Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Kernel improvements:

   - watchdog driver improvements by Li Zefan
   - Power7 CPI stack events related improvements by Sukadev Bhattiprolu
   - event multiplexing via hrtimers and other improvements by Stephane
     Eranian
   - kernel stack use optimization by Andrew Hunter
   - AMD IOMMU uncore PMU support by Suravee Suthikulpanit
   - NMI handling rate-limits by Dave Hansen
   - various hw_breakpoint fixes by Oleg Nesterov
   - hw_breakpoint overflow period sampling and related signal handling
     fixes by Jiri Olsa
   - Intel Haswell PMU support by Andi Kleen

  Tooling improvements:

   - Reset SIGTERM handler in workload child process, fix from David
     Ahern.
   - Makefile reorganization, prep work for Kconfig patches, from Jiri
     Olsa.
   - Add automated make test suite, from Jiri Olsa.
   - Add --percent-limit option to 'top' and 'report', from Namhyung
     Kim.
   - Sorting improvements, from Namhyung Kim.
   - Expand definition of sysfs format attribute, from Michael Ellerman.

  Tooling fixes:

   - 'perf tests' fixes from Jiri Olsa.
   - Make Power7 CPI stack events available in sysfs, from Sukadev
     Bhattiprolu.
   - Handle death by SIGTERM in 'perf record', fix from David Ahern.
   - Fix printing of perf_event_paranoid message, from David Ahern.
   - Handle realloc failures in 'perf kvm', from David Ahern.
   - Fix divide by 0 in variance, from David Ahern.
   - Save parent pid in thread struct, from David Ahern.
   - Handle JITed code in shared memory, from Andi Kleen.
   - Fixes for 'perf diff', from Jiri Olsa.
   - Remove some unused struct members, from Jiri Olsa.
   - Add missing liblk.a dependency for python/perf.so, fix from Jiri
     Olsa.
   - Respect CROSS_COMPILE in liblk.a, from Rabin Vincent.
   - No need to do locking when adding hists in perf report, only 'top'
     needs that, from Namhyung Kim.
   - Fix alignment of symbol column in in the hists browser (top,
     report) when -v is given, from NAmhyung Kim.
   - Fix 'perf top' -E option behavior, from Namhyung Kim.
   - Fix bug in isupper() and islower(), from Sukadev Bhattiprolu.
   - Fix compile errors in bp_signal 'perf test', from Sukadev
     Bhattiprolu.

  ... and more things"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (102 commits)
  perf/x86: Disable PEBS-LL in intel_pmu_pebs_disable()
  perf/x86: Fix shared register mutual exclusion enforcement
  perf/x86/intel: Support full width counting
  x86: Add NMI duration tracepoints
  perf: Drop sample rate when sampling is too slow
  x86: Warn when NMI handlers take large amounts of time
  hw_breakpoint: Introduce "struct bp_cpuinfo"
  hw_breakpoint: Simplify *register_wide_hw_breakpoint()
  hw_breakpoint: Introduce cpumask_of_bp()
  hw_breakpoint: Simplify the "weight" usage in toggle_bp_slot() paths
  hw_breakpoint: Simplify list/idx mess in toggle_bp_slot() paths
  perf/x86/intel: Add mem-loads/stores support for Haswell
  perf/x86/intel: Support Haswell/v4 LBR format
  perf/x86/intel: Move NMI clearing to end of PMI handler
  perf/x86/intel: Add Haswell PEBS support
  perf/x86/intel: Add simple Haswell PMU support
  perf/x86/intel: Add Haswell PEBS record support
  perf/x86/intel: Fix sparse warning
  perf/x86/amd: AMD IOMMU Performance Counter PERF uncore PMU implementation
  perf/x86/amd: Add IOMMU Performance Counter resource management
  ...

17 files changed, 1027 insertions, 115 deletions

diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index cf1a471a18a..bccfca68430 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -34,8 +34,6 @@
 #include <asm/sys_ia32.h>
 #include <asm/smap.h>
 
-#define FIX_EFLAGS	__FIX_EFLAGS
-
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 {
 	int err = 0;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 57cb6340221..8249df45d2f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -29,6 +29,9 @@
 #define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
 
+#define HSW_IN_TX					(1ULL << 32)
+#define HSW_IN_TX_CHECKPOINTED				(1ULL << 33)
+
 #define AMD64_EVENTSEL_INT_CORE_ENABLE			(1ULL << 36)
 #define AMD64_EVENTSEL_GUESTONLY			(1ULL << 40)
 #define AMD64_EVENTSEL_HOSTONLY				(1ULL << 41)
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
index beff97f7df3..7a958164088 100644
--- a/arch/x86/include/asm/sighandling.h
+++ b/arch/x86/include/asm/sighandling.h
@@ -7,10 +7,10 @@
 
 #include <asm/processor-flags.h>
 
-#define __FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
+#define FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
 			 X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
 			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
-			 X86_EFLAGS_CF)
+			 X86_EFLAGS_CF | X86_EFLAGS_RF)
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
 
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 2af848dfa75..bb0465090ae 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -170,6 +170,9 @@
 #define MSR_KNC_EVNTSEL0               0x00000028
 #define MSR_KNC_EVNTSEL1               0x00000029
 
+/* Alternative perfctr range with full access. */
+#define MSR_IA32_PMC0			0x000004c1
+
 /* AMD64 MSRs. Not complete. See the architecture manual for a more
    complete list. */
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index b0684e4a73a..47b56a7e99c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -31,11 +31,15 @@ obj-$(CONFIG_PERF_EVENTS)		+= perf_event.o
 
 ifdef CONFIG_PERF_EVENTS
 obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd.o perf_event_amd_uncore.o
+ifdef CONFIG_AMD_IOMMU
+obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd_iommu.o
+endif
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o
 endif
 
+
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 1025f3c99d2..9e581c5cf6d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -403,7 +403,8 @@ int x86_pmu_hw_config(struct perf_event *event)
 		 * check that PEBS LBR correction does not conflict with
 		 * whatever the user is asking with attr->branch_sample_type
 		 */
-		if (event->attr.precise_ip > 1) {
+		if (event->attr.precise_ip > 1 &&
+		    x86_pmu.intel_cap.pebs_format < 2) {
 			u64 *br_type = &event->attr.branch_sample_type;
 
 			if (has_branch_stack(event)) {
@@ -568,7 +569,7 @@ struct sched_state {
 struct perf_sched {
 	int			max_weight;
 	int			max_events;
-	struct event_constraint	**constraints;
+	struct perf_event	**events;
 	struct sched_state	state;
 	int			saved_states;
 	struct sched_state	saved[SCHED_STATES_MAX];
@@ -577,7 +578,7 @@ struct perf_sched {
 /*
  * Initialize interator that runs through all events and counters.
  */
-static void perf_sched_init(struct perf_sched *sched, struct event_constraint **c,
+static void perf_sched_init(struct perf_sched *sched, struct perf_event **events,
 			    int num, int wmin, int wmax)
 {
 	int idx;
@@ -585,10 +586,10 @@ static void perf_sched_init(struct perf_sched *sched, struct event_constraint **
 	memset(sched, 0, sizeof(*sched));
 	sched->max_events	= num;
 	sched->max_weight	= wmax;
-	sched->constraints	= c;
+	sched->events		= events;
 
 	for (idx = 0; idx < num; idx++) {
-		if (c[idx]->weight == wmin)
+		if (events[idx]->hw.constraint->weight == wmin)
 			break;
 	}
 
@@ -635,8 +636,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
 	if (sched->state.event >= sched->max_events)
 		return false;
 
