reserve_initrd(void)
 
 	relocate_initrd();
 
-	free_early(ramdisk_image, ramdisk_end);
+	memblock_x86_free_range(ramdisk_image, ramdisk_end);
 }
 #else
 static void __init reserve_initrd(void)
@@ -469,7 +468,7 @@ static void __init e820_reserve_setup_data(void)
 	e820_print_map("reserve setup_data");
 }
 
-static void __init reserve_early_setup_data(void)
+static void __init memblock_x86_reserve_range_setup_data(void)
 {
 	struct setup_data *data;
 	u64 pa_data;
@@ -481,7 +480,7 @@ static void __init reserve_early_setup_data(void)
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
 		sprintf(buf, "setup data %x", data->type);
-		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+		memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf);
 		pa_data = data->next;
 		early_iounmap(data, sizeof(*data));
 	}
@@ -519,23 +518,23 @@ static void __init reserve_crashkernel(void)
 	if (crash_base <= 0) {
 		const unsigned long long alignment = 16<<20;	/* 16M */
 
-		crash_base = find_e820_area(alignment, ULONG_MAX, crash_size,
+		crash_base = memblock_find_in_range(alignment, ULONG_MAX, crash_size,
 				 alignment);
-		if (crash_base == -1ULL) {
+		if (crash_base == MEMBLOCK_ERROR) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
 	} else {
 		unsigned long long start;
 
-		start = find_e820_area(crash_base, ULONG_MAX, crash_size,
+		start = memblock_find_in_range(crash_base, ULONG_MAX, crash_size,
 				 1<<20);
 		if (start != crash_base) {
 			pr_info("crashkernel reservation failed - memory is in use.\n");
 			return;
 		}
 	}
-	reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL");
+	memblock_x86_reserve_range(crash_base, crash_base + crash_size, "CRASH KERNEL");
 
 	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
 			"for crashkernel (System RAM: %ldMB)\n",
@@ -615,82 +614,10 @@ static __init void reserve_ibft_region(void)
 	addr = find_ibft_region(&size);
 
 	if (size)
-		reserve_early_overlap_ok(addr, addr + size, "ibft");
+		memblock_x86_reserve_range(addr, addr + size, "* ibft");
 }
 
-#ifdef CONFIG_X86_RESERVE_LOW_64K
-static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
-{
-	printk(KERN_NOTICE
-		"%s detected: BIOS may corrupt low RAM, working around it.\n",
-		d->ident);
-
-	e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED);
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
-
-	return 0;
-}
-#endif
-
-/* List of systems that have known low memory corruption BIOS problems */
-static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
-#ifdef CONFIG_X86_RESERVE_LOW_64K
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "AMI BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
-		},
-	},
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "Phoenix BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"),
-		},
-	},
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "Phoenix/MSC BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"),
-		},
-	},
-	/*
-	 * AMI BIOS with low memory corruption was found on Intel DG45ID and
-	 * DG45FC boards.
-	 * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
-	 * match only DMI_BOARD_NAME and see if there is more bad products
-	 * with this vendor.
-	 */
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "AMI BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "DG45ID"),
-		},
-	},
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "AMI BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "DG45FC"),
-		},
-	},
-	/*
-	 * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so
-	 * match on the product name.
-	 */
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "Phoenix BIOS",
-		.matches = {
-			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"),
-		},
-	},
-#endif
-	{}
-};
+static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
 
 static void __init trim_bios_range(void)
 {
@@ -698,8 +625,14 @@ static void __init trim_bios_range(void)
 	 * A special case is the first 4Kb of memory;
 	 * This is a BIOS owned area, not kernel ram, but generally
 	 * not listed as such in the E820 table.
+	 *
+	 * This typically reserves additional memory (64KiB by default)
+	 * since some BIOSes are known to corrupt low memory.  See the
+	 * Kconfig help text for X86_RESERVE_LOW.
 	 */
-	e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+	e820_update_range(0, ALIGN(reserve_low, PAGE_SIZE),
+			  E820_RAM, E820_RESERVED);
+
 	/*
 	 * special case: Some BIOSen report the PC BIOS
 	 * area (640->1Mb) as ram even though it is not.
@@ -709,6 +642,37 @@ static void __init trim_bios_range(void)
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
+static u64 __init get_max_mapped(void)
+{
+	u64 end = max_pfn_mapped;
+
+	end <<= PAGE_SHIFT;
+
+	return end;
+}
+
+static int __init parse_reservelow(char *p)
+{
+	unsigned long long size;
+
+	if (!p)
+		return -EINVAL;
+
+	size = memparse(p, &p);
+
+	if (size < 4096)
+		size = 4096;
+
+	if (size > 640*1024)
+		size = 640*1024;
+
+	reserve_low = size;
+
+	return 0;
+}
+
+early_param("reservelow", parse_reservelow);
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -726,6 +690,7 @@ void __init setup_arch(char **cmdline_p)
 {
 	int acpi = 0;
 	int k8 = 0;
+	unsigned long flags;
 
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
@@ -734,10 +699,10 @@ void __init setup_arch(char **cmdline_p)
 	printk(KERN_INFO "Command line: %s\n", boot_command_line);
 #endif
 
-	/* VMI may relocate the fixmap; do this before touching ioremap area */
-	vmi_init();
-
-	/* OFW also may relocate the fixmap */
+	/*
+	 * If we have OLPC OFW, we might end up relocating the fixmap due to
+	 * reserve_top(), so do this before touching the ioremap area.
+	 */
 	olpc_ofw_detect();
 
 	early_trap_init();
@@ -782,7 +747,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	 4)) {
 		efi_enabled = 1;
-		efi_reserve_early();
+		efi_memblock_x86_reserve_range();
 	}
 #endif
 
@@ -838,11 +803,8 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_report_nx();
 
-	/* Must be before kernel pagetables are setup */
-	vmi_activate();
-
 	/* after early param, so could get panic from serial */
-	reserve_early_setup_data();
+	memblock_x86_reserve_range_setup_data();
 
 	if (acpi_mps_check()) {
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -863,8 +825,6 @@ void __init setup_arch(char **cmdline_p)
 
 	dmi_scan_machine();
 
-	dmi_check_system(bad_bios_dmi_table);
-
 	/*
 	 * VMware detection requires dmi to be available, so this
 	 * needs to be done after dmi_scan_machine, for the BP.
@@ -897,8 +857,6 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	max_pfn = e820_end_of_ram_pfn();
 
-	/* preallocate 4k for mptable mpc */
-	early_reserve_e820_mpc_new();
 	/* update e820 for memory not covered by WB MTRRs */
 	mtrr_bp_init();
 	if (mtrr_trim_uncached_memory(max_pfn))
@@ -923,15 +881,6 @@ void __init setup_arch(char **cmdline_p)
 	max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
 #endif
 
-#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
-	setup_bios_corruption_check();
-#endif
-
-	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
-			max_pfn_mapped<<PAGE_SHIFT);
-
-	reserve_brk();
-
 	/*
 	 * Find and reserve possible boot-time SMP configuration:
 	 */
@@ -939,6 +888,26 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_ibft_region();
 
+	/*
+	 * Need to conclude brk, before memblock_x86_fill()
+	 *  it could use memblock_find_in_range, could overlap with
+	 *  brk area.
+	 */
+	reserve_brk();
+
+	memblock.current_limit = get_max_mapped();
+	memblock_x86_fill();
+
+	/* preallocate 4k for mptable mpc */
+	early_reserve_e820_mpc_new();
+
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+	setup_bios_corruption_check();
+#endif
+
+	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
+			max_pfn_mapped<<PAGE_SHIFT);
+
 	reserve_trampoline_memory();
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -962,6 +931,7 @@ void __init setup_arch(char **cmdline_p)
 		max_low_pfn = max_pfn;
 	}
 #endif
+	memblock.current_limit = get_max_mapped();
 
 	/*
 	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
@@ -1000,10 +970,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	initmem_init(0, max_pfn, acpi, k8);
-#ifndef CONFIG_NO_BOOTMEM
-	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
-#endif
-
+	memblock_find_dma_reserve();
 	dma32_reserve_bootmem();
 
 #ifdef CONFIG_KVM_CLOCK
@@ -1071,6 +1038,10 @@ void __init setup_arch(char **cmdline_p)
 	x86_init.oem.banner();
 
 	mcheck_init();
+
+	local_irq_save(flags);
+	arch_init_ideal_nop5();
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index a60df9ae6454..002b79685f73 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -131,13 +131,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	u64 start = __pa(ptr);
-	u64 end = start + size;
-	free_early_partial(start, end);
-#else
 	free_bootmem(__pa(ptr), size);
-#endif
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
@@ -253,7 +247,7 @@ void __init setup_per_cpu_areas(void)
 		 * Up to this point, the boot CPU has been using .init.data
 		 * area.  Reload any changed state for the boot CPU.
 		 */
-		if (cpu == boot_cpu_id)
+		if (!cpu)
 			switch_to_new_gdt(cpu);
 	}
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8b3bfc4dd708..2ced73ba048c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -62,7 +62,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mtrr.h>
-#include <asm/vmi.h>
+#include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
@@ -311,7 +311,6 @@ notrace static void __cpuinit start_secondary(void *unused)
 	__flush_tlb_all();
 #endif
 
-	vmi_bringup();
 	cpu_init();
 	preempt_disable();
 	smp_callin();
@@ -397,6 +396,19 @@ void __cpuinit smp_store_cpu_info(int id)
 		identify_secondary_cpu(c);
 }
 
+static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
+{
+	struct cpuinfo_x86 *c1 = &cpu_data(cpu1);
+	struct cpuinfo_x86 *c2 = &cpu_data(cpu2);
+
+	cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
+	cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
+	cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
+	cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
+	cpumask_set_cpu(cpu1, c2->llc_shared_map);
+	cpumask_set_cpu(cpu2, c1->llc_shared_map);
+}
+
 
 void __cpuinit set_cpu_sibling_map(int cpu)
 {
@@ -409,14 +421,13 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		for_each_cpu(i, cpu_sibling_setup_mask) {
 			struct cpuinfo_x86 *o = &cpu_data(i);
 
-			if (c->phys_proc_id == o->phys_proc_id &&
-			    c->cpu_core_id == o->cpu_core_id) {
-				cpumask_set_cpu(i, cpu_sibling_mask(cpu));
-				cpumask_set_cpu(cpu, cpu_sibling_mask(i));
-				cpumask_set_cpu(i, cpu_core_mask(cpu));
-				cpumask_set_cpu(cpu, cpu_core_mask(i));
-				cpumask_set_cpu(i, c->llc_shared_map);
-				cpumask_set_cpu(cpu, o->llc_shared_map);
+			if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+				if (c->phys_proc_id == o->phys_proc_id &&
+				    c->compute_unit_id == o->compute_unit_id)
+					link_thread_siblings(cpu, i);
+			} else if (c->phys_proc_id == o->phys_proc_id &&
+				   c->cpu_core_id == o->cpu_core_id) {
+				link_thread_siblings(cpu, i);
 			}
 		}
 	} else {
@@ -1109,8 +1120,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	}
 	set_cpu_sibling_map(0);
 
-	enable_IR_x2apic();
-	default_setup_apic_routing();
 
 	if (smp_sanity_check(max_cpus) < 0) {
 		printk(KERN_INFO "SMP disabled\n");
@@ -1118,6 +1127,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		goto out;
 	}
 
+	default_setup_apic_routing();
+
 	preempt_disable();
 	if (read_apic_id() != boot_cpu_physical_apicid) {
 		panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
@@ -1383,11 +1394,88 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
+static inline void mwait_play_dead(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int highest_cstate = 0;
+	unsigned int highest_subcstate = 0;
+	int i;
+	void *mwait_ptr;
+
+	if (!cpu_has(&current_cpu_data, X86_FEATURE_MWAIT))
+		return;
+	if (!cpu_has(&current_cpu_data, X86_FEATURE_CLFLSH))
+		return;
+	if (current_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+		return;
+
+	eax = CPUID_MWAIT_LEAF;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	/*
+	 * eax will be 0 if EDX enumeration is not valid.
+	 * Initialized below to cstate, sub_cstate value when EDX is valid.
+	 */
+	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
+		eax = 0;
+	} else {
+		edx >>= MWAIT_SUBSTATE_SIZE;
+		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
+			if (edx & MWAIT_SUBSTATE_MASK) {
+				highest_cstate = i;
+				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
+			}
+		}
+		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
+			(highest_subcstate - 1);
+	}
+
+	/*
+	 * This should be a memory location in a cache line which is
+	 * unlikely to be touched by other processors.  The actual
+	 * content is immaterial as it is not actually modified in any way.
+	 */
+	mwait_ptr = &current_thread_info()->flags;
+
+	wbinvd();
+
+	while (1) {
+		/*
+		 * The CLFLUSH is a workaround for erratum AAI65 for
+		 * the Xeon 7400 series.  It's not clear it is actually
+		 * needed, but it should be harmless in either case.
+		 * The WBINVD is insufficient due to the spurious-wakeup
+		 * case where we return around the loop.
+		 */
+		clflush(mwait_ptr);
+		__monitor(mwait_ptr, 0, 0);
+		mb();
+		__mwait(eax, 0);
+	}
+}
+
+static inline void hlt_play_dead(void)
+{
+	if (current_cpu_data.x86 >= 4)
+		wbinvd();
+
+	while (1) {
+		native_halt();
+	}
+}
+
 void native_play_dead(void)
 {
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
-	wbinvd_halt();
+
+	mwait_play_dead();	/* Only returns on failure */
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c
index d5e06624e34a..0b0cb5fede19 100644
--- a/arch/x86/kernel/sys_i386_32.c
+++ b/arch/x86/kernel/sys_i386_32.c
@@ -33,8 +33,8 @@ int kernel_execve(const char *filename,
 		  const char *const envp[])
 {
 	long __res;
-	asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx"
+	asm volatile ("int $0x80"
 	: "=a" (__res)
-	: "0" (__NR_execve), "ri" (filename), "c" (argv), "d" (envp) : "memory");
+	: "0" (__NR_execve), "b" (filename), "c" (argv), "d" (envp) : "memory");
 	return __res;
 }
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 312ef0292815..33e77e4f7c86 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -1001,10 +1001,10 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
 static ssize_t tunables_read(struct file *file, char __user *userbuf,
 						size_t count, loff_t *ppos)
 {
-	char buf[300];
+	char *buf;
 	int ret;
 
-	ret = snprintf(buf, 300, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n",
+	buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n",
 		"max_bau_concurrent plugged_delay plugsb4reset",
 		"timeoutsb4reset ipi_reset_limit complete_threshold",
 		"congested_response_us congested_reps congested_period",
@@ -1012,7 +1012,12 @@ static ssize_t tunables_read(struct file *file, char __user *userbuf,
 		timeoutsb4reset, ipi_reset_limit, complete_threshold,
 		congested_response_us, congested_reps, congested_period);
 
-	return simple_read_from_buffer(userbuf, count, ppos, buf, ret);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = simple_read_from_buffer(userbuf, count, ppos, buf, strlen(buf));
+	kfree(buf);
+	return ret;
 }
 
 /*
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index e2a595257390..4c3da5674e67 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -1,8 +1,8 @@
 #include <linux/io.h>
+#include <linux/memblock.h>
 
 #include <asm/trampoline.h>
 #include <asm/pgtable.h>
-#include <asm/e820.h>
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
 #define __trampinit
@@ -17,15 +17,15 @@ unsigned char *__trampinitdata trampoline_base;
 
 void __init reserve_trampoline_memory(void)
 {
-	unsigned long mem;
+	phys_addr_t mem;
 
 	/* Has to be in very low memory so we can execute real-mode AP code. */
-	mem = find_e820_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
-	if (mem == -1L)
+	mem = memblock_find_in_range(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
+	if (mem == MEMBLOCK_ERROR)
 		panic("Cannot allocate trampoline\n");
 
 	trampoline_base = __va(mem);
-	reserve_early(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
+	memblock_x86_reserve_range(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
 }
 
 /*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 60788dee0f8a..cb838ca42c96 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -575,6 +575,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	if (regs->flags & X86_VM_MASK) {
 		handle_vm86_trap((struct kernel_vm86_regs *) regs,
 				error_code, 1);
+		preempt_conditional_cli(regs);
 		return;
 	}
 
@@ -776,21 +777,10 @@ asmlinkage void math_state_restore(void)
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 
-#ifndef CONFIG_MATH_EMULATION
-void math_emulate(struct math_emu_info *info)
-{
-	printk(KERN_EMERG
-		"math-emulation not enabled and no coprocessor found.\n");
-	printk(KERN_EMERG "killing %s.\n", current->comm);
-	force_sig(SIGFPE, current);
-	schedule();
-}
-#endif /* CONFIG_MATH_EMULATION */
-
 dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_MATH_EMULATION
 	if (read_cr0() & X86_CR0_EM) {
 		struct math_emu_info info = { };
 
@@ -798,12 +788,12 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 
 		info.regs = regs;
 		math_emulate(&info);
-	} else {
-		math_state_restore(); /* interrupts still off */
-		conditional_sti(regs);
+		return;
 	}
-#else
-	math_state_restore();
+#endif
+	math_state_restore(); /* interrupts still off */
+#ifdef CONFIG_X86_32
+	conditional_sti(regs);
 #endif
 }
 
@@ -881,18 +871,6 @@ void __init trap_init(void)
 #endif
 
 #ifdef CONFIG_X86_32
-	if (cpu_has_fxsr) {
-		printk(KERN_INFO "Enabling fast FPU save and restore... ");
-		set_in_cr4(X86_CR4_OSFXSR);
-		printk("done.\n");
-	}
-	if (cpu_has_xmm) {
-		printk(KERN_INFO
-			"Enabling unmasked SIMD FPU exception support... ");
-		set_in_cr4(X86_CR4_OSXMMEXCPT);
-		printk("done.\n");
-	}
-
 	set_system_trap_gate(SYSCALL_VECTOR, &system_call);
 	set_bit(SYSCALL_VECTOR, used_vectors);
 #endif
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 26a863a9c2a8..4496315eb224 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -892,60 +892,6 @@ static void __init init_tsc_clocksource(void)
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
-#ifdef CONFIG_X86_64
-/*
- * calibrate_cpu is used on systems with fixed rate TSCs to determine
- * processor frequency
- */
-#define TICK_COUNT 100000000
-static unsigned long __init calibrate_cpu(void)
-{
-	int tsc_start, tsc_now;
-	int i, no_ctr_free;
-	unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
-	unsigned long flags;
-
-	for (i = 0; i < 4; i++)
-		if (avail_to_resrv_perfctr_nmi_bit(i))
-			break;
-	no_ctr_free = (i == 4);
-	if (no_ctr_free) {
-		WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
-		     "cpu_khz value may be incorrect.\n");
-		i = 3;
-		rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
-		wrmsrl(MSR_K7_EVNTSEL3, 0);
-		rdmsrl(MSR_K7_PERFCTR3, pmc3);
-	} else {
-		reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-		reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-	}
-	local_irq_save(flags);
-	/* start measuring cycles, incrementing from 0 */
-	wrmsrl(MSR_K7_PERFCTR0 + i, 0);
-	wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
-	rdtscl(tsc_start);
-	do {
-		rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
-		tsc_now = get_cycles();
-	} while ((tsc_now - tsc_start) < TICK_COUNT);
-
-	local_irq_restore(flags);
-	if (no_ctr_free) {
-		wrmsrl(MSR_K7_EVNTSEL3, 0);
-		wrmsrl(MSR_K7_PERFCTR3, pmc3);
-		wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
-	} else {
-		release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-		release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-	}
-
-	return pmc_now * tsc_khz / (tsc_now - tsc_start);
-}
-#else
-static inline unsigned long calibrate_cpu(void) { return cpu_khz; }
-#endif
-
 void __init tsc_init(void)
 {
 	u64 lpj;
@@ -964,10 +910,6 @@ void __init tsc_init(void)
 		return;
 	}
 
-	if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
-			(boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
-		cpu_khz = calibrate_cpu();
-
 	printk("Detected %lu.%03lu MHz processor.\n",
 			(unsigned long)cpu_khz / 1000,
 			(unsigned long)cpu_khz % 1000);
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 5ffb5622f793..61fb98519622 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -551,8 +551,14 @@ cannot_handle:
 int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno)
 {
 	if (VMPI.is_vm86pus) {
-		if ((trapno == 3) || (trapno == 1))
-			return_to_32bit(regs, VM86_TRAP + (trapno << 8));
+		if ((trapno == 3) || (trapno == 1)) {
+			KVM86->regs32->ax = VM86_TRAP + (trapno << 8);
+			/* setting this flag forces the code in entry_32.S to
+			   call save_v86_state() and change the stack pointer
+			   to KVM86->regs32 */
+			set_thread_flag(TIF_IRET);
+			return 0;
+		}
 		do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs));
 		return 0;
 	}
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
deleted file mode 100644
index ce9fbacb7526..000000000000
--- a/arch/x86/kernel/vmi_32.c
+++ /dev/null
@@ -1,893 +0,0 @@
-/*
- * VMI specific paravirt-ops implementation
- *
- * Copyright (C) 2005, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to zach@vmware.com
- *
- */
-
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/sched.h>
-#include <linux/gfp.h>
-#include <asm/vmi.h>
-#include <asm/io.h>
-#include <asm/fixmap.h>
-#include <asm/apicdef.h>
-#include <asm/apic.h>
-#include <asm/pgalloc.h>
-#include <asm/processor.h>
-#include <asm/timer.h>
-#include <asm/vmi_time.h>
-#include <asm/kmap_types.h>
-#include <asm/setup.h>
-
-/* Convenient for calling VMI functions indirectly in the ROM */
-typedef u32 __attribute__((regparm(1))) (VROMFUNC)(void);
-typedef u64 __attribute__((regparm(2))) (VROMLONGFUNC)(int);
-
-#define call_vrom_func(rom,func) \
-   (((VROMFUNC *)(rom->func))())
-
-#define call_vrom_long_func(rom,func,arg) \
-   (((VROMLONGFUNC *)(rom->func)) (arg))
-
-static struct vrom_header *vmi_rom;
-static int disable_pge;
-static int disable_pse;
-static int disable_sep;
-static int disable_tsc;
-static int disable_mtrr;
-static int disable_noidle;
-static int disable_vmi_timer;
-
-/* Cached VMI operations */
-static struct {
-	void (*cpuid)(void /* non-c */);
-	void (*_set_ldt)(u32 selector);
-	void (*set_tr)(u32 selector);
-	void (*write_idt_entry)(struct desc_struct *, int, u32, u32);
-	void (*write_gdt_entry)(struct desc_struct *, int, u32, u32);
-	void (*write_ldt_entry)(struct desc_struct *, int, u32, u32);
-	void (*set_kernel_stack)(u32 selector, u32 sp0);
-	void (*allocate_page)(u32, u32, u32, u32, u32);
-	void (*release_page)(u32, u32);
-	void (*set_pte)(pte_t, pte_t *, unsigned);
-	void (*update_pte)(pte_t *, unsigned);
-	void (*set_linear_mapping)(int, void *, u32, u32);
-	void (*_flush_tlb)(int);
-	void (*set_initial_ap_state)(int, int);
-	void (*halt)(void);
-  	void (*set_lazy_mode)(int mode);
-} vmi_ops;
-
-/* Cached VMI operations */
-struct vmi_timer_ops vmi_timer_ops;
-
-/*
- * VMI patching routines.
- */
-#define MNEM_CALL 0xe8
-#define MNEM_JMP  0xe9
-#define MNEM_RET  0xc3
-
-#define IRQ_PATCH_INT_MASK 0
-#define IRQ_PATCH_DISABLE  5
-
-static inline void patch_offset(void *insnbuf,
-				unsigned long ip, unsigned long dest)
-{
-        *(unsigned long *)(insnbuf+1) = dest-ip-5;
-}
-
-static unsigned patch_internal(int call, unsigned len, void *insnbuf,
-			       unsigned long ip)
-{
-	u64 reloc;
-	struct vmi_relocation_info *const rel = (struct vmi_relocation_info *)&reloc;
-	reloc = call_vrom_long_func(vmi_rom, get_reloc,	call);
-	switch(rel->type) {
-		case VMI_RELOCATION_CALL_REL:
-			BUG_ON(len < 5);
-			*(char *)insnbuf = MNEM_CALL;
-			patch_offset(insnbuf, ip, (unsigned long)rel->eip);
-			return 5;
-
-		case VMI_RELOCATION_JUMP_REL:
-			BUG_ON(len < 5);
-			*(char *)insnbuf = MNEM_JMP;
-			patch_offset(insnbuf, ip, (unsigned long)rel->eip);
-			return 5;
-
-		case VMI_RELOCATION_NOP:
-			/* obliterate the whole thing */
-			return 0;
-
-		case VMI_RELOCATION_NONE:
-			/* leave native code in place */
-			break;
-
-		default:
-			BUG();
-	}
-	return len;
-}
-
-/*
- * Apply patch if appropriate, return length of new instruction
- * sequence.  The callee does nop padding for us.
- */
-static unsigned vmi_patch(u8 type, u16 clobbers, void *insns,
-			  unsigned long ip, unsigned len)
-{
-	switch (type) {
-		case PARAVIRT_PATCH(pv_irq_ops.irq_disable):
-			return patch_internal(VMI_CALL_DisableInterrupts, len,
-					      insns, ip);
-		case PARAVIRT_PATCH(pv_irq_ops.irq_enable):
-			return patch_internal(VMI_CALL_EnableInterrupts, len,
-					      insns, ip);
-		case PARAVIRT_PATCH(pv_irq_ops.restore_fl):
-			return patch_internal(VMI_CALL_SetInterruptMask, len,
-					      insns, ip);
-		case PARAVIRT_PATCH(pv_irq_ops.save_fl):
-			return patch_internal(VMI_CALL_GetInterruptMask, len,
-					      insns, ip);
-		case PARAVIRT_PATCH(pv_cpu_ops.iret):
-			return patch_internal(VMI_CALL_IRET, len, insns, ip);
-		case PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit):
-			return patch_internal(VMI_CALL_SYSEXIT, len, insns, ip);
-		default:
-			break;
-	}
-	return len;
-}
-
-/* CPUID has non-C semantics, and paravirt-ops API doesn't match hardware ISA */
-static void vmi_cpuid(unsigned int *ax, unsigned int *bx,
-                               unsigned int *cx, unsigned int *dx)
-{
-	int override = 0;
-	if (*ax == 1)
-		override = 1;
-        asm volatile ("call *%6"
-                      : "=a" (*ax),
-                        "=b" (*bx),
-                        "=c" (*cx),
-                        "=d" (*dx)
-                      : "0" (*ax), "2" (*cx), "r" (vmi_ops.cpuid));
-	if (override) {
-		if (disable_pse)
-			*dx &= ~X86_FEATURE_PSE;
-		if (disable_pge)
-			*dx &= ~X86_FEATURE_PGE;
-		if (disable_sep)
-			*dx &= ~X86_FEATURE_SEP;
-		if (disable_tsc)
-			*dx &= ~X86_FEATURE_TSC;
-		if (disable_mtrr)
-			*dx &= ~X86_FEATURE_MTRR;
-	}
-}
-
-static inline void vmi_maybe_load_tls(struct desc_struct *gdt, int nr, struct desc_struct *new)
-{
-	if (gdt[nr].a != new->a || gdt[nr].b != new->b)
-		write_gdt_entry(gdt, nr, new, 0);
-}
-
-static void vmi_load_tls(struct thread_struct *t, unsigned int cpu)
-{
-	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
-	vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 0, &t->tls_array[0]);
-	vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 1, &t->tls_array[1]);
-	vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 2, &t->tls_array[2]);
-}
-
-static void vmi_set_ldt(const void *addr, unsigned entries)
-{
-	unsigned cpu = smp_processor_id();
-	struct desc_struct desc;
-
-	pack_descriptor(&desc, (unsigned long)addr,
-			entries * sizeof(struct desc_struct) - 1,
-			DESC_LDT, 0);
-	write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT, &desc, DESC_LDT);
-	vmi_ops._set_ldt(entries ? GDT_ENTRY_LDT*sizeof(struct desc_struct) : 0);
-}
-
-static void vmi_set_tr(void)
-{
-	vmi_ops.set_tr(GDT_ENTRY_TSS*sizeof(struct desc_struct));
-}
-
-static void vmi_write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
-{
-	u32 *idt_entry = (u32 *)g;
-	vmi_ops.write_idt_entry(dt, entry, idt_entry[0], idt_entry[1]);
-}
-
-static void vmi_write_gdt_entry(struct desc_struct *dt, int entry,
-				const void *desc, int type)
-{
-	u32 *gdt_entry = (u32 *)desc;
-	vmi_ops.write_gdt_entry(dt, entry, gdt_entry[0], gdt_entry[1]);
-}
-
-static void vmi_write_ldt_entry(struct desc_struct *dt, int entry,
-				const void *desc)
-{
-	u32 *ldt_entry = (u32 *)desc;
-	vmi_ops.write_ldt_entry(dt, entry, ldt_entry[0], ldt_entry[1]);
-}
-
-static void vmi_load_sp0(struct tss_struct *tss,
-				   struct thread_struct *thread)
-{
-	tss->x86_tss.sp0 = thread->sp0;
-
-	/* This can only happen when SEP is enabled, no need to test "SEP"arately */
-	if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
-		tss->x86_tss.ss1 = thread->sysenter_cs;
-		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
-	}
-	vmi_ops.set_kernel_stack(__KERNEL_DS, tss->x86_tss.sp0);
-}
-
-static void vmi_flush_tlb_user(void)
-{
-	vmi_ops._flush_tlb(VMI_FLUSH_TLB);
-}
-
-static void vmi_flush_tlb_kernel(void)
-{
-	vmi_ops._flush_tlb(VMI_FLUSH_TLB | VMI_FLUSH_GLOBAL);
-}
-
-/* Stub to do nothing at all; used for delays and unimplemented calls */
-static void vmi_nop(void)
-{
-}
-
-static void vmi_allocate_pte(struct mm_struct *mm, unsigned long pfn)
-{
-	vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
-}
-
-static void vmi_allocate_pmd(struct mm_struct *mm, unsigned long pfn)
-{
- 	/*
-	 * This call comes in very early, before mem_map is setup.
-	 * It is called only for swapper_pg_dir, which already has
-	 * data on it.
-	 */
-	vmi_ops.allocate_page(pfn, VMI_PAGE_L2, 0, 0, 0);
-}
-
-static void vmi_allocate_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count)
-{
-	vmi_ops.allocate_page(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE, clonepfn, start, count);
-}
-
-static void vmi_release_pte(unsigned long pfn)
-{
-	vmi_ops.release_page(pfn, VMI_PAGE_L1);
-}
-
-static void vmi_release_pmd(unsigned long pfn)
-{
-	vmi_ops.release_page(pfn, VMI_PAGE_L2);
-}
-
-/*
- * We use the pgd_free hook for releasing the pgd page:
- */
-static void vmi_pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	unsigned long pfn = __pa(pgd) >> PAGE_SHIFT;
-
-	vmi_ops.release_page(pfn, VMI_PAGE_L2);
-}
-
-/*
- * Helper macros for MMU update flags.  We can defer updates until a flush
- * or page invalidation only if the update is to the current address space
- * (otherwise, there is no flush).  We must check against init_mm, since
- * this could be a kernel update, which usually passes init_mm, although
- * sometimes this check can be skipped if we know the particular function
- * is only called on user mode PTEs.  We could change the kernel to pass
- * current->active_mm here, but in particular, I was unsure if changing
- * mm/highmem.c to do this would still be correct on other architectures.
- */
-#define is_current_as(mm, mustbeuser) ((mm) == current->active_mm ||    \
-                                       (!mustbeuser && (mm) == &init_mm))
-#define vmi_flags_addr(mm, addr, level, user)                           \
-        ((level) | (is_current_as(mm, user) ?                           \
-                (VMI_PAGE_CURRENT_AS | ((addr) & VMI_PAGE_VA_MASK)) : 0))
-#define vmi_flags_addr_defer(mm, addr, level, user)                     \
-        ((level) | (is_current_as(mm, user) ?                           \
-                (VMI_PAGE_DEFER | VMI_PAGE_CURRENT_AS | ((addr) & VMI_PAGE_VA_MASK)) : 0))
-
-static void vmi_update_pte(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	vmi_ops.update_pte(ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_update_pte_defer(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	vmi_ops.update_pte(ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_set_pte(pte_t *ptep, pte_t pte)
-{
-	/* XXX because of set_pmd_pte, this can be called on PT or PD layers */
-	vmi_ops.set_pte(pte, ptep, VMI_PAGE_PT);
-}
-
-static void vmi_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
-{
-	vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_set_pmd(pmd_t *pmdp, pmd_t pmdval)
-{
-#ifdef CONFIG_X86_PAE
-	const pte_t pte = { .pte = pmdval.pmd };
-#else
-	const pte_t pte = { pmdval.pud.pgd.pgd };
-#endif
-	vmi_ops.set_pte(pte, (pte_t *)pmdp, VMI_PAGE_PD);
-}
-
-#ifdef CONFIG_X86_PAE
-
-static void vmi_set_pte_atomic(pte_t *ptep, pte_t pteval)
-{
-	/*
-	 * XXX This is called from set_pmd_pte, but at both PT
-	 * and PD layers so the VMI_PAGE_PT flag is wrong.  But
-	 * it is only called for large page mapping changes,
-	 * the Xen backend, doesn't support large pages, and the
-	 * ESX backend doesn't depend on the flag.
-	 */
-	set_64bit((unsigned long long *)ptep,pte_val(pteval));
-	vmi_ops.update_pte(ptep, VMI_PAGE_PT);
-}
-
-static void vmi_set_pud(pud_t *pudp, pud_t pudval)
-{
-	/* Um, eww */
-	const pte_t pte = { .pte = pudval.pgd.pgd };
-	vmi_ops.set_pte(pte, (pte_t *)pudp, VMI_PAGE_PDP);
-}
-
-static void vmi_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	const pte_t pte = { .pte = 0 };
-	vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_pmd_clear(pmd_t *pmd)
-{
-	const pte_t pte = { .pte = 0 };
-	vmi_ops.set_pte(pte, (pte_t *)pmd, VMI_PAGE_PD);
-}
-#endif
-
-#ifdef CONFIG_SMP
-static void __devinit
-vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
-		     unsigned long start_esp)
-{
-	struct vmi_ap_state ap;
-
-	/* Default everything to zero.  This is fine for most GPRs. */
-	memset(&ap, 0, sizeof(struct vmi_ap_state));
-
-	ap.gdtr_limit = GDT_SIZE - 1;
-	ap.gdtr_base = (unsigned long) get_cpu_gdt_table(phys_apicid);
-
-	ap.idtr_limit = IDT_ENTRIES * 8 - 1;
-	ap.idtr_base = (unsigned long) idt_table;
-
-	ap.ldtr = 0;
-
-	ap.cs = __KERNEL_CS;
-	ap.eip = (unsigned long) start_eip;
-	ap.ss = __KERNEL_DS;
-	ap.esp = (unsigned long) start_esp;
-
-	ap.ds = __USER_DS;
-	ap.es = __USER_DS;
-	ap.fs = __KERNEL_PERCPU;
-	ap.gs = __KERNEL_STACK_CANARY;
-
-	ap.eflags = 0;
-
-#ifdef CONFIG_X86_PAE
-	/* efer should match BSP efer. */
-	if (cpu_has_nx) {
-		unsigned l, h;
-		rdmsr(MSR_EFER, l, h);
-		ap.efer = (unsigned long long) h << 32 | l;
-	}
-#endif
-
-	ap.cr3 = __pa(swapper_pg_dir);
-	/* Protected mode, paging, AM, WP, NE, MP. */
-	ap.cr0 = 0x80050023;
-	ap.cr4 = mmu_cr4_features;
-	vmi_ops.set_initial_ap_state((u32)&ap, phys_apicid);
-}
-#endif
-
-static void vmi_start_context_switch(struct task_struct *prev)
-{
-	paravirt_start_context_switch(prev);
-	vmi_ops.set_lazy_mode(2);
-}
-
-static void vmi_end_context_switch(struct task_struct *next)
-{
-	vmi_ops.set_lazy_mode(0);
-	paravirt_end_context_switch(next);
-}
-
-static void vmi_enter_lazy_mmu(void)
-{
-	paravirt_enter_lazy_mmu();
-	vmi_ops.set_lazy_mode(1);
-}
-
-static void vmi_leave_lazy_mmu(void)
-{
-	vmi_ops.set_lazy_mode(0);
-	paravirt_leave_lazy_mmu();
-}
-
-static inline int __init check_vmi_rom(struct vrom_header *rom)
-{
-	struct pci_header *pci;
-	struct pnp_header *pnp;
-	const char *manufacturer = "UNKNOWN";
-	const char *product = "UNKNOWN";
-	const char *license = "unspecified";
-
-	if (rom->rom_signature != 0xaa55)
-		return 0;
-	if (rom->vrom_signature != VMI_SIGNATURE)
-		return 0;
-	if (rom->api_version_maj != VMI_API_REV_MAJOR ||
-	    rom->api_version_min+1 < VMI_API_REV_MINOR+1) {
-		printk(KERN_WARNING "VMI: Found mismatched rom version %d.%d\n",
-				rom->api_version_maj,
-				rom->api_version_min);
-		return 0;
-	}
-
-	/*
-	 * Relying on the VMI_SIGNATURE field is not 100% safe, so check
-	 * the PCI header and device type to make sure this is really a
-	 * VMI device.
-	 */
-	if (!rom->pci_header_offs) {
-		printk(KERN_WARNING "VMI: ROM does not contain PCI header.\n");
-		return 0;
-	}
-
-	pci = (struct pci_header *)((char *)rom+rom->pci_header_offs);
-	if (pci->vendorID != PCI_VENDOR_ID_VMWARE ||
-	    pci->deviceID != PCI_DEVICE_ID_VMWARE_VMI) {
-		/* Allow it to run... anyways, but warn */
-		printk(KERN_WARNING "VMI: ROM from unknown manufacturer\n");
-	}
-
-	if (rom->pnp_header_offs) {
-		pnp = (struct pnp_header *)((char *)rom+rom->pnp_header_offs);
-		if (pnp->manufacturer_offset)
-			manufacturer = (const char *)rom+pnp->manufacturer_offset;
-		if (pnp->product_offset)
-			product = (const char *)rom+pnp->product_offset;
-	}
-
-	if (rom->license_offs)
-		license = (char *)rom+rom->license_offs;
-
-	printk(KERN_INFO "VMI: Found %s %s, API version %d.%d, ROM version %d.%d\n",
-		manufacturer, product,
-		rom->api_version_maj, rom->api_version_min,
-		pci->rom_version_maj, pci->rom_version_min);
-
-	/* Don't allow BSD/MIT here for now because we don't want to end up
-	   with any binary only shim layers */
-	if (strcmp(license, "GPL") && strcmp(license, "GPL v2")) {
-		printk(KERN_WARNING "VMI: Non GPL license `%s' found for ROM. Not used.\n",
-			license);
-		return 0;
-	}
-
-	return 1;
-}
-
-/*
- * Probe for the VMI option ROM
- */
-static inline int __init probe_vmi_rom(void)
-{
-	unsigned long base;
-
-	/* VMI ROM is in option ROM area, check signature */
-	for (base = 0xC0000; base < 0xE0000; base += 2048) {
-		struct vrom_header *romstart;
-		romstart = (struct vrom_header *)isa_bus_to_virt(base);
-		if (check_vmi_rom(romstart)) {
-			vmi_rom = romstart;
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * VMI setup common to all processors
- */
-void vmi_bringup(void)
-{
- 	/* We must establish the lowmem mapping for MMU ops to work */
-	if (vmi_ops.set_linear_mapping)
-		vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, MAXMEM_PFN, 0);
-}
-
-/*
- * Return a pointer to a VMI function or NULL if unimplemented
- */
-static void *vmi_get_function(int vmicall)
-{
-	u64 reloc;
-	const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc;
-	reloc = call_vrom_long_func(vmi_rom, get_reloc,	vmicall);
-	BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL);
-	if (rel->type == VMI_RELOCATION_CALL_REL)
-		return (void *)rel->eip;
-	else
-		return NULL;
-}
-
-/*
- * Helper macro for making the VMI paravirt-ops fill code readable.
- * For unimplemented operations, fall back to default, unless nop
- * is returned by the ROM.
- */
-#define para_fill(opname, vmicall)				\
-do {								\
-	reloc = call_vrom_long_func(vmi_rom, get_reloc,		\
-				    VMI_CALL_##vmicall);	\
-	if (rel->type == VMI_RELOCATION_CALL_REL) 		\
-		opname = (void *)rel->eip;			\
-	else if (rel->type == VMI_RELOCATION_NOP) 		\
-		opname = (void *)vmi_nop;			\
-	else if (rel->type != VMI_RELOCATION_NONE)		\
-		printk(KERN_WARNING "VMI: Unknown relocation "	\
-				    "type %d for " #vmicall"\n",\
-					rel->type);		\
-} while (0)
-
-/*
- * Helper macro for making the VMI paravirt-ops fill code readable.
- * For cached operations which do not match the VMI ROM ABI and must
- * go through a tranlation stub.  Ignore NOPs, since it is not clear
- * a NOP * VMI function corresponds to a NOP paravirt-op when the
- * functions are not in 1-1 correspondence.
- */
-#define para_wrap(opname, wrapper, cache, vmicall)		\
-do {								\
-	reloc = call_vrom_long_func(vmi_rom, get_reloc,		\
-				    VMI_CALL_##vmicall);	\
-	BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL);		\
-	if (rel->type == VMI_RELOCATION_CALL_REL) {		\
-		opname = wrapper;				\
-		vmi_ops.cache = (void *)rel->eip;		\
-	}							\
-} while (0)
-
-/*
- * Activate the VMI interface and switch into paravirtualized mode
- */
-static inline int __init activate_vmi(void)
-{
-	short kernel_cs;
-	u64 reloc;
-	const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc;
-
-	/*
-	 * Prevent page tables from being allocated in highmem, even if
-	 * CONFIG_HIGHPTE is enabled.
-	 */
-	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-
-	if (call_vrom_func(vmi_rom, vmi_init) != 0) {
-		printk(KERN_ERR "VMI ROM failed to initialize!");
-		return 0;
-	}
-	savesegment(cs, kernel_cs);
-
-	pv_info.paravirt_enabled = 1;
-	pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
-	pv_info.name = "vmi [deprecated]";
-
-	pv_init_ops.patch = vmi_patch;
-
-	/*
-	 * Many of these operations are ABI compatible with VMI.
-	 * This means we can fill in the paravirt-ops with direct
-	 * pointers into the VMI ROM.  If the calling convention for
-	 * these operations changes, this code needs to be updated.
-	 *
-	 * Exceptions
-	 *  CPUID paravirt-op uses pointers, not the native ISA
-	 *  halt has no VMI equivalent; all VMI halts are "safe"
-	 *  no MSR support yet - just trap and emulate.  VMI uses the
-	 *    same ABI as the native ISA, but Linux wants exceptions
-	 *    from bogus MSR read / write handled
-	 *  rdpmc is not yet used in Linux
-	 */
-
-	/* CPUID is special, so very special it gets wrapped like a present */
-	para_wrap(pv_cpu_ops.cpuid, vmi_cpuid, cpuid, CPUID);
-
-	para_fill(pv_cpu_ops.clts, CLTS);
-	para_fill(pv_cpu_ops.get_debugreg, GetDR);
-	para_fill(pv_cpu_ops.set_debugreg, SetDR);
-	para_fill(pv_cpu_ops.read_cr0, GetCR0);
-	para_fill(pv_mmu_ops.read_cr2, GetCR2);
-	para_fill(pv_mmu_ops.read_cr3, GetCR3);
-	para_fill(pv_cpu_ops.read_cr4, GetCR4);
-	para_fill(pv_cpu_ops.write_cr0, SetCR0);
-	para_fill(pv_mmu_ops.write_cr2, SetCR2);
-	para_fill(pv_mmu_ops.write_cr3, SetCR3);
-	para_fill(pv_cpu_ops.write_cr4, SetCR4);
-
-	para_fill(pv_irq_ops.save_fl.func, GetInterruptMask);
-	para_fill(pv_irq_ops.restore_fl.func, SetInterruptMask);
-	para_fill(pv_irq_ops.irq_disable.func, DisableInterrupts);
-	para_fill(pv_irq_ops.irq_enable.func, EnableInterrupts);
-
-	para_fill(pv_cpu_ops.wbinvd, WBINVD);
-	para_fill(pv_cpu_ops.read_tsc, RDTSC);
-
-	/* The following we emulate with trap and emulate for now */
-	/* paravirt_ops.read_msr = vmi_rdmsr */
-	/* paravirt_ops.write_msr = vmi_wrmsr */
-	/* paravirt_ops.rdpmc = vmi_rdpmc */
-
-	/* TR interface doesn't pass TR value, wrap */
-	para_wrap(pv_cpu_ops.load_tr_desc, vmi_set_tr, set_tr, SetTR);
-
-	/* LDT is special, too */
-	para_wrap(pv_cpu_ops.set_ldt, vmi_set_ldt, _set_ldt, SetLDT);
-
-	para_fill(pv_cpu_ops.load_gdt, SetGDT);
-	para_fill(pv_cpu_ops.load_idt, SetIDT);
-	para_fill(pv_cpu_ops.store_gdt, GetGDT);
-	para_fill(pv_cpu_ops.store_idt, GetIDT);
-	para_fill(pv_cpu_ops.store_tr, GetTR);
-	pv_cpu_ops.load_tls = vmi_load_tls;
-	para_wrap(pv_cpu_ops.write_ldt_entry, vmi_write_ldt_entry,
-		  write_ldt_entry, WriteLDTEntry);
-	para_wrap(pv_cpu_ops.write_gdt_entry, vmi_write_gdt_entry,
-		  write_gdt_entry, WriteGDTEntry);
-	para_wrap(pv_cpu_ops.write_idt_entry, vmi_write_idt_entry,
-		  write_idt_entry, WriteIDTEntry);
-	para_wrap(pv_cpu_ops.load_sp0, vmi_load_sp0, set_kernel_stack, UpdateKernelStack);
-	para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
-	para_fill(pv_cpu_ops.io_delay, IODelay);
-
-	para_wrap(pv_cpu_ops.start_context_switch, vmi_start_context_switch,
-		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_cpu_ops.end_context_switch, vmi_end_context_switch,
-		  set_lazy_mode, SetLazyMode);
-
-	para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
-		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy_mmu,
-		  set_lazy_mode, SetLazyMode);
-
-	/* user and kernel flush are just handled with different flags to FlushTLB */
-	para_wrap(pv_mmu_ops.flush_tlb_user, vmi_flush_tlb_user, _flush_tlb, FlushTLB);
-	para_wrap(pv_mmu_ops.flush_tlb_kernel, vmi_flush_tlb_kernel, _flush_tlb, FlushTLB);
-	para_fill(pv_mmu_ops.flush_tlb_single, InvalPage);
-
-	/*
-	 * Until a standard flag format can be agreed on, we need to
-	 * implement these as wrappers in Linux.  Get the VMI ROM
-	 * function pointers for the two backend calls.
-	 */
-#ifdef CONFIG_X86_PAE
-	vmi_ops.set_pte = vmi_get_function(VMI_CALL_SetPxELong);
-	vmi_ops.update_pte = vmi_get_function(VMI_CALL_UpdatePxELong);
-#else
-	vmi_ops.set_pte = vmi_get_function(VMI_CALL_SetPxE);
-	vmi_ops.update_pte = vmi_get_function(VMI_CALL_UpdatePxE);
-#endif
-
-	if (vmi_ops.set_pte) {
-		pv_mmu_ops.set_pte = vmi_set_pte;
-		pv_mmu_ops.set_pte_at = vmi_set_pte_at;
-		pv_mmu_ops.set_pmd = vmi_set_pmd;
-#ifdef CONFIG_X86_PAE
-		pv_mmu_ops.set_pte_atomic = vmi_set_pte_atomic;
-		pv_mmu_ops.set_pud = vmi_set_pud;
-		pv_mmu_ops.pte_clear = vmi_pte_clear;
-		pv_mmu_ops.pmd_clear = vmi_pmd_clear;
-#endif
-	}
-
-	if (vmi_ops.update_pte) {
-		pv_mmu_ops.pte_update = vmi_update_pte;
-		pv_mmu_ops.pte_update_defer = vmi_update_pte_defer;
-	}
-
-	vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage);
-	if (vmi_ops.allocate_page) {
-		pv_mmu_ops.alloc_pte = vmi_allocate_pte;
-		pv_mmu_ops.alloc_pmd = vmi_allocate_pmd;
-		pv_mmu_ops.alloc_pmd_clone = vmi_allocate_pmd_clone;
-	}
-
-	vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage);
-	if (vmi_ops.release_page) {
-		pv_mmu_ops.release_pte = vmi_release_pte;
-		pv_mmu_ops.release_pmd = vmi_release_pmd;
-		pv_mmu_ops.pgd_free = vmi_pgd_free;
-	}
-
-	/* Set linear is needed in all cases */
-	vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping);
-
-	/*
-	 * These MUST always be patched.  Don't support indirect jumps
-	 * through these operations, as the VMI interface may use either
-	 * a jump or a call to get to these operations, depending on
-	 * the backend.  They are performance critical anyway, so requiring
-	 * a patch is not a big problem.
-	 */
-	pv_cpu_ops.irq_enable_sysexit = (void *)0xfeedbab0;
-	pv_cpu_ops.iret = (void *)0xbadbab0;
-
-#ifdef CONFIG_SMP
-	para_wrap(pv_apic_ops.startup_ipi_hook, vmi_startup_ipi_hook, set_initial_ap_state, SetInitialAPState);
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-       para_fill(apic->read, APICRead);
-       para_fill(apic->write, APICWrite);
-#endif
-
-	/*
-	 * Check for VMI timer functionality by probing for a cycle frequency method
-	 */
-	reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_GetCycleFrequency);
-	if (!disable_vmi_timer && rel->type != VMI_RELOCATION_NONE) {
-		vmi_timer_ops.get_cycle_frequency = (void *)rel->eip;
-		vmi_timer_ops.get_cycle_counter =
-			vmi_get_function(VMI_CALL_GetCycleCounter);
-		vmi_timer_ops.get_wallclock =
-			vmi_get_function(VMI_CALL_GetWallclockTime);
-		vmi_timer_ops.wallclock_updated =
-			vmi_get_function(VMI_CALL_WallclockUpdated);
-		vmi_timer_ops.set_alarm = vmi_get_function(VMI_CALL_SetAlarm);
-		vmi_timer_ops.cancel_alarm =
-			 vmi_get_function(VMI_CALL_CancelAlarm);
-		x86_init.timers.timer_init = vmi_time_init;
-#ifdef CONFIG_X86_LOCAL_APIC
-		x86_init.timers.setup_percpu_clockev = vmi_time_bsp_init;
-		x86_cpuinit.setup_percpu_clockev = vmi_time_ap_init;
-#endif
-		pv_time_ops.sched_clock = vmi_sched_clock;
-		x86_platform.calibrate_tsc = vmi_tsc_khz;
-		x86_platform.get_wallclock = vmi_get_wallclock;
-		x86_platform.set_wallclock = vmi_set_wallclock;
-
-		/* We have true wallclock functions; disable CMOS clock sync */
-		no_sync_cmos_clock = 1;
-	} else {
-		disable_noidle = 1;
-		disable_vmi_timer = 1;
-	}
-
-	para_fill(pv_irq_ops.safe_halt, Halt);
-
-	/*
-	 * Alternative instruction rewriting doesn't happen soon enough
-	 * to convert VMI_IRET to a call instead of a jump; so we have
-	 * to do this before IRQs get reenabled.  Fortunately, it is
-	 * idempotent.
-	 */
-	apply_paravirt(__parainstructions, __parainstructions_end);
-
-	vmi_bringup();
-
-	return 1;
-}
-
-#undef para_fill
-
-void __init vmi_init(void)
-{
-	if (!vmi_rom)
-		probe_vmi_rom();
-	else
-		check_vmi_rom(vmi_rom);
-
-	/* In case probing for or validating the ROM failed, basil */
-	if (!vmi_rom)
-		return;
-
-	reserve_top_address(-vmi_rom->virtual_top);
-
-#ifdef CONFIG_X86_IO_APIC
-	/* This is virtual hardware; timer routing is wired correctly */
-	no_timer_check = 1;
-#endif
-}
-
-void __init vmi_activate(void)
-{
-	unsigned long flags;
-
-	if (!vmi_rom)
-		return;
-
-	local_irq_save(flags);
-	activate_vmi();
-	local_irq_restore(flags & X86_EFLAGS_IF);
-}
-
-static int __init parse_vmi(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-
-	if (!strcmp(arg, "disable_pge")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE);
-		disable_pge = 1;
-	} else if (!strcmp(arg, "disable_pse")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PSE);
-		disable_pse = 1;
-	} else if (!strcmp(arg, "disable_sep")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_SEP);
-		disable_sep = 1;
-	} else if (!strcmp(arg, "disable_tsc")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC);
-		disable_tsc = 1;
-	} else if (!strcmp(arg, "disable_mtrr")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_MTRR);
-		disable_mtrr = 1;
-	} else if (!strcmp(arg, "disable_timer")) {
-		disable_vmi_timer = 1;
-		disable_noidle = 1;
-	} else if (!strcmp(arg, "disable_noidle"))
-		disable_noidle = 1;
-	return 0;
-}
-
-early_param("vmi", parse_vmi);
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
deleted file mode 100644
index 5e1ff66ecd73..000000000000
--- a/arch/x86/kernel/vmiclock_32.c
+++ /dev/null
@@ -1,317 +0,0 @@
-/*
- * VMI paravirtual timer support routines.
- *
- * Copyright (C) 2007, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-#include <linux/smp.h>
-#include <linux/interrupt.h>
-#include <linux/cpumask.h>
-#include <linux/clocksource.h>
-#include <linux/clockchips.h>
-
-#include <asm/vmi.h>
-#include <asm/vmi_time.h>
-#include <asm/apicdef.h>
-#include <asm/apic.h>
-#include <asm/timer.h>
-#include <asm/i8253.h>
-#include <asm/irq_vectors.h>
-
-#define VMI_ONESHOT  (VMI_ALARM_IS_ONESHOT  | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
-#define VMI_PERIODIC (VMI_ALARM_IS_PERIODIC | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
-
-static DEFINE_PER_CPU(struct clock_event_device, local_events);
-
-static inline u32 vmi_counter(u32 flags)
-{
-	/* Given VMI_ONESHOT or VMI_PERIODIC, return the corresponding
-	 * cycle counter. */
-	return flags & VMI_ALARM_COUNTER_MASK;
-}
-
-/* paravirt_ops.get_wallclock = vmi_get_wallclock */
-unsigned long vmi_get_wallclock(void)
-{
-	unsigned long long wallclock;
-	wallclock = vmi_timer_ops.get_wallclock(); // nsec
-	(void)do_div(wallclock, 1000000000);       // sec
-
-	return wallclock;
-}
-
-/* paravirt_ops.set_wallclock = vmi_set_wallclock */
-int vmi_set_wallclock(unsigned long now)
-{
-	return 0;
-}
-
-/* paravirt_ops.sched_clock = vmi_sched_clock */
-unsigned long long vmi_sched_clock(void)
-{
-	return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE));
-}
-
-/* x86_platform.calibrate_tsc = vmi_tsc_khz */
-unsigned long vmi_tsc_khz(void)
-{
-	unsigned long long khz;
-	khz = vmi_timer_ops.get_cycle_frequency();
-	(void)do_div(khz, 1000);
-	return khz;
-}
-
-static inline unsigned int vmi_get_timer_vector(void)
-{
-	return IRQ0_VECTOR;
-}
-
-/** vmi clockchip */
-#ifdef CONFIG_X86_LOCAL_APIC
-static unsigned int startup_timer_irq(unsigned int irq)
-{
-	unsigned long val = apic_read(APIC_LVTT);
-	apic_write(APIC_LVTT, vmi_get_timer_vector());
-
-	return (val & APIC_SEND_PENDING);
-}
-
-static void mask_timer_irq(unsigned int irq)
-{
-	unsigned long val = apic_read(APIC_LVTT);
-	apic_write(APIC_LVTT, val | APIC_LVT_MASKED);
-}
-
-static void unmask_timer_irq(unsigned int irq)
-{
-	unsigned long val = apic_read(APIC_LVTT);
-	apic_write(APIC_LVTT, val & ~APIC_LVT_MASKED);
-}
-
-static void ack_timer_irq(unsigned int irq)
-{
-	ack_APIC_irq();
-}
-
-static struct irq_chip vmi_chip __read_mostly = {
-	.name 		= "VMI-LOCAL",
-	.startup 	= startup_timer_irq,
-	.mask	 	= mask_timer_irq,
-	.unmask	 	= unmask_timer_irq,
-	.ack 		= ack_timer_irq
-};
-#endif
-
-/** vmi clockevent */
-#define VMI_ALARM_WIRED_IRQ0    0x00000000
-#define VMI_ALARM_WIRED_LVTT    0x00010000
-static int vmi_wiring = VMI_ALARM_WIRED_IRQ0;
-
-static inline int vmi_get_alarm_wiring(void)
-{
-	return vmi_wiring;
-}
-
-static void vmi_timer_set_mode(enum clock_event_mode mode,
-			       struct clock_event_device *evt)
-{
-	cycle_t now, cycles_per_hz;
-	BUG_ON(!irqs_disabled());
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	case CLOCK_EVT_MODE_PERIODIC:
-		cycles_per_hz = vmi_timer_ops.get_cycle_frequency();
-		(void)do_div(cycles_per_hz, HZ);
-		now = vmi_timer_ops.get_cycle_counter(vmi_counter(VMI_PERIODIC));
-		vmi_timer_ops.set_alarm(VMI_PERIODIC, now, cycles_per_hz);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		switch (evt->mode) {
-		case CLOCK_EVT_MODE_ONESHOT:
-			vmi_timer_ops.cancel_alarm(VMI_ONESHOT);
-			break;
-		case CLOCK_EVT_MODE_PERIODIC:
-			vmi_timer_ops.cancel_alarm(VMI_PERIODIC);
-			break;
-		default:
-			break;
-		}
-		break;
-	default:
-		break;
-	}
-}
-
-static int vmi_timer_next_event(unsigned long delta,
-				struct clock_event_device *evt)
-{
-	/* Unfortunately, set_next_event interface only passes relative
-	 * expiry, but we want absolute expiry.  It'd be better if were
-	 * were passed an absolute expiry, since a bunch of time may
-	 * have been stolen between the time the delta is computed and
-	 * when we set the alarm below. */
-	cycle_t now = vmi_timer_ops.get_cycle_counter(vmi_counter(VMI_ONESHOT));
-
-	BUG_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
-	vmi_timer_ops.set_alarm(VMI_ONESHOT, now + delta, 0);
-	return 0;
-}
-
-static struct clock_event_device vmi_clockevent = {
-	.name		= "vmi-timer",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.shift		= 22,
-	.set_mode	= vmi_timer_set_mode,
-	.set_next_event = vmi_timer_next_event,
-	.rating         = 1000,
-	.irq		= 0,
-};
-
-static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id)
-{
-	struct clock_event_device *evt = &__get_cpu_var(local_events);
-	evt->event_handler(evt);
-	return IRQ_HANDLED;
-}
-
-static struct irqaction vmi_clock_action  = {
-	.name 		= "vmi-timer",
-	.handler 	= vmi_timer_interrupt,
-	.flags 		= IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER,
-};
-
-static void __devinit vmi_time_init_clockevent(void)
-{
-	cycle_t cycles_per_msec;
-	struct clock_event_device *evt;
-
-	int cpu = smp_processor_id();
-	evt = &__get_cpu_var(local_events);
-
-	/* Use cycles_per_msec since div_sc params are 32-bits. */
-	cycles_per_msec = vmi_timer_ops.get_cycle_frequency();
-	(void)do_div(cycles_per_msec, 1000);
-
-	memcpy(evt, &vmi_clockevent, sizeof(*evt));
-	/* Must pick .shift such that .mult fits in 32-bits.  Choosing
-	 * .shift to be 22 allows 2^(32-22) cycles per nano-seconds
-	 * before overflow. */
-	evt->mult = div_sc(cycles_per_msec, NSEC_PER_MSEC, evt->shift);
-	/* Upper bound is clockevent's use of ulong for cycle deltas. */
-	evt->max_delta_ns = clockevent_delta2ns(ULONG_MAX, evt);
-	evt->min_delta_ns = clockevent_delta2ns(1, evt);
-	evt->cpumask = cpumask_of(cpu);
-
-	printk(KERN_WARNING "vmi: registering clock event %s. mult=%u shift=%u\n",
-	       evt->name, evt->mult, evt->shift);
-	clockevents_register_device(evt);
-}
-
-void __init vmi_time_init(void)
-{
-	unsigned int cpu;
-	/* Disable PIT: BIOSes start PIT CH0 with 18.2hz peridic. */
-	outb_pit(0x3a, PIT_MODE); /* binary, mode 5, LSB/MSB, ch 0 */
-
-	vmi_time_init_clockevent();
-	setup_irq(0, &vmi_clock_action);
-	for_each_possible_cpu(cpu)
-		per_cpu(vector_irq, cpu)[vmi_get_timer_vector()] = 0;
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-void __devinit vmi_time_bsp_init(void)
-{
-	/*
-	 * On APIC systems, we want local timers to fire on each cpu.  We do
-	 * this by programming LVTT to deliver timer events to the IRQ handler
-	 * for IRQ-0, since we can't re-use the APIC local timer handler
-	 * without interfering with that code.
-	 */
-	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
-	local_irq_disable();
-#ifdef CONFIG_SMP
-	/*
-	 * XXX handle_percpu_irq only defined for SMP; we need to switch over
-	 * to using it, since this is a local interrupt, which each CPU must
-	 * handle individually without locking out or dropping simultaneous
-	 * local timers on other CPUs.  We also don't want to trigger the
-	 * quirk workaround code for interrupts which gets invoked from
-	 * handle_percpu_irq via eoi, so we use our own IRQ chip.
-	 */
-	set_irq_chip_and_handler_name(0, &vmi_chip, handle_percpu_irq, "lvtt");
-#else
-	set_irq_chip_and_handler_name(0, &vmi_chip, handle_edge_irq, "lvtt");
-#endif
-	vmi_wiring = VMI_ALARM_WIRED_LVTT;
-	apic_write(APIC_LVTT, vmi_get_timer_vector());
-	local_irq_enable();
-	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
-}
-
-void __devinit vmi_time_ap_init(void)
-{
-	vmi_time_init_clockevent();
-	apic_write(APIC_LVTT, vmi_get_timer_vector());
-}
-#endif
-
-/** vmi clocksource */
-static struct clocksource clocksource_vmi;
-
-static cycle_t read_real_cycles(struct clocksource *cs)
-{
-	cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
-	return max(ret, clocksource_vmi.cycle_last);
-}
-
-static struct clocksource clocksource_vmi = {
-	.name			= "vmi-timer",
-	.rating			= 450,
-	.read			= read_real_cycles,
-	.mask			= CLOCKSOURCE_MASK(64),
-	.mult			= 0, /* to be set */
-	.shift			= 22,
-	.flags			= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-static int __init init_vmi_clocksource(void)
-{
-	cycle_t cycles_per_msec;
-
-	if (!vmi_timer_ops.get_cycle_frequency)
-		return 0;
-	/* Use khz2mult rather than hz2mult since hz arg is only 32-bits. */
-	cycles_per_msec = vmi_timer_ops.get_cycle_frequency();
-	(void)do_div(cycles_per_msec, 1000);
-
-	/* Note that clocksource.{mult, shift} converts in the opposite direction
-	 * as clockevents.  */
-	clocksource_vmi.mult = clocksource_khz2mult(cycles_per_msec,
-						    clocksource_vmi.shift);
-
-	printk(KERN_WARNING "vmi: registering clock source khz=%lld\n", cycles_per_msec);
-	return clocksource_register(&clocksource_vmi);
-
-}
-module_init(init_vmi_clocksource);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index d0bb52296fa3..e03530aebfd0 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -242,6 +242,12 @@ SECTIONS
 		__x86_cpu_dev_end = .;
 	}
 
