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/alpha/kernel/perf_event.c

@@ -685,6 +685,10 @@ static int alpha_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HARDWARE:

arch/arm/kernel/perf_event.c

@@ -539,6 +539,10 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (armpmu->map_event(event) == -ENOENT)
 		return -ENOENT;
 

arch/mips/kernel/perf_event_mipsxx.c

@@ -606,6 +606,10 @@ static int mipspmu_event_init(struct perf_event *event)
 {
 	int err = 0;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HARDWARE:

arch/powerpc/kernel/perf_event.c

@@ -1084,6 +1084,10 @@ static int power_pmu_event_init(struct perf_event *event)
 	if (!ppmu)
 		return -ENOENT;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;

arch/sh/kernel/perf_event.c

@@ -310,6 +310,10 @@ static int sh_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HW_CACHE:

arch/sparc/kernel/perf_event.c

@@ -1105,6 +1105,10 @@ static int sparc_pmu_event_init(struct perf_event *event)
 	if (atomic_read(&nmi_active) < 0)
 		return -ENODEV;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (attr->type) {
 	case PERF_TYPE_HARDWARE:
 		if (attr->config >= sparc_pmu->max_events)

arch/x86/include/asm/msr-index.h

@@ -56,6 +56,13 @@
 #define MSR_OFFCORE_RSP_0		0x000001a6
 #define MSR_OFFCORE_RSP_1		0x000001a7
 
+#define MSR_LBR_SELECT			0x000001c8
+#define MSR_LBR_TOS			0x000001c9
+#define MSR_LBR_NHM_FROM		0x00000680
+#define MSR_LBR_NHM_TO			0x000006c0
+#define MSR_LBR_CORE_FROM		0x00000040
+#define MSR_LBR_CORE_TO			0x00000060
+
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345

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 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
 		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 @@ __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
 		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, ");
 }

include/linux/perf_event.h

@@ -129,10 +129,39 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PERIOD			= 1U << 8,
 	PERF_SAMPLE_STREAM_ID			= 1U << 9,
 	PERF_SAMPLE_RAW				= 1U << 10,
+	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
 
-	PERF_SAMPLE_MAX = 1U << 11,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 12,		/* non-ABI */
 };
 
+/*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type {
+	PERF_SAMPLE_BRANCH_USER		= 1U << 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL	= 1U << 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV		= 1U << 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY		= 1U << 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << 6, /* indirect calls */
+
+	PERF_SAMPLE_BRANCH_MAX		= 1U << 7, /* non-ABI */
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+	(PERF_SAMPLE_BRANCH_USER|\
+	 PERF_SAMPLE_BRANCH_KERNEL|\
+	 PERF_SAMPLE_BRANCH_HV)
+
 /*
  * The format of the data returned by read() on a perf event fd,
  * as specified by attr.read_format:
@@ -163,6 +192,8 @@ enum perf_event_read_format {
 };
 
 #define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1	72	/* add: config2 */
+#define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -240,6 +271,7 @@ struct perf_event_attr {
 		__u64		bp_len;
 		__u64		config2; /* extension of config1 */
 	};
+	__u64	branch_sample_type; /* enum branch_sample_type */
 };
 
 /*
@@ -458,6 +490,8 @@ enum perf_event_type {
 	 *
 	 *	{ u32			size;
 	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 *
+	 *	{ u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
@@ -530,12 +564,34 @@ struct perf_raw_record {
 	void				*data;
 };
 
+/*
+ * single taken branch record layout:
+ *
+ *      from: source instruction (may not always be a branch insn)
+ *        to: branch target
+ *   mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ */
 struct perf_branch_entry {
-	__u64				from;
-	__u64				to;
-	__u64				flags;
+	__u64	from;
+	__u64	to;
+	__u64	mispred:1,  /* target mispredicted */
+		predicted:1,/* target predicted */
+		reserved:62;
 };
 
+/*
+ * branch stack layout:
+ *  nr: number of taken branches stored in entries[]
+ *
+ * Note that nr can vary from sample to sample
+ * branches (to, from) are stored from most recent
+ * to least recent, i.e., entries[0] contains the most
+ * recent branch.
+ */
 struct perf_branch_stack {
 	__u64				nr;
 	struct perf_branch_entry	entries[0];
@@ -566,7 +622,9 @@ struct hw_perf_event {
 			unsigned long	event_base;
 			int		idx;
 			int		last_cpu;
+
 			struct hw_perf_event_extra extra_reg;
+			struct hw_perf_event_extra branch_reg;
 		};
 		struct { /* software */
 			struct hrtimer	hrtimer;
@@ -690,6 +748,11 @@ struct pmu {
 	 * if no implementation is provided it will default to: event->hw.idx + 1.
 	 */
 	int (*event_idx)		(struct perf_event *event); /*optional */
+
+	/*
+	 * flush branch stack on context-switches (needed in cpu-wide mode)
+	 */
+	void (*flush_branch_stack)	(void);
 };
 
 /**
@@ -923,7 +986,8 @@ struct perf_event_context {
 	u64				parent_gen;
 	u64				generation;
 	int				pin_count;
-	int				nr_cgroups; /* cgroup events present */
+	int				nr_cgroups;	 /* cgroup evts */
+	int				nr_branch_stack; /* branch_stack evt */
 	struct rcu_head			rcu_head;
 };
 
@@ -988,6 +1052,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr,
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
 
+
 struct perf_sample_data {
 	u64				type;
 
@@ -1007,12 +1072,14 @@ struct perf_sample_data {
 	u64				period;
 	struct perf_callchain_entry	*callchain;
 	struct perf_raw_record		*raw;
+	struct perf_branch_stack	*br_stack;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
 {
 	data->addr = addr;
 	data->raw  = NULL;
+	data->br_stack = NULL;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
@@ -1151,6 +1218,11 @@ extern void perf_bp_event(struct perf_event *event, void *data);
 # define perf_instruction_pointer(regs)	instruction_pointer(regs)
 #endif
 
+static inline bool has_branch_stack(struct perf_event *event)
+{
+	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
+}
+
 extern int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_event *event, unsigned int size);
 extern void perf_output_end(struct perf_output_handle *handle);

kernel/events/core.c

@@ -118,6 +118,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 		       PERF_FLAG_FD_OUTPUT  |\
 		       PERF_FLAG_PID_CGROUP)
 
+/*
+ * branch priv levels that need permission checks
+ */
+#define PERF_SAMPLE_BRANCH_PERM_PLM \
+	(PERF_SAMPLE_BRANCH_KERNEL |\
+	 PERF_SAMPLE_BRANCH_HV)
+
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
@@ -130,6 +137,7 @@ enum event_type_t {
  */
 struct static_key_deferred perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -881,6 +889,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (is_cgroup_event(event))
 		ctx->nr_cgroups++;
 
