Merge branch 'perf/hw-branch-sampling' into perf/core

Merge reason: The 'perf record -b' hardware branch sampling feature is ready for upstream.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/cpu/perf_event.c

@@ -353,6 +353,36 @@ int x86_setup_perfctr(struct perf_event *event)
 	return 0;
 }
 
+/*
+ * check that branch_sample_type is compatible with
+ * settings needed for precise_ip > 1 which implies
+ * using the LBR to capture ALL taken branches at the
+ * priv levels of the measurement
+ */
+static inline int precise_br_compat(struct perf_event *event)
+{
+	u64 m = event->attr.branch_sample_type;
+	u64 b = 0;
+
+	/* must capture all branches */
+	if (!(m & PERF_SAMPLE_BRANCH_ANY))
+		return 0;
+
+	m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_user)
+		b |= PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_kernel)
+		b |= PERF_SAMPLE_BRANCH_KERNEL;
+
+	/*
+	 * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86
+	 */
+
+	return m == b;
+}
+
 int x86_pmu_hw_config(struct perf_event *event)
 {
 	if (event->attr.precise_ip) {
@@ -369,6 +399,36 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+		/*
+		 * 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) {
+			u64 *br_type = &event->attr.branch_sample_type;
+
+			if (has_branch_stack(event)) {
+				if (!precise_br_compat(event))
+					return -EOPNOTSUPP;
+
+				/* branch_sample_type is compatible */
+
+			} else {
+				/*
+				 * user did not specify  branch_sample_type
+				 *
+				 * For PEBS fixups, we capture all
+				 * the branches at the priv level of the
+				 * event.
+				 */
+				*br_type = PERF_SAMPLE_BRANCH_ANY;
+
+				if (!event->attr.exclude_user)
+					*br_type |= PERF_SAMPLE_BRANCH_USER;
+
+				if (!event->attr.exclude_kernel)
+					*br_type |= PERF_SAMPLE_BRANCH_KERNEL;
+			}
+		}
 	}
 
 	/*
@@ -426,6 +486,10 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	/* mark unused */
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
 
+	/* mark not used */
+	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
+
 	return x86_pmu.hw_config(event);
 }
 
@@ -1607,25 +1671,32 @@ static const struct attribute_group *x86_pmu_attr_groups[] = {
 	NULL,
 };
 
+static void x86_pmu_flush_branch_stack(void)
+{
+	if (x86_pmu.flush_branch_stack)
+		x86_pmu.flush_branch_stack();
+}
+
 static struct pmu pmu = {
-	.pmu_enable	= x86_pmu_enable,
-	.pmu_disable	= x86_pmu_disable,
+	.pmu_enable		= x86_pmu_enable,
+	.pmu_disable		= x86_pmu_disable,
 
 	.attr_groups	= x86_pmu_attr_groups,
 
 	.event_init	= x86_pmu_event_init,
 
-	.add		= x86_pmu_add,
-	.del		= x86_pmu_del,
-	.start		= x86_pmu_start,
-	.stop		= x86_pmu_stop,
-	.read		= x86_pmu_read,
+	.add			= x86_pmu_add,
+	.del			= x86_pmu_del,
+	.start			= x86_pmu_start,
+	.stop			= x86_pmu_stop,
+	.read			= x86_pmu_read,
 
 	.start_txn	= x86_pmu_start_txn,
 	.cancel_txn	= x86_pmu_cancel_txn,
 	.commit_txn	= x86_pmu_commit_txn,
 
 	.event_idx	= x86_pmu_event_idx,
+	.flush_branch_stack	= x86_pmu_flush_branch_stack,
 };
 
 void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)

arch/x86/kernel/cpu/perf_event.h

@@ -33,6 +33,7 @@ enum extra_reg_type {
 
 	EXTRA_REG_RSP_0 = 0,	/* offcore_response_0 */
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
+	EXTRA_REG_LBR   = 2,	/* lbr_select */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
@@ -130,6 +131,8 @@ struct cpu_hw_events {
 	void				*lbr_context;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
+	struct er_account		*lbr_sel;
+	u64				br_sel;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -344,6 +347,7 @@ struct x86_pmu {
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
+	void		(*flush_branch_stack)(void);
 