+	/*
+	 * start address and size of operations which during runtime
+	 * can be patched with virtualization friendly instructions or
+	 * baremetal native ones. Think page table operations.
+	 * Details in paravirt_types.h
+	 */
 	. = ALIGN(8);
 	.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
 		__parainstructions = .;
@@ -249,6 +255,11 @@ SECTIONS
 		__parainstructions_end = .;
 	}
 
+	/*
+	 * struct alt_inst entries. From the header (alternative.h):
+	 * "Alternative instructions for different CPU types or capabilities"
+	 * Think locking instructions on spinlocks.
+	 */
 	. = ALIGN(8);
 	.altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
 		__alt_instructions = .;
@@ -256,11 +267,28 @@ SECTIONS
 		__alt_instructions_end = .;
 	}
 
+	/*
+	 * And here are the replacement instructions. The linker sticks
+	 * them as binary blobs. The .altinstructions has enough data to
+	 * get the address and the length of them to patch the kernel safely.
+	 */
 	.altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
 		*(.altinstr_replacement)
 	}
 
 	/*
+	 * struct iommu_table_entry entries are injected in this section.
+	 * It is an array of IOMMUs which during run time gets sorted depending
+	 * on its dependency order. After rootfs_initcall is complete
+	 * this section can be safely removed.
+	 */
+	.iommu_table : AT(ADDR(.iommu_table) - LOAD_OFFSET) {
+		__iommu_table = .;
+		*(.iommu_table)
+		__iommu_table_end = .;
+	}
+	. = ALIGN(8);
+	/*
 	 * .exit.text is discard at runtime, not link time, to deal with
 	 *  references from .altinstructions and .eh_frame
 	 */
@@ -273,7 +301,7 @@ SECTIONS
 	}
 
 #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-	PERCPU(PAGE_SIZE)
+	PERCPU(THREAD_SIZE)
 #endif
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 77d8c0f4817d..22b06f7660f4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1056,14 +1056,13 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.apic = apic;
 
-	apic->regs_page = alloc_page(GFP_KERNEL);
+	apic->regs_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
 	if (apic->regs_page == NULL) {
 		printk(KERN_ERR "malloc apic regs error for vcpu %x\n",
 		       vcpu->vcpu_id);
 		goto nomem_free_apic;
 	}
 	apic->regs = page_address(apic->regs_page);
-	memset(apic->regs, 0, PAGE_SIZE);
 	apic->vcpu = vcpu;
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3ff0a8ff275c..57330731d33a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2206,13 +2206,14 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ |
 		0 /* Reserved, DCA */ | F(XMM4_1) |
 		F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
-		0 /* Reserved, AES */ | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX);
+		0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
+		F(F16C);
 	/* cpuid 0x80000001.ecx */
 	const u32 kvm_supported_word6_x86_features =
 		F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
 		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
-		F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(SSE5) |
-		0 /* SKINIT */ | 0 /* WDT */;
+		F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) |
+		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index 5415a9d06f53..b908a59eccf5 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -22,22 +22,187 @@ EXPORT_SYMBOL(memset);
 
 void *memmove(void *dest, const void *src, size_t n)
 {
-	int d0, d1, d2;
-
-	if (dest < src) {
-		memcpy(dest, src, n);
-	} else {
-		__asm__ __volatile__(
-			"std\n\t"
-			"rep\n\t"
-			"movsb\n\t"
-			"cld"
-			: "=&c" (d0), "=&S" (d1), "=&D" (d2)
-			:"0" (n),
-			 "1" (n-1+src),
-			 "2" (n-1+dest)
-			:"memory");
-	}
-	return dest;
+	int d0,d1,d2,d3,d4,d5;
+	char *ret = dest;
+
+	__asm__ __volatile__(
+		/* Handle more 16bytes in loop */
+		"cmp $0x10, %0\n\t"
+		"jb	1f\n\t"
+
+		/* Decide forward/backward copy mode */
+		"cmp %2, %1\n\t"
+		"jb	2f\n\t"
+
+		/*
+		 * movs instruction have many startup latency
+		 * so we handle small size by general register.
+		 */
+		"cmp  $680, %0\n\t"
+		"jb 3f\n\t"
+		/*
+		 * movs instruction is only good for aligned case.
+		 */
+		"mov %1, %3\n\t"
+		"xor %2, %3\n\t"
+		"and $0xff, %3\n\t"
+		"jz 4f\n\t"
+		"3:\n\t"
+		"sub $0x10, %0\n\t"
+
+		/*
+		 * We gobble 16byts forward in each loop.
+		 */
+		"3:\n\t"
+		"sub $0x10, %0\n\t"
+		"mov 0*4(%1), %3\n\t"
+		"mov 1*4(%1), %4\n\t"
+		"mov  %3, 0*4(%2)\n\t"
+		"mov  %4, 1*4(%2)\n\t"
+		"mov 2*4(%1), %3\n\t"
+		"mov 3*4(%1), %4\n\t"
+		"mov  %3, 2*4(%2)\n\t"
+		"mov  %4, 3*4(%2)\n\t"
+		"lea  0x10(%1), %1\n\t"
+		"lea  0x10(%2), %2\n\t"
+		"jae 3b\n\t"
+		"add $0x10, %0\n\t"
+		"jmp 1f\n\t"
+
+		/*
+		 * Handle data forward by movs.
+		 */
+		".p2align 4\n\t"
+		"4:\n\t"
+		"mov -4(%1, %0), %3\n\t"
+		"lea -4(%2, %0), %4\n\t"
+		"shr $2, %0\n\t"
+		"rep movsl\n\t"
+		"mov %3, (%4)\n\t"
+		"jmp 11f\n\t"
+		/*
+		 * Handle data backward by movs.
+		 */
+		".p2align 4\n\t"
+		"6:\n\t"
+		"mov (%1), %3\n\t"
+		"mov %2, %4\n\t"
+		"lea -4(%1, %0), %1\n\t"
+		"lea -4(%2, %0), %2\n\t"
+		"shr $2, %0\n\t"
+		"std\n\t"
+		"rep movsl\n\t"
+		"mov %3,(%4)\n\t"
+		"cld\n\t"
+		"jmp 11f\n\t"
+
+		/*
+		 * Start to prepare for backward copy.
+		 */
+		".p2align 4\n\t"
+		"2:\n\t"
+		"cmp  $680, %0\n\t"
+		"jb 5f\n\t"
+		"mov %1, %3\n\t"
+		"xor %2, %3\n\t"
+		"and $0xff, %3\n\t"
+		"jz 6b\n\t"
+
+		/*
+		 * Calculate copy position to tail.
+		 */
+		"5:\n\t"
+		"add %0, %1\n\t"
+		"add %0, %2\n\t"
+		"sub $0x10, %0\n\t"
+
+		/*
+		 * We gobble 16byts backward in each loop.
+		 */
+		"7:\n\t"
+		"sub $0x10, %0\n\t"
+
+		"mov -1*4(%1), %3\n\t"
+		"mov -2*4(%1), %4\n\t"
+		"mov  %3, -1*4(%2)\n\t"
+		"mov  %4, -2*4(%2)\n\t"
+		"mov -3*4(%1), %3\n\t"
+		"mov -4*4(%1), %4\n\t"
+		"mov  %3, -3*4(%2)\n\t"
+		"mov  %4, -4*4(%2)\n\t"
+		"lea  -0x10(%1), %1\n\t"
+		"lea  -0x10(%2), %2\n\t"
+		"jae 7b\n\t"
+		/*
+		 * Calculate copy position to head.
+		 */
+		"add $0x10, %0\n\t"
+		"sub %0, %1\n\t"
+		"sub %0, %2\n\t"
+
+		/*
+		 * Move data from 8 bytes to 15 bytes.
+		 */
+		".p2align 4\n\t"
+		"1:\n\t"
+		"cmp $8, %0\n\t"
+		"jb 8f\n\t"
+		"mov 0*4(%1), %3\n\t"
+		"mov 1*4(%1), %4\n\t"
+		"mov -2*4(%1, %0), %5\n\t"
+		"mov -1*4(%1, %0), %1\n\t"
+
+		"mov  %3, 0*4(%2)\n\t"
+		"mov  %4, 1*4(%2)\n\t"
+		"mov  %5, -2*4(%2, %0)\n\t"
+		"mov  %1, -1*4(%2, %0)\n\t"
+		"jmp 11f\n\t"
+
+		/*
+		 * Move data from 4 bytes to 7 bytes.
+		 */
+		".p2align 4\n\t"
+		"8:\n\t"
+		"cmp $4, %0\n\t"
+		"jb 9f\n\t"
+		"mov 0*4(%1), %3\n\t"
+		"mov -1*4(%1, %0), %4\n\t"
+		"mov  %3, 0*4(%2)\n\t"
+		"mov  %4, -1*4(%2, %0)\n\t"
+		"jmp 11f\n\t"
+
+		/*
+		 * Move data from 2 bytes to 3 bytes.
+		 */
+		".p2align 4\n\t"
+		"9:\n\t"
+		"cmp $2, %0\n\t"
+		"jb 10f\n\t"
+		"movw 0*2(%1), %%dx\n\t"
+		"movw -1*2(%1, %0), %%bx\n\t"
+		"movw %%dx, 0*2(%2)\n\t"
+		"movw %%bx, -1*2(%2, %0)\n\t"
+		"jmp 11f\n\t"
+
+		/*
+		 * Move data for 1 byte.
+		 */
+		".p2align 4\n\t"
+		"10:\n\t"
+		"cmp $1, %0\n\t"
+		"jb 11f\n\t"
+		"movb (%1), %%cl\n\t"
+		"movb %%cl, (%2)\n\t"
+		".p2align 4\n\t"
+		"11:"
+		: "=&c" (d0), "=&S" (d1), "=&D" (d2),
+		  "=r" (d3),"=r" (d4), "=r"(d5)
+		:"0" (n),
+		 "1" (src),
+		 "2" (dest)
+		:"memory");
+
+	return ret;
+
 }
 EXPORT_SYMBOL(memmove);
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index bcbcd1e0f7d5..75ef61e35e38 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -40,84 +40,132 @@
 ENTRY(__memcpy)
 ENTRY(memcpy)
 	CFI_STARTPROC
+	movq %rdi, %rax
 
 	/*
-	 * Put the number of full 64-byte blocks into %ecx.
-	 * Tail portion is handled at the end:
+	 * Use 32bit CMP here to avoid long NOP padding.
 	 */
-	movq %rdi, %rax
-	movl %edx, %ecx
-	shrl   $6, %ecx
-	jz .Lhandle_tail
+	cmp  $0x20, %edx
+	jb .Lhandle_tail
 
-	.p2align 4
-.Lloop_64:
 	/*
-	 * We decrement the loop index here - and the zero-flag is
-	 * checked at the end of the loop (instructions inbetween do
-	 * not change the zero flag):
+	 * We check whether memory false dependece could occur,
+	 * then jump to corresponding copy mode.
 	 */
-	decl %ecx
+	cmp  %dil, %sil
+	jl .Lcopy_backward
+	subl $0x20, %edx
+.Lcopy_forward_loop:
+	subq $0x20,	%rdx
 
 	/*
-	 * Move in blocks of 4x16 bytes:
+	 * Move in blocks of 4x8 bytes:
 	 */
-	movq 0*8(%rsi),		%r11
-	movq 1*8(%rsi),		%r8
-	movq %r11,		0*8(%rdi)
-	movq %r8,		1*8(%rdi)
-
-	movq 2*8(%rsi),		%r9
-	movq 3*8(%rsi),		%r10
-	movq %r9,		2*8(%rdi)
-	movq %r10,		3*8(%rdi)
-
-	movq 4*8(%rsi),		%r11
-	movq 5*8(%rsi),		%r8
-	movq %r11,		4*8(%rdi)
-	movq %r8,		5*8(%rdi)
-
-	movq 6*8(%rsi),		%r9
-	movq 7*8(%rsi),		%r10
-	movq %r9,		6*8(%rdi)
-	movq %r10,		7*8(%rdi)
-
-	leaq 64(%rsi), %rsi
-	leaq 64(%rdi), %rdi
-
-	jnz  .Lloop_64
+	movq 0*8(%rsi),	%r8
+	movq 1*8(%rsi),	%r9
+	movq 2*8(%rsi),	%r10
+	movq 3*8(%rsi),	%r11
+	leaq 4*8(%rsi),	%rsi
+
+	movq %r8,	0*8(%rdi)
+	movq %r9,	1*8(%rdi)
+	movq %r10,	2*8(%rdi)
+	movq %r11,	3*8(%rdi)
+	leaq 4*8(%rdi),	%rdi
+	jae  .Lcopy_forward_loop
+	addq $0x20,	%rdx
+	jmp  .Lhandle_tail
+
+.Lcopy_backward:
+	/*
+	 * Calculate copy position to tail.
+	 */
+	addq %rdx,	%rsi
+	addq %rdx,	%rdi
+	subq $0x20,	%rdx
+	/*
+	 * At most 3 ALU operations in one cycle,
+	 * so append NOPS in the same 16bytes trunk.
+	 */
+	.p2align 4
+.Lcopy_backward_loop:
+	subq $0x20,	%rdx
+	movq -1*8(%rsi),	%r8
+	movq -2*8(%rsi),	%r9
+	movq -3*8(%rsi),	%r10
+	movq -4*8(%rsi),	%r11
+	leaq -4*8(%rsi),	%rsi
+	movq %r8,		-1*8(%rdi)
+	movq %r9,		-2*8(%rdi)
+	movq %r10,		-3*8(%rdi)
+	movq %r11,		-4*8(%rdi)
+	leaq -4*8(%rdi),	%rdi
+	jae  .Lcopy_backward_loop
 
+	/*
+	 * Calculate copy position to head.
+	 */
+	addq $0x20,	%rdx
+	subq %rdx,	%rsi
+	subq %rdx,	%rdi
 .Lhandle_tail:
-	movl %edx, %ecx
-	andl  $63, %ecx
-	shrl   $3, %ecx
-	jz   .Lhandle_7
+	cmpq $16,	%rdx
+	jb   .Lless_16bytes
 
+	/*
+	 * Move data from 16 bytes to 31 bytes.
+	 */
+	movq 0*8(%rsi), %r8
+	movq 1*8(%rsi),	%r9
+	movq -2*8(%rsi, %rdx),	%r10
+	movq -1*8(%rsi, %rdx),	%r11
+	movq %r8,	0*8(%rdi)
+	movq %r9,	1*8(%rdi)
+	movq %r10,	-2*8(%rdi, %rdx)
+	movq %r11,	-1*8(%rdi, %rdx)
+	retq
 	.p2align 4
-.Lloop_8:
-	decl %ecx
-	movq (%rsi),		%r8
-	movq %r8,		(%rdi)
-	leaq 8(%rdi),		%rdi
-	leaq 8(%rsi),		%rsi
-	jnz  .Lloop_8
-
-.Lhandle_7:
-	movl %edx, %ecx
-	andl $7, %ecx
-	jz .Lend
+.Lless_16bytes:
+	cmpq $8,	%rdx
+	jb   .Lless_8bytes
+	/*
+	 * Move data from 8 bytes to 15 bytes.
+	 */
+	movq 0*8(%rsi),	%r8
+	movq -1*8(%rsi, %rdx),	%r9
+	movq %r8,	0*8(%rdi)
+	movq %r9,	-1*8(%rdi, %rdx)
+	retq
+	.p2align 4
+.Lless_8bytes:
+	cmpq $4,	%rdx
+	jb   .Lless_3bytes
 
+	/*
+	 * Move data from 4 bytes to 7 bytes.
+	 */
+	movl (%rsi), %ecx
+	movl -4(%rsi, %rdx), %r8d
+	movl %ecx, (%rdi)
+	movl %r8d, -4(%rdi, %rdx)
+	retq
 	.p2align 4
+.Lless_3bytes:
+	cmpl $0, %edx
+	je .Lend
+	/*
+	 * Move data from 1 bytes to 3 bytes.
+	 */
 .Lloop_1:
 	movb (%rsi), %r8b
 	movb %r8b, (%rdi)
 	incq %rdi
 	incq %rsi
-	decl %ecx
+	decl %edx
 	jnz .Lloop_1
 
 .Lend:
-	ret
+	retq
 	CFI_ENDPROC
 ENDPROC(memcpy)
 ENDPROC(__memcpy)
diff --git a/arch/x86/lib/memmove_64.c b/arch/x86/lib/memmove_64.c
index 0a33909bf122..6d0f0ec41b34 100644
--- a/arch/x86/lib/memmove_64.c
+++ b/arch/x86/lib/memmove_64.c
@@ -8,14 +8,185 @@
 #undef memmove
 void *memmove(void *dest, const void *src, size_t count)
 {
-	if (dest < src) {
-		return memcpy(dest, src, count);
-	} else {
-		char *p = dest + count;
-		const char *s = src + count;
-		while (count--)
-			*--p = *--s;
-	}
-	return dest;
+	unsigned long d0,d1,d2,d3,d4,d5,d6,d7;
+	char *ret;
+
+	__asm__ __volatile__(
+		/* Handle more 32bytes in loop */
+		"mov %2, %3\n\t"
+		"cmp $0x20, %0\n\t"
+		"jb	1f\n\t"
+
+		/* Decide forward/backward copy mode */
+		"cmp %2, %1\n\t"
+		"jb	2f\n\t"
+
+		/*
+		 * movsq instruction have many startup latency
+		 * so we handle small size by general register.
+		 */
+		"cmp  $680, %0\n\t"
+		"jb 3f\n\t"
+		/*
+		 * movsq instruction is only good for aligned case.
+		 */
+		"cmpb %%dil, %%sil\n\t"
+		"je 4f\n\t"
+		"3:\n\t"
+		"sub $0x20, %0\n\t"
+		/*
+		 * We gobble 32byts forward in each loop.
+		 */
+		"5:\n\t"
+		"sub $0x20, %0\n\t"
+		"movq 0*8(%1), %4\n\t"
+		"movq 1*8(%1), %5\n\t"
+		"movq 2*8(%1), %6\n\t"
+		"movq 3*8(%1), %7\n\t"
+		"leaq 4*8(%1), %1\n\t"
+
+		"movq %4, 0*8(%2)\n\t"
+		"movq %5, 1*8(%2)\n\t"
+		"movq %6, 2*8(%2)\n\t"
+		"movq %7, 3*8(%2)\n\t"
+		"leaq 4*8(%2), %2\n\t"
+		"jae 5b\n\t"
+		"addq $0x20, %0\n\t"
+		"jmp 1f\n\t"
+		/*
+		 * Handle data forward by movsq.
+		 */
+		".p2align 4\n\t"
+		"4:\n\t"
+		"movq %0, %8\n\t"
+		"movq -8(%1, %0), %4\n\t"
+		"lea -8(%2, %0), %5\n\t"
+		"shrq $3, %8\n\t"
+		"rep movsq\n\t"
+		"movq %4, (%5)\n\t"
+		"jmp 13f\n\t"
+		/*
+		 * Handle data backward by movsq.
+		 */
+		".p2align 4\n\t"
+		"7:\n\t"
+		"movq %0, %8\n\t"
+		"movq (%1), %4\n\t"
+		"movq %2, %5\n\t"
+		"leaq -8(%1, %0), %1\n\t"
+		"leaq -8(%2, %0), %2\n\t"
+		"shrq $3, %8\n\t"
+		"std\n\t"
+		"rep movsq\n\t"
+		"cld\n\t"
+		"movq %4, (%5)\n\t"
+		"jmp 13f\n\t"
+
+		/*
+		 * Start to prepare for backward copy.
+		 */
+		".p2align 4\n\t"
+		"2:\n\t"
+		"cmp $680, %0\n\t"
+		"jb 6f \n\t"
+		"cmp %%dil, %%sil\n\t"
+		"je 7b \n\t"
+		"6:\n\t"
+		/*
+		 * Calculate copy position to tail.
+		 */
+		"addq %0, %1\n\t"
+		"addq %0, %2\n\t"
+		"subq $0x20, %0\n\t"
+		/*
+		 * We gobble 32byts backward in each loop.
+		 */
+		"8:\n\t"
+		"subq $0x20, %0\n\t"
+		"movq -1*8(%1), %4\n\t"
+		"movq -2*8(%1), %5\n\t"
+		"movq -3*8(%1), %6\n\t"
+		"movq -4*8(%1), %7\n\t"
+		"leaq -4*8(%1), %1\n\t"
+
+		"movq %4, -1*8(%2)\n\t"
+		"movq %5, -2*8(%2)\n\t"
+		"movq %6, -3*8(%2)\n\t"
+		"movq %7, -4*8(%2)\n\t"
+		"leaq -4*8(%2), %2\n\t"
+		"jae 8b\n\t"
+		/*
+		 * Calculate copy position to head.
+		 */
+		"addq $0x20, %0\n\t"
+		"subq %0, %1\n\t"
+		"subq %0, %2\n\t"
+		"1:\n\t"
+		"cmpq $16, %0\n\t"
+		"jb 9f\n\t"
+		/*
+		 * Move data from 16 bytes to 31 bytes.
+		 */
+		"movq 0*8(%1), %4\n\t"
+		"movq 1*8(%1), %5\n\t"
+		"movq -2*8(%1, %0), %6\n\t"
+		"movq -1*8(%1, %0), %7\n\t"
+		"movq %4, 0*8(%2)\n\t"
+		"movq %5, 1*8(%2)\n\t"
+		"movq %6, -2*8(%2, %0)\n\t"
+		"movq %7, -1*8(%2, %0)\n\t"
+		"jmp 13f\n\t"
+		".p2align 4\n\t"
+		"9:\n\t"
+		"cmpq $8, %0\n\t"
+		"jb 10f\n\t"
+		/*
+		 * Move data from 8 bytes to 15 bytes.
+		 */
+		"movq 0*8(%1), %4\n\t"
+		"movq -1*8(%1, %0), %5\n\t"
+		"movq %4, 0*8(%2)\n\t"
+		"movq %5, -1*8(%2, %0)\n\t"
+		"jmp 13f\n\t"
+		"10:\n\t"
+		"cmpq $4, %0\n\t"
+		"jb 11f\n\t"
+		/*
+		 * Move data from 4 bytes to 7 bytes.
+		 */
+		"movl (%1), %4d\n\t"
+		"movl -4(%1, %0), %5d\n\t"
+		"movl %4d, (%2)\n\t"
+		"movl %5d, -4(%2, %0)\n\t"
+		"jmp 13f\n\t"
+		"11:\n\t"
+		"cmp $2, %0\n\t"
+		"jb 12f\n\t"
+		/*
+		 * Move data from 2 bytes to 3 bytes.
+		 */
+		"movw (%1), %4w\n\t"
+		"movw -2(%1, %0), %5w\n\t"
+		"movw %4w, (%2)\n\t"
+		"movw %5w, -2(%2, %0)\n\t"
+		"jmp 13f\n\t"
+		"12:\n\t"
+		"cmp $1, %0\n\t"
+		"jb 13f\n\t"
+		/*
+		 * Move data for 1 byte.
+		 */
+		"movb (%1), %4b\n\t"
+		"movb %4b, (%2)\n\t"
+		"13:\n\t"
+		: "=&d" (d0), "=&S" (d1), "=&D" (d2), "=&a" (ret) ,
+		  "=r"(d3), "=r"(d4), "=r"(d5), "=r"(d6), "=&c" (d7)
+		:"0" (count),
+		 "1" (src),
+		 "2" (dest)
+		:"memory");
+
+		return ret;
+
 }
 EXPORT_SYMBOL(memmove);
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index a4c768397baa..55543397a8a7 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -26,4 +26,6 @@ obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
 obj-$(CONFIG_K8_NUMA)		+= k8topology_64.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
 
+obj-$(CONFIG_HAVE_MEMBLOCK)		+= memblock.o
+
 obj-$(CONFIG_MEMTEST)		+= memtest.o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 4c4508e8a204..caec22906d7c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -326,29 +326,7 @@ out:
 
 void vmalloc_sync_all(void)
 {
-	unsigned long address;
-
-	for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
-	     address += PGDIR_SIZE) {
-
-		const pgd_t *pgd_ref = pgd_offset_k(address);
-		unsigned long flags;
-		struct page *page;
-
-		if (pgd_none(*pgd_ref))
-			continue;
-
-		spin_lock_irqsave(&pgd_lock, flags);
-		list_for_each_entry(page, &pgd_list, lru) {
-			pgd_t *pgd;
-			pgd = (pgd_t *)page_address(page) + pgd_index(address);
-			if (pgd_none(*pgd))
-				set_pgd(pgd, *pgd_ref);
-			else
-				BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
-		}
-		spin_unlock_irqrestore(&pgd_lock, flags);
-	}
+	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
 }
 
 /*
@@ -894,8 +872,14 @@ spurious_fault(unsigned long error_code, unsigned long address)
 	if (pmd_large(*pmd))
 		return spurious_fault_check(error_code, (pte_t *) pmd);
 
+	/*
+	 * Note: don't use pte_present() here, since it returns true
+	 * if the _PAGE_PROTNONE bit is set.  However, this aliases the
+	 * _PAGE_GLOBAL bit, which for kernel pages give false positives
+	 * when CONFIG_DEBUG_PAGEALLOC is used.
+	 */
 	pte = pte_offset_kernel(pmd, address);
-	if (!pte_present(*pte))
+	if (!(pte_flags(*pte) & _PAGE_PRESENT))
 		return 0;
 
 	ret = spurious_fault_check(error_code, pte);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index b278535b14aa..c0e28a13de7d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -2,6 +2,7 @@
 #include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
+#include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
 #include <asm/e820.h>
@@ -33,6 +34,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 					  int use_gbpages)
 {
 	unsigned long puds, pmds, ptes, tables, start;
+	phys_addr_t base;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
 	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
@@ -75,12 +77,12 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #else
 	start = 0x8000;
 #endif
-	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+	base = memblock_find_in_range(start, max_pfn_mapped<<PAGE_SHIFT,
 					tables, PAGE_SIZE);
-	if (e820_table_start == -1UL)
+	if (base == MEMBLOCK_ERROR)
 		panic("Cannot find space for the kernel page tables");
 
-	e820_table_start >>= PAGE_SHIFT;
+	e820_table_start = base >> PAGE_SHIFT;
 	e820_table_end = e820_table_start;
 	e820_table_top = e820_table_start + (tables >> PAGE_SHIFT);
 
@@ -299,7 +301,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	__flush_tlb_all();
 
 	if (!after_bootmem && e820_table_end > e820_table_start)
-		reserve_early(e820_table_start << PAGE_SHIFT,
+		memblock_x86_reserve_range(e820_table_start << PAGE_SHIFT,
 				 e820_table_end << PAGE_SHIFT, "PGTABLE");
 
 	if (!after_bootmem)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bca79091b9d6..43bbc2975c3e 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -25,6 +25,7 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/memory_hotplug.h>
 #include <linux/initrd.h>
@@ -67,7 +68,7 @@ static __init void *alloc_low_page(void)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = __va(pfn * PAGE_SIZE);
-	memset(adr, 0, PAGE_SIZE);
+	clear_page(adr);
 	return adr;
 }
 
@@ -558,7 +559,7 @@ char swsusp_pg_dir[PAGE_SIZE]
 
 static inline void save_pg_dir(void)
 {
-	memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
+	copy_page(swsusp_pg_dir, swapper_pg_dir);
 }
 #else /* !CONFIG_ACPI_SLEEP */
 static inline void save_pg_dir(void)
@@ -712,14 +713,14 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
 		highstart_pfn = max_low_pfn;
-	e820_register_active_regions(0, 0, highend_pfn);
+	memblock_x86_register_active_regions(0, 0, highend_pfn);
 	sparse_memory_present_with_active_regions(0);
 	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
 		pages_to_mb(highend_pfn - highstart_pfn));
 	num_physpages = highend_pfn;
 	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-	e820_register_active_regions(0, 0, max_low_pfn);
+	memblock_x86_register_active_regions(0, 0, max_low_pfn);
 	sparse_memory_present_with_active_regions(0);
 	num_physpages = max_low_pfn;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
@@ -750,68 +751,12 @@ static void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
-#ifndef CONFIG_NO_BOOTMEM
-static unsigned long __init setup_node_bootmem(int nodeid,
-				 unsigned long start_pfn,
-				 unsigned long end_pfn,
-				 unsigned long bootmap)
-{
-	unsigned long bootmap_size;
-
-	/* don't touch min_low_pfn */
-	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
-					 bootmap >> PAGE_SHIFT,
-					 start_pfn, end_pfn);
-	printk(KERN_INFO "  node %d low ram: %08lx - %08lx\n",
-		nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
-	printk(KERN_INFO "  node %d bootmap %08lx - %08lx\n",
-		 nodeid, bootmap, bootmap + bootmap_size);
-	free_bootmem_with_active_regions(nodeid, end_pfn);
-
-	return bootmap + bootmap_size;
-}
-#endif
-
 void __init setup_bootmem_allocator(void)
 {
-#ifndef CONFIG_NO_BOOTMEM
-	int nodeid;
-	unsigned long bootmap_size, bootmap;
-	/*
-	 * Initialize the boot-time allocator (with low memory only):
-	 */
-	bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
-				 PAGE_SIZE);
-	if (bootmap == -1L)
-		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
-#endif
-
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
 		 max_pfn_mapped<<PAGE_SHIFT);
 	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
 
-#ifndef CONFIG_NO_BOOTMEM
-	for_each_online_node(nodeid) {
-		 unsigned long start_pfn, end_pfn;
-
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-		start_pfn = node_start_pfn[nodeid];
-		end_pfn = node_end_pfn[nodeid];
-		if (start_pfn > max_low_pfn)
-			continue;
-		if (end_pfn > max_low_pfn)
-			end_pfn = max_low_pfn;
-#else
-		start_pfn = 0;
-		end_pfn = max_low_pfn;
-#endif
-		bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
-						 bootmap);
-	}
-#endif
-
 	after_bootmem = 1;
 }
 
@@ -1070,8 +1015,3 @@ void mark_rodata_ro(void)
 }
 #endif
 
-int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
-				   int flags)
-{
-	return reserve_bootmem(phys, len, flags);
-}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9a6674689a20..e545be0ebf34 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -21,6 +21,7 @@
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
 #include <linux/pfn.h>
@@ -52,8 +53,6 @@
 #include <asm/init.h>
 #include <linux/bootmem.h>
 
-static unsigned long dma_reserve __initdata;
-
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -98,6 +97,36 @@ static int __init nonx32_setup(char *str)
 __setup("noexec32=", nonx32_setup);
 
 /*
+ * When memory was added/removed make sure all the processes MM have
+ * suitable PGD entries in the local PGD level page.
+ */
+void sync_global_pgds(unsigned long start, unsigned long end)
+{
+       unsigned long address;
+
+       for (address = start; address <= end; address += PGDIR_SIZE) {
+	       const pgd_t *pgd_ref = pgd_offset_k(address);
+	       unsigned long flags;
+	       struct page *page;
+
+	       if (pgd_none(*pgd_ref))
+		       continue;
+
+	       spin_lock_irqsave(&pgd_lock, flags);
+	       list_for_each_entry(page, &pgd_list, lru) {
+		       pgd_t *pgd;
+		       pgd = (pgd_t *)page_address(page) + pgd_index(address);
+		       if (pgd_none(*pgd))
+			       set_pgd(pgd, *pgd_ref);
+		       else
+			       BUG_ON(pgd_page_vaddr(*pgd)
+					!= pgd_page_vaddr(*pgd_ref));
+	       }
+	       spin_unlock_irqrestore(&pgd_lock, flags);
+       }
+}
+
+/*
  * NOTE: This function is marked __ref because it calls __init function
  * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
  */
@@ -293,7 +322,7 @@ static __ref void *alloc_low_page(unsigned long *phys)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
-	memset(adr, 0, PAGE_SIZE);
+	clear_page(adr);
 	*phys  = pfn * PAGE_SIZE;
 	return adr;
 }
@@ -534,11 +563,13 @@ kernel_physical_mapping_init(unsigned long start,
 			     unsigned long end,
 			     unsigned long page_size_mask)
 {
-
+	bool pgd_changed = false;
 	unsigned long next, last_map_addr = end;
+	unsigned long addr;
 
 	start = (unsigned long)__va(start);
 	end = (unsigned long)__va(end);
+	addr = start;
 
 	for (; start < end; start = next) {
 		pgd_t *pgd = pgd_offset_k(start);
@@ -563,7 +594,12 @@ kernel_physical_mapping_init(unsigned long start,
 		spin_lock(&init_mm.page_table_lock);
 		pgd_populate(&init_mm, pgd, __va(pud_phys));
 		spin_unlock(&init_mm.page_table_lock);
+		pgd_changed = true;
 	}
+
+	if (pgd_changed)
+		sync_global_pgds(addr, end);
+
 	__flush_tlb_all();
 
 	return last_map_addr;
@@ -573,23 +609,7 @@ kernel_physical_mapping_init(unsigned long start,
 void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 				int acpi, int k8)
 {
-#ifndef CONFIG_NO_BOOTMEM
-	unsigned long bootmap_size, bootmap;
-
-	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
-				 PAGE_SIZE);
-	if (bootmap == -1L)
-		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
-	/* don't touch min_low_pfn */
-	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
-					 0, end_pfn);
-	e820_register_active_regions(0, start_pfn, end_pfn);
-	free_bootmem_with_active_regions(0, end_pfn);
-#else
-	e820_register_active_regions(0, start_pfn, end_pfn);
-#endif
+	memblock_x86_register_active_regions(0, start_pfn, end_pfn);
 }
 #endif
 
@@ -799,52 +819,6 @@ void mark_rodata_ro(void)
 
 #endif
 
-int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
-				   int flags)
-{
-#ifdef CONFIG_NUMA
-	int nid, next_nid;
-	int ret;
-#endif
-	unsigned long pfn = phys >> PAGE_SHIFT;
-
-	if (pfn >= max_pfn) {
-		/*
-		 * This can happen with kdump kernels when accessing
-		 * firmware tables:
-		 */
-		if (pfn < max_pfn_mapped)
-			return -EFAULT;
-
-		printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %lu\n",
-				phys, len);
-		return -EFAULT;
-	}
-
-	/* Should check here against the e820 map to avoid double free */
-#ifdef CONFIG_NUMA
-	nid = phys_to_nid(phys);
-	next_nid = phys_to_nid(phys + len - 1);
-	if (nid == next_nid)
-		ret = reserve_bootmem_node(NODE_DATA(nid), phys, len, flags);
-	else
-		ret = reserve_bootmem(phys, len, flags);
-
-	if (ret != 0)
-		return ret;
-
-#else
-	reserve_bootmem(phys, len, flags);
-#endif
-
-	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
-		dma_reserve += len / PAGE_SIZE;
-		set_dma_reserve(dma_reserve);
-	}
-
-	return 0;
-}
-
 int kern_addr_valid(unsigned long addr)
 {
 	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
@@ -1003,6 +977,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 		}
 
 	}
+	sync_global_pgds((unsigned long)start_page, end);
 	return 0;
 }
 
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 970ed579d4e4..804a3b6c6e14 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -11,6 +11,8 @@
 #include <linux/string.h>
 #include <linux/module.h>
 #include <linux/nodemask.h>
+#include <linux/memblock.h>
+
 #include <asm/io.h>
 #include <linux/pci_ids.h>
 #include <linux/acpi.h>
@@ -22,7 +24,7 @@
 #include <asm/numa.h>
 #include <asm/mpspec.h>
 #include <asm/apic.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 static struct bootnode __initdata nodes[8];
 static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;
@@ -54,8 +56,8 @@ static __init int find_northbridge(void)
 static __init void early_get_boot_cpu_id(void)
 {
 	/*
-	 * need to get boot_cpu_id so can use that to create apicid_to_node
-	 * in k8_scan_nodes()
+	 * need to get the APIC ID of the BSP so can use that to
+	 * create apicid_to_node in k8_scan_nodes()
 	 */
 #ifdef CONFIG_X86_MPPARSE
 	/*
@@ -212,7 +214,7 @@ int __init k8_scan_nodes(void)
 	bits = boot_cpu_data.x86_coreid_bits;
 	cores = (1<<bits);
 	apicid_base = 0;
-	/* need to get boot_cpu_id early for system with apicid lifting */
+	/* get the APIC ID of the BSP early for systems with apicid lifting */
 	early_get_boot_cpu_id();
 	if (boot_cpu_physical_apicid > 0) {
 		pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
@@ -222,7 +224,7 @@ int __init k8_scan_nodes(void)
 	for_each_node_mask(i, node_possible_map) {
 		int j;
 
-		e820_register_active_regions(i,
+		memblock_x86_register_active_regions(i,
 				nodes[i].start >> PAGE_SHIFT,
 				nodes[i].end >> PAGE_SHIFT);
 		for (j = apicid_base; j < cores + apicid_base; j++)
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
index 63c19e27aa6f..324aa3f07237 100644
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ b/arch/x86/mm/kmemcheck/opcode.c
@@ -9,7 +9,7 @@ static bool opcode_is_prefix(uint8_t b)
 		b == 0xf0 || b == 0xf2 || b == 0xf3
 		/* Group 2 */
 		|| b == 0x2e || b == 0x36 || b == 0x3e || b == 0x26
-		|| b == 0x64 || b == 0x65 || b == 0x2e || b == 0x3e
+		|| b == 0x64 || b == 0x65
 		/* Group 3 */
 		|| b == 0x66
 		/* Group 4 */
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
new file mode 100644
index 000000000000..50ecbc59757f
--- /dev/null
+++ b/arch/x86/mm/memblock.c
@@ -0,0 +1,354 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/bitops.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/range.h>
+
+/* Check for already reserved areas */
+static inline bool __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+{
+	struct memblock_region *r;
+	u64 addr = *addrp, last;
+	u64 size = *sizep;
+	bool changed = false;
+
+again:
+	last = addr + size;
+	for_each_memblock(reserved, r) {
+		if (last > r->base && addr < r->base) {
+			size = r->base - addr;
+			changed = true;
+			goto again;
+		}
+		if (last > (r->base + r->size) && addr < (r->base + r->size)) {
+			addr = round_up(r->base + r->size, align);
+			size = last - addr;
+			changed = true;
+			goto again;
+		}
+		if (last <= (r->base + r->size) && addr >= r->base) {
+			(*sizep)++;
+			return false;
+		}
+	}
+	if (changed) {
+		*addrp = addr;
+		*sizep = size;
+	}
+	return changed;
+}
+
+static u64 __init __memblock_x86_find_in_range_size(u64 ei_start, u64 ei_last, u64 start,
+			 u64 *sizep, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	*sizep = ei_last - addr;
+	while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
+		;
+	last = addr + *sizep;
+	if (last > ei_last)
+		goto out;
+
+	return addr;
+
+out:
+	return MEMBLOCK_ERROR;
+}
+
+/*
+ * Find next free range after start, and size is returned in *sizep
+ */
+u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
+{
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r) {
+		u64 ei_start = r->base;
+		u64 ei_last = ei_start + r->size;
+		u64 addr;
+
+		addr = __memblock_x86_find_in_range_size(ei_start, ei_last, start,
+					 sizep, align);
+
+		if (addr != MEMBLOCK_ERROR)
+			return addr;
+	}
+
+	return MEMBLOCK_ERROR;
+}
+
+static __init struct range *find_range_array(int count)
+{
+	u64 end, size, mem;
+	struct range *range;
+
+	size = sizeof(struct range) * count;
+	end = memblock.current_limit;
+
+	mem = memblock_find_in_range(0, end, size, sizeof(struct range));
+	if (mem == MEMBLOCK_ERROR)
+		panic("can not find more space for range array");
+
+	/*
+	 * This range is tempoaray, so don't reserve it, it will not be
+	 * overlapped because We will not alloccate new buffer before
+	 * We discard this one
+	 */
+	range = __va(mem);
+	memset(range, 0, size);
+
+	return range;
+}
+
+static void __init memblock_x86_subtract_reserved(struct range *range, int az)
+{
+	u64 final_start, final_end;
+	struct memblock_region *r;
+
+	/* Take out region array itself at first*/
+	memblock_free_reserved_regions();
+
+	memblock_dbg("Subtract (%ld early reservations)\n", memblock.reserved.cnt);
+
+	for_each_memblock(reserved, r) {
+		memblock_dbg("  [%010llx-%010llx]\n", (u64)r->base, (u64)r->base + r->size - 1);
+		final_start = PFN_DOWN(r->base);
+		final_end = PFN_UP(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		subtract_range(range, az, final_start, final_end);
+	}
+
+	/* Put region array back ? */
+	memblock_reserve_reserved_regions();
+}
+
+struct count_data {
+	int nr;
+};
+
+static int __init count_work_fn(unsigned long start_pfn,
+				unsigned long end_pfn, void *datax)
+{
+	struct count_data *data = datax;
+
+	data->nr++;
+
+	return 0;
+}
+
+static int __init count_early_node_map(int nodeid)
+{
+	struct count_data data;
+
+	data.nr = 0;
+	work_with_active_regions(nodeid, count_work_fn, &data);
+
+	return data.nr;
+}
+
+int __init get_free_all_memory_range(struct range **rangep, int nodeid)
+{
+	int count;
+	struct range *range;
+	int nr_range;
+
+	count = (memblock.reserved.cnt + count_early_node_map(nodeid)) * 2;
+
+	range = find_range_array(count);
+	nr_range = 0;
+
+	/*
+	 * Use early_node_map[] and memblock.reserved.region to get range array
+	 * at first
+	 */
+	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+#ifdef CONFIG_X86_32
+	subtract_range(range, count, max_low_pfn, -1ULL);
+#endif
+	memblock_x86_subtract_reserved(range, count);
+	nr_range = clean_sort_range(range, count);
+
+	*rangep = range;
+	return nr_range;
+}
+
+static u64 __init __memblock_x86_memory_in_range(u64 addr, u64 limit, bool get_free)
+{
+	int i, count;
+	struct range *range;
+	int nr_range;
+	u64 final_start, final_end;
+	u64 free_size;
+	struct memblock_region *r;
+
+	count = (memblock.reserved.cnt + memblock.memory.cnt) * 2;
+
+	range = find_range_array(count);
+	nr_range = 0;
+
+	addr = PFN_UP(addr);
+	limit = PFN_DOWN(limit);
+
+	for_each_memblock(memory, r) {
+		final_start = PFN_UP(r->base);
+		final_end = PFN_DOWN(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		if (final_start >= limit || final_end <= addr)
+			continue;
+
+		nr_range = add_range(range, count, nr_range, final_start, final_end);
+	}
+	subtract_range(range, count, 0, addr);
+	subtract_range(range, count, limit, -1ULL);
+
+	/* Subtract memblock.reserved.region in range ? */
+	if (!get_free)
+		goto sort_and_count_them;
+	for_each_memblock(reserved, r) {
+		final_start = PFN_DOWN(r->base);
+		final_end = PFN_UP(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		if (final_start >= limit || final_end <= addr)
+			continue;
+
+		subtract_range(range, count, final_start, final_end);
+	}
+
+sort_and_count_them:
+	nr_range = clean_sort_range(range, count);
+
+	free_size = 0;
+	for (i = 0; i < nr_range; i++)
+		free_size += range[i].end - range[i].start;
+
+	return free_size << PAGE_SHIFT;
+}
+
+u64 __init memblock_x86_free_memory_in_range(u64 addr, u64 limit)
+{
+	return __memblock_x86_memory_in_range(addr, limit, true);
+}
+
+u64 __init memblock_x86_memory_in_range(u64 addr, u64 limit)
+{
+	return __memblock_x86_memory_in_range(addr, limit, false);
+}
+
+void __init memblock_x86_reserve_range(u64 start, u64 end, char *name)
+{
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "memblock_x86_reserve_range: wrong range [%#llx, %#llx)\n", start, end))
+		return;
+
+	memblock_dbg("    memblock_x86_reserve_range: [%#010llx-%#010llx] %16s\n", start, end - 1, name);
+
+	memblock_reserve(start, end - start);
+}
+
+void __init memblock_x86_free_range(u64 start, u64 end)
+{
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "memblock_x86_free_range: wrong range [%#llx, %#llx)\n", start, end))
+		return;
+
+	memblock_dbg("       memblock_x86_free_range: [%#010llx-%#010llx]\n", start, end - 1);
+
+	memblock_free(start, end - start);
+}
+
+/*
+ * Need to call this function after memblock_x86_register_active_regions,
+ * so early_node_map[] is filled already.
+ */
+u64 __init memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align)
+{
+	u64 addr;
+	addr = find_memory_core_early(nid, size, align, start, end);
+	if (addr != MEMBLOCK_ERROR)
+		return addr;
+
+	/* Fallback, should already have start end within node range */
+	return memblock_find_in_range(start, end, size, align);
+}
+
+/*
+ * Finds an active region in the address range from start_pfn to last_pfn and
+ * returns its range in ei_startpfn and ei_endpfn for the memblock entry.
+ */
+static int __init memblock_x86_find_active_region(const struct memblock_region *ei,
+				  unsigned long start_pfn,
+				  unsigned long last_pfn,
+				  unsigned long *ei_startpfn,
+				  unsigned long *ei_endpfn)
+{
+	u64 align = PAGE_SIZE;
+
+	*ei_startpfn = round_up(ei->base, align) >> PAGE_SHIFT;
+	*ei_endpfn = round_down(ei->base + ei->size, align) >> PAGE_SHIFT;
+
+	/* Skip map entries smaller than a page */
+	if (*ei_startpfn >= *ei_endpfn)
+		return 0;
+
+	/* Skip if map is outside the node */
+	if (*ei_endpfn <= start_pfn || *ei_startpfn >= last_pfn)
+		return 0;
+
+	/* Check for overlaps */
+	if (*ei_startpfn < start_pfn)
+		*ei_startpfn = start_pfn;
+	if (*ei_endpfn > last_pfn)
+		*ei_endpfn = last_pfn;
+
+	return 1;
+}
+
+/* Walk the memblock.memory map and register active regions within a node */
+void __init memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long last_pfn)
+{
+	unsigned long ei_startpfn;
+	unsigned long ei_endpfn;
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r)
+		if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
+					   &ei_startpfn, &ei_endpfn))
+			add_active_range(nid, ei_startpfn, ei_endpfn);
+}
+
+/*
+ * Find the hole size (in bytes) in the memory range.
+ * @start: starting address of the memory range to scan
+ * @end: ending address of the memory range to scan
+ */
+u64 __init memblock_x86_hole_size(u64 start, u64 end)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long last_pfn = end >> PAGE_SHIFT;
+	unsigned long ei_startpfn, ei_endpfn, ram = 0;
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r)
+		if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
+					   &ei_startpfn, &ei_endpfn))
+			ram += ei_endpfn - ei_startpfn;
+
+	return end - start - ((u64)ram << PAGE_SHIFT);
+}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 18d244f70205..92faf3a1c53e 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -6,8 +6,7 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/pfn.h>
-
-#include <asm/e820.h>
+#include <linux/memblock.h>
 
 static u64 patterns[] __initdata = {
 	0,
@@ -35,7 +34,7 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
 	       (unsigned long long) pattern,
 	       (unsigned long long) start_bad,
 	       (unsigned long long) end_bad);
-	reserve_early(start_bad, end_bad, "BAD RAM");
+	memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM");
 }
 
 static void __init memtest(u64 pattern, u64 start_phys, u64 size)
@@ -74,7 +73,7 @@ static void __init do_one_pass(u64 pattern, u64 start, u64 end)
 	u64 size = 0;
 
 	while (start < end) {
-		start = find_e820_area_size(start, &size, 1);
+		start = memblock_x86_find_in_range_size(start, &size, 1);
 
 		/* done ? */
 		if (start >= end)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 809baaaf48b1..70ddeb75ba25 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
 
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/highmem.h>
 #include <linux/initrd.h>
@@ -120,7 +121,7 @@ int __init get_memcfg_numa_flat(void)
 
 	node_start_pfn[0] = 0;
 	node_end_pfn[0] = max_pfn;
-	e820_register_active_regions(0, 0, max_pfn);
+	memblock_x86_register_active_regions(0, 0, max_pfn);
 	memory_present(0, 0, max_pfn);
 	node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn);
 
@@ -161,14 +162,14 @@ static void __init allocate_pgdat(int nid)
 		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
 	else {
 		unsigned long pgdat_phys;
-		pgdat_phys = find_e820_area(min_low_pfn<<PAGE_SHIFT,
+		pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT,
 				 max_pfn_mapped<<PAGE_SHIFT,
 				 sizeof(pg_data_t),
 				 PAGE_SIZE);
 		NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT));
 		memset(buf, 0, sizeof(buf));
 		sprintf(buf, "NODE_DATA %d",  nid);
-		reserve_early(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
+		memblock_x86_reserve_range(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
 	}
 	printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n",
 		nid, (unsigned long)NODE_DATA(nid));
@@ -291,15 +292,15 @@ static __init unsigned long calculate_numa_remap_pages(void)
 						 PTRS_PER_PTE);
 		node_kva_target <<= PAGE_SHIFT;
 		do {
-			node_kva_final = find_e820_area(node_kva_target,
+			node_kva_final = memblock_find_in_range(node_kva_target,
 					((u64)node_end_pfn[nid])<<PAGE_SHIFT,
 						((u64)size)<<PAGE_SHIFT,
 						LARGE_PAGE_BYTES);
 			node_kva_target -= LARGE_PAGE_BYTES;
-		} while (node_kva_final == -1ULL &&
+		} while (node_kva_final == MEMBLOCK_ERROR &&
 			 (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid]));
 
-		if (node_kva_final == -1ULL)
+		if (node_kva_final == MEMBLOCK_ERROR)
 			panic("Can not get kva ram\n");
 
 		node_remap_size[nid] = size;
@@ -318,9 +319,9 @@ static __init unsigned long calculate_numa_remap_pages(void)
 		 *  but we could have some hole in high memory, and it will only
 		 *  check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide
 		 *  to use it as free.
-		 *  So reserve_early here, hope we don't run out of that array
+		 *  So memblock_x86_reserve_range here, hope we don't run out of that array
 		 */
-		reserve_early(node_kva_final,
+		memblock_x86_reserve_range(node_kva_final,
 			      node_kva_final+(((u64)size)<<PAGE_SHIFT),
 			      "KVA RAM");
 
@@ -367,14 +368,14 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 
 	kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
 	do {
-		kva_start_pfn = find_e820_area(kva_target_pfn<<PAGE_SHIFT,
+		kva_start_pfn = memblock_find_in_range(kva_target_pfn<<PAGE_SHIFT,
 					max_low_pfn<<PAGE_SHIFT,
 					kva_pages<<PAGE_SHIFT,
 					PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT;
 		kva_target_pfn -= PTRS_PER_PTE;
-	} while (kva_start_pfn == -1UL && kva_target_pfn > min_low_pfn);
+	} while (kva_start_pfn == MEMBLOCK_ERROR && kva_target_pfn > min_low_pfn);
 
-	if (kva_start_pfn == -1UL)
+	if (kva_start_pfn == MEMBLOCK_ERROR)
 		panic("Can not get kva space\n");
 
 	printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n",
@@ -382,7 +383,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	printk(KERN_INFO "max_pfn = %lx\n", max_pfn);
 
 	/* avoid clash with initrd */
-	reserve_early(kva_start_pfn<<PAGE_SHIFT,
+	memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT,
 		      (kva_start_pfn + kva_pages)<<PAGE_SHIFT,
 		     "KVA PG");
 #ifdef CONFIG_HIGHMEM
@@ -419,9 +420,6 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	for_each_online_node(nid) {
 		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
 		NODE_DATA(nid)->node_id = nid;
-#ifndef CONFIG_NO_BOOTMEM
-		NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
-#endif
 	}
 
 	setup_bootmem_allocator();
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index a7bcc23ef96c..60f498511dd6 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -7,6 +7,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
@@ -18,7 +19,7 @@
 #include <asm/dma.h>
 #include <asm/numa.h>
 #include <asm/acpi.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
@@ -86,16 +87,16 @@ static int __init allocate_cachealigned_memnodemap(void)
 
 	addr = 0x8000;
 	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
-	nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT,
+	nodemap_addr = memblock_find_in_range(addr, max_pfn<<PAGE_SHIFT,
 				      nodemap_size, L1_CACHE_BYTES);
-	if (nodemap_addr == -1UL) {
+	if (nodemap_addr == MEMBLOCK_ERROR) {
 		printk(KERN_ERR
 		       "NUMA: Unable to allocate Memory to Node hash map\n");
 		nodemap_addr = nodemap_size = 0;
 		return -1;
 	}
 	memnodemap = phys_to_virt(nodemap_addr);
-	reserve_early(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
+	memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
 
 	printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
 	       nodemap_addr, nodemap_addr + nodemap_size);
@@ -171,8 +172,8 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 	if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
 	    end > (MAX_DMA32_PFN<<PAGE_SHIFT))
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, align);
-	if (mem != -1L)
+	mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
+	if (mem != MEMBLOCK_ERROR)
 		return __va(mem);
 
 	/* extend the search scope */
@@ -181,8 +182,8 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
 	else
 		start = MAX_DMA_PFN<<PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, align);
-	if (mem != -1L)
+	mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
+	if (mem != MEMBLOCK_ERROR)
 		return __va(mem);
 
 	printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
@@ -198,10 +199,6 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	unsigned long start_pfn, last_pfn, nodedata_phys;
 	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
-#ifndef CONFIG_NO_BOOTMEM
-	unsigned long bootmap_start, bootmap_pages, bootmap_size;
-	void *bootmap;
-#endif
 
 	if (!end)
 		return;
@@ -226,7 +223,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	if (node_data[nodeid] == NULL)
 		return;
 	nodedata_phys = __pa(node_data[nodeid]);
-	reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
+	memblock_x86_reserve_range(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
 	printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
 		nodedata_phys + pgdat_size - 1);
 	nid = phys_to_nid(nodedata_phys);
@@ -238,47 +235,6 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
 	NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
 
-#ifndef CONFIG_NO_BOOTMEM
-	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
-
-	/*
-	 * Find a place for the bootmem map
-	 * nodedata_phys could be on other nodes by alloc_bootmem,
-	 * so need to sure bootmap_start not to be small, otherwise
-	 * early_node_mem will get that with find_e820_area instead
-	 * of alloc_bootmem, that could clash with reserved range
-	 */
-	bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
-	bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
-	/*
-	 * SMP_CACHE_BYTES could be enough, but init_bootmem_node like
-	 * to use that to align to PAGE_SIZE
-	 */
-	bootmap = early_node_mem(nodeid, bootmap_start, end,
-				 bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
-	if (bootmap == NULL)  {
-		free_early(nodedata_phys, nodedata_phys + pgdat_size);
-		node_data[nodeid] = NULL;
-		return;
-	}
-	bootmap_start = __pa(bootmap);
-	reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
-			"BOOTMAP");
-
-	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
-					 bootmap_start >> PAGE_SHIFT,
-					 start_pfn, last_pfn);
-
-	printk(KERN_INFO "  bootmap [%016lx -  %016lx] pages %lx\n",
-		 bootmap_start, bootmap_start + bootmap_size - 1,
-		 bootmap_pages);
-	nid = phys_to_nid(bootmap_start);
-	if (nid != nodeid)
-		printk(KERN_INFO "    bootmap(%d) on node %d\n", nodeid, nid);
-
-	free_bootmem_with_active_regions(nodeid, end);
-#endif
-
 	node_set_online(nodeid);
 }
 
@@ -416,7 +372,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 		nr_nodes = MAX_NUMNODES;
 	}
 
-	size = (max_addr - addr - e820_hole_size(addr, max_addr)) / nr_nodes;
+	size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes;
 	/*
 	 * Calculate the number of big nodes that can be allocated as a result
 	 * of consolidating the remainder.
@@ -452,7 +408,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * non-reserved memory is less than the per-node size.
 			 */
 			while (end - physnodes[i].start -
-				e820_hole_size(physnodes[i].start, end) < size) {
+				memblock_x86_hole_size(physnodes[i].start, end) < size) {
 				end += FAKE_NODE_MIN_SIZE;
 				if (end > physnodes[i].end) {
 					end = physnodes[i].end;
@@ -466,7 +422,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -475,7 +431,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    memblock_x86_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -503,7 +459,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 {
 	u64 end = start + size;
 
-	while (end - start - e820_hole_size(start, end) < size) {
+	while (end - start - memblock_x86_hole_size(start, end) < size) {
 		end += FAKE_NODE_MIN_SIZE;
 		if (end > max_addr) {
 			end = max_addr;
@@ -532,7 +488,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 	 * creates a uniform distribution of node sizes across the entire
 	 * machine (but not necessarily over physical nodes).
 	 */
-	min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) /
+	min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
 						MAX_NUMNODES;
 	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
 	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
@@ -565,7 +521,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -574,7 +530,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    memblock_x86_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -638,7 +594,7 @@ static int __init numa_emulation(unsigned long start_pfn,
 	 */
 	remove_all_active_ranges();
 	for_each_node_mask(i, node_possible_map) {
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+		memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 	}
@@ -691,7 +647,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
 	node_set(0, node_possible_map);
 	for (i = 0; i < nr_cpu_ids; i++)
 		numa_set_node(i, 0);
-	e820_register_active_regions(0, start_pfn, last_pfn);
+	memblock_x86_register_active_regions(0, start_pfn, last_pfn);
 	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT);
 }
 
@@ -703,9 +659,7 @@ unsigned long __init numa_free_all_bootmem(void)
 	for_each_online_node(i)
 		pages += free_all_bootmem_node(NODE_DATA(i));
 
-#ifdef CONFIG_NO_BOOTMEM
 	pages += free_all_memory_core_early(MAX_NUMNODES);
-#endif
 
 	return pages;
 }
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 5c4ee422590e..a96023e872ae 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -98,10 +98,6 @@ static void pgd_ctor(pgd_t *pgd)
 		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
 				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
 				KERNEL_PGD_PTRS);
-		paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT,
-					 __pa(swapper_pg_dir) >> PAGE_SHIFT,
-					 KERNEL_PGD_BOUNDARY,
-					 KERNEL_PGD_PTRS);
 	}
 
 	/* list required to sync kernel mapping updates */
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 9324f13492d5..a17dffd136c1 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -25,6 +25,7 @@
  */
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/acpi.h>
 #include <linux/nodemask.h>
@@ -264,7 +265,7 @@ int __init get_memcfg_from_srat(void)
 		if (node_read_chunk(chunk->nid, chunk))
 			continue;
 
-		e820_register_active_regions(chunk->nid, chunk->start_pfn,
+		memblock_x86_register_active_regions(chunk->nid, chunk->start_pfn,
 					     min(chunk->end_pfn, max_pfn));
 	}
 	/* for out of order entries in SRAT */
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index f9897f7a9ef1..7f44eb62a5e9 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/topology.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <asm/proto.h>
 #include <asm/numa.h>
@@ -98,15 +99,15 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 	unsigned long phys;
 
 	length = slit->header.length;
-	phys = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, length,
+	phys = memblock_find_in_range(0, max_pfn_mapped<<PAGE_SHIFT, length,
 		 PAGE_SIZE);
 
-	if (phys == -1L)
+	if (phys == MEMBLOCK_ERROR)
 		panic(" Can not save slit!\n");
 
 	acpi_slit = __va(phys);
 	memcpy(acpi_slit, slit, length);
-	reserve_early(phys, phys + length, "ACPI SLIT");
+	memblock_x86_reserve_range(phys, phys + length, "ACPI SLIT");
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
@@ -324,7 +325,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 			pxmram = 0;
 	}
 
-	e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
+	e820ram = max_pfn - (memblock_x86_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
 	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
 	if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
 		printk(KERN_ERR
@@ -421,7 +422,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 	}
 
 	for_each_node_mask(i, nodes_parsed)
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+		memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
 	/* for out of order entries in SRAT */
 	sort_node_map();
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 42086ac406af..94fe465b7730 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -45,6 +45,7 @@
 #include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <linux/gfp.h>
+#include <linux/memblock.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -1814,7 +1815,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 	__xen_write_cr3(true, __pa(pgd));
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 
-	reserve_early(__pa(xen_start_info->pt_base),
+	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
@@ -1852,7 +1853,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 
 	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
 
-	reserve_early(__pa(xen_start_info->pt_base),
+	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
@@ -1969,7 +1970,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.alloc_pte = xen_alloc_pte_init,
 	.release_pte = xen_release_pte_init,
 	.alloc_pmd = xen_alloc_pmd_init,
-	.alloc_pmd_clone = paravirt_nop,
 	.release_pmd = xen_release_pmd_init,
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index a013ec9d0c54..22471001b74c 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -5,6 +5,7 @@
 
 #include <asm/xen/hypervisor.h>
 #include <xen/xen.h>
+#include <asm/iommu_table.h>
 
 int xen_swiotlb __read_mostly;
 
@@ -56,3 +57,7 @@ void __init pci_xen_swiotlb_init(void)
 		dma_ops = &xen_swiotlb_dma_ops;
 	}
 }
+IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
+		  0,
+		  pci_xen_swiotlb_init,
+		  0);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 328b00305426..9729c903404b 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
+#include <linux/memblock.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
@@ -129,7 +130,7 @@ char * __init xen_memory_setup(void)
 	 *  - xen_start_info
 	 * See comment above "struct start_info" in <xen/interface/xen.h>
 	 */
-	reserve_early(__pa(xen_start_info->mfn_list),
+	memblock_x86_reserve_range(__pa(xen_start_info->mfn_list),
 		      __pa(xen_start_info->pt_base),
 			"XEN START INFO");
 
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index c64a5d387de5..87508886cbbd 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -92,7 +92,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 6b115f6c4313..6afceb3d4034 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -30,18 +30,13 @@
 #include <linux/slab.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
+#include <asm/mwait.h>
 
 #define ACPI_PROCESSOR_AGGREGATOR_CLASS	"acpi_pad"
 #define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator"
 #define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80
 static DEFINE_MUTEX(isolated_cpus_lock);
 
-#define MWAIT_SUBSTATE_MASK	(0xf)
-#define MWAIT_CSTATE_MASK	(0xf)
-#define MWAIT_SUBSTATE_SIZE	(4)
-#define CPUID_MWAIT_LEAF (5)
-#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
-#define CPUID5_ECX_INTERRUPT_BREAK	(0x2)
 static unsigned long power_saving_mwait_eax;
 
 static unsigned char tsc_detected_unstable;
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 9fc630ce1ddb..f6f37a05a0c3 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -45,7 +45,8 @@ static ssize_t show_##name(struct sys_device *dev,		\
 	return sprintf(buf, "%d\n", topology_##name(cpu));	\
 }
 
-#if defined(topology_thread_cpumask) || defined(topology_core_cpumask)
+#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
+    defined(topology_book_cpumask)
 static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
 {
 	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
@@ -114,6 +115,14 @@ define_siblings_show_func(core_cpumask);
 define_one_ro_named(core_siblings, show_core_cpumask);
 define_one_ro_named(core_siblings_list, show_core_cpumask_list);
 
+#ifdef CONFIG_SCHED_BOOK
+define_id_show_func(book_id);
+define_one_ro(book_id);
+define_siblings_show_func(book_cpumask);
+define_one_ro_named(book_siblings, show_book_cpumask);
+define_one_ro_named(book_siblings_list, show_book_cpumask_list);
+#endif
+
 static struct attribute *default_attrs[] = {
 	&attr_physical_package_id.attr,
 	&attr_core_id.attr,
@@ -121,6 +130,11 @@ static struct attribute *default_attrs[] = {
 	&attr_thread_siblings_list.attr,
 	&attr_core_siblings.attr,
 	&attr_core_siblings_list.attr,
+#ifdef CONFIG_SCHED_BOOK
+	&attr_book_id.attr,
+	&attr_book_siblings.attr,
+	&attr_book_siblings_list.attr,
+#endif
 	NULL
 };
 
diff --git a/drivers/char/agp/Kconfig b/drivers/char/agp/Kconfig
index 4b66c69eaf57..5ddf67e76f8b 100644
--- a/drivers/char/agp/Kconfig
+++ b/drivers/char/agp/Kconfig
@@ -57,7 +57,7 @@ config AGP_AMD
 
 config AGP_AMD64
 	tristate "AMD Opteron/Athlon64 on-CPU GART support"
-	depends on AGP && X86 && K8_NB
+	depends on AGP && X86 && AMD_NB
 	help
 	  This option gives you AGP support for the GLX component of
 	  X using the on-CPU northbridge of the AMD Athlon64/Opteron CPUs.
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index 70312da4c968..42396df55556 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -15,7 +15,7 @@
 #include <linux/mmzone.h>
 #include <asm/page.h>		/* PAGE_SIZE */
 #include <asm/e820.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/gart.h>
 #include "agp.h"
 