+	if (has_branch_stack(event))
+		ctx->nr_branch_stack++;
+
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	if (!ctx->nr_events)
 		perf_pmu_rotate_start(ctx->pmu);
@@ -1020,6 +1031,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 			cpuctx->cgrp = NULL;
 	}
 
+	if (has_branch_stack(event))
+		ctx->nr_branch_stack--;
+
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -2194,6 +2208,66 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	perf_pmu_rotate_start(ctx->pmu);
 }
 
+/*
+ * When sampling the branck stack in system-wide, it may be necessary
+ * to flush the stack on context switch. This happens when the branch
+ * stack does not tag its entries with the pid of the current task.
+ * Otherwise it becomes impossible to associate a branch entry with a
+ * task. This ambiguity is more likely to appear when the branch stack
+ * supports priv level filtering and the user sets it to monitor only
+ * at the user level (which could be a useful measurement in system-wide
+ * mode). In that case, the risk is high of having a branch stack with
+ * branch from multiple tasks. Flushing may mean dropping the existing
+ * entries or stashing them somewhere in the PMU specific code layer.
+ *
+ * This function provides the context switch callback to the lower code
+ * layer. It is invoked ONLY when there is at least one system-wide context
+ * with at least one active event using taken branch sampling.
+ */
+static void perf_branch_stack_sched_in(struct task_struct *prev,
+				       struct task_struct *task)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+
+	/* no need to flush branch stack if not changing task */
+	if (prev == task)
+		return;
+
+	local_irq_save(flags);
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+		/*
+		 * check if the context has at least one
+		 * event using PERF_SAMPLE_BRANCH_STACK
+		 */
+		if (cpuctx->ctx.nr_branch_stack > 0
+		    && pmu->flush_branch_stack) {
+
+			pmu = cpuctx->ctx.pmu;
+
+			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+			perf_pmu_disable(pmu);
+
+			pmu->flush_branch_stack();
+
+			perf_pmu_enable(pmu);
+
+			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+		}
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
 /*
  * Called from scheduler to add the events of the current task
  * with interrupts disabled.
@@ -2225,6 +2299,10 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	 */
 	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
 		perf_cgroup_sched_in(prev, task);
+
+	/* check for system-wide branch_stack events */
+	if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
+		perf_branch_stack_sched_in(prev, task);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -2791,6 +2869,14 @@ static void free_event(struct perf_event *event)
 			atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
 			static_key_slow_dec_deferred(&perf_sched_events);
 		}
+
+		if (has_branch_stack(event)) {
+			static_key_slow_dec_deferred(&perf_sched_events);
+			/* is system-wide event */
+			if (!(event->attach_state & PERF_ATTACH_TASK))
+				atomic_dec(&per_cpu(perf_branch_stack_events,
+						    event->cpu));
+		}
 	}
 
 	if (event->rb) {
@@ -3907,6 +3993,24 @@ void perf_output_sample(struct perf_output_handle *handle,
 			}
 		}
 	}
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		if (data->br_stack) {
+			size_t size;
+
+			size = data->br_stack->nr
+			     * sizeof(struct perf_branch_entry);
+
+			perf_output_put(handle, data->br_stack->nr);
+			perf_output_copy(handle, data->br_stack->entries, size);
+		} else {
+			/*
+			 * we always store at least the value of nr
+			 */
+			u64 nr = 0;
+			perf_output_put(handle, nr);
+		}
+	}
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -3949,6 +4053,15 @@ void perf_prepare_sample(struct perf_event_header *header,
 		WARN_ON_ONCE(size & (sizeof(u64)-1));
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		int size = sizeof(u64); /* nr */
+		if (data->br_stack) {
+			size += data->br_stack->nr
+			      * sizeof(struct perf_branch_entry);
+		}
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -5010,6 +5123,12 @@ static int perf_swevent_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_SOFTWARE)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event_id) {
 	case PERF_COUNT_SW_CPU_CLOCK:
 	case PERF_COUNT_SW_TASK_CLOCK:
@@ -5120,6 +5239,12 @@ static int perf_tp_event_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for tracepoint events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	err = perf_trace_init(event);
 	if (err)
 		return err;
@@ -5345,6 +5470,12 @@ static int cpu_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	perf_swevent_init_hrtimer(event);
 
 	return 0;
@@ -5419,6 +5550,12 @@ static int task_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	perf_swevent_init_hrtimer(event);
 
 	return 0;
@@ -5866,6 +6003,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 				return ERR_PTR(err);
 			}
 		}
+		if (has_branch_stack(event)) {
+			static_key_slow_inc(&perf_sched_events.key);
+			if (!(event->attach_state & PERF_ATTACH_TASK))
+				atomic_inc(&per_cpu(perf_branch_stack_events,
+						    event->cpu));
+		}
 	}
 
 	return event;
@@ -5935,6 +6078,40 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (attr->read_format & ~(PERF_FORMAT_MAX-1))
 		return -EINVAL;
 
+	if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		u64 mask = attr->branch_sample_type;
+
+		/* only using defined bits */
+		if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1))
+			return -EINVAL;
+
+		/* at least one branch bit must be set */
+		if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL))
+			return -EINVAL;
+
+		/* kernel level capture: check permissions */
+		if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
+		    && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
+
+		/* propagate priv level, when not set for branch */
+		if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) {
+
+			/* exclude_kernel checked on syscall entry */
+			if (!attr->exclude_kernel)
+				mask |= PERF_SAMPLE_BRANCH_KERNEL;
+
+			if (!attr->exclude_user)
+				mask |= PERF_SAMPLE_BRANCH_USER;
+
+			if (!attr->exclude_hv)
+				mask |= PERF_SAMPLE_BRANCH_HV;
+			/*
+			 * adjust user setting (for HW filter setup)
+			 */
+			attr->branch_sample_type = mask;
+		}
+	}
 out:
 	return ret;
 

kernel/events/hw_breakpoint.c

@@ -581,6 +581,12 @@ static int hw_breakpoint_event_init(struct perf_event *bp)
 	if (bp->attr.type != PERF_TYPE_BREAKPOINT)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for breakpoint events
+	 */
+	if (has_branch_stack(bp))
+		return -EOPNOTSUPP;
+
 	err = register_perf_hw_breakpoint(bp);
 	if (err)
 		return err;

tools/perf/Documentation/perf-record.txt

@@ -152,6 +152,36 @@ an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must ha
 corresponding events, i.e., they always refer to events defined earlier on the command
 line.
 