 	/*
 	 * Intel Arch Perfmon v2+
@@ -365,6 +369,8 @@ struct x86_pmu {
 	 */
 	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
 	int		lbr_nr;			   /* hardware stack size */
+	u64		lbr_sel_mask;		   /* LBR_SELECT valid bits */
+	const int	*lbr_sel_map;		   /* lbr_select mappings */
 
 	/*
 	 * Extra registers for events
@@ -478,6 +484,15 @@ extern struct event_constraint emptyconstraint;
 
 extern struct event_constraint unconstrained;
 
+static inline bool kernel_ip(unsigned long ip)
+{
+#ifdef CONFIG_X86_32
+	return ip > PAGE_OFFSET;
+#else
+	return (long)ip < 0;
+#endif
+}
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
@@ -558,6 +573,10 @@ void intel_pmu_lbr_init_nhm(void);
 
 void intel_pmu_lbr_init_atom(void);
 
+void intel_pmu_lbr_init_snb(void);
+
+int intel_pmu_setup_lbr_filter(struct perf_event *event);
+
 int p4_pmu_init(void);
 
 int p6_pmu_init(void);

arch/x86/kernel/cpu/perf_event_amd.c

@@ -139,6 +139,9 @@ static int amd_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (event->attr.exclude_host && event->attr.exclude_guest)
 		/*
 		 * When HO == GO == 1 the hardware treats that as GO == HO == 0

arch/x86/kernel/cpu/perf_event_intel.c

@@ -728,6 +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);
@@ -882,6 +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;
@@ -936,6 +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);
@@ -1058,6 +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);
 	}
@@ -1124,17 +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];
@@ -1157,14 +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;
@@ -1201,11 +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;
 }
 
@@ -1253,6 +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,
@@ -1295,6 +1336,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		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;
 
@@ -1433,7 +1480,7 @@ 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);
@@ -1455,22 +1502,28 @@ 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)
@@ -1488,6 +1541,18 @@ 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();
+}
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
@@ -1515,6 +1580,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.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)
@@ -1745,7 +1811,7 @@ __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;

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -3,6 +3,7 @@
 #include <linux/slab.h>
 
 #include <asm/perf_event.h>
+#include <asm/insn.h>
 
 #include "perf_event.h"
 
@@ -439,9 +440,6 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
-
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
-		intel_pmu_lbr_enable(event);
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -454,9 +452,6 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
 	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
-
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
-		intel_pmu_lbr_disable(event);
 }
 
 void intel_pmu_pebs_enable_all(void)
@@ -475,17 +470,6 @@ void intel_pmu_pebs_disable_all(void)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 }
 
-#include <asm/insn.h>
-
-static inline bool kernel_ip(unsigned long ip)
-{
-#ifdef CONFIG_X86_32
-	return ip > PAGE_OFFSET;
-#else
-	return (long)ip < 0;
-#endif
-}
-
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -572,6 +556,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * both formats and we don't use the other fields in this
 	 * routine.
 	 */
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct pebs_record_core *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
@@ -602,6 +587,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	else
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
+	if (has_branch_stack(event))
+		data.br_stack = &cpuc->lbr_stack;
+
 	if (perf_event_overflow(event, &data, &regs))
 		x86_pmu_stop(event, 0);
 }

arch/x86/kernel/cpu/perf_event_intel_lbr.c

@@ -3,6 +3,7 @@
 
 #include <asm/perf_event.h>
 #include <asm/msr.h>
+#include <asm/insn.h>
 
 #include "perf_event.h"
 
@@ -13,6 +14,100 @@ enum {
 	LBR_FORMAT_EIP_FLAGS	= 0x03,
 };
 