-	c = sched->constraints[sched->state.event];
-
+	c = sched->events[sched->state.event]->hw.constraint;
 	/* Prefer fixed purpose counters */
 	if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
 		idx = INTEL_PMC_IDX_FIXED;
@@ -694,7 +694,7 @@ static bool perf_sched_next_event(struct perf_sched *sched)
 			if (sched->state.weight > sched->max_weight)
 				return false;
 		}
-		c = sched->constraints[sched->state.event];
+		c = sched->events[sched->state.event]->hw.constraint;
 	} while (c->weight != sched->state.weight);
 
 	sched->state.counter = 0;	/* start with first counter */
@@ -705,12 +705,12 @@ static bool perf_sched_next_event(struct perf_sched *sched)
 /*
  * Assign a counter for each event.
  */
-int perf_assign_events(struct event_constraint **constraints, int n,
+int perf_assign_events(struct perf_event **events, int n,
 			int wmin, int wmax, int *assign)
 {
 	struct perf_sched sched;
 
-	perf_sched_init(&sched, constraints, n, wmin, wmax);
+	perf_sched_init(&sched, events, n, wmin, wmax);
 
 	do {
 		if (!perf_sched_find_counter(&sched))
@@ -724,16 +724,19 @@ int perf_assign_events(struct event_constraint **constraints, int n,
 
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 {
-	struct event_constraint *c, *constraints[X86_PMC_IDX_MAX];
+	struct event_constraint *c;
 	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	struct perf_event *e;
 	int i, wmin, wmax, num = 0;
 	struct hw_perf_event *hwc;
 
 	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
 
 	for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
+		hwc = &cpuc->event_list[i]->hw;
 		c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
-		constraints[i] = c;
+		hwc->constraint = c;
+
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
 	}
@@ -743,7 +746,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	 */
 	for (i = 0; i < n; i++) {
 		hwc = &cpuc->event_list[i]->hw;
-		c = constraints[i];
+		c = hwc->constraint;
 
 		/* never assigned */
 		if (hwc->idx == -1)
@@ -764,16 +767,35 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 
 	/* slow path */
 	if (i != n)
-		num = perf_assign_events(constraints, n, wmin, wmax, assign);
+		num = perf_assign_events(cpuc->event_list, n, wmin,
+					 wmax, assign);
 
 	/*
+	 * Mark the event as committed, so we do not put_constraint()
+	 * in case new events are added and fail scheduling.
+	 */
+	if (!num && assign) {
+		for (i = 0; i < n; i++) {
+			e = cpuc->event_list[i];
+			e->hw.flags |= PERF_X86_EVENT_COMMITTED;
+		}
+	}
+	/*
 	 * scheduling failed or is just a simulation,
 	 * free resources if necessary
 	 */
 	if (!assign || num) {
 		for (i = 0; i < n; i++) {
+			e = cpuc->event_list[i];
+			/*
+			 * do not put_constraint() on comitted events,
+			 * because they are good to go
+			 */
+			if ((e->hw.flags & PERF_X86_EVENT_COMMITTED))
+				continue;
+
 			if (x86_pmu.put_event_constraints)
-				x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
+				x86_pmu.put_event_constraints(cpuc, e);
 		}
 	}
 	return num ? -EINVAL : 0;
@@ -1153,6 +1175,11 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	int i;
 
 	/*
+	 * event is descheduled
+	 */
+	event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
+
+	/*
 	 * If we're called during a txn, we don't need to do anything.
 	 * The events never got scheduled and ->cancel_txn will truncate
 	 * the event_list.
@@ -1249,10 +1276,20 @@ void perf_events_lapic_init(void)
 static int __kprobes
 perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
+	int ret;
+	u64 start_clock;
+	u64 finish_clock;
+
 	if (!atomic_read(&active_events))
 		return NMI_DONE;
 
-	return x86_pmu.handle_irq(regs);
+	start_clock = local_clock();
+	ret = x86_pmu.handle_irq(regs);
+	finish_clock = local_clock();
+
+	perf_sample_event_took(finish_clock - start_clock);
+
+	return ret;
 }
 
 struct event_constraint emptyconstraint;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index ba9aadfa683..97e557bc4c9 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -63,10 +63,12 @@ struct event_constraint {
 	int	flags;
 };
 /*
- * struct event_constraint flags
+ * struct hw_perf_event.flags flags
  */
 #define PERF_X86_EVENT_PEBS_LDLAT	0x1 /* ld+ldlat data address sampling */
 #define PERF_X86_EVENT_PEBS_ST		0x2 /* st data address sampling */
+#define PERF_X86_EVENT_PEBS_ST_HSW	0x4 /* haswell style st data sampling */
+#define PERF_X86_EVENT_COMMITTED	0x8 /* event passed commit_txn */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -227,11 +229,14 @@ struct cpu_hw_events {
  *  - inv
  *  - edge
  *  - cnt-mask
+ *  - in_tx
+ *  - in_tx_checkpointed
  *  The other filters are supported by fixed counters.
  *  The any-thread option is supported starting with v3.
  */
+#define FIXED_EVENT_FLAGS (X86_RAW_EVENT_MASK|HSW_IN_TX|HSW_IN_TX_CHECKPOINTED)
 #define FIXED_EVENT_CONSTRAINT(c, n)	\
-	EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK)
+	EVENT_CONSTRAINT(c, (1ULL << (32+n)), FIXED_EVENT_FLAGS)
 
 /*
  * Constraint on the Event code + UMask
@@ -247,6 +252,11 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
 
+/* DataLA version of store sampling without extra enable bit. */
+#define INTEL_PST_HSW_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
+
 #define EVENT_CONSTRAINT_END		\
 	EVENT_CONSTRAINT(0, 0, 0)
 
@@ -301,6 +311,11 @@ union perf_capabilities {
 		u64	pebs_arch_reg:1;
 		u64	pebs_format:4;
 		u64	smm_freeze:1;
+		/*
+		 * PMU supports separate counter range for writing
+		 * values > 32bit.
+		 */
+		u64	full_width_write:1;
 	};
 	u64	capabilities;
 };
@@ -375,6 +390,7 @@ struct x86_pmu {
 	struct event_constraint *event_constraints;
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
+	bool		late_ack;
 
 	/*
 	 * sysfs attrs
@@ -528,7 +544,7 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 
 void x86_pmu_enable_all(int added);
 
-int perf_assign_events(struct event_constraint **constraints, int n,
+int perf_assign_events(struct perf_event **events, int n,
 			int wmin, int wmax, int *assign);
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
 
@@ -633,6 +649,8 @@ extern struct event_constraint intel_snb_pebs_event_constraints[];
 
 extern struct event_constraint intel_ivb_pebs_event_constraints[];
 
+extern struct event_constraint intel_hsw_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_enable(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 7e28d9467bb..4cbe03287b0 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -648,48 +648,48 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.cpu_dead		= amd_pmu_cpu_dead,
 };
 
-static int setup_event_constraints(void)
+static int __init amd_core_pmu_init(void)
 {
-	if (boot_cpu_data.x86 == 0x15)
+	if (!cpu_has_perfctr_core)
+		return 0;
+
+	switch (boot_cpu_data.x86) {
+	case 0x15:
+		pr_cont("Fam15h ");
 		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
-	return 0;
-}
+		break;
 
-static int setup_perfctr_core(void)
-{
-	if (!cpu_has_perfctr_core) {
-		WARN(x86_pmu.get_event_constraints == amd_get_event_constraints_f15h,
-		     KERN_ERR "Odd, counter constraints enabled but no core perfctrs detected!");
+	default:
+		pr_err("core perfctr but no constraints; unknown hardware!\n");
 		return -ENODEV;
 	}
 