+-b::
+--branch-any::
+Enable taken branch stack sampling. Any type of taken branch may be sampled.
+This is a shortcut for --branch-filter any. See --branch-filter for more infos.
+
+-j::
+--branch-filter::
+Enable taken branch stack sampling. Each sample captures a series of consecutive
+taken branches. The number of branches captured with each sample depends on the
+underlying hardware, the type of branches of interest, and the executed code.
+It is possible to select the types of branches captured by enabling filters. The
+following filters are defined:
+
+        - any:  any type of branches
+        - any_call: any function call or system call
+        - any_ret: any function return or system call return
+        - any_ind: any indirect branch
+        - u:  only when the branch target is at the user level
+        - k: only when the branch target is in the kernel
+        - hv: only when the target is at the hypervisor level
+
++
+The option requires at least one branch type among any, any_call, any_ret, ind_call.
+The privilege levels may be ommitted, in which case, the privilege levels of the associated
+event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
+levels are subject to permissions.  When sampling on multiple events, branch stack sampling
+is enabled for all the sampling events. The sampled branch type is the same for all events.
+The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
+Note that this feature may not be available on all processors.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]

tools/perf/Documentation/perf-report.txt

@@ -153,6 +153,16 @@ OPTIONS
 	information which may be very large and thus may clutter the display.
 	It currently includes: cpu and numa topology of the host system.
 
+-b::
+--branch-stack::
+	Use the addresses of sampled taken branches instead of the instruction
+	address to build the histograms. To generate meaningful output, the
+	perf.data file must have been obtained using perf record -b or
+	perf record --branch-filter xxx where xxx is a branch filter option.
+	perf report is able to auto-detect whether a perf.data file contains
+	branch stacks and it will automatically switch to the branch view mode,
+	unless --no-branch-stack is used.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]

tools/perf/builtin-record.c

@@ -473,6 +473,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 	if (!have_tracepoints(&evsel_list->entries))
 		perf_header__clear_feat(&session->header, HEADER_TRACE_INFO);
 
+	if (!rec->opts.branch_stack)
+		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+
 	if (!rec->file_new) {
 		err = perf_session__read_header(session, output);
 		if (err < 0)
@@ -638,6 +641,90 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 	return err;
 }
 
+#define BRANCH_OPT(n, m) \
+	{ .name = n, .mode = (m) }
+
+#define BRANCH_END { .name = NULL }
+
+struct branch_mode {
+	const char *name;
+	int mode;
+};
+
+static const struct branch_mode branch_modes[] = {
+	BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
+	BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
+	BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
+	BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
+	BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
+	BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
+	BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
+	BRANCH_END
+};
+
+static int
+parse_branch_stack(const struct option *opt, const char *str, int unset)
+{
+#define ONLY_PLM \
+	(PERF_SAMPLE_BRANCH_USER	|\
+	 PERF_SAMPLE_BRANCH_KERNEL	|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+	uint64_t *mode = (uint64_t *)opt->value;
+	const struct branch_mode *br;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
+
+	/*
+	 * cannot set it twice, -b + --branch-filter for instance
+	 */
+	if (*mode)
+		return -1;
+
+	/* str may be NULL in case no arg is passed to -b */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			for (br = branch_modes; br->name; br++) {
+				if (!strcasecmp(s, br->name))
+					break;
+			}
+			if (!br->name) {
+				ui__warning("unknown branch filter %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= br->mode;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	/* default to any branch */
+	if ((*mode & ~ONLY_PLM) == 0) {
+		*mode = PERF_SAMPLE_BRANCH_ANY;
+	}
+error:
+	free(os);
+	return ret;
+}
+
 static const char * const record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -727,6 +814,14 @@ const struct option record_options[] = {
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
 	OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"),
+
+	OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack,
+		     "branch any", "sample any taken branches",
+		     parse_branch_stack),
+
+	OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
+		     "branch filter mask", "branch stack filter modes",
+		     parse_branch_stack),
 	OPT_END()
 };
 

tools/perf/builtin-report.c

@@ -53,6 +53,82 @@ struct perf_report {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
+					struct addr_location *al,
+					struct perf_sample *sample,
+					struct perf_evsel *evsel,
+				      struct machine *machine)
+{
+	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct symbol *parent = NULL;
+	int err = 0;
+	unsigned i;
+	struct hist_entry *he;
+	struct branch_info *bi, *bx;
+
+	if ((sort__has_parent || symbol_conf.use_callchain)
+	    && sample->callchain) {
+		err = machine__resolve_callchain(machine, evsel, al->thread,
+						 sample->callchain, &parent);
+		if (err)
+			return err;
+	}
+
+	bi = machine__resolve_bstack(machine, al->thread,
+				     sample->branch_stack);
+	if (!bi)
+		return -ENOMEM;
+
+	for (i = 0; i < sample->branch_stack->nr; i++) {
+		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+			continue;
+		/*
+		 * The report shows the percentage of total branches captured
+		 * and not events sampled. Thus we use a pseudo period of 1.
+		 */
+		he = __hists__add_branch_entry(&evsel->hists, al, parent,
+				&bi[i], 1);
+		if (he) {
+			struct annotation *notes;
+			err = -ENOMEM;
+			bx = he->branch_info;
+			if (bx->from.sym && use_browser > 0) {
+				notes = symbol__annotation(bx->from.sym);
+				if (!notes->src
+				    && symbol__alloc_hist(bx->from.sym) < 0)
+					goto out;
+
+				err = symbol__inc_addr_samples(bx->from.sym,
+							       bx->from.map,
+							       evsel->idx,
+							       bx->from.al_addr);
+				if (err)
+					goto out;
+			}
+
+			if (bx->to.sym && use_browser > 0) {
+				notes = symbol__annotation(bx->to.sym);
+				if (!notes->src
+				    && symbol__alloc_hist(bx->to.sym) < 0)
+					goto out;
+
+				err = symbol__inc_addr_samples(bx->to.sym,
+							       bx->to.map,
+							       evsel->idx,
+							       bx->to.al_addr);
+				if (err)
+					goto out;
+			}
+			evsel->hists.stats.total_period += 1;
+			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+			err = 0;
+		} else
+			return -ENOMEM;
+	}
+out:
+	return err;
+}
+
 static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 				      struct addr_location *al,
 				      struct perf_sample *sample,
@@ -126,14 +202,21 @@ static int process_sample_event(struct perf_tool *tool,
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (al.map != NULL)
-		al.map->dso->hit = 1;
+	if (sort__branch_mode == 1) {
+		if (perf_report__add_branch_hist_entry(tool, &al, sample,
+						       evsel, machine)) {
+			pr_debug("problem adding lbr entry, skipping event\n");
+			return -1;
+		}
+	} else {
+		if (al.map != NULL)
+			al.map->dso->hit = 1;
 
