Basic perf PMU support for Haswell v3

Basic perf PMU support for Haswell v3

[Andi Kleen]

This is based on v7 of the full Haswell PMU support, but 
ported to the latest perf/core and stripped down to the
extreme "perf for dummies" edition as requested.  

I removed some more patches, these will come soon later.
I moved parts of an later patch (counter constraints for qualifiers) 
into an earlier patch, to support the full raw bits at least.

For anything beyond basic usage this is not very useful.
I expect speedy merging of the other parts now.
No git branch, because it doesn't make sense to have that 
many branches.

Contains support for:
- Basic Haswell PMU and PEBS support
- Late unmasking of the PMI
- Support for wide counters

v2: Addressed Stephane's feedback. See individual patches for details.
v3: now even more bite-sized. Qualifier constraints merged earlier.
Add some Reviewed-bys.

-Andi

[PATCH 1/5] perf, x86: Add PEBSv2 record support

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add support for the v2 PEBS format. It has a superset of the v1 PEBS
fields, but has a longer record so we need to adjust the code paths.

The main advantage is the new "EventingRip" support which directly
gives the instruction, not off-by-one instruction. So with precise == 2
we use that directly and don't try to use LBRs and walking basic blocks.
This lowers the overhead significantly.

Some other features are added in later patches.

Reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event.c          |    2 +-
 arch/x86/kernel/cpu/perf_event_intel_ds.c |  101 ++++++++++++++++++++++-------
 2 files changed, 79 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6774c17..c95290a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -397,7 +397,7 @@ 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)) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 826054a..9d0dae0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -41,6 +41,12 @@ struct pebs_record_nhm {
 	u64 status, dla, dse, lat;
 };
 
+struct pebs_record_v2 {
+	struct pebs_record_nhm nhm;
+	u64 eventingrip;
+	u64 tsx_tuning;
+};
+
 void init_debug_store_on_cpu(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -559,8 +565,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 {
 	/*
 	 * We cast to pebs_record_core since that is a subset of
-	 * both formats and we don't use the other fields in this
-	 * routine.
+	 * both formats.
 	 */
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct pebs_record_core *pebs = __pebs;
@@ -588,7 +593,10 @@ 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 = ((struct pebs_record_v2 *)pebs)->eventingrip;
+		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;
@@ -641,35 +649,21 @@ 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_common(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;
@@ -692,6 +686,61 @@ 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_common(iregs, at, top);
+}
+
+static void intel_pmu_drain_pebs_v2(struct pt_regs *iregs)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct pebs_record_v2 *at, *top;
+	int n;
+
+	if (!x86_pmu.pebs_active)
+		return;
+
+	at  = (struct pebs_record_v2 *)(unsigned long)ds->pebs_buffer_base;
+	top = (struct pebs_record_v2 *)(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_common(iregs, at, top);
+}
+
 /*
  * BTS, PEBS probe and setup
  */
@@ -723,6 +772,12 @@ void intel_ds_init(void)
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
 			break;
 
+		case 2:
+			printk(KERN_CONT "PEBS fmt2%c, ", pebs_type);
+			x86_pmu.pebs_record_size = sizeof(struct pebs_record_v2);
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_v2;
+			break;
+
 		default:
 			printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
 			x86_pmu.pebs = 0;
-- 
1.7.7.6

[PATCH 2/5] perf, x86: Basic Haswell PMU support v4

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add basic Haswell PMU support.

Similar to SandyBridge, but has a few new events and two
new counter bits.

There are some new counter flags that need to be prevented
from being set on fixed counters, and allowed to be set
for generic counters.

Also we add support for the counter 2 constraint to handle
all raw events.