-	WARN(x86_pmu.get_event_constraints == amd_get_event_constraints,
-	     KERN_ERR "hw perf events core counters need constraints handler!");
-
 	/*
 	 * If core performance counter extensions exists, we must use
 	 * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also
-	 * x86_pmu_addr_offset().
+	 * amd_pmu_addr_offset().
 	 */
 	x86_pmu.eventsel	= MSR_F15H_PERF_CTL;
 	x86_pmu.perfctr		= MSR_F15H_PERF_CTR;
 	x86_pmu.num_counters	= AMD64_NUM_COUNTERS_CORE;
 
-	printk(KERN_INFO "perf: AMD core performance counters detected\n");
-
+	pr_cont("core perfctr, ");
 	return 0;
 }
 
 __init int amd_pmu_init(void)
 {
+	int ret;
+
 	/* Performance-monitoring supported from K7 and later: */
 	if (boot_cpu_data.x86 < 6)
 		return -ENODEV;
 
 	x86_pmu = amd_pmu;
 
-	setup_event_constraints();
-	setup_perfctr_core();
+	ret = amd_core_pmu_init();
+	if (ret)
+		return ret;
 
 	/* Events are common for all AMDs */
 	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
new file mode 100644
index 00000000000..0db655ef391
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
@@ -0,0 +1,504 @@
+/*
+ * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ *
+ * Author: Steven Kinney <Steven.Kinney@amd.com>
+ * Author: Suravee Suthikulpanit <Suraveee.Suthikulpanit@amd.com>
+ *
+ * Perf: amd_iommu - AMD IOMMU Performance Counter PMU implementation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/perf_event.h>
+#include <linux/module.h>
+#include <linux/cpumask.h>
+#include <linux/slab.h>
+
+#include "perf_event.h"
+#include "perf_event_amd_iommu.h"
+
+#define COUNTER_SHIFT		16
+
+#define _GET_BANK(ev)       ((u8)(ev->hw.extra_reg.reg >> 8))
+#define _GET_CNTR(ev)       ((u8)(ev->hw.extra_reg.reg))
+
+/* iommu pmu config masks */
+#define _GET_CSOURCE(ev)    ((ev->hw.config & 0xFFULL))
+#define _GET_DEVID(ev)      ((ev->hw.config >> 8)  & 0xFFFFULL)
+#define _GET_PASID(ev)      ((ev->hw.config >> 24) & 0xFFFFULL)
+#define _GET_DOMID(ev)      ((ev->hw.config >> 40) & 0xFFFFULL)
+#define _GET_DEVID_MASK(ev) ((ev->hw.extra_reg.config)  & 0xFFFFULL)
+#define _GET_PASID_MASK(ev) ((ev->hw.extra_reg.config >> 16) & 0xFFFFULL)
+#define _GET_DOMID_MASK(ev) ((ev->hw.extra_reg.config >> 32) & 0xFFFFULL)
+
+static struct perf_amd_iommu __perf_iommu;
+
+struct perf_amd_iommu {
+	struct pmu pmu;
+	u8 max_banks;
+	u8 max_counters;
+	u64 cntr_assign_mask;
+	raw_spinlock_t lock;
+	const struct attribute_group *attr_groups[4];
+};
+
+#define format_group	attr_groups[0]
+#define cpumask_group	attr_groups[1]
+#define events_group	attr_groups[2]
+#define null_group	attr_groups[3]
+
+/*---------------------------------------------
+ * sysfs format attributes
+ *---------------------------------------------*/
+PMU_FORMAT_ATTR(csource,    "config:0-7");
+PMU_FORMAT_ATTR(devid,      "config:8-23");
+PMU_FORMAT_ATTR(pasid,      "config:24-39");
+PMU_FORMAT_ATTR(domid,      "config:40-55");
+PMU_FORMAT_ATTR(devid_mask, "config1:0-15");
+PMU_FORMAT_ATTR(pasid_mask, "config1:16-31");
+PMU_FORMAT_ATTR(domid_mask, "config1:32-47");
+
+static struct attribute *iommu_format_attrs[] = {
+	&format_attr_csource.attr,
+	&format_attr_devid.attr,
+	&format_attr_pasid.attr,
+	&format_attr_domid.attr,
+	&format_attr_devid_mask.attr,
+	&format_attr_pasid_mask.attr,
+	&format_attr_domid_mask.attr,
+	NULL,
+};
+
+static struct attribute_group amd_iommu_format_group = {
+	.name = "format",
+	.attrs = iommu_format_attrs,
+};
+
+/*---------------------------------------------
+ * sysfs events attributes
+ *---------------------------------------------*/
+struct amd_iommu_event_desc {
+	struct kobj_attribute attr;
+	const char *event;
+};
+
+static ssize_t _iommu_event_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *buf)
+{
+	struct amd_iommu_event_desc *event =
+		container_of(attr, struct amd_iommu_event_desc, attr);
+	return sprintf(buf, "%s\n", event->event);
+}
+
+#define AMD_IOMMU_EVENT_DESC(_name, _event)			\
+{								\
+	.attr  = __ATTR(_name, 0444, _iommu_event_show, NULL),	\
+	.event = _event,					\
+}
+
+static struct amd_iommu_event_desc amd_iommu_v2_event_descs[] = {
+	AMD_IOMMU_EVENT_DESC(mem_pass_untrans,        "csource=0x01"),
+	AMD_IOMMU_EVENT_DESC(mem_pass_pretrans,       "csource=0x02"),
+	AMD_IOMMU_EVENT_DESC(mem_pass_excl,           "csource=0x03"),
+	AMD_IOMMU_EVENT_DESC(mem_target_abort,        "csource=0x04"),
+	AMD_IOMMU_EVENT_DESC(mem_trans_total,         "csource=0x05"),
+	AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pte_hit,   "csource=0x06"),
+	AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pte_mis,   "csource=0x07"),
+	AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pde_hit,   "csource=0x08"),
+	AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pde_mis,   "csource=0x09"),
+	AMD_IOMMU_EVENT_DESC(mem_dte_hit,             "csource=0x0a"),
+	AMD_IOMMU_EVENT_DESC(mem_dte_mis,             "csource=0x0b"),
+	AMD_IOMMU_EVENT_DESC(page_tbl_read_tot,       "csource=0x0c"),
+	AMD_IOMMU_EVENT_DESC(page_tbl_read_nst,       "csource=0x0d"),
+	AMD_IOMMU_EVENT_DESC(page_tbl_read_gst,       "csource=0x0e"),
+	AMD_IOMMU_EVENT_DESC(int_dte_hit,             "csource=0x0f"),
+	AMD_IOMMU_EVENT_DESC(int_dte_mis,             "csource=0x10"),
+	AMD_IOMMU_EVENT_DESC(cmd_processed,           "csource=0x11"),
+	AMD_IOMMU_EVENT_DESC(cmd_processed_inv,       "csource=0x12"),
+	AMD_IOMMU_EVENT_DESC(tlb_inv,                 "csource=0x13"),
+	{ /* end: all zeroes */ },
+};
+
+/*---------------------------------------------
+ * sysfs cpumask attributes
+ *---------------------------------------------*/
+static cpumask_t iommu_cpumask;
+
+static ssize_t _iommu_cpumask_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &iommu_cpumask);
+	buf[n++] = '\n';
+	buf[n] = '\0';
+	return n;
+}
+static DEVICE_ATTR(cpumask, S_IRUGO, _iommu_cpumask_show, NULL);
+
+static struct attribute *iommu_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group amd_iommu_cpumask_group = {
+	.attrs = iommu_cpumask_attrs,
+};
+
+/*---------------------------------------------*/
+
+static int get_next_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu)
+{
+	unsigned long flags;
+	int shift, bank, cntr, retval;
+	int max_banks = perf_iommu->max_banks;
+	int max_cntrs = perf_iommu->max_counters;
+
+	raw_spin_lock_irqsave(&perf_iommu->lock, flags);
+
+	for (bank = 0, shift = 0; bank < max_banks; bank++) {
+		for (cntr = 0; cntr < max_cntrs; cntr++) {
+			shift = bank + (bank*3) + cntr;
+			if (perf_iommu->cntr_assign_mask & (1ULL<<shift)) {
+				continue;
+			} else {
+				perf_iommu->cntr_assign_mask |= (1ULL<<shift);
+				retval = ((u16)((u16)bank<<8) | (u8)(cntr));
+				goto out;
+			}
+		}
+	}
+	retval = -ENOSPC;
+out:
+	raw_spin_unlock_irqrestore(&perf_iommu->lock, flags);
+	return retval;
+}
+
+static int clear_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu,
+					u8 bank, u8 cntr)
+{
+	unsigned long flags;
+	int max_banks, max_cntrs;
+	int shift = 0;
+
+	max_banks = perf_iommu->max_banks;
+	max_cntrs = perf_iommu->max_counters;
+
+	if ((bank > max_banks) || (cntr > max_cntrs))
+		return -EINVAL;
+
+	shift = bank + cntr + (bank*3);
+
+	raw_spin_lock_irqsave(&perf_iommu->lock, flags);
+	perf_iommu->cntr_assign_mask &= ~(1ULL<<shift);
+	raw_spin_unlock_irqrestore(&perf_iommu->lock, flags);
+
+	return 0;
+}
+
+static int perf_iommu_event_init(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_amd_iommu *perf_iommu;
+	u64 config, config1;
+
+	/* test the event attr type check for PMU enumeration */
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/*
+	 * IOMMU counters are shared across all cores.
+	 * Therefore, it does not support per-process mode.
+	 * Also, it does not support event sampling mode.
+	 */
+	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
+		return -EINVAL;
+
+	/* IOMMU counters do not have usr/os/guest/host bits */
+	if (event->attr.exclude_user || event->attr.exclude_kernel ||
+	    event->attr.exclude_host || event->attr.exclude_guest)
+		return -EINVAL;
+
+	if (event->cpu < 0)
+		return -EINVAL;
+
+	perf_iommu = &__perf_iommu;
+
+	if (event->pmu != &perf_iommu->pmu)
+		return -ENOENT;
+
+	if (perf_iommu) {
+		config = event->attr.config;
+		config1 = event->attr.config1;
+	} else {
+		return -EINVAL;
+	}
+
+	/* integrate with iommu base devid (0000), assume one iommu */