@@ -124,7 +124,7 @@ static int amd64_fetch_size(void)
 	u32 temp;
 	struct aper_size_info_32 *values;
 
-	dev = k8_northbridges[0];
+	dev = k8_northbridges.nb_misc[0];
 	if (dev==NULL)
 		return 0;
 
@@ -181,10 +181,14 @@ static int amd_8151_configure(void)
 	unsigned long gatt_bus = virt_to_phys(agp_bridge->gatt_table_real);
 	int i;
 
+	if (!k8_northbridges.gart_supported)
+		return 0;
+
 	/* Configure AGP regs in each x86-64 host bridge. */
-        for (i = 0; i < num_k8_northbridges; i++) {
+	for (i = 0; i < k8_northbridges.num; i++) {
 		agp_bridge->gart_bus_addr =
-				amd64_configure(k8_northbridges[i], gatt_bus);
+				amd64_configure(k8_northbridges.nb_misc[i],
+						gatt_bus);
 	}
 	k8_flush_garts();
 	return 0;
@@ -195,11 +199,15 @@ static void amd64_cleanup(void)
 {
 	u32 tmp;
 	int i;
-        for (i = 0; i < num_k8_northbridges; i++) {
-		struct pci_dev *dev = k8_northbridges[i];
+
+	if (!k8_northbridges.gart_supported)
+		return;
+
+	for (i = 0; i < k8_northbridges.num; i++) {
+		struct pci_dev *dev = k8_northbridges.nb_misc[i];
 		/* disable gart translation */
 		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &tmp);
-		tmp &= ~AMD64_GARTEN;
+		tmp &= ~GARTEN;
 		pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, tmp);
 	}
 }
@@ -313,22 +321,25 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp,
 	if (order < 0 || !agp_aperture_valid(aper, (32*1024*1024)<<order))
 		return -1;
 
-	pci_write_config_dword(nb, AMD64_GARTAPERTURECTL, order << 1);
+	gart_set_size_and_enable(nb, order);
 	pci_write_config_dword(nb, AMD64_GARTAPERTUREBASE, aper >> 25);
 
 	return 0;
 }
 
-static __devinit int cache_nbs (struct pci_dev *pdev, u32 cap_ptr)
+static __devinit int cache_nbs(struct pci_dev *pdev, u32 cap_ptr)
 {
 	int i;
 
 	if (cache_k8_northbridges() < 0)
 		return -ENODEV;
 
+	if (!k8_northbridges.gart_supported)
+		return -ENODEV;
+
 	i = 0;
-	for (i = 0; i < num_k8_northbridges; i++) {
-		struct pci_dev *dev = k8_northbridges[i];
+	for (i = 0; i < k8_northbridges.num; i++) {
+		struct pci_dev *dev = k8_northbridges.nb_misc[i];
 		if (fix_northbridge(dev, pdev, cap_ptr) < 0) {
 			dev_err(&dev->dev, "no usable aperture found\n");
 #ifdef __x86_64__
@@ -405,7 +416,8 @@ static int __devinit uli_agp_init(struct pci_dev *pdev)
 	}
 
 	/* shadow x86-64 registers into ULi registers */
-	pci_read_config_dword (k8_northbridges[0], AMD64_GARTAPERTUREBASE, &httfea);
+	pci_read_config_dword (k8_northbridges.nb_misc[0], AMD64_GARTAPERTUREBASE,
+			       &httfea);
 
 	/* if x86-64 aperture base is beyond 4G, exit here */
 	if ((httfea & 0x7fff) >> (32 - 25)) {
@@ -472,7 +484,8 @@ static int nforce3_agp_init(struct pci_dev *pdev)
 	pci_write_config_dword(dev1, NVIDIA_X86_64_1_APSIZE, tmp);
 
 	/* shadow x86-64 registers into NVIDIA registers */
-	pci_read_config_dword (k8_northbridges[0], AMD64_GARTAPERTUREBASE, &apbase);
+	pci_read_config_dword (k8_northbridges.nb_misc[0], AMD64_GARTAPERTUREBASE,
+			       &apbase);
 
 	/* if x86-64 aperture base is beyond 4G, exit here */
 	if ( (apbase & 0x7fff) >> (32 - 25) ) {
diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c
index 78235ceccfa1..4956f1c8f9d5 100644
--- a/drivers/char/agp/generic.c
+++ b/drivers/char/agp/generic.c
@@ -976,7 +976,9 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 
 	bridge->driver->cache_flush();
 #ifdef CONFIG_X86
-	set_memory_uc((unsigned long)table, 1 << page_order);
+	if (set_memory_uc((unsigned long)table, 1 << page_order))
+		printk(KERN_WARNING "Could not set GATT table memory to UC!");
+
 	bridge->gatt_table = (void *)table;
 #else
 	bridge->gatt_table = ioremap_nocache(virt_to_phys(table),
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 4573ccc11f93..708c2282db9f 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -66,7 +66,7 @@ config EDAC_MCE
 
 config EDAC_AMD64
 	tristate "AMD64 (Opteron, Athlon64) K8, F10h, F11h"
-	depends on EDAC_MM_EDAC && K8_NB && X86_64 && PCI && EDAC_DECODE_MCE
+	depends on EDAC_MM_EDAC && AMD_NB && X86_64 && PCI && EDAC_DECODE_MCE
 	help
 	  Support for error detection and correction on the AMD 64
 	  Families of Memory Controllers (K8, F10h and F11h)
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index e7d5d6b5dcf6..09fcc5282327 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1,5 +1,5 @@
 #include "amd64_edac.h"
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 static struct edac_pci_ctl_info *amd64_ctl_pci;
 
@@ -2927,7 +2927,7 @@ static int __init amd64_edac_init(void)
 	 * to finish initialization of the MC instances.
 	 */
 	err = -ENODEV;
-	for (nb = 0; nb < num_k8_northbridges; nb++) {
+	for (nb = 0; nb < k8_northbridges.num; nb++) {
 		if (!pvt_lookup[nb])
 			continue;
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 0906fc5b69b9..d0e42e05c807 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -59,18 +59,11 @@
 #include <linux/hrtimer.h>	/* ktime_get_real() */
 #include <trace/events/power.h>
 #include <linux/sched.h>
+#include <asm/mwait.h>
 
 #define INTEL_IDLE_VERSION "0.4"
 #define PREFIX "intel_idle: "
 
-#define MWAIT_SUBSTATE_MASK	(0xf)
-#define MWAIT_CSTATE_MASK	(0xf)
-#define MWAIT_SUBSTATE_SIZE	(4)
-#define MWAIT_MAX_NUM_CSTATES	8
-#define CPUID_MWAIT_LEAF (5)
-#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
-#define CPUID5_ECX_INTERRUPT_BREAK	(0x2)
-
 static struct cpuidle_driver intel_idle_driver = {
 	.name = "intel_idle",
 	.owner = THIS_MODULE,
diff --git a/drivers/isdn/act2000/act2000.h b/drivers/isdn/act2000/act2000.h
index d4c50512a1ff..88c9423500d8 100644
--- a/drivers/isdn/act2000/act2000.h
+++ b/drivers/isdn/act2000/act2000.h
@@ -141,9 +141,9 @@ typedef struct irq_data_isa {
 	__u8            rcvhdr[8];
 } irq_data_isa;
 
-typedef union irq_data {
+typedef union act2000_irq_data {
 	irq_data_isa isa;
-} irq_data;
+} act2000_irq_data;
 
 /*
  * Per card driver data
@@ -176,7 +176,7 @@ typedef struct act2000_card {
 	char   *status_buf_read;
 	char   *status_buf_write;
 	char   *status_buf_end;
-	irq_data idat;			/* Data used for IRQ handler        */
+	act2000_irq_data idat;		/* Data used for IRQ handler        */
 	isdn_if interface;		/* Interface to upper layer         */
 	char regname[35];		/* Name used for request_region     */
 } act2000_card;
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index 097f24d8bceb..61c86642407c 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -78,7 +78,7 @@ struct sih {
 	u8	irq_lines;		/* number of supported irq lines */
 
 	/* SIR ignored -- set interrupt, for testing only */
-	struct irq_data {
+	struct sih_irq_data {
 		u8	isr_offset;
 		u8	imr_offset;
 	} mask[2];
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 0a19708074c2..4ef56a0920a7 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -36,6 +36,7 @@
 #include <linux/tboot.h>
 #include <linux/dmi.h>
 #include <linux/slab.h>
+#include <asm/iommu_table.h>
 
 #define PREFIX "DMAR: "
 
@@ -687,7 +688,7 @@ failed:
 	return 0;
 }
 
-void __init detect_intel_iommu(void)
+int __init detect_intel_iommu(void)
 {
 	int ret;
 
@@ -723,6 +724,8 @@ void __init detect_intel_iommu(void)
 	}
 	early_acpi_os_unmap_memory(dmar_tbl, dmar_tbl_size);
 	dmar_tbl = NULL;
+
+	return ret ? 1 : -ENODEV;
 }
 
 
@@ -1455,3 +1458,4 @@ int __init dmar_ir_support(void)
 		return 0;
 	return dmar->flags & 0x1;
 }
+IOMMU_INIT_POST(detect_intel_iommu);
diff --git a/drivers/video/omap2/vram.c b/drivers/video/omap2/vram.c
index 37557b60c171..dba46f2256aa 100644
--- a/drivers/video/omap2/vram.c
+++ b/drivers/video/omap2/vram.c
@@ -564,12 +564,8 @@ void __init omap_vram_reserve_sdram_memblock(void)
 	size = PAGE_ALIGN(size);
 
 	if (paddr) {
-		struct memblock_property res;
-
-		res.base = paddr;
-		res.size = size;
-		if ((paddr & ~PAGE_MASK) || memblock_find(&res) ||
-		    res.base != paddr || res.size != size) {
+		if ((paddr & ~PAGE_MASK) ||
+		    !memblock_region_is_memory(paddr, size)) {
 			pr_err("Illegal SDRAM region for VRAM\n");
 			return;
 		}
diff --git a/include/asm-generic/hardirq.h b/include/asm-generic/hardirq.h
index 62f59080e5cc..04d0a977cd43 100644
--- a/include/asm-generic/hardirq.h
+++ b/include/asm-generic/hardirq.h
@@ -3,13 +3,13 @@
 
 #include <linux/cache.h>
 #include <linux/threads.h>
-#include <linux/irq.h>
 
 typedef struct {
 	unsigned int __softirq_pending;
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+#include <linux/irq.h>
 
 #ifndef ack_bad_irq
 static inline void ack_bad_irq(unsigned int irq)
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 9c7ea63729de..6f3c6ae4fe03 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -129,6 +129,10 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
 #define move_pte(pte, prot, old_addr, new_addr)	(pte)
 #endif
 
+#ifndef flush_tlb_fix_spurious_fault
+#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
+#endif
+
 #ifndef pgprot_noncached
 #define pgprot_noncached(prot)	(prot)
 #endif
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 946ffa261f15..688109cc9b89 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -220,6 +220,8 @@
 									\
 	BUG_TABLE							\
 									\
+	JUMP_TABLE							\
+									\
 	/* PCI quirks */						\
 	.pci_fixup        : AT(ADDR(.pci_fixup) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start_pci_fixups_early) = .;		\
@@ -563,6 +565,14 @@
 #define BUG_TABLE
 #endif
 
+#define JUMP_TABLE							\
+	. = ALIGN(8);							\
+	__jump_table : AT(ADDR(__jump_table) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(__start___jump_table) = .;		\
+		*(__jump_table)						\
+		VMLINUX_SYMBOL(__stop___jump_table) = .;		\
+	}
+
 #ifdef CONFIG_PM_TRACE
 #define TRACEDATA							\
 	. = ALIGN(4);							\
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 29b3ce3f2a1d..2833452ea01c 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -49,7 +49,6 @@ struct task_struct;
 
 #ifdef CONFIG_LOCKDEP
 extern void debug_show_all_locks(void);
-extern void __debug_show_held_locks(struct task_struct *task);
 extern void debug_show_held_locks(struct task_struct *task);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
 extern void debug_check_no_locks_held(struct task_struct *task);
@@ -58,10 +57,6 @@ static inline void debug_show_all_locks(void)
 {
 }
 
-static inline void __debug_show_held_locks(struct task_struct *task)
-{
-}
-
 static inline void debug_show_held_locks(struct task_struct *task)
 {
 }
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index d7cecc90ed34..a20602041511 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -57,15 +57,15 @@ extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
 
 /* Intel IOMMU detection */
-extern void detect_intel_iommu(void);
+extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 
 extern int parse_ioapics_under_ir(void);
 extern int alloc_iommu(struct dmar_drhd_unit *);
 #else
-static inline void detect_intel_iommu(void)
+static inline int detect_intel_iommu(void)
 {
-	return;
+	return -ENODEV;
 }
 
 static inline int dmar_table_init(void)
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 52c0da4bdd18..bef3cda44c4c 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -1,6 +1,8 @@
 #ifndef _DYNAMIC_DEBUG_H
 #define _DYNAMIC_DEBUG_H
 
+#include <linux/jump_label.h>
+
 /* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which
  * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They
  * use independent hash functions, to reduce the chance of false positives.
@@ -22,8 +24,6 @@ struct _ddebug {
 	const char *function;
 	const char *filename;
 	const char *format;
-	char primary_hash;
-	char secondary_hash;
 	unsigned int lineno:24;
 	/*
  	 * The flags field controls the behaviour at the callsite.
@@ -33,6 +33,7 @@ struct _ddebug {
 #define _DPRINTK_FLAGS_PRINT   (1<<0)  /* printk() a message using the format */
 #define _DPRINTK_FLAGS_DEFAULT 0
 	unsigned int flags:8;
+	char enabled;
 } __attribute__((aligned(8)));
 
 
@@ -42,33 +43,35 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 #if defined(CONFIG_DYNAMIC_DEBUG)
 extern int ddebug_remove_module(const char *mod_name);
 
-#define __dynamic_dbg_enabled(dd)  ({	     \
-	int __ret = 0;							     \
-	if (unlikely((dynamic_debug_enabled & (1LL << DEBUG_HASH)) &&	     \
-			(dynamic_debug_enabled2 & (1LL << DEBUG_HASH2))))   \
-				if (unlikely(dd.flags))			     \
-					__ret = 1;			     \
-	__ret; })
-
 #define dynamic_pr_debug(fmt, ...) do {					\
+	__label__ do_printk;						\
+	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
-	{ KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH,	\
-		DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT };	\
-	if (__dynamic_dbg_enabled(descriptor))				\
-		printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);		\
+	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
+		_DPRINTK_FLAGS_DEFAULT };				\
+	JUMP_LABEL(&descriptor.enabled, do_printk);			\
+	goto out;							\
+do_printk:								\
+	printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);			\
+out:	;								\
 	} while (0)
 
 
 #define dynamic_dev_dbg(dev, fmt, ...) do {				\
+	__label__ do_printk;						\
+	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
-	{ KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH,	\
-		DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT };	\
-	if (__dynamic_dbg_enabled(descriptor))				\
-		dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);	\
+	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
+		_DPRINTK_FLAGS_DEFAULT };				\
+	JUMP_LABEL(&descriptor.enabled, do_printk);			\
+	goto out;							\
+do_printk:								\
+	dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);		\
+out:	;								\
 	} while (0)
 
 #else
diff --git a/include/linux/early_res.h b/include/linux/early_res.h
deleted file mode 100644
index 29c09f57a13c..000000000000
--- a/include/linux/early_res.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef _LINUX_EARLY_RES_H
-#define _LINUX_EARLY_RES_H
-#ifdef __KERNEL__
-
-extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
-extern void free_early(u64 start, u64 end);
-void free_early_partial(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
-
-void reserve_early_without_check(u64 start, u64 end, char *name);
-u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align);
-u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
-			 u64 *sizep, u64 align);
-u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align);
-u64 get_max_mapped(void);
-#include <linux/range.h>
-int get_free_all_memory_range(struct range **rangep, int nodeid);
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_EARLY_RES_H */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 02b8b24f8f51..8beabb958f61 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -191,8 +191,8 @@ struct ftrace_event_call {
 	unsigned int		flags;
 
 #ifdef CONFIG_PERF_EVENTS
-	int			perf_refcount;
-	struct hlist_head	*perf_events;
+	int				perf_refcount;
+	struct hlist_head __percpu	*perf_events;
 #endif
 };
 
@@ -252,8 +252,8 @@ DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
 
 extern int  perf_trace_init(struct perf_event *event);
 extern void perf_trace_destroy(struct perf_event *event);
-extern int  perf_trace_enable(struct perf_event *event);
-extern void perf_trace_disable(struct perf_event *event);
+extern int  perf_trace_add(struct perf_event *event, int flags);
+extern void perf_trace_del(struct perf_event *event, int flags);
 extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a0384a4d1e6f..2782d8c63b9e 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -18,6 +18,7 @@
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
+#include <trace/events/irq.h>
 
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
@@ -407,10 +408,14 @@ asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
-#define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0)
+static inline void __raise_softirq_irqoff(unsigned int nr)
+{
+	trace_softirq_raise((struct softirq_action *)(unsigned long)nr, NULL);
+	or_softirq_pending(1UL << nr);
+}
+
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
-extern void wakeup_softirqd(void);
 
 /* This is the worklist that queues up per-cpu softirq work.
  *
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c03243ad84b4..a507260fcace 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -84,32 +84,78 @@ struct proc_dir_entry;
 struct msi_desc;
 
 /**
+ * struct irq_data - per irq and irq chip data passed down to chip functions
+ * @irq:		interrupt number
+ * @node:		node index useful for balancing
+ * @chip:		low level interrupt hardware access
+ * @handler_data:	per-IRQ data for the irq_chip methods
+ * @chip_data:		platform-specific per-chip private data for the chip
+ *			methods, to allow shared chip implementations
+ * @msi_desc:		MSI descriptor
+ * @affinity:		IRQ affinity on SMP
+ * @irq_2_iommu:	iommu with this irq
+ *
+ * The fields here need to overlay the ones in irq_desc until we
+ * cleaned up the direct references and switched everything over to
+ * irq_data.
+ */
+struct irq_data {
+	unsigned int		irq;
+	unsigned int		node;
+	struct irq_chip		*chip;
+	void			*handler_data;
+	void			*chip_data;
+	struct msi_desc		*msi_desc;
+#ifdef CONFIG_SMP
+	cpumask_var_t		affinity;
+#endif
+#ifdef CONFIG_INTR_REMAP
+	struct irq_2_iommu      *irq_2_iommu;
+#endif
+};
+
+/**
  * struct irq_chip - hardware interrupt chip descriptor
  *
  * @name:		name for /proc/interrupts
- * @startup:		start up the interrupt (defaults to ->enable if NULL)
- * @shutdown:		shut down the interrupt (defaults to ->disable if NULL)
- * @enable:		enable the interrupt (defaults to chip->unmask if NULL)
- * @disable:		disable the interrupt
- * @ack:		start of a new interrupt
- * @mask:		mask an interrupt source
- * @mask_ack:		ack and mask an interrupt source
- * @unmask:		unmask an interrupt source
- * @eoi:		end of interrupt - chip level
- * @end:		end of interrupt - flow level
- * @set_affinity:	set the CPU affinity on SMP machines
- * @retrigger:		resend an IRQ to the CPU
- * @set_type:		set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
- * @set_wake:		enable/disable power-management wake-on of an IRQ
+ * @startup:		deprecated, replaced by irq_startup
+ * @shutdown:		deprecated, replaced by irq_shutdown
+ * @enable:		deprecated, replaced by irq_enable
+ * @disable:		deprecated, replaced by irq_disable
+ * @ack:		deprecated, replaced by irq_ack
+ * @mask:		deprecated, replaced by irq_mask
+ * @mask_ack:		deprecated, replaced by irq_mask_ack
+ * @unmask:		deprecated, replaced by irq_unmask
+ * @eoi:		deprecated, replaced by irq_eoi
+ * @end:		deprecated, will go away with __do_IRQ()
+ * @set_affinity:	deprecated, replaced by irq_set_affinity
+ * @retrigger:		deprecated, replaced by irq_retrigger
+ * @set_type:		deprecated, replaced by irq_set_type
+ * @set_wake:		deprecated, replaced by irq_wake
+ * @bus_lock:		deprecated, replaced by irq_bus_lock
+ * @bus_sync_unlock:	deprecated, replaced by irq_bus_sync_unlock
  *
- * @bus_lock:		function to lock access to slow bus (i2c) chips
- * @bus_sync_unlock:	function to sync and unlock slow bus (i2c) chips
+ * @irq_startup:	start up the interrupt (defaults to ->enable if NULL)
+ * @irq_shutdown:	shut down the interrupt (defaults to ->disable if NULL)
+ * @irq_enable:		enable the interrupt (defaults to chip->unmask if NULL)
+ * @irq_disable:	disable the interrupt
+ * @irq_ack:		start of a new interrupt
+ * @irq_mask:		mask an interrupt source
+ * @irq_mask_ack:	ack and mask an interrupt source
+ * @irq_unmask:		unmask an interrupt source
+ * @irq_eoi:		end of interrupt
+ * @irq_set_affinity:	set the CPU affinity on SMP machines
+ * @irq_retrigger:	resend an IRQ to the CPU
+ * @irq_set_type:	set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
+ * @irq_set_wake:	enable/disable power-management wake-on of an IRQ
+ * @irq_bus_lock:	function to lock access to slow bus (i2c) chips
+ * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips
  *
  * @release:		release function solely used by UML
- * @typename:		obsoleted by name, kept as migration helper
  */
 struct irq_chip {
 	const char	*name;
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	unsigned int	(*startup)(unsigned int irq);
 	void		(*shutdown)(unsigned int irq);
 	void		(*enable)(unsigned int irq);
@@ -130,32 +176,40 @@ struct irq_chip {
 
 	void		(*bus_lock)(unsigned int irq);
 	void		(*bus_sync_unlock)(unsigned int irq);
+#endif
+	unsigned int	(*irq_startup)(struct irq_data *data);
+	void		(*irq_shutdown)(struct irq_data *data);
+	void		(*irq_enable)(struct irq_data *data);
+	void		(*irq_disable)(struct irq_data *data);
+
+	void		(*irq_ack)(struct irq_data *data);
+	void		(*irq_mask)(struct irq_data *data);
+	void		(*irq_mask_ack)(struct irq_data *data);
+	void		(*irq_unmask)(struct irq_data *data);
+	void		(*irq_eoi)(struct irq_data *data);
+
+	int		(*irq_set_affinity)(struct irq_data *data, const struct cpumask *dest, bool force);
+	int		(*irq_retrigger)(struct irq_data *data);
+	int		(*irq_set_type)(struct irq_data *data, unsigned int flow_type);
+	int		(*irq_set_wake)(struct irq_data *data, unsigned int on);
+
+	void		(*irq_bus_lock)(struct irq_data *data);
+	void		(*irq_bus_sync_unlock)(struct irq_data *data);
 
 	/* Currently used only by UML, might disappear one day.*/
 #ifdef CONFIG_IRQ_RELEASE_METHOD
 	void		(*release)(unsigned int irq, void *dev_id);
 #endif
-	/*
-	 * For compatibility, ->typename is copied into ->name.
-	 * Will disappear.
-	 */
-	const char	*typename;
 };
 
 struct timer_rand_state;
 struct irq_2_iommu;
 /**
  * struct irq_desc - interrupt descriptor
- * @irq:		interrupt number for this descriptor
+ * @irq_data:		per irq and chip data passed down to chip functions
  * @timer_rand_state:	pointer to timer rand state struct
  * @kstat_irqs:		irq stats per cpu
- * @irq_2_iommu:	iommu with this irq
  * @handle_irq:		highlevel irq-events handler [if NULL, __do_IRQ()]
- * @chip:		low level interrupt hardware access
- * @msi_desc:		MSI descriptor
- * @handler_data:	per-IRQ data for the irq_chip methods
- * @chip_data:		platform-specific per-chip private data for the chip
- *			methods, to allow shared chip implementations
  * @action:		the irq action chain
  * @status:		status information
  * @depth:		disable-depth, for nested irq_disable() calls
@@ -164,8 +218,6 @@ struct irq_2_iommu;
  * @last_unhandled:	aging timer for unhandled count
  * @irqs_unhandled:	stats field for spurious unhandled interrupts
  * @lock:		locking for SMP
- * @affinity:		IRQ affinity on SMP
- * @node:		node index useful for balancing
  * @pending_mask:	pending rebalanced interrupts
  * @threads_active:	number of irqaction threads currently running
  * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
@@ -173,17 +225,37 @@ struct irq_2_iommu;
  * @name:		flow handler name for /proc/interrupts output
  */
 struct irq_desc {
-	unsigned int		irq;
-	struct timer_rand_state *timer_rand_state;
-	unsigned int            *kstat_irqs;
+
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+	struct irq_data		irq_data;
+#else
+	/*
+	 * This union will go away, once we fixed the direct access to
+	 * irq_desc all over the place. The direct fields are a 1:1
+	 * overlay of irq_data.
+	 */
+	union {
+		struct irq_data		irq_data;
+		struct {
+			unsigned int		irq;
+			unsigned int		node;
+			struct irq_chip		*chip;
+			void			*handler_data;
+			void			*chip_data;
+			struct msi_desc		*msi_desc;
+#ifdef CONFIG_SMP
+			cpumask_var_t		affinity;
+#endif
 #ifdef CONFIG_INTR_REMAP
-	struct irq_2_iommu      *irq_2_iommu;
+			struct irq_2_iommu      *irq_2_iommu;
+#endif
+		};
+	};
 #endif
+
+	struct timer_rand_state *timer_rand_state;
+	unsigned int            *kstat_irqs;
 	irq_flow_handler_t	handle_irq;
-	struct irq_chip		*chip;
-	struct msi_desc		*msi_desc;
-	void			*handler_data;
-	void			*chip_data;
 	struct irqaction	*action;	/* IRQ action list */
 	unsigned int		status;		/* IRQ status */
 
@@ -194,9 +266,7 @@ struct irq_desc {
 	unsigned int		irqs_unhandled;
 	raw_spinlock_t		lock;
 #ifdef CONFIG_SMP
-	cpumask_var_t		affinity;
 	const struct cpumask	*affinity_hint;
-	unsigned int		node;
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_var_t		pending_mask;
 #endif
@@ -412,15 +482,15 @@ extern int set_irq_chip_data(unsigned int irq, void *data);
 extern int set_irq_type(unsigned int irq, unsigned int type);
 extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
-#define get_irq_chip(irq)	(irq_to_desc(irq)->chip)
-#define get_irq_chip_data(irq)	(irq_to_desc(irq)->chip_data)
-#define get_irq_data(irq)	(irq_to_desc(irq)->handler_data)
-#define get_irq_msi(irq)	(irq_to_desc(irq)->msi_desc)
+#define get_irq_chip(irq)	(irq_to_desc(irq)->irq_data.chip)
+#define get_irq_chip_data(irq)	(irq_to_desc(irq)->irq_data.chip_data)
+#define get_irq_data(irq)	(irq_to_desc(irq)->irq_data.handler_data)
+#define get_irq_msi(irq)	(irq_to_desc(irq)->irq_data.msi_desc)
 
-#define get_irq_desc_chip(desc)		((desc)->chip)
-#define get_irq_desc_chip_data(desc)	((desc)->chip_data)
-#define get_irq_desc_data(desc)		((desc)->handler_data)
-#define get_irq_desc_msi(desc)		((desc)->msi_desc)
+#define get_irq_desc_chip(desc)		((desc)->irq_data.chip)
+#define get_irq_desc_chip_data(desc)	((desc)->irq_data.chip_data)
+#define get_irq_desc_data(desc)		((desc)->irq_data.handler_data)
+#define get_irq_desc_msi(desc)		((desc)->irq_data.msi_desc)
 
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
@@ -439,18 +509,18 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
 							bool boot)
 {
+#ifdef CONFIG_CPUMASK_OFFSTACK
 	gfp_t gfp = GFP_ATOMIC;
 
 	if (boot)
 		gfp = GFP_NOWAIT;
 
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	if (!alloc_cpumask_var_node(&desc->affinity, gfp, node))
+	if (!alloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node))
 		return false;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (!alloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
-		free_cpumask_var(desc->affinity);
+		free_cpumask_var(desc->irq_data.affinity);
 		return false;
 	}
 #endif
@@ -460,7 +530,7 @@ static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
 
 static inline void init_desc_masks(struct irq_desc *desc)
 {
-	cpumask_setall(desc->affinity);
+	cpumask_setall(desc->irq_data.affinity);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_clear(desc->pending_mask);
 #endif
@@ -480,7 +550,7 @@ static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 					struct irq_desc *new_desc)
 {
 #ifdef CONFIG_CPUMASK_OFFSTACK
-	cpumask_copy(new_desc->affinity, old_desc->affinity);
+	cpumask_copy(new_desc->irq_data.affinity, old_desc->irq_data.affinity);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_copy(new_desc->pending_mask, old_desc->pending_mask);
@@ -491,7 +561,7 @@ static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 static inline void free_desc_masks(struct irq_desc *old_desc,
 				   struct irq_desc *new_desc)
 {
-	free_cpumask_var(old_desc->affinity);
+	free_cpumask_var(old_desc->irq_data.affinity);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	free_cpumask_var(old_desc->pending_mask);
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
new file mode 100644
index 000000000000..b72cd9f92c2e
--- /dev/null
+++ b/include/linux/jump_label.h
@@ -0,0 +1,64 @@
+#ifndef _LINUX_JUMP_LABEL_H
+#define _LINUX_JUMP_LABEL_H
+
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL)
+# include <asm/jump_label.h>
+# define HAVE_JUMP_LABEL
+#endif
+
+enum jump_label_type {
+	JUMP_LABEL_ENABLE,
+	JUMP_LABEL_DISABLE
+};
+
+struct module;
+
+#ifdef HAVE_JUMP_LABEL
+
+extern struct jump_entry __start___jump_table[];
+extern struct jump_entry __stop___jump_table[];
+
+extern void arch_jump_label_transform(struct jump_entry *entry,
+				 enum jump_label_type type);
+extern void arch_jump_label_text_poke_early(jump_label_t addr);
+extern void jump_label_update(unsigned long key, enum jump_label_type type);
+extern void jump_label_apply_nops(struct module *mod);
+extern int jump_label_text_reserved(void *start, void *end);
+
+#define enable_jump_label(key) \
+	jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE);
+
+#define disable_jump_label(key) \
+	jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE);
+
+#else
+
+#define JUMP_LABEL(key, label)			\
+do {						\
+	if (unlikely(*key))			\
+		goto label;			\
+} while (0)
+
+#define enable_jump_label(cond_var)	\
+do {					\
+       *(cond_var) = 1;			\
+} while (0)
+
+#define disable_jump_label(cond_var)	\
+do {					\
+       *(cond_var) = 0;			\
+} while (0)
+
+static inline int jump_label_apply_nops(struct module *mod)
+{
+	return 0;
+}
+
+static inline int jump_label_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
+#endif
+
+#endif
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index a59faf2b5edd..5096458c7535 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -2,6 +2,7 @@
 #define _LINUX_MEMBLOCK_H
 #ifdef __KERNEL__
 
+#ifdef CONFIG_HAVE_MEMBLOCK
 /*
  * Logical memory blocks.
  *
@@ -16,73 +17,151 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 
-#define MAX_MEMBLOCK_REGIONS 128
+#include <asm/memblock.h>
 
-struct memblock_property {
-	u64 base;
-	u64 size;
-};
+#define INIT_MEMBLOCK_REGIONS	128
+#define MEMBLOCK_ERROR		0
 
 struct memblock_region {
-	unsigned long cnt;
-	u64 size;
-	struct memblock_property region[MAX_MEMBLOCK_REGIONS+1];
+	phys_addr_t base;
+	phys_addr_t size;
+};
+
+struct memblock_type {
+	unsigned long cnt;	/* number of regions */
+	unsigned long max;	/* size of the allocated array */
+	struct memblock_region *regions;
 };
 
 struct memblock {
-	unsigned long debug;
-	u64 rmo_size;
-	struct memblock_region memory;
-	struct memblock_region reserved;
+	phys_addr_t current_limit;
+	phys_addr_t memory_size;	/* Updated by memblock_analyze() */
+	struct memblock_type memory;
+	struct memblock_type reserved;
 };
 
 extern struct memblock memblock;
+extern int memblock_debug;
+extern int memblock_can_resize;
 
-extern void __init memblock_init(void);
-extern void __init memblock_analyze(void);
-extern long memblock_add(u64 base, u64 size);
-extern long memblock_remove(u64 base, u64 size);
-extern long __init memblock_free(u64 base, u64 size);
-extern long __init memblock_reserve(u64 base, u64 size);
-extern u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
-				u64 (*nid_range)(u64, u64, int *));
-extern u64 __init memblock_alloc(u64 size, u64 align);
-extern u64 __init memblock_alloc_base(u64 size,
-		u64, u64 max_addr);
-extern u64 __init __memblock_alloc_base(u64 size,
-		u64 align, u64 max_addr);
-extern u64 __init memblock_phys_mem_size(void);
-extern u64 memblock_end_of_DRAM(void);
-extern void __init memblock_enforce_memory_limit(u64 memory_limit);
-extern int __init memblock_is_reserved(u64 addr);
-extern int memblock_is_region_reserved(u64 base, u64 size);
-extern int memblock_find(struct memblock_property *res);
+#define memblock_dbg(fmt, ...) \
+	if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
+
+u64 memblock_find_in_range(u64 start, u64 end, u64 size, u64 align);
+int memblock_free_reserved_regions(void);
+int memblock_reserve_reserved_regions(void);
+
+extern void memblock_init(void);
+extern void memblock_analyze(void);
+extern long memblock_add(phys_addr_t base, phys_addr_t size);
+extern long memblock_remove(phys_addr_t base, phys_addr_t size);
+extern long memblock_free(phys_addr_t base, phys_addr_t size);
+extern long memblock_reserve(phys_addr_t base, phys_addr_t size);
+
+/* The numa aware allocator is only available if
+ * CONFIG_ARCH_POPULATES_NODE_MAP is set
+ */
+extern phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align,
+					int nid);
+extern phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align,
+					    int nid);
+
+extern phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
+
+/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
+#define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
+#define MEMBLOCK_ALLOC_ACCESSIBLE	0
+
+extern phys_addr_t memblock_alloc_base(phys_addr_t size,
+					 phys_addr_t align,
+					 phys_addr_t max_addr);
+extern phys_addr_t __memblock_alloc_base(phys_addr_t size,
+					   phys_addr_t align,
+					   phys_addr_t max_addr);
+extern phys_addr_t memblock_phys_mem_size(void);
+extern phys_addr_t memblock_end_of_DRAM(void);
+extern void memblock_enforce_memory_limit(phys_addr_t memory_limit);
+extern int memblock_is_memory(phys_addr_t addr);
+extern int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
+extern int memblock_is_reserved(phys_addr_t addr);
+extern int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 
 extern void memblock_dump_all(void);
 
-static inline u64
-memblock_size_bytes(struct memblock_region *type, unsigned long region_nr)
+/* Provided by the architecture */
+extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid);
+extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+				   phys_addr_t addr2, phys_addr_t size2);
+
+/**
+ * memblock_set_current_limit - Set the current allocation limit to allow
+ *                         limiting allocations to what is currently
+ *                         accessible during boot
+ * @limit: New limit value (physical address)
+ */
+extern void memblock_set_current_limit(phys_addr_t limit);
+
+
+/*
+ * pfn conversion functions
+ *
+ * While the memory MEMBLOCKs should always be page aligned, the reserved
+ * MEMBLOCKs may not be. This accessor attempt to provide a very clear
+ * idea of what they return for such non aligned MEMBLOCKs.
+ */
+
+/**
+ * memblock_region_base_pfn - Return the lowest pfn intersecting with the region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_base_pfn(const struct memblock_region *reg)
 {
-	return type->region[region_nr].size;
+	return reg->base >> PAGE_SHIFT;
 }
-static inline u64
-memblock_size_pages(struct memblock_region *type, unsigned long region_nr)
+
+/**
+ * memblock_region_last_pfn - Return the highest pfn intersecting with the region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_last_pfn(const struct memblock_region *reg)
 {
-	return memblock_size_bytes(type, region_nr) >> PAGE_SHIFT;
+	return (reg->base + reg->size - 1) >> PAGE_SHIFT;
 }
-static inline u64
-memblock_start_pfn(struct memblock_region *type, unsigned long region_nr)
+
+/**
+ * memblock_region_end_pfn - Return the pfn of the first page following the region
+ *                      but not intersecting it
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_end_pfn(const struct memblock_region *reg)
 {
-	return type->region[region_nr].base >> PAGE_SHIFT;
+	return memblock_region_last_pfn(reg) + 1;
 }
-static inline u64
-memblock_end_pfn(struct memblock_region *type, unsigned long region_nr)
+
+/**
+ * memblock_region_pages - Return the number of pages covering a region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_pages(const struct memblock_region *reg)
 {
-	return memblock_start_pfn(type, region_nr) +
-	       memblock_size_pages(type, region_nr);
+	return memblock_region_end_pfn(reg) - memblock_region_end_pfn(reg);
 }
 
-#include <asm/memblock.h>
+#define for_each_memblock(memblock_type, region)					\
+	for (region = memblock.memblock_type.regions;				\
+	     region < (memblock.memblock_type.regions + memblock.memblock_type.cnt);	\
+	     region++)
+
+
+#ifdef ARCH_DISCARD_MEMBLOCK
+#define __init_memblock __init
+#define __initdata_memblock __initdata
+#else
+#define __init_memblock
+#define __initdata_memblock
+#endif
+
+#endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 74949fbef8c6..7687228dd3b7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1175,6 +1175,8 @@ extern void free_bootmem_with_active_regions(int nid,
 						unsigned long max_low_pfn);
 int add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid);
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit);
 void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
 				 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
diff --git a/include/linux/module.h b/include/linux/module.h
index aace066bad8f..b29e7458b966 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -350,7 +350,10 @@ struct module
 	struct tracepoint *tracepoints;
 	unsigned int num_tracepoints;
 #endif
-
+#ifdef HAVE_JUMP_LABEL
+	struct jump_entry *jump_entries;
+	unsigned int num_jump_entries;
+#endif
 #ifdef CONFIG_TRACING
 	const char **trace_bprintk_fmt_start;
 	unsigned int num_trace_bprintk_fmt;
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index acd38acf0b41..e439e7b8bdfb 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -517,6 +517,7 @@
 #define PCI_DEVICE_ID_AMD_11H_NB_DRAM	0x1302
 #define PCI_DEVICE_ID_AMD_11H_NB_MISC	0x1303
 #define PCI_DEVICE_ID_AMD_11H_NB_LINK	0x1304
+#define PCI_DEVICE_ID_AMD_15H_NB_MISC	0x1603
 #define PCI_DEVICE_ID_AMD_LANCE		0x2000
 #define PCI_DEVICE_ID_AMD_LANCE_HOME	0x2001
 #define PCI_DEVICE_ID_AMD_SCSI		0x2020
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index ce2dc655cd1d..ab20d119a85d 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -139,6 +139,18 @@
 	__aligned(PAGE_SIZE)
 
 /*
+ * Declaration/definition used for large per-CPU variables that must be
+ * aligned to something larger than the pagesize.
+ */
+#define DECLARE_PER_CPU_MULTIPAGE_ALIGNED(type, name, size)		\
+	DECLARE_PER_CPU_SECTION(type, name, "..page_aligned")		\
+	__aligned(size)
+
+#define DEFINE_PER_CPU_MULTIPAGE_ALIGNED(type, name, size)		\
+	DEFINE_PER_CPU_SECTION(type, name, "..page_aligned")		\
+	__aligned(size)
+
+/*
  * Intermodule exports for per-CPU variables.  sparse forgets about
  * address space across EXPORT_SYMBOL(), change EXPORT_SYMBOL() to
  * noop if __CHECKER__.
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index aeeeef1093cd..5095b834a6fb 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -39,6 +39,15 @@
 	preempt_enable();				\
 } while (0)
 
+#define get_cpu_ptr(var) ({				\
+	preempt_disable();				\
+	this_cpu_ptr(var); })
+
+#define put_cpu_ptr(var) do {				\
+	(void)(var);					\
+	preempt_enable();				\
+} while (0)
+
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(32 << 10)
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 716f99b682c1..61b1e2d760fd 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -529,7 +529,6 @@ struct hw_perf_event {
 			int		last_cpu;
 		};
 		struct { /* software */
-			s64		remaining;
 			struct hrtimer	hrtimer;
 		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
@@ -539,6 +538,7 @@ struct hw_perf_event {
 		};
 #endif
 	};
+	int				state;
 	local64_t			prev_count;
 	u64				sample_period;
 	u64				last_period;
@@ -550,6 +550,13 @@ struct hw_perf_event {
 #endif
 };
 
+/*
+ * hw_perf_event::state flags
+ */
+#define PERF_HES_STOPPED	0x01 /* the counter is stopped */
+#define PERF_HES_UPTODATE	0x02 /* event->count up-to-date */
+#define PERF_HES_ARCH		0x04
+
 struct perf_event;
 
 /*
@@ -561,36 +568,70 @@ struct perf_event;
  * struct pmu - generic performance monitoring unit
  */
 struct pmu {
-	int (*enable)			(struct perf_event *event);
-	void (*disable)			(struct perf_event *event);
-	int (*start)			(struct perf_event *event);
-	void (*stop)			(struct perf_event *event);
-	void (*read)			(struct perf_event *event);
-	void (*unthrottle)		(struct perf_event *event);
+	struct list_head		entry;
+
+	int * __percpu			pmu_disable_count;
+	struct perf_cpu_context * __percpu pmu_cpu_context;
+	int				task_ctx_nr;
 
 	/*
-	 * Group events scheduling is treated as a transaction, add group
-	 * events as a whole and perform one schedulability test. If the test
-	 * fails, roll back the whole group
+	 * Fully disable/enable this PMU, can be used to protect from the PMI
+	 * as well as for lazy/batch writing of the MSRs.
 	 */
+	void (*pmu_enable)		(struct pmu *pmu); /* optional */
+	void (*pmu_disable)		(struct pmu *pmu); /* optional */
 
 	/*
-	 * Start the transaction, after this ->enable() doesn't need
-	 * to do schedulability tests.
+	 * Try and initialize the event for this PMU.
+	 * Should return -ENOENT when the @event doesn't match this PMU.
 	 */
-	void (*start_txn)	(const struct pmu *pmu);
+	int (*event_init)		(struct perf_event *event);
+
+#define PERF_EF_START	0x01		/* start the counter when adding    */
+#define PERF_EF_RELOAD	0x02		/* reload the counter when starting */
+#define PERF_EF_UPDATE	0x04		/* update the counter when stopping */
+
 	/*
-	 * If ->start_txn() disabled the ->enable() schedulability test
+	 * Adds/Removes a counter to/from the PMU, can be done inside
+	 * a transaction, see the ->*_txn() methods.
+	 */
+	int  (*add)			(struct perf_event *event, int flags);
+	void (*del)			(struct perf_event *event, int flags);
+
+	/*
+	 * Starts/Stops a counter present on the PMU. The PMI handler
+	 * should stop the counter when perf_event_overflow() returns
+	 * !0. ->start() will be used to continue.
+	 */
+	void (*start)			(struct perf_event *event, int flags);
+	void (*stop)			(struct perf_event *event, int flags);
+
+	/*
+	 * Updates the counter value of the event.
+	 */
+	void (*read)			(struct perf_event *event);
+
+	/*
+	 * Group events scheduling is treated as a transaction, add
+	 * group events as a whole and perform one schedulability test.
+	 * If the test fails, roll back the whole group
+	 *
+	 * Start the transaction, after this ->add() doesn't need to
+	 * do schedulability tests.
+	 */
+	void (*start_txn)	(struct pmu *pmu); /* optional */
+	/*
+	 * If ->start_txn() disabled the ->add() schedulability test
 	 * then ->commit_txn() is required to perform one. On success
 	 * the transaction is closed. On error the transaction is kept
 	 * open until ->cancel_txn() is called.
 	 */
-	int  (*commit_txn)	(const struct pmu *pmu);
+	int  (*commit_txn)	(struct pmu *pmu); /* optional */
 	/*
-	 * Will cancel the transaction, assumes ->disable() is called for
-	 * each successfull ->enable() during the transaction.
+	 * Will cancel the transaction, assumes ->del() is called
+	 * for each successfull ->add() during the transaction.
 	 */
-	void (*cancel_txn)	(const struct pmu *pmu);
+	void (*cancel_txn)	(struct pmu *pmu); /* optional */
 };
 
 /**
@@ -669,7 +710,7 @@ struct perf_event {
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
-	const struct pmu		*pmu;
+	struct pmu			*pmu;
 
 	enum perf_event_active_state	state;
 	unsigned int			attach_state;
@@ -763,12 +804,19 @@ struct perf_event {
 #endif /* CONFIG_PERF_EVENTS */
 };
 
+enum perf_event_context_type {
+	task_context,
+	cpu_context,
+};
+
 /**
  * struct perf_event_context - event context structure
  *
  * Used as a container for task events and CPU events as well:
  */
 struct perf_event_context {
+	enum perf_event_context_type	type;
+	struct pmu			*pmu;
 	/*
 	 * Protect the states of the events in the list,
 	 * nr_active, and the list:
@@ -808,6 +856,12 @@ struct perf_event_context {
 	struct rcu_head			rcu_head;
 };
 
+/*
+ * Number of contexts where an event can trigger:
+ * 	task, softirq, hardirq, nmi.
+ */
+#define PERF_NR_CONTEXTS	4
+
 /**
  * struct perf_event_cpu_context - per cpu event context structure
  */
@@ -815,18 +869,9 @@ struct perf_cpu_context {
 	struct perf_event_context	ctx;
 	struct perf_event_context	*task_ctx;
 	int				active_oncpu;
-	int				max_pertask;
 	int				exclusive;
-	struct swevent_hlist		*swevent_hlist;
-	struct mutex			hlist_mutex;
-	int				hlist_refcount;
-
-	/*
-	 * Recursion avoidance:
-	 *
-	 * task, softirq, irq, nmi context
-	 */
-	int				recursion[4];
+	struct list_head		rotation_list;
+	int				jiffies_interval;
 };
 
 struct perf_output_handle {
@@ -842,26 +887,20 @@ struct perf_output_handle {
 
 #ifdef CONFIG_PERF_EVENTS
 
-/*
- * Set by architecture code:
- */
-extern int perf_max_events;
-
-extern const struct pmu *hw_perf_event_init(struct perf_event *event);
+extern int perf_pmu_register(struct pmu *pmu);
+extern void perf_pmu_unregister(struct pmu *pmu);
 
 extern void perf_event_task_sched_in(struct task_struct *task);
 extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
-extern void perf_event_task_tick(struct task_struct *task);
 extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
+extern void perf_event_delayed_put(struct task_struct *task);
 extern void set_perf_event_pending(void);
 extern void perf_event_do_pending(void);
 extern void perf_event_print_debug(void);
-extern void __perf_disable(void);
-extern bool __perf_enable(void);
-extern void perf_disable(void);
-extern void perf_enable(void);
+extern void perf_pmu_disable(struct pmu *pmu);
+extern void perf_pmu_enable(struct pmu *pmu);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
 extern void perf_event_update_userpage(struct perf_event *event);
@@ -869,7 +908,7 @@ extern int perf_event_release_kernel(struct perf_event *event);
 extern struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr,
 				int cpu,
-				pid_t pid,
+				struct task_struct *task,
 				perf_overflow_handler_t callback);
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
@@ -920,14 +959,7 @@ extern int perf_event_overflow(struct perf_event *event, int nmi,
  */
 static inline int is_software_event(struct perf_event *event)
 {
-	switch (event->attr.type) {
-	case PERF_TYPE_SOFTWARE:
-	case PERF_TYPE_TRACEPOINT:
-	/* for now the breakpoint stuff also works as software event */
-	case PERF_TYPE_BREAKPOINT:
-		return 1;
-	}
-	return 0;
+	return event->pmu->task_ctx_nr == perf_sw_context;
 }
 
 extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
@@ -976,7 +1008,21 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks
 extern void perf_event_comm(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
-extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+/* Callchains */
+DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
+
+extern void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs);
+
+
+static inline void
+perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+	if (entry->nr < PERF_MAX_STACK_DEPTH)
+		entry->ip[entry->nr++] = ip;
+}
 
 extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
@@ -1019,21 +1065,19 @@ extern int perf_swevent_get_recursion_context(void);
 extern void perf_swevent_put_recursion_context(int rctx);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
+extern void perf_event_task_tick(void);
 #else
 static inline void
 perf_event_task_sched_in(struct task_struct *task)			{ }
 static inline void
 perf_event_task_sched_out(struct task_struct *task,
 			    struct task_struct *next)			{ }
-static inline void
-perf_event_task_tick(struct task_struct *task)				{ }
 static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)	{ }
 static inline void perf_event_free_task(struct task_struct *task)	{ }
+static inline void perf_event_delayed_put(struct task_struct *task)	{ }
 static inline void perf_event_do_pending(void)				{ }
 static inline void perf_event_print_debug(void)				{ }
-static inline void perf_disable(void)					{ }
-static inline void perf_enable(void)					{ }
 static inline int perf_event_task_disable(void)				{ return -EINVAL; }
 static inline int perf_event_task_enable(void)				{ return -EINVAL; }
 
@@ -1056,6 +1100,7 @@ static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
 static inline void perf_swevent_put_recursion_context(int rctx)		{ }
 static inline void perf_event_enable(struct perf_event *event)		{ }
 static inline void perf_event_disable(struct perf_event *event)		{ }
+static inline void perf_event_task_tick(void)				{ }
 #endif
 
 #define perf_output_put(handle, x) \
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 03cda7bed985..0d0b64038a2b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -413,7 +413,7 @@ extern int rcu_my_thread_group_empty(void);
  * This is the RCU-bh counterpart to rcu_dereference_check().
  */
 #define rcu_dereference_bh_check(p, c) \
-	__rcu_dereference_check((p), rcu_read_lock_bh_held() || (c), __rcu)
+	__rcu_dereference_check((p), rcu_read_lock_bh_held() || irqs_disabled() || (c), __rcu)
 
 /**
  * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 85bc4c3487a1..1fc45ce07a1a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -878,6 +878,7 @@ enum sched_domain_level {
 	SD_LV_NONE = 0,
 	SD_LV_SIBLING,
 	SD_LV_MC,
+	SD_LV_BOOK,
 	SD_LV_CPU,
 	SD_LV_NODE,
 	SD_LV_ALLNODES,
@@ -1163,6 +1164,13 @@ struct sched_rt_entity {
 
 struct rcu_node;
 
+enum perf_event_task_context {
+	perf_invalid_context = -1,
+	perf_hw_context = 0,
+	perf_sw_context,
+	perf_nr_task_contexts,
+};
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
@@ -1436,7 +1444,7 @@ struct task_struct {
 	struct futex_pi_state *pi_state_cache;
 #endif
 #ifdef CONFIG_PERF_EVENTS
-	struct perf_event_context *perf_event_ctxp;
+	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
 	struct mutex perf_event_mutex;
 	struct list_head perf_event_list;
 #endif
@@ -1686,8 +1694,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 /*
  * Per process flags
  */
-#define PF_ALIGNWARN	0x00000001	/* Print alignment warning msgs */
-					/* Not implemented yet, only for 486*/
 #define PF_STARTING	0x00000002	/* being created */
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index a8cc4e13434c..c90696544176 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -23,12 +23,12 @@ struct restart_block {
 		};
 		/* For futex_wait and futex_wait_requeue_pi */
 		struct {
-			u32 *uaddr;
+			u32 __user *uaddr;
 			u32 val;
 			u32 flags;
 			u32 bitset;
 			u64 time;
-			u32 *uaddr2;
+			u32 __user *uaddr2;
 		} futex;
 		/* For nanosleep */
 		struct {
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 64e084ff5e5c..b91a40e847d2 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -201,6 +201,12 @@ int arch_update_cpu_topology(void);
 	.balance_interval	= 64,					\
 }
 
+#ifdef CONFIG_SCHED_BOOK
+#ifndef SD_BOOK_INIT
+#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
+#endif
+#endif /* CONFIG_SCHED_BOOK */
+
 #ifdef CONFIG_NUMA
 #ifndef SD_NODE_INIT
 #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!!
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 103d1b61aacb..a4a90b6726ce 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/rcupdate.h>
+#include <linux/jump_label.h>
 
 struct module;
 struct tracepoint;
@@ -145,7 +146,9 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
-		if (unlikely(__tracepoint_##name.state))		\
+		JUMP_LABEL(&__tracepoint_##name.state, do_trace);	\
+		return;							\
+do_trace:								\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args));			\
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
index 0e4cfb694fe7..6fa7cbab7d93 100644
--- a/include/trace/events/irq.h
+++ b/include/trace/events/irq.h
@@ -5,7 +5,9 @@
 #define _TRACE_IRQ_H
 
 #include <linux/tracepoint.h>
-#include <linux/interrupt.h>
+
+struct irqaction;
+struct softirq_action;
 
 #define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
 #define show_softirq_name(val)				\
@@ -93,7 +95,10 @@ DECLARE_EVENT_CLASS(softirq,
 	),
 
 	TP_fast_assign(
-		__entry->vec = (int)(h - vec);
+		if (vec)
+			__entry->vec = (int)(h - vec);
+		else
+			__entry->vec = (int)(long)h;
 	),
 
 	TP_printk("vec=%d [action=%s]", __entry->vec,
@@ -136,6 +141,23 @@ DEFINE_EVENT(softirq, softirq_exit,
 	TP_ARGS(h, vec)
 );
 
+/**
+ * softirq_raise - called immediately when a softirq is raised
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter contains a pointer to the softirq vector number which is
+ * raised. @vec is NULL and it means @h includes vector number not
+ * softirq_action. When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq raise latency.
+ */
+DEFINE_EVENT(softirq, softirq_raise,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec)
+);
+
 #endif /*  _TRACE_IRQ_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
index 188deca2f3c7..8fe1e93f531d 100644
--- a/include/trace/events/napi.h
+++ b/include/trace/events/napi.h
@@ -6,10 +6,31 @@
 
 #include <linux/netdevice.h>
 #include <linux/tracepoint.h>
+#include <linux/ftrace.h>
+
+#define NO_DEV "(no_device)"
+
+TRACE_EVENT(napi_poll,
 
-DECLARE_TRACE(napi_poll,
 	TP_PROTO(struct napi_struct *napi),
-	TP_ARGS(napi));
+
+	TP_ARGS(napi),
+
+	TP_STRUCT__entry(
+		__field(	struct napi_struct *,	napi)
+		__string(	dev_name, napi->dev ? napi->dev->name : NO_DEV)
+	),
+
+	TP_fast_assign(
+		__entry->napi = napi;
+		__assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV);
+	),
+
+	TP_printk("napi poll on napi struct %p for device %s",
+		__entry->napi, __get_str(dev_name))
+);
+
+#undef NO_DEV
 
 #endif /* _TRACE_NAPI_H_ */
 
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
new file mode 100644
index 000000000000..5f247f5ffc56
--- /dev/null
+++ b/include/trace/events/net.h
@@ -0,0 +1,82 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM net
+
+#if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NET_H
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/ip.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(net_dev_xmit,
+
+	TP_PROTO(struct sk_buff *skb,
+		 int rc),
+
+	TP_ARGS(skb, rc),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__field(	int,		rc		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__entry->rc = rc;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
+		__get_str(name), __entry->skbaddr, __entry->len, __entry->rc)
+);
+
+DECLARE_EVENT_CLASS(net_dev_template,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u",
+		__get_str(name), __entry->skbaddr, __entry->len)
+)
+
+DEFINE_EVENT(net_dev_template, net_dev_queue,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_receive_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_rx,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+#endif /* _TRACE_NET_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 35a2a6e7bf1e..286784d69b8f 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -10,12 +10,17 @@
 #ifndef _TRACE_POWER_ENUM_
 #define _TRACE_POWER_ENUM_
 enum {
-	POWER_NONE = 0,
-	POWER_CSTATE = 1,
-	POWER_PSTATE = 2,
+	POWER_NONE	= 0,
+	POWER_CSTATE	= 1,	/* C-State */
+	POWER_PSTATE	= 2,	/* Fequency change or DVFS */
+	POWER_SSTATE	= 3,	/* Suspend */
 };
 #endif
 
+/*
+ * The power events are used for cpuidle & suspend (power_start, power_end)
+ *  and for cpufreq (power_frequency)
+ */
 DECLARE_EVENT_CLASS(power,
 
 	TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
@@ -70,6 +75,85 @@ TRACE_EVENT(power_end,
 
 );
 
+/*
+ * The clock events are used for clock enable/disable and for
+ *  clock rate change
+ */
+DECLARE_EVENT_CLASS(clock,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_enable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_disable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_set_rate,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+/*
+ * The power domain events are used for power domains transitions
+ */
+DECLARE_EVENT_CLASS(power_domain,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(power_domain, power_domain_target,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
 #endif /* _TRACE_POWER_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9208c92aeab5..f6334782a593 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -362,6 +362,35 @@ TRACE_EVENT(sched_stat_runtime,
 			(unsigned long long)__entry->vruntime)
 );
 
+/*
+ * Tracepoint for showing priority inheritance modifying a tasks
+ * priority.
+ */
+TRACE_EVENT(sched_pi_setprio,
+
+	TP_PROTO(struct task_struct *tsk, int newprio),
+
+	TP_ARGS(tsk, newprio),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( int,	oldprio			)
+		__field( int,	newprio			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid		= tsk->pid;
+		__entry->oldprio	= tsk->prio;
+		__entry->newprio	= newprio;
+	),
+
+	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
+			__entry->comm, __entry->pid,
+			__entry->oldprio, __entry->newprio)
+);
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 4b2be6dc76f0..75ce9d500d8e 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -35,6 +35,23 @@ TRACE_EVENT(kfree_skb,
 		__entry->skbaddr, __entry->protocol, __entry->location)
 );
 
+TRACE_EVENT(consume_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,	skbaddr	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+	),
+
+	TP_printk("skbaddr=%p", __entry->skbaddr)
+);
+
 TRACE_EVENT(skb_copy_datagram_iovec,
 
 	TP_PROTO(const struct sk_buff *skb, int len),
diff --git a/init/Kconfig b/init/Kconfig
index e06ba2bec6d6..731763b45c8c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -332,6 +332,8 @@ config AUDIT_TREE
 	depends on AUDITSYSCALL
 	select FSNOTIFY
 