-	if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
-		pr_debug("problem incrementing symbol period, skipping event\n");
-		return -1;
+		if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
+			pr_debug("problem incrementing symbol period, skipping event\n");
+			return -1;
+		}
 	}
-
 	return 0;
 }
 
@@ -188,6 +271,15 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 			}
 	}
 
+	if (sort__branch_mode == 1) {
+		if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+			fprintf(stderr, "selected -b but no branch data."
+					" Did you call perf record without"
+					" -b?\n");
+			return -1;
+		}
+	}
+
 	return 0;
 }
 
@@ -246,7 +338,7 @@ static int __cmd_report(struct perf_report *rep)
 {
 	int ret = -EINVAL;
 	u64 nr_samples;
-	struct perf_session *session;
+	struct perf_session *session = rep->session;
 	struct perf_evsel *pos;
 	struct map *kernel_map;
 	struct kmap *kernel_kmap;
@@ -254,13 +346,6 @@ static int __cmd_report(struct perf_report *rep)
 
 	signal(SIGINT, sig_handler);
 
-	session = perf_session__new(rep->input_name, O_RDONLY,
-				    rep->force, false, &rep->tool);
-	if (session == NULL)
-		return -ENOMEM;
-
-	rep->session = session;
-
 	if (rep->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, rep->cpu_list,
 					       rep->cpu_bitmap);
@@ -427,9 +512,19 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 	return 0;
 }
 
+static int
+parse_branch_mode(const struct option *opt __used, const char *str __used, int unset)
+{
+	sort__branch_mode = !unset;
+	return 0;
+}
+
 int cmd_report(int argc, const char **argv, const char *prefix __used)
 {
+	struct perf_session *session;
 	struct stat st;
+	bool has_br_stack = false;
+	int ret = -1;
 	char callchain_default_opt[] = "fractal,0.5,callee";
 	const char * const report_usage[] = {
 		"perf report [<options>]",
@@ -477,7 +572,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
 		    "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, dso_to,"
+		   " dso_from, symbol_to, symbol_from, mispredict"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -517,6 +613,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
+	OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "",
+		    "use branch records for histogram filling", parse_branch_mode),
 	OPT_END()
 	};
 
@@ -536,11 +634,36 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 		else
 			report.input_name = "perf.data";
 	}
+	session = perf_session__new(report.input_name, O_RDONLY,
+				    report.force, false, &report.tool);
+	if (session == NULL)
+		return -ENOMEM;
 
-	if (strcmp(report.input_name, "-") != 0)
+	report.session = session;
+
+	has_br_stack = perf_header__has_feat(&session->header,
+					     HEADER_BRANCH_STACK);
+
+	if (sort__branch_mode == -1 && has_br_stack)
+		sort__branch_mode = 1;
+
+	/* sort__branch_mode could be 0 if --no-branch-stack */
+	if (sort__branch_mode == 1) {
+		/*
+		 * if no sort_order is provided, then specify
+		 * branch-mode specific order
+		 */
+		if (sort_order == default_sort_order)
+			sort_order = "comm,dso_from,symbol_from,"
+				     "dso_to,symbol_to";
+
+	}
+
+	if (strcmp(report.input_name, "-") != 0) {
 		setup_browser(true);
-	else
+	} else {
 		use_browser = 0;
+	}
 
 	/*
 	 * Only in the newt browser we are doing integrated annotation,
@@ -568,13 +691,13 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	}
 
 	if (symbol__init() < 0)
-		return -1;
+		goto error;
 
 	setup_sorting(report_usage, options);
 
 	if (parent_pattern != default_parent_pattern) {
 		if (sort_dimension__add("parent") < 0)
-			return -1;
+			goto error;
 
 		/*
 		 * Only show the parent fields if we explicitly
@@ -592,9 +715,20 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	if (argc)
 		usage_with_options(report_usage, options);
 
-	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
 	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
-	sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
 
-	return __cmd_report(&report);
+	if (sort__branch_mode == 1) {
+		sort_entry__setup_elide(&sort_dso_from, symbol_conf.dso_from_list, "dso_from", stdout);
+		sort_entry__setup_elide(&sort_dso_to, symbol_conf.dso_to_list, "dso_to", stdout);
+		sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
+		sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
+	} else {
+		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
+		sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
+	}
+
+	ret = __cmd_report(&report);
+error:
+	perf_session__delete(session);
+	return ret;
 }

tools/perf/perf.h

@@ -179,6 +179,23 @@ struct ip_callchain {
 	u64 ips[0];
 };
 
+struct branch_flags {
+	u64 mispred:1;
+	u64 predicted:1;
+	u64 reserved:62;
+};
+
+struct branch_entry {
+	u64				from;
+	u64				to;
+	struct branch_flags flags;
+};
+
+struct branch_stack {
+	u64				nr;
+	struct branch_entry	entries[0];
+};
+
 extern bool perf_host, perf_guest;
 extern const char perf_version_string[];
 
@@ -205,6 +222,7 @@ struct perf_record_opts {
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int user_freq;
+	int	     branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
 	const char   *cpu_list;

tools/perf/util/event.h

@@ -81,6 +81,7 @@ struct perf_sample {
 	u32 raw_size;
 	void *raw_data;
 	struct ip_callchain *callchain;
+	struct branch_stack *branch_stack;
 };
 
 #define BUILD_ID_SIZE 20

tools/perf/util/evsel.c

@@ -126,6 +126,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
 		attr->watermark = 0;
 		attr->wakeup_events = 1;
 	}
+	if (opts->branch_stack) {
+		attr->sample_type	|= PERF_SAMPLE_BRANCH_STACK;
+		attr->branch_sample_type = opts->branch_stack;
+	}
 
 	attr->mmap = track;
 	attr->comm = track;
@@ -576,6 +580,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 		data->raw_data = (void *) pdata;
 	}
 
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		u64 sz;
+
+		data->branch_stack = (struct branch_stack *)array;
+		array++; /* nr */
+
+		sz = data->branch_stack->nr * sizeof(struct branch_entry);
+		sz /= sizeof(u64);
+		array += sz;
+	}
 	return 0;
 }
 

tools/perf/util/header.c

@@ -1023,6 +1023,12 @@ static int write_cpuid(int fd, struct perf_header *h __used,
 	return do_write_string(fd, buffer);
 }
 
+static int write_branch_stack(int fd __used, struct perf_header *h __used,
+		       struct perf_evlist *evlist __used)
+{
+	return 0;
+}
+
 static void print_hostname(struct perf_header *ph, int fd, FILE *fp)
 {
 	char *str = do_read_string(fd, ph);
@@ -1144,8 +1150,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 	uint64_t id;
 	void *buf = NULL;
 	char *str;
-	u32 nre, sz, nr, i, j, msz;
-	int ret;
+	u32 nre, sz, nr, i, j;
+	ssize_t ret;
+	size_t msz;
 
