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 ...
2026-03-06 15:25:10 -08:00 · 2013-07-02 16:15:23 -07:00
parent a4883ef6af 983433b581
commit f0bb4c0ab0
71 changed files with 2949 additions and 1055 deletions
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -27,14 +27,36 @@ Description:	Generic performance monitoring events
 		"basename".


-What: 		/sys/devices/cpu/events/PM_LD_MISS_L1
-		/sys/devices/cpu/events/PM_LD_REF_L1
-		/sys/devices/cpu/events/PM_CYC
+What: 		/sys/devices/cpu/events/PM_1PLUS_PPC_CMPL
 		/sys/devices/cpu/events/PM_BRU_FIN
-		/sys/devices/cpu/events/PM_GCT_NOSLOT_CYC
 		/sys/devices/cpu/events/PM_BRU_MPRED
-		/sys/devices/cpu/events/PM_INST_CMPL
 		/sys/devices/cpu/events/PM_CMPLU_STALL
+		/sys/devices/cpu/events/PM_CMPLU_STALL_BRU
+		/sys/devices/cpu/events/PM_CMPLU_STALL_DCACHE_MISS
+		/sys/devices/cpu/events/PM_CMPLU_STALL_DFU
+		/sys/devices/cpu/events/PM_CMPLU_STALL_DIV
+		/sys/devices/cpu/events/PM_CMPLU_STALL_ERAT_MISS
+		/sys/devices/cpu/events/PM_CMPLU_STALL_FXU
+		/sys/devices/cpu/events/PM_CMPLU_STALL_IFU
+		/sys/devices/cpu/events/PM_CMPLU_STALL_LSU
+		/sys/devices/cpu/events/PM_CMPLU_STALL_REJECT
+		/sys/devices/cpu/events/PM_CMPLU_STALL_SCALAR
+		/sys/devices/cpu/events/PM_CMPLU_STALL_SCALAR_LONG
+		/sys/devices/cpu/events/PM_CMPLU_STALL_STORE
+		/sys/devices/cpu/events/PM_CMPLU_STALL_THRD
+		/sys/devices/cpu/events/PM_CMPLU_STALL_VECTOR
+		/sys/devices/cpu/events/PM_CMPLU_STALL_VECTOR_LONG
+		/sys/devices/cpu/events/PM_CYC
+		/sys/devices/cpu/events/PM_GCT_NOSLOT_BR_MPRED
+		/sys/devices/cpu/events/PM_GCT_NOSLOT_BR_MPRED_IC_MISS
+		/sys/devices/cpu/events/PM_GCT_NOSLOT_CYC
+		/sys/devices/cpu/events/PM_GCT_NOSLOT_IC_MISS
+		/sys/devices/cpu/events/PM_GRP_CMPL
+		/sys/devices/cpu/events/PM_INST_CMPL
+		/sys/devices/cpu/events/PM_LD_MISS_L1
+		/sys/devices/cpu/events/PM_LD_REF_L1
+		/sys/devices/cpu/events/PM_RUN_CYC
+		/sys/devices/cpu/events/PM_RUN_INST_CMPL

 Date:		2013/01/08

--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
@@ -9,6 +9,12 @@ Description:
 		we want to export, so that userspace can deal with sane
 		name/value pairs.

+		Userspace must be prepared for the possibility that attributes
+		define overlapping bit ranges. For example:
+			attr1 = 'config:0-23'
+			attr2 = 'config:0-7'
+			attr3 = 'config:12-35'
+
 		Example: 'config1:1,6-10,44'
 		Defines contents of attribute that occupies bits 1,6-10,44 of
 		perf_event_attr::config1.
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -70,12 +70,12 @@ show up in /proc/sys/kernel:
 - shmall
 - shmmax                      [ sysv ipc ]
 - shmmni
- softlockup_thresh
 - stop-a                      [ SPARC only ]
 - sysrq                       ==> Documentation/sysrq.txt
 - tainted
 - threads-max
 - unknown_nmi_panic
+- watchdog_thresh
 - version

 ==============================================================
@@ -427,6 +427,32 @@ This file shows up if CONFIG_DEBUG_STACKOVERFLOW is enabled.