+source "kernel/irq/Kconfig"
+
 menu "RCU Subsystem"
 
 choice
diff --git a/kernel/Makefile b/kernel/Makefile
index 17046b6e7c90..8a0feb737ca4 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,8 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o range.o
-obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
+	    async.o range.o jump_label.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/kernel/early_res.c b/kernel/early_res.c
deleted file mode 100644
index 7bfae887f211..000000000000
--- a/kernel/early_res.c
+++ /dev/null
@@ -1,590 +0,0 @@
-/*
- * early_res, could be used to replace bootmem
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/early_res.h>
-#include <linux/slab.h>
-#include <linux/kmemleak.h>
-
-/*
- * Early reserved memory areas.
- */
-/*
- * need to make sure this one is bigger enough before
- * find_fw_memmap_area could be used
- */
-#define MAX_EARLY_RES_X 32
-
-struct early_res {
-	u64 start, end;
-	char name[15];
-	char overlap_ok;
-};
-static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
-
-static int max_early_res __initdata = MAX_EARLY_RES_X;
-static struct early_res *early_res __initdata = &early_res_x[0];
-static int early_res_count __initdata;
-
-static int __init find_overlapped_early(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-		if (end > r->start && start < r->end)
-			break;
-	}
-
-	return i;
-}
-
-/*
- * Drop the i-th range from the early reservation map,
- * by copying any higher ranges down one over it, and
- * clearing what had been the last slot.
- */
-static void __init drop_range(int i)
-{
-	int j;
-
-	for (j = i + 1; j < max_early_res && early_res[j].end; j++)
-		;
-
-	memmove(&early_res[i], &early_res[i + 1],
-	       (j - 1 - i) * sizeof(struct early_res));
-
-	early_res[j - 1].end = 0;
-	early_res_count--;
-}
-
-static void __init drop_range_partial(int i, u64 start, u64 end)
-{
-	u64 common_start, common_end;
-	u64 old_start, old_end;
-
-	old_start = early_res[i].start;
-	old_end = early_res[i].end;
-	common_start = max(old_start, start);
-	common_end = min(old_end, end);
-
-	/* no overlap ? */
-	if (common_start >= common_end)
-		return;
-
-	if (old_start < common_start) {
-		/* make head segment */
-		early_res[i].end = common_start;
-		if (old_end > common_end) {
-			char name[15];
-
-			/*
-			 * Save a local copy of the name, since the
-			 * early_res array could get resized inside
-			 * reserve_early_without_check() ->
-			 * __check_and_double_early_res(), which would
-			 * make the current name pointer invalid.
-			 */
-			strncpy(name, early_res[i].name,
-					 sizeof(early_res[i].name) - 1);
-			/* add another for left over on tail */
-			reserve_early_without_check(common_end, old_end, name);
-		}
-		return;
-	} else {
-		if (old_end > common_end) {
-			/* reuse the entry for tail left */
-			early_res[i].start = common_end;
-			return;
-		}
-		/* all covered */
-		drop_range(i);
-	}
-}
-
-/*
- * Split any existing ranges that:
- *  1) are marked 'overlap_ok', and
- *  2) overlap with the stated range [start, end)
- * into whatever portion (if any) of the existing range is entirely
- * below or entirely above the stated range.  Drop the portion
- * of the existing range that overlaps with the stated range,
- * which will allow the caller of this routine to then add that
- * stated range without conflicting with any existing range.
- */
-static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-	u64 lower_start, lower_end;
-	u64 upper_start, upper_end;
-	char name[15];
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-
-		/* Continue past non-overlapping ranges */
-		if (end <= r->start || start >= r->end)
-			continue;
-
-		/*
-		 * Leave non-ok overlaps as is; let caller
-		 * panic "Overlapping early reservations"
-		 * when it hits this overlap.
-		 */
-		if (!r->overlap_ok)
-			return;
-
-		/*
-		 * We have an ok overlap.  We will drop it from the early
-		 * reservation map, and add back in any non-overlapping
-		 * portions (lower or upper) as separate, overlap_ok,
-		 * non-overlapping ranges.
-		 */
-
-		/* 1. Note any non-overlapping (lower or upper) ranges. */
-		strncpy(name, r->name, sizeof(name) - 1);
-
-		lower_start = lower_end = 0;
-		upper_start = upper_end = 0;
-		if (r->start < start) {
-			lower_start = r->start;
-			lower_end = start;
-		}
-		if (r->end > end) {
-			upper_start = end;
-			upper_end = r->end;
-		}
-
-		/* 2. Drop the original ok overlapping range */
-		drop_range(i);
-
-		i--;		/* resume for-loop on copied down entry */
-
-		/* 3. Add back in any non-overlapping ranges. */
-		if (lower_end)
-			reserve_early_overlap_ok(lower_start, lower_end, name);
-		if (upper_end)
-			reserve_early_overlap_ok(upper_start, upper_end, name);
-	}
-}
-
-static void __init __reserve_early(u64 start, u64 end, char *name,
-						int overlap_ok)
-{
-	int i;
-	struct early_res *r;
-
-	i = find_overlapped_early(start, end);
-	if (i >= max_early_res)
-		panic("Too many early reservations");
-	r = &early_res[i];
-	if (r->end)
-		panic("Overlapping early reservations "
-		      "%llx-%llx %s to %llx-%llx %s\n",
-		      start, end - 1, name ? name : "", r->start,
-		      r->end - 1, r->name);
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = overlap_ok;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-/*
- * A few early reservtations come here.
- *
- * The 'overlap_ok' in the name of this routine does -not- mean it
- * is ok for these reservations to overlap an earlier reservation.
- * Rather it means that it is ok for subsequent reservations to
- * overlap this one.
- *
- * Use this entry point to reserve early ranges when you are doing
- * so out of "Paranoia", reserving perhaps more memory than you need,
- * just in case, and don't mind a subsequent overlapping reservation
- * that is known to be needed.
- *
- * The drop_overlaps_that_are_ok() call here isn't really needed.
- * It would be needed if we had two colliding 'overlap_ok'
- * reservations, so that the second such would not panic on the
- * overlap with the first.  We don't have any such as of this
- * writing, but might as well tolerate such if it happens in
- * the future.
- */
-void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
-{
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 1);
-}
-
-static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
-{
-	u64 start, end, size, mem;
-	struct early_res *new;
-
-	/* do we have enough slots left ? */
-	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
-		return;
-
-	/* double it */
-	mem = -1ULL;
-	size = sizeof(struct early_res) * max_early_res * 2;
-	if (early_res == early_res_x)
-		start = 0;
-	else
-		start = early_res[0].end;
-	end = ex_start;
-	if (start + size < end)
-		mem = find_fw_memmap_area(start, end, size,
-					 sizeof(struct early_res));
-	if (mem == -1ULL) {
-		start = ex_end;
-		end = get_max_mapped();
-		if (start + size < end)
-			mem = find_fw_memmap_area(start, end, size,
-						 sizeof(struct early_res));
-	}
-	if (mem == -1ULL)
-		panic("can not find more space for early_res array");
-
-	new = __va(mem);
-	/* save the first one for own */
-	new[0].start = mem;
-	new[0].end = mem + size;
-	new[0].overlap_ok = 0;
-	/* copy old to new */
-	if (early_res == early_res_x) {
-		memcpy(&new[1], &early_res[0],
-			 sizeof(struct early_res) * max_early_res);
-		memset(&new[max_early_res+1], 0,
-			 sizeof(struct early_res) * (max_early_res - 1));
-		early_res_count++;
-	} else {
-		memcpy(&new[1], &early_res[1],
-			 sizeof(struct early_res) * (max_early_res - 1));
-		memset(&new[max_early_res], 0,
-			 sizeof(struct early_res) * max_early_res);
-	}
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = new;
-	max_early_res *= 2;
-	printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
-		max_early_res, mem, mem + size - 1);
-}
-
-/*
- * Most early reservations come here.
- *
- * We first have drop_overlaps_that_are_ok() drop any pre-existing
- * 'overlap_ok' ranges, so that we can then reserve this memory
- * range without risk of panic'ing on an overlapping overlap_ok
- * early reservation.
- */
-void __init reserve_early(u64 start, u64 end, char *name)
-{
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(start, end);
-
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 0);
-}
-
-void __init reserve_early_without_check(u64 start, u64 end, char *name)
-{
-	struct early_res *r;
-
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(start, end);
-
-	r = &early_res[early_res_count];
-
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = 0;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-void __init free_early(u64 start, u64 end)
-{
-	struct early_res *r;
-	int i;
-
-	kmemleak_free_part(__va(start), end - start);
-
-	i = find_overlapped_early(start, end);
-	r = &early_res[i];
-	if (i >= max_early_res || r->end != end || r->start != start)
-		panic("free_early on not reserved area: %llx-%llx!",
-			 start, end - 1);
-
-	drop_range(i);
-}
-
-void __init free_early_partial(u64 start, u64 end)
-{
-	struct early_res *r;
-	int i;
-
-	kmemleak_free_part(__va(start), end - start);
-
-	if (start == end)
-		return;
-
-	if (WARN_ONCE(start > end, "  wrong range [%#llx, %#llx]\n", start, end))
-		return;
-
-try_next:
-	i = find_overlapped_early(start, end);
-	if (i >= max_early_res)
-		return;
-
-	r = &early_res[i];
-	/* hole ? */
-	if (r->end >= end && r->start <= start) {
-		drop_range_partial(i, start, end);
-		return;
-	}
-
-	drop_range_partial(i, start, end);
-	goto try_next;
-}
-
-#ifdef CONFIG_NO_BOOTMEM
-static void __init subtract_early_res(struct range *range, int az)
-{
-	int i, count;
-	u64 final_start, final_end;
-	int idx = 0;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-#define DEBUG_PRINT_EARLY_RES 1
-
-#if DEBUG_PRINT_EARLY_RES
-	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
-#endif
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
-#if DEBUG_PRINT_EARLY_RES
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s\n", i,
-			r->start, r->end, r->name);
-#endif
-		final_start = PFN_DOWN(r->start);
-		final_end = PFN_UP(r->end);
-		if (final_start >= final_end)
-			continue;
-		subtract_range(range, az, final_start, final_end);
-	}
-
-}
-
-int __init get_free_all_memory_range(struct range **rangep, int nodeid)
-{
-	int i, count;
-	u64 start = 0, end;
-	u64 size;
-	u64 mem;
-	struct range *range;
-	int nr_range;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	count *= 2;
-
-	size = sizeof(struct range) * count;
-	end = get_max_mapped();
-#ifdef MAX_DMA32_PFN
-	if (end > (MAX_DMA32_PFN << PAGE_SHIFT))
-		start = MAX_DMA32_PFN << PAGE_SHIFT;
-#endif
-	mem = find_fw_memmap_area(start, end, size, sizeof(struct range));
-	if (mem == -1ULL)
-		panic("can not find more space for range free");
-
-	range = __va(mem);
-	/* use early_node_map[] and early_res to get range array at first */
-	memset(range, 0, size);
-	nr_range = 0;
-
-	/* need to go over early_node_map to find out good range for node */
-	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
-#ifdef CONFIG_X86_32
-	subtract_range(range, count, max_low_pfn, -1ULL);
-#endif
-	subtract_early_res(range, count);
-	nr_range = clean_sort_range(range, count);
-
-	/* need to clear it ? */
-	if (nodeid == MAX_NUMNODES) {
-		memset(&early_res[0], 0,
-			 sizeof(struct early_res) * max_early_res);
-		early_res = NULL;
-		max_early_res = 0;
-	}
-
-	*rangep = range;
-	return nr_range;
-}
-#else
-void __init early_res_to_bootmem(u64 start, u64 end)
-{
-	int i, count;
-	u64 final_start, final_end;
-	int idx = 0;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
-			 count - idx, max_early_res, start, end);
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
-			r->start, r->end, r->name);
-		final_start = max(start, r->start);
-		final_end = min(end, r->end);
-		if (final_start >= final_end) {
-			printk(KERN_CONT "\n");
-			continue;
-		}
-		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
-			final_start, final_end);
-		reserve_bootmem_generic(final_start, final_end - final_start,
-				BOOTMEM_DEFAULT);
-	}
-	/* clear them */
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = NULL;
-	max_early_res = 0;
-	early_res_count = 0;
-}
-#endif
-
-/* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
-{
-	int i;
-	u64 addr = *addrp;
-	int changed = 0;
-	struct early_res *r;
-again:
-	i = find_overlapped_early(addr, addr + size);
-	r = &early_res[i];
-	if (i < max_early_res && r->end) {
-		*addrp = addr = round_up(r->end, align);
-		changed = 1;
-		goto again;
-	}
-	return changed;
-}
-
-/* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
-{
-	int i;
-	u64 addr = *addrp, last;
-	u64 size = *sizep;
-	int changed = 0;
-again:
-	last = addr + size;
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		struct early_res *r = &early_res[i];
-		if (last > r->start && addr < r->start) {
-			size = r->start - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last > r->end && addr < r->end) {
-			addr = round_up(r->end, align);
-			size = last - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last <= r->end && addr >= r->start) {
-			(*sizep)++;
-			return 0;
-		}
-	}
-	if (changed) {
-		*addrp = addr;
-		*sizep = size;
-	}
-	return changed;
-}
-
-/*
- * Find a free area with specified alignment in a specific range.
- * only with the area.between start to end is active range from early_node_map
- * so they are good as RAM
- */
-u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align)
-{
-	u64 addr, last;
-
-	addr = round_up(ei_start, align);
-	if (addr < start)
-		addr = round_up(start, align);
-	if (addr >= ei_last)
-		goto out;
-	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
-		;
-	last = addr + size;
-	if (last > ei_last)
-		goto out;
-	if (last > end)
-		goto out;
-
-	return addr;
-
-out:
-	return -1ULL;
-}
-
-u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
-			 u64 *sizep, u64 align)
-{
-	u64 addr, last;
-
-	addr = round_up(ei_start, align);
-	if (addr < start)
-		addr = round_up(start, align);
-	if (addr >= ei_last)
-		goto out;
-	*sizep = ei_last - addr;
-	while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
-		;
-	last = addr + *sizep;
-	if (last > ei_last)
-		goto out;
-
-	return addr;
-
-out:
-	return -1ULL;
-}
diff --git a/kernel/exit.c b/kernel/exit.c
index 03120229db28..e2bdf37f9fde 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -149,9 +149,7 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
-#ifdef CONFIG_PERF_EVENTS
-	WARN_ON_ONCE(tsk->perf_event_ctxp);
-#endif
+	perf_event_delayed_put(tsk);
 	trace_sched_process_free(tsk);
 	put_task_struct(tsk);
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index 6a3a5fa1526d..92a31d4cd564 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1360,6 +1360,7 @@ out:
 
 /* The key must be already stored in q->key. */
 static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
+	__acquires(&hb->lock)
 {
 	struct futex_hash_bucket *hb;
 
@@ -1373,6 +1374,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 
 static inline void
 queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+	__releases(&hb->lock)
 {
 	spin_unlock(&hb->lock);
 	drop_futex_key_refs(&q->key);
@@ -1391,6 +1393,7 @@ queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
  * an example).
  */
 static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
+	__releases(&hb->lock)
 {
 	int prio;
 
@@ -1471,6 +1474,7 @@ retry:
  * and dropped here.
  */
 static void unqueue_me_pi(struct futex_q *q)
+	__releases(q->lock_ptr)
 {
 	WARN_ON(plist_node_empty(&q->list));
 	plist_del(&q->list, &q->list.plist);
@@ -1843,7 +1847,7 @@ retry:
 
 	restart = &current_thread_info()->restart_block;
 	restart->fn = futex_wait_restart;
-	restart->futex.uaddr = (u32 *)uaddr;
+	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
 	restart->futex.time = abs_time->tv64;
 	restart->futex.bitset = bitset;
@@ -1869,7 +1873,7 @@ out:
 
 static long futex_wait_restart(struct restart_block *restart)
 {
-	u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
+	u32 __user *uaddr = restart->futex.uaddr;
 	int fshared = 0;
 	ktime_t t, *tp = NULL;
 
@@ -2458,7 +2462,7 @@ retry:
  */
 static inline int fetch_robust_entry(struct robust_list __user **entry,
 				     struct robust_list __user * __user *head,
-				     int *pi)
+				     unsigned int *pi)
 {
 	unsigned long uentry;
 
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index d49afb2395e5..06da4dfc339b 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -19,7 +19,7 @@
  */
 static inline int
 fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
-		   compat_uptr_t __user *head, int *pi)
+		   compat_uptr_t __user *head, unsigned int *pi)
 {
 	if (get_user(*uentry, head))
 		return -EFAULT;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 0c642d51aac2..53ead174da2f 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -98,7 +98,7 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 	printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
 			" disables this message.\n");
 	sched_show_task(t);
-	__debug_show_held_locks(t);
+	debug_show_held_locks(t);
 
 	touch_nmi_watchdog();
 
@@ -111,7 +111,7 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
  * periodically exit the critical section and enter a new one.
  *
  * For preemptible RCU it is sufficient to call rcu_read_unlock in order
- * exit the grace period. For classic RCU, a reschedule is required.
+ * to exit the grace period. For classic RCU, a reschedule is required.
  */
 static void rcu_lock_break(struct task_struct *g, struct task_struct *t)
 {
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index c7c2aed9e2dc..3b714e839c10 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -433,8 +433,7 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
 			    struct task_struct *tsk)
 {
-	return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk),
-						triggered);
+	return perf_event_create_kernel_counter(attr, -1, tsk, triggered);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
@@ -516,7 +515,7 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		pevent = per_cpu_ptr(cpu_events, cpu);
-		bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered);
+		bp = perf_event_create_kernel_counter(attr, cpu, NULL, triggered);
 
 		*pevent = bp;
 
@@ -566,6 +565,61 @@ static struct notifier_block hw_breakpoint_exceptions_nb = {
 	.priority = 0x7fffffff
 };
 
+static void bp_perf_event_destroy(struct perf_event *event)
+{
+	release_bp_slot(event);
+}
+
+static int hw_breakpoint_event_init(struct perf_event *bp)
+{
+	int err;
+
+	if (bp->attr.type != PERF_TYPE_BREAKPOINT)
+		return -ENOENT;
+
+	err = register_perf_hw_breakpoint(bp);
+	if (err)
+		return err;
+
+	bp->destroy = bp_perf_event_destroy;
+
+	return 0;
+}
+
+static int hw_breakpoint_add(struct perf_event *bp, int flags)
+{
+	if (!(flags & PERF_EF_START))
+		bp->hw.state = PERF_HES_STOPPED;
+
+	return arch_install_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_del(struct perf_event *bp, int flags)
+{
+	arch_uninstall_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_start(struct perf_event *bp, int flags)
+{
+	bp->hw.state = 0;
+}
+
+static void hw_breakpoint_stop(struct perf_event *bp, int flags)
+{
+	bp->hw.state = PERF_HES_STOPPED;
+}
+
+static struct pmu perf_breakpoint = {
+	.task_ctx_nr	= perf_sw_context, /* could eventually get its own */
+
+	.event_init	= hw_breakpoint_event_init,
+	.add		= hw_breakpoint_add,
+	.del		= hw_breakpoint_del,
+	.start		= hw_breakpoint_start,
+	.stop		= hw_breakpoint_stop,
+	.read		= hw_breakpoint_pmu_read,
+};
+
 static int __init init_hw_breakpoint(void)
 {
 	unsigned int **task_bp_pinned;
@@ -587,6 +641,8 @@ static int __init init_hw_breakpoint(void)
 
 	constraints_initialized = 1;
 
+	perf_pmu_register(&perf_breakpoint);
+
 	return register_die_notifier(&hw_breakpoint_exceptions_nb);
 
  err_alloc:
@@ -602,8 +658,3 @@ static int __init init_hw_breakpoint(void)
 core_initcall(init_hw_breakpoint);
 
 
-struct pmu perf_ops_bp = {
-	.enable		= arch_install_hw_breakpoint,
-	.disable	= arch_uninstall_hw_breakpoint,
-	.read		= hw_breakpoint_pmu_read,
-};
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
new file mode 100644
index 000000000000..a42c0191d71a
--- /dev/null
+++ b/kernel/irq/Kconfig
@@ -0,0 +1,58 @@
+config HAVE_GENERIC_HARDIRQS
+	def_bool n
+
+if HAVE_GENERIC_HARDIRQS
+menu "IRQ subsystem"
+#
+# Interrupt subsystem related configuration options
+#
+config GENERIC_HARDIRQS
+       def_bool y
+
+config GENERIC_HARDIRQS_NO__DO_IRQ
+       def_bool y
+
+# Select this to disable the deprecated stuff
+config GENERIC_HARDIRQS_NO_DEPRECATED
+       def_bool n
+
+# Options selectable by the architecture code
+config HAVE_SPARSE_IRQ
+       def_bool n
+
+config GENERIC_IRQ_PROBE
+	def_bool n
+
+config GENERIC_PENDING_IRQ
+	def_bool n
+
+if SPARSE_IRQ && NUMA
+config NUMA_IRQ_DESC
+	def_bool n
+endif
+
+config AUTO_IRQ_AFFINITY
+       def_bool n
+
+config IRQ_PER_CPU
+       def_bool n
+
+config HARDIRQS_SW_RESEND
+       def_bool n
+
+config SPARSE_IRQ
+	bool "Support sparse irq numbering"
+	depends on HAVE_SPARSE_IRQ
+	---help---
+
+	  Sparse irq numbering is useful for distro kernels that want
+	  to define a high CONFIG_NR_CPUS value but still want to have
+	  low kernel memory footprint on smaller machines.
+
+	  ( Sparse irqs can also be beneficial on NUMA boxes, as they spread
+	    out the interrupt descriptors in a more NUMA-friendly way. )
+
+	  If you don't know what to do here, say N.
+
+endmenu
+endif
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 2295a31ef110..505798f86c36 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -57,9 +57,10 @@ unsigned long probe_irq_on(void)
 			 * Some chips need to know about probing in
 			 * progress:
 			 */
-			if (desc->chip->set_type)
-				desc->chip->set_type(i, IRQ_TYPE_PROBE);
-			desc->chip->startup(i);
+			if (desc->irq_data.chip->irq_set_type)
+				desc->irq_data.chip->irq_set_type(&desc->irq_data,
+							 IRQ_TYPE_PROBE);
+			desc->irq_data.chip->irq_startup(&desc->irq_data);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -76,7 +77,7 @@ unsigned long probe_irq_on(void)
 		raw_spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
 			desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
-			if (desc->chip->startup(i))
+			if (desc->irq_data.chip->irq_startup(&desc->irq_data))
 				desc->status |= IRQ_PENDING;
 		}
 		raw_spin_unlock_irq(&desc->lock);
@@ -98,7 +99,7 @@ unsigned long probe_irq_on(void)
 			/* It triggered already - consider it spurious. */
 			if (!(status & IRQ_WAITING)) {
 				desc->status = status & ~IRQ_AUTODETECT;
-				desc->chip->shutdown(i);
+				desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 			} else
 				if (i < 32)
 					mask |= 1 << i;
@@ -137,7 +138,7 @@ unsigned int probe_irq_mask(unsigned long val)
 				mask |= 1 << i;
 
 			desc->status = status & ~IRQ_AUTODETECT;
-			desc->chip->shutdown(i);
+			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -181,7 +182,7 @@ int probe_irq_off(unsigned long val)
 				nr_of_irqs++;
 			}
 			desc->status = status & ~IRQ_AUTODETECT;
-			desc->chip->shutdown(i);
+			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b7091d5ca2f8..323547983f15 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -32,18 +32,18 @@ static void dynamic_irq_init_x(unsigned int irq, bool keep_chip_data)
 	/* Ensure we don't have left over values from a previous use of this irq */
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	desc->status = IRQ_DISABLED;
-	desc->chip = &no_irq_chip;
+	desc->irq_data.chip = &no_irq_chip;
 	desc->handle_irq = handle_bad_irq;
 	desc->depth = 1;
-	desc->msi_desc = NULL;
-	desc->handler_data = NULL;
+	desc->irq_data.msi_desc = NULL;
+	desc->irq_data.handler_data = NULL;
 	if (!keep_chip_data)
-		desc->chip_data = NULL;
+		desc->irq_data.chip_data = NULL;
 	desc->action = NULL;
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
 #ifdef CONFIG_SMP
-	cpumask_setall(desc->affinity);
+	cpumask_setall(desc->irq_data.affinity);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_clear(desc->pending_mask);
 #endif
@@ -64,7 +64,7 @@ void dynamic_irq_init(unsigned int irq)
  *	dynamic_irq_init_keep_chip_data - initialize a dynamically allocated irq
  *	@irq:	irq number to initialize
  *
- *	does not set irq_to_desc(irq)->chip_data to NULL
+ *	does not set irq_to_desc(irq)->irq_data.chip_data to NULL
  */
 void dynamic_irq_init_keep_chip_data(unsigned int irq)
 {
@@ -88,12 +88,12 @@ static void dynamic_irq_cleanup_x(unsigned int irq, bool keep_chip_data)
 			irq);
 		return;
 	}
-	desc->msi_desc = NULL;
-	desc->handler_data = NULL;
+	desc->irq_data.msi_desc = NULL;
+	desc->irq_data.handler_data = NULL;
 	if (!keep_chip_data)
-		desc->chip_data = NULL;
+		desc->irq_data.chip_data = NULL;
 	desc->handle_irq = handle_bad_irq;
-	desc->chip = &no_irq_chip;
+	desc->irq_data.chip = &no_irq_chip;
 	desc->name = NULL;
 	clear_kstat_irqs(desc);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -112,7 +112,7 @@ void dynamic_irq_cleanup(unsigned int irq)
  *	dynamic_irq_cleanup_keep_chip_data - cleanup a dynamically allocated irq
  *	@irq:	irq number to initialize
  *
- *	does not set irq_to_desc(irq)->chip_data to NULL
+ *	does not set irq_to_desc(irq)->irq_data.chip_data to NULL
  */
 void dynamic_irq_cleanup_keep_chip_data(unsigned int irq)
 {
@@ -140,7 +140,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	irq_chip_set_defaults(chip);
-	desc->chip = chip;
+	desc->irq_data.chip = chip;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	return 0;
@@ -193,7 +193,7 @@ int set_irq_data(unsigned int irq, void *data)
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->handler_data = data;
+	desc->irq_data.handler_data = data;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
 }
@@ -218,7 +218,7 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->msi_desc = entry;
+	desc->irq_data.msi_desc = entry;
 	if (entry)
 		entry->irq = irq;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -243,13 +243,13 @@ int set_irq_chip_data(unsigned int irq, void *data)
 		return -EINVAL;
 	}
 
-	if (!desc->chip) {
+	if (!desc->irq_data.chip) {
 		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
 		return -EINVAL;
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->chip_data = data;
+	desc->irq_data.chip_data = data;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	return 0;
@@ -287,93 +287,216 @@ EXPORT_SYMBOL_GPL(set_irq_nested_thread);
 /*
  * default enable function
  */
-static void default_enable(unsigned int irq)
+static void default_enable(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	desc->chip->unmask(irq);
+	desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	desc->status &= ~IRQ_MASKED;
 }
 
 /*
  * default disable function
  */
-static void default_disable(unsigned int irq)
+static void default_disable(struct irq_data *data)
 {
 }
 
 /*
  * default startup function
  */
-static unsigned int default_startup(unsigned int irq)
+static unsigned int default_startup(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	desc->chip->enable(irq);
+	desc->irq_data.chip->irq_enable(data);
 	return 0;
 }
 
 /*
  * default shutdown function
  */
-static void default_shutdown(unsigned int irq)
+static void default_shutdown(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	desc->chip->mask(irq);
+	desc->irq_data.chip->irq_mask(&desc->irq_data);
 	desc->status |= IRQ_MASKED;
 }
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+/* Temporary migration helpers */
+static void compat_irq_mask(struct irq_data *data)
+{
+	data->chip->mask(data->irq);
+}
+
+static void compat_irq_unmask(struct irq_data *data)
+{
+	data->chip->unmask(data->irq);
+}
+
+static void compat_irq_ack(struct irq_data *data)
+{
+	data->chip->ack(data->irq);
+}
+
+static void compat_irq_mask_ack(struct irq_data *data)
+{
+	data->chip->mask_ack(data->irq);
+}
+
+static void compat_irq_eoi(struct irq_data *data)
+{
+	data->chip->eoi(data->irq);
+}
+
+static void compat_irq_enable(struct irq_data *data)
+{
+	data->chip->enable(data->irq);
+}
+
+static void compat_irq_disable(struct irq_data *data)
+{
+	data->chip->disable(data->irq);
+}
+
+static void compat_irq_shutdown(struct irq_data *data)
+{
+	data->chip->shutdown(data->irq);
+}
+
+static unsigned int compat_irq_startup(struct irq_data *data)
+{
+	return data->chip->startup(data->irq);
+}
+
+static int compat_irq_set_affinity(struct irq_data *data,
+				   const struct cpumask *dest, bool force)
+{
+	return data->chip->set_affinity(data->irq, dest);
+}
+
+static int compat_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	return data->chip->set_type(data->irq, type);
+}
+
+static int compat_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+	return data->chip->set_wake(data->irq, on);
+}
+
+static int compat_irq_retrigger(struct irq_data *data)
+{
+	return data->chip->retrigger(data->irq);
+}
+
+static void compat_bus_lock(struct irq_data *data)
+{
+	data->chip->bus_lock(data->irq);
+}
+
+static void compat_bus_sync_unlock(struct irq_data *data)
+{
+	data->chip->bus_sync_unlock(data->irq);
+}
+#endif
+
 /*
  * Fixup enable/disable function pointers
  */
 void irq_chip_set_defaults(struct irq_chip *chip)
 {
-	if (!chip->enable)
-		chip->enable = default_enable;
-	if (!chip->disable)
-		chip->disable = default_disable;
-	if (!chip->startup)
-		chip->startup = default_startup;
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+	/*
+	 * Compat fixup functions need to be before we set the
+	 * defaults for enable/disable/startup/shutdown
+	 */
+	if (chip->enable)
+		chip->irq_enable = compat_irq_enable;
+	if (chip->disable)
+		chip->irq_disable = compat_irq_disable;
+	if (chip->shutdown)
+		chip->irq_shutdown = compat_irq_shutdown;
+	if (chip->startup)
+		chip->irq_startup = compat_irq_startup;
+#endif
 	/*
-	 * We use chip->disable, when the user provided its own. When
-	 * we have default_disable set for chip->disable, then we need
+	 * The real defaults
+	 */
+	if (!chip->irq_enable)
+		chip->irq_enable = default_enable;
+	if (!chip->irq_disable)
+		chip->irq_disable = default_disable;
+	if (!chip->irq_startup)
+		chip->irq_startup = default_startup;
+	/*
+	 * We use chip->irq_disable, when the user provided its own. When
+	 * we have default_disable set for chip->irq_disable, then we need
 	 * to use default_shutdown, otherwise the irq line is not
 	 * disabled on free_irq():
 	 */
-	if (!chip->shutdown)
-		chip->shutdown = chip->disable != default_disable ?
-			chip->disable : default_shutdown;
-	if (!chip->name)
-		chip->name = chip->typename;
+	if (!chip->irq_shutdown)
+		chip->irq_shutdown = chip->irq_disable != default_disable ?
+			chip->irq_disable : default_shutdown;
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	if (!chip->end)
 		chip->end = dummy_irq_chip.end;
+
+	/*
+	 * Now fix up the remaining compat handlers
+	 */
+	if (chip->bus_lock)
+		chip->irq_bus_lock = compat_bus_lock;
+	if (chip->bus_sync_unlock)
+		chip->irq_bus_sync_unlock = compat_bus_sync_unlock;
+	if (chip->mask)
+		chip->irq_mask = compat_irq_mask;
+	if (chip->unmask)
+		chip->irq_unmask = compat_irq_unmask;
+	if (chip->ack)
+		chip->irq_ack = compat_irq_ack;
+	if (chip->mask_ack)
+		chip->irq_mask_ack = compat_irq_mask_ack;
+	if (chip->eoi)
+		chip->irq_eoi = compat_irq_eoi;
+	if (chip->set_affinity)
+		chip->irq_set_affinity = compat_irq_set_affinity;
+	if (chip->set_type)
+		chip->irq_set_type = compat_irq_set_type;
+	if (chip->set_wake)
+		chip->irq_set_wake = compat_irq_set_wake;
+	if (chip->retrigger)
+		chip->irq_retrigger = compat_irq_retrigger;
+#endif
 }
 
-static inline void mask_ack_irq(struct irq_desc *desc, int irq)
+static inline void mask_ack_irq(struct irq_desc *desc)
 {
-	if (desc->chip->mask_ack)
-		desc->chip->mask_ack(irq);
+	if (desc->irq_data.chip->irq_mask_ack)
+		desc->irq_data.chip->irq_mask_ack(&desc->irq_data);
 	else {
-		desc->chip->mask(irq);
-		if (desc->chip->ack)
-			desc->chip->ack(irq);
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
+		if (desc->irq_data.chip->irq_ack)
+			desc->irq_data.chip->irq_ack(&desc->irq_data);
 	}
 	desc->status |= IRQ_MASKED;
 }
 
-static inline void mask_irq(struct irq_desc *desc, int irq)
+static inline void mask_irq(struct irq_desc *desc)
 {
-	if (desc->chip->mask) {
-		desc->chip->mask(irq);
+	if (desc->irq_data.chip->irq_mask) {
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
 		desc->status |= IRQ_MASKED;
 	}
 }
 
-static inline void unmask_irq(struct irq_desc *desc, int irq)
+static inline void unmask_irq(struct irq_desc *desc)
 {
-	if (desc->chip->unmask) {
-		desc->chip->unmask(irq);
+	if (desc->irq_data.chip->irq_unmask) {
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 		desc->status &= ~IRQ_MASKED;
 	}
 }
@@ -476,7 +599,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	irqreturn_t action_ret;
 
 	raw_spin_lock(&desc->lock);
-	mask_ack_irq(desc, irq);
+	mask_ack_irq(desc);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
@@ -502,7 +625,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	desc->status &= ~IRQ_INPROGRESS;
 
 	if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
-		unmask_irq(desc, irq);
+		unmask_irq(desc);
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -539,7 +662,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
 		desc->status |= IRQ_PENDING;
-		mask_irq(desc, irq);
+		mask_irq(desc);
 		goto out;
 	}
 
@@ -554,7 +677,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 	desc->status &= ~IRQ_INPROGRESS;
 out:
-	desc->chip->eoi(irq);
+	desc->irq_data.chip->irq_eoi(&desc->irq_data);
 
 	raw_spin_unlock(&desc->lock);
 }
@@ -590,14 +713,13 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) ||
 		    !desc->action)) {
 		desc->status |= (IRQ_PENDING | IRQ_MASKED);
-		mask_ack_irq(desc, irq);
+		mask_ack_irq(desc);
 		goto out_unlock;
 	}
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Start handling the irq */
-	if (desc->chip->ack)
-		desc->chip->ack(irq);
+	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
 	/* Mark the IRQ currently in progress.*/
 	desc->status |= IRQ_INPROGRESS;
@@ -607,7 +729,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		irqreturn_t action_ret;
 
 		if (unlikely(!action)) {
-			mask_irq(desc, irq);
+			mask_irq(desc);
 			goto out_unlock;
 		}
 
@@ -619,7 +741,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		if (unlikely((desc->status &
 			       (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
 			      (IRQ_PENDING | IRQ_MASKED))) {
-			unmask_irq(desc, irq);
+			unmask_irq(desc);
 		}
 
 		desc->status &= ~IRQ_PENDING;
@@ -650,15 +772,15 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	if (desc->chip->ack)
-		desc->chip->ack(irq);
+	if (desc->irq_data.chip->irq_ack)
+		desc->irq_data.chip->irq_ack(&desc->irq_data);
 
 	action_ret = handle_IRQ_event(irq, desc->action);
 	if (!noirqdebug)
 		note_interrupt(irq, desc, action_ret);
 
-	if (desc->chip->eoi)
-		desc->chip->eoi(irq);
+	if (desc->irq_data.chip->irq_eoi)
+		desc->irq_data.chip->irq_eoi(&desc->irq_data);
 }
 
 void
@@ -676,7 +798,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 
 	if (!handle)
 		handle = handle_bad_irq;
-	else if (desc->chip == &no_irq_chip) {
+	else if (desc->irq_data.chip == &no_irq_chip) {
 		printk(KERN_WARNING "Trying to install %sinterrupt handler "
 		       "for IRQ%d\n", is_chained ? "chained " : "", irq);
 		/*
@@ -686,16 +808,16 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		 * prevent us to setup the interrupt at all. Switch it to
 		 * dummy_irq_chip for easy transition.
 		 */
-		desc->chip = &dummy_irq_chip;
+		desc->irq_data.chip = &dummy_irq_chip;
 	}
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
 	/* Uninstall? */
 	if (handle == handle_bad_irq) {
-		if (desc->chip != &no_irq_chip)
-			mask_ack_irq(desc, irq);
+		if (desc->irq_data.chip != &no_irq_chip)
+			mask_ack_irq(desc);
 		desc->status |= IRQ_DISABLED;
 		desc->depth = 1;
 	}
@@ -706,10 +828,10 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		desc->status &= ~IRQ_DISABLED;
 		desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
 		desc->depth = 0;
-		desc->chip->startup(irq);
+		desc->irq_data.chip->irq_startup(&desc->irq_data);
 	}
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL_GPL(__set_irq_handler);
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 27e5c6911223..3fcef37154a1 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -75,12 +75,10 @@ EXPORT_SYMBOL_GPL(nr_irqs);
 #ifdef CONFIG_SPARSE_IRQ
 
 static struct irq_desc irq_desc_init = {
-	.irq	    = -1,
-	.status	    = IRQ_DISABLED,
-	.chip	    = &no_irq_chip,
-	.handle_irq = handle_bad_irq,
-	.depth      = 1,
-	.lock       = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
+	.status		= IRQ_DISABLED,
+	.handle_irq	= handle_bad_irq,
+	.depth		= 1,
+	.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
 };
 
 void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
@@ -105,9 +103,9 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
 	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
 
 	raw_spin_lock_init(&desc->lock);
-	desc->irq = irq;
+	desc->irq_data.irq = irq;
 #ifdef CONFIG_SMP
-	desc->node = node;
+	desc->irq_data.node = node;
 #endif
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	init_kstat_irqs(desc, node, nr_cpu_ids);
@@ -151,12 +149,10 @@ void replace_irq_desc(unsigned int irq, struct irq_desc *desc)
 
 static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS_LEGACY-1] = {
-		.irq	    = -1,
-		.status	    = IRQ_DISABLED,
-		.chip	    = &no_irq_chip,
-		.handle_irq = handle_bad_irq,
-		.depth	    = 1,
-		.lock	    = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
+		.status		= IRQ_DISABLED,
+		.handle_irq	= handle_bad_irq,
+		.depth		= 1,
+		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
 	}
 };
 
@@ -183,10 +179,13 @@ int __init early_irq_init(void)
 	kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
 					  sizeof(int), GFP_NOWAIT, node);
 
+	irq_desc_init.irq_data.chip = &no_irq_chip;
+
 	for (i = 0; i < legacy_count; i++) {
-		desc[i].irq = i;
+		desc[i].irq_data.irq = i;
+		desc[i].irq_data.chip = &no_irq_chip;
 #ifdef CONFIG_SMP
-		desc[i].node = node;
+		desc[i].irq_data.node = node;
 #endif
 		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
@@ -241,11 +240,10 @@ out_unlock:
 
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
-		.status = IRQ_DISABLED,
-		.chip = &no_irq_chip,
-		.handle_irq = handle_bad_irq,
-		.depth = 1,
-		.lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
+		.status		= IRQ_DISABLED,
+		.handle_irq	= handle_bad_irq,
+		.depth		= 1,
+		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
 	}
 };
 
@@ -264,7 +262,8 @@ int __init early_irq_init(void)
 	count = ARRAY_SIZE(irq_desc);
 
 	for (i = 0; i < count; i++) {
-		desc[i].irq = i;
+		desc[i].irq_data.irq = i;
+		desc[i].irq_data.chip = &no_irq_chip;
 		alloc_desc_masks(&desc[i], 0, true);
 		init_desc_masks(&desc[i]);
 		desc[i].kstat_irqs = kstat_irqs_all[i];
@@ -292,37 +291,42 @@ void clear_kstat_irqs(struct irq_desc *desc)
  * What should we do if we get a hw irq event on an illegal vector?
  * Each architecture has to answer this themself.
  */
-static void ack_bad(unsigned int irq)
+static void ack_bad(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	print_irq_desc(irq, desc);
-	ack_bad_irq(irq);
+	print_irq_desc(data->irq, desc);
+	ack_bad_irq(data->irq);
 }
 
 /*
  * NOP functions
  */
-static void noop(unsigned int irq)
-{
-}
+static void noop(struct irq_data *data) { }
 
-static unsigned int noop_ret(unsigned int irq)
+static unsigned int noop_ret(struct irq_data *data)
 {
 	return 0;
 }
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+static void compat_noop(unsigned int irq) { }
+#define END_INIT .end = compat_noop
+#else
+#define END_INIT
+#endif
+
 /*
  * Generic no controller implementation
  */
 struct irq_chip no_irq_chip = {
 	.name		= "none",
-	.startup	= noop_ret,
-	.shutdown	= noop,
-	.enable		= noop,
-	.disable	= noop,
-	.ack		= ack_bad,
-	.end		= noop,
+	.irq_startup	= noop_ret,
+	.irq_shutdown	= noop,
+	.irq_enable	= noop,
+	.irq_disable	= noop,
+	.irq_ack	= ack_bad,
+	END_INIT
 };
 
 /*
@@ -331,14 +335,14 @@ struct irq_chip no_irq_chip = {
  */
 struct irq_chip dummy_irq_chip = {
 	.name		= "dummy",
-	.startup	= noop_ret,
-	.shutdown	= noop,
-	.enable		= noop,
-	.disable	= noop,
-	.ack		= noop,
-	.mask		= noop,
-	.unmask		= noop,
-	.end		= noop,
+	.irq_startup	= noop_ret,
+	.irq_shutdown	= noop,
+	.irq_enable	= noop,
+	.irq_disable	= noop,
+	.irq_ack	= noop,
+	.irq_mask	= noop,
+	.irq_unmask	= noop,
+	END_INIT
 };
 
 /*
@@ -457,20 +461,20 @@ unsigned int __do_IRQ(unsigned int irq)
 		/*
 		 * No locking required for CPU-local interrupts:
 		 */
-		if (desc->chip->ack)
-			desc->chip->ack(irq);
+		if (desc->irq_data.chip->ack)
+			desc->irq_data.chip->ack(irq);
 		if (likely(!(desc->status & IRQ_DISABLED))) {
 			action_ret = handle_IRQ_event(irq, desc->action);
 			if (!noirqdebug)
 				note_interrupt(irq, desc, action_ret);
 		}
-		desc->chip->end(irq);
+		desc->irq_data.chip->end(irq);
 		return 1;
 	}
 
 	raw_spin_lock(&desc->lock);
-	if (desc->chip->ack)
-		desc->chip->ack(irq);
+	if (desc->irq_data.chip->ack)
+		desc->irq_data.chip->ack(irq);
 	/*
 	 * REPLAY is when Linux resends an IRQ that was dropped earlier
 	 * WAITING is used by probe to mark irqs that are being tested
@@ -530,7 +534,7 @@ out:
 	 * The ->end() handler has to deal with interrupts which got
 	 * disabled while the handler was running.
 	 */
-	desc->chip->end(irq);
+	desc->irq_data.chip->end(irq);
 	raw_spin_unlock(&desc->lock);
 
 	return 1;
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index c63f3bc88f0b..b905f0ab1bb2 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -4,6 +4,8 @@
 
 extern int noirqdebug;
 
+#define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
+
 /* Set default functions for irq_chip structures: */
 extern void irq_chip_set_defaults(struct irq_chip *chip);
 
@@ -40,17 +42,27 @@ extern int irq_select_affinity_usr(unsigned int irq);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+static inline void irq_end(unsigned int irq, struct irq_desc *desc)
+{
+	if (desc->irq_data.chip && desc->irq_data.chip->end)
+		desc->irq_data.chip->end(irq);
+}
+#else
+static inline void irq_end(unsigned int irq, struct irq_desc *desc) { }
+#endif
+
 /* Inline functions for support of irq chips on slow busses */
-static inline void chip_bus_lock(unsigned int irq, struct irq_desc *desc)
+static inline void chip_bus_lock(struct irq_desc *desc)
 {
-	if (unlikely(desc->chip->bus_lock))
-		desc->chip->bus_lock(irq);
+	if (unlikely(desc->irq_data.chip->irq_bus_lock))
+		desc->irq_data.chip->irq_bus_lock(&desc->irq_data);
 }
 
-static inline void chip_bus_sync_unlock(unsigned int irq, struct irq_desc *desc)
+static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 {
-	if (unlikely(desc->chip->bus_sync_unlock))
-		desc->chip->bus_sync_unlock(irq);
+	if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock))
+		desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
 }
 
 /*
@@ -67,8 +79,8 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 		irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
 	printk("->handle_irq():  %p, ", desc->handle_irq);
 	print_symbol("%s\n", (unsigned long)desc->handle_irq);
-	printk("->chip(): %p, ", desc->chip);
-	print_symbol("%s\n", (unsigned long)desc->chip);
+	printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
+	print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
 	printk("->action(): %p\n", desc->action);
 	if (desc->action) {
 		printk("->action->handler(): %p, ", desc->action->handler);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c3003e9d91a3..644e8d5fa367 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -73,8 +73,8 @@ int irq_can_set_affinity(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip ||
-	    !desc->chip->set_affinity)
+	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->irq_data.chip ||
+	    !desc->irq_data.chip->irq_set_affinity)
 		return 0;
 
 	return 1;
@@ -109,17 +109,18 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_chip *chip = desc->irq_data.chip;
 	unsigned long flags;
 
-	if (!desc->chip->set_affinity)
+	if (!chip->irq_set_affinity)
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PCNTXT) {
-		if (!desc->chip->set_affinity(irq, cpumask)) {
-			cpumask_copy(desc->affinity, cpumask);
+		if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
+			cpumask_copy(desc->irq_data.affinity, cpumask);
 			irq_set_thread_affinity(desc);
 		}
 	}
@@ -128,8 +129,8 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 		cpumask_copy(desc->pending_mask, cpumask);
 	}
 #else
-	if (!desc->chip->set_affinity(irq, cpumask)) {
-		cpumask_copy(desc->affinity, cpumask);
+	if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
+		cpumask_copy(desc->irq_data.affinity, cpumask);
 		irq_set_thread_affinity(desc);
 	}
 #endif
@@ -168,16 +169,16 @@ static int setup_affinity(unsigned int irq, struct irq_desc *desc)
 	 * one of the targets is online.
 	 */
 	if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-		if (cpumask_any_and(desc->affinity, cpu_online_mask)
+		if (cpumask_any_and(desc->irq_data.affinity, cpu_online_mask)
 		    < nr_cpu_ids)
 			goto set_affinity;
 		else
 			desc->status &= ~IRQ_AFFINITY_SET;
 	}
 
-	cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
+	cpumask_and(desc->irq_data.affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
-	desc->chip->set_affinity(irq, desc->affinity);
+	desc->irq_data.chip->irq_set_affinity(&desc->irq_data, desc->irq_data.affinity, false);
 
 	return 0;
 }
@@ -223,7 +224,7 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
 
 	if (!desc->depth++) {
 		desc->status |= IRQ_DISABLED;
-		desc->chip->disable(irq);
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
 	}
 }
 
@@ -246,11 +247,11 @@ void disable_irq_nosync(unsigned int irq)
 	if (!desc)
 		return;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	__disable_irq(desc, irq, false);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
 
@@ -313,7 +314,7 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
  *	IRQ line is re-enabled.
  *
  *	This function may be called from IRQ context only when
- *	desc->chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
+ *	desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
  */
 void enable_irq(unsigned int irq)
 {
@@ -323,11 +324,11 @@ void enable_irq(unsigned int irq)
 	if (!desc)
 		return;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	__enable_irq(desc, irq, false);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(enable_irq);
 
@@ -336,8 +337,8 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
 	struct irq_desc *desc = irq_to_desc(irq);
 	int ret = -ENXIO;
 
-	if (desc->chip->set_wake)
-		ret = desc->chip->set_wake(irq, on);
+	if (desc->irq_data.chip->irq_set_wake)
+		ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on);
 
 	return ret;
 }
@@ -429,12 +430,12 @@ void compat_irq_chip_set_default_handler(struct irq_desc *desc)
 }
 
 int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
-		unsigned long flags)
+		      unsigned long flags)
 {
 	int ret;
-	struct irq_chip *chip = desc->chip;
+	struct irq_chip *chip = desc->irq_data.chip;
 
-	if (!chip || !chip->set_type) {
+	if (!chip || !chip->irq_set_type) {
 		/*
 		 * IRQF_TRIGGER_* but the PIC does not support multiple
 		 * flow-types?
@@ -445,11 +446,11 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 	}
 
 	/* caller masked out all except trigger mode flags */
-	ret = chip->set_type(irq, flags);
+	ret = chip->irq_set_type(&desc->irq_data, flags);
 
 	if (ret)
-		pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
-				(int)flags, irq, chip->set_type);
+		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
+		       flags, irq, chip->irq_set_type);
 	else {
 		if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 			flags |= IRQ_LEVEL;
@@ -457,8 +458,8 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
 		desc->status |= flags;
 
-		if (chip != desc->chip)
-			irq_chip_set_defaults(desc->chip);
+		if (chip != desc->irq_data.chip)
+			irq_chip_set_defaults(desc->irq_data.chip);
 	}
 
 	return ret;
@@ -507,7 +508,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
 {
 again:
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irq(&desc->lock);
 
 	/*
@@ -521,17 +522,17 @@ again:
 	 */
 	if (unlikely(desc->status & IRQ_INPROGRESS)) {
 		raw_spin_unlock_irq(&desc->lock);
-		chip_bus_sync_unlock(irq, desc);
+		chip_bus_sync_unlock(desc);
 		cpu_relax();
 		goto again;
 	}
 
 	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
 		desc->status &= ~IRQ_MASKED;
-		desc->chip->unmask(irq);
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	}
 	raw_spin_unlock_irq(&desc->lock);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 
 #ifdef CONFIG_SMP
@@ -556,7 +557,7 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
 	}
 
 	raw_spin_lock_irq(&desc->lock);
-	cpumask_copy(mask, desc->affinity);
+	cpumask_copy(mask, desc->irq_data.affinity);
 	raw_spin_unlock_irq(&desc->lock);
 
 	set_cpus_allowed_ptr(current, mask);
@@ -657,7 +658,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	if (!desc)
 		return -EINVAL;
 
-	if (desc->chip == &no_irq_chip)
+	if (desc->irq_data.chip == &no_irq_chip)
 		return -ENOSYS;
 	/*
 	 * Some drivers like serial.c use request_irq() heavily,
@@ -752,7 +753,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	}
 
 	if (!shared) {
-		irq_chip_set_defaults(desc->chip);
+		irq_chip_set_defaults(desc->irq_data.chip);
 
 		init_waitqueue_head(&desc->wait_for_threads);
 
@@ -779,7 +780,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		if (!(desc->status & IRQ_NOAUTOEN)) {
 			desc->depth = 0;
 			desc->status &= ~IRQ_DISABLED;
-			desc->chip->startup(irq);
+			desc->irq_data.chip->irq_startup(&desc->irq_data);
 		} else
 			/* Undo nested disables: */
 			desc->depth = 1;
@@ -912,17 +913,17 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 
 	/* Currently used only by UML, might disappear one day: */
 #ifdef CONFIG_IRQ_RELEASE_METHOD
-	if (desc->chip->release)
-		desc->chip->release(irq, dev_id);
+	if (desc->irq_data.chip->release)
+		desc->irq_data.chip->release(irq, dev_id);
 #endif
 
 	/* If this was the last handler, shut down the IRQ line: */
 	if (!desc->action) {
 		desc->status |= IRQ_DISABLED;
-		if (desc->chip->shutdown)
-			desc->chip->shutdown(irq);
+		if (desc->irq_data.chip->irq_shutdown)
+			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 		else
-			desc->chip->disable(irq);
+			desc->irq_data.chip->irq_disable(&desc->irq_data);
 	}
 
 #ifdef CONFIG_SMP
@@ -997,9 +998,9 @@ void free_irq(unsigned int irq, void *dev_id)
 	if (!desc)
 		return;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	kfree(__free_irq(irq, dev_id));
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(free_irq);
 
@@ -1086,9 +1087,9 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	action->name = devname;
 	action->dev_id = dev_id;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, action);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 
 	if (retval)
 		kfree(action);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 241962280836..1d2541940480 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -7,6 +7,7 @@
 void move_masked_irq(int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_chip *chip = desc->irq_data.chip;
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
 		return;
@@ -24,7 +25,7 @@ void move_masked_irq(int irq)
 	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
 
-	if (!desc->chip->set_affinity)
+	if (!chip->irq_set_affinity)
 		return;
 
 	assert_raw_spin_locked(&desc->lock);
@@ -43,8 +44,9 @@ void move_masked_irq(int irq)
 	 */
 	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
 		   < nr_cpu_ids))
-		if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
-			cpumask_copy(desc->affinity, desc->pending_mask);
+		if (!chip->irq_set_affinity(&desc->irq_data,
+					    desc->pending_mask, false)) {
+			cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
 			irq_set_thread_affinity(desc);
 		}
 
@@ -61,8 +63,8 @@ void move_native_irq(int irq)
 	if (unlikely(desc->status & IRQ_DISABLED))
 		return;
 
-	desc->chip->mask(irq);
+	desc->irq_data.chip->irq_mask(&desc->irq_data);
 	move_masked_irq(irq);
-	desc->chip->unmask(irq);
+	desc->irq_data.chip->irq_unmask(&desc->irq_data);
 }
 
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 65d3845665ac..e7f1f16402c1 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -44,7 +44,7 @@ static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
 		return false;
 	}
 	raw_spin_lock_init(&desc->lock);
-	desc->node = node;
+	desc->irq_data.node = node;
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	init_copy_kstat_irqs(old_desc, desc, node, nr_cpu_ids);
 	init_copy_desc_masks(old_desc, desc);
@@ -66,7 +66,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	unsigned int irq;
 	unsigned long flags;
 
-	irq = old_desc->irq;
+	irq = old_desc->irq_data.irq;
 
 	raw_spin_lock_irqsave(&sparse_irq_lock, flags);
 
@@ -109,10 +109,10 @@ out_unlock:
 struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
 {
 	/* those static or target node is -1, do not move them */
-	if (desc->irq < NR_IRQS_LEGACY || node == -1)
+	if (desc->irq_data.irq < NR_IRQS_LEGACY || node == -1)
 		return desc;
 
-	if (desc->node != node)
+	if (desc->irq_data.node != node)
 		desc = __real_move_irq_desc(desc, node);
 
 	return desc;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 09a2ee540bd2..d9fddf918b41 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -21,7 +21,7 @@ static struct proc_dir_entry *root_irq_dir;
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	const struct cpumask *mask = desc->affinity;
+	const struct cpumask *mask = desc->irq_data.affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PENDING)
@@ -65,7 +65,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
 	cpumask_var_t new_value;
 	int err;
 
-	if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity ||
+	if (!irq_to_desc(irq)->irq_data.chip->irq_set_affinity || no_irq_affinity ||
 	    irq_balancing_disabled(irq))
 		return -EIO;
 
@@ -185,7 +185,7 @@ static int irq_node_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long) m->private);
 
-	seq_printf(m, "%d\n", desc->node);
+	seq_printf(m, "%d\n", desc->irq_data.node);
 	return 0;
 }
 
@@ -269,7 +269,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
 	char name [MAX_NAMELEN];
 
-	if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
+	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
 		return;
 
 	memset(name, 0, MAX_NAMELEN);
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 090c3763f3a2..891115a929aa 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -60,7 +60,7 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 	/*
 	 * Make sure the interrupt is enabled, before resending it:
 	 */
-	desc->chip->enable(irq);
+	desc->irq_data.chip->irq_enable(&desc->irq_data);
 
 	/*
 	 * We do not resend level type interrupts. Level type
@@ -70,7 +70,8 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 	if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
 		desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
 
-		if (!desc->chip->retrigger || !desc->chip->retrigger(irq)) {
+		if (!desc->irq_data.chip->irq_retrigger ||
+		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 			/* Set it pending and activate the softirq: */
 			set_bit(irq, irqs_resend);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 89fb90ae534f..3089d3b9d5f3 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -14,6 +14,8 @@
 #include <linux/moduleparam.h>
 #include <linux/timer.h>
 
+#include "internals.h"
+
 static int irqfixup __read_mostly;
 
 #define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
@@ -78,8 +80,8 @@ static int try_one_irq(int irq, struct irq_desc *desc)
 	 * If we did actual work for the real IRQ line we must let the
 	 * IRQ controller clean up too
 	 */
-	if (work && desc->chip && desc->chip->end)
-		desc->chip->end(irq);
+	if (work)
+		irq_end(irq, desc);
 	raw_spin_unlock(&desc->lock);
 
 	return ok;
@@ -254,7 +256,7 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
 		desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED;
 		desc->depth++;
-		desc->chip->disable(irq);
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
 
 		mod_timer(&poll_spurious_irq_timer,
 			  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
new file mode 100644
index 000000000000..7be868bf25c6
--- /dev/null
+++ b/kernel/jump_label.c
@@ -0,0 +1,429 @@
+/*
+ * jump label support
+ *
+ * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
+ *
+ */
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/err.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+#define JUMP_LABEL_HASH_BITS 6
+#define JUMP_LABEL_TABLE_SIZE (1 << JUMP_LABEL_HASH_BITS)
+static struct hlist_head jump_label_table[JUMP_LABEL_TABLE_SIZE];
+
+/* mutex to protect coming/going of the the jump_label table */
+static DEFINE_MUTEX(jump_label_mutex);
+
+struct jump_label_entry {
+	struct hlist_node hlist;
+	struct jump_entry *table;
+	int nr_entries;
+	/* hang modules off here */
+	struct hlist_head modules;
+	unsigned long key;
+};
+
+struct jump_label_module_entry {
+	struct hlist_node hlist;
+	struct jump_entry *table;
+	int nr_entries;
+	struct module *mod;
+};
+
+static int jump_label_cmp(const void *a, const void *b)
+{
+	const struct jump_entry *jea = a;
+	const struct jump_entry *jeb = b;
+
+	if (jea->key < jeb->key)
+		return -1;
+
+	if (jea->key > jeb->key)
+		return 1;
+
+	return 0;
+}
+
+static void
+sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop)
+{
+	unsigned long size;
+
+	size = (((unsigned long)stop - (unsigned long)start)
+					/ sizeof(struct jump_entry));
+	sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL);
+}
+
+static struct jump_label_entry *get_jump_label_entry(jump_label_t key)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct jump_label_entry *e;
+	u32 hash = jhash((void *)&key, sizeof(jump_label_t), 0);
+
+	head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)];
+	hlist_for_each_entry(e, node, head, hlist) {
+		if (key == e->key)
+			return e;
+	}
+	return NULL;
+}
+
+static struct jump_label_entry *
+add_jump_label_entry(jump_label_t key, int nr_entries, struct jump_entry *table)
+{
+	struct hlist_head *head;
+	struct jump_label_entry *e;
+	u32 hash;
+
+	e = get_jump_label_entry(key);
+	if (e)
+		return ERR_PTR(-EEXIST);
+
+	e = kmalloc(sizeof(struct jump_label_entry), GFP_KERNEL);
+	if (!e)
+		return ERR_PTR(-ENOMEM);
+
+	hash = jhash((void *)&key, sizeof(jump_label_t), 0);
+	head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)];
+	e->key = key;
+	e->table = table;
+	e->nr_entries = nr_entries;
+	INIT_HLIST_HEAD(&(e->modules));
+	hlist_add_head(&e->hlist, head);
+	return e;
+}
+
+static int
+build_jump_label_hashtable(struct jump_entry *start, struct jump_entry *stop)
+{
+	struct jump_entry *iter, *iter_begin;
+	struct jump_label_entry *entry;
+	int count;
+
+	sort_jump_label_entries(start, stop);
+	iter = start;
+	while (iter < stop) {
+		entry = get_jump_label_entry(iter->key);
+		if (!entry) {
+			iter_begin = iter;
+			count = 0;
+			while ((iter < stop) &&
+				(iter->key == iter_begin->key)) {
+				iter++;
+				count++;
+			}
+			entry = add_jump_label_entry(iter_begin->key,
+							count, iter_begin);
+			if (IS_ERR(entry))
+				return PTR_ERR(entry);
+		 } else {
+			WARN_ONCE(1, KERN_ERR "build_jump_hashtable: unexpected entry!\n");
+			return -1;
+		}
+	}
+	return 0;
+}
+
+/***
+ * jump_label_update - update jump label text
+ * @key -  key value associated with a a jump label
+ * @type - enum set to JUMP_LABEL_ENABLE or JUMP_LABEL_DISABLE
+ *
+ * Will enable/disable the jump for jump label @key, depending on the
+ * value of @type.
+ *
+ */
+
+void jump_label_update(unsigned long key, enum jump_label_type type)
+{
+	struct jump_entry *iter;
+	struct jump_label_entry *entry;
+	struct hlist_node *module_node;
+	struct jump_label_module_entry *e_module;
+	int count;
+
+	mutex_lock(&jump_label_mutex);
+	entry = get_jump_label_entry((jump_label_t)key);
+	if (entry) {
+		count = entry->nr_entries;
+		iter = entry->table;
+		while (count--) {
+			if (kernel_text_address(iter->code))
+				arch_jump_label_transform(iter, type);
+			iter++;
+		}
+		/* eanble/disable jump labels in modules */
+		hlist_for_each_entry(e_module, module_node, &(entry->modules),
+							hlist) {
+			count = e_module->nr_entries;
+			iter = e_module->table;
+			while (count--) {
+				if (kernel_text_address(iter->code))
+					arch_jump_label_transform(iter, type);
+				iter++;
+			}
+		}
+	}
+	mutex_unlock(&jump_label_mutex);
+}
+
+static int addr_conflict(struct jump_entry *entry, void *start, void *end)
+{
+	if (entry->code <= (unsigned long)end &&
+		entry->code + JUMP_LABEL_NOP_SIZE > (unsigned long)start)
+		return 1;
+
+	return 0;
+}
+
+#ifdef CONFIG_MODULES
+
+static int module_conflict(void *start, void *end)
+{
+	struct hlist_head *head;
+	struct hlist_node *node, *node_next, *module_node, *module_node_next;
+	struct jump_label_entry *e;
+	struct jump_label_module_entry *e_module;
+	struct jump_entry *iter;
+	int i, count;
+	int conflict = 0;
+
+	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
+		head = &jump_label_table[i];
+		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
+			hlist_for_each_entry_safe(e_module, module_node,
+							module_node_next,
+							&(e->modules), hlist) {
+				count = e_module->nr_entries;
+				iter = e_module->table;
+				while (count--) {
+					if (addr_conflict(iter, start, end)) {
+						conflict = 1;
+						goto out;
+					}
+					iter++;
+				}
+			}
+		}
+	}
+out:
+	return conflict;
+}
+
+#endif
+
+/***
+ * jump_label_text_reserved - check if addr range is reserved
+ * @start: start text addr
+ * @end: end text addr
+ *
+ * checks if the text addr located between @start and @end
+ * overlaps with any of the jump label patch addresses. Code
+ * that wants to modify kernel text should first verify that
+ * it does not overlap with any of the jump label addresses.
+ *
+ * returns 1 if there is an overlap, 0 otherwise
+ */
+int jump_label_text_reserved(void *start, void *end)
+{
+	struct jump_entry *iter;
+	struct jump_entry *iter_start = __start___jump_table;
+	struct jump_entry *iter_stop = __start___jump_table;
+	int conflict = 0;
+
+	mutex_lock(&jump_label_mutex);
+	iter = iter_start;
+	while (iter < iter_stop) {
+		if (addr_conflict(iter, start, end)) {
+			conflict = 1;
+			goto out;
+		}
+		iter++;
+	}
+
+	/* now check modules */
+#ifdef CONFIG_MODULES
+	conflict = module_conflict(start, end);
+#endif
+out:
+	mutex_unlock(&jump_label_mutex);
+	return conflict;
+}
+
+static __init int init_jump_label(void)
+{
+	int ret;
+	struct jump_entry *iter_start = __start___jump_table;
+	struct jump_entry *iter_stop = __stop___jump_table;
+	struct jump_entry *iter;
+
+	mutex_lock(&jump_label_mutex);
+	ret = build_jump_label_hashtable(__start___jump_table,
+					 __stop___jump_table);
+	iter = iter_start;
+	while (iter < iter_stop) {
+		arch_jump_label_text_poke_early(iter->code);
+		iter++;
+	}
+	mutex_unlock(&jump_label_mutex);
+	return ret;
+}
+early_initcall(init_jump_label);
+
+#ifdef CONFIG_MODULES
+
+static struct jump_label_module_entry *
+add_jump_label_module_entry(struct jump_label_entry *entry,
+			    struct jump_entry *iter_begin,
+			    int count, struct module *mod)
+{
+	struct jump_label_module_entry *e;
+
+	e = kmalloc(sizeof(struct jump_label_module_entry), GFP_KERNEL);
+	if (!e)
+		return ERR_PTR(-ENOMEM);
+	e->mod = mod;
+	e->nr_entries = count;
+	e->table = iter_begin;
+	hlist_add_head(&e->hlist, &entry->modules);
+	return e;
+}
+
+static int add_jump_label_module(struct module *mod)
+{
+	struct jump_entry *iter, *iter_begin;
+	struct jump_label_entry *entry;
+	struct jump_label_module_entry *module_entry;
+	int count;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return 0;
+
+	sort_jump_label_entries(mod->jump_entries,
+				mod->jump_entries + mod->num_jump_entries);
+	iter = mod->jump_entries;
+	while (iter < mod->jump_entries + mod->num_jump_entries) {
+		entry = get_jump_label_entry(iter->key);
+		iter_begin = iter;
+		count = 0;
+		while ((iter < mod->jump_entries + mod->num_jump_entries) &&
+			(iter->key == iter_begin->key)) {
+				iter++;
+				count++;
+		}
+		if (!entry) {
+			entry = add_jump_label_entry(iter_begin->key, 0, NULL);
+			if (IS_ERR(entry))
+				return PTR_ERR(entry);
+		}
+		module_entry = add_jump_label_module_entry(entry, iter_begin,
+							   count, mod);
+		if (IS_ERR(module_entry))
+			return PTR_ERR(module_entry);
+	}
+	return 0;
+}
+
+static void remove_jump_label_module(struct module *mod)
+{
+	struct hlist_head *head;
+	struct hlist_node *node, *node_next, *module_node, *module_node_next;
+	struct jump_label_entry *e;
+	struct jump_label_module_entry *e_module;
+	int i;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return;
+
+	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
+		head = &jump_label_table[i];
+		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
+			hlist_for_each_entry_safe(e_module, module_node,
+						  module_node_next,
+						  &(e->modules), hlist) {
+				if (e_module->mod == mod) {
+					hlist_del(&e_module->hlist);
+					kfree(e_module);
+				}
+			}
+			if (hlist_empty(&e->modules) && (e->nr_entries == 0)) {
+				hlist_del(&e->hlist);
+				kfree(e);
+			}
+		}
+	}
+}
+
+static int
+jump_label_module_notify(struct notifier_block *self, unsigned long val,
+			 void *data)
+{
+	struct module *mod = data;
+	int ret = 0;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		mutex_lock(&jump_label_mutex);
+		ret = add_jump_label_module(mod);
+		if (ret)
+			remove_jump_label_module(mod);
+		mutex_unlock(&jump_label_mutex);
+		break;
+	case MODULE_STATE_GOING:
+		mutex_lock(&jump_label_mutex);
+		remove_jump_label_module(mod);
+		mutex_unlock(&jump_label_mutex);
+		break;
+	}
+	return ret;
+}
+
+/***
+ * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop()
+ * @mod: module to patch
+ *
+ * Allow for run-time selection of the optimal nops. Before the module
+ * loads patch these with arch_get_jump_label_nop(), which is specified by
+ * the arch specific jump label code.
+ */
+void jump_label_apply_nops(struct module *mod)
+{
+	struct jump_entry *iter;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return;
+
+	iter = mod->jump_entries;
+	while (iter < mod->jump_entries + mod->num_jump_entries) {
+		arch_jump_label_text_poke_early(iter->code);
+		iter++;
+	}
+}
+
+struct notifier_block jump_label_module_nb = {
+	.notifier_call = jump_label_module_notify,
+	.priority = 0,
+};
+
+static __init int init_jump_label_module(void)
+{
+	return register_module_notifier(&jump_label_module_nb);
+}
+early_initcall(init_jump_label_module);
+
+#endif /* CONFIG_MODULES */
+
+#endif
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 282035f3ae96..ec4210c6501e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -47,6 +47,7 @@
 #include <linux/memory.h>
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
+#include <linux/jump_label.h>
 