 	/* number of events */
 	ret = read(fd, &nre, sizeof(nre));
@@ -1162,25 +1169,23 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 	if (ph->needs_swap)
 		sz = bswap_32(sz);
 
-	/*
-	 * ensure it is at least to our ABI rev
-	 */
-	if (sz < (u32)sizeof(attr))
-		goto error;
-
 	memset(&attr, 0, sizeof(attr));
 
-	/* read entire region to sync up to next field */
+	/* buffer to hold on file attr struct */
 	buf = malloc(sz);
 	if (!buf)
 		goto error;
 
 	msz = sizeof(attr);
-	if (sz < msz)
+	if (sz < (ssize_t)msz)
 		msz = sz;
 
 	for (i = 0 ; i < nre; i++) {
 
+		/*
+		 * must read entire on-file attr struct to
+		 * sync up with layout.
+		 */
 		ret = read(fd, buf, sz);
 		if (ret != (ssize_t)sz)
 			goto error;
@@ -1316,6 +1321,12 @@ static void print_cpuid(struct perf_header *ph, int fd, FILE *fp)
 	free(str);
 }
 
+static void print_branch_stack(struct perf_header *ph __used, int fd __used,
+			       FILE *fp)
+{
+	fprintf(fp, "# contains samples with branch stack\n");
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
 				    char *filename,
 				    struct perf_session *session)
@@ -1520,6 +1531,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPA(HEADER_CMDLINE,	cmdline),
 	FEAT_OPF(HEADER_CPU_TOPOLOGY,	cpu_topology),
 	FEAT_OPF(HEADER_NUMA_TOPOLOGY,	numa_topology),
+	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 };
 
 struct header_print_data {
@@ -1804,35 +1816,101 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 	return err;
 }
 
-static int check_magic_endian(u64 *magic, struct perf_file_header *header,
-			      struct perf_header *ph)
+static const int attr_file_abi_sizes[] = {
+	[0] = PERF_ATTR_SIZE_VER0,
+	[1] = PERF_ATTR_SIZE_VER1,
+	0,
+};
+
+/*
+ * In the legacy file format, the magic number is not used to encode endianness.
+ * hdr_sz was used to encode endianness. But given that hdr_sz can vary based
+ * on ABI revisions, we need to try all combinations for all endianness to
+ * detect the endianness.
+ */
+static int try_all_file_abis(uint64_t hdr_sz, struct perf_header *ph)
 {
-	int ret;
+	uint64_t ref_size, attr_size;
+	int i;
 
-	/* check for legacy format */
-	ret = memcmp(magic, __perf_magic1, sizeof(*magic));
-	if (ret == 0) {
-		pr_debug("legacy perf.data format\n");
-		if (!header)
-			return -1;
+	for (i = 0 ; attr_file_abi_sizes[i]; i++) {
+		ref_size = attr_file_abi_sizes[i]
+			 + sizeof(struct perf_file_section);
+		if (hdr_sz != ref_size) {
+			attr_size = bswap_64(hdr_sz);
+			if (attr_size != ref_size)
+				continue;
 
-		if (header->attr_size != sizeof(struct perf_file_attr)) {
-			u64 attr_size = bswap_64(header->attr_size);
+			ph->needs_swap = true;
+		}
+		pr_debug("ABI%d perf.data file detected, need_swap=%d\n",
+			 i,
+			 ph->needs_swap);
+		return 0;
+	}
+	/* could not determine endianness */
+	return -1;
+}
 
-			if (attr_size != sizeof(struct perf_file_attr))
-				return -1;
+#define PERF_PIPE_HDR_VER0	16
+
+static const size_t attr_pipe_abi_sizes[] = {
+	[0] = PERF_PIPE_HDR_VER0,
+	0,
+};
+
+/*
+ * In the legacy pipe format, there is an implicit assumption that endiannesss
+ * between host recording the samples, and host parsing the samples is the
+ * same. This is not always the case given that the pipe output may always be
+ * redirected into a file and analyzed on a different machine with possibly a
+ * different endianness and perf_event ABI revsions in the perf tool itself.
+ */
+static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph)
+{
+	u64 attr_size;
+	int i;
+
+	for (i = 0 ; attr_pipe_abi_sizes[i]; i++) {
+		if (hdr_sz != attr_pipe_abi_sizes[i]) {
+			attr_size = bswap_64(hdr_sz);
+			if (attr_size != hdr_sz)
+				continue;
 
 			ph->needs_swap = true;
 		}
+		pr_debug("Pipe ABI%d perf.data file detected\n", i);
 		return 0;
 	}
+	return -1;
+}
+
+static int check_magic_endian(u64 magic, uint64_t hdr_sz,
+			      bool is_pipe, struct perf_header *ph)
+{
+	int ret;
+
+	/* check for legacy format */
+	ret = memcmp(&magic, __perf_magic1, sizeof(magic));
+	if (ret == 0) {
+		pr_debug("legacy perf.data format\n");
+		if (is_pipe)
+			return try_all_pipe_abis(hdr_sz, ph);
+
+		return try_all_file_abis(hdr_sz, ph);
+	}
+	/*
+	 * the new magic number serves two purposes:
+	 * - unique number to identify actual perf.data files
+	 * - encode endianness of file
+	 */
 
-	/* check magic number with same endianness */
-	if (*magic == __perf_magic2)
+	/* check magic number with one endianness */
+	if (magic == __perf_magic2)
 		return 0;
 
-	/* check magic number but opposite endianness */
-	if (*magic != __perf_magic2_sw)
+	/* check magic number with opposite endianness */
+	if (magic != __perf_magic2_sw)
 		return -1;
 
 	ph->needs_swap = true;
@@ -1851,8 +1929,11 @@ int perf_file_header__read(struct perf_file_header *header,
 	if (ret <= 0)
 		return -1;
 
-	if (check_magic_endian(&header->magic, header, ph) < 0)
+	if (check_magic_endian(header->magic,
+			       header->attr_size, false, ph) < 0) {
+		pr_debug("magic/endian check failed\n");
 		return -1;
+	}
 
 	if (ph->needs_swap) {
 		mem_bswap_64(header, offsetof(struct perf_file_header,
@@ -1939,21 +2020,17 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
 	if (ret <= 0)
 		return -1;
 
-	 if (check_magic_endian(&header->magic, NULL, ph) < 0)
+	if (check_magic_endian(header->magic, header->size, true, ph) < 0) {
+		pr_debug("endian/magic failed\n");
 		return -1;
+	}
+
+	if (ph->needs_swap)
+		header->size = bswap_64(header->size);
 
 	if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
 		return -1;
 