+/*
+ * Intel LBR_SELECT bits
+ * Intel Vol3a, April 2011, Section 16.7 Table 16-10
+ *
+ * Hardware branch filter (not available on all CPUs)
+ */
+#define LBR_KERNEL_BIT		0 /* do not capture at ring0 */
+#define LBR_USER_BIT		1 /* do not capture at ring > 0 */
+#define LBR_JCC_BIT		2 /* do not capture conditional branches */
+#define LBR_REL_CALL_BIT	3 /* do not capture relative calls */
+#define LBR_IND_CALL_BIT	4 /* do not capture indirect calls */
+#define LBR_RETURN_BIT		5 /* do not capture near returns */
+#define LBR_IND_JMP_BIT		6 /* do not capture indirect jumps */
+#define LBR_REL_JMP_BIT		7 /* do not capture relative jumps */
+#define LBR_FAR_BIT		8 /* do not capture far branches */
+
+#define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
+#define LBR_USER	(1 << LBR_USER_BIT)
+#define LBR_JCC		(1 << LBR_JCC_BIT)
+#define LBR_REL_CALL	(1 << LBR_REL_CALL_BIT)
+#define LBR_IND_CALL	(1 << LBR_IND_CALL_BIT)
+#define LBR_RETURN	(1 << LBR_RETURN_BIT)
+#define LBR_REL_JMP	(1 << LBR_REL_JMP_BIT)
+#define LBR_IND_JMP	(1 << LBR_IND_JMP_BIT)
+#define LBR_FAR		(1 << LBR_FAR_BIT)
+
+#define LBR_PLM (LBR_KERNEL | LBR_USER)
+
+#define LBR_SEL_MASK	0x1ff	/* valid bits in LBR_SELECT */
+#define LBR_NOT_SUPP	-1	/* LBR filter not supported */
+#define LBR_IGN		0	/* ignored */
+
+#define LBR_ANY		 \
+	(LBR_JCC	|\
+	 LBR_REL_CALL	|\
+	 LBR_IND_CALL	|\
+	 LBR_RETURN	|\
+	 LBR_REL_JMP	|\
+	 LBR_IND_JMP	|\
+	 LBR_FAR)
+
+#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
+
+#define for_each_branch_sample_type(x) \
+	for ((x) = PERF_SAMPLE_BRANCH_USER; \
+	     (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
+
+/*
+ * x86control flow change classification
+ * x86control flow changes include branches, interrupts, traps, faults
+ */
+enum {
+	X86_BR_NONE     = 0,      /* unknown */
+
+	X86_BR_USER     = 1 << 0, /* branch target is user */
+	X86_BR_KERNEL   = 1 << 1, /* branch target is kernel */
+
+	X86_BR_CALL     = 1 << 2, /* call */
+	X86_BR_RET      = 1 << 3, /* return */
+	X86_BR_SYSCALL  = 1 << 4, /* syscall */
+	X86_BR_SYSRET   = 1 << 5, /* syscall return */
+	X86_BR_INT      = 1 << 6, /* sw interrupt */
+	X86_BR_IRET     = 1 << 7, /* return from interrupt */
+	X86_BR_JCC      = 1 << 8, /* conditional */
+	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 */
+};
+
+#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
+
+#define X86_BR_ANY       \
+	(X86_BR_CALL    |\
+	 X86_BR_RET     |\
+	 X86_BR_SYSCALL |\
+	 X86_BR_SYSRET  |\
+	 X86_BR_INT     |\
+	 X86_BR_IRET    |\
+	 X86_BR_JCC     |\
+	 X86_BR_JMP	 |\
+	 X86_BR_IRQ	 |\
+	 X86_BR_IND_CALL)
+
+#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
+
+#define X86_BR_ANY_CALL		 \
+	(X86_BR_CALL		|\
+	 X86_BR_IND_CALL	|\
+	 X86_BR_SYSCALL		|\
+	 X86_BR_IRQ		|\
+	 X86_BR_INT)
+
+static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
+
 /*
  * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
  * otherwise it becomes near impossible to get a reliable stack.
@@ -21,6 +116,10 @@ enum {
 static void __intel_pmu_lbr_enable(void)
 {
 	u64 debugctl;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->lbr_sel)
+		wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
@@ -76,11 +175,11 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 	 * Reset the LBR stack if we changed task context to
 	 * avoid data leaks.
 	 */
-
 	if (event->ctx->task && cpuc->lbr_context != event->ctx) {
 		intel_pmu_lbr_reset();
 		cpuc->lbr_context = event->ctx;
 	}
+	cpuc->br_sel = event->hw.branch_reg.reg;
 
 	cpuc->lbr_users++;
 }
@@ -95,8 +194,11 @@ void intel_pmu_lbr_disable(struct perf_event *event)
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 
-	if (cpuc->enabled && !cpuc->lbr_users)
+	if (cpuc->enabled && !cpuc->lbr_users) {
 		__intel_pmu_lbr_disable();
+		/* avoid stale pointer */
+		cpuc->lbr_context = NULL;
+	}
 }
 
 void intel_pmu_lbr_enable_all(void)
@@ -115,6 +217,9 @@ void intel_pmu_lbr_disable_all(void)
 		__intel_pmu_lbr_disable();
 }
 