+	perf_iommu->max_banks =
+		amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID);
+	perf_iommu->max_counters =
+		amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID);
+	if ((perf_iommu->max_banks == 0) || (perf_iommu->max_counters == 0))
+		return -EINVAL;
+
+	/* update the hw_perf_event struct with the iommu config data */
+	hwc->config = config;
+	hwc->extra_reg.config = config1;
+
+	return 0;
+}
+
+static void perf_iommu_enable_event(struct perf_event *ev)
+{
+	u8 csource = _GET_CSOURCE(ev);
+	u16 devid = _GET_DEVID(ev);
+	u64 reg = 0ULL;
+
+	reg = csource;
+	amd_iommu_pc_get_set_reg_val(devid,
+			_GET_BANK(ev), _GET_CNTR(ev) ,
+			 IOMMU_PC_COUNTER_SRC_REG, &reg, true);
+
+	reg = 0ULL | devid | (_GET_DEVID_MASK(ev) << 32);
+	if (reg)
+		reg |= (1UL << 31);
+	amd_iommu_pc_get_set_reg_val(devid,
+			_GET_BANK(ev), _GET_CNTR(ev) ,
+			 IOMMU_PC_DEVID_MATCH_REG, &reg, true);
+
+	reg = 0ULL | _GET_PASID(ev) | (_GET_PASID_MASK(ev) << 32);
+	if (reg)
+		reg |= (1UL << 31);
+	amd_iommu_pc_get_set_reg_val(devid,
+			_GET_BANK(ev), _GET_CNTR(ev) ,
+			 IOMMU_PC_PASID_MATCH_REG, &reg, true);
+
+	reg = 0ULL | _GET_DOMID(ev) | (_GET_DOMID_MASK(ev) << 32);
+	if (reg)
+		reg |= (1UL << 31);
+	amd_iommu_pc_get_set_reg_val(devid,
+			_GET_BANK(ev), _GET_CNTR(ev) ,
+			 IOMMU_PC_DOMID_MATCH_REG, &reg, true);
+}
+
+static void perf_iommu_disable_event(struct perf_event *event)
+{
+	u64 reg = 0ULL;
+
+	amd_iommu_pc_get_set_reg_val(_GET_DEVID(event),
+			_GET_BANK(event), _GET_CNTR(event),
+			IOMMU_PC_COUNTER_SRC_REG, &reg, true);
+}
+
+static void perf_iommu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	pr_debug("perf: amd_iommu:perf_iommu_start\n");
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+	hwc->state = 0;
+
+	if (flags & PERF_EF_RELOAD) {
+		u64 prev_raw_count =  local64_read(&hwc->prev_count);
+		amd_iommu_pc_get_set_reg_val(_GET_DEVID(event),
+				_GET_BANK(event), _GET_CNTR(event),
+				IOMMU_PC_COUNTER_REG, &prev_raw_count, true);
+	}
+
+	perf_iommu_enable_event(event);
+	perf_event_update_userpage(event);
+
+}
+
+static void perf_iommu_read(struct perf_event *event)
+{
+	u64 count = 0ULL;
+	u64 prev_raw_count = 0ULL;
+	u64 delta = 0ULL;
+	struct hw_perf_event *hwc = &event->hw;
+	pr_debug("perf: amd_iommu:perf_iommu_read\n");
+
+	amd_iommu_pc_get_set_reg_val(_GET_DEVID(event),
+				_GET_BANK(event), _GET_CNTR(event),
+				IOMMU_PC_COUNTER_REG, &count, false);
+
+	/* IOMMU pc counter register is only 48 bits */
+	count &= 0xFFFFFFFFFFFFULL;
+
+	prev_raw_count =  local64_read(&hwc->prev_count);
+	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+					count) != prev_raw_count)
+		return;
+
+	/* Handling 48-bit counter overflowing */
+	delta = (count << COUNTER_SHIFT) - (prev_raw_count << COUNTER_SHIFT);
+	delta >>= COUNTER_SHIFT;
+	local64_add(delta, &event->count);
+
+}
+
+static void perf_iommu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 config;
+
+	pr_debug("perf: amd_iommu:perf_iommu_stop\n");
+
+	if (hwc->state & PERF_HES_UPTODATE)
+		return;
+
+	perf_iommu_disable_event(event);
+	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+	hwc->state |= PERF_HES_STOPPED;
+
+	if (hwc->state & PERF_HES_UPTODATE)
+		return;
+
+	config = hwc->config;
+	perf_iommu_read(event);
+	hwc->state |= PERF_HES_UPTODATE;
+}
+
+static int perf_iommu_add(struct perf_event *event, int flags)
+{
+	int retval;
+	struct perf_amd_iommu *perf_iommu =
+			container_of(event->pmu, struct perf_amd_iommu, pmu);
+
+	pr_debug("perf: amd_iommu:perf_iommu_add\n");
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	/* request an iommu bank/counter */
+	retval = get_next_avail_iommu_bnk_cntr(perf_iommu);
+	if (retval != -ENOSPC)
+		event->hw.extra_reg.reg = (u16)retval;
+	else
+		return retval;
+
+	if (flags & PERF_EF_START)
+		perf_iommu_start(event, PERF_EF_RELOAD);
+
+	return 0;
+}
+
+static void perf_iommu_del(struct perf_event *event, int flags)
+{
+	struct perf_amd_iommu *perf_iommu =
+			container_of(event->pmu, struct perf_amd_iommu, pmu);
+
+	pr_debug("perf: amd_iommu:perf_iommu_del\n");
+	perf_iommu_stop(event, PERF_EF_UPDATE);
+
+	/* clear the assigned iommu bank/counter */
+	clear_avail_iommu_bnk_cntr(perf_iommu,
+				     _GET_BANK(event),
+				     _GET_CNTR(event));
+
+	perf_event_update_userpage(event);
+}
+
+static __init int _init_events_attrs(struct perf_amd_iommu *perf_iommu)
+{
+	struct attribute **attrs;
+	struct attribute_group *attr_group;
+	int i = 0, j;
+
+	while (amd_iommu_v2_event_descs[i].attr.attr.name)
+		i++;
+
+	attr_group = kzalloc(sizeof(struct attribute *)
+		* (i + 1) + sizeof(*attr_group), GFP_KERNEL);
+	if (!attr_group)
+		return -ENOMEM;
+
+	attrs = (struct attribute **)(attr_group + 1);
+	for (j = 0; j < i; j++)
+		attrs[j] = &amd_iommu_v2_event_descs[j].attr.attr;
+
+	attr_group->name = "events";
+	attr_group->attrs = attrs;
+	perf_iommu->events_group = attr_group;
+
+	return 0;
+}
+
+static __init void amd_iommu_pc_exit(void)
+{
+	if (__perf_iommu.events_group != NULL) {
+		kfree(__perf_iommu.events_group);
+		__perf_iommu.events_group = NULL;
+	}
+}
+
+static __init int _init_perf_amd_iommu(
+	struct perf_amd_iommu *perf_iommu, char *name)
+{
+	int ret;
+
+	raw_spin_lock_init(&perf_iommu->lock);
+
+	/* Init format attributes */
+	perf_iommu->format_group = &amd_iommu_format_group;
+
+	/* Init cpumask attributes to only core 0 */
+	cpumask_set_cpu(0, &iommu_cpumask);
+	perf_iommu->cpumask_group = &amd_iommu_cpumask_group;
+
+	/* Init events attributes */
+	if (_init_events_attrs(perf_iommu) != 0)
+		pr_err("perf: amd_iommu: Only support raw events.\n");
+
+	/* Init null attributes */
+	perf_iommu->null_group = NULL;
+	perf_iommu->pmu.attr_groups = perf_iommu->attr_groups;
+
+	ret = perf_pmu_register(&perf_iommu->pmu, name, -1);
+	if (ret) {
+		pr_err("perf: amd_iommu: Failed to initialized.\n");
+		amd_iommu_pc_exit();
+	} else {
+		pr_info("perf: amd_iommu: Detected. (%d banks, %d counters/bank)\n",
+			amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID),
+			amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID));
+	}
+
+	return ret;
+}
+
+static struct perf_amd_iommu __perf_iommu = {
+	.pmu = {
+		.event_init	= perf_iommu_event_init,
+		.add		= perf_iommu_add,
+		.del		= perf_iommu_del,
+		.start		= perf_iommu_start,
+		.stop		= perf_iommu_stop,
+		.read		= perf_iommu_read,
+	},
+	.max_banks		= 0x00,
+	.max_counters		= 0x00,
+	.cntr_assign_mask	= 0ULL,
+	.format_group		= NULL,
+	.cpumask_group		= NULL,
+	.events_group		= NULL,
+	.null_group		= NULL,
+};
+
+static __init int amd_iommu_pc_init(void)
+{
+	/* Make sure the IOMMU PC resource is available */
+	if (!amd_iommu_pc_supported()) {
+		pr_err("perf: amd_iommu PMU not installed. No support!\n");
+		return -ENODEV;
+	}
+
+	_init_perf_amd_iommu(&__perf_iommu, "amd_iommu");
+
+	return 0;
+}
+
+device_initcall(amd_iommu_pc_init);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.h b/arch/x86/kernel/cpu/perf_event_amd_iommu.h
new file mode 100644
index 00000000000..845d173278e
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ *
+ * Author: Steven Kinney <Steven.Kinney@amd.com>
+ * Author: Suravee Suthikulpanit <Suraveee.Suthikulpanit@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _PERF_EVENT_AMD_IOMMU_H_
+#define _PERF_EVENT_AMD_IOMMU_H_
+
+/* iommu pc mmio region register indexes */
+#define IOMMU_PC_COUNTER_REG			0x00
+#define IOMMU_PC_COUNTER_SRC_REG		0x08
+#define IOMMU_PC_PASID_MATCH_REG		0x10
+#define IOMMU_PC_DOMID_MATCH_REG		0x18
+#define IOMMU_PC_DEVID_MATCH_REG		0x20
+#define IOMMU_PC_COUNTER_REPORT_REG		0x28
+
+/* maximun specified bank/counters */
+#define PC_MAX_SPEC_BNKS			64
+#define PC_MAX_SPEC_CNTRS			16
+
+/* iommu pc reg masks*/
+#define IOMMU_BASE_DEVID			0x0000
+
+/* amd_iommu_init.c external support functions */
+extern bool amd_iommu_pc_supported(void);
+
+extern u8 amd_iommu_pc_get_max_banks(u16 devid);
+
+extern u8 amd_iommu_pc_get_max_counters(u16 devid);
+
+extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr,
+			u8 fxn, u64 *value, bool is_write);
+
+#endif /*_PERF_EVENT_AMD_IOMMU_H_*/
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a9e22073bd5..fbc9210b45b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 
+#include <asm/cpufeature.h>
 #include <asm/hardirq.h>
 #include <asm/apic.h>
 