-	if (header->size != sizeof(*header)) {
-		u64 size = bswap_64(header->size);
-
-		if (size != sizeof(*header))
-			return -1;
-
-		ph->needs_swap = true;
-	}
-
 	return 0;
 }
 
@@ -1973,6 +2050,52 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
 	return 0;
 }
 
+static int read_attr(int fd, struct perf_header *ph,
+		     struct perf_file_attr *f_attr)
+{
+	struct perf_event_attr *attr = &f_attr->attr;
+	size_t sz, left;
+	size_t our_sz = sizeof(f_attr->attr);
+	int ret;
+
+	memset(f_attr, 0, sizeof(*f_attr));
+
+	/* read minimal guaranteed structure */
+	ret = readn(fd, attr, PERF_ATTR_SIZE_VER0);
+	if (ret <= 0) {
+		pr_debug("cannot read %d bytes of header attr\n",
+			 PERF_ATTR_SIZE_VER0);
+		return -1;
+	}
+
+	/* on file perf_event_attr size */
+	sz = attr->size;
+
+	if (ph->needs_swap)
+		sz = bswap_32(sz);
+
+	if (sz == 0) {
+		/* assume ABI0 */
+		sz =  PERF_ATTR_SIZE_VER0;
+	} else if (sz > our_sz) {
+		pr_debug("file uses a more recent and unsupported ABI"
+			 " (%zu bytes extra)\n", sz - our_sz);
+		return -1;
+	}
+	/* what we have not yet read and that we know about */
+	left = sz - PERF_ATTR_SIZE_VER0;
+	if (left) {
+		void *ptr = attr;
+		ptr += PERF_ATTR_SIZE_VER0;
+
+		ret = readn(fd, ptr, left);
+	}
+	/* read perf_file_section, ids are read in caller */
+	ret = readn(fd, &f_attr->ids, sizeof(f_attr->ids));
+
+	return ret <= 0 ? -1 : 0;
+}
+
 int perf_session__read_header(struct perf_session *session, int fd)
 {
 	struct perf_header *header = &session->header;
@@ -1988,19 +2111,17 @@ int perf_session__read_header(struct perf_session *session, int fd)
 	if (session->fd_pipe)
 		return perf_header__read_pipe(session, fd);
 
-	if (perf_file_header__read(&f_header, header, fd) < 0) {
-		pr_debug("incompatible file format\n");
+	if (perf_file_header__read(&f_header, header, fd) < 0)
 		return -EINVAL;
-	}
 
-	nr_attrs = f_header.attrs.size / sizeof(f_attr);
+	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
 	for (i = 0; i < nr_attrs; i++) {
 		struct perf_evsel *evsel;
 		off_t tmp;
 
-		if (readn(fd, &f_attr, sizeof(f_attr)) <= 0)
+		if (read_attr(fd, header, &f_attr) < 0)
 			goto out_errno;
 
 		if (header->needs_swap)

tools/perf/util/header.h

@@ -27,7 +27,7 @@ enum {
 	HEADER_EVENT_DESC,
 	HEADER_CPU_TOPOLOGY,
 	HEADER_NUMA_TOPOLOGY,
-
+	HEADER_BRANCH_STACK,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };

tools/perf/util/hist.c

@@ -50,21 +50,25 @@ static void hists__reset_col_len(struct hists *hists)
 		hists__set_col_len(hists, col, 0);
 }
 
+static void hists__set_unres_dso_col_len(struct hists *hists, int dso)
+{
+	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+
+	if (hists__col_len(hists, dso) < unresolved_col_width &&
+	    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
+	    !symbol_conf.dso_list)
+		hists__set_col_len(hists, dso, unresolved_col_width);
+}
+
 static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 {
+	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
 	u16 len;
 
 	if (h->ms.sym)
-		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen);
-	else {
-		const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
-
-		if (hists__col_len(hists, HISTC_DSO) < unresolved_col_width &&
-		    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-		    !symbol_conf.dso_list)
-			hists__set_col_len(hists, HISTC_DSO,
-					   unresolved_col_width);
-	}
+		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
+	else
+		hists__set_unres_dso_col_len(hists, HISTC_DSO);
 
 	len = thread__comm_len(h->thread);
 	if (hists__new_col_len(hists, HISTC_COMM, len))
@@ -74,6 +78,37 @@ static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		len = dso__name_len(h->ms.map->dso);
 		hists__new_col_len(hists, HISTC_DSO, len);
 	}
+
+	if (h->branch_info) {
+		int symlen;
+		/*
+		 * +4 accounts for '[x] ' priv level info
+		 * +2 account of 0x prefix on raw addresses
+		 */
+		if (h->branch_info->from.sym) {
+			symlen = (int)h->branch_info->from.sym->namelen + 4;
+			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+
+			symlen = dso__name_len(h->branch_info->from.map->dso);
+			hists__new_col_len(hists, HISTC_DSO_FROM, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM);
+		}
+
+		if (h->branch_info->to.sym) {
+			symlen = (int)h->branch_info->to.sym->namelen + 4;
+			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+
+			symlen = dso__name_len(h->branch_info->to.map->dso);
+			hists__new_col_len(hists, HISTC_DSO_TO, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
+		}
+	}
 }
 
 static void hist_entry__add_cpumode_period(struct hist_entry *he,
@@ -195,26 +230,14 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
-struct hist_entry *__hists__add_entry(struct hists *hists,
+static struct hist_entry *add_hist_entry(struct hists *hists,
+				      struct hist_entry *entry,
 				      struct addr_location *al,
-				      struct symbol *sym_parent, u64 period)
+				      u64 period)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
-	struct hist_entry entry = {
-		.thread	= al->thread,
-		.ms = {
-			.map	= al->map,
-			.sym	= al->sym,
-		},
-		.cpu	= al->cpu,
-		.ip	= al->addr,
-		.level	= al->level,
-		.period	= period,
-		.parent = sym_parent,
-		.filtered = symbol__parent_filter(sym_parent),
-	};
 	int cmp;
 
 	pthread_mutex_lock(&hists->lock);
@@ -225,7 +248,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		parent = *p;
 		he = rb_entry(parent, struct hist_entry, rb_node_in);
 
-		cmp = hist_entry__cmp(&entry, he);
+		cmp = hist_entry__cmp(entry, he);
 
 		if (!cmp) {
 			he->period += period;
@@ -239,7 +262,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(&entry);
+	he = hist_entry__new(entry);
 	if (!he)
 		goto out_unlock;
 
@@ -252,6 +275,51 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 	return he;
 }
 