 ==============================================================

+perf_cpu_time_max_percent:
+
+Hints to the kernel how much CPU time it should be allowed to
+use to handle perf sampling events.  If the perf subsystem
+is informed that its samples are exceeding this limit, it
+will drop its sampling frequency to attempt to reduce its CPU
+usage.
+
+Some perf sampling happens in NMIs.  If these samples
+unexpectedly take too long to execute, the NMIs can become
+stacked up next to each other so much that nothing else is
+allowed to execute.
+
+0: disable the mechanism.  Do not monitor or correct perf's
+   sampling rate no matter how CPU time it takes.
+
+1-100: attempt to throttle perf's sample rate to this
+   percentage of CPU.  Note: the kernel calculates an
+   "expected" length of each sample event.  100 here means
+   100% of that expected length.  Even if this is set to
+   100, you may still see sample throttling if this
+   length is exceeded.  Set to 0 if you truly do not care
+   how much CPU is consumed.
+
+==============================================================
+

 pid_max:

@@ -604,15 +630,6 @@ without users and with a dead originative process will be destroyed.

 ==============================================================

-softlockup_thresh:
-
-This value can be used to lower the softlockup tolerance threshold.  The
-default threshold is 60 seconds.  If a cpu is locked up for 60 seconds,
-the kernel complains.  Valid values are 1-60 seconds.  Setting this
-tunable to zero will disable the softlockup detection altogether.
-
-==============================================================
-
 tainted:

 Non-zero if the kernel has been tainted.  Numeric values, which
@@ -648,3 +665,16 @@ that time, kernel debugging information is displayed on console.

 NMI switch that most IA32 servers have fires unknown NMI up, for
 example.  If a system hangs up, try pressing the NMI switch.
+
+==============================================================
+
+watchdog_thresh:
+
+This value can be used to control the frequency of hrtimer and NMI
+events and the soft and hard lockup thresholds. The default threshold
+is 10 seconds.
+
+The softlockup threshold is (2 * watchdog_thresh). Setting this
+tunable to zero will disable lockup detection altogether.
+
+==============================================================
--- a/Documentation/trace/events-nmi.txt
+++ b/Documentation/trace/events-nmi.txt
@@ -0,0 +1,43 @@
+NMI Trace Events
+
+These events normally show up here:
+
+	/sys/kernel/debug/tracing/events/nmi
+
+--
+
+nmi_handler:
+
+You might want to use this tracepoint if you suspect that your
+NMI handlers are hogging large amounts of CPU time.  The kernel
+will warn if it sees long-running handlers:
+
+	INFO: NMI handler took too long to run: 9.207 msecs
+
+and this tracepoint will allow you to drill down and get some
+more details.
+
+Let's say you suspect that perf_event_nmi_handler() is causing
+you some problems and you only want to trace that handler
+specifically.  You need to find its address:
+
+	$ grep perf_event_nmi_handler /proc/kallsyms
+	ffffffff81625600 t perf_event_nmi_handler
+
+Let's also say you are only interested in when that function is
+really hogging a lot of CPU time, like a millisecond at a time.
+Note that the kernel's output is in milliseconds, but the input
+to the filter is in nanoseconds!  You can filter on 'delta_ns':
+
+cd /sys/kernel/debug/tracing/events/nmi/nmi_handler
+echo 'handler==0xffffffff81625600 && delta_ns>1000000' > filter
+echo 1 > enable
+
+Your output would then look like:
+
+$ cat /sys/kernel/debug/tracing/trace_pipe
+<idle>-0     [000] d.h3   505.397558: nmi_handler: perf_event_nmi_handler() delta_ns: 3236765 handled: 1
+<idle>-0     [000] d.h3   505.805893: nmi_handler: perf_event_nmi_handler() delta_ns: 3174234 handled: 1
+<idle>-0     [000] d.h3   506.158206: nmi_handler: perf_event_nmi_handler() delta_ns: 3084642 handled: 1
+<idle>-0     [000] d.h3   506.334346: nmi_handler: perf_event_nmi_handler() delta_ns: 3080351 handled: 1
+
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -882,7 +882,7 @@ static int __init init_hw_perf_events(void)
 	}

 	register_cpu_notifier(&metag_pmu_notifier);
-	ret = perf_pmu_register(&pmu, (char *)metag_pmu->name, PERF_TYPE_RAW);
+	ret = perf_pmu_register(&pmu, metag_pmu->name, PERF_TYPE_RAW);
 out:
 	return ret;
 }
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -62,6 +62,29 @@
 #define	PME_PM_BRU_FIN			0x10068
 #define	PME_PM_BRU_MPRED		0x400f6