@@ -190,6 +191,22 @@ struct attribute *snb_events_attrs[] = {
 	NULL,
 };
 
+static struct event_constraint intel_hsw_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */
+	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
+	INTEL_EVENT_CONSTRAINT(0x08a3, 0x4),
+	/* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
+	INTEL_EVENT_CONSTRAINT(0x0ca3, 0x4),
+	/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
+	INTEL_EVENT_CONSTRAINT(0x04a3, 0xf),
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -872,7 +889,8 @@ static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
 		return true;
 
 	/* implicit branch sampling to correct PEBS skid */
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
+	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 &&
+	    x86_pmu.intel_cap.pebs_format < 2)
 		return true;
 
 	return false;
@@ -1167,15 +1185,11 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	/*
-	 * Some chipsets need to unmask the LVTPC in a particular spot
-	 * inside the nmi handler.  As a result, the unmasking was pushed
-	 * into all the nmi handlers.
-	 *
-	 * This handler doesn't seem to have any issues with the unmasking
-	 * so it was left at the top.
+	 * No known reason to not always do late ACK,
+	 * but just in case do it opt-in.
 	 */
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-
+	if (!x86_pmu.late_ack)
+		apic_write(APIC_LVTPC, APIC_DM_NMI);
 	intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
@@ -1188,8 +1202,12 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 again:
 	intel_pmu_ack_status(status);
 	if (++loops > 100) {
-		WARN_ONCE(1, "perfevents: irq loop stuck!\n");
-		perf_event_print_debug();
+		static bool warned = false;
+		if (!warned) {
+			WARN(1, "perfevents: irq loop stuck!\n");
+			perf_event_print_debug();
+			warned = true;
+		}
 		intel_pmu_reset();
 		goto done;
 	}
@@ -1235,6 +1253,13 @@ again:
 
 done:
 	intel_pmu_enable_all(0);
+	/*
+	 * Only unmask the NMI after the overflow counters
+	 * have been reset. This avoids spurious NMIs on
+	 * Haswell CPUs.
+	 */
+	if (x86_pmu.late_ack)
+		apic_write(APIC_LVTPC, APIC_DM_NMI);
 	return handled;
 }
 