+/*
+ * TOS = most recently recorded branch
+ */
 static inline u64 intel_pmu_lbr_tos(void)
 {
 	u64 tos;
@@ -142,15 +247,15 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
 
-		cpuc->lbr_entries[i].from  = msr_lastbranch.from;
-		cpuc->lbr_entries[i].to    = msr_lastbranch.to;
-		cpuc->lbr_entries[i].flags = 0;
+		cpuc->lbr_entries[i].from	= msr_lastbranch.from;
+		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
+		cpuc->lbr_entries[i].mispred	= 0;
+		cpuc->lbr_entries[i].predicted	= 0;
+		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
 }
 
-#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
-
 /*
  * Due to lack of segmentation in Linux the effective address (offset)
  * is the same as the linear address, allowing us to merge the LIP and EIP
@@ -165,19 +270,22 @@ 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, flags = 0;
+		u64 from, to, mis = 0, pred = 0;
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
 		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
 		if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
-			flags = !!(from & LBR_FROM_FLAG_MISPRED);
+			mis = !!(from & LBR_FROM_FLAG_MISPRED);
+			pred = !mis;
 			from = (u64)((((s64)from) << 1) >> 1);
 		}
 
-		cpuc->lbr_entries[i].from  = from;
-		cpuc->lbr_entries[i].to    = to;
-		cpuc->lbr_entries[i].flags = flags;
+		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].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
 }
@@ -193,28 +301,404 @@ void intel_pmu_lbr_read(void)
 		intel_pmu_lbr_read_32(cpuc);
 	else
 		intel_pmu_lbr_read_64(cpuc);
+
+	intel_pmu_lbr_filter(cpuc);
 }
 