Contains fixes from Stephane Eranian

v2: Folded TSX bits into standard FIXED_EVENT_CONSTRAINTS
v3: Use SNB LBR init code. Comment fix (Stephane Eranian)
v4: Add the counter2 constraints. Fix comment in the right place.
Reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/include/asm/perf_event.h      |    3 +
 arch/x86/kernel/cpu/perf_event.h       |    5 ++-
 arch/x86/kernel/cpu/perf_event_intel.c |   71 ++++++++++++++++++++++++++++++++
 3 files changed, 78 insertions(+), 1 deletions(-)

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 4fabcdf..4003bb6 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_INTX					(1ULL << 32)
+#define HSW_INTX_CHECKPOINTED				(1ULL << 33)
+
 #define AMD_PERFMON_EVENTSEL_GUESTONLY			(1ULL << 40)
 #define AMD_PERFMON_EVENTSEL_HOSTONLY			(1ULL << 41)
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 115c1ea..8941899 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -219,11 +219,14 @@ struct cpu_hw_events {
  *  - inv
  *  - edge
  *  - cnt-mask
+ *  - intx
+ *  - intx_cp
  *  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_INTX|HSW_INTX_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
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 93b9e11..58b737d 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>
 
@@ -133,6 +134,17 @@ static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+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 */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -1585,6 +1597,45 @@ 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_INTX|HSW_INTX_CHECKPOINTED);
+
+	/*
+	 * INTX/INTX-CP do not play well with PEBS or ANY thread mode.
+	 */
+	if ((event->hw.config & (HSW_INTX|HSW_INTX_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 intx_checkpointed only in counter 2 */
+	if (event->hw.config & HSW_INTX_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"	);
@@ -2107,6 +2158,26 @@ __init int intel_pmu_init(void)
 		break;
 
 
+	case 60: /* Haswell Client */
+	case 70:
+	case 71:
+		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_hsw_event_constraints;
+
+		x86_pmu.extra_regs = intel_snb_extra_regs;
+		/* 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;
+		pr_cont("Haswell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
-- 
1.7.7.6

[PATCH 3/5] perf, x86: Basic Haswell PEBS support v4

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add basic PEBS support for Haswell.
The constraints are similar to SandyBridge with a few new events.

v2: Readd missing pebs_aliases
v3: Readd missing hunk. Fix some constraints.
v4: Fix typo in PEBS event table (Stephane Eranian)
Reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event.h          |    2 ++
 arch/x86/kernel/cpu/perf_event_intel.c    |    6 ++++--
 arch/x86/kernel/cpu/perf_event_intel_ds.c |   29 +++++++++++++++++++++++++++++
 3 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8941899..1567b0d 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -596,6 +596,8 @@ 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_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 58b737d..aa48048 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -827,7 +827,8 @@ 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;
@@ -2167,8 +2168,9 @@ __init int intel_pmu_init(void)
 		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;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 9d0dae0..0252930 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -427,6 +427,35 @@ 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_UEVENT_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_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
+	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
+	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */
+	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
+	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
+	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */
+	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
+	INTEL_UEVENT_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 */
+	INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
+	INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
+	INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
+	INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */
+	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;
-- 
1.7.7.6

[PATCH 4/5] perf, x86: Support full width counting

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Recent Intel CPUs have a new alternative MSR range for perfctrs that allows
writing the full counter width. Enable this range if the hardware reports it
using a new capability bit. This lowers overhead of perf stat slightly because
it has to do less interrupts to accumulate the counter value. On Haswell it
also avoids some problems with TSX aborting when the end of the counter
range is reached.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/include/uapi/asm/msr-index.h  |    3 +++
 arch/x86/kernel/cpu/perf_event.h       |    1 +
 arch/x86/kernel/cpu/perf_event_intel.c |    6 ++++++
 3 files changed, 10 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 433a59f..af41a77 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -163,6 +163,9 @@
 #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/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 1567b0d..ce2a863 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -278,6 +278,7 @@ union perf_capabilities {
 		u64	pebs_arch_reg:1;
 		u64	pebs_format:4;
 		u64	smm_freeze:1;
+		u64	fw_write:1;
 	};
 	u64	capabilities;
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index aa48048..d96010a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2228,5 +2228,11 @@ __init int intel_pmu_init(void)
 		}
 	}
 
+	/* Support full width counters using alternative MSR range */
+	if (x86_pmu.intel_cap.fw_write) {
+		x86_pmu.max_period = x86_pmu.cntval_mask;
+		x86_pmu.perfctr = MSR_IA32_PMC0;
+	}
+
 	return 0;
 }
-- 
1.7.7.6

[PATCH 5/5] perf, x86: Move NMI clearing to end of PMI handler after the counter registers are reset

