Merge branch 'perf/core' into perf/uprobes

Merge in latest upstream (and the latest perf development tree),
to prepare for tooling changes, and also to pick up v3.4 MM
changes that the uprobes code needs to take care of.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 152 insertions, 42 deletions

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3bd37bdf1b8..26b3e2fef10 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -385,14 +385,15 @@ static __initconst const u64 westmere_hw_cache_event_ids
 #define NHM_LOCAL_DRAM		(1 << 14)
 #define NHM_NON_DRAM		(1 << 15)
 
-#define NHM_ALL_DRAM		(NHM_REMOTE_DRAM|NHM_LOCAL_DRAM)
+#define NHM_LOCAL		(NHM_LOCAL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_REMOTE		(NHM_REMOTE_DRAM)
 
 #define NHM_DMND_READ		(NHM_DMND_DATA_RD)
 #define NHM_DMND_WRITE		(NHM_DMND_RFO|NHM_DMND_WB)
 #define NHM_DMND_PREFETCH	(NHM_PF_DATA_RD|NHM_PF_DATA_RFO)
 
 #define NHM_L3_HIT	(NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM)
-#define NHM_L3_MISS	(NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_L3_MISS	(NHM_NON_DRAM|NHM_LOCAL_DRAM|NHM_REMOTE_DRAM|NHM_REMOTE_CACHE_FWD)
 #define NHM_L3_ACCESS	(NHM_L3_HIT|NHM_L3_MISS)
 
 static __initconst const u64 nehalem_hw_cache_extra_regs
@@ -416,16 +417,16 @@ static __initconst const u64 nehalem_hw_cache_extra_regs
  },
  [ C(NODE) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_ALL_DRAM,
-		[ C(RESULT_MISS)   ] = NHM_DMND_READ|NHM_REMOTE_DRAM,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_LOCAL|NHM_REMOTE,
+		[ C(RESULT_MISS)   ] = NHM_DMND_READ|NHM_REMOTE,
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_ALL_DRAM,
-		[ C(RESULT_MISS)   ] = NHM_DMND_WRITE|NHM_REMOTE_DRAM,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_LOCAL|NHM_REMOTE,
+		[ C(RESULT_MISS)   ] = NHM_DMND_WRITE|NHM_REMOTE,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_ALL_DRAM,
-		[ C(RESULT_MISS)   ] = NHM_DMND_PREFETCH|NHM_REMOTE_DRAM,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_LOCAL|NHM_REMOTE,
+		[ C(RESULT_MISS)   ] = NHM_DMND_PREFETCH|NHM_REMOTE,
 	},
  },
 };
@@ -727,6 +728,19 @@ static __initconst const u64 atom_hw_cache_event_ids
  },
 };
 
+static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
+{
+	/* user explicitly requested branch sampling */
+	if (has_branch_stack(event))
+		return true;
+
+	/* implicit branch sampling to correct PEBS skid */
+	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
+		return true;
+
+	return false;
+}
+
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -881,6 +895,13 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 
+	/*
+	 * must disable before any actual event
+	 * because any event may be combined with LBR
+	 */
+	if (intel_pmu_needs_lbr_smpl(event))
+		intel_pmu_lbr_disable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
@@ -935,6 +956,12 @@ static void intel_pmu_enable_event(struct perf_event *event)
 		intel_pmu_enable_bts(hwc->config);
 		return;
 	}
+	/*
+	 * must enabled before any actual event
+	 * because any event may be combined with LBR
+	 */
+	if (intel_pmu_needs_lbr_smpl(event))
+		intel_pmu_lbr_enable(event);
 
 	if (event->attr.exclude_host)
 		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
@@ -1057,6 +1084,9 @@ again:
 
 		data.period = event->hw.last_period;
 