+#define PME_PM_CMPLU_STALL_FXU			0x20014
+#define PME_PM_CMPLU_STALL_DIV			0x40014
+#define PME_PM_CMPLU_STALL_SCALAR		0x40012
+#define PME_PM_CMPLU_STALL_SCALAR_LONG		0x20018
+#define PME_PM_CMPLU_STALL_VECTOR		0x2001c
+#define PME_PM_CMPLU_STALL_VECTOR_LONG		0x4004a
+#define PME_PM_CMPLU_STALL_LSU			0x20012
+#define PME_PM_CMPLU_STALL_REJECT		0x40016
+#define PME_PM_CMPLU_STALL_ERAT_MISS		0x40018
+#define PME_PM_CMPLU_STALL_DCACHE_MISS		0x20016
+#define PME_PM_CMPLU_STALL_STORE		0x2004a
+#define PME_PM_CMPLU_STALL_THRD			0x1001c
+#define PME_PM_CMPLU_STALL_IFU			0x4004c
+#define PME_PM_CMPLU_STALL_BRU			0x4004e
+#define PME_PM_GCT_NOSLOT_IC_MISS		0x2001a
+#define PME_PM_GCT_NOSLOT_BR_MPRED		0x4001a
+#define PME_PM_GCT_NOSLOT_BR_MPRED_IC_MISS	0x4001c
+#define PME_PM_GRP_CMPL				0x30004
+#define PME_PM_1PLUS_PPC_CMPL			0x100f2
+#define PME_PM_CMPLU_STALL_DFU			0x2003c
+#define PME_PM_RUN_CYC				0x200f4
+#define PME_PM_RUN_INST_CMPL			0x400fa
+
 /*
 * Layout of constraint bits:
 * 6666555555555544444444443333333333222222222211111111110000000000
@@ -393,6 +416,31 @@ POWER_EVENT_ATTR(LD_MISS_L1,			LD_MISS_L1);
 POWER_EVENT_ATTR(BRU_FIN,			BRU_FIN)
 POWER_EVENT_ATTR(BRU_MPRED,			BRU_MPRED);