@@ -1425,7 +1450,6 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
 			if ((event->hw.config & c->cmask) == c->code) {
-				/* hw.flags zeroed at initialization */
 				event->hw.flags |= c->flags;
 				return c;
 			}
@@ -1473,7 +1497,6 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 					struct perf_event *event)
 {
-	event->hw.flags = 0;
 	intel_put_shared_regs_event_constraints(cpuc, event);
 }
 
@@ -1646,6 +1669,47 @@ static void core_pmu_enable_all(int added)
 	}
 }
 
+static int hsw_hw_config(struct perf_event *event)
+{
+	int ret = intel_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+	if (!boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has(X86_FEATURE_HLE))
+		return 0;
+	event->hw.config |= event->attr.config & (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED);
+
+	/*
+	 * IN_TX/IN_TX-CP filters are not supported by the Haswell PMU with
+	 * PEBS or in ANY thread mode. Since the results are non-sensical forbid
+	 * this combination.
+	 */
+	if ((event->hw.config & (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED)) &&
+	     ((event->hw.config & ARCH_PERFMON_EVENTSEL_ANY) ||
+	      event->attr.precise_ip > 0))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static struct event_constraint counter2_constraint =
+			EVENT_CONSTRAINT(0, 0x4, 0);
+
+static struct event_constraint *
+hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	struct event_constraint *c = intel_get_event_constraints(cpuc, event);
+
+	/* Handle special quirk on in_tx_checkpointed only in counter 2 */
+	if (event->hw.config & HSW_IN_TX_CHECKPOINTED) {
+		if (c->idxmsk64 & (1U << 2))
+			return &counter2_constraint;
+		return &emptyconstraint;
+	}
+
+	return c;
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -1653,6 +1717,8 @@ PMU_FORMAT_ATTR(pc,	"config:19"	);
 PMU_FORMAT_ATTR(any,	"config:21"	); /* v3 + */
 PMU_FORMAT_ATTR(inv,	"config:23"	);
 PMU_FORMAT_ATTR(cmask,	"config:24-31"	);
+PMU_FORMAT_ATTR(in_tx,  "config:32");
+PMU_FORMAT_ATTR(in_tx_cp, "config:33");
 
 static struct attribute *intel_arch_formats_attr[] = {
 	&format_attr_event.attr,
@@ -1807,6 +1873,8 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_any.attr,
 	&format_attr_inv.attr,
 	&format_attr_cmask.attr,
+	&format_attr_in_tx.attr,
+	&format_attr_in_tx_cp.attr,
 
 	&format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
 	&format_attr_ldlat.attr, /* PEBS load latency */
@@ -1966,6 +2034,15 @@ static __init void intel_nehalem_quirk(void)
 	}
 }
 
+EVENT_ATTR_STR(mem-loads,      mem_ld_hsw,     "event=0xcd,umask=0x1,ldlat=3");
+EVENT_ATTR_STR(mem-stores,     mem_st_hsw,     "event=0xd0,umask=0x82")
+
+static struct attribute *hsw_events_attrs[] = {
+	EVENT_PTR(mem_ld_hsw),
+	EVENT_PTR(mem_st_hsw),
+	NULL
+};
+
 __init int intel_pmu_init(void)
 {
 	union cpuid10_edx edx;
@@ -2189,6 +2266,30 @@ __init int intel_pmu_init(void)
 		break;
 
 
+	case 60: /* Haswell Client */
+	case 70:
+	case 71:
+	case 63:
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_hsw_event_constraints;
+		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_snb_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		pr_cont("Haswell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
@@ -2227,7 +2328,7 @@ __init int intel_pmu_init(void)
 		 * counter, so do not extend mask to generic counters
 		 */
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if (c->cmask != X86_RAW_EVENT_MASK
+			if (c->cmask != FIXED_EVENT_FLAGS
 			    || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
 				continue;
 			}
@@ -2237,5 +2338,12 @@ __init int intel_pmu_init(void)
 		}
 	}
 
+	/* Support full width counters using alternative MSR range */
+	if (x86_pmu.intel_cap.full_width_write) {
+		x86_pmu.max_period = x86_pmu.cntval_mask;
+		x86_pmu.perfctr = MSR_IA32_PMC0;
+		pr_cont("full-width counters, ");
+	}
+
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 60250f68705..3065c57a63c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -107,6 +107,19 @@ static u64 precise_store_data(u64 status)
 	return val;
 }
 
+static u64 precise_store_data_hsw(u64 status)
+{
+	union perf_mem_data_src dse;
+
+	dse.val = 0;
+	dse.mem_op = PERF_MEM_OP_STORE;
+	dse.mem_lvl = PERF_MEM_LVL_NA;
+	if (status & 1)
+		dse.mem_lvl = PERF_MEM_LVL_L1;
+	/* Nothing else supported. Sorry. */
+	return dse.val;
+}
+
 static u64 load_latency_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
@@ -165,6 +178,22 @@ struct pebs_record_nhm {
 	u64 status, dla, dse, lat;
 };
 
+/*
+ * Same as pebs_record_nhm, with two additional fields.
+ */
+struct pebs_record_hsw {
+	struct pebs_record_nhm nhm;
+	/*
+	 * Real IP of the event. In the Intel documentation this
+	 * is called eventingrip.
+	 */
+	u64 real_ip;
+	/*
+	 * TSX tuning information field: abort cycles and abort flags.
+	 */
+	u64 tsx_tuning;
+};
+
 void init_debug_store_on_cpu(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -548,6 +577,42 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
         EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_hsw_pebs_event_constraints[] = {
+	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+	INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+	INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
+	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
+	INTEL_UEVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */
+	INTEL_UEVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */
+	INTEL_UEVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.NEAR_TAKEN */
+	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.* */
+	/* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
+	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf),
+	/* MEM_UOPS_RETIRED.STLB_MISS_STORES */
+	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
+	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
+	/* MEM_UOPS_RETIRED.SPLIT_STORES */
+	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
+	INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
+	INTEL_UEVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */
+	INTEL_UEVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */
+	INTEL_UEVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L3_HIT */
+	/* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
+	INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf),
+	/* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
+	INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf),
+	/* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
+	INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf),
+	/* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */
+	INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x04c8, 0xf), /* HLE_RETIRED.Abort */
+	INTEL_UEVENT_CONSTRAINT(0x04c9, 0xf), /* RTM_RETIRED.Abort */
+
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *c;
@@ -588,6 +653,12 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
+
+	if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT)
+		cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
+	else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST)
+		cpuc->pebs_enabled &= ~(1ULL << 63);
+
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
@@ -697,6 +768,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 */
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct pebs_record_nhm *pebs = __pebs;
+	struct pebs_record_hsw *pebs_hsw = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
 	u64 sample_type;
@@ -706,7 +778,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 		return;
 
 	fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
-	fst = event->hw.flags & PERF_X86_EVENT_PEBS_ST;
+	fst = event->hw.flags & (PERF_X86_EVENT_PEBS_ST |
+				 PERF_X86_EVENT_PEBS_ST_HSW);
 
 	perf_sample_data_init(&data, 0, event->hw.last_period);
 
@@ -717,9 +790,6 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * if PEBS-LL or PreciseStore
 	 */
 	if (fll || fst) {
-		if (sample_type & PERF_SAMPLE_ADDR)
-			data.addr = pebs->dla;
-
 		/*
 		 * Use latency for weight (only avail with PEBS-LL)
 		 */
@@ -732,6 +802,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 		if (sample_type & PERF_SAMPLE_DATA_SRC) {
 			if (fll)
 				data.data_src.val = load_latency_data(pebs->dse);
+			else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
+				data.data_src.val =
+					precise_store_data_hsw(pebs->dse);
 			else
 				data.data_src.val = precise_store_data(pebs->dse);
 		}
@@ -753,11 +826,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	regs.bp = pebs->bp;
 	regs.sp = pebs->sp;
 