 #include <asm-generic/sections.h>
 #include <asm/cacheflush.h>
@@ -399,7 +400,7 @@ static inline int kprobe_optready(struct kprobe *p)
  * Return an optimized kprobe whose optimizing code replaces
  * instructions including addr (exclude breakpoint).
  */
-struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
+static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
 {
 	int i;
 	struct kprobe *p = NULL;
@@ -831,6 +832,7 @@ void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
 
 void __kprobes kretprobe_hash_lock(struct task_struct *tsk,
 			 struct hlist_head **head, unsigned long *flags)
+__acquires(hlist_lock)
 {
 	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
 	spinlock_t *hlist_lock;
@@ -842,6 +844,7 @@ void __kprobes kretprobe_hash_lock(struct task_struct *tsk,
 
 static void __kprobes kretprobe_table_lock(unsigned long hash,
 	unsigned long *flags)
+__acquires(hlist_lock)
 {
 	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
 	spin_lock_irqsave(hlist_lock, *flags);
@@ -849,6 +852,7 @@ static void __kprobes kretprobe_table_lock(unsigned long hash,
 
 void __kprobes kretprobe_hash_unlock(struct task_struct *tsk,
 	unsigned long *flags)
+__releases(hlist_lock)
 {
 	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
 	spinlock_t *hlist_lock;
@@ -857,7 +861,9 @@ void __kprobes kretprobe_hash_unlock(struct task_struct *tsk,
 	spin_unlock_irqrestore(hlist_lock, *flags);
 }
 
-void __kprobes kretprobe_table_unlock(unsigned long hash, unsigned long *flags)
+static void __kprobes kretprobe_table_unlock(unsigned long hash,
+       unsigned long *flags)
+__releases(hlist_lock)
 {
 	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
 	spin_unlock_irqrestore(hlist_lock, *flags);
@@ -1141,7 +1147,8 @@ int __kprobes register_kprobe(struct kprobe *p)
 	preempt_disable();
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    in_kprobes_functions((unsigned long) p->addr) ||
-	    ftrace_text_reserved(p->addr, p->addr)) {
+	    ftrace_text_reserved(p->addr, p->addr) ||
+	    jump_label_text_reserved(p->addr, p->addr)) {
 		preempt_enable();
 		return -EINVAL;
 	}
@@ -1339,18 +1346,19 @@ int __kprobes register_jprobes(struct jprobe **jps, int num)
 	if (num <= 0)
 		return -EINVAL;
 	for (i = 0; i < num; i++) {
-		unsigned long addr;
+		unsigned long addr, offset;
 		jp = jps[i];
 		addr = arch_deref_entry_point(jp->entry);
 
-		if (!kernel_text_address(addr))
-			ret = -EINVAL;
-		else {
-			/* Todo: Verify probepoint is a function entry point */
+		/* Verify probepoint is a function entry point */
+		if (kallsyms_lookup_size_offset(addr, NULL, &offset) &&
+		    offset == 0) {
 			jp->kp.pre_handler = setjmp_pre_handler;
 			jp->kp.break_handler = longjmp_break_handler;
 			ret = register_kprobe(&jp->kp);
-		}
+		} else
+			ret = -EINVAL;
+
 		if (ret < 0) {
 			if (i > 0)
 				unregister_jprobes(jps, i);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index f2852a510232..84baa71cfda5 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3775,7 +3775,7 @@ EXPORT_SYMBOL_GPL(debug_show_all_locks);
  * Careful: only use this function if you are sure that
  * the task cannot run in parallel!
  */
-void __debug_show_held_locks(struct task_struct *task)
+void debug_show_held_locks(struct task_struct *task)
 {
 	if (unlikely(!debug_locks)) {
 		printk("INFO: lockdep is turned off.\n");
@@ -3783,12 +3783,6 @@ void __debug_show_held_locks(struct task_struct *task)
 	}
 	lockdep_print_held_locks(task);
 }
-EXPORT_SYMBOL_GPL(__debug_show_held_locks);
-
-void debug_show_held_locks(struct task_struct *task)
-{
-		__debug_show_held_locks(task);
-}
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
 void lockdep_sys_exit(void)
diff --git a/kernel/module.c b/kernel/module.c
index 808cc7c332b3..437a74a7524a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -55,6 +55,7 @@
 #include <linux/async.h>
 #include <linux/percpu.h>
 #include <linux/kmemleak.h>
+#include <linux/jump_label.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
@@ -2309,6 +2310,11 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 					sizeof(*mod->tracepoints),
 					&mod->num_tracepoints);
 #endif
+#ifdef HAVE_JUMP_LABEL
+	mod->jump_entries = section_objs(info, "__jump_table",
+					sizeof(*mod->jump_entries),
+					&mod->num_jump_entries);
+#endif
 #ifdef CONFIG_EVENT_TRACING
 	mod->trace_events = section_objs(info, "_ftrace_events",
 					 sizeof(*mod->trace_events),
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index db5b56064687..64507eaa2d9e 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -31,24 +31,18 @@
 #include <linux/kernel_stat.h>
 #include <linux/perf_event.h>
 #include <linux/ftrace_event.h>
-#include <linux/hw_breakpoint.h>
 
 #include <asm/irq_regs.h>
 
-/*
- * Each CPU has a list of per CPU events:
- */
-static DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
-
-int perf_max_events __read_mostly = 1;
-static int perf_reserved_percpu __read_mostly;
-static int perf_overcommit __read_mostly = 1;
-
 static atomic_t nr_events __read_mostly;
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
 
+static LIST_HEAD(pmus);
+static DEFINE_MUTEX(pmus_lock);
+static struct srcu_struct pmus_srcu;
+
 /*
  * perf event paranoia level:
  *  -1 - not paranoid at all
@@ -67,36 +61,38 @@ int sysctl_perf_event_sample_rate __read_mostly = 100000;
 
 static atomic64_t perf_event_id;
 
-/*
- * Lock for (sysadmin-configurable) event reservations:
- */
-static DEFINE_SPINLOCK(perf_resource_lock);
+void __weak perf_event_print_debug(void)	{ }
 
-/*
- * Architecture provided APIs - weak aliases:
- */
-extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
+void perf_pmu_disable(struct pmu *pmu)
 {
-	return NULL;
+	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+	if (!(*count)++)
+		pmu->pmu_disable(pmu);
 }
 
-void __weak hw_perf_disable(void)		{ barrier(); }
-void __weak hw_perf_enable(void)		{ barrier(); }
-
-void __weak perf_event_print_debug(void)	{ }
-
-static DEFINE_PER_CPU(int, perf_disable_count);
-
-void perf_disable(void)
+void perf_pmu_enable(struct pmu *pmu)
 {
-	if (!__get_cpu_var(perf_disable_count)++)
-		hw_perf_disable();
+	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+	if (!--(*count))
+		pmu->pmu_enable(pmu);
 }
 
-void perf_enable(void)
+static DEFINE_PER_CPU(struct list_head, rotation_list);
+
+/*
+ * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
+ * because they're strictly cpu affine and rotate_start is called with IRQs
+ * disabled, while rotate_context is called from IRQ context.
+ */
+static void perf_pmu_rotate_start(struct pmu *pmu)
 {
-	if (!--__get_cpu_var(perf_disable_count))
-		hw_perf_enable();
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+	struct list_head *head = &__get_cpu_var(rotation_list);
+
+	WARN_ON(!irqs_disabled());
+
+	if (list_empty(&cpuctx->rotation_list))
+		list_add(&cpuctx->rotation_list, head);
 }
 
 static void get_ctx(struct perf_event_context *ctx)
@@ -151,13 +147,13 @@ static u64 primary_event_id(struct perf_event *event)
  * the context could get moved to another task.
  */
 static struct perf_event_context *
-perf_lock_task_context(struct task_struct *task, unsigned long *flags)
+perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags)
 {
 	struct perf_event_context *ctx;
 
 	rcu_read_lock();
- retry:
-	ctx = rcu_dereference(task->perf_event_ctxp);
+retry:
+	ctx = rcu_dereference(task->perf_event_ctxp[ctxn]);
 	if (ctx) {
 		/*
 		 * If this context is a clone of another, it might
@@ -170,7 +166,7 @@ perf_lock_task_context(struct task_struct *task, unsigned long *flags)
 		 * can't get swapped on us any more.
 		 */
 		raw_spin_lock_irqsave(&ctx->lock, *flags);
-		if (ctx != rcu_dereference(task->perf_event_ctxp)) {
+		if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) {
 			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
 			goto retry;
 		}
@@ -189,12 +185,13 @@ perf_lock_task_context(struct task_struct *task, unsigned long *flags)
  * can't get swapped to another task.  This also increments its
  * reference count so that the context can't get freed.
  */
-static struct perf_event_context *perf_pin_task_context(struct task_struct *task)
+static struct perf_event_context *
+perf_pin_task_context(struct task_struct *task, int ctxn)
 {
 	struct perf_event_context *ctx;
 	unsigned long flags;
 
-	ctx = perf_lock_task_context(task, &flags);
+	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
 		++ctx->pin_count;
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
@@ -302,6 +299,8 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 	}
 
 	list_add_rcu(&event->event_entry, &ctx->event_list);
+	if (!ctx->nr_events)
+		perf_pmu_rotate_start(ctx->pmu);
 	ctx->nr_events++;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat++;
@@ -436,7 +435,7 @@ event_sched_out(struct perf_event *event,
 		event->state = PERF_EVENT_STATE_OFF;
 	}
 	event->tstamp_stopped = ctx->time;
-	event->pmu->disable(event);
+	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
 	if (!is_software_event(event))
@@ -466,6 +465,12 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -474,9 +479,9 @@ group_sched_out(struct perf_event *group_event,
  */
 static void __perf_event_remove_from_context(void *info)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	/*
 	 * If this is a task context, we need to check whether it is
@@ -487,27 +492,11 @@ static void __perf_event_remove_from_context(void *info)
 		return;
 
 	raw_spin_lock(&ctx->lock);
-	/*
-	 * Protect the list operation against NMI by disabling the
-	 * events on a global level.
-	 */
-	perf_disable();
 
 	event_sched_out(event, cpuctx, ctx);
 
 	list_del_event(event, ctx);
 
-	if (!ctx->task) {
-		/*
-		 * Allow more per task events with respect to the
-		 * reservation:
-		 */
-		cpuctx->max_pertask =
-			min(perf_max_events - ctx->nr_events,
-			    perf_max_events - perf_reserved_percpu);
-	}
-
-	perf_enable();
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -572,8 +561,8 @@ retry:
 static void __perf_event_disable(void *info)
 {
 	struct perf_event *event = info;
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	/*
 	 * If this is a per-task event, need to check whether this
@@ -628,7 +617,7 @@ void perf_event_disable(struct perf_event *event)
 		return;
 	}
 
- retry:
+retry:
 	task_oncpu_function_call(task, __perf_event_disable, event);
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -667,7 +656,7 @@ event_sched_in(struct perf_event *event,
 	 */
 	smp_wmb();
 
-	if (event->pmu->enable(event)) {
+	if (event->pmu->add(event, PERF_EF_START)) {
 		event->state = PERF_EVENT_STATE_INACTIVE;
 		event->oncpu = -1;
 		return -EAGAIN;
@@ -691,22 +680,15 @@ group_sched_in(struct perf_event *group_event,
 	       struct perf_event_context *ctx)
 {
 	struct perf_event *event, *partial_group = NULL;
-	const struct pmu *pmu = group_event->pmu;
-	bool txn = false;
+	struct pmu *pmu = group_event->pmu;
 
 	if (group_event->state == PERF_EVENT_STATE_OFF)
 		return 0;
 
-	/* Check if group transaction availabe */
-	if (pmu->start_txn)
-		txn = true;
-
-	if (txn)
-		pmu->start_txn(pmu);
+	pmu->start_txn(pmu);
 
 	if (event_sched_in(group_event, cpuctx, ctx)) {
-		if (txn)
-			pmu->cancel_txn(pmu);
+		pmu->cancel_txn(pmu);
 		return -EAGAIN;
 	}
 
@@ -720,7 +702,7 @@ group_sched_in(struct perf_event *group_event,
 		}
 	}
 
-	if (!txn || !pmu->commit_txn(pmu))
+	if (!pmu->commit_txn(pmu))
 		return 0;
 
 group_error:
@@ -735,8 +717,7 @@ group_error:
 	}
 	event_sched_out(group_event, cpuctx, ctx);
 
-	if (txn)
-		pmu->cancel_txn(pmu);
+	pmu->cancel_txn(pmu);
 
 	return -EAGAIN;
 }
@@ -789,10 +770,10 @@ static void add_event_to_ctx(struct perf_event *event,
  */
 static void __perf_install_in_context(void *info)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *leader = event->group_leader;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
 	/*
@@ -812,12 +793,6 @@ static void __perf_install_in_context(void *info)
 	ctx->is_active = 1;
 	update_context_time(ctx);
 
-	/*
-	 * Protect the list operation against NMI by disabling the
-	 * events on a global level. NOP for non NMI based events.
-	 */
-	perf_disable();
-
 	add_event_to_ctx(event, ctx);
 
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
@@ -855,12 +830,7 @@ static void __perf_install_in_context(void *info)
 		}
 	}
 
-	if (!err && !ctx->task && cpuctx->max_pertask)
-		cpuctx->max_pertask--;
-
- unlock:
-	perf_enable();
-
+unlock:
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -883,6 +853,8 @@ perf_install_in_context(struct perf_event_context *ctx,
 {
 	struct task_struct *task = ctx->task;
 
+	event->ctx = ctx;
+
 	if (!task) {
 		/*
 		 * Per cpu events are installed via an smp call and
@@ -931,10 +903,12 @@ static void __perf_event_mark_enabled(struct perf_event *event,
 
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	event->tstamp_enabled = ctx->time - event->total_time_enabled;
-	list_for_each_entry(sub, &event->sibling_list, group_entry)
-		if (sub->state >= PERF_EVENT_STATE_INACTIVE)
+	list_for_each_entry(sub, &event->sibling_list, group_entry) {
+		if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
 			sub->tstamp_enabled =
 				ctx->time - sub->total_time_enabled;
+		}
+	}
 }
 
 /*
@@ -943,9 +917,9 @@ static void __perf_event_mark_enabled(struct perf_event *event,
 static void __perf_event_enable(void *info)
 {
 	struct perf_event *event = info;
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *leader = event->group_leader;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
 	/*
@@ -979,12 +953,10 @@ static void __perf_event_enable(void *info)
 	if (!group_can_go_on(event, cpuctx, 1)) {
 		err = -EEXIST;
 	} else {
-		perf_disable();
 		if (event == leader)
 			err = group_sched_in(event, cpuctx, ctx);
 		else
 			err = event_sched_in(event, cpuctx, ctx);
-		perf_enable();
 	}
 
 	if (err) {
@@ -1000,7 +972,7 @@ static void __perf_event_enable(void *info)
 		}
 	}
 
- unlock:
+unlock:
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -1041,7 +1013,7 @@ void perf_event_enable(struct perf_event *event)
 	if (event->state == PERF_EVENT_STATE_ERROR)
 		event->state = PERF_EVENT_STATE_OFF;
 
- retry:
+retry:
 	raw_spin_unlock_irq(&ctx->lock);
 	task_oncpu_function_call(task, __perf_event_enable, event);
 
@@ -1061,7 +1033,7 @@ void perf_event_enable(struct perf_event *event)
 	if (event->state == PERF_EVENT_STATE_OFF)
 		__perf_event_mark_enabled(event, ctx);
 
- out:
+out:
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
@@ -1092,26 +1064,26 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	struct perf_event *event;
 
 	raw_spin_lock(&ctx->lock);
+	perf_pmu_disable(ctx->pmu);
 	ctx->is_active = 0;
 	if (likely(!ctx->nr_events))
 		goto out;
 	update_context_time(ctx);
 
-	perf_disable();
 	if (!ctx->nr_active)
-		goto out_enable;
+		goto out;
 
-	if (event_type & EVENT_PINNED)
+	if (event_type & EVENT_PINNED) {
 		list_for_each_entry(event, &ctx->pinned_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
+	}
 
-	if (event_type & EVENT_FLEXIBLE)
+	if (event_type & EVENT_FLEXIBLE) {
 		list_for_each_entry(event, &ctx->flexible_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
-
- out_enable:
-	perf_enable();
- out:
+	}
+out:
+	perf_pmu_enable(ctx->pmu);
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -1209,34 +1181,25 @@ static void perf_event_sync_stat(struct perf_event_context *ctx,
 	}
 }
 
-/*
- * Called from scheduler to remove the events of the current task,
- * with interrupts disabled.
- *
- * We stop each event and update the event value in event->count.
- *
- * This does not protect us against NMI, but disable()
- * sets the disabled bit in the control field of event _before_
- * accessing the event control register. If a NMI hits, then it will
- * not restart the event.
- */
-void perf_event_task_sched_out(struct task_struct *task,
-				 struct task_struct *next)
+void perf_event_context_sched_out(struct task_struct *task, int ctxn,
+				  struct task_struct *next)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_event_context *ctx = task->perf_event_ctxp;
+	struct perf_event_context *ctx = task->perf_event_ctxp[ctxn];
 	struct perf_event_context *next_ctx;
 	struct perf_event_context *parent;
+	struct perf_cpu_context *cpuctx;
 	int do_switch = 1;
 
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
+	if (likely(!ctx))
+		return;
 
-	if (likely(!ctx || !cpuctx->task_ctx))
+	cpuctx = __get_cpu_context(ctx);
+	if (!cpuctx->task_ctx)
 		return;
 
 	rcu_read_lock();
 	parent = rcu_dereference(ctx->parent_ctx);
-	next_ctx = next->perf_event_ctxp;
+	next_ctx = next->perf_event_ctxp[ctxn];
 	if (parent && next_ctx &&
 	    rcu_dereference(next_ctx->parent_ctx) == parent) {
 		/*
@@ -1255,8 +1218,8 @@ void perf_event_task_sched_out(struct task_struct *task,
 			 * XXX do we need a memory barrier of sorts
 			 * wrt to rcu_dereference() of perf_event_ctxp
 			 */
-			task->perf_event_ctxp = next_ctx;
-			next->perf_event_ctxp = ctx;
+			task->perf_event_ctxp[ctxn] = next_ctx;
+			next->perf_event_ctxp[ctxn] = ctx;
 			ctx->task = next;
 			next_ctx->task = task;
 			do_switch = 0;
@@ -1274,10 +1237,35 @@ void perf_event_task_sched_out(struct task_struct *task,
 	}
 }
 
+#define for_each_task_context_nr(ctxn)					\
+	for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++)
+
+/*
+ * Called from scheduler to remove the events of the current task,
+ * with interrupts disabled.
+ *
+ * We stop each event and update the event value in event->count.
+ *
+ * This does not protect us against NMI, but disable()
+ * sets the disabled bit in the control field of event _before_
+ * accessing the event control register. If a NMI hits, then it will
+ * not restart the event.
+ */
+void perf_event_task_sched_out(struct task_struct *task,
+			       struct task_struct *next)
+{
+	int ctxn;
+
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
+
+	for_each_task_context_nr(ctxn)
+		perf_event_context_sched_out(task, ctxn, next);
+}
+
 static void task_ctx_sched_out(struct perf_event_context *ctx,
 			       enum event_type_t event_type)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	if (!cpuctx->task_ctx)
 		return;
@@ -1350,9 +1338,10 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 		if (event->cpu != -1 && event->cpu != smp_processor_id())
 			continue;
 
-		if (group_can_go_on(event, cpuctx, can_add_hw))
+		if (group_can_go_on(event, cpuctx, can_add_hw)) {
 			if (group_sched_in(event, cpuctx, ctx))
 				can_add_hw = 0;
+		}
 	}
 }
 
@@ -1368,8 +1357,6 @@ ctx_sched_in(struct perf_event_context *ctx,
 
 	ctx->timestamp = perf_clock();
 
-	perf_disable();
-
 	/*
 	 * First go through the list and put on any pinned groups
 	 * in order to give them the best chance of going on.
@@ -1381,8 +1368,7 @@ ctx_sched_in(struct perf_event_context *ctx,
 	if (event_type & EVENT_FLEXIBLE)
 		ctx_flexible_sched_in(ctx, cpuctx);
 
-	perf_enable();
- out:
+out:
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -1394,43 +1380,28 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
 	ctx_sched_in(ctx, cpuctx, event_type);
 }
 
-static void task_ctx_sched_in(struct task_struct *task,
+static void task_ctx_sched_in(struct perf_event_context *ctx,
 			      enum event_type_t event_type)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_event_context *ctx = task->perf_event_ctxp;
+	struct perf_cpu_context *cpuctx;
 
-	if (likely(!ctx))
-		return;
+       	cpuctx = __get_cpu_context(ctx);
 	if (cpuctx->task_ctx == ctx)
 		return;
+
 	ctx_sched_in(ctx, cpuctx, event_type);
 	cpuctx->task_ctx = ctx;
 }
-/*
- * Called from scheduler to add the events of the current task
- * with interrupts disabled.
- *
- * We restore the event value and then enable it.
- *
- * This does not protect us against NMI, but enable()
- * sets the enabled bit in the control field of event _before_
- * accessing the event control register. If a NMI hits, then it will
- * keep the event running.
- */
-void perf_event_task_sched_in(struct task_struct *task)
-{
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_event_context *ctx = task->perf_event_ctxp;
 
-	if (likely(!ctx))
-		return;
+void perf_event_context_sched_in(struct perf_event_context *ctx)
+{
+	struct perf_cpu_context *cpuctx;
 
+	cpuctx = __get_cpu_context(ctx);
 	if (cpuctx->task_ctx == ctx)
 		return;
 
-	perf_disable();
-
+	perf_pmu_disable(ctx->pmu);
 	/*
 	 * We want to keep the following priority order:
 	 * cpu pinned (that don't need to move), task pinned,
@@ -1444,7 +1415,37 @@ void perf_event_task_sched_in(struct task_struct *task)
 
 	cpuctx->task_ctx = ctx;
 
-	perf_enable();
+	/*
+	 * Since these rotations are per-cpu, we need to ensure the
+	 * cpu-context we got scheduled on is actually rotating.
+	 */
+	perf_pmu_rotate_start(ctx->pmu);
+	perf_pmu_enable(ctx->pmu);
+}
+
+/*
+ * Called from scheduler to add the events of the current task
+ * with interrupts disabled.
+ *
+ * We restore the event value and then enable it.
+ *
+ * This does not protect us against NMI, but enable()
+ * sets the enabled bit in the control field of event _before_
+ * accessing the event control register. If a NMI hits, then it will
+ * keep the event running.
+ */
+void perf_event_task_sched_in(struct task_struct *task)
+{
+	struct perf_event_context *ctx;
+	int ctxn;
+
+	for_each_task_context_nr(ctxn) {
+		ctx = task->perf_event_ctxp[ctxn];
+		if (likely(!ctx))
+			continue;
+
+		perf_event_context_sched_in(ctx);
+	}
 }
 
 #define MAX_INTERRUPTS (~0ULL)
@@ -1524,22 +1525,6 @@ do {					\
 	return div64_u64(dividend, divisor);
 }
 
-static void perf_event_stop(struct perf_event *event)
-{
-	if (!event->pmu->stop)
-		return event->pmu->disable(event);
-
-	return event->pmu->stop(event);
-}
-
-static int perf_event_start(struct perf_event *event)
-{
-	if (!event->pmu->start)
-		return event->pmu->enable(event);
-
-	return event->pmu->start(event);
-}
-
 static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -1559,15 +1544,13 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 	hwc->sample_period = sample_period;
 
 	if (local64_read(&hwc->period_left) > 8*sample_period) {
-		perf_disable();
-		perf_event_stop(event);
+		event->pmu->stop(event, PERF_EF_UPDATE);
 		local64_set(&hwc->period_left, 0);
-		perf_event_start(event);
-		perf_enable();
+		event->pmu->start(event, PERF_EF_RELOAD);
 	}
 }
 
-static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
+static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
 {
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
@@ -1592,23 +1575,19 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 		 */
 		if (interrupts == MAX_INTERRUPTS) {
 			perf_log_throttle(event, 1);
-			perf_disable();
-			event->pmu->unthrottle(event);
-			perf_enable();
+			event->pmu->start(event, 0);
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
 			continue;
 
-		perf_disable();
 		event->pmu->read(event);
 		now = local64_read(&event->count);
 		delta = now - hwc->freq_count_stamp;
 		hwc->freq_count_stamp = now;
 
 		if (delta > 0)
-			perf_adjust_period(event, TICK_NSEC, delta);
-		perf_enable();
+			perf_adjust_period(event, period, delta);
 	}
 	raw_spin_unlock(&ctx->lock);
 }
@@ -1626,32 +1605,38 @@ static void rotate_ctx(struct perf_event_context *ctx)
 	raw_spin_unlock(&ctx->lock);
 }
 
-void perf_event_task_tick(struct task_struct *curr)
+/*
+ * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
+ * because they're strictly cpu affine and rotate_start is called with IRQs
+ * disabled, while rotate_context is called from IRQ context.
+ */
+static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
-	int rotate = 0;
+	u64 interval = (u64)cpuctx->jiffies_interval * TICK_NSEC;
+	struct perf_event_context *ctx = NULL;
+	int rotate = 0, remove = 1;
 
-	if (!atomic_read(&nr_events))
-		return;
-
-	cpuctx = &__get_cpu_var(perf_cpu_context);
-	if (cpuctx->ctx.nr_events &&
-	    cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
-		rotate = 1;
+	if (cpuctx->ctx.nr_events) {
+		remove = 0;
+		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
+			rotate = 1;
+	}
 
-	ctx = curr->perf_event_ctxp;
-	if (ctx && ctx->nr_events && ctx->nr_events != ctx->nr_active)
-		rotate = 1;
+	ctx = cpuctx->task_ctx;
+	if (ctx && ctx->nr_events) {
+		remove = 0;
+		if (ctx->nr_events != ctx->nr_active)
+			rotate = 1;
+	}
 
-	perf_ctx_adjust_freq(&cpuctx->ctx);
+	perf_pmu_disable(cpuctx->ctx.pmu);
+	perf_ctx_adjust_freq(&cpuctx->ctx, interval);
 	if (ctx)
-		perf_ctx_adjust_freq(ctx);
+		perf_ctx_adjust_freq(ctx, interval);
 
 	if (!rotate)
-		return;
+		goto done;
 
-	perf_disable();
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
 		task_ctx_sched_out(ctx, EVENT_FLEXIBLE);
@@ -1662,8 +1647,27 @@ void perf_event_task_tick(struct task_struct *curr)
 
 	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
-		task_ctx_sched_in(curr, EVENT_FLEXIBLE);
-	perf_enable();
+		task_ctx_sched_in(ctx, EVENT_FLEXIBLE);
+
+done:
+	if (remove)
+		list_del_init(&cpuctx->rotation_list);
+
+	perf_pmu_enable(cpuctx->ctx.pmu);
+}
+
+void perf_event_task_tick(void)
+{
+	struct list_head *head = &__get_cpu_var(rotation_list);
+	struct perf_cpu_context *cpuctx, *tmp;
+
+	WARN_ON(!irqs_disabled());
+
+	list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) {
+		if (cpuctx->jiffies_interval == 1 ||
+				!(jiffies % cpuctx->jiffies_interval))
+			perf_rotate_context(cpuctx);
+	}
 }
 
 static int event_enable_on_exec(struct perf_event *event,
@@ -1685,20 +1689,18 @@ static int event_enable_on_exec(struct perf_event *event,
  * Enable all of a task's events that have been marked enable-on-exec.
  * This expects task == current.
  */
-static void perf_event_enable_on_exec(struct task_struct *task)
+static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 {
-	struct perf_event_context *ctx;
 	struct perf_event *event;
 	unsigned long flags;
 	int enabled = 0;
 	int ret;
 
 	local_irq_save(flags);
-	ctx = task->perf_event_ctxp;
 	if (!ctx || !ctx->nr_events)
 		goto out;
 
-	__perf_event_task_sched_out(ctx);
+	task_ctx_sched_out(ctx, EVENT_ALL);
 
 	raw_spin_lock(&ctx->lock);
 
@@ -1722,8 +1724,8 @@ static void perf_event_enable_on_exec(struct task_struct *task)
 
 	raw_spin_unlock(&ctx->lock);
 
-	perf_event_task_sched_in(task);
- out:
+	perf_event_context_sched_in(ctx);
+out:
 	local_irq_restore(flags);
 }
 
@@ -1732,9 +1734,9 @@ static void perf_event_enable_on_exec(struct task_struct *task)
  */
 static void __perf_event_read(void *info)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	/*
 	 * If this is a task context, we need to check whether it is
@@ -1782,11 +1784,219 @@ static u64 perf_event_read(struct perf_event *event)
 }
 
 /*
- * Initialize the perf_event context in a task_struct:
+ * Callchain support
  */
+
+struct callchain_cpus_entries {
+	struct rcu_head			rcu_head;
+	struct perf_callchain_entry	*cpu_entries[0];
+};
+
+static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
+static atomic_t nr_callchain_events;
+static DEFINE_MUTEX(callchain_mutex);
+struct callchain_cpus_entries *callchain_cpus_entries;
+
+
+__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs)
+{
+}
+
+__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs)
+{
+}
+
+static void release_callchain_buffers_rcu(struct rcu_head *head)
+{
+	struct callchain_cpus_entries *entries;
+	int cpu;
+
+	entries = container_of(head, struct callchain_cpus_entries, rcu_head);
+
+	for_each_possible_cpu(cpu)
+		kfree(entries->cpu_entries[cpu]);
+
+	kfree(entries);
+}
+
+static void release_callchain_buffers(void)
+{
+	struct callchain_cpus_entries *entries;
+
+	entries = callchain_cpus_entries;
+	rcu_assign_pointer(callchain_cpus_entries, NULL);
+	call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
+}
+
+static int alloc_callchain_buffers(void)
+{
+	int cpu;
+	int size;
+	struct callchain_cpus_entries *entries;
+
+	/*
+	 * We can't use the percpu allocation API for data that can be
+	 * accessed from NMI. Use a temporary manual per cpu allocation
+	 * until that gets sorted out.
+	 */
+	size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) *
+		num_possible_cpus();
+
+	entries = kzalloc(size, GFP_KERNEL);
+	if (!entries)
+		return -ENOMEM;
+
+	size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
+
+	for_each_possible_cpu(cpu) {
+		entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
+							 cpu_to_node(cpu));
+		if (!entries->cpu_entries[cpu])
+			goto fail;
+	}
+
+	rcu_assign_pointer(callchain_cpus_entries, entries);
+
+	return 0;
+
+fail:
+	for_each_possible_cpu(cpu)
+		kfree(entries->cpu_entries[cpu]);
+	kfree(entries);
+
+	return -ENOMEM;
+}
+
+static int get_callchain_buffers(void)
+{
+	int err = 0;
+	int count;
+
+	mutex_lock(&callchain_mutex);
+
+	count = atomic_inc_return(&nr_callchain_events);
+	if (WARN_ON_ONCE(count < 1)) {
+		err = -EINVAL;
+		goto exit;
+	}
+
+	if (count > 1) {
+		/* If the allocation failed, give up */
+		if (!callchain_cpus_entries)
+			err = -ENOMEM;
+		goto exit;
+	}
+
+	err = alloc_callchain_buffers();
+	if (err)
+		release_callchain_buffers();
+exit:
+	mutex_unlock(&callchain_mutex);
+
+	return err;
+}
+
+static void put_callchain_buffers(void)
+{
+	if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
+		release_callchain_buffers();
+		mutex_unlock(&callchain_mutex);
+	}
+}
+
+static int get_recursion_context(int *recursion)
+{
+	int rctx;
+
+	if (in_nmi())
+		rctx = 3;
+	else if (in_irq())
+		rctx = 2;
+	else if (in_softirq())
+		rctx = 1;
+	else
+		rctx = 0;
+
+	if (recursion[rctx])
+		return -1;
+
+	recursion[rctx]++;
+	barrier();
+
+	return rctx;
+}
+
+static inline void put_recursion_context(int *recursion, int rctx)
+{
+	barrier();
+	recursion[rctx]--;
+}
+
+static struct perf_callchain_entry *get_callchain_entry(int *rctx)
+{
+	int cpu;
+	struct callchain_cpus_entries *entries;
+
+	*rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
+	if (*rctx == -1)
+		return NULL;
+
+	entries = rcu_dereference(callchain_cpus_entries);
+	if (!entries)
+		return NULL;
+
+	cpu = smp_processor_id();
+
+	return &entries->cpu_entries[cpu][*rctx];
+}
+
 static void
-__perf_event_init_context(struct perf_event_context *ctx,
-			    struct task_struct *task)
+put_callchain_entry(int rctx)
+{
+	put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
+}
+
+static struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	int rctx;
+	struct perf_callchain_entry *entry;
+
+
+	entry = get_callchain_entry(&rctx);
+	if (rctx == -1)
+		return NULL;
+
+	if (!entry)
+		goto exit_put;
+
+	entry->nr = 0;
+
+	if (!user_mode(regs)) {
+		perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+		perf_callchain_kernel(entry, regs);
+		if (current->mm)
+			regs = task_pt_regs(current);
+		else
+			regs = NULL;
+	}
+
+	if (regs) {
+		perf_callchain_store(entry, PERF_CONTEXT_USER);
+		perf_callchain_user(entry, regs);
+	}
+
+exit_put:
+	put_callchain_entry(rctx);
+
+	return entry;
+}
+
+/*
+ * Initialize the perf_event context in a task_struct:
+ */
+static void __perf_event_init_context(struct perf_event_context *ctx)
 {
 	raw_spin_lock_init(&ctx->lock);
 	mutex_init(&ctx->mutex);
@@ -1794,45 +2004,38 @@ __perf_event_init_context(struct perf_event_context *ctx,
 	INIT_LIST_HEAD(&ctx->flexible_groups);
 	INIT_LIST_HEAD(&ctx->event_list);
 	atomic_set(&ctx->refcount, 1);
-	ctx->task = task;
 }
 
-static struct perf_event_context *find_get_context(pid_t pid, int cpu)
+static struct perf_event_context *
+alloc_perf_context(struct pmu *pmu, struct task_struct *task)
 {
 	struct perf_event_context *ctx;
-	struct perf_cpu_context *cpuctx;
-	struct task_struct *task;
-	unsigned long flags;
-	int err;
-
-	if (pid == -1 && cpu != -1) {
-		/* Must be root to operate on a CPU event: */
-		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return ERR_PTR(-EACCES);
 
-		if (cpu < 0 || cpu >= nr_cpumask_bits)
-			return ERR_PTR(-EINVAL);
+	ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL);
+	if (!ctx)
+		return NULL;
 
-		/*
-		 * We could be clever and allow to attach a event to an
-		 * offline CPU and activate it when the CPU comes up, but
-		 * that's for later.
-		 */
-		if (!cpu_online(cpu))
-			return ERR_PTR(-ENODEV);
+	__perf_event_init_context(ctx);
+	if (task) {
+		ctx->task = task;
+		get_task_struct(task);
+	}
+	ctx->pmu = pmu;
 
-		cpuctx = &per_cpu(perf_cpu_context, cpu);
-		ctx = &cpuctx->ctx;
-		get_ctx(ctx);
+	return ctx;
+}
 
-		return ctx;
-	}
+static struct task_struct *
+find_lively_task_by_vpid(pid_t vpid)
+{
+	struct task_struct *task;
+	int err;
 
 	rcu_read_lock();
-	if (!pid)
+	if (!vpid)
 		task = current;
 	else
-		task = find_task_by_vpid(pid);
+		task = find_task_by_vpid(vpid);
 	if (task)
 		get_task_struct(task);
 	rcu_read_unlock();
@@ -1852,35 +2055,79 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu)
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto errout;
 
- retry:
-	ctx = perf_lock_task_context(task, &flags);
+	return task;
+errout:
+	put_task_struct(task);
+	return ERR_PTR(err);
+
+}
+
+static struct perf_event_context *
+find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
+{
+	struct perf_event_context *ctx;
+	struct perf_cpu_context *cpuctx;
+	unsigned long flags;
+	int ctxn, err;
+
+	if (!task && cpu != -1) {
+		/* Must be root to operate on a CPU event: */
+		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+			return ERR_PTR(-EACCES);
+
+		if (cpu < 0 || cpu >= nr_cpumask_bits)
+			return ERR_PTR(-EINVAL);
+
+		/*
+		 * We could be clever and allow to attach a event to an
+		 * offline CPU and activate it when the CPU comes up, but
+		 * that's for later.
+		 */
+		if (!cpu_online(cpu))
+			return ERR_PTR(-ENODEV);
+
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+		ctx = &cpuctx->ctx;
+		get_ctx(ctx);
+
+		return ctx;
+	}
+
+	err = -EINVAL;
+	ctxn = pmu->task_ctx_nr;
+	if (ctxn < 0)
+		goto errout;
+
+retry:
+	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
 		unclone_ctx(ctx);
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
 
 	if (!ctx) {
-		ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL);
+		ctx = alloc_perf_context(pmu, task);
 		err = -ENOMEM;
 		if (!ctx)
 			goto errout;
-		__perf_event_init_context(ctx, task);
+
 		get_ctx(ctx);
-		if (cmpxchg(&task->perf_event_ctxp, NULL, ctx)) {
+
+		if (cmpxchg(&task->perf_event_ctxp[ctxn], NULL, ctx)) {
 			/*
 			 * We raced with some other task; use
 			 * the context they set.
 			 */
+			put_task_struct(task);
 			kfree(ctx);
 			goto retry;
 		}
-		get_task_struct(task);
 	}
 
 	put_task_struct(task);
 	return ctx;
 
- errout:
+errout:
 	put_task_struct(task);
 	return ERR_PTR(err);
 }
@@ -1913,6 +2160,8 @@ static void free_event(struct perf_event *event)
 			atomic_dec(&nr_comm_events);
 		if (event->attr.task)
 			atomic_dec(&nr_task_events);
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			put_callchain_buffers();
 	}
 
 	if (event->buffer) {
@@ -1923,7 +2172,9 @@ static void free_event(struct perf_event *event)
 	if (event->destroy)
 		event->destroy(event);
 
-	put_ctx(event->ctx);
+	if (event->ctx)
+		put_ctx(event->ctx);
+
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
 
@@ -2344,6 +2595,9 @@ int perf_event_task_disable(void)
 
 static int perf_event_index(struct perf_event *event)
 {
+	if (event->hw.state & PERF_HES_STOPPED)
+		return 0;
+
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
 		return 0;
 
@@ -2956,16 +3210,6 @@ void perf_event_do_pending(void)
 }
 
 /*
- * Callchain support -- arch specific
- */
-
-__weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	return NULL;
-}
-
-
-/*
  * We assume there is only KVM supporting the callbacks.
  * Later on, we might change it to a list if there is
  * another virtualization implementation supporting the callbacks.
@@ -3071,7 +3315,7 @@ again:
 	if (handle->wakeup != local_read(&buffer->wakeup))
 		perf_output_wakeup(handle);
 
- out:
+out:
 	preempt_enable();
 }
 
@@ -3459,14 +3703,20 @@ static void perf_event_output(struct perf_event *event, int nmi,
 	struct perf_output_handle handle;
 	struct perf_event_header header;
 
+	/* protect the callchain buffers */
+	rcu_read_lock();
+
 	perf_prepare_sample(&header, data, event, regs);
 
 	if (perf_output_begin(&handle, event, header.size, nmi, 1))
-		return;
+		goto exit;
 
 	perf_output_sample(&handle, &header, data, event);
 
 	perf_output_end(&handle);
+
+exit:
+	rcu_read_unlock();
 }
 
 /*
@@ -3580,16 +3830,27 @@ static void perf_event_task_ctx(struct perf_event_context *ctx,
 static void perf_event_task_event(struct perf_task_event *task_event)
 {
 	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx = task_event->task_ctx;
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+	int ctxn;
 
 	rcu_read_lock();
-	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_event_task_ctx(&cpuctx->ctx, task_event);
-	if (!ctx)
-		ctx = rcu_dereference(current->perf_event_ctxp);
-	if (ctx)
-		perf_event_task_ctx(ctx, task_event);
-	put_cpu_var(perf_cpu_context);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		perf_event_task_ctx(&cpuctx->ctx, task_event);
+
+		ctx = task_event->task_ctx;
+		if (!ctx) {
+			ctxn = pmu->task_ctx_nr;
+			if (ctxn < 0)
+				goto next;
+			ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		}
+		if (ctx)
+			perf_event_task_ctx(ctx, task_event);
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
+	}
 	rcu_read_unlock();
 }
 
@@ -3694,8 +3955,10 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 {
 	struct perf_cpu_context *cpuctx;
 	struct perf_event_context *ctx;
-	unsigned int size;
 	char comm[TASK_COMM_LEN];
+	unsigned int size;
+	struct pmu *pmu;
+	int ctxn;
 
 	memset(comm, 0, sizeof(comm));
 	strlcpy(comm, comm_event->task->comm, sizeof(comm));
@@ -3707,21 +3970,36 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
 
 	rcu_read_lock();
-	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_event_comm_ctx(&cpuctx->ctx, comm_event);
-	ctx = rcu_dereference(current->perf_event_ctxp);
-	if (ctx)
-		perf_event_comm_ctx(ctx, comm_event);
-	put_cpu_var(perf_cpu_context);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		perf_event_comm_ctx(&cpuctx->ctx, comm_event);
+
+		ctxn = pmu->task_ctx_nr;
+		if (ctxn < 0)
+			goto next;
+
+		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		if (ctx)
+			perf_event_comm_ctx(ctx, comm_event);
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
+	}
 	rcu_read_unlock();
 }
 
 void perf_event_comm(struct task_struct *task)
 {
 	struct perf_comm_event comm_event;
+	struct perf_event_context *ctx;
+	int ctxn;
 
-	if (task->perf_event_ctxp)
-		perf_event_enable_on_exec(task);
+	for_each_task_context_nr(ctxn) {
+		ctx = task->perf_event_ctxp[ctxn];
+		if (!ctx)
+			continue;
+
+		perf_event_enable_on_exec(ctx);
+	}
 
 	if (!atomic_read(&nr_comm_events))
 		return;
@@ -3823,6 +4101,8 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	char tmp[16];
 	char *buf = NULL;
 	const char *name;
+	struct pmu *pmu;
+	int ctxn;
 
 	memset(tmp, 0, sizeof(tmp));
 
@@ -3875,12 +4155,23 @@ got_name:
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
 	rcu_read_lock();
-	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, vma->vm_flags & VM_EXEC);
-	ctx = rcu_dereference(current->perf_event_ctxp);
-	if (ctx)
-		perf_event_mmap_ctx(ctx, mmap_event, vma->vm_flags & VM_EXEC);
-	put_cpu_var(perf_cpu_context);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
+					vma->vm_flags & VM_EXEC);
+
+		ctxn = pmu->task_ctx_nr;
+		if (ctxn < 0)
+			goto next;
+
+		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		if (ctx) {
+			perf_event_mmap_ctx(ctx, mmap_event,
+					vma->vm_flags & VM_EXEC);
+		}
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
+	}
 	rcu_read_unlock();
 
 	kfree(buf);
@@ -3962,8 +4253,6 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
 	struct hw_perf_event *hwc = &event->hw;
 	int ret = 0;
 
-	throttle = (throttle && event->pmu->unthrottle != NULL);
-
 	if (!throttle) {
 		hwc->interrupts++;
 	} else {
@@ -4031,6 +4320,17 @@ int perf_event_overflow(struct perf_event *event, int nmi,
  * Generic software event infrastructure
  */
 
+struct swevent_htable {
+	struct swevent_hlist		*swevent_hlist;
+	struct mutex			hlist_mutex;
+	int				hlist_refcount;
+
+	/* Recursion avoidance in each contexts */
+	int				recursion[PERF_NR_CONTEXTS];
+};
+
+static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
+
 /*
  * We directly increment event->count and keep a second value in
  * event->hw.period_left to count intervals. This period event
@@ -4088,7 +4388,7 @@ static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
 	}
 }
 
-static void perf_swevent_add(struct perf_event *event, u64 nr,
+static void perf_swevent_event(struct perf_event *event, u64 nr,
 			       int nmi, struct perf_sample_data *data,
 			       struct pt_regs *regs)
 {
@@ -4114,6 +4414,9 @@ static void perf_swevent_add(struct perf_event *event, u64 nr,
 static int perf_exclude_event(struct perf_event *event,
 			      struct pt_regs *regs)
 {
+	if (event->hw.state & PERF_HES_STOPPED)
+		return 0;
+
 	if (regs) {
 		if (event->attr.exclude_user && user_mode(regs))
 			return 1;
@@ -4160,11 +4463,11 @@ __find_swevent_head(struct swevent_hlist *hlist, u64 type, u32 event_id)
 
 /* For the read side: events when they trigger */
 static inline struct hlist_head *
-find_swevent_head_rcu(struct perf_cpu_context *ctx, u64 type, u32 event_id)
+find_swevent_head_rcu(struct swevent_htable *swhash, u64 type, u32 event_id)
 {
 	struct swevent_hlist *hlist;
 
-	hlist = rcu_dereference(ctx->swevent_hlist);
+	hlist = rcu_dereference(swhash->swevent_hlist);
 	if (!hlist)
 		return NULL;
 
@@ -4173,7 +4476,7 @@ find_swevent_head_rcu(struct perf_cpu_context *ctx, u64 type, u32 event_id)
 
 /* For the event head insertion and removal in the hlist */
 static inline struct hlist_head *
-find_swevent_head(struct perf_cpu_context *ctx, struct perf_event *event)
+find_swevent_head(struct swevent_htable *swhash, struct perf_event *event)
 {
 	struct swevent_hlist *hlist;
 	u32 event_id = event->attr.config;
@@ -4184,7 +4487,7 @@ find_swevent_head(struct perf_cpu_context *ctx, struct perf_event *event)
 	 * and release. Which makes the protected version suitable here.
 	 * The context lock guarantees that.
 	 */
-	hlist = rcu_dereference_protected(ctx->swevent_hlist,
+	hlist = rcu_dereference_protected(swhash->swevent_hlist,
 					  lockdep_is_held(&event->ctx->lock));
 	if (!hlist)
 		return NULL;
@@ -4197,23 +4500,19 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
 				    struct perf_sample_data *data,
 				    struct pt_regs *regs)
 {
-	struct perf_cpu_context *cpuctx;
+	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
 	struct perf_event *event;
 	struct hlist_node *node;
 	struct hlist_head *head;
 
-	cpuctx = &__get_cpu_var(perf_cpu_context);
-
 	rcu_read_lock();
-
-	head = find_swevent_head_rcu(cpuctx, type, event_id);
-
+	head = find_swevent_head_rcu(swhash, type, event_id);
 	if (!head)
 		goto end;
 
 	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_swevent_match(event, type, event_id, data, regs))
-			perf_swevent_add(event, nr, nmi, data, regs);
+			perf_swevent_event(event, nr, nmi, data, regs);
 	}
 end:
 	rcu_read_unlock();
@@ -4221,33 +4520,17 @@ end:
 
 int perf_swevent_get_recursion_context(void)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	int rctx;
-
-	if (in_nmi())
-		rctx = 3;
-	else if (in_irq())
-		rctx = 2;
-	else if (in_softirq())
-		rctx = 1;
-	else
-		rctx = 0;
+	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
 
-	if (cpuctx->recursion[rctx])
-		return -1;
-
-	cpuctx->recursion[rctx]++;
-	barrier();
-
-	return rctx;
+	return get_recursion_context(swhash->recursion);
 }
 EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
 void inline perf_swevent_put_recursion_context(int rctx)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	barrier();
-	cpuctx->recursion[rctx]--;
+	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+
+	put_recursion_context(swhash->recursion, rctx);
 }
 
 void __perf_sw_event(u32 event_id, u64 nr, int nmi,
@@ -4273,20 +4556,20 @@ static void perf_swevent_read(struct perf_event *event)
 {
 }
 
-static int perf_swevent_enable(struct perf_event *event)
+static int perf_swevent_add(struct perf_event *event, int flags)
 {
+	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
 	struct hw_perf_event *hwc = &event->hw;
-	struct perf_cpu_context *cpuctx;
 	struct hlist_head *head;
 
-	cpuctx = &__get_cpu_var(perf_cpu_context);
-
 	if (hwc->sample_period) {
 		hwc->last_period = hwc->sample_period;
 		perf_swevent_set_period(event);
 	}
 
-	head = find_swevent_head(cpuctx, event);
+	hwc->state = !(flags & PERF_EF_START);
+
+	head = find_swevent_head(swhash, event);
 	if (WARN_ON_ONCE(!head))
 		return -EINVAL;
 
@@ -4295,202 +4578,27 @@ static int perf_swevent_enable(struct perf_event *event)
 	return 0;
 }
 
-static void perf_swevent_disable(struct perf_event *event)
+static void perf_swevent_del(struct perf_event *event, int flags)
 {
 	hlist_del_rcu(&event->hlist_entry);
 }
 
-static void perf_swevent_void(struct perf_event *event)
-{
-}
-
-static int perf_swevent_int(struct perf_event *event)
-{
-	return 0;
-}
-
-static const struct pmu perf_ops_generic = {
-	.enable		= perf_swevent_enable,
-	.disable	= perf_swevent_disable,
-	.start		= perf_swevent_int,
-	.stop		= perf_swevent_void,
-	.read		= perf_swevent_read,
-	.unthrottle	= perf_swevent_void, /* hwc->interrupts already reset */
-};
-
-/*
- * hrtimer based swevent callback
- */
-
-static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
-{
-	enum hrtimer_restart ret = HRTIMER_RESTART;
-	struct perf_sample_data data;
-	struct pt_regs *regs;
-	struct perf_event *event;
-	u64 period;
-
-	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
-	event->pmu->read(event);
-
-	perf_sample_data_init(&data, 0);
-	data.period = event->hw.last_period;
-	regs = get_irq_regs();
-
-	if (regs && !perf_exclude_event(event, regs)) {
-		if (!(event->attr.exclude_idle && current->pid == 0))
-			if (perf_event_overflow(event, 0, &data, regs))
-				ret = HRTIMER_NORESTART;
-	}
-
-	period = max_t(u64, 10000, event->hw.sample_period);
-	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
-
-	return ret;
-}
-
-static void perf_swevent_start_hrtimer(struct perf_event *event)
+static void perf_swevent_start(struct perf_event *event, int flags)
 {
-	struct hw_perf_event *hwc = &event->hw;
-
-	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hwc->hrtimer.function = perf_swevent_hrtimer;
-	if (hwc->sample_period) {
-		u64 period;
-
-		if (hwc->remaining) {
-			if (hwc->remaining < 0)
-				period = 10000;
-			else
-				period = hwc->remaining;
-			hwc->remaining = 0;
-		} else {
-			period = max_t(u64, 10000, hwc->sample_period);
-		}
-		__hrtimer_start_range_ns(&hwc->hrtimer,
-				ns_to_ktime(period), 0,
-				HRTIMER_MODE_REL, 0);
-	}
+	event->hw.state = 0;
 }
 
-static void perf_swevent_cancel_hrtimer(struct perf_event *event)
+static void perf_swevent_stop(struct perf_event *event, int flags)
 {
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (hwc->sample_period) {
-		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
-		hwc->remaining = ktime_to_ns(remaining);
-
-		hrtimer_cancel(&hwc->hrtimer);
-	}
+	event->hw.state = PERF_HES_STOPPED;
 }
 
-/*
- * Software event: cpu wall time clock
- */
-
-static void cpu_clock_perf_event_update(struct perf_event *event)
-{
-	int cpu = raw_smp_processor_id();
-	s64 prev;
-	u64 now;
-
-	now = cpu_clock(cpu);
-	prev = local64_xchg(&event->hw.prev_count, now);
-	local64_add(now - prev, &event->count);
-}
-
-static int cpu_clock_perf_event_enable(struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	int cpu = raw_smp_processor_id();
-
-	local64_set(&hwc->prev_count, cpu_clock(cpu));
-	perf_swevent_start_hrtimer(event);
-
-	return 0;
-}
-
-static void cpu_clock_perf_event_disable(struct perf_event *event)
-{
-	perf_swevent_cancel_hrtimer(event);
-	cpu_clock_perf_event_update(event);
-}
-
-static void cpu_clock_perf_event_read(struct perf_event *event)
-{
-	cpu_clock_perf_event_update(event);
-}
-
-static const struct pmu perf_ops_cpu_clock = {
-	.enable		= cpu_clock_perf_event_enable,
-	.disable	= cpu_clock_perf_event_disable,
-	.read		= cpu_clock_perf_event_read,
-};
-
-/*
- * Software event: task time clock
- */
-
-static void task_clock_perf_event_update(struct perf_event *event, u64 now)
-{
-	u64 prev;
-	s64 delta;
-
-	prev = local64_xchg(&event->hw.prev_count, now);
-	delta = now - prev;
-	local64_add(delta, &event->count);
-}
-
-static int task_clock_perf_event_enable(struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	u64 now;
-
-	now = event->ctx->time;
-
-	local64_set(&hwc->prev_count, now);
-
-	perf_swevent_start_hrtimer(event);
-
-	return 0;
-}
-
-static void task_clock_perf_event_disable(struct perf_event *event)
-{
-	perf_swevent_cancel_hrtimer(event);
-	task_clock_perf_event_update(event, event->ctx->time);
-
-}
-
-static void task_clock_perf_event_read(struct perf_event *event)
-{
-	u64 time;
-
-	if (!in_nmi()) {
-		update_context_time(event->ctx);
-		time = event->ctx->time;
-	} else {
-		u64 now = perf_clock();
-		u64 delta = now - event->ctx->timestamp;
-		time = event->ctx->time + delta;
-	}
-
-	task_clock_perf_event_update(event, time);
-}
-
-static const struct pmu perf_ops_task_clock = {
-	.enable		= task_clock_perf_event_enable,
-	.disable	= task_clock_perf_event_disable,
-	.read		= task_clock_perf_event_read,
-};
-
 /* Deref the hlist from the update side */
 static inline struct swevent_hlist *
-swevent_hlist_deref(struct perf_cpu_context *cpuctx)
+swevent_hlist_deref(struct swevent_htable *swhash)
 {
-	return rcu_dereference_protected(cpuctx->swevent_hlist,
-					 lockdep_is_held(&cpuctx->hlist_mutex));
+	return rcu_dereference_protected(swhash->swevent_hlist,
+					 lockdep_is_held(&swhash->hlist_mutex));
 }
 
 static void swevent_hlist_release_rcu(struct rcu_head *rcu_head)
@@ -4501,27 +4609,27 @@ static void swevent_hlist_release_rcu(struct rcu_head *rcu_head)
 	kfree(hlist);
 }
 
-static void swevent_hlist_release(struct perf_cpu_context *cpuctx)
+static void swevent_hlist_release(struct swevent_htable *swhash)
 {
-	struct swevent_hlist *hlist = swevent_hlist_deref(cpuctx);
+	struct swevent_hlist *hlist = swevent_hlist_deref(swhash);
 
 	if (!hlist)
 		return;
 
-	rcu_assign_pointer(cpuctx->swevent_hlist, NULL);
+	rcu_assign_pointer(swhash->swevent_hlist, NULL);
 	call_rcu(&hlist->rcu_head, swevent_hlist_release_rcu);
 }
 
 static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)
 {
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
-	mutex_lock(&cpuctx->hlist_mutex);
+	mutex_lock(&swhash->hlist_mutex);
 
-	if (!--cpuctx->hlist_refcount)
-		swevent_hlist_release(cpuctx);
+	if (!--swhash->hlist_refcount)
+		swevent_hlist_release(swhash);
 
-	mutex_unlock(&cpuctx->hlist_mutex);
+	mutex_unlock(&swhash->hlist_mutex);
 }
 
 static void swevent_hlist_put(struct perf_event *event)
@@ -4539,12 +4647,12 @@ static void swevent_hlist_put(struct perf_event *event)
 
 static int swevent_hlist_get_cpu(struct perf_event *event, int cpu)
 {
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 	int err = 0;
 
-	mutex_lock(&cpuctx->hlist_mutex);
+	mutex_lock(&swhash->hlist_mutex);
 
-	if (!swevent_hlist_deref(cpuctx) && cpu_online(cpu)) {
+	if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
@@ -4552,11 +4660,11 @@ static int swevent_hlist_get_cpu(struct perf_event *event, int cpu)
 			err = -ENOMEM;
 			goto exit;
 		}
-		rcu_assign_pointer(cpuctx->swevent_hlist, hlist);
+		rcu_assign_pointer(swhash->swevent_hlist, hlist);
 	}
-	cpuctx->hlist_refcount++;
- exit:
-	mutex_unlock(&cpuctx->hlist_mutex);
+	swhash->hlist_refcount++;
+exit:
+	mutex_unlock(&swhash->hlist_mutex);
 
 	return err;
 }
@@ -4580,7 +4688,7 @@ static int swevent_hlist_get(struct perf_event *event)
 	put_online_cpus();
 
 	return 0;
- fail:
+fail:
 	for_each_possible_cpu(cpu) {
 		if (cpu == failed_cpu)
 			break;
@@ -4591,17 +4699,64 @@ static int swevent_hlist_get(struct perf_event *event)
 	return err;
 }
 
-#ifdef CONFIG_EVENT_TRACING
+atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
+
+static void sw_perf_event_destroy(struct perf_event *event)
+{
+	u64 event_id = event->attr.config;
+
+	WARN_ON(event->parent);
+
+	atomic_dec(&perf_swevent_enabled[event_id]);
+	swevent_hlist_put(event);
+}
+
+static int perf_swevent_init(struct perf_event *event)
+{
+	int event_id = event->attr.config;
 
-static const struct pmu perf_ops_tracepoint = {
-	.enable		= perf_trace_enable,
-	.disable	= perf_trace_disable,
-	.start		= perf_swevent_int,
-	.stop		= perf_swevent_void,
+	if (event->attr.type != PERF_TYPE_SOFTWARE)
+		return -ENOENT;
+
+	switch (event_id) {
+	case PERF_COUNT_SW_CPU_CLOCK:
+	case PERF_COUNT_SW_TASK_CLOCK:
+		return -ENOENT;
+
+	default:
+		break;
+	}
+
+	if (event_id > PERF_COUNT_SW_MAX)
+		return -ENOENT;
+
+	if (!event->parent) {
+		int err;
+
+		err = swevent_hlist_get(event);
+		if (err)
+			return err;
+
+		atomic_inc(&perf_swevent_enabled[event_id]);
+		event->destroy = sw_perf_event_destroy;
+	}
+
+	return 0;
+}
+
+static struct pmu perf_swevent = {
+	.task_ctx_nr	= perf_sw_context,
+
+	.event_init	= perf_swevent_init,
+	.add		= perf_swevent_add,
+	.del		= perf_swevent_del,
+	.start		= perf_swevent_start,
+	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
-	.unthrottle	= perf_swevent_void,
 };
 
+#ifdef CONFIG_EVENT_TRACING
+
 static int perf_tp_filter_match(struct perf_event *event,
 				struct perf_sample_data *data)
 {
@@ -4645,7 +4800,7 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
 
 	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_tp_event_match(event, &data, regs))
-			perf_swevent_add(event, count, 1, &data, regs);
+			perf_swevent_event(event, count, 1, &data, regs);
 	}
 
 	perf_swevent_put_recursion_context(rctx);
@@ -4657,10 +4812,13 @@ static void tp_perf_event_destroy(struct perf_event *event)
 	perf_trace_destroy(event);
 }
 
-static const struct pmu *tp_perf_event_init(struct perf_event *event)
+static int perf_tp_event_init(struct perf_event *event)
 {
 	int err;
 
+	if (event->attr.type != PERF_TYPE_TRACEPOINT)
+		return -ENOENT;
+
 	/*
 	 * Raw tracepoint data is a severe data leak, only allow root to
 	 * have these.
@@ -4668,15 +4826,31 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event)
 	if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
 			perf_paranoid_tracepoint_raw() &&
 			!capable(CAP_SYS_ADMIN))
-		return ERR_PTR(-EPERM);
+		return -EPERM;
 
 	err = perf_trace_init(event);
 	if (err)
-		return NULL;
+		return err;
 
 	event->destroy = tp_perf_event_destroy;
 
-	return &perf_ops_tracepoint;
+	return 0;
+}
+
+static struct pmu perf_tracepoint = {
+	.task_ctx_nr	= perf_sw_context,
+
+	.event_init	= perf_tp_event_init,
+	.add		= perf_trace_add,
+	.del		= perf_trace_del,
+	.start		= perf_swevent_start,
+	.stop		= perf_swevent_stop,
+	.read		= perf_swevent_read,
+};
+
+static inline void perf_tp_register(void)
+{
+	perf_pmu_register(&perf_tracepoint);
 }
 
 static int perf_event_set_filter(struct perf_event *event, void __user *arg)
@@ -4704,9 +4878,8 @@ static void perf_event_free_filter(struct perf_event *event)
 
 #else
 
-static const struct pmu *tp_perf_event_init(struct perf_event *event)
+static inline void perf_tp_register(void)
 {
-	return NULL;
 }
 
 static int perf_event_set_filter(struct perf_event *event, void __user *arg)
@@ -4721,105 +4894,389 @@ static void perf_event_free_filter(struct perf_event *event)
 #endif /* CONFIG_EVENT_TRACING */
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
-static void bp_perf_event_destroy(struct perf_event *event)
+void perf_bp_event(struct perf_event *bp, void *data)
 {
-	release_bp_slot(event);
+	struct perf_sample_data sample;
+	struct pt_regs *regs = data;
+
+	perf_sample_data_init(&sample, bp->attr.bp_addr);
+
+	if (!bp->hw.state && !perf_exclude_event(bp, regs))
+		perf_swevent_event(bp, 1, 1, &sample, regs);
 }
+#endif
+
+/*
+ * hrtimer based swevent callback
+ */
 
-static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 {
-	int err;
+	enum hrtimer_restart ret = HRTIMER_RESTART;
+	struct perf_sample_data data;
+	struct pt_regs *regs;
+	struct perf_event *event;
+	u64 period;
 
-	err = register_perf_hw_breakpoint(bp);
-	if (err)
-		return ERR_PTR(err);
+	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
+	event->pmu->read(event);
 
-	bp->destroy = bp_perf_event_destroy;
+	perf_sample_data_init(&data, 0);
+	data.period = event->hw.last_period;
+	regs = get_irq_regs();
+
+	if (regs && !perf_exclude_event(event, regs)) {
+		if (!(event->attr.exclude_idle && current->pid == 0))
+			if (perf_event_overflow(event, 0, &data, regs))
+				ret = HRTIMER_NORESTART;
+	}
 
-	return &perf_ops_bp;
+	period = max_t(u64, 10000, event->hw.sample_period);
+	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
+
+	return ret;
 }
 
-void perf_bp_event(struct perf_event *bp, void *data)
+static void perf_swevent_start_hrtimer(struct perf_event *event)
 {
-	struct perf_sample_data sample;
-	struct pt_regs *regs = data;
+	struct hw_perf_event *hwc = &event->hw;
 
-	perf_sample_data_init(&sample, bp->attr.bp_addr);
+	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hwc->hrtimer.function = perf_swevent_hrtimer;
+	if (hwc->sample_period) {
+		s64 period = local64_read(&hwc->period_left);
 
-	if (!perf_exclude_event(bp, regs))
-		perf_swevent_add(bp, 1, 1, &sample, regs);
+		if (period) {
+			if (period < 0)
+				period = 10000;
+
+			local64_set(&hwc->period_left, 0);
+		} else {
+			period = max_t(u64, 10000, hwc->sample_period);
+		}
+		__hrtimer_start_range_ns(&hwc->hrtimer,
+				ns_to_ktime(period), 0,
+				HRTIMER_MODE_REL_PINNED, 0);
+	}
 }
-#else
-static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+
+static void perf_swevent_cancel_hrtimer(struct perf_event *event)
 {
-	return NULL;
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->sample_period) {
+		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
+		local64_set(&hwc->period_left, ktime_to_ns(remaining));
+
+		hrtimer_cancel(&hwc->hrtimer);
+	}
 }
 