+struct hist_entry *__hists__add_branch_entry(struct hists *self,
+					     struct addr_location *al,
+					     struct symbol *sym_parent,
+					     struct branch_info *bi,
+					     u64 period)
+{
+	struct hist_entry entry = {
+		.thread	= al->thread,
+		.ms = {
+			.map	= bi->to.map,
+			.sym	= bi->to.sym,
+		},
+		.cpu	= al->cpu,
+		.ip	= bi->to.addr,
+		.level	= al->level,
+		.period	= period,
+		.parent = sym_parent,
+		.filtered = symbol__parent_filter(sym_parent),
+		.branch_info = bi,
+	};
+
+	return add_hist_entry(self, &entry, al, period);
+}
+
+struct hist_entry *__hists__add_entry(struct hists *self,
+				      struct addr_location *al,
+				      struct symbol *sym_parent, u64 period)
+{
+	struct hist_entry entry = {
+		.thread	= al->thread,
+		.ms = {
+			.map	= al->map,
+			.sym	= al->sym,
+		},
+		.cpu	= al->cpu,
+		.ip	= al->addr,
+		.level	= al->level,
+		.period	= period,
+		.parent = sym_parent,
+		.filtered = symbol__parent_filter(sym_parent),
+	};
+
+	return add_hist_entry(self, &entry, al, period);
+}
+
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {

tools/perf/util/hist.h

@@ -42,6 +42,11 @@ enum hist_column {
 	HISTC_COMM,
 	HISTC_PARENT,
 	HISTC_CPU,
+	HISTC_MISPREDICT,
+	HISTC_SYMBOL_FROM,
+	HISTC_SYMBOL_TO,
+	HISTC_DSO_FROM,
+	HISTC_DSO_TO,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -74,6 +79,12 @@ int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size,
 			 struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
+struct hist_entry *__hists__add_branch_entry(struct hists *self,
+					     struct addr_location *al,
+					     struct symbol *sym_parent,
+					     struct branch_info *bi,
+					     u64 period);
+
 void hists__output_resort(struct hists *self);
 void hists__output_resort_threaded(struct hists *hists);
 void hists__collapse_resort(struct hists *self);

tools/perf/util/session.c

@@ -24,7 +24,7 @@ static int perf_session__open(struct perf_session *self, bool force)
 		self->fd = STDIN_FILENO;
 
 		if (perf_session__read_header(self, self->fd) < 0)
-			pr_err("incompatible file format");
+			pr_err("incompatible file format (rerun with -v to learn more)");
 
 		return 0;
 	}
@@ -56,7 +56,7 @@ static int perf_session__open(struct perf_session *self, bool force)
 	}
 
 	if (perf_session__read_header(self, self->fd) < 0) {
-		pr_err("incompatible file format");
+		pr_err("incompatible file format (rerun with -v to learn more)");
 		goto out_close;
 	}
 
@@ -229,6 +229,64 @@ static bool symbol__match_parent_regex(struct symbol *sym)
 	return 0;
 }
 
+static const u8 cpumodes[] = {
+	PERF_RECORD_MISC_USER,
+	PERF_RECORD_MISC_KERNEL,
+	PERF_RECORD_MISC_GUEST_USER,
+	PERF_RECORD_MISC_GUEST_KERNEL
+};
+#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
+
+static void ip__resolve_ams(struct machine *self, struct thread *thread,
+			    struct addr_map_symbol *ams,
+			    u64 ip)
+{
+	struct addr_location al;
+	size_t i;
+	u8 m;
+
+	memset(&al, 0, sizeof(al));
+
+	for (i = 0; i < NCPUMODES; i++) {
+		m = cpumodes[i];
+		/*
+		 * We cannot use the header.misc hint to determine whether a
+		 * branch stack address is user, kernel, guest, hypervisor.
+		 * Branches may straddle the kernel/user/hypervisor boundaries.
+		 * Thus, we have to try consecutively until we find a match
+		 * or else, the symbol is unknown
+		 */
+		thread__find_addr_location(thread, self, m, MAP__FUNCTION,
+				ip, &al, NULL);
+		if (al.sym)
+			goto found;
+	}
+found:
+	ams->addr = ip;
+	ams->al_addr = al.addr;
+	ams->sym = al.sym;
+	ams->map = al.map;
+}
+
+struct branch_info *machine__resolve_bstack(struct machine *self,
+					    struct thread *thr,
+					    struct branch_stack *bs)
+{
+	struct branch_info *bi;
+	unsigned int i;
+
+	bi = calloc(bs->nr, sizeof(struct branch_info));
+	if (!bi)
+		return NULL;
+
+	for (i = 0; i < bs->nr; i++) {
+		ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from);
+		bi[i].flags = bs->entries[i].flags;
+	}
+	return bi;
+}
+
 int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
 			       struct thread *thread,
 			       struct ip_callchain *chain,
@@ -697,6 +755,18 @@ static void callchain__printf(struct perf_sample *sample)
 		       i, sample->callchain->ips[i]);
 }
 
+static void branch_stack__printf(struct perf_sample *sample)
+{
+	uint64_t i;
+
+	printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);
+
+	for (i = 0; i < sample->branch_stack->nr; i++)
+		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n",
+			i, sample->branch_stack->entries[i].from,
+			sample->branch_stack->entries[i].to);
+}
+
 static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
@@ -744,6 +814,9 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
 
 	if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
 		callchain__printf(sample);
+
+	if (session->sample_type & PERF_SAMPLE_BRANCH_STACK)
+		branch_stack__printf(sample);
 }
 
 static struct machine *

tools/perf/util/session.h

@@ -73,6 +73,10 @@ int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel
 				    struct ip_callchain *chain,
 				    struct symbol **parent);
 
+struct branch_info *machine__resolve_bstack(struct machine *self,
+					    struct thread *thread,
+					    struct branch_stack *bs);
+
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
 void mem_bswap_64(void *src, int byte_size);

tools/perf/util/sort.c

@@ -8,6 +8,7 @@ const char	default_sort_order[] = "comm,dso,symbol";
 const char	*sort_order = default_sort_order;
 int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
+int		sort__branch_mode = -1; /* -1 = means not set */
 
 enum sort_type	sort__first_dimension;
 
@@ -94,6 +95,26 @@ static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
 	return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
 }
 
+static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
+{
+	struct dso *dso_l = map_l ? map_l->dso : NULL;
+	struct dso *dso_r = map_r ? map_r->dso : NULL;
+	const char *dso_name_l, *dso_name_r;
+
+	if (!dso_l || !dso_r)
+		return cmp_null(dso_l, dso_r);
+
+	if (verbose) {
+		dso_name_l = dso_l->long_name;
+		dso_name_r = dso_r->long_name;
+	} else {
+		dso_name_l = dso_l->short_name;
+		dso_name_r = dso_r->short_name;
+	}
+
+	return strcmp(dso_name_l, dso_name_r);
+}
+
 struct sort_entry sort_comm = {
 	.se_header	= "Command",
 	.se_cmp		= sort__comm_cmp,
@@ -107,36 +128,74 @@ struct sort_entry sort_comm = {
 static int64_t
 sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL;
-	struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL;
-	const char *dso_name_l, *dso_name_r;
+	return _sort__dso_cmp(left->ms.map, right->ms.map);
+}
 