+		if (has_branch_stack(event))
+			data.br_stack = &cpuc->lbr_stack;
+
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
@@ -1123,17 +1153,17 @@ static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
  */
 static struct event_constraint *
 __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
-				   struct perf_event *event)
+				   struct perf_event *event,
+				   struct hw_perf_event_extra *reg)
 {
 	struct event_constraint *c = &emptyconstraint;
-	struct hw_perf_event_extra *reg = &event->hw.extra_reg;
 	struct er_account *era;
 	unsigned long flags;
 	int orig_idx = reg->idx;
 
 	/* already allocated shared msr */
 	if (reg->alloc)
-		return &unconstrained;
+		return NULL; /* call x86_get_event_constraint() */
 
 again:
 	era = &cpuc->shared_regs->regs[reg->idx];
@@ -1156,14 +1186,10 @@ again:
 		reg->alloc = 1;
 
 		/*
-		 * All events using extra_reg are unconstrained.
-		 * Avoids calling x86_get_event_constraints()
-		 *
-		 * Must revisit if extra_reg controlling events
-		 * ever have constraints. Worst case we go through
-		 * the regular event constraint table.
+		 * need to call x86_get_event_constraint()
+		 * to check if associated event has constraints
 		 */
-		c = &unconstrained;
+		c = NULL;
 	} else if (intel_try_alt_er(event, orig_idx)) {
 		raw_spin_unlock_irqrestore(&era->lock, flags);
 		goto again;
@@ -1200,11 +1226,23 @@ static struct event_constraint *
 intel_shared_regs_constraints(struct cpu_hw_events *cpuc,
 			      struct perf_event *event)
 {
-	struct event_constraint *c = NULL;
-
-	if (event->hw.extra_reg.idx != EXTRA_REG_NONE)
-		c = __intel_shared_reg_get_constraints(cpuc, event);
-
+	struct event_constraint *c = NULL, *d;
+	struct hw_perf_event_extra *xreg, *breg;
+
+	xreg = &event->hw.extra_reg;
+	if (xreg->idx != EXTRA_REG_NONE) {
+		c = __intel_shared_reg_get_constraints(cpuc, event, xreg);
+		if (c == &emptyconstraint)
+			return c;
+	}
+	breg = &event->hw.branch_reg;
+	if (breg->idx != EXTRA_REG_NONE) {
+		d = __intel_shared_reg_get_constraints(cpuc, event, breg);
+		if (d == &emptyconstraint) {
+			__intel_shared_reg_put_constraints(cpuc, xreg);
+			c = d;
+		}
+	}
 	return c;
 }
 
@@ -1252,6 +1290,10 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
 	reg = &event->hw.extra_reg;
 	if (reg->idx != EXTRA_REG_NONE)
 		__intel_shared_reg_put_constraints(cpuc, reg);
+
+	reg = &event->hw.branch_reg;
+	if (reg->idx != EXTRA_REG_NONE)
+		__intel_shared_reg_put_constraints(cpuc, reg);
 }
 
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
@@ -1287,12 +1329,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		 *
 		 * Thereby we gain a PEBS capable cycle counter.
 		 */
-		u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */
+		u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
+
 
 		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
 		event->hw.config = alt_config;
 	}
 
+	if (intel_pmu_needs_lbr_smpl(event)) {
+		ret = intel_pmu_setup_lbr_filter(event);
+		if (ret)
+			return ret;
+	}
+
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
@@ -1382,6 +1431,24 @@ static void core_pmu_enable_all(int added)
 	}
 }
 