-void perf_bp_event(struct perf_event *bp, void *regs)
+/*
+ * Software event: cpu wall time clock
+ */
+
+static void cpu_clock_event_update(struct perf_event *event)
 {
+	s64 prev;
+	u64 now;
+
+	now = local_clock();
+	prev = local64_xchg(&event->hw.prev_count, now);
+	local64_add(now - prev, &event->count);
 }
-#endif
 
-atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
+static void cpu_clock_event_start(struct perf_event *event, int flags)
+{
+	local64_set(&event->hw.prev_count, local_clock());
+	perf_swevent_start_hrtimer(event);
+}
 
-static void sw_perf_event_destroy(struct perf_event *event)
+static void cpu_clock_event_stop(struct perf_event *event, int flags)
 {
-	u64 event_id = event->attr.config;
+	perf_swevent_cancel_hrtimer(event);
+	cpu_clock_event_update(event);
+}
 
-	WARN_ON(event->parent);
+static int cpu_clock_event_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		cpu_clock_event_start(event, flags);
 
-	atomic_dec(&perf_swevent_enabled[event_id]);
-	swevent_hlist_put(event);
+	return 0;
 }
 
-static const struct pmu *sw_perf_event_init(struct perf_event *event)
+static void cpu_clock_event_del(struct perf_event *event, int flags)
 {
-	const struct pmu *pmu = NULL;
-	u64 event_id = event->attr.config;
+	cpu_clock_event_stop(event, flags);
+}
+
+static void cpu_clock_event_read(struct perf_event *event)
+{
+	cpu_clock_event_update(event);
+}
+
+static int cpu_clock_event_init(struct perf_event *event)
+{
+	if (event->attr.type != PERF_TYPE_SOFTWARE)
+		return -ENOENT;
+
+	if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
+		return -ENOENT;
+
+	return 0;
+}
+
+static struct pmu perf_cpu_clock = {
+	.task_ctx_nr	= perf_sw_context,
+
+	.event_init	= cpu_clock_event_init,
+	.add		= cpu_clock_event_add,
+	.del		= cpu_clock_event_del,
+	.start		= cpu_clock_event_start,
+	.stop		= cpu_clock_event_stop,
+	.read		= cpu_clock_event_read,
+};
+
+/*
+ * Software event: task time clock
+ */
+
+static void task_clock_event_update(struct perf_event *event, u64 now)
+{
+	u64 prev;
+	s64 delta;
+
+	prev = local64_xchg(&event->hw.prev_count, now);
+	delta = now - prev;
+	local64_add(delta, &event->count);
+}
+
+static void task_clock_event_start(struct perf_event *event, int flags)
+{
+	local64_set(&event->hw.prev_count, event->ctx->time);
+	perf_swevent_start_hrtimer(event);
+}
+
+static void task_clock_event_stop(struct perf_event *event, int flags)
+{
+	perf_swevent_cancel_hrtimer(event);
+	task_clock_event_update(event, event->ctx->time);
+}
+
+static int task_clock_event_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		task_clock_event_start(event, flags);
+
+	return 0;
+}
+
+static void task_clock_event_del(struct perf_event *event, int flags)
+{
+	task_clock_event_stop(event, PERF_EF_UPDATE);
+}
+
+static void task_clock_event_read(struct perf_event *event)
+{
+	u64 time;
+
+	if (!in_nmi()) {
+		update_context_time(event->ctx);
+		time = event->ctx->time;
+	} else {
+		u64 now = perf_clock();
+		u64 delta = now - event->ctx->timestamp;
+		time = event->ctx->time + delta;
+	}
+
+	task_clock_event_update(event, time);
+}
+
+static int task_clock_event_init(struct perf_event *event)
+{
+	if (event->attr.type != PERF_TYPE_SOFTWARE)
+		return -ENOENT;
+
+	if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
+		return -ENOENT;
+
+	return 0;
+}
+
+static struct pmu perf_task_clock = {
+	.task_ctx_nr	= perf_sw_context,
+
+	.event_init	= task_clock_event_init,
+	.add		= task_clock_event_add,
+	.del		= task_clock_event_del,
+	.start		= task_clock_event_start,
+	.stop		= task_clock_event_stop,
+	.read		= task_clock_event_read,
+};
+
+static void perf_pmu_nop_void(struct pmu *pmu)
+{
+}
+
+static int perf_pmu_nop_int(struct pmu *pmu)
+{
+	return 0;
+}
+
+static void perf_pmu_start_txn(struct pmu *pmu)
+{
+	perf_pmu_disable(pmu);
+}
+
+static int perf_pmu_commit_txn(struct pmu *pmu)
+{
+	perf_pmu_enable(pmu);
+	return 0;
+}
 
+static void perf_pmu_cancel_txn(struct pmu *pmu)
+{
+	perf_pmu_enable(pmu);
+}
+
+/*
+ * Ensures all contexts with the same task_ctx_nr have the same
+ * pmu_cpu_context too.
+ */
+static void *find_pmu_context(int ctxn)
+{
+	struct pmu *pmu;
+
+	if (ctxn < 0)
+		return NULL;
+
+	list_for_each_entry(pmu, &pmus, entry) {
+		if (pmu->task_ctx_nr == ctxn)
+			return pmu->pmu_cpu_context;
+	}
+
+	return NULL;
+}
+
+static void free_pmu_context(void * __percpu cpu_context)
+{
+	struct pmu *pmu;
+
+	mutex_lock(&pmus_lock);
 	/*
-	 * Software events (currently) can't in general distinguish
-	 * between user, kernel and hypervisor events.
-	 * However, context switches and cpu migrations are considered
-	 * to be kernel events, and page faults are never hypervisor
-	 * events.
+	 * Like a real lame refcount.
 	 */
-	switch (event_id) {
-	case PERF_COUNT_SW_CPU_CLOCK:
-		pmu = &perf_ops_cpu_clock;
+	list_for_each_entry(pmu, &pmus, entry) {
+		if (pmu->pmu_cpu_context == cpu_context)
+			goto out;
+	}
 
-		break;
-	case PERF_COUNT_SW_TASK_CLOCK:
-		/*
-		 * If the user instantiates this as a per-cpu event,
-		 * use the cpu_clock event instead.
-		 */
-		if (event->ctx->task)
-			pmu = &perf_ops_task_clock;
-		else
-			pmu = &perf_ops_cpu_clock;
+	free_percpu(cpu_context);
+out:
+	mutex_unlock(&pmus_lock);
+}
 
-		break;
-	case PERF_COUNT_SW_PAGE_FAULTS:
-	case PERF_COUNT_SW_PAGE_FAULTS_MIN:
-	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
-	case PERF_COUNT_SW_CONTEXT_SWITCHES:
-	case PERF_COUNT_SW_CPU_MIGRATIONS:
-	case PERF_COUNT_SW_ALIGNMENT_FAULTS:
-	case PERF_COUNT_SW_EMULATION_FAULTS:
-		if (!event->parent) {
-			int err;
-
-			err = swevent_hlist_get(event);
-			if (err)
-				return ERR_PTR(err);
+int perf_pmu_register(struct pmu *pmu)
+{
+	int cpu, ret;
 
-			atomic_inc(&perf_swevent_enabled[event_id]);
-			event->destroy = sw_perf_event_destroy;
+	mutex_lock(&pmus_lock);
+	ret = -ENOMEM;
+	pmu->pmu_disable_count = alloc_percpu(int);
+	if (!pmu->pmu_disable_count)
+		goto unlock;
+
+	pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr);
+	if (pmu->pmu_cpu_context)
+		goto got_cpu_context;
+
+	pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
+	if (!pmu->pmu_cpu_context)
+		goto free_pdc;
+
+	for_each_possible_cpu(cpu) {
+		struct perf_cpu_context *cpuctx;
+
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+		__perf_event_init_context(&cpuctx->ctx);
+		cpuctx->ctx.type = cpu_context;
+		cpuctx->ctx.pmu = pmu;
+		cpuctx->jiffies_interval = 1;
+		INIT_LIST_HEAD(&cpuctx->rotation_list);
+	}
+
+got_cpu_context:
+	if (!pmu->start_txn) {
+		if (pmu->pmu_enable) {
+			/*
+			 * If we have pmu_enable/pmu_disable calls, install
+			 * transaction stubs that use that to try and batch
+			 * hardware accesses.
+			 */
+			pmu->start_txn  = perf_pmu_start_txn;
+			pmu->commit_txn = perf_pmu_commit_txn;
+			pmu->cancel_txn = perf_pmu_cancel_txn;
+		} else {
+			pmu->start_txn  = perf_pmu_nop_void;
+			pmu->commit_txn = perf_pmu_nop_int;
+			pmu->cancel_txn = perf_pmu_nop_void;
+		}
+	}
+
+	if (!pmu->pmu_enable) {
+		pmu->pmu_enable  = perf_pmu_nop_void;
+		pmu->pmu_disable = perf_pmu_nop_void;
+	}
+
+	list_add_rcu(&pmu->entry, &pmus);
+	ret = 0;
+unlock:
+	mutex_unlock(&pmus_lock);
+
+	return ret;
+
+free_pdc:
+	free_percpu(pmu->pmu_disable_count);
+	goto unlock;
+}
+
+void perf_pmu_unregister(struct pmu *pmu)
+{
+	mutex_lock(&pmus_lock);
+	list_del_rcu(&pmu->entry);
+	mutex_unlock(&pmus_lock);
+
+	/*
+	 * We dereference the pmu list under both SRCU and regular RCU, so
+	 * synchronize against both of those.
+	 */
+	synchronize_srcu(&pmus_srcu);
+	synchronize_rcu();
+
+	free_percpu(pmu->pmu_disable_count);
+	free_pmu_context(pmu->pmu_cpu_context);
+}
+
+struct pmu *perf_init_event(struct perf_event *event)
+{
+	struct pmu *pmu = NULL;
+	int idx;
+
+	idx = srcu_read_lock(&pmus_srcu);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		int ret = pmu->event_init(event);
+		if (!ret)
+			goto unlock;
+
+		if (ret != -ENOENT) {
+			pmu = ERR_PTR(ret);
+			goto unlock;
 		}
-		pmu = &perf_ops_generic;
-		break;
 	}
+	pmu = ERR_PTR(-ENOENT);
+unlock:
+	srcu_read_unlock(&pmus_srcu, idx);
 
 	return pmu;
 }
@@ -4828,20 +5285,17 @@ static const struct pmu *sw_perf_event_init(struct perf_event *event)
  * Allocate and initialize a event structure
  */
 static struct perf_event *
-perf_event_alloc(struct perf_event_attr *attr,
-		   int cpu,
-		   struct perf_event_context *ctx,
+perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		   struct perf_event *group_leader,
 		   struct perf_event *parent_event,
-		   perf_overflow_handler_t overflow_handler,
-		   gfp_t gfpflags)
+		   perf_overflow_handler_t overflow_handler)
 {
-	const struct pmu *pmu;
+	struct pmu *pmu;
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	long err;
 
-	event = kzalloc(sizeof(*event), gfpflags);
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
 	if (!event)
 		return ERR_PTR(-ENOMEM);
 
@@ -4866,7 +5320,6 @@ perf_event_alloc(struct perf_event_attr *attr,
 	event->attr		= *attr;
 	event->group_leader	= group_leader;
 	event->pmu		= NULL;
-	event->ctx		= ctx;
 	event->oncpu		= -1;
 
 	event->parent		= parent_event;
@@ -4900,29 +5353,8 @@ perf_event_alloc(struct perf_event_attr *attr,
 	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
 		goto done;
 
-	switch (attr->type) {
-	case PERF_TYPE_RAW:
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-		pmu = hw_perf_event_init(event);
-		break;
+	pmu = perf_init_event(event);
 
-	case PERF_TYPE_SOFTWARE:
-		pmu = sw_perf_event_init(event);
-		break;
-
-	case PERF_TYPE_TRACEPOINT:
-		pmu = tp_perf_event_init(event);
-		break;
-
-	case PERF_TYPE_BREAKPOINT:
-		pmu = bp_perf_event_init(event);
-		break;
-
-
-	default:
-		break;
-	}
 done:
 	err = 0;
 	if (!pmu)
@@ -4947,6 +5379,13 @@ done:
 			atomic_inc(&nr_comm_events);
 		if (event->attr.task)
 			atomic_inc(&nr_task_events);
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
+			err = get_callchain_buffers();
+			if (err) {
+				free_event(event);
+				return ERR_PTR(err);
+			}
+		}
 	}
 
 	return event;
@@ -5094,12 +5533,16 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_attr __user *, attr_uptr,
 		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
 {
-	struct perf_event *event, *group_leader = NULL, *output_event = NULL;
+	struct perf_event *group_leader = NULL, *output_event = NULL;
+	struct perf_event *event, *sibling;
 	struct perf_event_attr attr;
 	struct perf_event_context *ctx;
 	struct file *event_file = NULL;
 	struct file *group_file = NULL;
+	struct task_struct *task = NULL;
+	struct pmu *pmu;
 	int event_fd;
+	int move_group = 0;
 	int fput_needed = 0;
 	int err;
 
@@ -5125,20 +5568,11 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (event_fd < 0)
 		return event_fd;
 
-	/*
-	 * Get the target context (task or percpu):
-	 */
-	ctx = find_get_context(pid, cpu);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto err_fd;
-	}
-
 	if (group_fd != -1) {
 		group_leader = perf_fget_light(group_fd, &fput_needed);
 		if (IS_ERR(group_leader)) {
 			err = PTR_ERR(group_leader);
-			goto err_put_context;
+			goto err_fd;
 		}
 		group_file = group_leader->filp;
 		if (flags & PERF_FLAG_FD_OUTPUT)
@@ -5147,6 +5581,58 @@ SYSCALL_DEFINE5(perf_event_open,
 			group_leader = NULL;
 	}
 
+	event = perf_event_alloc(&attr, cpu, group_leader, NULL, NULL);
+	if (IS_ERR(event)) {
+		err = PTR_ERR(event);
+		goto err_fd;
+	}
+
+	/*
+	 * Special case software events and allow them to be part of
+	 * any hardware group.
+	 */
+	pmu = event->pmu;
+
+	if (group_leader &&
+	    (is_software_event(event) != is_software_event(group_leader))) {
+		if (is_software_event(event)) {
+			/*
+			 * If event and group_leader are not both a software
+			 * event, and event is, then group leader is not.
+			 *
+			 * Allow the addition of software events to !software
+			 * groups, this is safe because software events never
+			 * fail to schedule.
+			 */
+			pmu = group_leader->pmu;
+		} else if (is_software_event(group_leader) &&
+			   (group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
+			/*
+			 * In case the group is a pure software group, and we
+			 * try to add a hardware event, move the whole group to
+			 * the hardware context.
+			 */
+			move_group = 1;
+		}
+	}
+
+	if (pid != -1) {
+		task = find_lively_task_by_vpid(pid);
+		if (IS_ERR(task)) {
+			err = PTR_ERR(task);
+			goto err_group_fd;
+		}
+	}
+
+	/*
+	 * Get the target context (task or percpu):
+	 */
+	ctx = find_get_context(pmu, task, cpu);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto err_group_fd;
+	}
+
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
@@ -5158,42 +5644,66 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * becoming part of another group-sibling):
 		 */
 		if (group_leader->group_leader != group_leader)
-			goto err_put_context;
+			goto err_context;
 		/*
 		 * Do not allow to attach to a group in a different
 		 * task or CPU context:
 		 */
-		if (group_leader->ctx != ctx)
-			goto err_put_context;
+		if (move_group) {
+			if (group_leader->ctx->type != ctx->type)
+				goto err_context;
+		} else {
+			if (group_leader->ctx != ctx)
+				goto err_context;
+		}
+
 		/*
 		 * Only a group leader can be exclusive or pinned
 		 */
 		if (attr.exclusive || attr.pinned)
-			goto err_put_context;
-	}
-
-	event = perf_event_alloc(&attr, cpu, ctx, group_leader,
-				     NULL, NULL, GFP_KERNEL);
-	if (IS_ERR(event)) {
-		err = PTR_ERR(event);
-		goto err_put_context;
+			goto err_context;
 	}
 
 	if (output_event) {
 		err = perf_event_set_output(event, output_event);
 		if (err)
-			goto err_free_put_context;
+			goto err_context;
 	}
 
 	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
 	if (IS_ERR(event_file)) {
 		err = PTR_ERR(event_file);
-		goto err_free_put_context;
+		goto err_context;
+	}
+
+	if (move_group) {
+		struct perf_event_context *gctx = group_leader->ctx;
+
+		mutex_lock(&gctx->mutex);
+		perf_event_remove_from_context(group_leader);
+		list_for_each_entry(sibling, &group_leader->sibling_list,
+				    group_entry) {
+			perf_event_remove_from_context(sibling);
+			put_ctx(gctx);
+		}
+		mutex_unlock(&gctx->mutex);
+		put_ctx(gctx);
 	}
 
 	event->filp = event_file;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
+
+	if (move_group) {
+		perf_install_in_context(ctx, group_leader, cpu);
+		get_ctx(ctx);
+		list_for_each_entry(sibling, &group_leader->sibling_list,
+				    group_entry) {
+			perf_install_in_context(ctx, sibling, cpu);
+			get_ctx(ctx);
+		}
+	}
+
 	perf_install_in_context(ctx, event, cpu);
 	++ctx->generation;
 	mutex_unlock(&ctx->mutex);
@@ -5214,11 +5724,11 @@ SYSCALL_DEFINE5(perf_event_open,
 	fd_install(event_fd, event_file);
 	return event_fd;
 
-err_free_put_context:
-	free_event(event);
-err_put_context:
-	fput_light(group_file, fput_needed);
+err_context:
 	put_ctx(ctx);
+err_group_fd:
+	fput_light(group_file, fput_needed);
+	free_event(event);
 err_fd:
 	put_unused_fd(event_fd);
 	return err;
@@ -5229,32 +5739,31 @@ err_fd:
  *
  * @attr: attributes of the counter to create
  * @cpu: cpu in which the counter is bound
- * @pid: task to profile
+ * @task: task to profile (NULL for percpu)
  */
 struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
-				 pid_t pid,
+				 struct task_struct *task,
 				 perf_overflow_handler_t overflow_handler)
 {
-	struct perf_event *event;
 	struct perf_event_context *ctx;
+	struct perf_event *event;
 	int err;
 
 	/*
 	 * Get the target context (task or percpu):
 	 */
 
-	ctx = find_get_context(pid, cpu);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto err_exit;
-	}
-
-	event = perf_event_alloc(attr, cpu, ctx, NULL,
-				 NULL, overflow_handler, GFP_KERNEL);
+	event = perf_event_alloc(attr, cpu, NULL, NULL, overflow_handler);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
-		goto err_put_context;
+		goto err;
+	}
+
+	ctx = find_get_context(event->pmu, task, cpu);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto err_free;
 	}
 
 	event->filp = NULL;
@@ -5272,112 +5781,13 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	return event;
 
- err_put_context:
-	put_ctx(ctx);
- err_exit:
+err_free:
+	free_event(event);
+err:
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
 
-/*
- * inherit a event from parent task to child task:
- */
-static struct perf_event *
-inherit_event(struct perf_event *parent_event,
-	      struct task_struct *parent,
-	      struct perf_event_context *parent_ctx,
-	      struct task_struct *child,
-	      struct perf_event *group_leader,
-	      struct perf_event_context *child_ctx)
-{
-	struct perf_event *child_event;
-
-	/*
-	 * Instead of creating recursive hierarchies of events,
-	 * we link inherited events back to the original parent,
-	 * which has a filp for sure, which we use as the reference
-	 * count:
-	 */
-	if (parent_event->parent)
-		parent_event = parent_event->parent;
-
-	child_event = perf_event_alloc(&parent_event->attr,
-					   parent_event->cpu, child_ctx,
-					   group_leader, parent_event,
-					   NULL, GFP_KERNEL);
-	if (IS_ERR(child_event))
-		return child_event;
-	get_ctx(child_ctx);
-
-	/*
-	 * Make the child state follow the state of the parent event,
-	 * not its attr.disabled bit.  We hold the parent's mutex,
-	 * so we won't race with perf_event_{en, dis}able_family.
-	 */
-	if (parent_event->state >= PERF_EVENT_STATE_INACTIVE)
-		child_event->state = PERF_EVENT_STATE_INACTIVE;
-	else
-		child_event->state = PERF_EVENT_STATE_OFF;
-
-	if (parent_event->attr.freq) {
-		u64 sample_period = parent_event->hw.sample_period;
-		struct hw_perf_event *hwc = &child_event->hw;
-
-		hwc->sample_period = sample_period;
-		hwc->last_period   = sample_period;
-
-		local64_set(&hwc->period_left, sample_period);
-	}
-
-	child_event->overflow_handler = parent_event->overflow_handler;
-
-	/*
-	 * Link it up in the child's context:
-	 */
-	add_event_to_ctx(child_event, child_ctx);
-
-	/*
-	 * Get a reference to the parent filp - we will fput it
-	 * when the child event exits. This is safe to do because
-	 * we are in the parent and we know that the filp still
-	 * exists and has a nonzero count:
-	 */
-	atomic_long_inc(&parent_event->filp->f_count);
-
-	/*
-	 * Link this into the parent event's child list
-	 */
-	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
-	mutex_lock(&parent_event->child_mutex);
-	list_add_tail(&child_event->child_list, &parent_event->child_list);
-	mutex_unlock(&parent_event->child_mutex);
-
-	return child_event;
-}
-
-static int inherit_group(struct perf_event *parent_event,
-	      struct task_struct *parent,
-	      struct perf_event_context *parent_ctx,
-	      struct task_struct *child,
-	      struct perf_event_context *child_ctx)
-{
-	struct perf_event *leader;
-	struct perf_event *sub;
-	struct perf_event *child_ctr;
-
-	leader = inherit_event(parent_event, parent, parent_ctx,
-				 child, NULL, child_ctx);
-	if (IS_ERR(leader))
-		return PTR_ERR(leader);
-	list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
-		child_ctr = inherit_event(sub, parent, parent_ctx,
-					    child, leader, child_ctx);
-		if (IS_ERR(child_ctr))
-			return PTR_ERR(child_ctr);
-	}
-	return 0;
-}
-
 static void sync_child_event(struct perf_event *child_event,
 			       struct task_struct *child)
 {
@@ -5434,16 +5844,13 @@ __perf_event_exit_task(struct perf_event *child_event,
 	}
 }
 
-/*
- * When a child task exits, feed back event values to parent events.
- */
-void perf_event_exit_task(struct task_struct *child)
+static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 {
 	struct perf_event *child_event, *tmp;
 	struct perf_event_context *child_ctx;
 	unsigned long flags;
 
-	if (likely(!child->perf_event_ctxp)) {
+	if (likely(!child->perf_event_ctxp[ctxn])) {
 		perf_event_task(child, NULL, 0);
 		return;
 	}
@@ -5455,7 +5862,7 @@ void perf_event_exit_task(struct task_struct *child)
 	 * scheduled, so we are now safe from rescheduling changing
 	 * our context.
 	 */
-	child_ctx = child->perf_event_ctxp;
+	child_ctx = child->perf_event_ctxp[ctxn];
 	__perf_event_task_sched_out(child_ctx);
 
 	/*
@@ -5464,7 +5871,7 @@ void perf_event_exit_task(struct task_struct *child)
 	 * incremented the context's refcount before we do put_ctx below.
 	 */
 	raw_spin_lock(&child_ctx->lock);
-	child->perf_event_ctxp = NULL;
+	child->perf_event_ctxp[ctxn] = NULL;
 	/*
 	 * If this context is a clone; unclone it so it can't get
 	 * swapped to another process while we're removing all
@@ -5517,6 +5924,17 @@ again:
 	put_ctx(child_ctx);
 }
 
+/*
+ * When a child task exits, feed back event values to parent events.
+ */
+void perf_event_exit_task(struct task_struct *child)
+{
+	int ctxn;
+
+	for_each_task_context_nr(ctxn)
+		perf_event_exit_task_context(child, ctxn);
+}
+
 static void perf_free_event(struct perf_event *event,
 			    struct perf_event_context *ctx)
 {
@@ -5538,48 +5956,165 @@ static void perf_free_event(struct perf_event *event,
 
 /*
  * free an unexposed, unused context as created by inheritance by
- * init_task below, used by fork() in case of fail.
+ * perf_event_init_task below, used by fork() in case of fail.
  */
 void perf_event_free_task(struct task_struct *task)
 {
-	struct perf_event_context *ctx = task->perf_event_ctxp;
+	struct perf_event_context *ctx;
 	struct perf_event *event, *tmp;
+	int ctxn;
 
-	if (!ctx)
-		return;
+	for_each_task_context_nr(ctxn) {
+		ctx = task->perf_event_ctxp[ctxn];
+		if (!ctx)
+			continue;
 
-	mutex_lock(&ctx->mutex);
+		mutex_lock(&ctx->mutex);
 again:
-	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		perf_free_event(event, ctx);
+		list_for_each_entry_safe(event, tmp, &ctx->pinned_groups,
+				group_entry)
+			perf_free_event(event, ctx);
 
-	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups,
-				 group_entry)
-		perf_free_event(event, ctx);
+		list_for_each_entry_safe(event, tmp, &ctx->flexible_groups,
+				group_entry)
+			perf_free_event(event, ctx);
 
-	if (!list_empty(&ctx->pinned_groups) ||
-	    !list_empty(&ctx->flexible_groups))
-		goto again;
+		if (!list_empty(&ctx->pinned_groups) ||
+				!list_empty(&ctx->flexible_groups))
+			goto again;
 
-	mutex_unlock(&ctx->mutex);
+		mutex_unlock(&ctx->mutex);
 
-	put_ctx(ctx);
+		put_ctx(ctx);
+	}
+}
+
+void perf_event_delayed_put(struct task_struct *task)
+{
+	int ctxn;
+
+	for_each_task_context_nr(ctxn)
+		WARN_ON_ONCE(task->perf_event_ctxp[ctxn]);
+}
+
+/*
+ * inherit a event from parent task to child task:
+ */
+static struct perf_event *
+inherit_event(struct perf_event *parent_event,
+	      struct task_struct *parent,
+	      struct perf_event_context *parent_ctx,
+	      struct task_struct *child,
+	      struct perf_event *group_leader,
+	      struct perf_event_context *child_ctx)
+{
+	struct perf_event *child_event;
+	unsigned long flags;
+
+	/*
+	 * Instead of creating recursive hierarchies of events,
+	 * we link inherited events back to the original parent,
+	 * which has a filp for sure, which we use as the reference
+	 * count:
+	 */
+	if (parent_event->parent)
+		parent_event = parent_event->parent;
+
+	child_event = perf_event_alloc(&parent_event->attr,
+					   parent_event->cpu,
+					   group_leader, parent_event,
+					   NULL);
+	if (IS_ERR(child_event))
+		return child_event;
+	get_ctx(child_ctx);
+
+	/*
+	 * Make the child state follow the state of the parent event,
+	 * not its attr.disabled bit.  We hold the parent's mutex,
+	 * so we won't race with perf_event_{en, dis}able_family.
+	 */
+	if (parent_event->state >= PERF_EVENT_STATE_INACTIVE)
+		child_event->state = PERF_EVENT_STATE_INACTIVE;
+	else
+		child_event->state = PERF_EVENT_STATE_OFF;
+
+	if (parent_event->attr.freq) {
+		u64 sample_period = parent_event->hw.sample_period;
+		struct hw_perf_event *hwc = &child_event->hw;
+
+		hwc->sample_period = sample_period;
+		hwc->last_period   = sample_period;
+
+		local64_set(&hwc->period_left, sample_period);
+	}
+
+	child_event->ctx = child_ctx;
+	child_event->overflow_handler = parent_event->overflow_handler;
+
+	/*
+	 * Link it up in the child's context:
+	 */
+	raw_spin_lock_irqsave(&child_ctx->lock, flags);
+	add_event_to_ctx(child_event, child_ctx);
+	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
+
+	/*
+	 * Get a reference to the parent filp - we will fput it
+	 * when the child event exits. This is safe to do because
+	 * we are in the parent and we know that the filp still
+	 * exists and has a nonzero count:
+	 */
+	atomic_long_inc(&parent_event->filp->f_count);
+
+	/*
+	 * Link this into the parent event's child list
+	 */
+	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
+	mutex_lock(&parent_event->child_mutex);
+	list_add_tail(&child_event->child_list, &parent_event->child_list);
+	mutex_unlock(&parent_event->child_mutex);
+
+	return child_event;
+}
+
+static int inherit_group(struct perf_event *parent_event,
+	      struct task_struct *parent,
+	      struct perf_event_context *parent_ctx,
+	      struct task_struct *child,
+	      struct perf_event_context *child_ctx)
+{
+	struct perf_event *leader;
+	struct perf_event *sub;
+	struct perf_event *child_ctr;
+
+	leader = inherit_event(parent_event, parent, parent_ctx,
+				 child, NULL, child_ctx);
+	if (IS_ERR(leader))
+		return PTR_ERR(leader);
+	list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
+		child_ctr = inherit_event(sub, parent, parent_ctx,
+					    child, leader, child_ctx);
+		if (IS_ERR(child_ctr))
+			return PTR_ERR(child_ctr);
+	}
+	return 0;
 }
 
 static int
 inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		   struct perf_event_context *parent_ctx,
-		   struct task_struct *child,
+		   struct task_struct *child, int ctxn,
 		   int *inherited_all)
 {
 	int ret;
-	struct perf_event_context *child_ctx = child->perf_event_ctxp;
+	struct perf_event_context *child_ctx;
 
 	if (!event->attr.inherit) {
 		*inherited_all = 0;
 		return 0;
 	}
 
+       	child_ctx = child->perf_event_ctxp[ctxn];
 	if (!child_ctx) {
 		/*
 		 * This is executed from the parent task context, so
@@ -5588,14 +6123,11 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		 * child.
 		 */
 
-		child_ctx = kzalloc(sizeof(struct perf_event_context),
-				    GFP_KERNEL);
+		child_ctx = alloc_perf_context(event->pmu, child);
 		if (!child_ctx)
 			return -ENOMEM;
 
-		__perf_event_init_context(child_ctx, child);
-		child->perf_event_ctxp = child_ctx;
-		get_task_struct(child);
+		child->perf_event_ctxp[ctxn] = child_ctx;
 	}
 
 	ret = inherit_group(event, parent, parent_ctx,
@@ -5607,11 +6139,10 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 	return ret;
 }
 
-
 /*
  * Initialize the perf_event context in task_struct
  */
-int perf_event_init_task(struct task_struct *child)
+int perf_event_init_context(struct task_struct *child, int ctxn)
 {
 	struct perf_event_context *child_ctx, *parent_ctx;
 	struct perf_event_context *cloned_ctx;
@@ -5620,19 +6151,19 @@ int perf_event_init_task(struct task_struct *child)
 	int inherited_all = 1;
 	int ret = 0;
 
-	child->perf_event_ctxp = NULL;
+	child->perf_event_ctxp[ctxn] = NULL;
 
 	mutex_init(&child->perf_event_mutex);
 	INIT_LIST_HEAD(&child->perf_event_list);
 
-	if (likely(!parent->perf_event_ctxp))
+	if (likely(!parent->perf_event_ctxp[ctxn]))
 		return 0;
 
 	/*
 	 * If the parent's context is a clone, pin it so it won't get
 	 * swapped under us.
 	 */
-	parent_ctx = perf_pin_task_context(parent);
+	parent_ctx = perf_pin_task_context(parent, ctxn);
 
 	/*
 	 * No need to check if parent_ctx != NULL here; since we saw
@@ -5652,20 +6183,20 @@ int perf_event_init_task(struct task_struct *child)
 	 * the list, not manipulating it:
 	 */
 	list_for_each_entry(event, &parent_ctx->pinned_groups, group_entry) {
-		ret = inherit_task_group(event, parent, parent_ctx, child,
-					 &inherited_all);
+		ret = inherit_task_group(event, parent, parent_ctx,
+					 child, ctxn, &inherited_all);
 		if (ret)
 			break;
 	}
 
 	list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
-		ret = inherit_task_group(event, parent, parent_ctx, child,
-					 &inherited_all);
+		ret = inherit_task_group(event, parent, parent_ctx,
+					 child, ctxn, &inherited_all);
 		if (ret)
 			break;
 	}
 
-	child_ctx = child->perf_event_ctxp;
+	child_ctx = child->perf_event_ctxp[ctxn];
 
 	if (child_ctx && inherited_all) {
 		/*
@@ -5694,63 +6225,98 @@ int perf_event_init_task(struct task_struct *child)
 	return ret;
 }
 
+/*
+ * Initialize the perf_event context in task_struct
+ */
+int perf_event_init_task(struct task_struct *child)
+{
+	int ctxn, ret;
+
+	for_each_task_context_nr(ctxn) {
+		ret = perf_event_init_context(child, ctxn);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static void __init perf_event_init_all_cpus(void)
 {
+	struct swevent_htable *swhash;
 	int cpu;
-	struct perf_cpu_context *cpuctx;
 
 	for_each_possible_cpu(cpu) {
-		cpuctx = &per_cpu(perf_cpu_context, cpu);
-		mutex_init(&cpuctx->hlist_mutex);
-		__perf_event_init_context(&cpuctx->ctx, NULL);
+		swhash = &per_cpu(swevent_htable, cpu);
+		mutex_init(&swhash->hlist_mutex);
+		INIT_LIST_HEAD(&per_cpu(rotation_list, cpu));
 	}
 }
 
 static void __cpuinit perf_event_init_cpu(int cpu)
 {
-	struct perf_cpu_context *cpuctx;
-
-	cpuctx = &per_cpu(perf_cpu_context, cpu);
-
-	spin_lock(&perf_resource_lock);
-	cpuctx->max_pertask = perf_max_events - perf_reserved_percpu;
-	spin_unlock(&perf_resource_lock);
+	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
-	mutex_lock(&cpuctx->hlist_mutex);
-	if (cpuctx->hlist_refcount > 0) {
+	mutex_lock(&swhash->hlist_mutex);
+	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
-		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
-		WARN_ON_ONCE(!hlist);
-		rcu_assign_pointer(cpuctx->swevent_hlist, hlist);
+		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
+		WARN_ON(!hlist);
+		rcu_assign_pointer(swhash->swevent_hlist, hlist);
 	}
-	mutex_unlock(&cpuctx->hlist_mutex);
+	mutex_unlock(&swhash->hlist_mutex);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void __perf_event_exit_cpu(void *info)
+static void perf_pmu_rotate_stop(struct pmu *pmu)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_event_context *ctx = &cpuctx->ctx;
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+	WARN_ON(!irqs_disabled());
+
+	list_del_init(&cpuctx->rotation_list);
+}
+
+static void __perf_event_exit_context(void *__info)
+{
+	struct perf_event_context *ctx = __info;
 	struct perf_event *event, *tmp;
 
+	perf_pmu_rotate_stop(ctx->pmu);
+
 	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
 		__perf_event_remove_from_context(event);
 	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
 		__perf_event_remove_from_context(event);
 }
+
+static void perf_event_exit_cpu_context(int cpu)
+{
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+	int idx;
+
+	idx = srcu_read_lock(&pmus_srcu);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		ctx = &per_cpu_ptr(pmu->pmu_cpu_context, cpu)->ctx;
+
+		mutex_lock(&ctx->mutex);
+		smp_call_function_single(cpu, __perf_event_exit_context, ctx, 1);
+		mutex_unlock(&ctx->mutex);
+	}
+	srcu_read_unlock(&pmus_srcu, idx);
+}
+
 static void perf_event_exit_cpu(int cpu)
 {
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
-	struct perf_event_context *ctx = &cpuctx->ctx;
+	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
-	mutex_lock(&cpuctx->hlist_mutex);
-	swevent_hlist_release(cpuctx);
-	mutex_unlock(&cpuctx->hlist_mutex);
+	mutex_lock(&swhash->hlist_mutex);
+	swevent_hlist_release(swhash);
+	mutex_unlock(&swhash->hlist_mutex);
 
-	mutex_lock(&ctx->mutex);
-	smp_call_function_single(cpu, __perf_event_exit_cpu, NULL, 1);
-	mutex_unlock(&ctx->mutex);
+	perf_event_exit_cpu_context(cpu);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
@@ -5780,118 +6346,13 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 	return NOTIFY_OK;
 }
 
-/*
- * This has to have a higher priority than migration_notifier in sched.c.
- */
-static struct notifier_block __cpuinitdata perf_cpu_nb = {
-	.notifier_call		= perf_cpu_notify,
-	.priority		= 20,
-};
-
 void __init perf_event_init(void)
 {
 	perf_event_init_all_cpus();
-	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
-			(void *)(long)smp_processor_id());
-	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE,
-			(void *)(long)smp_processor_id());
-	register_cpu_notifier(&perf_cpu_nb);
-}
-
-static ssize_t perf_show_reserve_percpu(struct sysdev_class *class,
-					struct sysdev_class_attribute *attr,
-					char *buf)
-{
-	return sprintf(buf, "%d\n", perf_reserved_percpu);
-}
-
-static ssize_t
-perf_set_reserve_percpu(struct sysdev_class *class,
-			struct sysdev_class_attribute *attr,
-			const char *buf,
-			size_t count)
-{
-	struct perf_cpu_context *cpuctx;
-	unsigned long val;
-	int err, cpu, mpt;
-
-	err = strict_strtoul(buf, 10, &val);
-	if (err)
-		return err;
-	if (val > perf_max_events)
-		return -EINVAL;
-
-	spin_lock(&perf_resource_lock);
-	perf_reserved_percpu = val;
-	for_each_online_cpu(cpu) {
-		cpuctx = &per_cpu(perf_cpu_context, cpu);
-		raw_spin_lock_irq(&cpuctx->ctx.lock);
-		mpt = min(perf_max_events - cpuctx->ctx.nr_events,
-			  perf_max_events - perf_reserved_percpu);
-		cpuctx->max_pertask = mpt;
-		raw_spin_unlock_irq(&cpuctx->ctx.lock);
-	}
-	spin_unlock(&perf_resource_lock);
-
-	return count;
-}
-
-static ssize_t perf_show_overcommit(struct sysdev_class *class,
-				    struct sysdev_class_attribute *attr,
-				    char *buf)
-{
-	return sprintf(buf, "%d\n", perf_overcommit);
-}
-
-static ssize_t
-perf_set_overcommit(struct sysdev_class *class,
-		    struct sysdev_class_attribute *attr,
-		    const char *buf, size_t count)
-{
-	unsigned long val;
-	int err;
-
-	err = strict_strtoul(buf, 10, &val);
-	if (err)
-		return err;
-	if (val > 1)
-		return -EINVAL;
-
-	spin_lock(&perf_resource_lock);
-	perf_overcommit = val;
-	spin_unlock(&perf_resource_lock);
-
-	return count;
-}
-
-static SYSDEV_CLASS_ATTR(
-				reserve_percpu,
-				0644,
-				perf_show_reserve_percpu,
-				perf_set_reserve_percpu
-			);
-
-static SYSDEV_CLASS_ATTR(
-				overcommit,
-				0644,
-				perf_show_overcommit,
-				perf_set_overcommit
-			);
-
-static struct attribute *perfclass_attrs[] = {
-	&attr_reserve_percpu.attr,
-	&attr_overcommit.attr,
-	NULL
-};
-
-static struct attribute_group perfclass_attr_group = {
-	.attrs			= perfclass_attrs,
-	.name			= "perf_events",
-};
-
-static int __init perf_event_sysfs_init(void)
-{
-	return sysfs_create_group(&cpu_sysdev_class.kset.kobj,
-				  &perfclass_attr_group);
+	init_srcu_struct(&pmus_srcu);
+	perf_pmu_register(&perf_swevent);
+	perf_pmu_register(&perf_cpu_clock);
+	perf_pmu_register(&perf_task_clock);
+	perf_tp_register();
+	perf_cpu_notifier(perf_cpu_notify);
 }
-device_initcall(perf_event_sysfs_init);
diff --git a/kernel/sched.c b/kernel/sched.c
index df6579d9b4df..6334e1c8165b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -426,9 +426,7 @@ struct root_domain {
 	 */
 	cpumask_var_t rto_mask;
 	atomic_t rto_count;
-#ifdef CONFIG_SMP
 	struct cpupri cpupri;
-#endif
 };
 
 /*
@@ -437,7 +435,7 @@ struct root_domain {
  */
 static struct root_domain def_root_domain;
 
-#endif
+#endif /* CONFIG_SMP */
 
 /*
  * This is the main, per-CPU runqueue data structure.
@@ -723,7 +721,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 		size_t cnt, loff_t *ppos)
 {
 	char buf[64];
-	char *cmp = buf;
+	char *cmp;
 	int neg = 0;
 	int i;
 
@@ -734,6 +732,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 		return -EFAULT;
 
 	buf[cnt] = 0;
+	cmp = strstrip(buf);
 
 	if (strncmp(buf, "NO_", 3) == 0) {
 		neg = 1;
@@ -741,9 +740,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 	}
 
 	for (i = 0; sched_feat_names[i]; i++) {
-		int len = strlen(sched_feat_names[i]);
-
-		if (strncmp(cmp, sched_feat_names[i], len) == 0) {
+		if (strcmp(cmp, sched_feat_names[i]) == 0) {
 			if (neg)
 				sysctl_sched_features &= ~(1UL << i);
 			else
@@ -2852,14 +2849,14 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 */
 	arch_start_context_switch(prev);
 
-	if (likely(!mm)) {
+	if (!mm) {
 		next->active_mm = oldmm;
 		atomic_inc(&oldmm->mm_count);
 		enter_lazy_tlb(oldmm, next);
 	} else
 		switch_mm(oldmm, mm, next);
 
-	if (likely(!prev->mm)) {
+	if (!prev->mm) {
 		prev->active_mm = NULL;
 		rq->prev_mm = oldmm;
 	}
@@ -3584,7 +3581,7 @@ void scheduler_tick(void)
 	curr->sched_class->task_tick(rq, curr, 0);
 	raw_spin_unlock(&rq->lock);
 
-	perf_event_task_tick(curr);
+	perf_event_task_tick();
 
 #ifdef CONFIG_SMP
 	rq->idle_at_tick = idle_cpu(cpu);
@@ -4358,6 +4355,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	rq = task_rq_lock(p, &flags);
 
+	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
 	on_rq = p->se.on_rq;
@@ -6514,6 +6512,7 @@ struct s_data {
 	cpumask_var_t		nodemask;
 	cpumask_var_t		this_sibling_map;
 	cpumask_var_t		this_core_map;
+	cpumask_var_t		this_book_map;
 	cpumask_var_t		send_covered;
 	cpumask_var_t		tmpmask;
 	struct sched_group	**sched_group_nodes;
@@ -6525,6 +6524,7 @@ enum s_alloc {
 	sa_rootdomain,
 	sa_tmpmask,
 	sa_send_covered,
+	sa_this_book_map,
 	sa_this_core_map,
 	sa_this_sibling_map,
 	sa_nodemask,
@@ -6560,31 +6560,48 @@ cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
 #ifdef CONFIG_SCHED_MC
 static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
-#endif /* CONFIG_SCHED_MC */
 
-#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
 static int
 cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 		  struct sched_group **sg, struct cpumask *mask)
 {
 	int group;
-
+#ifdef CONFIG_SCHED_SMT
 	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
+#else
+	group = cpu;
+#endif
 	if (sg)
 		*sg = &per_cpu(sched_group_core, group).sg;
 	return group;
 }
-#elif defined(CONFIG_SCHED_MC)
+#endif /* CONFIG_SCHED_MC */
+
+/*
+ * book sched-domains:
+ */
+#ifdef CONFIG_SCHED_BOOK
+static DEFINE_PER_CPU(struct static_sched_domain, book_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_book);
+
 static int
-cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *unused)
+cpu_to_book_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *mask)
 {
+	int group = cpu;
+#ifdef CONFIG_SCHED_MC
+	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+	group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_SMT)
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
+	group = cpumask_first(mask);
+#endif
 	if (sg)
-		*sg = &per_cpu(sched_group_core, cpu).sg;
-	return cpu;
+		*sg = &per_cpu(sched_group_book, group).sg;
+	return group;
 }
-#endif
+#endif /* CONFIG_SCHED_BOOK */
 
 static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
@@ -6594,7 +6611,10 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
 		  struct sched_group **sg, struct cpumask *mask)
 {
 	int group;
-#ifdef CONFIG_SCHED_MC
+#ifdef CONFIG_SCHED_BOOK
+	cpumask_and(mask, cpu_book_mask(cpu), cpu_map);
+	group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_MC)
 	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
@@ -6855,6 +6875,9 @@ SD_INIT_FUNC(CPU)
 #ifdef CONFIG_SCHED_MC
  SD_INIT_FUNC(MC)
 #endif
+#ifdef CONFIG_SCHED_BOOK
+ SD_INIT_FUNC(BOOK)
+#endif
 
 static int default_relax_domain_level = -1;
 
@@ -6904,6 +6927,8 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 		free_cpumask_var(d->tmpmask); /* fall through */
 	case sa_send_covered:
 		free_cpumask_var(d->send_covered); /* fall through */
+	case sa_this_book_map:
+		free_cpumask_var(d->this_book_map); /* fall through */
 	case sa_this_core_map:
 		free_cpumask_var(d->this_core_map); /* fall through */
 	case sa_this_sibling_map:
@@ -6950,8 +6975,10 @@ static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
 		return sa_nodemask;
 	if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
 		return sa_this_sibling_map;
-	if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+	if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL))
 		return sa_this_core_map;
+	if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+		return sa_this_book_map;
 	if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
 		return sa_send_covered;
 	d->rd = alloc_rootdomain();
@@ -7009,6 +7036,23 @@ static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
 	return sd;
 }
 
+static struct sched_domain *__build_book_sched_domain(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+	struct sched_domain *parent, int i)
+{
+	struct sched_domain *sd = parent;
+#ifdef CONFIG_SCHED_BOOK
+	sd = &per_cpu(book_domains, i).sd;
+	SD_INIT(sd, BOOK);
+	set_domain_attribute(sd, attr);
+	cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i));
+	sd->parent = parent;
+	parent->child = sd;
+	cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask);
+#endif
+	return sd;
+}
+
 static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
 	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
 	struct sched_domain *parent, int i)
@@ -7066,6 +7110,15 @@ static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
 						d->send_covered, d->tmpmask);
 		break;
 #endif
+#ifdef CONFIG_SCHED_BOOK
+	case SD_LV_BOOK: /* set up book groups */
+		cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu));
+		if (cpu == cpumask_first(d->this_book_map))
+			init_sched_build_groups(d->this_book_map, cpu_map,
+						&cpu_to_book_group,
+						d->send_covered, d->tmpmask);
+		break;
+#endif
 	case SD_LV_CPU: /* set up physical groups */
 		cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
 		if (!cpumask_empty(d->nodemask))
@@ -7113,12 +7166,14 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 
 		sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
 		sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+		sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i);
 		sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
 		sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
 	}
 
 	for_each_cpu(i, cpu_map) {
 		build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+		build_sched_groups(&d, SD_LV_BOOK, cpu_map, i);
 		build_sched_groups(&d, SD_LV_MC, cpu_map, i);
 	}
 
@@ -7149,6 +7204,12 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		init_sched_groups_power(i, sd);
 	}
 #endif
+#ifdef CONFIG_SCHED_BOOK
+	for_each_cpu(i, cpu_map) {
+		sd = &per_cpu(book_domains, i).sd;
+		init_sched_groups_power(i, sd);
+	}
+#endif
 
 	for_each_cpu(i, cpu_map) {
 		sd = &per_cpu(phys_domains, i).sd;
@@ -7174,6 +7235,8 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		sd = &per_cpu(cpu_domains, i).sd;
 #elif defined(CONFIG_SCHED_MC)
 		sd = &per_cpu(core_domains, i).sd;
+#elif defined(CONFIG_SCHED_BOOK)
+		sd = &per_cpu(book_domains, i).sd;
 #else
 		sd = &per_cpu(phys_domains, i).sd;
 #endif
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index db3f674ca49d..623e9aceef8f 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3031,7 +3031,14 @@ redo:
 
 	if (!ld_moved) {
 		schedstat_inc(sd, lb_failed[idle]);
-		sd->nr_balance_failed++;
+		/*
+		 * Increment the failure counter only on periodic balance.
+		 * We do not want newidle balance, which can be very
+		 * frequent, pollute the failure counter causing
+		 * excessive cache_hot migrations and active balances.
+		 */
+		if (idle != CPU_NEWLY_IDLE)
+			sd->nr_balance_failed++;
 
 		if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
 					this_cpu)) {
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index d10c80ebb67a..baef30f08405 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -960,18 +960,19 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 	 * runqueue. Otherwise simply start this RT task
 	 * on its current runqueue.
 	 *
-	 * We want to avoid overloading runqueues. Even if
-	 * the RT task is of higher priority than the current RT task.
-	 * RT tasks behave differently than other tasks. If
-	 * one gets preempted, we try to push it off to another queue.
-	 * So trying to keep a preempting RT task on the same
-	 * cache hot CPU will force the running RT task to
-	 * a cold CPU. So we waste all the cache for the lower
-	 * RT task in hopes of saving some of a RT task
-	 * that is just being woken and probably will have
-	 * cold cache anyway.
+	 * We want to avoid overloading runqueues. If the woken
+	 * task is a higher priority, then it will stay on this CPU
+	 * and the lower prio task should be moved to another CPU.
+	 * Even though this will probably make the lower prio task
+	 * lose its cache, we do not want to bounce a higher task
+	 * around just because it gave up its CPU, perhaps for a
+	 * lock?
+	 *
+	 * For equal prio tasks, we just let the scheduler sort it out.
 	 */
 	if (unlikely(rt_task(rq->curr)) &&
+	    (rq->curr->rt.nr_cpus_allowed < 2 ||
+	     rq->curr->prio < p->prio) &&
 	    (p->rt.nr_cpus_allowed > 1)) {
 		int cpu = find_lowest_rq(p);
 
@@ -1491,7 +1492,10 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 	if (!task_running(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
 	    has_pushable_tasks(rq) &&
-	    p->rt.nr_cpus_allowed > 1)
+	    p->rt.nr_cpus_allowed > 1 &&
+	    rt_task(rq->curr) &&
+	    (rq->curr->rt.nr_cpus_allowed < 2 ||
+	     rq->curr->prio < p->prio))
 		push_rt_tasks(rq);
 }
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 07b4f1b1a73a..80f6e3bd1d2a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -67,7 +67,7 @@ char *softirq_to_name[NR_SOFTIRQS] = {
  * to the pending events, so lets the scheduler to balance
  * the softirq load for us.
  */
-void wakeup_softirqd(void)
+static void wakeup_softirqd(void)
 {
 	/* Interrupts are disabled: no need to stop preemption */
 	struct task_struct *tsk = __get_cpu_var(ksoftirqd);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index c63116863a80..d2321891538f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -149,10 +149,18 @@ static void ntp_update_offset(long offset)
 	time_reftime = get_seconds();
 
 	offset64    = offset;
-	freq_adj    = (offset64 * secs) <<
-			(NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant));
+	freq_adj    = ntp_update_offset_fll(offset64, secs);
 
-	freq_adj    += ntp_update_offset_fll(offset64, secs);
+	/*
+	 * Clamp update interval to reduce PLL gain with low
+	 * sampling rate (e.g. intermittent network connection)
+	 * to avoid instability.
+	 */
+	if (unlikely(secs > 1 << (SHIFT_PLL + 1 + time_constant)))
+		secs = 1 << (SHIFT_PLL + 1 + time_constant);
+
+	freq_adj    += (offset64 * secs) <<
+			(NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant));
 
 	freq_adj    = min(freq_adj + time_freq, MAXFREQ_SCALED);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index fa7ece649fe1..65fb077ea79c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -884,10 +884,8 @@ enum {
 	FTRACE_ENABLE_CALLS		= (1 << 0),
 	FTRACE_DISABLE_CALLS		= (1 << 1),
 	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
-	FTRACE_ENABLE_MCOUNT		= (1 << 3),
-	FTRACE_DISABLE_MCOUNT		= (1 << 4),
-	FTRACE_START_FUNC_RET		= (1 << 5),
-	FTRACE_STOP_FUNC_RET		= (1 << 6),
+	FTRACE_START_FUNC_RET		= (1 << 3),
+	FTRACE_STOP_FUNC_RET		= (1 << 4),
 };
 
 static int ftrace_filtered;
@@ -1226,8 +1224,6 @@ static void ftrace_shutdown(int command)
 
 static void ftrace_startup_sysctl(void)
 {
-	int command = FTRACE_ENABLE_MCOUNT;
-
 	if (unlikely(ftrace_disabled))
 		return;
 
@@ -1235,23 +1231,17 @@ static void ftrace_startup_sysctl(void)
 	saved_ftrace_func = NULL;
 	/* ftrace_start_up is true if we want ftrace running */
 	if (ftrace_start_up)
-		command |= FTRACE_ENABLE_CALLS;
-
-	ftrace_run_update_code(command);
+		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
 }
 
 static void ftrace_shutdown_sysctl(void)
 {
-	int command = FTRACE_DISABLE_MCOUNT;
-
 	if (unlikely(ftrace_disabled))
 		return;
 
 	/* ftrace_start_up is true if ftrace is running */
 	if (ftrace_start_up)
-		command |= FTRACE_DISABLE_CALLS;
-
-	ftrace_run_update_code(command);
+		ftrace_run_update_code(FTRACE_DISABLE_CALLS);
 }
 
 static cycle_t		ftrace_update_time;
@@ -1368,24 +1358,29 @@ enum {
 #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */
 
 struct ftrace_iterator {
-	struct ftrace_page	*pg;
-	int			hidx;
-	int			idx;
-	unsigned		flags;
-	struct trace_parser	parser;
+	loff_t				pos;
+	loff_t				func_pos;
+	struct ftrace_page		*pg;
+	struct dyn_ftrace		*func;
+	struct ftrace_func_probe	*probe;
+	struct trace_parser		parser;
+	int				hidx;
+	int				idx;
+	unsigned			flags;
 };
 
 static void *
-t_hash_next(struct seq_file *m, void *v, loff_t *pos)
+t_hash_next(struct seq_file *m, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
-	struct hlist_node *hnd = v;
+	struct hlist_node *hnd = NULL;
 	struct hlist_head *hhd;
 
-	WARN_ON(!(iter->flags & FTRACE_ITER_HASH));
-
 	(*pos)++;
+	iter->pos = *pos;
 
+	if (iter->probe)
+		hnd = &iter->probe->node;
  retry:
 	if (iter->hidx >= FTRACE_FUNC_HASHSIZE)
 		return NULL;
@@ -1408,7 +1403,12 @@ t_hash_next(struct seq_file *m, void *v, loff_t *pos)
 		}
 	}
 
-	return hnd;
+	if (WARN_ON_ONCE(!hnd))
+		return NULL;
+
+	iter->probe = hlist_entry(hnd, struct ftrace_func_probe, node);
+
+	return iter;
 }
 
 static void *t_hash_start(struct seq_file *m, loff_t *pos)
@@ -1417,26 +1417,32 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos)
 	void *p = NULL;
 	loff_t l;
 
-	if (!(iter->flags & FTRACE_ITER_HASH))
-		*pos = 0;
-
-	iter->flags |= FTRACE_ITER_HASH;
+	if (iter->func_pos > *pos)
+		return NULL;
 
 	iter->hidx = 0;
-	for (l = 0; l <= *pos; ) {
-		p = t_hash_next(m, p, &l);
+	for (l = 0; l <= (*pos - iter->func_pos); ) {
+		p = t_hash_next(m, &l);
 		if (!p)
 			break;
 	}
-	return p;
+	if (!p)
+		return NULL;
+
+	/* Only set this if we have an item */
+	iter->flags |= FTRACE_ITER_HASH;
+
+	return iter;
 }
 
-static int t_hash_show(struct seq_file *m, void *v)
+static int
+t_hash_show(struct seq_file *m, struct ftrace_iterator *iter)
 {
 	struct ftrace_func_probe *rec;
-	struct hlist_node *hnd = v;
 
-	rec = hlist_entry(hnd, struct ftrace_func_probe, node);
+	rec = iter->probe;
+	if (WARN_ON_ONCE(!rec))
+		return -EIO;
 
 	if (rec->ops->print)
 		return rec->ops->print(m, rec->ip, rec->ops, rec->data);
@@ -1457,12 +1463,13 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 	struct dyn_ftrace *rec = NULL;
 
 	if (iter->flags & FTRACE_ITER_HASH)
-		return t_hash_next(m, v, pos);
+		return t_hash_next(m, pos);
 
 	(*pos)++;
+	iter->pos = *pos;
 
 	if (iter->flags & FTRACE_ITER_PRINTALL)
-		return NULL;
+		return t_hash_start(m, pos);
 
  retry:
 	if (iter->idx >= iter->pg->index) {
@@ -1491,7 +1498,20 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		}
 	}
 
-	return rec;
+	if (!rec)
+		return t_hash_start(m, pos);
+
+	iter->func_pos = *pos;
+	iter->func = rec;
+
+	return iter;
+}
+
+static void reset_iter_read(struct ftrace_iterator *iter)
+{
+	iter->pos = 0;
+	iter->func_pos = 0;
+	iter->flags &= ~(FTRACE_ITER_PRINTALL & FTRACE_ITER_HASH);
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
@@ -1502,6 +1522,12 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 
 	mutex_lock(&ftrace_lock);
 	/*
+	 * If an lseek was done, then reset and start from beginning.
+	 */
+	if (*pos < iter->pos)
+		reset_iter_read(iter);
+
+	/*
 	 * For set_ftrace_filter reading, if we have the filter
 	 * off, we can short cut and just print out that all
 	 * functions are enabled.
@@ -1518,6 +1544,11 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 	if (iter->flags & FTRACE_ITER_HASH)
 		return t_hash_start(m, pos);
 
+	/*
+	 * Unfortunately, we need to restart at ftrace_pages_start
+	 * every time we let go of the ftrace_mutex. This is because
+	 * those pointers can change without the lock.
+	 */
 	iter->pg = ftrace_pages_start;
 	iter->idx = 0;
 	for (l = 0; l <= *pos; ) {
@@ -1526,10 +1557,14 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 			break;
 	}
 
-	if (!p && iter->flags & FTRACE_ITER_FILTER)
-		return t_hash_start(m, pos);
+	if (!p) {
+		if (iter->flags & FTRACE_ITER_FILTER)
+			return t_hash_start(m, pos);
 
-	return p;
+		return NULL;
+	}
+
+	return iter;
 }
 
 static void t_stop(struct seq_file *m, void *p)
@@ -1540,16 +1575,18 @@ static void t_stop(struct seq_file *m, void *p)
 static int t_show(struct seq_file *m, void *v)
 {
 	struct ftrace_iterator *iter = m->private;
-	struct dyn_ftrace *rec = v;
+	struct dyn_ftrace *rec;
 
 	if (iter->flags & FTRACE_ITER_HASH)
-		return t_hash_show(m, v);
+		return t_hash_show(m, iter);
 
 	if (iter->flags & FTRACE_ITER_PRINTALL) {
 		seq_printf(m, "#### all functions enabled ####\n");
 		return 0;
 	}
 
+	rec = iter->func;
+
 	if (!rec)
 		return 0;
 
@@ -2418,7 +2455,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = no_llseek,
+	.llseek = ftrace_regex_lseek,
 	.release = ftrace_filter_release,
 };
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 492197e2f86c..4e2f03410377 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2606,6 +2606,19 @@ void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
 
+/*
+ * The total entries in the ring buffer is the running counter
+ * of entries entered into the ring buffer, minus the sum of
+ * the entries read from the ring buffer and the number of
+ * entries that were overwritten.
+ */
+static inline unsigned long
+rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	return local_read(&cpu_buffer->entries) -
+		(local_read(&cpu_buffer->overrun) + cpu_buffer->read);
+}
+
 /**
  * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
  * @buffer: The ring buffer
@@ -2614,16 +2627,13 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned long ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = (local_read(&cpu_buffer->entries) - local_read(&cpu_buffer->overrun))
-		- cpu_buffer->read;
 
-	return ret;
+	return rb_num_of_entries(cpu_buffer);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
 
@@ -2684,8 +2694,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 	/* if you care about this being correct, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		entries += (local_read(&cpu_buffer->entries) -
-			    local_read(&cpu_buffer->overrun)) - cpu_buffer->read;
+		entries += rb_num_of_entries(cpu_buffer);
 	}
 
 	return entries;
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 31cc4cb0dbf2..39c059ca670e 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -9,7 +9,7 @@
 #include <linux/kprobes.h>
 #include "trace.h"
 
-static char *perf_trace_buf[4];
+static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS];
 
 /*
  * Force it to be aligned to unsigned long to avoid misaligned accesses
@@ -24,7 +24,7 @@ static int	total_ref_count;
 static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
-	struct hlist_head *list;
+	struct hlist_head __percpu *list;
 	int ret = -ENOMEM;
 	int cpu;
 
@@ -42,11 +42,11 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 	tp_event->perf_events = list;
 
 	if (!total_ref_count) {
-		char *buf;
+		char __percpu *buf;
 		int i;
 
-		for (i = 0; i < 4; i++) {
-			buf = (char *)alloc_percpu(perf_trace_t);
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+			buf = (char __percpu *)alloc_percpu(perf_trace_t);
 			if (!buf)
 				goto fail;
 
@@ -65,7 +65,7 @@ fail:
 	if (!total_ref_count) {
 		int i;
 
-		for (i = 0; i < 4; i++) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 			free_percpu(perf_trace_buf[i]);
 			perf_trace_buf[i] = NULL;
 		}
@@ -101,22 +101,26 @@ int perf_trace_init(struct perf_event *p_event)
 	return ret;
 }
 
-int perf_trace_enable(struct perf_event *p_event)
+int perf_trace_add(struct perf_event *p_event, int flags)
 {
 	struct ftrace_event_call *tp_event = p_event->tp_event;
+	struct hlist_head __percpu *pcpu_list;
 	struct hlist_head *list;
 
-	list = tp_event->perf_events;
-	if (WARN_ON_ONCE(!list))
+	pcpu_list = tp_event->perf_events;
+	if (WARN_ON_ONCE(!pcpu_list))
 		return -EINVAL;
 
-	list = this_cpu_ptr(list);
+	if (!(flags & PERF_EF_START))
+		p_event->hw.state = PERF_HES_STOPPED;
+
+	list = this_cpu_ptr(pcpu_list);
 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
 	return 0;
 }
 
-void perf_trace_disable(struct perf_event *p_event)
+void perf_trace_del(struct perf_event *p_event, int flags)
 {
 	hlist_del_rcu(&p_event->hlist_entry);
 }
@@ -142,7 +146,7 @@ void perf_trace_destroy(struct perf_event *p_event)
 	tp_event->perf_events = NULL;
 
 	if (!--total_ref_count) {
-		for (i = 0; i < 4; i++) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 			free_percpu(perf_trace_buf[i]);
 			perf_trace_buf[i] = NULL;
 		}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 4c758f146328..398c0e8b332c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -600,21 +600,29 @@ out:
 
 enum {
 	FORMAT_HEADER		= 1,
-	FORMAT_PRINTFMT		= 2,
+	FORMAT_FIELD_SEPERATOR	= 2,
+	FORMAT_PRINTFMT		= 3,
 };
 
 static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct ftrace_event_call *call = m->private;
 	struct ftrace_event_field *field;
-	struct list_head *head;
+	struct list_head *common_head = &ftrace_common_fields;
+	struct list_head *head = trace_get_fields(call);
 
 	(*pos)++;
 
 	switch ((unsigned long)v) {
 	case FORMAT_HEADER:
-		head = &ftrace_common_fields;
+		if (unlikely(list_empty(common_head)))
+			return NULL;
+
+		field = list_entry(common_head->prev,
+				   struct ftrace_event_field, link);
+		return field;
 