-	if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
+	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
+		regs.ip = pebs_hsw->real_ip;
+		regs.flags |= PERF_EFLAGS_EXACT;
+	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
 		regs.flags |= PERF_EFLAGS_EXACT;
 	else
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
+	if ((event->attr.sample_type & PERF_SAMPLE_ADDR) &&
+		x86_pmu.intel_cap.pebs_format >= 1)
+		data.addr = pebs->dla;
+
 	if (has_branch_stack(event))
 		data.br_stack = &cpuc->lbr_stack;
 
@@ -806,35 +886,22 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 	__intel_pmu_pebs_event(event, iregs, at);
 }
 
-static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
+static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at,
+					void *top)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
-	struct pebs_record_nhm *at, *top;
 	struct perf_event *event = NULL;
 	u64 status = 0;
-	int bit, n;
-
-	if (!x86_pmu.pebs_active)
-		return;
-
-	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
-	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
+	int bit;
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
-	n = top - at;
-	if (n <= 0)
-		return;
-
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ONCE(n > x86_pmu.max_pebs_events, "Unexpected number of pebs records %d\n", n);
+	for (; at < top; at += x86_pmu.pebs_record_size) {
+		struct pebs_record_nhm *p = at;
 
-	for ( ; at < top; at++) {
-		for_each_set_bit(bit, (unsigned long *)&at->status, x86_pmu.max_pebs_events) {
+		for_each_set_bit(bit, (unsigned long *)&p->status,
+				 x86_pmu.max_pebs_events) {
 			event = cpuc->events[bit];
 			if (!test_bit(bit, cpuc->active_mask))
 				continue;
@@ -857,6 +924,61 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	}
 }
 
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct pebs_record_nhm *at, *top;
+	int n;
+
+	if (!x86_pmu.pebs_active)
+		return;
+
+	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
+
+	ds->pebs_index = ds->pebs_buffer_base;
+
+	n = top - at;
+	if (n <= 0)
+		return;
+
+	/*
+	 * Should not happen, we program the threshold at 1 and do not
+	 * set a reset value.
+	 */
+	WARN_ONCE(n > x86_pmu.max_pebs_events,
+		  "Unexpected number of pebs records %d\n", n);
+
+	return __intel_pmu_drain_pebs_nhm(iregs, at, top);
+}
+
+static void intel_pmu_drain_pebs_hsw(struct pt_regs *iregs)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct pebs_record_hsw *at, *top;
+	int n;
+
+	if (!x86_pmu.pebs_active)
+		return;
+
+	at  = (struct pebs_record_hsw *)(unsigned long)ds->pebs_buffer_base;
+	top = (struct pebs_record_hsw *)(unsigned long)ds->pebs_index;
+
+	n = top - at;
+	if (n <= 0)
+		return;
+	/*
+	 * Should not happen, we program the threshold at 1 and do not
+	 * set a reset value.
+	 */
+	WARN_ONCE(n > x86_pmu.max_pebs_events,
+		  "Unexpected number of pebs records %d\n", n);
+
+	return __intel_pmu_drain_pebs_nhm(iregs, at, top);
+}
+
 /*
  * BTS, PEBS probe and setup
  */
@@ -888,6 +1010,12 @@ void intel_ds_init(void)
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
 			break;
 
+		case 2:
+			pr_cont("PEBS fmt2%c, ", pebs_type);
+			x86_pmu.pebs_record_size = sizeof(struct pebs_record_hsw);
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_hsw;
+			break;
+
 		default:
 			printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
 			x86_pmu.pebs = 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index d978353c939..d5be06a5005 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -12,6 +12,16 @@ enum {
 	LBR_FORMAT_LIP		= 0x01,
 	LBR_FORMAT_EIP		= 0x02,
 	LBR_FORMAT_EIP_FLAGS	= 0x03,
+	LBR_FORMAT_EIP_FLAGS2	= 0x04,
+	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_EIP_FLAGS2,
+};
+
+static enum {
+	LBR_EIP_FLAGS		= 1,
+	LBR_TSX			= 2,
+} lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = {
+	[LBR_FORMAT_EIP_FLAGS]  = LBR_EIP_FLAGS,
+	[LBR_FORMAT_EIP_FLAGS2] = LBR_EIP_FLAGS | LBR_TSX,
 };
 
 /*
@@ -56,6 +66,8 @@ enum {
 	 LBR_FAR)
 
 #define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
+#define LBR_FROM_FLAG_IN_TX    (1ULL << 62)
+#define LBR_FROM_FLAG_ABORT    (1ULL << 61)
 
 #define for_each_branch_sample_type(x) \
 	for ((x) = PERF_SAMPLE_BRANCH_USER; \
@@ -81,9 +93,13 @@ enum {
 	X86_BR_JMP      = 1 << 9, /* jump */
 	X86_BR_IRQ      = 1 << 10,/* hw interrupt or trap or fault */
 	X86_BR_IND_CALL = 1 << 11,/* indirect calls */
+	X86_BR_ABORT    = 1 << 12,/* transaction abort */
+	X86_BR_IN_TX    = 1 << 13,/* in transaction */
+	X86_BR_NO_TX    = 1 << 14,/* not in transaction */
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
+#define X86_BR_ANYTX (X86_BR_NO_TX | X86_BR_IN_TX)
 
 #define X86_BR_ANY       \
 	(X86_BR_CALL    |\
@@ -95,6 +111,7 @@ enum {
 	 X86_BR_JCC     |\
 	 X86_BR_JMP	 |\
 	 X86_BR_IRQ	 |\
+	 X86_BR_ABORT	 |\
 	 X86_BR_IND_CALL)
 
 #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
@@ -270,21 +287,31 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		unsigned long lbr_idx = (tos - i) & mask;
-		u64 from, to, mis = 0, pred = 0;
+		u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0;
+		int skip = 0;
+		int lbr_flags = lbr_desc[lbr_format];
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
 		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
-		if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
+		if (lbr_flags & LBR_EIP_FLAGS) {
 			mis = !!(from & LBR_FROM_FLAG_MISPRED);
 			pred = !mis;
-			from = (u64)((((s64)from) << 1) >> 1);
+			skip = 1;
+		}
+		if (lbr_flags & LBR_TSX) {
+			in_tx = !!(from & LBR_FROM_FLAG_IN_TX);
+			abort = !!(from & LBR_FROM_FLAG_ABORT);
+			skip = 3;
 		}
+		from = (u64)((((s64)from) << skip) >> skip);
 
 		cpuc->lbr_entries[i].from	= from;
 		cpuc->lbr_entries[i].to		= to;
 		cpuc->lbr_entries[i].mispred	= mis;
 		cpuc->lbr_entries[i].predicted	= pred;
+		cpuc->lbr_entries[i].in_tx	= in_tx;
+		cpuc->lbr_entries[i].abort	= abort;
 		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
@@ -310,7 +337,7 @@ void intel_pmu_lbr_read(void)
  * - in case there is no HW filter
  * - in case the HW filter has errata or limitations
  */
-static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
+static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 {
 	u64 br_type = event->attr.branch_sample_type;
 	int mask = 0;
@@ -318,11 +345,8 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 	if (br_type & PERF_SAMPLE_BRANCH_USER)
 		mask |= X86_BR_USER;
 
-	if (br_type & PERF_SAMPLE_BRANCH_KERNEL) {
-		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+	if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
 		mask |= X86_BR_KERNEL;
-	}
 