+PMU_FORMAT_ATTR(event,	"config:0-7"	);
+PMU_FORMAT_ATTR(umask,	"config:8-15"	);
+PMU_FORMAT_ATTR(edge,	"config:18"	);
+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"	);
+
+static struct attribute *intel_arch_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_pc.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -1406,6 +1473,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.put_event_constraints	= intel_put_event_constraints,
 	.event_constraints	= intel_core_event_constraints,
 	.guest_get_msrs		= core_guest_get_msrs,
+	.format_attrs		= intel_arch_formats_attr,
 };
 
 struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1431,7 +1499,7 @@ static int intel_pmu_cpu_prepare(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 
-	if (!x86_pmu.extra_regs)
+	if (!(x86_pmu.extra_regs || x86_pmu.lbr_sel_map))
 		return NOTIFY_OK;
 
 	cpuc->shared_regs = allocate_shared_regs(cpu);
@@ -1453,22 +1521,28 @@ static void intel_pmu_cpu_starting(int cpu)
 	 */
 	intel_pmu_lbr_reset();
 
-	if (!cpuc->shared_regs || (x86_pmu.er_flags & ERF_NO_HT_SHARING))
+	cpuc->lbr_sel = NULL;
+
+	if (!cpuc->shared_regs)
 		return;
 
-	for_each_cpu(i, topology_thread_cpumask(cpu)) {
-		struct intel_shared_regs *pc;
+	if (!(x86_pmu.er_flags & ERF_NO_HT_SHARING)) {
+		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+			struct intel_shared_regs *pc;
 
-		pc = per_cpu(cpu_hw_events, i).shared_regs;
-		if (pc && pc->core_id == core_id) {
-			cpuc->kfree_on_online = cpuc->shared_regs;
-			cpuc->shared_regs = pc;
-			break;
+			pc = per_cpu(cpu_hw_events, i).shared_regs;
+			if (pc && pc->core_id == core_id) {
+				cpuc->kfree_on_online = cpuc->shared_regs;
+				cpuc->shared_regs = pc;
+				break;
+			}
 		}
+		cpuc->shared_regs->core_id = core_id;
+		cpuc->shared_regs->refcnt++;
 	}
 
-	cpuc->shared_regs->core_id = core_id;
-	cpuc->shared_regs->refcnt++;
+	if (x86_pmu.lbr_sel_map)
+		cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
 }
 
 static void intel_pmu_cpu_dying(int cpu)
@@ -1486,6 +1560,33 @@ static void intel_pmu_cpu_dying(int cpu)
 	fini_debug_store_on_cpu(cpu);
 }
 
+static void intel_pmu_flush_branch_stack(void)
+{
+	/*
+	 * Intel LBR does not tag entries with the
+	 * PID of the current task, then we need to
+	 * flush it on ctxsw
+	 * For now, we simply reset it
+	 */
+	if (x86_pmu.lbr_nr)
+		intel_pmu_lbr_reset();
+}
+
+PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
+
+static struct attribute *intel_arch3_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_pc.attr,
+	&format_attr_any.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+
+	&format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
+	NULL,
+};
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
@@ -1509,10 +1610,13 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.get_event_constraints	= intel_get_event_constraints,
 	.put_event_constraints	= intel_put_event_constraints,
 
+	.format_attrs		= intel_arch3_formats_attr,
+
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.guest_get_msrs		= intel_guest_get_msrs,
+	.flush_branch_stack	= intel_pmu_flush_branch_stack,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -1689,9 +1793,11 @@ __init int intel_pmu_init(void)
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
 
 		/* UOPS_ISSUED.STALLED_CYCLES */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
 		/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
 		x86_add_quirk(intel_nehalem_quirk);
 
@@ -1726,9 +1832,11 @@ __init int intel_pmu_init(void)
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 
 		/* UOPS_ISSUED.STALLED_CYCLES */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
 		/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
 		pr_cont("Westmere events, ");
 		break;
@@ -1739,7 +1847,7 @@ __init int intel_pmu_init(void)
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
-		intel_pmu_lbr_init_nhm();
+		intel_pmu_lbr_init_snb();
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
@@ -1749,9 +1857,11 @@ __init int intel_pmu_init(void)
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
 
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
 		/* UOPS_DISPATCHED.THREAD,c=1,i=1 to count stall cycles*/
-		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x18001b1;
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1);
 
 		pr_cont("SandyBridge events, ");
 		break;