+	case FORMAT_FIELD_SEPERATOR:
 		if (unlikely(list_empty(head)))
 			return NULL;
 
@@ -626,31 +634,10 @@ static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 		return NULL;
 	}
 
-	head = trace_get_fields(call);
-
-	/*
-	 * To separate common fields from event fields, the
-	 * LSB is set on the first event field. Clear it in case.
-	 */
-	v = (void *)((unsigned long)v & ~1L);
-
 	field = v;
-	/*
-	 * If this is a common field, and at the end of the list, then
-	 * continue with main list.
-	 */
-	if (field->link.prev == &ftrace_common_fields) {
-		if (unlikely(list_empty(head)))
-			return NULL;
-		field = list_entry(head->prev, struct ftrace_event_field, link);
-		/* Set the LSB to notify f_show to print an extra newline */
-		field = (struct ftrace_event_field *)
-			((unsigned long)field | 1);
-		return field;
-	}
-
-	/* If we are done tell f_show to print the format */
-	if (field->link.prev == head)
+	if (field->link.prev == common_head)
+		return (void *)FORMAT_FIELD_SEPERATOR;
+	else if (field->link.prev == head)
 		return (void *)FORMAT_PRINTFMT;
 
 	field = list_entry(field->link.prev, struct ftrace_event_field, link);
@@ -688,22 +675,16 @@ static int f_show(struct seq_file *m, void *v)
 		seq_printf(m, "format:\n");
 		return 0;
 
+	case FORMAT_FIELD_SEPERATOR:
+		seq_putc(m, '\n');
+		return 0;
+
 	case FORMAT_PRINTFMT:
 		seq_printf(m, "\nprint fmt: %s\n",
 			   call->print_fmt);
 		return 0;
 	}
 
-	/*
-	 * To separate common fields from event fields, the
-	 * LSB is set on the first event field. Clear it and
-	 * print a newline if it is set.
-	 */
-	if ((unsigned long)v & 1) {
-		seq_putc(m, '\n');
-		v = (void *)((unsigned long)v & ~1L);
-	}
-
 	field = v;
 
 	/*
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 6f233698518e..02c708ae0d42 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -15,15 +15,19 @@
 #include "trace.h"
 #include "trace_output.h"
 
+/* When set, irq functions will be ignored */
+static int ftrace_graph_skip_irqs;
+
 struct fgraph_cpu_data {
 	pid_t		last_pid;
 	int		depth;
+	int		depth_irq;
 	int		ignore;
 	unsigned long	enter_funcs[FTRACE_RETFUNC_DEPTH];
 };
 
 struct fgraph_data {
-	struct fgraph_cpu_data		*cpu_data;
+	struct fgraph_cpu_data __percpu *cpu_data;
 
 	/* Place to preserve last processed entry. */
 	struct ftrace_graph_ent_entry	ent;
@@ -41,6 +45,7 @@ struct fgraph_data {
 #define TRACE_GRAPH_PRINT_PROC		0x8
 #define TRACE_GRAPH_PRINT_DURATION	0x10
 #define TRACE_GRAPH_PRINT_ABS_TIME	0x20
+#define TRACE_GRAPH_PRINT_IRQS		0x40
 
 static struct tracer_opt trace_opts[] = {
 	/* Display overruns? (for self-debug purpose) */
@@ -55,13 +60,15 @@ static struct tracer_opt trace_opts[] = {
 	{ TRACER_OPT(funcgraph-duration, TRACE_GRAPH_PRINT_DURATION) },
 	/* Display absolute time of an entry */
 	{ TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) },
+	/* Display interrupts */
+	{ TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
 	{ } /* Empty entry */
 };
 
 static struct tracer_flags tracer_flags = {
 	/* Don't display overruns and proc by default */
 	.val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD |
-	       TRACE_GRAPH_PRINT_DURATION,
+	       TRACE_GRAPH_PRINT_DURATION | TRACE_GRAPH_PRINT_IRQS,
 	.opts = trace_opts
 };
 
@@ -204,6 +211,14 @@ int __trace_graph_entry(struct trace_array *tr,
 	return 1;
 }
 
+static inline int ftrace_graph_ignore_irqs(void)
+{
+	if (!ftrace_graph_skip_irqs)
+		return 0;
+
+	return in_irq();
+}
+
 int trace_graph_entry(struct ftrace_graph_ent *trace)
 {
 	struct trace_array *tr = graph_array;
@@ -218,7 +233,8 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 		return 0;
 
 	/* trace it when it is-nested-in or is a function enabled. */
-	if (!(trace->depth || ftrace_graph_addr(trace->func)))
+	if (!(trace->depth || ftrace_graph_addr(trace->func)) ||
+	      ftrace_graph_ignore_irqs())
 		return 0;
 
 	local_irq_save(flags);
@@ -855,6 +871,92 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 	return 0;
 }
 
+/*
+ * Entry check for irq code
+ *
+ * returns 1 if
+ *  - we are inside irq code
+ *  - we just extered irq code
+ *
+ * retunns 0 if
+ *  - funcgraph-interrupts option is set
+ *  - we are not inside irq code
+ */
+static int
+check_irq_entry(struct trace_iterator *iter, u32 flags,
+		unsigned long addr, int depth)
+{
+	int cpu = iter->cpu;
+	struct fgraph_data *data = iter->private;
+	int *depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
+	if (flags & TRACE_GRAPH_PRINT_IRQS)
+		return 0;
+
+	/*
+	 * We are inside the irq code
+	 */
+	if (*depth_irq >= 0)
+		return 1;
+
+	if ((addr < (unsigned long)__irqentry_text_start) ||
+	    (addr >= (unsigned long)__irqentry_text_end))
+		return 0;
+
+	/*
+	 * We are entering irq code.
+	 */
+	*depth_irq = depth;
+	return 1;
+}
+
+/*
+ * Return check for irq code
+ *
+ * returns 1 if
+ *  - we are inside irq code
+ *  - we just left irq code
+ *
+ * returns 0 if
+ *  - funcgraph-interrupts option is set
+ *  - we are not inside irq code
+ */
+static int
+check_irq_return(struct trace_iterator *iter, u32 flags, int depth)
+{
+	int cpu = iter->cpu;
+	struct fgraph_data *data = iter->private;
+	int *depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
+	if (flags & TRACE_GRAPH_PRINT_IRQS)
+		return 0;
+
+	/*
+	 * We are not inside the irq code.
+	 */
+	if (*depth_irq == -1)
+		return 0;
+
+	/*
+	 * We are inside the irq code, and this is returning entry.
+	 * Let's not trace it and clear the entry depth, since
+	 * we are out of irq code.
+	 *
+	 * This condition ensures that we 'leave the irq code' once
+	 * we are out of the entry depth. Thus protecting us from
+	 * the RETURN entry loss.
+	 */
+	if (*depth_irq >= depth) {
+		*depth_irq = -1;
+		return 1;
+	}
+
+	/*
+	 * We are inside the irq code, and this is not the entry.
+	 */
+	return 1;
+}
+
 static enum print_line_t
 print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
 			struct trace_iterator *iter, u32 flags)
@@ -865,6 +967,9 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
 	static enum print_line_t ret;
 	int cpu = iter->cpu;
 
+	if (check_irq_entry(iter, flags, call->func, call->depth))
+		return TRACE_TYPE_HANDLED;
+
 	if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func, flags))
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -902,6 +1007,9 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 	int ret;
 	int i;
 
+	if (check_irq_return(iter, flags, trace->depth))
+		return TRACE_TYPE_HANDLED;
+
 	if (data) {
 		struct fgraph_cpu_data *cpu_data;
 		int cpu = iter->cpu;
@@ -1210,9 +1318,12 @@ void graph_trace_open(struct trace_iterator *iter)
 		pid_t *pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
 		int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
 		int *ignore = &(per_cpu_ptr(data->cpu_data, cpu)->ignore);
+		int *depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
 		*pid = -1;
 		*depth = 0;
 		*ignore = 0;
+		*depth_irq = -1;
 	}
 
 	iter->private = data;
@@ -1235,6 +1346,14 @@ void graph_trace_close(struct trace_iterator *iter)
 	}
 }
 
+static int func_graph_set_flag(u32 old_flags, u32 bit, int set)
+{
+	if (bit == TRACE_GRAPH_PRINT_IRQS)
+		ftrace_graph_skip_irqs = !set;
+
+	return 0;
+}
+
 static struct trace_event_functions graph_functions = {
 	.trace		= print_graph_function_event,
 };
@@ -1261,6 +1380,7 @@ static struct tracer graph_trace __read_mostly = {
 	.print_line	= print_graph_function,
 	.print_header	= print_graph_headers,
 	.flags		= &tracer_flags,
+	.set_flag	= func_graph_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_function_graph,
 #endif
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index a7cc3793baf6..209b379a4721 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -263,6 +263,11 @@ int __init trace_workqueue_early_init(void)
 {
 	int ret, cpu;
 
+	for_each_possible_cpu(cpu) {
+		spin_lock_init(&workqueue_cpu_stat(cpu)->lock);
+		INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list);
+	}
+
 	ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
 	if (ret)
 		goto out;
@@ -279,11 +284,6 @@ int __init trace_workqueue_early_init(void)
 	if (ret)
 		goto no_creation;
 
-	for_each_possible_cpu(cpu) {
-		spin_lock_init(&workqueue_cpu_stat(cpu)->lock);
-		INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list);
-	}
-
 	return 0;
 
 no_creation:
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index c77f3eceea25..d6073a50a6ca 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/jump_label.h>
 
 extern struct tracepoint __start___tracepoints[];
 extern struct tracepoint __stop___tracepoints[];
@@ -263,7 +264,13 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 	 * is used.
 	 */
 	rcu_assign_pointer(elem->funcs, (*entry)->funcs);
-	elem->state = active;
+	if (!elem->state && active) {
+		enable_jump_label(&elem->state);
+		elem->state = active;
+	} else if (elem->state && !active) {
+		disable_jump_label(&elem->state);
+		elem->state = active;
+	}
 }
 
 /*
@@ -277,7 +284,10 @@ static void disable_tracepoint(struct tracepoint *elem)
 	if (elem->unregfunc && elem->state)
 		elem->unregfunc();
 
-	elem->state = 0;
+	if (elem->state) {
+		disable_jump_label(&elem->state);
+		elem->state = 0;
+	}
 	rcu_assign_pointer(elem->funcs, NULL);
 }
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 7f9c3c52ecc1..bafba687a6d8 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -43,7 +43,6 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
 
-static int __read_mostly did_panic;
 static int __initdata no_watchdog;
 
 
@@ -187,18 +186,6 @@ static int is_softlockup(unsigned long touch_ts)
 	return 0;
 }
 
-static int
-watchdog_panic(struct notifier_block *this, unsigned long event, void *ptr)
-{
-	did_panic = 1;
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block panic_block = {
-	.notifier_call = watchdog_panic,
-};
-
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static struct perf_event_attr wd_hw_attr = {
 	.type		= PERF_TYPE_HARDWARE,
@@ -209,7 +196,7 @@ static struct perf_event_attr wd_hw_attr = {
 };
 
 /* Callback function for perf event subsystem */
-void watchdog_overflow_callback(struct perf_event *event, int nmi,
+static void watchdog_overflow_callback(struct perf_event *event, int nmi,
 		 struct perf_sample_data *data,
 		 struct pt_regs *regs)
 {
@@ -371,14 +358,14 @@ static int watchdog_nmi_enable(int cpu)
 	/* Try to register using hardware perf events */
 	wd_attr = &wd_hw_attr;
 	wd_attr->sample_period = hw_nmi_get_sample_period();
-	event = perf_event_create_kernel_counter(wd_attr, cpu, -1, watchdog_overflow_callback);
+	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback);
 	if (!IS_ERR(event)) {
 		printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");
 		goto out_save;
 	}
 
 	printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event);
-	return -1;
+	return PTR_ERR(event);
 
 	/* success path */
 out_save:
@@ -422,17 +409,19 @@ static int watchdog_prepare_cpu(int cpu)
 static int watchdog_enable(int cpu)
 {
 	struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
+	int err;
 
 	/* enable the perf event */
-	if (watchdog_nmi_enable(cpu) != 0)
-		return -1;
+	err = watchdog_nmi_enable(cpu);
+	if (err)
+		return err;
 
 	/* create the watchdog thread */
 	if (!p) {
 		p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu);
 		if (IS_ERR(p)) {
 			printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu);
-			return -1;
+			return PTR_ERR(p);
 		}
 		kthread_bind(p, cpu);
 		per_cpu(watchdog_touch_ts, cpu) = 0;
@@ -484,6 +473,9 @@ static void watchdog_disable_all_cpus(void)
 {
 	int cpu;
 
+	if (no_watchdog)
+		return;
+
 	for_each_online_cpu(cpu)
 		watchdog_disable(cpu);
 
@@ -526,17 +518,16 @@ static int __cpuinit
 cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
 	int hotcpu = (unsigned long)hcpu;
+	int err = 0;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		if (watchdog_prepare_cpu(hotcpu))
-			return NOTIFY_BAD;
+		err = watchdog_prepare_cpu(hotcpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		if (watchdog_enable(hotcpu))
-			return NOTIFY_BAD;
+		err = watchdog_enable(hotcpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
@@ -549,7 +540,7 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 #endif /* CONFIG_HOTPLUG_CPU */
 	}
-	return NOTIFY_OK;
+	return notifier_from_errno(err);
 }
 
 static struct notifier_block __cpuinitdata cpu_nfb = {
@@ -565,13 +556,11 @@ static int __init spawn_watchdog_task(void)
 		return 0;
 
 	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
-	WARN_ON(err == NOTIFY_BAD);
+	WARN_ON(notifier_to_errno(err));
 
 	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
 	register_cpu_notifier(&cpu_nfb);
 
-	atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
-
 	return 0;
 }
 early_initcall(spawn_watchdog_task);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9ecceaddcef9..c5bb71f7e36c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -482,6 +482,7 @@ config PROVE_LOCKING
 	select DEBUG_SPINLOCK
 	select DEBUG_MUTEXES
 	select DEBUG_LOCK_ALLOC
+	select TRACE_IRQFLAGS
 	default n
 	help
 	 This feature enables the kernel to prove that all locking
@@ -596,11 +597,10 @@ config DEBUG_LOCKDEP
 	  of more runtime overhead.
 
 config TRACE_IRQFLAGS
-	depends on DEBUG_KERNEL
 	bool
-	default y
-	depends on TRACE_IRQFLAGS_SUPPORT
-	depends on PROVE_LOCKING
+	help
+	  Enables hooks to interrupt enabling and disabling for
+	  either tracing or lock debugging.
 
 config DEBUG_SPINLOCK_SLEEP
 	bool "Spinlock debugging: sleep-inside-spinlock checking"
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 02afc2533728..e925c7b960f1 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -26,19 +26,11 @@
 #include <linux/dynamic_debug.h>
 #include <linux/debugfs.h>
 #include <linux/slab.h>
+#include <linux/jump_label.h>
 
 extern struct _ddebug __start___verbose[];
 extern struct _ddebug __stop___verbose[];
 
-/* dynamic_debug_enabled, and dynamic_debug_enabled2 are bitmasks in which
- * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They
- * use independent hash functions, to reduce the chance of false positives.
- */
-long long dynamic_debug_enabled;
-EXPORT_SYMBOL_GPL(dynamic_debug_enabled);
-long long dynamic_debug_enabled2;
-EXPORT_SYMBOL_GPL(dynamic_debug_enabled2);
-
 struct ddebug_table {
 	struct list_head link;
 	char *mod_name;
@@ -88,26 +80,6 @@ static char *ddebug_describe_flags(struct _ddebug *dp, char *buf,
 }
 
 /*
- * must be called with ddebug_lock held
- */
-
-static int disabled_hash(char hash, bool first_table)
-{
-	struct ddebug_table *dt;
-	char table_hash_value;
-
-	list_for_each_entry(dt, &ddebug_tables, link) {
-		if (first_table)
-			table_hash_value = dt->ddebugs->primary_hash;
-		else
-			table_hash_value = dt->ddebugs->secondary_hash;
-		if (dt->num_enabled && (hash == table_hash_value))
-			return 0;
-	}
-	return 1;
-}
-
-/*
  * Search the tables for _ddebug's which match the given
  * `query' and apply the `flags' and `mask' to them.  Tells
  * the user which ddebug's were changed, or whether none
@@ -170,17 +142,9 @@ static void ddebug_change(const struct ddebug_query *query,
 				dt->num_enabled++;
 			dp->flags = newflags;
 			if (newflags) {
-				dynamic_debug_enabled |=
-						(1LL << dp->primary_hash);
-				dynamic_debug_enabled2 |=
-						(1LL << dp->secondary_hash);
+				enable_jump_label(&dp->enabled);
 			} else {
-				if (disabled_hash(dp->primary_hash, true))
-					dynamic_debug_enabled &=
-						~(1LL << dp->primary_hash);
-				if (disabled_hash(dp->secondary_hash, false))
-					dynamic_debug_enabled2 &=
-						~(1LL << dp->secondary_hash);
+				disable_jump_label(&dp->enabled);
 			}
 			if (verbose)
 				printk(KERN_INFO
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 142c84a54993..13b0caa9793c 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/kmemleak.h>
 #include <linux/range.h>
+#include <linux/memblock.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
@@ -434,7 +435,8 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 			      unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(physaddr, physaddr + size);
+	kmemleak_free_part(__va(physaddr), size);
+	memblock_x86_free_range(physaddr, physaddr + size);
 #else
 	unsigned long start, end;
 
@@ -459,7 +461,8 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(addr, addr + size);
+	kmemleak_free_part(__va(addr), size);
+	memblock_x86_free_range(addr, addr + size);
 #else
 	unsigned long start, end;
 
@@ -526,6 +529,12 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size,
 }
 
 #ifndef CONFIG_NO_BOOTMEM
+int __weak __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
+				   int flags)
+{
+	return reserve_bootmem(phys, len, flags);
+}
+
 static unsigned long __init align_idx(struct bootmem_data *bdata,
 				      unsigned long idx, unsigned long step)
 {
diff --git a/mm/memblock.c b/mm/memblock.c
index 43840b305ecb..d5d63ac1fd83 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -11,237 +11,418 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
+#include <linux/poison.h>
+#include <linux/pfn.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 #include <linux/memblock.h>
 
-#define MEMBLOCK_ALLOC_ANYWHERE	0
+struct memblock memblock __initdata_memblock;
 
-struct memblock memblock;
+int memblock_debug __initdata_memblock;
+int memblock_can_resize __initdata_memblock;
+static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock;
+static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock;
 
-static int memblock_debug;
+/* inline so we don't get a warning when pr_debug is compiled out */
+static inline const char *memblock_type_name(struct memblock_type *type)
+{
+	if (type == &memblock.memory)
+		return "memory";
+	else if (type == &memblock.reserved)
+		return "reserved";
+	else
+		return "unknown";
+}
 
-static int __init early_memblock(char *p)
+/*
+ * Address comparison utilities
+ */
+
+static phys_addr_t __init_memblock memblock_align_down(phys_addr_t addr, phys_addr_t size)
 {
-	if (p && strstr(p, "debug"))
-		memblock_debug = 1;
+	return addr & ~(size - 1);
+}
+
+static phys_addr_t __init_memblock memblock_align_up(phys_addr_t addr, phys_addr_t size)
+{
+	return (addr + (size - 1)) & ~(size - 1);
+}
+
+static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
+				       phys_addr_t base2, phys_addr_t size2)
+{
+	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
+}
+
+static long __init_memblock memblock_addrs_adjacent(phys_addr_t base1, phys_addr_t size1,
+			       phys_addr_t base2, phys_addr_t size2)
+{
+	if (base2 == base1 + size1)
+		return 1;
+	else if (base1 == base2 + size2)
+		return -1;
+
 	return 0;
 }
-early_param("memblock", early_memblock);
 
-static void memblock_dump(struct memblock_region *region, char *name)
+static long __init_memblock memblock_regions_adjacent(struct memblock_type *type,
+				 unsigned long r1, unsigned long r2)
 {
-	unsigned long long base, size;
-	int i;
+	phys_addr_t base1 = type->regions[r1].base;
+	phys_addr_t size1 = type->regions[r1].size;
+	phys_addr_t base2 = type->regions[r2].base;
+	phys_addr_t size2 = type->regions[r2].size;
 
-	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
+	return memblock_addrs_adjacent(base1, size1, base2, size2);
+}
 
-	for (i = 0; i < region->cnt; i++) {
-		base = region->region[i].base;
-		size = region->region[i].size;
+long __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
+{
+	unsigned long i;
 
-		pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
-		    name, i, base, base + size - 1, size);
+	for (i = 0; i < type->cnt; i++) {
+		phys_addr_t rgnbase = type->regions[i].base;
+		phys_addr_t rgnsize = type->regions[i].size;
+		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
+			break;
 	}
+
+	return (i < type->cnt) ? i : -1;
 }
 
-void memblock_dump_all(void)
+/*
+ * Find, allocate, deallocate or reserve unreserved regions. All allocations
+ * are top-down.
+ */
+
+static phys_addr_t __init memblock_find_region(phys_addr_t start, phys_addr_t end,
+					  phys_addr_t size, phys_addr_t align)
 {
-	if (!memblock_debug)
-		return;
+	phys_addr_t base, res_base;
+	long j;
 
-	pr_info("MEMBLOCK configuration:\n");
-	pr_info(" rmo_size    = 0x%llx\n", (unsigned long long)memblock.rmo_size);
-	pr_info(" memory.size = 0x%llx\n", (unsigned long long)memblock.memory.size);
+	/* Prevent allocations returning 0 as it's also used to
+	 * indicate an allocation failure
+	 */
+	if (start == 0)
+		start = PAGE_SIZE;
 
-	memblock_dump(&memblock.memory, "memory");
-	memblock_dump(&memblock.reserved, "reserved");
+	base = memblock_align_down((end - size), align);
+	while (start <= base) {
+		j = memblock_overlaps_region(&memblock.reserved, base, size);
+		if (j < 0)
+			return base;
+		res_base = memblock.reserved.regions[j].base;
+		if (res_base < size)
+			break;
+		base = memblock_align_down(res_base - size, align);
+	}
+
+	return MEMBLOCK_ERROR;
 }
 
-static unsigned long memblock_addrs_overlap(u64 base1, u64 size1, u64 base2,
-					u64 size2)
+static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size,
+			phys_addr_t align, phys_addr_t start, phys_addr_t end)
 {
-	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
+	long i;
+
+	BUG_ON(0 == size);
+
+	size = memblock_align_up(size, align);
+
+	/* Pump up max_addr */
+	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
+		end = memblock.current_limit;
+
+	/* We do a top-down search, this tends to limit memory
+	 * fragmentation by keeping early boot allocs near the
+	 * top of memory
+	 */
+	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
+		phys_addr_t memblockbase = memblock.memory.regions[i].base;
+		phys_addr_t memblocksize = memblock.memory.regions[i].size;
+		phys_addr_t bottom, top, found;
+
+		if (memblocksize < size)
+			continue;
+		if ((memblockbase + memblocksize) <= start)
+			break;
+		bottom = max(memblockbase, start);
+		top = min(memblockbase + memblocksize, end);
+		if (bottom >= top)
+			continue;
+		found = memblock_find_region(bottom, top, size, align);
+		if (found != MEMBLOCK_ERROR)
+			return found;
+	}
+	return MEMBLOCK_ERROR;
 }
 
-static long memblock_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2)
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+u64 __init_memblock memblock_find_in_range(u64 start, u64 end, u64 size, u64 align)
 {
-	if (base2 == base1 + size1)
-		return 1;
-	else if (base1 == base2 + size2)
-		return -1;
+	return memblock_find_base(size, align, start, end);
+}
 
-	return 0;
+/*
+ * Free memblock.reserved.regions
+ */
+int __init_memblock memblock_free_reserved_regions(void)
+{
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
+
+	return memblock_free(__pa(memblock.reserved.regions),
+		 sizeof(struct memblock_region) * memblock.reserved.max);
 }
 
-static long memblock_regions_adjacent(struct memblock_region *rgn,
-		unsigned long r1, unsigned long r2)
+/*
+ * Reserve memblock.reserved.regions
+ */
+int __init_memblock memblock_reserve_reserved_regions(void)
 {
-	u64 base1 = rgn->region[r1].base;
-	u64 size1 = rgn->region[r1].size;
-	u64 base2 = rgn->region[r2].base;
-	u64 size2 = rgn->region[r2].size;
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
 
-	return memblock_addrs_adjacent(base1, size1, base2, size2);
+	return memblock_reserve(__pa(memblock.reserved.regions),
+		 sizeof(struct memblock_region) * memblock.reserved.max);
 }
 
-static void memblock_remove_region(struct memblock_region *rgn, unsigned long r)
+static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
 {
 	unsigned long i;
 
-	for (i = r; i < rgn->cnt - 1; i++) {
-		rgn->region[i].base = rgn->region[i + 1].base;
-		rgn->region[i].size = rgn->region[i + 1].size;
+	for (i = r; i < type->cnt - 1; i++) {
+		type->regions[i].base = type->regions[i + 1].base;
+		type->regions[i].size = type->regions[i + 1].size;
 	}
-	rgn->cnt--;
+	type->cnt--;
 }
 
 /* Assumption: base addr of region 1 < base addr of region 2 */
-static void memblock_coalesce_regions(struct memblock_region *rgn,
+static void __init_memblock memblock_coalesce_regions(struct memblock_type *type,
 		unsigned long r1, unsigned long r2)
 {
-	rgn->region[r1].size += rgn->region[r2].size;
-	memblock_remove_region(rgn, r2);
+	type->regions[r1].size += type->regions[r2].size;
+	memblock_remove_region(type, r2);
 }
 
-void __init memblock_init(void)
+/* Defined below but needed now */
+static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size);
+
+static int __init_memblock memblock_double_array(struct memblock_type *type)
 {
-	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
-	 * This simplifies the memblock_add() code below...
+	struct memblock_region *new_array, *old_array;
+	phys_addr_t old_size, new_size, addr;
+	int use_slab = slab_is_available();
+
+	/* We don't allow resizing until we know about the reserved regions
+	 * of memory that aren't suitable for allocation
 	 */
-	memblock.memory.region[0].base = 0;
-	memblock.memory.region[0].size = 0;
-	memblock.memory.cnt = 1;
+	if (!memblock_can_resize)
+		return -1;
 
-	/* Ditto. */
-	memblock.reserved.region[0].base = 0;
-	memblock.reserved.region[0].size = 0;
-	memblock.reserved.cnt = 1;
-}
+	/* Calculate new doubled size */
+	old_size = type->max * sizeof(struct memblock_region);
+	new_size = old_size << 1;
+
+	/* Try to find some space for it.
+	 *
+	 * WARNING: We assume that either slab_is_available() and we use it or
+	 * we use MEMBLOCK for allocations. That means that this is unsafe to use
+	 * when bootmem is currently active (unless bootmem itself is implemented
+	 * on top of MEMBLOCK which isn't the case yet)
+	 *
+	 * This should however not be an issue for now, as we currently only
+	 * call into MEMBLOCK while it's still active, or much later when slab is
+	 * active for memory hotplug operations
+	 */
+	if (use_slab) {
+		new_array = kmalloc(new_size, GFP_KERNEL);
+		addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array);
+	} else
+		addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE);
+	if (addr == MEMBLOCK_ERROR) {
+		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
+		       memblock_type_name(type), type->max, type->max * 2);
+		return -1;
+	}
+	new_array = __va(addr);
 
-void __init memblock_analyze(void)
-{
-	int i;
+	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
+		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
 
-	memblock.memory.size = 0;
+	/* Found space, we now need to move the array over before
+	 * we add the reserved region since it may be our reserved
+	 * array itself that is full.
+	 */
+	memcpy(new_array, type->regions, old_size);
+	memset(new_array + type->max, 0, old_size);
+	old_array = type->regions;
+	type->regions = new_array;
+	type->max <<= 1;
+
+	/* If we use SLAB that's it, we are done */
+	if (use_slab)
+		return 0;
 
-	for (i = 0; i < memblock.memory.cnt; i++)
-		memblock.memory.size += memblock.memory.region[i].size;
+	/* Add the new reserved region now. Should not fail ! */
+	BUG_ON(memblock_add_region(&memblock.reserved, addr, new_size) < 0);
+
+	/* If the array wasn't our static init one, then free it. We only do
+	 * that before SLAB is available as later on, we don't know whether
+	 * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
+	 * anyways
+	 */
+	if (old_array != memblock_memory_init_regions &&
+	    old_array != memblock_reserved_init_regions)
+		memblock_free(__pa(old_array), old_size);
+
+	return 0;
 }
 
-static long memblock_add_region(struct memblock_region *rgn, u64 base, u64 size)
+extern int __init_memblock __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+					  phys_addr_t addr2, phys_addr_t size2)
+{
+	return 1;
+}
+
+static long __init_memblock memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
 	unsigned long coalesced = 0;
 	long adjacent, i;
 
-	if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
+	if ((type->cnt == 1) && (type->regions[0].size == 0)) {
+		type->regions[0].base = base;
+		type->regions[0].size = size;
 		return 0;
 	}
 
 	/* First try and coalesce this MEMBLOCK with another. */
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
+	for (i = 0; i < type->cnt; i++) {
+		phys_addr_t rgnbase = type->regions[i].base;
+		phys_addr_t rgnsize = type->regions[i].size;
 
 		if ((rgnbase == base) && (rgnsize == size))
 			/* Already have this region, so we're done */
 			return 0;
 
 		adjacent = memblock_addrs_adjacent(base, size, rgnbase, rgnsize);
+		/* Check if arch allows coalescing */
+		if (adjacent != 0 && type == &memblock.memory &&
+		    !memblock_memory_can_coalesce(base, size, rgnbase, rgnsize))
+			break;
 		if (adjacent > 0) {
-			rgn->region[i].base -= size;
-			rgn->region[i].size += size;
+			type->regions[i].base -= size;
+			type->regions[i].size += size;
 			coalesced++;
 			break;
 		} else if (adjacent < 0) {
-			rgn->region[i].size += size;
+			type->regions[i].size += size;
 			coalesced++;
 			break;
 		}
 	}
 
-	if ((i < rgn->cnt - 1) && memblock_regions_adjacent(rgn, i, i+1)) {
-		memblock_coalesce_regions(rgn, i, i+1);
+	/* If we plugged a hole, we may want to also coalesce with the
+	 * next region
+	 */
+	if ((i < type->cnt - 1) && memblock_regions_adjacent(type, i, i+1) &&
+	    ((type != &memblock.memory || memblock_memory_can_coalesce(type->regions[i].base,
+							     type->regions[i].size,
+							     type->regions[i+1].base,
+							     type->regions[i+1].size)))) {
+		memblock_coalesce_regions(type, i, i+1);
 		coalesced++;
 	}
 
 	if (coalesced)
 		return coalesced;
-	if (rgn->cnt >= MAX_MEMBLOCK_REGIONS)
+
+	/* If we are out of space, we fail. It's too late to resize the array
+	 * but then this shouldn't have happened in the first place.
+	 */
+	if (WARN_ON(type->cnt >= type->max))
 		return -1;
 
 	/* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */
-	for (i = rgn->cnt - 1; i >= 0; i--) {
-		if (base < rgn->region[i].base) {
-			rgn->region[i+1].base = rgn->region[i].base;
-			rgn->region[i+1].size = rgn->region[i].size;
+	for (i = type->cnt - 1; i >= 0; i--) {
+		if (base < type->regions[i].base) {
+			type->regions[i+1].base = type->regions[i].base;
+			type->regions[i+1].size = type->regions[i].size;
 		} else {
-			rgn->region[i+1].base = base;
-			rgn->region[i+1].size = size;
+			type->regions[i+1].base = base;
+			type->regions[i+1].size = size;
 			break;
 		}
 	}
 
-	if (base < rgn->region[0].base) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
+	if (base < type->regions[0].base) {
+		type->regions[0].base = base;
+		type->regions[0].size = size;
+	}
+	type->cnt++;
+
+	/* The array is full ? Try to resize it. If that fails, we undo
+	 * our allocation and return an error
+	 */
+	if (type->cnt == type->max && memblock_double_array(type)) {
+		type->cnt--;
+		return -1;
 	}
-	rgn->cnt++;
 
 	return 0;
 }
 
-long memblock_add(u64 base, u64 size)
+long __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
-	struct memblock_region *_rgn = &memblock.memory;
-
-	/* On pSeries LPAR systems, the first MEMBLOCK is our RMO region. */
-	if (base == 0)
-		memblock.rmo_size = size;
-
-	return memblock_add_region(_rgn, base, size);
+	return memblock_add_region(&memblock.memory, base, size);
 
 }
 
-static long __memblock_remove(struct memblock_region *rgn, u64 base, u64 size)
+static long __init_memblock __memblock_remove(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
-	u64 rgnbegin, rgnend;
-	u64 end = base + size;
+	phys_addr_t rgnbegin, rgnend;
+	phys_addr_t end = base + size;
 	int i;
 
 	rgnbegin = rgnend = 0; /* supress gcc warnings */
 
 	/* Find the region where (base, size) belongs to */
-	for (i=0; i < rgn->cnt; i++) {
-		rgnbegin = rgn->region[i].base;
-		rgnend = rgnbegin + rgn->region[i].size;
+	for (i=0; i < type->cnt; i++) {
+		rgnbegin = type->regions[i].base;
+		rgnend = rgnbegin + type->regions[i].size;
 
 		if ((rgnbegin <= base) && (end <= rgnend))
 			break;
 	}
 
 	/* Didn't find the region */
-	if (i == rgn->cnt)
+	if (i == type->cnt)
 		return -1;
 
 	/* Check to see if we are removing entire region */
 	if ((rgnbegin == base) && (rgnend == end)) {
-		memblock_remove_region(rgn, i);
+		memblock_remove_region(type, i);
 		return 0;
 	}
 
 	/* Check to see if region is matching at the front */
 	if (rgnbegin == base) {
-		rgn->region[i].base = end;
-		rgn->region[i].size -= size;
+		type->regions[i].base = end;
+		type->regions[i].size -= size;
 		return 0;
 	}
 
 	/* Check to see if the region is matching at the end */
 	if (rgnend == end) {
-		rgn->region[i].size -= size;
+		type->regions[i].size -= size;
 		return 0;
 	}
 
@@ -249,208 +430,189 @@ static long __memblock_remove(struct memblock_region *rgn, u64 base, u64 size)
 	 * We need to split the entry -  adjust the current one to the
 	 * beginging of the hole and add the region after hole.
 	 */
-	rgn->region[i].size = base - rgn->region[i].base;
-	return memblock_add_region(rgn, end, rgnend - end);
+	type->regions[i].size = base - type->regions[i].base;
+	return memblock_add_region(type, end, rgnend - end);
 }
 
-long memblock_remove(u64 base, u64 size)
+long __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
 {
 	return __memblock_remove(&memblock.memory, base, size);
 }
 
-long __init memblock_free(u64 base, u64 size)
+long __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
 {
 	return __memblock_remove(&memblock.reserved, base, size);
 }
 
-long __init memblock_reserve(u64 base, u64 size)
+long __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 {
-	struct memblock_region *_rgn = &memblock.reserved;
+	struct memblock_type *_rgn = &memblock.reserved;
 
 	BUG_ON(0 == size);
 
 	return memblock_add_region(_rgn, base, size);
 }
 
-long memblock_overlaps_region(struct memblock_region *rgn, u64 base, u64 size)
+phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	unsigned long i;
+	phys_addr_t found;
 
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
-		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
-			break;
-	}
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
+	size = memblock_align_up(size, align);
 
-	return (i < rgn->cnt) ? i : -1;
+	found = memblock_find_base(size, align, 0, max_addr);
+	if (found != MEMBLOCK_ERROR &&
+	    memblock_add_region(&memblock.reserved, found, size) >= 0)
+		return found;
+
+	return 0;
 }
 
-static u64 memblock_align_down(u64 addr, u64 size)
+phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	return addr & ~(size - 1);
+	phys_addr_t alloc;
+
+	alloc = __memblock_alloc_base(size, align, max_addr);
+
+	if (alloc == 0)
+		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
+		      (unsigned long long) size, (unsigned long long) max_addr);
+
+	return alloc;
 }
 
-static u64 memblock_align_up(u64 addr, u64 size)
+phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
-	return (addr + (size - 1)) & ~(size - 1);
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
-static u64 __init memblock_alloc_nid_unreserved(u64 start, u64 end,
-					   u64 size, u64 align)
+
+/*
+ * Additional node-local allocators. Search for node memory is bottom up
+ * and walks memblock regions within that node bottom-up as well, but allocation
+ * within an memblock region is top-down. XXX I plan to fix that at some stage
+ *
+ * WARNING: Only available after early_node_map[] has been populated,
+ * on some architectures, that is after all the calls to add_active_range()
+ * have been done to populate it.
+ */
+
+phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
 {
-	u64 base, res_base;
-	long j;
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+	/*
+	 * This code originates from sparc which really wants use to walk by addresses
+	 * and returns the nid. This is not very convenient for early_pfn_map[] users
+	 * as the map isn't sorted yet, and it really wants to be walked by nid.
+	 *
+	 * For now, I implement the inefficient method below which walks the early
+	 * map multiple times. Eventually we may want to use an ARCH config option
+	 * to implement a completely different method for both case.
+	 */
+	unsigned long start_pfn, end_pfn;
+	int i;
 
-	base = memblock_align_down((end - size), align);
-	while (start <= base) {
-		j = memblock_overlaps_region(&memblock.reserved, base, size);
-		if (j < 0) {
-			/* this area isn't reserved, take it */
-			if (memblock_add_region(&memblock.reserved, base, size) < 0)
-				base = ~(u64)0;
-			return base;
-		}
-		res_base = memblock.reserved.region[j].base;
-		if (res_base < size)
-			break;
-		base = memblock_align_down(res_base - size, align);
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		get_pfn_range_for_nid(i, &start_pfn, &end_pfn);
+		if (start < PFN_PHYS(start_pfn) || start >= PFN_PHYS(end_pfn))
+			continue;
+		*nid = i;
+		return min(end, PFN_PHYS(end_pfn));
 	}
+#endif
+	*nid = 0;
 
-	return ~(u64)0;
+	return end;
 }
 
-static u64 __init memblock_alloc_nid_region(struct memblock_property *mp,
-				       u64 (*nid_range)(u64, u64, int *),
-				       u64 size, u64 align, int nid)
+static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
+					       phys_addr_t size,
+					       phys_addr_t align, int nid)
 {
-	u64 start, end;
+	phys_addr_t start, end;
 
 	start = mp->base;
 	end = start + mp->size;
 
 	start = memblock_align_up(start, align);
 	while (start < end) {
-		u64 this_end;
+		phys_addr_t this_end;
 		int this_nid;
 
-		this_end = nid_range(start, end, &this_nid);
+		this_end = memblock_nid_range(start, end, &this_nid);
 		if (this_nid == nid) {
-			u64 ret = memblock_alloc_nid_unreserved(start, this_end,
-							   size, align);
-			if (ret != ~(u64)0)
+			phys_addr_t ret = memblock_find_region(start, this_end, size, align);
+			if (ret != MEMBLOCK_ERROR &&
+			    memblock_add_region(&memblock.reserved, ret, size) >= 0)
 				return ret;
 		}
 		start = this_end;
 	}
 
-	return ~(u64)0;
+	return MEMBLOCK_ERROR;
 }
 
-u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
-			 u64 (*nid_range)(u64 start, u64 end, int *nid))
+phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	struct memblock_region *mem = &memblock.memory;
+	struct memblock_type *mem = &memblock.memory;
 	int i;
 
 	BUG_ON(0 == size);
 
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
 	size = memblock_align_up(size, align);
 
+	/* We do a bottom-up search for a region with the right
+	 * nid since that's easier considering how memblock_nid_range()
+	 * works
+	 */
 	for (i = 0; i < mem->cnt; i++) {
-		u64 ret = memblock_alloc_nid_region(&mem->region[i],
-					       nid_range,
+		phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
 					       size, align, nid);
-		if (ret != ~(u64)0)
+		if (ret != MEMBLOCK_ERROR)
 			return ret;
 	}
 
-	return memblock_alloc(size, align);
-}
-
-u64 __init memblock_alloc(u64 size, u64 align)
-{
-	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
+	return 0;
 }
 
-u64 __init memblock_alloc_base(u64 size, u64 align, u64 max_addr)
+phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	u64 alloc;
+	phys_addr_t res = memblock_alloc_nid(size, align, nid);
 
-	alloc = __memblock_alloc_base(size, align, max_addr);
-
-	if (alloc == 0)
-		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
-		      (unsigned long long) size, (unsigned long long) max_addr);
-
-	return alloc;
+	if (res)
+		return res;
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
 }
 
-u64 __init __memblock_alloc_base(u64 size, u64 align, u64 max_addr)
-{
-	long i, j;
-	u64 base = 0;
-	u64 res_base;
-
-	BUG_ON(0 == size);
-
-	size = memblock_align_up(size, align);
-
-	/* On some platforms, make sure we allocate lowmem */
-	/* Note that MEMBLOCK_REAL_LIMIT may be MEMBLOCK_ALLOC_ANYWHERE */
-	if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-		max_addr = MEMBLOCK_REAL_LIMIT;
-
-	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
-		u64 memblockbase = memblock.memory.region[i].base;
-		u64 memblocksize = memblock.memory.region[i].size;
-
-		if (memblocksize < size)
-			continue;
-		if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-			base = memblock_align_down(memblockbase + memblocksize - size, align);
-		else if (memblockbase < max_addr) {
-			base = min(memblockbase + memblocksize, max_addr);
-			base = memblock_align_down(base - size, align);
-		} else
-			continue;
 
-		while (base && memblockbase <= base) {
-			j = memblock_overlaps_region(&memblock.reserved, base, size);
-			if (j < 0) {
-				/* this area isn't reserved, take it */
-				if (memblock_add_region(&memblock.reserved, base, size) < 0)
-					return 0;
-				return base;
-			}
-			res_base = memblock.reserved.region[j].base;
-			if (res_base < size)
-				break;
-			base = memblock_align_down(res_base - size, align);
-		}
-	}
-	return 0;
-}
+/*
+ * Remaining API functions
+ */
 
 /* You must call memblock_analyze() before this. */
-u64 __init memblock_phys_mem_size(void)
+phys_addr_t __init memblock_phys_mem_size(void)
 {
-	return memblock.memory.size;
+	return memblock.memory_size;
 }
 
-u64 memblock_end_of_DRAM(void)
+phys_addr_t __init_memblock memblock_end_of_DRAM(void)
 {
 	int idx = memblock.memory.cnt - 1;
 
-	return (memblock.memory.region[idx].base + memblock.memory.region[idx].size);
+	return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
 }
 
 /* You must call memblock_analyze() after this. */
-void __init memblock_enforce_memory_limit(u64 memory_limit)
+void __init memblock_enforce_memory_limit(phys_addr_t memory_limit)
 {
 	unsigned long i;
-	u64 limit;
-	struct memblock_property *p;
+	phys_addr_t limit;
+	struct memblock_region *p;
 
 	if (!memory_limit)
 		return;
@@ -458,24 +620,21 @@ void __init memblock_enforce_memory_limit(u64 memory_limit)
 	/* Truncate the memblock regions to satisfy the memory limit. */
 	limit = memory_limit;
 	for (i = 0; i < memblock.memory.cnt; i++) {
-		if (limit > memblock.memory.region[i].size) {
-			limit -= memblock.memory.region[i].size;
+		if (limit > memblock.memory.regions[i].size) {
+			limit -= memblock.memory.regions[i].size;
 			continue;
 		}
 
-		memblock.memory.region[i].size = limit;
+		memblock.memory.regions[i].size = limit;
 		memblock.memory.cnt = i + 1;
 		break;
 	}
 
-	if (memblock.memory.region[0].size < memblock.rmo_size)
-		memblock.rmo_size = memblock.memory.region[0].size;
-
 	memory_limit = memblock_end_of_DRAM();
 
 	/* And truncate any reserves above the limit also. */
 	for (i = 0; i < memblock.reserved.cnt; i++) {
-		p = &memblock.reserved.region[i];
+		p = &memblock.reserved.regions[i];
 
 		if (p->base > memory_limit)
 			p->size = 0;
@@ -489,53 +648,184 @@ void __init memblock_enforce_memory_limit(u64 memory_limit)
 	}
 }
 
-int __init memblock_is_reserved(u64 addr)
+static int memblock_search(struct memblock_type *type, phys_addr_t addr)
 {
+	unsigned int left = 0, right = type->cnt;
+
+	do {
+		unsigned int mid = (right + left) / 2;
+
+		if (addr < type->regions[mid].base)
+			right = mid;
+		else if (addr >= (type->regions[mid].base +
+				  type->regions[mid].size))
+			left = mid + 1;
+		else
+			return mid;
+	} while (left < right);
+	return -1;
+}
+
+int __init memblock_is_reserved(phys_addr_t addr)
+{
+	return memblock_search(&memblock.reserved, addr) != -1;
+}
+
+int __init_memblock memblock_is_memory(phys_addr_t addr)
+{
+	return memblock_search(&memblock.memory, addr) != -1;
+}
+
+int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
+{
+	int idx = memblock_search(&memblock.reserved, base);
+
+	if (idx == -1)
+		return 0;
+	return memblock.reserved.regions[idx].base <= base &&
+		(memblock.reserved.regions[idx].base +
+		 memblock.reserved.regions[idx].size) >= (base + size);
+}
+
+int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
+}
+
+
+void __init_memblock memblock_set_current_limit(phys_addr_t limit)
+{
+	memblock.current_limit = limit;
+}
+
+static void __init_memblock memblock_dump(struct memblock_type *region, char *name)
+{
+	unsigned long long base, size;
 	int i;
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		u64 upper = memblock.reserved.region[i].base +
-			memblock.reserved.region[i].size - 1;
-		if ((addr >= memblock.reserved.region[i].base) && (addr <= upper))
-			return 1;
+	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
+
+	for (i = 0; i < region->cnt; i++) {
+		base = region->regions[i].base;
+		size = region->regions[i].size;
+
+		pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes\n",
+		    name, i, base, base + size - 1, size);
 	}
-	return 0;
 }
 
-int memblock_is_region_reserved(u64 base, u64 size)
+void __init_memblock memblock_dump_all(void)
 {
-	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
+	if (!memblock_debug)
+		return;
+
+	pr_info("MEMBLOCK configuration:\n");
+	pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
+
+	memblock_dump(&memblock.memory, "memory");
+	memblock_dump(&memblock.reserved, "reserved");
 }
 
-/*
- * Given a <base, len>, find which memory regions belong to this range.
- * Adjust the request and return a contiguous chunk.
- */
-int memblock_find(struct memblock_property *res)
+void __init memblock_analyze(void)
 {
 	int i;
-	u64 rstart, rend;
 
-	rstart = res->base;
-	rend = rstart + res->size - 1;
+	/* Check marker in the unused last array entry */
+	WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+	WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+
+	memblock.memory_size = 0;
+
+	for (i = 0; i < memblock.memory.cnt; i++)
+		memblock.memory_size += memblock.memory.regions[i].size;
+
+	/* We allow resizing from there */
+	memblock_can_resize = 1;
+}
+
+void __init memblock_init(void)
+{
+	/* Hookup the initial arrays */
+	memblock.memory.regions	= memblock_memory_init_regions;
+	memblock.memory.max		= INIT_MEMBLOCK_REGIONS;
+	memblock.reserved.regions	= memblock_reserved_init_regions;
+	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
+
+	/* Write a marker in the unused last array entry */
+	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+
+	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
+	 * This simplifies the memblock_add() code below...
+	 */
+	memblock.memory.regions[0].base = 0;
+	memblock.memory.regions[0].size = 0;
+	memblock.memory.cnt = 1;
+
+	/* Ditto. */
+	memblock.reserved.regions[0].base = 0;
+	memblock.reserved.regions[0].size = 0;
+	memblock.reserved.cnt = 1;
+
+	memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
+}
+
+static int __init early_memblock(char *p)
+{
+	if (p && strstr(p, "debug"))
+		memblock_debug = 1;
+	return 0;
+}
+early_param("memblock", early_memblock);
+
+#if defined(CONFIG_DEBUG_FS) && !defined(ARCH_DISCARD_MEMBLOCK)
+
+static int memblock_debug_show(struct seq_file *m, void *private)
+{
+	struct memblock_type *type = m->private;
+	struct memblock_region *reg;
+	int i;
+
+	for (i = 0; i < type->cnt; i++) {
+		reg = &type->regions[i];
+		seq_printf(m, "%4d: ", i);
+		if (sizeof(phys_addr_t) == 4)
+			seq_printf(m, "0x%08lx..0x%08lx\n",
+				   (unsigned long)reg->base,
+				   (unsigned long)(reg->base + reg->size - 1));
+		else
+			seq_printf(m, "0x%016llx..0x%016llx\n",
+				   (unsigned long long)reg->base,
+				   (unsigned long long)(reg->base + reg->size - 1));
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		u64 start = memblock.memory.region[i].base;
-		u64 end = start + memblock.memory.region[i].size - 1;
-
-		if (start > rend)
-			return -1;
-
-		if ((end >= rstart) && (start < rend)) {
-			/* adjust the request */
-			if (rstart < start)
-				rstart = start;
-			if (rend > end)
-				rend = end;
-			res->base = rstart;
-			res->size = rend - rstart + 1;
-			return 0;
-		}
 	}
-	return -1;
+	return 0;
 }
+
+static int memblock_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, memblock_debug_show, inode->i_private);
+}
+
+static const struct file_operations memblock_debug_fops = {
+	.open = memblock_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init memblock_init_debugfs(void)
+{
+	struct dentry *root = debugfs_create_dir("memblock", NULL);
+	if (!root)
+		return -ENXIO;
+	debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
+	debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
+
+	return 0;
+}
+__initcall(memblock_init_debugfs);
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/mm/memory.c b/mm/memory.c
index 0e18b4d649ec..98b58fecedef 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3185,7 +3185,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 		 * with threads.
 		 */
 		if (flags & FAULT_FLAG_WRITE)
-			flush_tlb_page(vma, address);
+			flush_tlb_fix_spurious_fault(vma, address);
 	}
 unlock:
 	pte_unmap_unlock(pte, ptl);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a8cfa9cc6e86..9536017108ec 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -21,6 +21,7 @@
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/kmemcheck.h>
@@ -3636,6 +3637,41 @@ void __init free_bootmem_with_active_regions(int nid,
 	}
 }
 
+#ifdef CONFIG_HAVE_MEMBLOCK
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	int i;
+
+	/* Need to go over early_node_map to find out good range for node */
+	for_each_active_range_index_in_nid(i, nid) {
+		u64 addr;
+		u64 ei_start, ei_last;
+		u64 final_start, final_end;
+
+		ei_last = early_node_map[i].end_pfn;
+		ei_last <<= PAGE_SHIFT;
+		ei_start = early_node_map[i].start_pfn;
+		ei_start <<= PAGE_SHIFT;
+
+		final_start = max(ei_start, goal);
+		final_end = min(ei_last, limit);
+
+		if (final_start >= final_end)
+			continue;
+
+		addr = memblock_find_in_range(final_start, final_end, size, align);
+
+		if (addr == MEMBLOCK_ERROR)
+			continue;
+
+		return addr;
+	}
+
+	return MEMBLOCK_ERROR;
+}
+#endif
+
 int __init add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid)
 {
@@ -3655,46 +3691,26 @@ int __init add_from_early_node_map(struct range *range, int az,
 void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit)
 {
-	int i;
 	void *ptr;
+	u64 addr;
 
-	if (limit > get_max_mapped())
-		limit = get_max_mapped();
-
-	/* need to go over early_node_map to find out good range for node */
-	for_each_active_range_index_in_nid(i, nid) {
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		ei_last = early_node_map[i].end_pfn;
-		ei_last <<= PAGE_SHIFT;
-		ei_start = early_node_map[i].start_pfn;
-		ei_start <<= PAGE_SHIFT;
-		addr = find_early_area(ei_start, ei_last,
-					 goal, limit, size, align);
-
-		if (addr == -1ULL)
-			continue;
+	if (limit > memblock.current_limit)
+		limit = memblock.current_limit;
 
-#if 0
-		printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
-				nid,
-				ei_start, ei_last, goal, limit, size,
-				align, addr);
-#endif
+	addr = find_memory_core_early(nid, size, align, goal, limit);
 
-		ptr = phys_to_virt(addr);
-		memset(ptr, 0, size);
-		reserve_early_without_check(addr, addr + size, "BOOTMEM");
-		/*
-		 * The min_count is set to 0 so that bootmem allocated blocks
-		 * are never reported as leaks.
-		 */
-		kmemleak_alloc(ptr, size, 0, 0);
-		return ptr;
-	}
+	if (addr == MEMBLOCK_ERROR)
+		return NULL;
 
-	return NULL;
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
+	/*
+	 * The min_count is set to 0 so that bootmem allocated blocks
+	 * are never reported as leaks.
+	 */
+	kmemleak_alloc(ptr, size, 0, 0);
+	return ptr;
 }
 #endif
 
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index aa33fd67fa41..29d6cbffb283 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -220,18 +220,7 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 
 	if (vmemmap_buf_start) {
 		/* need to free left buf */
-#ifdef CONFIG_NO_BOOTMEM
-		free_early(__pa(vmemmap_buf_start), __pa(vmemmap_buf_end));
-		if (vmemmap_buf_start < vmemmap_buf) {
-			char name[15];
-
-			snprintf(name, sizeof(name), "MEMMAP %d", nodeid);
-			reserve_early_without_check(__pa(vmemmap_buf_start),
-						    __pa(vmemmap_buf), name);
-		}
-#else
 		free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf);
-#endif
 		vmemmap_buf = NULL;
 		vmemmap_buf_end = NULL;
 	}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c623e0ce3f00..9f909622a25e 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -517,6 +517,15 @@ static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
 static void purge_fragmented_blocks_allcpus(void);
 
 /*
+ * called before a call to iounmap() if the caller wants vm_area_struct's
+ * immediately freed.
+ */
+void set_iounmap_nonlazy(void)
+{
+	atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
+}
+
+/*
  * Purges all lazily-freed vmap areas.
  *
  * If sync is 0 then don't purge if there is already a purge in progress.
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 4df1b7a6c1bf..cd1e039c8755 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -243,6 +243,7 @@ void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb)
 	unlock_sock_fast(sk, slow);
 
 	/* skb is now orphaned, can be freed outside of locked section */
+	trace_kfree_skb(skb, skb_free_datagram_locked);
 	__kfree_skb(skb);
 }
 EXPORT_SYMBOL(skb_free_datagram_locked);
diff --git a/net/core/dev.c b/net/core/dev.c
index 7d149550e8d6..52c01cb646db 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -128,6 +128,8 @@
 #include <linux/jhash.h>
 #include <linux/random.h>
 #include <trace/events/napi.h>
+#include <trace/events/net.h>
+#include <trace/events/skb.h>
 #include <linux/pci.h>
 #include <linux/inetdevice.h>
 
@@ -2013,6 +2015,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 		}
 
 		rc = ops->ndo_start_xmit(skb, dev);
+		trace_net_dev_xmit(skb, rc);
 		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
 		return rc;
@@ -2033,6 +2036,7 @@ gso:
 			skb_dst_drop(nskb);
 
 		rc = ops->ndo_start_xmit(nskb, dev);
+		trace_net_dev_xmit(nskb, rc);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
 				goto out_kfree_gso_skb;
@@ -2224,6 +2228,7 @@ int dev_queue_xmit(struct sk_buff *skb)
 #ifdef CONFIG_NET_CLS_ACT
 	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
 #endif
+	trace_net_dev_queue(skb);
 	if (q->enqueue) {
 		rc = __dev_xmit_skb(skb, q, dev, txq);
 		goto out;
@@ -2580,6 +2585,7 @@ int netif_rx(struct sk_buff *skb)
 	if (netdev_tstamp_prequeue)
 		net_timestamp_check(skb);
 
+	trace_netif_rx(skb);
 #ifdef CONFIG_RPS
 	{
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
@@ -2639,6 +2645,7 @@ static void net_tx_action(struct softirq_action *h)
 			clist = clist->next;
 
 			WARN_ON(atomic_read(&skb->users));
+			trace_kfree_skb(skb, net_tx_action);
 			__kfree_skb(skb);
 		}
 	}
@@ -2895,6 +2902,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	if (!netdev_tstamp_prequeue)
 		net_timestamp_check(skb);
 
+	trace_netif_receive_skb(skb);
 	if (vlan_tx_tag_present(skb))
 		vlan_hwaccel_do_receive(skb);
 
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index afa6380ed88a..7f1bb2aba03b 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -26,6 +26,7 @@
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/skb.h>
+#include <trace/events/net.h>
 #include <trace/events/napi.h>
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 752c1972b3a7..f472b089127a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -464,6 +464,7 @@ void consume_skb(struct sk_buff *skb)
 		smp_rmb();
 	else if (likely(!atomic_dec_and_test(&skb->users)))
 		return;
+	trace_consume_skb(skb);
 	__kfree_skb(skb);
 }
 EXPORT_SYMBOL(consume_skb);
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 54fd1b700131..7bfcf1a09ac5 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -101,14 +101,6 @@ basename_flags = -D"KBUILD_BASENAME=KBUILD_STR($(call name-fix,$(basetarget)))"
 modname_flags  = $(if $(filter 1,$(words $(modname))),\
                  -D"KBUILD_MODNAME=KBUILD_STR($(call name-fix,$(modname)))")
 
-#hash values
-ifdef CONFIG_DYNAMIC_DEBUG
-debug_flags = -D"DEBUG_HASH=$(shell ./scripts/basic/hash djb2 $(@D)$(modname))"\
-              -D"DEBUG_HASH2=$(shell ./scripts/basic/hash r5 $(@D)$(modname))"
-else
-debug_flags =
-endif
-
 orig_c_flags   = $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(KBUILD_SUBDIR_CCFLAGS) \
                  $(ccflags-y) $(CFLAGS_$(basetarget).o)
 _c_flags       = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(orig_c_flags))
@@ -152,8 +144,7 @@ endif
 
 c_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(__c_flags) $(modkern_cflags)                           \
-		 -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags) \
-		  $(debug_flags)
+		 -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags)
 
 a_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(__a_flags) $(modkern_aflags)
diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile
index 09559951df12..4c324a1f1e0e 100644
--- a/scripts/basic/Makefile
+++ b/scripts/basic/Makefile
@@ -9,7 +9,7 @@
 # fixdep: 	 Used to generate dependency information during build process
 # docproc:	 Used in Documentation/DocBook
 
-hostprogs-y	:= fixdep docproc hash
+hostprogs-y	:= fixdep docproc
 always		:= $(hostprogs-y)
 
 # fixdep is needed to compile other host programs
diff --git a/scripts/basic/hash.c b/scripts/basic/hash.c
deleted file mode 100644
index 2ef5d3f666b8..000000000000
--- a/scripts/basic/hash.c
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * Copyright (C) 2008 Red Hat, Inc., Jason Baron <jbaron@redhat.com>
- *
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
-#define DYNAMIC_DEBUG_HASH_BITS 6
-
-static const char *program;
-
-static void usage(void)
-{
-	printf("Usage: %s <djb2|r5> <modname>\n", program);
-	exit(1);
-}
-
-/* djb2 hashing algorithm by Dan Bernstein. From:
- * http://www.cse.yorku.ca/~oz/hash.html
- */
-
-static unsigned int djb2_hash(char *str)
-{
-	unsigned long hash = 5381;
-	int c;
-
-	c = *str;
-	while (c) {
-		hash = ((hash << 5) + hash) + c;
-		c = *++str;
-	}
-	return (unsigned int)(hash & ((1 << DYNAMIC_DEBUG_HASH_BITS) - 1));
-}
-
-static unsigned int r5_hash(char *str)
-{
-	unsigned long hash = 0;
-	int c;
-
-	c = *str;
-	while (c) {
-		hash = (hash + (c << 4) + (c >> 4)) * 11;
-		c = *++str;
-	}
-	return (unsigned int)(hash & ((1 << DYNAMIC_DEBUG_HASH_BITS) - 1));
-}
-
-int main(int argc, char *argv[])
-{
-	program = argv[0];
-
-	if (argc != 3)
-		usage();
-	if (!strcmp(argv[1], "djb2"))
-		printf("%d\n", djb2_hash(argv[2]));
-	else if (!strcmp(argv[1], "r5"))
-		printf("%d\n", r5_hash(argv[2]));
-	else
-		usage();
-	exit(0);
-}
-
diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh
new file mode 100644
index 000000000000..520d16b1ffaf
--- /dev/null
+++ b/scripts/gcc-goto.sh
@@ -0,0 +1,5 @@
+#!/bin/sh
+# Test for gcc 'asm goto' suport
+# Copyright (C) 2010, Jason Baron <jbaron@redhat.com>
+
+echo "int main(void) { entry: asm goto (\"\"::::entry); return 0; }" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 5164a655c39f..b2c63309a651 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -8,7 +8,7 @@ perf-annotate - Read perf.data (created by perf record) and display annotated co
 SYNOPSIS
 --------
 [verse]
-'perf annotate' [-i <file> | --input=file] symbol_name
+'perf annotate' [-i <file> | --input=file] [symbol_name]
 
 DESCRIPTION
 -----------
@@ -24,6 +24,13 @@ OPTIONS
 --input=::
         Input file name. (default: perf.data)
 
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface Use of --tui requires a tty, if one is not
+	present, as when piping to other commands, the stdio interface is
+	used. This interfaces starts by centering on the line with more
+	samples, TAB/UNTAB cycles thru the lines with more samples.
+
 SEE ALSO
 --------
-linkperf:perf-record[1]
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index abfabe9147a4..12052c9ed0ba 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -65,6 +65,13 @@ OPTIONS
 		 the tree is considered as a new profiled object. +
 	Default: fractal,0.5.
 