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

This avoids some problems with spurious PMIs on Haswell.
Haswell seems to behave more like P4 in this regard. Do
the same thing as the P4 perf handler by unmasking
the NMI only at the end. Shouldn't make any difference
for earlier non P4 cores.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c |   15 +++++----------
 1 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index d96010a..33fc662 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1122,16 +1122,6 @@ 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.
-	 */
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-
 	intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
@@ -1191,6 +1181,11 @@ again:
 
 done:
 	intel_pmu_enable_all(0);
+	/*
+	 * Only unmask the NMI after the overflow counters
+	 * have been reset.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
 	return handled;
 }
 
-- 
1.7.7.6

Re: [PATCH 1/5] perf, x86: Add PEBSv2 record support

[Ingo Molnar]

* Andi Kleen <andi@firstfloor.org> wrote:

> From: Andi Kleen <ak@linux.intel.com>
> 
> Add support for the v2 PEBS format. It has a superset of the v1 PEBS
> fields, but has a longer record so we need to adjust the code paths.
> 
> The main advantage is the new "EventingRip" support which directly
> gives the instruction, not off-by-one instruction. So with precise == 2
> we use that directly and don't try to use LBRs and walking basic blocks.
> This lowers the overhead significantly.
> 
> Some other features are added in later patches.
> 
> Reviewed-by: Stephane Eranian <eranian@google.com>
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  arch/x86/kernel/cpu/perf_event.c          |    2 +-
>  arch/x86/kernel/cpu/perf_event_intel_ds.c |  101 ++++++++++++++++++++++-------
>  2 files changed, 79 insertions(+), 24 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
> index 6774c17..c95290a 100644
> --- a/arch/x86/kernel/cpu/perf_event.c
> +++ b/arch/x86/kernel/cpu/perf_event.c
> @@ -397,7 +397,7 @@ 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)) {
> diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
> index 826054a..9d0dae0 100644
> --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
> @@ -41,6 +41,12 @@ struct pebs_record_nhm {
>  	u64 status, dla, dse, lat;
>  };
>  
> +struct pebs_record_v2 {
> +	struct pebs_record_nhm nhm;
> +	u64 eventingrip;
> +	u64 tsx_tuning;

'eventingrip' should be something more readable and obvious. 
Also, comments for fields are needed when introducing new 
structs.

> +};
> +
>  void init_debug_store_on_cpu(int cpu)
>  {
>  	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
> @@ -559,8 +565,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
>  {
>  	/*
>  	 * We cast to pebs_record_core since that is a subset of
> -	 * both formats and we don't use the other fields in this
> -	 * routine.
> +	 * both formats.
>  	 */
>  	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
>  	struct pebs_record_core *pebs = __pebs;
> @@ -588,7 +593,10 @@ 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 = ((struct pebs_record_v2 *)pebs)->eventingrip;
> +		regs.flags |= PERF_EFLAGS_EXACT;

Here you messed up the record types in this function with the 
introduction of the new pebs record format quite a bit.

First we have 'pebs' as type 'struct pebs_record_core *', but 
here it's cast over to 'struct pebs_record_v2 *' just to access 
a field that is not really in the pebs_record_core format...

If we continue down that road then code quickly becomes an 
unmaintainable mess. I'm sure you can think of a better,
cleaner solution than mixing types and forcing casts like
that.

> +	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
>  		regs.flags |= PERF_EFLAGS_EXACT;
>  	else
>  		regs.flags &= ~PERF_EFLAGS_EXACT;
> @@ -641,35 +649,21 @@ 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_common(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;

This function shows record type confusion as well: the function 
got renamed from intel_pmu_drain_pebs_nhm() to 
intel_pmu_drain_pebs_common(), but then it deals with 
pebs_record_nhm - which is obviously not 'common'.

> +		case 2:
> +			printk(KERN_CONT "PEBS fmt2%c, ", pebs_type);
> +			x86_pmu.pebs_record_size = sizeof(struct pebs_record_v2);
> +			x86_pmu.drain_pebs = intel_pmu_drain_pebs_v2;
> +			break;
> +

That's inconsistent too - the data types and the code talks 
about 'PEBS v2' but here it's printed out to the kernel log as 
'PEBS fmt2'. Death by a thousand cuts of sloppiness and all 
that.

Thanks,

	Ingo