+POWER_EVENT_ATTR(CMPLU_STALL_FXU,		CMPLU_STALL_FXU);
+POWER_EVENT_ATTR(CMPLU_STALL_DIV,		CMPLU_STALL_DIV);
+POWER_EVENT_ATTR(CMPLU_STALL_SCALAR,		CMPLU_STALL_SCALAR);
+POWER_EVENT_ATTR(CMPLU_STALL_SCALAR_LONG,	CMPLU_STALL_SCALAR_LONG);
+POWER_EVENT_ATTR(CMPLU_STALL_VECTOR,		CMPLU_STALL_VECTOR);
+POWER_EVENT_ATTR(CMPLU_STALL_VECTOR_LONG,	CMPLU_STALL_VECTOR_LONG);
+POWER_EVENT_ATTR(CMPLU_STALL_LSU,		CMPLU_STALL_LSU);
+POWER_EVENT_ATTR(CMPLU_STALL_REJECT,		CMPLU_STALL_REJECT);
+
+POWER_EVENT_ATTR(CMPLU_STALL_ERAT_MISS,		CMPLU_STALL_ERAT_MISS);
+POWER_EVENT_ATTR(CMPLU_STALL_DCACHE_MISS,	CMPLU_STALL_DCACHE_MISS);
+POWER_EVENT_ATTR(CMPLU_STALL_STORE,		CMPLU_STALL_STORE);
+POWER_EVENT_ATTR(CMPLU_STALL_THRD,		CMPLU_STALL_THRD);
+POWER_EVENT_ATTR(CMPLU_STALL_IFU,		CMPLU_STALL_IFU);
+POWER_EVENT_ATTR(CMPLU_STALL_BRU,		CMPLU_STALL_BRU);
+POWER_EVENT_ATTR(GCT_NOSLOT_IC_MISS,		GCT_NOSLOT_IC_MISS);
+
+POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED,		GCT_NOSLOT_BR_MPRED);
+POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED_IC_MISS,	GCT_NOSLOT_BR_MPRED_IC_MISS);
+POWER_EVENT_ATTR(GRP_CMPL,			GRP_CMPL);
+POWER_EVENT_ATTR(1PLUS_PPC_CMPL,		1PLUS_PPC_CMPL);
+POWER_EVENT_ATTR(CMPLU_STALL_DFU,		CMPLU_STALL_DFU);
+POWER_EVENT_ATTR(RUN_CYC,			RUN_CYC);
+POWER_EVENT_ATTR(RUN_INST_CMPL,			RUN_INST_CMPL);
+
 static struct attribute *power7_events_attr[] = {
 	GENERIC_EVENT_PTR(CYC),
 	GENERIC_EVENT_PTR(GCT_NOSLOT_CYC),
@@ -411,6 +459,31 @@ static struct attribute *power7_events_attr[] = {
 	POWER_EVENT_PTR(LD_MISS_L1),
 	POWER_EVENT_PTR(BRU_FIN),
 	POWER_EVENT_PTR(BRU_MPRED),
+
+	POWER_EVENT_PTR(CMPLU_STALL_FXU),
+	POWER_EVENT_PTR(CMPLU_STALL_DIV),
+	POWER_EVENT_PTR(CMPLU_STALL_SCALAR),
+	POWER_EVENT_PTR(CMPLU_STALL_SCALAR_LONG),
+	POWER_EVENT_PTR(CMPLU_STALL_VECTOR),
+	POWER_EVENT_PTR(CMPLU_STALL_VECTOR_LONG),
+	POWER_EVENT_PTR(CMPLU_STALL_LSU),
+	POWER_EVENT_PTR(CMPLU_STALL_REJECT),
+
+	POWER_EVENT_PTR(CMPLU_STALL_ERAT_MISS),
+	POWER_EVENT_PTR(CMPLU_STALL_DCACHE_MISS),
+	POWER_EVENT_PTR(CMPLU_STALL_STORE),
+	POWER_EVENT_PTR(CMPLU_STALL_THRD),
+	POWER_EVENT_PTR(CMPLU_STALL_IFU),
+	POWER_EVENT_PTR(CMPLU_STALL_BRU),
+	POWER_EVENT_PTR(GCT_NOSLOT_IC_MISS),
+	POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED),
+
+	POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED_IC_MISS),
+	POWER_EVENT_PTR(GRP_CMPL),
+	POWER_EVENT_PTR(1PLUS_PPC_CMPL),
+	POWER_EVENT_PTR(CMPLU_STALL_DFU),
+	POWER_EVENT_PTR(RUN_CYC),
+	POWER_EVENT_PTR(RUN_INST_CMPL),
 	NULL
 };

--- 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;
--- 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)
--- 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);

--- 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. */

--- 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/

--- 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;
@@ -1152,6 +1174,11 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	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
@@ -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;
--- 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);
--- 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)
-		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
-	return 0;
-}
+	if (!cpu_has_perfctr_core)
+		return 0;

-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!");
+	switch (boot_cpu_data.x86) {
+	case 0x15:
+		pr_cont("Fam15h ");
+		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
+		break;
+
+	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,
--- a/arch/x86/kernel/cpu/perf_event_amd_iommu.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
--- a/arch/x86/kernel/cpu/perf_event_amd_iommu.h
+++ 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_*/
--- 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;
 }
--- 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;
+	for (; at < top; at += x86_pmu.pebs_record_size) {
+		struct pebs_record_nhm *p = at;

-	/*
-	 * 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++) {
-		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;
--- 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) {
--- 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++)
--- a/Show More
+++ b/Show More