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface, that is integrated with annotate and allows
+        zooming into DSOs or threads, among other features. Use of --tui
+	requires a tty, if one is not present, as when piping to other
+	commands, the stdio interface is used.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 1950e19af1cf..d1db0f676a4b 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -313,6 +313,9 @@ TEST_PROGRAMS =
 
 SCRIPT_SH += perf-archive.sh
 
+grep-libs = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
+
 #
 # No Perl scripts right now:
 #
@@ -588,14 +591,17 @@ endif
 ifdef NO_LIBPERL
 	BASIC_CFLAGS += -DNO_LIBPERL
 else
-	PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null`
+       PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
+       PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
+       PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
 	PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
 	FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
 	ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED)),y)
 		BASIC_CFLAGS += -DNO_LIBPERL
 	else
-		ALL_LDFLAGS += $(PERL_EMBED_LDOPTS)
+               ALL_LDFLAGS += $(PERL_EMBED_LDFLAGS)
+               EXTLIBS += $(PERL_EMBED_LIBADD)
 		LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
 		LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
 	endif
@@ -604,13 +610,16 @@ endif
 ifdef NO_LIBPYTHON
 	BASIC_CFLAGS += -DNO_LIBPYTHON
 else
-	PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null`
+       PYTHON_EMBED_LDOPTS = $(shell python-config --ldflags 2>/dev/null)
+       PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+       PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
 	PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
 	FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 	ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
 		BASIC_CFLAGS += -DNO_LIBPYTHON
 	else
-		ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS)
+               ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
+               EXTLIBS += $(PYTHON_EMBED_LIBADD)
 		LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
 		LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
 	endif
@@ -653,6 +662,15 @@ else
 	endif
 endif
 
+
+ifdef NO_STRLCPY
+	BASIC_CFLAGS += -DNO_STRLCPY
+else
+	ifneq ($(call try-cc,$(SOURCE_STRLCPY),),y)
+		BASIC_CFLAGS += -DNO_STRLCPY
+	endif
+endif
+
 ifndef CC_LD_DYNPATH
 	ifdef NO_R_TO_GCC_LINKER
 		# Some gcc does not accept and pass -R to the linker to specify
@@ -910,8 +928,8 @@ $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
 		$(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
 
 $(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
-	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(OUTPUT)perf.o \
-		$(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) $(OUTPUT)perf.o \
+               $(BUILTIN_OBJS) $(LIBS) -o $@
 
 $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1478dc64bf15..6d5604d8df95 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -28,7 +28,7 @@
 
 static char		const *input_name = "perf.data";
 
-static bool		force;
+static bool		force, use_tui, use_stdio;
 
 static bool		full_paths;
 
@@ -321,7 +321,7 @@ static int hist_entry__tty_annotate(struct hist_entry *he)
 
 static void hists__find_annotations(struct hists *self)
 {
-	struct rb_node *first = rb_first(&self->entries), *nd = first;
+	struct rb_node *nd = rb_first(&self->entries), *next;
 	int key = KEY_RIGHT;
 
 	while (nd) {
@@ -343,20 +343,19 @@ find_next:
 
 		if (use_browser > 0) {
 			key = hist_entry__tui_annotate(he);
-			if (is_exit_key(key))
-				break;
 			switch (key) {
 			case KEY_RIGHT:
-			case '\t':
-				nd = rb_next(nd);
+				next = rb_next(nd);
 				break;
 			case KEY_LEFT:
-				if (nd == first)
-					continue;
-				nd = rb_prev(nd);
-			default:
+				next = rb_prev(nd);
 				break;
+			default:
+				return;
 			}
+
+			if (next != NULL)
+				nd = next;
 		} else {
 			hist_entry__tty_annotate(he);
 			nd = rb_next(nd);
@@ -428,6 +427,8 @@ static const struct option options[] = {
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
+	OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
@@ -443,6 +444,11 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __used)
 {
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 
+	if (use_stdio)
+		use_browser = 0;
+	else if (use_tui)
+		use_browser = 1;
+
 	setup_browser();
 
 	symbol_conf.priv_size = sizeof(struct sym_priv);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 55fc1f46892a..5de405d45230 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -32,7 +32,7 @@
 
 static char		const *input_name = "perf.data";
 
-static bool		force;
+static bool		force, use_tui, use_stdio;
 static bool		hide_unresolved;
 static bool		dont_use_callchains;
 
@@ -107,7 +107,8 @@ static int perf_session__add_hist_entry(struct perf_session *self,
 		goto out_free_syms;
 	err = 0;
 	if (symbol_conf.use_callchain) {
-		err = append_chain(he->callchain, data->callchain, syms, data->period);
+		err = callchain_append(he->callchain, data->callchain, syms,
+				       data->period);
 		if (err)
 			goto out_free_syms;
 	}
@@ -450,6 +451,8 @@ static const struct option options[] = {
 		    "Show per-thread event counters"),
 	OPT_STRING(0, "pretty", &pretty_printing_style, "key",
 		   "pretty printing style key: normal raw"),
+	OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
@@ -482,8 +485,15 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 {
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
+	if (use_stdio)
+		use_browser = 0;
+	else if (use_tui)
+		use_browser = 1;
+
 	if (strcmp(input_name, "-") != 0)
 		setup_browser();
+	else
+		use_browser = 0;
 	/*
 	 * Only in the newt browser we are doing integrated annotation,
 	 * so don't allocate extra space that won't be used in the stdio
diff --git a/tools/perf/feature-tests.mak b/tools/perf/feature-tests.mak
index 7a7b60859053..b253db634f04 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/feature-tests.mak
@@ -110,6 +110,17 @@ int main(void)
 }
 endef
 
+define SOURCE_STRLCPY
+#include <stdlib.h>
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+
+int main(void)
+{
+	strlcpy(NULL, NULL, 0);
+	return 0;
+}
+endef
+
 # try-cc
 # Usage: option = $(call try-cc, source-to-build, cc-options)
 try-cc = $(shell sh -c						  \
diff --git a/tools/perf/scripts/python/bin/netdev-times-record b/tools/perf/scripts/python/bin/netdev-times-record
new file mode 100644
index 000000000000..d931a828126b
--- /dev/null
+++ b/tools/perf/scripts/python/bin/netdev-times-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+perf record -a -e net:net_dev_xmit -e net:net_dev_queue		\
+		-e net:netif_receive_skb -e net:netif_rx		\
+		-e skb:consume_skb -e skb:kfree_skb			\
+		-e skb:skb_copy_datagram_iovec -e napi:napi_poll	\
+		-e irq:irq_handler_entry -e irq:irq_handler_exit	\
+		-e irq:softirq_entry -e irq:softirq_exit		\
+		-e irq:softirq_raise $@
diff --git a/tools/perf/scripts/python/bin/netdev-times-report b/tools/perf/scripts/python/bin/netdev-times-report
new file mode 100644
index 000000000000..c3d0a638123d
--- /dev/null
+++ b/tools/perf/scripts/python/bin/netdev-times-report
@@ -0,0 +1,5 @@
+#!/bin/bash
+# description: display a process of packet and processing time
+# args: [tx] [rx] [dev=] [debug]
+
+perf trace -s ~/libexec/perf-core/scripts/python/netdev-times.py $@
diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py
new file mode 100644
index 000000000000..9aa0a32972e8
--- /dev/null
+++ b/tools/perf/scripts/python/netdev-times.py
@@ -0,0 +1,464 @@
+# Display a process of packets and processed time.
+# It helps us to investigate networking or network device.
+#
+# options
+# tx: show only tx chart
+# rx: show only rx chart
+# dev=: show only thing related to specified device
+# debug: work with debug mode. It shows buffer status.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+all_event_list = []; # insert all tracepoint event related with this script
+irq_dic = {}; # key is cpu and value is a list which stacks irqs
+              # which raise NET_RX softirq
+net_rx_dic = {}; # key is cpu and value include time of NET_RX softirq-entry
+		 # and a list which stacks receive
+receive_hunk_list = []; # a list which include a sequence of receive events
+rx_skb_list = []; # received packet list for matching
+		       # skb_copy_datagram_iovec
+
+buffer_budget = 65536; # the budget of rx_skb_list, tx_queue_list and
+		       # tx_xmit_list
+of_count_rx_skb_list = 0; # overflow count
+
+tx_queue_list = []; # list of packets which pass through dev_queue_xmit
+of_count_tx_queue_list = 0; # overflow count
+
+tx_xmit_list = [];  # list of packets which pass through dev_hard_start_xmit
+of_count_tx_xmit_list = 0; # overflow count
+
+tx_free_list = [];  # list of packets which is freed
+
+# options
+show_tx = 0;
+show_rx = 0;
+dev = 0; # store a name of device specified by option "dev="
+debug = 0;
+
+# indices of event_info tuple
+EINFO_IDX_NAME=   0
+EINFO_IDX_CONTEXT=1
+EINFO_IDX_CPU=    2
+EINFO_IDX_TIME=   3
+EINFO_IDX_PID=    4
+EINFO_IDX_COMM=   5
+
+# Calculate a time interval(msec) from src(nsec) to dst(nsec)
+def diff_msec(src, dst):
+	return (dst - src) / 1000000.0
+
+# Display a process of transmitting a packet
+def print_transmit(hunk):
+	if dev != 0 and hunk['dev'].find(dev) < 0:
+		return
+	print "%7s %5d %6d.%06dsec %12.3fmsec      %12.3fmsec" % \
+		(hunk['dev'], hunk['len'],
+		nsecs_secs(hunk['queue_t']),
+		nsecs_nsecs(hunk['queue_t'])/1000,
+		diff_msec(hunk['queue_t'], hunk['xmit_t']),
+		diff_msec(hunk['xmit_t'], hunk['free_t']))
+
+# Format for displaying rx packet processing
+PF_IRQ_ENTRY= "  irq_entry(+%.3fmsec irq=%d:%s)"
+PF_SOFT_ENTRY="  softirq_entry(+%.3fmsec)"
+PF_NAPI_POLL= "  napi_poll_exit(+%.3fmsec %s)"
+PF_JOINT=     "         |"
+PF_WJOINT=    "         |            |"
+PF_NET_RECV=  "         |---netif_receive_skb(+%.3fmsec skb=%x len=%d)"
+PF_NET_RX=    "         |---netif_rx(+%.3fmsec skb=%x)"
+PF_CPY_DGRAM= "         |      skb_copy_datagram_iovec(+%.3fmsec %d:%s)"
+PF_KFREE_SKB= "         |      kfree_skb(+%.3fmsec location=%x)"
+PF_CONS_SKB=  "         |      consume_skb(+%.3fmsec)"
+
+# Display a process of received packets and interrputs associated with
+# a NET_RX softirq
+def print_receive(hunk):
+	show_hunk = 0
+	irq_list = hunk['irq_list']
+	cpu = irq_list[0]['cpu']
+	base_t = irq_list[0]['irq_ent_t']
+	# check if this hunk should be showed
+	if dev != 0:
+		for i in range(len(irq_list)):
+			if irq_list[i]['name'].find(dev) >= 0:
+				show_hunk = 1
+				break
+	else:
+		show_hunk = 1
+	if show_hunk == 0:
+		return
+
+	print "%d.%06dsec cpu=%d" % \
+		(nsecs_secs(base_t), nsecs_nsecs(base_t)/1000, cpu)
+	for i in range(len(irq_list)):
+		print PF_IRQ_ENTRY % \
+			(diff_msec(base_t, irq_list[i]['irq_ent_t']),
+			irq_list[i]['irq'], irq_list[i]['name'])
+		print PF_JOINT
+		irq_event_list = irq_list[i]['event_list']
+		for j in range(len(irq_event_list)):
+			irq_event = irq_event_list[j]
+			if irq_event['event'] == 'netif_rx':
+				print PF_NET_RX % \
+					(diff_msec(base_t, irq_event['time']),
+					irq_event['skbaddr'])
+				print PF_JOINT
+	print PF_SOFT_ENTRY % \
+		diff_msec(base_t, hunk['sirq_ent_t'])
+	print PF_JOINT
+	event_list = hunk['event_list']
+	for i in range(len(event_list)):
+		event = event_list[i]
+		if event['event_name'] == 'napi_poll':
+			print PF_NAPI_POLL % \
+			    (diff_msec(base_t, event['event_t']), event['dev'])
+			if i == len(event_list) - 1:
+				print ""
+			else:
+				print PF_JOINT
+		else:
+			print PF_NET_RECV % \
+			    (diff_msec(base_t, event['event_t']), event['skbaddr'],
+				event['len'])
+			if 'comm' in event.keys():
+				print PF_WJOINT
+				print PF_CPY_DGRAM % \
+					(diff_msec(base_t, event['comm_t']),
+					event['pid'], event['comm'])
+			elif 'handle' in event.keys():
+				print PF_WJOINT
+				if event['handle'] == "kfree_skb":
+					print PF_KFREE_SKB % \
+						(diff_msec(base_t,
+						event['comm_t']),
+						event['location'])
+				elif event['handle'] == "consume_skb":
+					print PF_CONS_SKB % \
+						diff_msec(base_t,
+							event['comm_t'])
+			print PF_JOINT
+
+def trace_begin():
+	global show_tx
+	global show_rx
+	global dev
+	global debug
+
+	for i in range(len(sys.argv)):
+		if i == 0:
+			continue
+		arg = sys.argv[i]
+		if arg == 'tx':
+			show_tx = 1
+		elif arg =='rx':
+			show_rx = 1
+		elif arg.find('dev=',0, 4) >= 0:
+			dev = arg[4:]
+		elif arg == 'debug':
+			debug = 1
+	if show_tx == 0  and show_rx == 0:
+		show_tx = 1
+		show_rx = 1
+
+def trace_end():
+	# order all events in time
+	all_event_list.sort(lambda a,b :cmp(a[EINFO_IDX_TIME],
+					    b[EINFO_IDX_TIME]))
+	# process all events
+	for i in range(len(all_event_list)):
+		event_info = all_event_list[i]
+		name = event_info[EINFO_IDX_NAME]
+		if name == 'irq__softirq_exit':
+			handle_irq_softirq_exit(event_info)
+		elif name == 'irq__softirq_entry':
+			handle_irq_softirq_entry(event_info)
+		elif name == 'irq__softirq_raise':
+			handle_irq_softirq_raise(event_info)
+		elif name == 'irq__irq_handler_entry':
+			handle_irq_handler_entry(event_info)
+		elif name == 'irq__irq_handler_exit':
+			handle_irq_handler_exit(event_info)
+		elif name == 'napi__napi_poll':
+			handle_napi_poll(event_info)
+		elif name == 'net__netif_receive_skb':
+			handle_netif_receive_skb(event_info)
+		elif name == 'net__netif_rx':
+			handle_netif_rx(event_info)
+		elif name == 'skb__skb_copy_datagram_iovec':
+			handle_skb_copy_datagram_iovec(event_info)
+		elif name == 'net__net_dev_queue':
+			handle_net_dev_queue(event_info)
+		elif name == 'net__net_dev_xmit':
+			handle_net_dev_xmit(event_info)
+		elif name == 'skb__kfree_skb':
+			handle_kfree_skb(event_info)
+		elif name == 'skb__consume_skb':
+			handle_consume_skb(event_info)
+	# display receive hunks
+	if show_rx:
+		for i in range(len(receive_hunk_list)):
+			print_receive(receive_hunk_list[i])
+	# display transmit hunks
+	if show_tx:
+		print "   dev    len      Qdisc        " \
+			"       netdevice             free"
+		for i in range(len(tx_free_list)):
+			print_transmit(tx_free_list[i])
+	if debug:
+		print "debug buffer status"
+		print "----------------------------"
+		print "xmit Qdisc:remain:%d overflow:%d" % \
+			(len(tx_queue_list), of_count_tx_queue_list)
+		print "xmit netdevice:remain:%d overflow:%d" % \
+			(len(tx_xmit_list), of_count_tx_xmit_list)
+		print "receive:remain:%d overflow:%d" % \
+			(len(rx_skb_list), of_count_rx_skb_list)
+
+# called from perf, when it finds a correspoinding event
+def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm,
+			irq, irq_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			irq, irq_name)
+	all_event_list.append(event_info)
+
+def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret)
+	all_event_list.append(event_info)
+
+def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			napi, dev_name)
+	all_event_list.append(event_info)
+
+def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+			skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+			skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, skblen, rc, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, rc ,dev_name)
+	all_event_list.append(event_info)
+
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, protocol, location):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, protocol, location)
+	all_event_list.append(event_info)
+
+def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr)
+	all_event_list.append(event_info)
+
+def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm,
+	skbaddr, skblen):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen)
+	all_event_list.append(event_info)
+
+def handle_irq_handler_entry(event_info):
+	(name, context, cpu, time, pid, comm, irq, irq_name) = event_info
+	if cpu not in irq_dic.keys():
+		irq_dic[cpu] = []
+	irq_record = {'irq':irq, 'name':irq_name, 'cpu':cpu, 'irq_ent_t':time}
+	irq_dic[cpu].append(irq_record)
+
+def handle_irq_handler_exit(event_info):
+	(name, context, cpu, time, pid, comm, irq, ret) = event_info
+	if cpu not in irq_dic.keys():
+		return
+	irq_record = irq_dic[cpu].pop()
+	if irq != irq_record['irq']:
+		return
+	irq_record.update({'irq_ext_t':time})
+	# if an irq doesn't include NET_RX softirq, drop.
+	if 'event_list' in irq_record.keys():
+		irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_raise(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	if cpu not in irq_dic.keys() \
+	or len(irq_dic[cpu]) == 0:
+		return
+	irq_record = irq_dic[cpu].pop()
+	if 'event_list' in irq_record.keys():
+		irq_event_list = irq_record['event_list']
+	else:
+		irq_event_list = []
+	irq_event_list.append({'time':time, 'event':'sirq_raise'})
+	irq_record.update({'event_list':irq_event_list})
+	irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_entry(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	net_rx_dic[cpu] = {'sirq_ent_t':time, 'event_list':[]}
+
+def handle_irq_softirq_exit(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	irq_list = []
+	event_list = 0
+	if cpu in irq_dic.keys():
+		irq_list = irq_dic[cpu]
+		del irq_dic[cpu]
+	if cpu in net_rx_dic.keys():
+		sirq_ent_t = net_rx_dic[cpu]['sirq_ent_t']
+		event_list = net_rx_dic[cpu]['event_list']
+		del net_rx_dic[cpu]
+	if irq_list == [] or event_list == 0:
+		return
+	rec_data = {'sirq_ent_t':sirq_ent_t, 'sirq_ext_t':time,
+		    'irq_list':irq_list, 'event_list':event_list}
+	# merge information realted to a NET_RX softirq
+	receive_hunk_list.append(rec_data)
+
+def handle_napi_poll(event_info):
+	(name, context, cpu, time, pid, comm, napi, dev_name) = event_info
+	if cpu in net_rx_dic.keys():
+		event_list = net_rx_dic[cpu]['event_list']
+		rec_data = {'event_name':'napi_poll',
+				'dev':dev_name, 'event_t':time}
+		event_list.append(rec_data)
+
+def handle_netif_rx(event_info):
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	if cpu not in irq_dic.keys() \
+	or len(irq_dic[cpu]) == 0:
+		return
+	irq_record = irq_dic[cpu].pop()
+	if 'event_list' in irq_record.keys():
+		irq_event_list = irq_record['event_list']
+	else:
+		irq_event_list = []
+	irq_event_list.append({'time':time, 'event':'netif_rx',
+		'skbaddr':skbaddr, 'skblen':skblen, 'dev_name':dev_name})
+	irq_record.update({'event_list':irq_event_list})
+	irq_dic[cpu].append(irq_record)
+
+def handle_netif_receive_skb(event_info):
+	global of_count_rx_skb_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	if cpu in net_rx_dic.keys():
+		rec_data = {'event_name':'netif_receive_skb',
+			    'event_t':time, 'skbaddr':skbaddr, 'len':skblen}
+		event_list = net_rx_dic[cpu]['event_list']
+		event_list.append(rec_data)
+		rx_skb_list.insert(0, rec_data)
+		if len(rx_skb_list) > buffer_budget:
+			rx_skb_list.pop()
+			of_count_rx_skb_list += 1
+
+def handle_net_dev_queue(event_info):
+	global of_count_tx_queue_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	skb = {'dev':dev_name, 'skbaddr':skbaddr, 'len':skblen, 'queue_t':time}
+	tx_queue_list.insert(0, skb)
+	if len(tx_queue_list) > buffer_budget:
+		tx_queue_list.pop()
+		of_count_tx_queue_list += 1
+
+def handle_net_dev_xmit(event_info):
+	global of_count_tx_xmit_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, rc, dev_name) = event_info
+	if rc == 0: # NETDEV_TX_OK
+		for i in range(len(tx_queue_list)):
+			skb = tx_queue_list[i]
+			if skb['skbaddr'] == skbaddr:
+				skb['xmit_t'] = time
+				tx_xmit_list.insert(0, skb)
+				del tx_queue_list[i]
+				if len(tx_xmit_list) > buffer_budget:
+					tx_xmit_list.pop()
+					of_count_tx_xmit_list += 1
+				return
+
+def handle_kfree_skb(event_info):
+	(name, context, cpu, time, pid, comm,
+		skbaddr, protocol, location) = event_info
+	for i in range(len(tx_queue_list)):
+		skb = tx_queue_list[i]
+		if skb['skbaddr'] == skbaddr:
+			del tx_queue_list[i]
+			return
+	for i in range(len(tx_xmit_list)):
+		skb = tx_xmit_list[i]
+		if skb['skbaddr'] == skbaddr:
+			skb['free_t'] = time
+			tx_free_list.append(skb)
+			del tx_xmit_list[i]
+			return
+	for i in range(len(rx_skb_list)):
+		rec_data = rx_skb_list[i]
+		if rec_data['skbaddr'] == skbaddr:
+			rec_data.update({'handle':"kfree_skb",
+					'comm':comm, 'pid':pid, 'comm_t':time})
+			del rx_skb_list[i]
+			return
+
+def handle_consume_skb(event_info):
+	(name, context, cpu, time, pid, comm, skbaddr) = event_info
+	for i in range(len(tx_xmit_list)):
+		skb = tx_xmit_list[i]
+		if skb['skbaddr'] == skbaddr:
+			skb['free_t'] = time
+			tx_free_list.append(skb)
+			del tx_xmit_list[i]
+			return
+
+def handle_skb_copy_datagram_iovec(event_info):
+	(name, context, cpu, time, pid, comm, skbaddr, skblen) = event_info
+	for i in range(len(rx_skb_list)):
+		rec_data = rx_skb_list[i]
+		if skbaddr == rec_data['skbaddr']:
+			rec_data.update({'handle':"skb_copy_datagram_iovec",
+					'comm':comm, 'pid':pid, 'comm_t':time})
+			del rx_skb_list[i]
+			return
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 27e9ebe4076e..a7729797fd96 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -82,6 +82,8 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
 	__attribute__((format (printf, 1, 2)));
 
+#ifdef NO_STRLCPY
 extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index f231f43424d2..e12d539417b2 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -28,6 +28,9 @@ bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event)
 #define chain_for_each_child(child, parent)	\
 	list_for_each_entry(child, &parent->children, brothers)
 
+#define chain_for_each_child_safe(child, next, parent)	\
+	list_for_each_entry_safe(child, next, &parent->children, brothers)
+
 static void
 rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 		    enum chain_mode mode)
@@ -86,10 +89,10 @@ __sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
  * sort them by hit
  */
 static void
-sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
+sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
 		u64 min_hit, struct callchain_param *param __used)
 {
-	__sort_chain_flat(rb_root, node, min_hit);
+	__sort_chain_flat(rb_root, &root->node, min_hit);
 }
 
 static void __sort_chain_graph_abs(struct callchain_node *node,
@@ -108,11 +111,11 @@ static void __sort_chain_graph_abs(struct callchain_node *node,
 }
 
 static void
-sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_node *chain_root,
+sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root,
 		     u64 min_hit, struct callchain_param *param __used)
 {
-	__sort_chain_graph_abs(chain_root, min_hit);
-	rb_root->rb_node = chain_root->rb_root.rb_node;
+	__sort_chain_graph_abs(&chain_root->node, min_hit);
+	rb_root->rb_node = chain_root->node.rb_root.rb_node;
 }
 
 static void __sort_chain_graph_rel(struct callchain_node *node,
@@ -133,11 +136,11 @@ static void __sort_chain_graph_rel(struct callchain_node *node,
 }
 
 static void
-sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_node *chain_root,
+sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root,
 		     u64 min_hit __used, struct callchain_param *param)
 {
-	__sort_chain_graph_rel(chain_root, param->min_percent / 100.0);
-	rb_root->rb_node = chain_root->rb_root.rb_node;
+	__sort_chain_graph_rel(&chain_root->node, param->min_percent / 100.0);
+	rb_root->rb_node = chain_root->node.rb_root.rb_node;
 }
 
 int register_callchain_param(struct callchain_param *param)
@@ -284,19 +287,18 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
 }
 
 static int
-__append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start, u64 period);
+append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	     unsigned int start, u64 period);
 
 static void
-__append_chain_children(struct callchain_node *root,
-			struct resolved_chain *chain,
-			unsigned int start, u64 period)
+append_chain_children(struct callchain_node *root, struct resolved_chain *chain,
+		      unsigned int start, u64 period)
 {
 	struct callchain_node *rnode;
 
 	/* lookup in childrens */
 	chain_for_each_child(rnode, root) {
-		unsigned int ret = __append_chain(rnode, chain, start, period);
+		unsigned int ret = append_chain(rnode, chain, start, period);
 
 		if (!ret)
 			goto inc_children_hit;
@@ -309,8 +311,8 @@ inc_children_hit:
 }
 
 static int
-__append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start, u64 period)
+append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	     unsigned int start, u64 period)
 {
 	struct callchain_list *cnode;
 	unsigned int i = start;
@@ -357,7 +359,7 @@ __append_chain(struct callchain_node *root, struct resolved_chain *chain,
 	}
 
 	/* We match the node and still have a part remaining */
-	__append_chain_children(root, chain, i, period);
+	append_chain_children(root, chain, i, period);
 
 	return 0;
 }
@@ -380,8 +382,8 @@ static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
 }
 
 
-int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms, u64 period)
+int callchain_append(struct callchain_root *root, struct ip_callchain *chain,
+		     struct map_symbol *syms, u64 period)
 {
 	struct resolved_chain *filtered;
 
@@ -398,9 +400,65 @@ int append_chain(struct callchain_node *root, struct ip_callchain *chain,
 	if (!filtered->nr)
 		goto end;
 
-	__append_chain_children(root, filtered, 0, period);
+	append_chain_children(&root->node, filtered, 0, period);
+
+	if (filtered->nr > root->max_depth)
+		root->max_depth = filtered->nr;
 end:
 	free(filtered);
 
 	return 0;
 }
+
+static int
+merge_chain_branch(struct callchain_node *dst, struct callchain_node *src,
+		   struct resolved_chain *chain)
+{
+	struct callchain_node *child, *next_child;
+	struct callchain_list *list, *next_list;
+	int old_pos = chain->nr;
+	int err = 0;
+
+	list_for_each_entry_safe(list, next_list, &src->val, list) {
+		chain->ips[chain->nr].ip = list->ip;
+		chain->ips[chain->nr].ms = list->ms;
+		chain->nr++;
+		list_del(&list->list);
+		free(list);
+	}
+
+	if (src->hit)
+		append_chain_children(dst, chain, 0, src->hit);
+
+	chain_for_each_child_safe(child, next_child, src) {
+		err = merge_chain_branch(dst, child, chain);
+		if (err)
+			break;
+
+		list_del(&child->brothers);
+		free(child);
+	}
+
+	chain->nr = old_pos;
+
+	return err;
+}
+
+int callchain_merge(struct callchain_root *dst, struct callchain_root *src)
+{
+	struct resolved_chain *chain;
+	int err;
+
+	chain = malloc(sizeof(*chain) +
+		       src->max_depth * sizeof(struct resolved_ip));
+	if (!chain)
+		return -ENOMEM;
+
+	chain->nr = 0;
+
+	err = merge_chain_branch(&dst->node, &src->node, chain);
+
+	free(chain);
+
+	return err;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 6de4313924fb..c15fb8c24ad2 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -26,9 +26,14 @@ struct callchain_node {
 	u64			children_hit;
 };
 
+struct callchain_root {
+	u64			max_depth;
+	struct callchain_node	node;
+};
+
 struct callchain_param;
 
-typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_node *,
+typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
 				 u64, struct callchain_param *);
 
 struct callchain_param {
@@ -44,15 +49,16 @@ struct callchain_list {
 	struct list_head	list;
 };
 
-static inline void callchain_init(struct callchain_node *node)
+static inline void callchain_init(struct callchain_root *root)
 {
-	INIT_LIST_HEAD(&node->brothers);
-	INIT_LIST_HEAD(&node->children);
-	INIT_LIST_HEAD(&node->val);
+	INIT_LIST_HEAD(&root->node.brothers);
+	INIT_LIST_HEAD(&root->node.children);
+	INIT_LIST_HEAD(&root->node.val);
 
-	node->children_hit = 0;
-	node->parent = NULL;
-	node->hit = 0;
+	root->node.parent = NULL;
+	root->node.hit = 0;
+	root->node.children_hit = 0;
+	root->max_depth = 0;
 }
 
 static inline u64 cumul_hits(struct callchain_node *node)
@@ -61,8 +67,9 @@ static inline u64 cumul_hits(struct callchain_node *node)
 }
 
 int register_callchain_param(struct callchain_param *param);
-int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms, u64 period);
+int callchain_append(struct callchain_root *root, struct ip_callchain *chain,
+		     struct map_symbol *syms, u64 period);
+int callchain_merge(struct callchain_root *dst, struct callchain_root *src);
 
 bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event);
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index be22ae6ef055..2022e8740994 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -87,7 +87,7 @@ static void hist_entry__add_cpumode_period(struct hist_entry *self,
 
 static struct hist_entry *hist_entry__new(struct hist_entry *template)
 {
-	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_node) : 0;
+	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
 	struct hist_entry *self = malloc(sizeof(*self) + callchain_size);
 
 	if (self != NULL) {
@@ -226,6 +226,8 @@ static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
 
 		if (!cmp) {
 			iter->period += he->period;
+			if (symbol_conf.use_callchain)
+				callchain_merge(iter->callchain, he->callchain);
 			hist_entry__free(he);
 			return false;
 		}
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 58a470d036dd..bd7497711424 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -22,6 +22,7 @@ static const char *get_perf_dir(void)
 	return ".";
 }
 
+#ifdef NO_STRLCPY
 size_t strlcpy(char *dest, const char *src, size_t size)
 {
 	size_t ret = strlen(src);
@@ -33,7 +34,7 @@ size_t strlcpy(char *dest, const char *src, size_t size)
 	}
 	return ret;
 }
-
+#endif
 
 static char *get_pathname(void)
 {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 46e531d09e8b..0b91053a7d11 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -70,7 +70,7 @@ struct hist_entry {
 		struct hist_entry *pair;
 		struct rb_root	  sorted_chain;
 	};
-	struct callchain_node	callchain[0];
+	struct callchain_root	callchain[0];
 };
 
 enum sort_type {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b2f5ae97f33d..b39f499e575a 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -388,6 +388,20 @@ size_t dso__fprintf_buildid(struct dso *self, FILE *fp)
 	return fprintf(fp, "%s", sbuild_id);
 }
 
+size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp)
+{
+	size_t ret = 0;
+	struct rb_node *nd;
+	struct symbol_name_rb_node *pos;
+
+	for (nd = rb_first(&self->symbol_names[type]); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
+		fprintf(fp, "%s\n", pos->sym.name);
+	}
+
+	return ret;
+}
+
 size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
 {
 	struct rb_node *nd;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ea95c2756f05..038f2201ee09 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -182,6 +182,7 @@ size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp);
 size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits);
 
 size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
+size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp);
 size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
 
 enum dso_origin {
diff --git a/tools/perf/util/ui/browser.c b/tools/perf/util/ui/browser.c
index 66f2d583d8c4..6d0df809a2ed 100644
--- a/tools/perf/util/ui/browser.c
+++ b/tools/perf/util/ui/browser.c
@@ -1,16 +1,6 @@
-#define _GNU_SOURCE
-#include <stdio.h>
-#undef _GNU_SOURCE
-/*
- * slang versions <= 2.0.6 have a "#if HAVE_LONG_LONG" that breaks
- * the build if it isn't defined. Use the equivalent one that glibc
- * has on features.h.
- */
-#include <features.h>
-#ifndef HAVE_LONG_LONG
-#define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG
-#endif
 #include <slang.h>
+#include "libslang.h"
+#include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdlib.h>
@@ -19,17 +9,9 @@
 #include "helpline.h"
 #include "../color.h"
 #include "../util.h"
+#include <stdio.h>
 
-#if SLANG_VERSION < 20104
-#define sltt_set_color(obj, name, fg, bg) \
-	SLtt_set_color(obj,(char *)name, (char *)fg, (char *)bg)
-#else
-#define sltt_set_color SLtt_set_color
-#endif
-
-newtComponent newt_form__new(void);
-
-int ui_browser__percent_color(double percent, bool current)
+static int ui_browser__percent_color(double percent, bool current)
 {
 	if (current)
 		return HE_COLORSET_SELECTED;
@@ -40,6 +22,23 @@ int ui_browser__percent_color(double percent, bool current)
 	return HE_COLORSET_NORMAL;
 }
 
+void ui_browser__set_color(struct ui_browser *self __used, int color)
+{
+	SLsmg_set_color(color);
+}
+
+void ui_browser__set_percent_color(struct ui_browser *self,
+				   double percent, bool current)
+{
+	 int color = ui_browser__percent_color(percent, current);
+	 ui_browser__set_color(self, color);
+}
+
+void ui_browser__gotorc(struct ui_browser *self, int y, int x)
+{
+	SLsmg_gotorc(self->y + y, self->x + x);
+}
+
 void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whence)
 {
 	struct list_head *head = self->entries;
@@ -111,7 +110,7 @@ unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self)
 	nd = self->top;
 
 	while (nd != NULL) {
-		SLsmg_gotorc(self->y + row, self->x);
+		ui_browser__gotorc(self, row, 0);
 		self->write(self, nd, row);
 		if (++row == self->height)
 			break;
@@ -131,13 +130,10 @@ void ui_browser__refresh_dimensions(struct ui_browser *self)
 	int cols, rows;
 	newtGetScreenSize(&cols, &rows);
 
-	if (self->width > cols - 4)
-		self->width = cols - 4;
-	self->height = rows - 5;
-	if (self->height > self->nr_entries)
-		self->height = self->nr_entries;
-	self->y  = (rows - self->height) / 2;
-	self->x = (cols - self->width) / 2;
+	self->width = cols - 1;
+	self->height = rows - 2;
+	self->y = 1;
+	self->x = 0;
 }
 
 void ui_browser__reset_index(struct ui_browser *self)
@@ -146,34 +142,48 @@ void ui_browser__reset_index(struct ui_browser *self)
 	self->seek(self, 0, SEEK_SET);
 }
 
+void ui_browser__add_exit_key(struct ui_browser *self, int key)
+{
+	newtFormAddHotKey(self->form, key);
+}
+
+void ui_browser__add_exit_keys(struct ui_browser *self, int keys[])
+{
+	int i = 0;
+
+	while (keys[i] && i < 64) {
+		ui_browser__add_exit_key(self, keys[i]);
+		++i;
+	}
+}
+
 int ui_browser__show(struct ui_browser *self, const char *title,
 		     const char *helpline, ...)
 {
 	va_list ap;
+	int keys[] = { NEWT_KEY_UP, NEWT_KEY_DOWN, NEWT_KEY_PGUP,
+		       NEWT_KEY_PGDN, NEWT_KEY_HOME, NEWT_KEY_END, ' ',
+		       NEWT_KEY_LEFT, NEWT_KEY_ESCAPE, 'q', CTRL('c'), 0 };
 
-	if (self->form != NULL) {
+	if (self->form != NULL)
 		newtFormDestroy(self->form);
-		newtPopWindow();
-	}
+
 	ui_browser__refresh_dimensions(self);
-	newtCenteredWindow(self->width, self->height, title);
-	self->form = newt_form__new();
+	self->form = newtForm(NULL, NULL, 0);
 	if (self->form == NULL)
 		return -1;
 
-	self->sb = newtVerticalScrollbar(self->width, 0, self->height,
+	self->sb = newtVerticalScrollbar(self->width, 1, self->height,
 					 HE_COLORSET_NORMAL,
 					 HE_COLORSET_SELECTED);
 	if (self->sb == NULL)
 		return -1;
 
-	newtFormAddHotKey(self->form, NEWT_KEY_UP);
-	newtFormAddHotKey(self->form, NEWT_KEY_DOWN);
-	newtFormAddHotKey(self->form, NEWT_KEY_PGUP);
-	newtFormAddHotKey(self->form, NEWT_KEY_PGDN);
-	newtFormAddHotKey(self->form, NEWT_KEY_HOME);
-	newtFormAddHotKey(self->form, NEWT_KEY_END);
-	newtFormAddHotKey(self->form, ' ');
+	SLsmg_gotorc(0, 0);
+	ui_browser__set_color(self, NEWT_COLORSET_ROOT);
+	slsmg_write_nstring(title, self->width);
+
+	ui_browser__add_exit_keys(self, keys);
 	newtFormAddComponent(self->form, self->sb);
 
 	va_start(ap, helpline);
@@ -185,7 +195,6 @@ int ui_browser__show(struct ui_browser *self, const char *title,
 void ui_browser__hide(struct ui_browser *self)
 {
 	newtFormDestroy(self->form);
-	newtPopWindow();
 	self->form = NULL;
 	ui_helpline__pop();
 }
@@ -196,28 +205,28 @@ int ui_browser__refresh(struct ui_browser *self)
 
 	newtScrollbarSet(self->sb, self->index, self->nr_entries - 1);
 	row = self->refresh(self);
-	SLsmg_set_color(HE_COLORSET_NORMAL);
+	ui_browser__set_color(self, HE_COLORSET_NORMAL);
 	SLsmg_fill_region(self->y + row, self->x,
 			  self->height - row, self->width, ' ');
 
 	return 0;
 }
 
-int ui_browser__run(struct ui_browser *self, struct newtExitStruct *es)
+int ui_browser__run(struct ui_browser *self)
 {
+	struct newtExitStruct es;
+
 	if (ui_browser__refresh(self) < 0)
 		return -1;
 
 	while (1) {
 		off_t offset;
 
-		newtFormRun(self->form, es);
+		newtFormRun(self->form, &es);
 
-		if (es->reason != NEWT_EXIT_HOTKEY)
+		if (es.reason != NEWT_EXIT_HOTKEY)
 			break;
-		if (is_exit_key(es->u.key))
-			return es->u.key;
-		switch (es->u.key) {
+		switch (es.u.key) {
 		case NEWT_KEY_DOWN:
 			if (self->index == self->nr_entries - 1)
 				break;
@@ -274,12 +283,12 @@ int ui_browser__run(struct ui_browser *self, struct newtExitStruct *es)
 			self->seek(self, -offset, SEEK_END);
 			break;
 		default:
-			return es->u.key;
+			return es.u.key;
 		}
 		if (ui_browser__refresh(self) < 0)
 			return -1;
 	}
-	return 0;
+	return -1;
 }
 
 unsigned int ui_browser__list_head_refresh(struct ui_browser *self)
@@ -294,7 +303,7 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *self)
 	pos = self->top;
 
 	list_for_each_from(pos, head) {
-		SLsmg_gotorc(self->y + row, self->x);
+		ui_browser__gotorc(self, row, 0);
 		self->write(self, pos, row);
 		if (++row == self->height)
 			break;
diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h
index 0b9f829214f7..0dc7e4da36f5 100644
--- a/tools/perf/util/ui/browser.h
+++ b/tools/perf/util/ui/browser.h
@@ -25,16 +25,21 @@ struct ui_browser {
 };
 
 
-int ui_browser__percent_color(double percent, bool current);
+void ui_browser__set_color(struct ui_browser *self, int color);
+void ui_browser__set_percent_color(struct ui_browser *self,
+				   double percent, bool current);
 bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row);
 void ui_browser__refresh_dimensions(struct ui_browser *self);
 void ui_browser__reset_index(struct ui_browser *self);
 
+void ui_browser__gotorc(struct ui_browser *self, int y, int x);
+void ui_browser__add_exit_key(struct ui_browser *self, int key);
+void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]);
 int ui_browser__show(struct ui_browser *self, const char *title,
 		     const char *helpline, ...);
 void ui_browser__hide(struct ui_browser *self);
 int ui_browser__refresh(struct ui_browser *self);
-int ui_browser__run(struct ui_browser *self, struct newtExitStruct *es);
+int ui_browser__run(struct ui_browser *self);
 
 void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence);
 unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self);
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index a90273e63f4f..82b78f99251b 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -40,14 +40,12 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
 
 	if (ol->offset != -1) {
 		struct objdump_line_rb_node *olrb = objdump_line__rb(ol);
-		int color = ui_browser__percent_color(olrb->percent, current_entry);
-		SLsmg_set_color(color);
+		ui_browser__set_percent_color(self, olrb->percent, current_entry);
 		slsmg_printf(" %7.2f ", olrb->percent);
 		if (!current_entry)
-			SLsmg_set_color(HE_COLORSET_CODE);
+			ui_browser__set_color(self, HE_COLORSET_CODE);
 	} else {
-		int color = ui_browser__percent_color(0, current_entry);
-		SLsmg_set_color(color);
+		ui_browser__set_percent_color(self, 0, current_entry);
 		slsmg_write_nstring(" ", 9);
 	}
 
@@ -135,32 +133,31 @@ static void annotate_browser__set_top(struct annotate_browser *self,
 	self->curr_hot = nd;
 }
 
-static int annotate_browser__run(struct annotate_browser *self,
-				 struct newtExitStruct *es)
+static int annotate_browser__run(struct annotate_browser *self)
 {
 	struct rb_node *nd;
 	struct hist_entry *he = self->b.priv;
+	int key;
 
 	if (ui_browser__show(&self->b, he->ms.sym->name,
-			     "<- or ESC: exit, TAB/shift+TAB: cycle thru samples") < 0)
+			     "<-, -> or ESC: exit, TAB/shift+TAB: cycle thru samples") < 0)
 		return -1;
-
-	newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
-	newtFormAddHotKey(self->b.form, NEWT_KEY_RIGHT);
+	/*
+	 * To allow builtin-annotate to cycle thru multiple symbols by
+	 * examining the exit key for this function.
+	 */
+	ui_browser__add_exit_key(&self->b, NEWT_KEY_RIGHT);
 
 	nd = self->curr_hot;
 	if (nd) {
-		newtFormAddHotKey(self->b.form, NEWT_KEY_TAB);
-		newtFormAddHotKey(self->b.form, NEWT_KEY_UNTAB);
+		int tabs[] = { NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0 };
+		ui_browser__add_exit_keys(&self->b, tabs);
 	}
 
 	while (1) {
-		ui_browser__run(&self->b, es);
-
-		if (es->reason != NEWT_EXIT_HOTKEY)
-			break;
+		key = ui_browser__run(&self->b);
 
-		switch (es->u.key) {
+		switch (key) {
 		case NEWT_KEY_TAB:
 			nd = rb_prev(nd);
 			if (nd == NULL)
@@ -179,12 +176,11 @@ static int annotate_browser__run(struct annotate_browser *self,
 	}
 out:
 	ui_browser__hide(&self->b);
-	return es->u.key;
+	return key;
 }
 
 int hist_entry__tui_annotate(struct hist_entry *self)
 {
-	struct newtExitStruct es;
 	struct objdump_line *pos, *n;
 	struct objdump_line_rb_node *rbpos;
 	LIST_HEAD(head);
@@ -232,7 +228,7 @@ int hist_entry__tui_annotate(struct hist_entry *self)
 		annotate_browser__set_top(&browser, browser.curr_hot);
 
 	browser.b.width += 18; /* Percentage */
-	ret = annotate_browser__run(&browser, &es);
+	ret = annotate_browser__run(&browser);
 	list_for_each_entry_safe(pos, n, &head, node) {
 		list_del(&pos->node);
 		objdump_line__free(pos);
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 6866aa4c41e0..ebda8c3fde9e 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -58,6 +58,11 @@ static char callchain_list__folded(const struct callchain_list *self)
 	return map_symbol__folded(&self->ms);
 }
 
+static void map_symbol__set_folding(struct map_symbol *self, bool unfold)
+{
+	self->unfolded = unfold ? self->has_children : false;
+}
+
 static int callchain_node__count_rows_rb_tree(struct callchain_node *self)
 {
 	int n = 0;
@@ -129,16 +134,16 @@ static void callchain_node__init_have_children_rb_tree(struct callchain_node *se
 	for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) {
 		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
 		struct callchain_list *chain;
-		int first = true;
+		bool first = true;
 
 		list_for_each_entry(chain, &child->val, list) {
 			if (first) {
 				first = false;
 				chain->ms.has_children = chain->list.next != &child->val ||
-							 rb_first(&child->rb_root) != NULL;
+							 !RB_EMPTY_ROOT(&child->rb_root);
 			} else
 				chain->ms.has_children = chain->list.next == &child->val &&
-							 rb_first(&child->rb_root) != NULL;
+							 !RB_EMPTY_ROOT(&child->rb_root);
 		}
 
 		callchain_node__init_have_children_rb_tree(child);
@@ -150,7 +155,7 @@ static void callchain_node__init_have_children(struct callchain_node *self)
 	struct callchain_list *chain;
 
 	list_for_each_entry(chain, &self->val, list)
-		chain->ms.has_children = rb_first(&self->rb_root) != NULL;
+		chain->ms.has_children = !RB_EMPTY_ROOT(&self->rb_root);
 
 	callchain_node__init_have_children_rb_tree(self);
 }
@@ -168,6 +173,7 @@ static void callchain__init_have_children(struct rb_root *self)
 static void hist_entry__init_have_children(struct hist_entry *self)
 {
 	if (!self->init_have_children) {
+		self->ms.has_children = !RB_EMPTY_ROOT(&self->sorted_chain);
 		callchain__init_have_children(&self->sorted_chain);
 		self->init_have_children = true;
 	}
@@ -195,43 +201,114 @@ static bool hist_browser__toggle_fold(struct hist_browser *self)
 	return false;
 }
 
-static int hist_browser__run(struct hist_browser *self, const char *title,
-			     struct newtExitStruct *es)
+static int callchain_node__set_folding_rb_tree(struct callchain_node *self, bool unfold)
+{
+	int n = 0;
+	struct rb_node *nd;
+
+	for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) {
+		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
+		struct callchain_list *chain;
+		bool has_children = false;
+
+		list_for_each_entry(chain, &child->val, list) {
+			++n;
+			map_symbol__set_folding(&chain->ms, unfold);
+			has_children = chain->ms.has_children;
+		}
+
+		if (has_children)
+			n += callchain_node__set_folding_rb_tree(child, unfold);
+	}
+
+	return n;
+}
+
+static int callchain_node__set_folding(struct callchain_node *node, bool unfold)
+{
+	struct callchain_list *chain;
+	bool has_children = false;
+	int n = 0;
+
+	list_for_each_entry(chain, &node->val, list) {
+		++n;
+		map_symbol__set_folding(&chain->ms, unfold);
+		has_children = chain->ms.has_children;
+	}
+
+	if (has_children)
+		n += callchain_node__set_folding_rb_tree(node, unfold);
+
+	return n;
+}
+
+static int callchain__set_folding(struct rb_root *chain, bool unfold)
+{
+	struct rb_node *nd;
+	int n = 0;
+
+	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
+		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+		n += callchain_node__set_folding(node, unfold);
+	}
+
+	return n;
+}
+
+static void hist_entry__set_folding(struct hist_entry *self, bool unfold)
+{
+	hist_entry__init_have_children(self);
+	map_symbol__set_folding(&self->ms, unfold);
+
+	if (self->ms.has_children) {
+		int n = callchain__set_folding(&self->sorted_chain, unfold);
+		self->nr_rows = unfold ? n : 0;
+	} else
+		self->nr_rows = 0;
+}
+
+static void hists__set_folding(struct hists *self, bool unfold)
+{
+	struct rb_node *nd;
+
+	self->nr_entries = 0;
+
+	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+		hist_entry__set_folding(he, unfold);
+		self->nr_entries += 1 + he->nr_rows;
+	}
+}
+
+static void hist_browser__set_folding(struct hist_browser *self, bool unfold)
+{
+	hists__set_folding(self->hists, unfold);
+	self->b.nr_entries = self->hists->nr_entries;
+	/* Go to the start, we may be way after valid entries after a collapse */
+	ui_browser__reset_index(&self->b);
+}
+
+static int hist_browser__run(struct hist_browser *self, const char *title)
 {
-	char str[256], unit;
-	unsigned long nr_events = self->hists->stats.nr_events[PERF_RECORD_SAMPLE];
+	int key;
+	int exit_keys[] = { 'a', '?', 'h', 'C', 'd', 'D', 'E', 't',
+			    NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT, 0, };
 
 	self->b.entries = &self->hists->entries;
 	self->b.nr_entries = self->hists->nr_entries;
 
 	hist_browser__refresh_dimensions(self);
 
-	nr_events = convert_unit(nr_events, &unit);
-	snprintf(str, sizeof(str), "Events: %lu%c                            ",
-		 nr_events, unit);
-	newtDrawRootText(0, 0, str);
-
 	if (ui_browser__show(&self->b, title,
 			     "Press '?' for help on key bindings") < 0)
 		return -1;
 
-	newtFormAddHotKey(self->b.form, 'a');
-	newtFormAddHotKey(self->b.form, '?');
-	newtFormAddHotKey(self->b.form, 'h');
-	newtFormAddHotKey(self->b.form, 'd');
-	newtFormAddHotKey(self->b.form, 'D');
-	newtFormAddHotKey(self->b.form, 't');
-
-	newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
-	newtFormAddHotKey(self->b.form, NEWT_KEY_RIGHT);
-	newtFormAddHotKey(self->b.form, NEWT_KEY_ENTER);
+	ui_browser__add_exit_keys(&self->b, exit_keys);
 
 	while (1) {
-		ui_browser__run(&self->b, es);
+		key = ui_browser__run(&self->b);
 
-		if (es->reason != NEWT_EXIT_HOTKEY)
-			break;
-		switch (es->u.key) {
+		switch (key) {
 		case 'D': { /* Debug */
 			static int seq;
 			struct hist_entry *h = rb_entry(self->b.top,
@@ -245,18 +322,26 @@ static int hist_browser__run(struct hist_browser *self, const char *title,
 					   self->b.top_idx,
 					   h->row_offset, h->nr_rows);
 		}
-			continue;
+			break;
+		case 'C':
+			/* Collapse the whole world. */
+			hist_browser__set_folding(self, false);
+			break;
+		case 'E':
+			/* Expand the whole world. */
+			hist_browser__set_folding(self, true);
+			break;
 		case NEWT_KEY_ENTER:
 			if (hist_browser__toggle_fold(self))
 				break;
 			/* fall thru */
 		default:
-			return 0;
+			goto out;
 		}
 	}
-
+out:
 	ui_browser__hide(&self->b);
-	return 0;
+	return key;
 }
 
 static char *callchain_list__sym_name(struct callchain_list *self,
@@ -306,15 +391,10 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self,
 			int color;
 			bool was_first = first;
 
-			if (first) {
+			if (first)
 				first = false;
-				chain->ms.has_children = chain->list.next != &child->val ||
-							 rb_first(&child->rb_root) != NULL;
-			} else {
+			else
 				extra_offset = LEVEL_OFFSET_STEP;
-				chain->ms.has_children = chain->list.next == &child->val &&
-							 rb_first(&child->rb_root) != NULL;
-			}
 
 			folded_sign = callchain_list__folded(chain);
 			if (*row_offset != 0) {
@@ -341,8 +421,8 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self,
 				*is_current_entry = true;
 			}
 
-			SLsmg_set_color(color);
-			SLsmg_gotorc(self->b.y + row, self->b.x);
+			ui_browser__set_color(&self->b, color);
+			ui_browser__gotorc(&self->b, row, 0);
 			slsmg_write_nstring(" ", offset + extra_offset);
 			slsmg_printf("%c ", folded_sign);
 			slsmg_write_nstring(str, width);
@@ -384,12 +464,7 @@ static int hist_browser__show_callchain_node(struct hist_browser *self,
 	list_for_each_entry(chain, &node->val, list) {
 		char ipstr[BITS_PER_LONG / 4 + 1], *s;
 		int color;
-		/*
-		 * FIXME: This should be moved to somewhere else,
-		 * probably when the callchain is created, so as not to
-		 * traverse it all over again
-		 */
-		chain->ms.has_children = rb_first(&node->rb_root) != NULL;
+
 		folded_sign = callchain_list__folded(chain);
 
 		if (*row_offset != 0) {
@@ -405,8 +480,8 @@ static int hist_browser__show_callchain_node(struct hist_browser *self,
 		}
 
 		s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
-		SLsmg_gotorc(self->b.y + row, self->b.x);
-		SLsmg_set_color(color);
+		ui_browser__gotorc(&self->b, row, 0);
+		ui_browser__set_color(&self->b, color);
 		slsmg_write_nstring(" ", offset);
 		slsmg_printf("%c ", folded_sign);
 		slsmg_write_nstring(s, width - 2);
@@ -465,7 +540,7 @@ static int hist_browser__show_entry(struct hist_browser *self,
 	}
 
 	if (symbol_conf.use_callchain) {
-		entry->ms.has_children = !RB_EMPTY_ROOT(&entry->sorted_chain);
+		hist_entry__init_have_children(entry);
 		folded_sign = hist_entry__folded(entry);
 	}
 
@@ -484,8 +559,8 @@ static int hist_browser__show_entry(struct hist_browser *self,
 				color = HE_COLORSET_NORMAL;
 		}
 
-		SLsmg_set_color(color);
-		SLsmg_gotorc(self->b.y + row, self->b.x);
+		ui_browser__set_color(&self->b, color);
+		ui_browser__gotorc(&self->b, row, 0);
 		if (symbol_conf.use_callchain) {
 			slsmg_printf("%c ", folded_sign);
 			width -= 2;
@@ -687,8 +762,6 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
 
 static void hist_browser__delete(struct hist_browser *self)
 {
-	newtFormDestroy(self->b.form);
-	newtPopWindow();
 	free(self);
 }
 
@@ -702,21 +775,26 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *self)
 	return self->he_selection->thread;
 }
 
-static int hist_browser__title(char *bf, size_t size, const char *ev_name,
-			       const struct dso *dso, const struct thread *thread)
+static int hists__browser_title(struct hists *self, char *bf, size_t size,
+				const char *ev_name, const struct dso *dso,
+				const struct thread *thread)
 {
-	int printed = 0;
+	char unit;
+	int printed;
+	unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE];
+
+	nr_events = convert_unit(nr_events, &unit);
+	printed = snprintf(bf, size, "Events: %lu%c %s", nr_events, unit, ev_name);
 
 	if (thread)
 		printed += snprintf(bf + printed, size - printed,
-				    "Thread: %s(%d)",
-				    (thread->comm_set ?  thread->comm : ""),
+				    ", Thread: %s(%d)",
+				    (thread->comm_set ? thread->comm : ""),
 				    thread->pid);
 	if (dso)
 		printed += snprintf(bf + printed, size - printed,
-				    "%sDSO: %s", thread ? " " : "",
-				    dso->short_name);
-	return printed ?: snprintf(bf, size, "Event: %s", ev_name);
+				    ", DSO: %s", dso->short_name);
+	return printed;
 }
 
 int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
@@ -725,7 +803,6 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 	struct pstack *fstack;
 	const struct thread *thread_filter = NULL;
 	const struct dso *dso_filter = NULL;
-	struct newtExitStruct es;
 	char msg[160];
 	int key = -1;
 
@@ -738,9 +815,8 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 
 	ui_helpline__push(helpline);
 
-	hist_browser__title(msg, sizeof(msg), ev_name,
-			    dso_filter, thread_filter);
-
+	hists__browser_title(self, msg, sizeof(msg), ev_name,
+			     dso_filter, thread_filter);
 	while (1) {
 		const struct thread *thread;
 		const struct dso *dso;
@@ -749,70 +825,63 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 		    annotate = -2, zoom_dso = -2, zoom_thread = -2,
 		    browse_map = -2;
 
-		if (hist_browser__run(browser, msg, &es))
-			break;
+		key = hist_browser__run(browser, msg);
 
 		thread = hist_browser__selected_thread(browser);
 		dso = browser->selection->map ? browser->selection->map->dso : NULL;
 
-		if (es.reason == NEWT_EXIT_HOTKEY) {
-			key = es.u.key;
-
-			switch (key) {
-			case NEWT_KEY_F1:
-				goto do_help;
-			case NEWT_KEY_TAB:
-			case NEWT_KEY_UNTAB:
-				/*
-				 * Exit the browser, let hists__browser_tree
-				 * go to the next or previous
-				 */
-				goto out_free_stack;
-			default:;
-			}
-
-			switch (key) {
-			case 'a':
-				if (browser->selection->map == NULL ||
-				    browser->selection->map->dso->annotate_warned)
-					continue;
-				goto do_annotate;
-			case 'd':
-				goto zoom_dso;
-			case 't':
-				goto zoom_thread;
-			case 'h':
-			case '?':
-do_help:
-				ui__help_window("->        Zoom into DSO/Threads & Annotate current symbol\n"
-						"<-        Zoom out\n"
-						"a         Annotate current symbol\n"
-						"h/?/F1    Show this window\n"
-						"d         Zoom into current DSO\n"
-						"t         Zoom into current Thread\n"
-						"q/CTRL+C  Exit browser");
+		switch (key) {
+		case NEWT_KEY_TAB:
+		case NEWT_KEY_UNTAB:
+			/*
+			 * Exit the browser, let hists__browser_tree
+			 * go to the next or previous
+			 */
+			goto out_free_stack;
+		case 'a':
+			if (browser->selection->map == NULL &&
+			    browser->selection->map->dso->annotate_warned)
 				continue;
-			default:;
-			}
-			if (is_exit_key(key)) {
-				if (key == NEWT_KEY_ESCAPE &&
-				    !ui__dialog_yesno("Do you really want to exit?"))
-					continue;
-				break;
-			}
-
-			if (es.u.key == NEWT_KEY_LEFT) {
-				const void *top;
+			goto do_annotate;
+		case 'd':
+			goto zoom_dso;
+		case 't':
+			goto zoom_thread;
+		case NEWT_KEY_F1:
+		case 'h':
+		case '?':
+			ui__help_window("->        Zoom into DSO/Threads & Annotate current symbol\n"
+					"<-        Zoom out\n"
+					"a         Annotate current symbol\n"
+					"h/?/F1    Show this window\n"
+					"C         Collapse all callchains\n"
+					"E         Expand all callchains\n"
+					"d         Zoom into current DSO\n"
+					"t         Zoom into current Thread\n"
+					"q/CTRL+C  Exit browser");
+			continue;
+		case NEWT_KEY_ENTER:
+		case NEWT_KEY_RIGHT:
+			/* menu */
+			break;
+		case NEWT_KEY_LEFT: {
+			const void *top;
 
-				if (pstack__empty(fstack))
-					continue;
-				top = pstack__pop(fstack);
-				if (top == &dso_filter)
-					goto zoom_out_dso;
-				if (top == &thread_filter)
-					goto zoom_out_thread;
+			if (pstack__empty(fstack))
 				continue;
-			}
+			top = pstack__pop(fstack);
+			if (top == &dso_filter)
+				goto zoom_out_dso;
+			if (top == &thread_filter)
+				goto zoom_out_thread;
+			continue;
+		}
+		case NEWT_KEY_ESCAPE:
+			if (!ui__dialog_yesno("Do you really want to exit?"))
+				continue;
+			/* Fall thru */
+		default:
+			goto out_free_stack;
 		}
 
 		if (browser->selection->sym != NULL &&
@@ -885,8 +954,8 @@ zoom_out_dso:
 				pstack__push(fstack, &dso_filter);
 			}
 			hists__filter_by_dso(self, dso_filter);
-			hist_browser__title(msg, sizeof(msg), ev_name,
-					    dso_filter, thread_filter);
+			hists__browser_title(self, msg, sizeof(msg), ev_name,
+					     dso_filter, thread_filter);
 			hist_browser__reset(browser);
 		} else if (choice == zoom_thread) {
 zoom_thread:
@@ -903,8 +972,8 @@ zoom_out_thread:
 				pstack__push(fstack, &thread_filter);
 			}
 			hists__filter_by_thread(self, thread_filter);
-			hist_browser__title(msg, sizeof(msg), ev_name,
-					    dso_filter, thread_filter);
+			hists__browser_title(self, msg, sizeof(msg), ev_name,
+					     dso_filter, thread_filter);
 			hist_browser__reset(browser);
 		}
 	}
@@ -925,10 +994,6 @@ int hists__tui_browse_tree(struct rb_root *self, const char *help)
 		const char *ev_name = __event_name(hists->type, hists->config);
 
 		key = hists__browse(hists, help, ev_name);
-
-		if (is_exit_key(key))
-			break;
-
 		switch (key) {
 		case NEWT_KEY_TAB:
 			next = rb_next(nd);
@@ -940,7 +1005,7 @@ int hists__tui_browse_tree(struct rb_root *self, const char *help)
 				continue;
 			nd = rb_prev(nd);
 		default:
-			break;
+			return key;
 		}
 	}
 
diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c
index 142b825b42bf..e35437dfa5b4 100644
--- a/tools/perf/util/ui/browsers/map.c
+++ b/tools/perf/util/ui/browsers/map.c
@@ -1,6 +1,5 @@
 #include "../libslang.h"
 #include <elf.h>
-#include <newt.h>
 #include <sys/ttydefaults.h>
 #include <ctype.h>
 #include <string.h>
@@ -47,7 +46,6 @@ out_free_form:
 struct map_browser {
 	struct ui_browser b;
 	struct map	  *map;
-	u16		  namelen;
 	u8		  addrlen;
 };
 
@@ -56,14 +54,16 @@ static void map_browser__write(struct ui_browser *self, void *nd, int row)
 	struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
 	struct map_browser *mb = container_of(self, struct map_browser, b);
 	bool current_entry = ui_browser__is_current_entry(self, row);
-	int color = ui_browser__percent_color(0, current_entry);
+	int width;
 
-	SLsmg_set_color(color);
+	ui_browser__set_percent_color(self, 0, current_entry);
 	slsmg_printf("%*llx %*llx %c ",
 		     mb->addrlen, sym->start, mb->addrlen, sym->end,
 		     sym->binding == STB_GLOBAL ? 'g' :
 		     sym->binding == STB_LOCAL  ? 'l' : 'w');
-	slsmg_write_nstring(sym->name, mb->namelen);
+	width = self->width - ((mb->addrlen * 2) + 4);
+	if (width > 0)
+		slsmg_write_nstring(sym->name, width);
 }
 
 /* FIXME uber-kludgy, see comment on cmd_report... */
@@ -98,31 +98,29 @@ static int map_browser__search(struct map_browser *self)
 	return 0;
 }
 
-static int map_browser__run(struct map_browser *self, struct newtExitStruct *es)
+static int map_browser__run(struct map_browser *self)
 {
+	int key;
+
 	if (ui_browser__show(&self->b, self->map->dso->long_name,
 			     "Press <- or ESC to exit, %s / to search",
 			     verbose ? "" : "restart with -v to use") < 0)
 		return -1;
 
-	newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
-	newtFormAddHotKey(self->b.form, NEWT_KEY_ENTER);
 	if (verbose)
-		newtFormAddHotKey(self->b.form, '/');
+		ui_browser__add_exit_key(&self->b, '/');
 
 	while (1) {
-		ui_browser__run(&self->b, es);
+		key = ui_browser__run(&self->b);
 
-		if (es->reason != NEWT_EXIT_HOTKEY)
-			break;
-		if (verbose && es->u.key == '/')
+		if (verbose && key == '/')
 			map_browser__search(self);
 		else
 			break;
 	}
 
 	ui_browser__hide(&self->b);
-	return 0;
+	return key;
 }
 
 int map__browse(struct map *self)
@@ -136,7 +134,6 @@ int map__browse(struct map *self)
 		},
 		.map = self,
 	};
-	struct newtExitStruct es;
 	struct rb_node *nd;
 	char tmp[BITS_PER_LONG / 4];
 	u64 maxaddr = 0;
@@ -144,8 +141,6 @@ int map__browse(struct map *self)
 	for (nd = rb_first(mb.b.entries); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 
-		if (mb.namelen < pos->namelen)
-			mb.namelen = pos->namelen;
 		if (maxaddr < pos->end)
 			maxaddr = pos->end;
 		if (verbose) {
@@ -156,6 +151,5 @@ int map__browse(struct map *self)
 	}
 
 	mb.addrlen = snprintf(tmp, sizeof(tmp), "%llx", maxaddr);
-	mb.b.width += mb.addrlen * 2 + 4 + mb.namelen;
-	return map_browser__run(&mb, &es);
+	return map_browser__run(&mb);
 }
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 04600e26ceea..9706d9d40279 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -11,8 +11,6 @@
 #include "helpline.h"
 #include "util.h"
 
-newtComponent newt_form__new(void);
-
 static void newt_form__set_exit_keys(newtComponent self)
 {
 	newtFormAddHotKey(self, NEWT_KEY_LEFT);
@@ -22,7 +20,7 @@ static void newt_form__set_exit_keys(newtComponent self)
 	newtFormAddHotKey(self, CTRL('c'));
 }
 
-newtComponent newt_form__new(void)
+static newtComponent newt_form__new(void)
 {
 	newtComponent self = newtForm(NULL, NULL, 0);
 	if (self)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index f380fed74359..7562707ddd1c 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -266,19 +266,6 @@ bool strglobmatch(const char *str, const char *pat);
 bool strlazymatch(const char *str, const char *pat);
 unsigned long convert_unit(unsigned long value, char *unit);
 
-#ifndef ESC
-#define ESC 27
-#endif
-
-static inline bool is_exit_key(int key)
-{
-	char up;
-	if (key == CTRL('c') || key == ESC)
-		return true;
-	up = toupper(key);
-	return up == 'Q';
-}
-
 #define _STR(x) #x
 #define STR(x) _STR(x)