+/*
+ * SW filter is used:
+ * - in case there is no HW filter
+ * - in case the HW filter has errata or limitations
+ */
+static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
+{
+	u64 br_type = event->attr.branch_sample_type;
+	int mask = 0;
+
+	if (br_type & PERF_SAMPLE_BRANCH_USER)
+		mask |= X86_BR_USER;
+
+	if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
+		mask |= X86_BR_KERNEL;
+
+	/* we ignore BRANCH_HV here */
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY)
+		mask |= X86_BR_ANY;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL)
+		mask |= X86_BR_ANY_CALL;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+		mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET;
+
+	if (br_type & PERF_SAMPLE_BRANCH_IND_CALL)
+		mask |= X86_BR_IND_CALL;
+	/*
+	 * stash actual user request into reg, it may
+	 * be used by fixup code for some CPU
+	 */
+	event->hw.branch_reg.reg = mask;
+}
+
+/*
+ * setup the HW LBR filter
+ * Used only when available, may not be enough to disambiguate
+ * all branches, may need the help of the SW filter
+ */
+static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg;
+	u64 br_type = event->attr.branch_sample_type;
+	u64 mask = 0, m;
+	u64 v;
+
+	for_each_branch_sample_type(m) {
+		if (!(br_type & m))
+			continue;
+
+		v = x86_pmu.lbr_sel_map[m];
+		if (v == LBR_NOT_SUPP)
+			return -EOPNOTSUPP;
+
+		if (v != LBR_IGN)
+			mask |= v;
+	}
+	reg = &event->hw.branch_reg;
+	reg->idx = EXTRA_REG_LBR;
+
+	/* LBR_SELECT operates in suppress mode so invert mask */
+	reg->config = ~mask & x86_pmu.lbr_sel_mask;
+
+	return 0;
+}
+
+int intel_pmu_setup_lbr_filter(struct perf_event *event)
+{
+	int ret = 0;
+
+	/*
+	 * no LBR on this PMU
+	 */
+	if (!x86_pmu.lbr_nr)
+		return -EOPNOTSUPP;
+
+	/*
+	 * setup SW LBR filter
+	 */
+	intel_pmu_setup_sw_lbr_filter(event);
+
+	/*
+	 * setup HW LBR filter, if any
+	 */
+	if (x86_pmu.lbr_sel_map)
+		ret = intel_pmu_setup_hw_lbr_filter(event);
+
+	return ret;
+}
+
+/*
+ * return the type of control flow change at address "from"
+ * intruction is not necessarily a branch (in case of interrupt).
+ *
+ * The branch type returned also includes the priv level of the
+ * target of the control flow change (X86_BR_USER, X86_BR_KERNEL).
+ *
+ * If a branch type is unknown OR the instruction cannot be
+ * decoded (e.g., text page not present), then X86_BR_NONE is
+ * returned.
+ */
+static int branch_type(unsigned long from, unsigned long to)
+{
+	struct insn insn;
+	void *addr;
+	int bytes, size = MAX_INSN_SIZE;
+	int ret = X86_BR_NONE;
+	int ext, to_plm, from_plm;
+	u8 buf[MAX_INSN_SIZE];
+	int is64 = 0;
+
+	to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
+	from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER;
+
+	/*
+	 * maybe zero if lbr did not fill up after a reset by the time
+	 * we get a PMU interrupt
+	 */
+	if (from == 0 || to == 0)
+		return X86_BR_NONE;
+
+	if (from_plm == X86_BR_USER) {
+		/*
+		 * can happen if measuring at the user level only
+		 * and we interrupt in a kernel thread, e.g., idle.
+		 */
+		if (!current->mm)
+			return X86_BR_NONE;
+
+		/* may fail if text not present */
+		bytes = copy_from_user_nmi(buf, (void __user *)from, size);
+		if (bytes != size)
+			return X86_BR_NONE;
+
+		addr = buf;
+	} else
+		addr = (void *)from;
+
+	/*
+	 * decoder needs to know the ABI especially
+	 * on 64-bit systems running 32-bit apps
+	 */
+#ifdef CONFIG_X86_64
+	is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
+#endif
+	insn_init(&insn, addr, is64);
+	insn_get_opcode(&insn);
+
+	switch (insn.opcode.bytes[0]) {
+	case 0xf:
+		switch (insn.opcode.bytes[1]) {
+		case 0x05: /* syscall */
+		case 0x34: /* sysenter */
+			ret = X86_BR_SYSCALL;
+			break;
+		case 0x07: /* sysret */
+		case 0x35: /* sysexit */
+			ret = X86_BR_SYSRET;
+			break;
+		case 0x80 ... 0x8f: /* conditional */
+			ret = X86_BR_JCC;
+			break;
+		default:
+			ret = X86_BR_NONE;
+		}
+		break;
+	case 0x70 ... 0x7f: /* conditional */
+		ret = X86_BR_JCC;
+		break;
+	case 0xc2: /* near ret */
+	case 0xc3: /* near ret */
+	case 0xca: /* far ret */
+	case 0xcb: /* far ret */
+		ret = X86_BR_RET;
+		break;
+	case 0xcf: /* iret */
+		ret = X86_BR_IRET;
+		break;
+	case 0xcc ... 0xce: /* int */
+		ret = X86_BR_INT;
+		break;
+	case 0xe8: /* call near rel */
+	case 0x9a: /* call far absolute */
+		ret = X86_BR_CALL;
+		break;
+	case 0xe0 ... 0xe3: /* loop jmp */
+		ret = X86_BR_JCC;
+		break;
+	case 0xe9 ... 0xeb: /* jmp */
+		ret = X86_BR_JMP;
+		break;
+	case 0xff: /* call near absolute, call far absolute ind */
+		insn_get_modrm(&insn);
+		ext = (insn.modrm.bytes[0] >> 3) & 0x7;
+		switch (ext) {
+		case 2: /* near ind call */
+		case 3: /* far ind call */
+			ret = X86_BR_IND_CALL;
+			break;
+		case 4:
+		case 5:
+			ret = X86_BR_JMP;
+			break;
+		}
+		break;
+	default:
+		ret = X86_BR_NONE;
+	}
+	/*
+	 * interrupts, traps, faults (and thus ring transition) may
+	 * occur on any instructions. Thus, to classify them correctly,
+	 * we need to first look at the from and to priv levels. If they
+	 * are different and to is in the kernel, then it indicates
+	 * a ring transition. If the from instruction is not a ring
+	 * transition instr (syscall, systenter, int), then it means
+	 * it was a irq, trap or fault.
+	 *
+	 * we have no way of detecting kernel to kernel faults.
+	 */
+	if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL
+	    && ret != X86_BR_SYSCALL && ret != X86_BR_INT)
+		ret = X86_BR_IRQ;
+
+	/*
+	 * branch priv level determined by target as
+	 * is done by HW when LBR_SELECT is implemented
+	 */
+	if (ret != X86_BR_NONE)
+		ret |= to_plm;
+
+	return ret;
+}
+
+/*
+ * implement actual branch filter based on user demand.
+ * Hardware may not exactly satisfy that request, thus
+ * we need to inspect opcodes. Mismatched branches are
+ * discarded. Therefore, the number of branches returned
+ * in PERF_SAMPLE_BRANCH_STACK sample may vary.
+ */
+static void
+intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
+{
+	u64 from, to;
+	int br_sel = cpuc->br_sel;
+	int i, j, type;
+	bool compress = false;
+
+	/* if sampling all branches, then nothing to filter */
+	if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
+		return;
+
+	for (i = 0; i < cpuc->lbr_stack.nr; i++) {
+
+		from = cpuc->lbr_entries[i].from;
+		to = cpuc->lbr_entries[i].to;
+
+		type = branch_type(from, to);
+
+		/* if type does not correspond, then discard */
+		if (type == X86_BR_NONE || (br_sel & type) != type) {
+			cpuc->lbr_entries[i].from = 0;
+			compress = true;
+		}
+	}
+
+	if (!compress)
+		return;
+
+	/* remove all entries with from=0 */
+	for (i = 0; i < cpuc->lbr_stack.nr; ) {
+		if (!cpuc->lbr_entries[i].from) {
+			j = i;
+			while (++j < cpuc->lbr_stack.nr)
+				cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
+			cpuc->lbr_stack.nr--;
+			if (!cpuc->lbr_entries[i].from)
+				continue;
+		}
+		i++;
+	}
+}
+
+/*
+ * Map interface branch filters onto LBR filters
+ */
+static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
+	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_REL_JMP
+					| LBR_IND_JMP | LBR_FAR,
+	/*
+	 * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
+	 */
+	[PERF_SAMPLE_BRANCH_ANY_CALL] =
+	 LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
+	/*
+	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
+	 */
+	[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
+};
+
+static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
+	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL]	= LBR_REL_CALL | LBR_IND_CALL
+					| LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL]	= LBR_IND_CALL,
+};
+
+/* core */
 void intel_pmu_lbr_init_core(void)
 {
 	x86_pmu.lbr_nr     = 4;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x40;
-	x86_pmu.lbr_to     = 0x60;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	/*
+	 * SW branch filter usage:
+	 * - compensate for lack of HW filter
+	 */
+	pr_cont("4-deep LBR, ");
 }
 