 	/* we ignore BRANCH_HV here */
 
@@ -337,13 +361,21 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 
 	if (br_type & PERF_SAMPLE_BRANCH_IND_CALL)
 		mask |= X86_BR_IND_CALL;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ABORT_TX)
+		mask |= X86_BR_ABORT;
+
+	if (br_type & PERF_SAMPLE_BRANCH_IN_TX)
+		mask |= X86_BR_IN_TX;
+
+	if (br_type & PERF_SAMPLE_BRANCH_NO_TX)
+		mask |= X86_BR_NO_TX;
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
 	 */
 	event->hw.branch_reg.reg = mask;
-
-	return 0;
 }
 
 /*
@@ -391,9 +423,7 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event)
 	/*
 	 * setup SW LBR filter
 	 */
-	ret = intel_pmu_setup_sw_lbr_filter(event);
-	if (ret)
-		return ret;
+	intel_pmu_setup_sw_lbr_filter(event);
 
 	/*
 	 * setup HW LBR filter, if any
@@ -415,7 +445,7 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event)
  * decoded (e.g., text page not present), then X86_BR_NONE is
  * returned.
  */
-static int branch_type(unsigned long from, unsigned long to)
+static int branch_type(unsigned long from, unsigned long to, int abort)
 {
 	struct insn insn;
 	void *addr;
@@ -435,6 +465,9 @@ static int branch_type(unsigned long from, unsigned long to)
 	if (from == 0 || to == 0)
 		return X86_BR_NONE;
 
+	if (abort)
+		return X86_BR_ABORT | to_plm;
+
 	if (from_plm == X86_BR_USER) {
 		/*
 		 * can happen if measuring at the user level only
@@ -581,7 +614,13 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 		from = cpuc->lbr_entries[i].from;
 		to = cpuc->lbr_entries[i].to;
 
-		type = branch_type(from, to);
+		type = branch_type(from, to, cpuc->lbr_entries[i].abort);
+		if (type != X86_BR_NONE && (br_sel & X86_BR_ANYTX)) {
+			if (cpuc->lbr_entries[i].in_tx)
+				type |= X86_BR_IN_TX;
+			else
+				type |= X86_BR_NO_TX;
+		}
 
 		/* if type does not correspond, then discard */
 		if (type == X86_BR_NONE || (br_sel & type) != type) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 52441a2af53..9dd99751ccf 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -536,7 +536,7 @@ __snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *eve
 	if (!uncore_box_is_fake(box))
 		reg1->alloc |= alloc;
 
-	return 0;
+	return NULL;
 fail:
 	for (; i >= 0; i--) {
 		if (alloc & (0x1 << i))
@@ -644,7 +644,7 @@ snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
 	    (!uncore_box_is_fake(box) && reg1->alloc))
 		return NULL;
 again:
-	mask = 0xff << (idx * 8);
+	mask = 0xffULL << (idx * 8);
 	raw_spin_lock_irqsave(&er->lock, flags);
 	if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) ||
 	    !((config1 ^ er->config) & mask)) {
@@ -1923,7 +1923,7 @@ static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modif
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	int idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
+	u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
 	u64 config = reg1->config;
 
 	/* get the non-shared control bits and shift them */
@@ -2723,15 +2723,16 @@ static void uncore_put_event_constraint(struct intel_uncore_box *box, struct per
 static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int n)
 {
 	unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
-	struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX];
+	struct event_constraint *c;
 	int i, wmin, wmax, ret = 0;
 	struct hw_perf_event *hwc;
 
 	bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);
 
 	for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
+		hwc = &box->event_list[i]->hw;
 		c = uncore_get_event_constraint(box, box->event_list[i]);
-		constraints[i] = c;
+		hwc->constraint = c;
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
 	}
@@ -2739,7 +2740,7 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	/* fastpath, try to reuse previous register */
 	for (i = 0; i < n; i++) {
 		hwc = &box->event_list[i]->hw;
-		c = constraints[i];
+		c = hwc->constraint;
 
 		/* never assigned */
 		if (hwc->idx == -1)
@@ -2759,7 +2760,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	}
 	/* slow path */
 	if (i != n)
-		ret = perf_assign_events(constraints, n, wmin, wmax, assign);
+		ret = perf_assign_events(box->event_list, n,
+					 wmin, wmax, assign);
 
 	if (!assign || ret) {
 		for (i = 0; i < n; i++)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index f9528917f6e..47b3d00c9d8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -337,10 +337,10 @@
 		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
 
 #define NHMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 11) - 1) | (1 << 23))
-#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (11 + 3 * (n)))
+#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (11 + 3 * (n)))
 
 #define WSMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 12) - 1) | (1 << 24))
-#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (12 + 3 * (n)))
+#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (12 + 3 * (n)))
 
 /*
  * use the 9~13 bits to select event If the 7th bit is not set,
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 60308053fdb..0920212e615 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -14,6 +14,7 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/nmi.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/hardirq.h>
 #include <linux/slab.h>
@@ -29,6 +30,9 @@
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/nmi.h>
+
 struct nmi_desc {
 	spinlock_t lock;
 	struct list_head head;
@@ -82,6 +86,15 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
 #define nmi_to_desc(type) (&nmi_desc[type])
 
+static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC;
+static int __init nmi_warning_debugfs(void)
+{
+	debugfs_create_u64("nmi_longest_ns", 0644,
+			arch_debugfs_dir, &nmi_longest_ns);
+	return 0;
+}
+fs_initcall(nmi_warning_debugfs);
+
 static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
@@ -96,8 +109,27 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
 	 * can be latched at any given time.  Walk the whole list
 	 * to handle those situations.
 	 */
-	list_for_each_entry_rcu(a, &desc->head, list)
-		handled += a->handler(type, regs);
+	list_for_each_entry_rcu(a, &desc->head, list) {
+		u64 before, delta, whole_msecs;
+		int decimal_msecs, thishandled;
+
+		before = local_clock();
+		thishandled = a->handler(type, regs);
+		handled += thishandled;
+		delta = local_clock() - before;
+		trace_nmi_handler(a->handler, (int)delta, thishandled);
+
+		if (delta < nmi_longest_ns)
+			continue;
+
+		nmi_longest_ns = delta;
+		whole_msecs = do_div(delta, (1000 * 1000));
+		decimal_msecs = do_div(delta, 1000) % 1000;
+		printk_ratelimited(KERN_INFO
+			"INFO: NMI handler (%ps) took too long to run: "
+			"%lld.%03d msecs\n", a->handler, whole_msecs,
+			decimal_msecs);
+	}
 
 	rcu_read_unlock();
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 69562992e45..cf913587d4d 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -43,12 +43,6 @@
 
 #include <asm/sigframe.h>
 
-#ifdef CONFIG_X86_32
-# define FIX_EFLAGS	(__FIX_EFLAGS | X86_EFLAGS_RF)
-#else
-# define FIX_EFLAGS	__FIX_EFLAGS
-#endif
-
 #define COPY(x)			do {			\
 	get_user_ex(regs->x, &sc->x);			\
 } while (0)
@@ -668,15 +662,17 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	if (!failed) {
 		/*
 		 * Clear the direction flag as per the ABI for function entry.
-		 */
-		regs->flags &= ~X86_EFLAGS_DF;
-		/*
+		 *
+		 * Clear RF when entering the signal handler, because
+		 * it might disable possible debug exception from the
+		 * signal handler.
+		 *
 		 * Clear TF when entering the signal handler, but
 		 * notify any tracer that was single-stepping it.
 		 * The tracer may want to single-step inside the
 		 * handler too.
 		 */
-		regs->flags &= ~X86_EFLAGS_TF;
+		regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF);
 	}
 	signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
 }