+/* nehalem/westmere */
 void intel_pmu_lbr_init_nhm(void)
 {
 	x86_pmu.lbr_nr     = 16;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x680;
-	x86_pmu.lbr_to     = 0x6c0;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;
+
+	/*
+	 * SW branch filter usage:
+	 * - workaround LBR_SEL errata (see above)
+	 * - support syscall, sysret capture.
+	 *   That requires LBR_FAR but that means far
+	 *   jmp need to be filtered out
+	 */
+	pr_cont("16-deep LBR, ");
 }
 
+/* sandy bridge */
+void intel_pmu_lbr_init_snb(void)
+{
+	x86_pmu.lbr_nr	 = 16;
+	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
+	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+	/*
+	 * SW branch filter usage:
+	 * - support syscall, sysret capture.
+	 *   That requires LBR_FAR but that means far
+	 *   jmp need to be filtered out
+	 */
+	pr_cont("16-deep LBR, ");
+}
+
+/* atom */
 void intel_pmu_lbr_init_atom(void)
 {
+	/*
+	 * only models starting at stepping 10 seems
+	 * to have an operational LBR which can freeze
+	 * on PMU interrupt
+	 */
+	if (boot_cpu_data.x86_mask < 10) {
+		pr_cont("LBR disabled due to erratum");
+		return;
+	}
+
 	x86_pmu.lbr_nr	   = 8;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x40;
-	x86_pmu.lbr_to     = 0x60;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	/*
+	 * SW branch filter usage:
+	 * - compensate for lack of HW filter
+	 */
+	pr_cont("8-deep LBR, ");
 }