-	if (!dso_l || !dso_r)
-		return cmp_null(dso_l, dso_r);
 
-	if (verbose) {
-		dso_name_l = dso_l->long_name;
-		dso_name_r = dso_r->long_name;
-	} else {
-		dso_name_l = dso_l->short_name;
-		dso_name_r = dso_r->short_name;
+static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r,
+			      u64 ip_l, u64 ip_r)
+{
+	if (!sym_l || !sym_r)
+		return cmp_null(sym_l, sym_r);
+
+	if (sym_l == sym_r)
+		return 0;
+
+	if (sym_l)
+		ip_l = sym_l->start;
+	if (sym_r)
+		ip_r = sym_r->start;
+
+	return (int64_t)(ip_r - ip_l);
+}
+
+static int _hist_entry__dso_snprintf(struct map *map, char *bf,
+				     size_t size, unsigned int width)
+{
+	if (map && map->dso) {
+		const char *dso_name = !verbose ? map->dso->short_name :
+			map->dso->long_name;
+		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
 	}
 
-	return strcmp(dso_name_l, dso_name_r);
+	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
 }
 
 static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
 				    size_t size, unsigned int width)
 {
-	if (self->ms.map && self->ms.map->dso) {
-		const char *dso_name = !verbose ? self->ms.map->dso->short_name :
-						  self->ms.map->dso->long_name;
-		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
+	return _hist_entry__dso_snprintf(self->ms.map, bf, size, width);
+}
+
+static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
+				     u64 ip, char level, char *bf, size_t size,
+				     unsigned int width __used)
+{
+	size_t ret = 0;
+
+	if (verbose) {
+		char o = map ? dso__symtab_origin(map->dso) : '!';
+		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
+				       BITS_PER_LONG / 4, ip, o);
 	}
 
-	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
+	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
+	if (sym)
+		ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+				       width - ret,
+				       sym->name);
+	else {
+		size_t len = BITS_PER_LONG / 4;
+		ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
+				       len, ip);
+		ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+				       width - ret, "");
+	}
+
+	return ret;
 }
 
+
 struct sort_entry sort_dso = {
 	.se_header	= "Shared Object",
 	.se_cmp		= sort__dso_cmp,
@@ -144,8 +203,14 @@ struct sort_entry sort_dso = {
 	.se_width_idx	= HISTC_DSO,
 };
 
-/* --sort symbol */
+static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width __used)
+{
+	return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip,
+					 self->level, bf, size, width);
+}
 
+/* --sort symbol */
 static int64_t
 sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -163,31 +228,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 	ip_l = left->ms.sym->start;
 	ip_r = right->ms.sym->start;
 
-	return (int64_t)(ip_r - ip_l);
-}
-
-static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width __used)
-{
-	size_t ret = 0;
-
-	if (verbose) {
-		char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
-		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
-				       BITS_PER_LONG / 4, self->ip, o);
-	}
-
-	if (!sort_dso.elide)
-		ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level);
-
-	if (self->ms.sym)
-		ret += repsep_snprintf(bf + ret, size - ret, "%s",
-				       self->ms.sym->name);
-	else
-		ret += repsep_snprintf(bf + ret, size - ret, "%-#*llx",
-				       BITS_PER_LONG / 4, self->ip);
-
-	return ret;
+	return _sort__sym_cmp(left->ms.sym, right->ms.sym, ip_l, ip_r);
 }
 
 struct sort_entry sort_sym = {
@@ -246,19 +287,155 @@ struct sort_entry sort_cpu = {
 	.se_width_idx	= HISTC_CPU,
 };
 
+static int64_t
+sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__dso_cmp(left->branch_info->from.map,
+			      right->branch_info->from.map);
+}
+
+static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	return _hist_entry__dso_snprintf(self->branch_info->from.map,
+					 bf, size, width);
+}
+
+struct sort_entry sort_dso_from = {
+	.se_header	= "Source Shared Object",
+	.se_cmp		= sort__dso_from_cmp,
+	.se_snprintf	= hist_entry__dso_from_snprintf,
+	.se_width_idx	= HISTC_DSO_FROM,
+};
+
+static int64_t
+sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__dso_cmp(left->branch_info->to.map,
+			      right->branch_info->to.map);
+}
+
+static int hist_entry__dso_to_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width)
+{
+	return _hist_entry__dso_snprintf(self->branch_info->to.map,
+					 bf, size, width);
+}
+
+static int64_t
+sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct addr_map_symbol *from_l = &left->branch_info->from;
+	struct addr_map_symbol *from_r = &right->branch_info->from;
+
+	if (!from_l->sym && !from_r->sym)
+		return right->level - left->level;
+
+	return _sort__sym_cmp(from_l->sym, from_r->sym, from_l->addr,
+			     from_r->addr);
+}
+
+static int64_t
+sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct addr_map_symbol *to_l = &left->branch_info->to;
+	struct addr_map_symbol *to_r = &right->branch_info->to;
+
+	if (!to_l->sym && !to_r->sym)
+		return right->level - left->level;
+
+	return _sort__sym_cmp(to_l->sym, to_r->sym, to_l->addr, to_r->addr);
+}
+
+static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width __used)
+{
+	struct addr_map_symbol *from = &self->branch_info->from;
+	return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
+					 self->level, bf, size, width);
+
+}
+
+static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width __used)
+{
+	struct addr_map_symbol *to = &self->branch_info->to;
+	return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
+					 self->level, bf, size, width);
+
+}
+
+struct sort_entry sort_dso_to = {
+	.se_header	= "Target Shared Object",
+	.se_cmp		= sort__dso_to_cmp,
+	.se_snprintf	= hist_entry__dso_to_snprintf,
+	.se_width_idx	= HISTC_DSO_TO,
+};
+
+struct sort_entry sort_sym_from = {
+	.se_header	= "Source Symbol",
+	.se_cmp		= sort__sym_from_cmp,
+	.se_snprintf	= hist_entry__sym_from_snprintf,
+	.se_width_idx	= HISTC_SYMBOL_FROM,
+};
+
+struct sort_entry sort_sym_to = {
+	.se_header	= "Target Symbol",
+	.se_cmp		= sort__sym_to_cmp,
+	.se_snprintf	= hist_entry__sym_to_snprintf,
+	.se_width_idx	= HISTC_SYMBOL_TO,
+};
+
+static int64_t
+sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	const unsigned char mp = left->branch_info->flags.mispred !=
+					right->branch_info->flags.mispred;
+	const unsigned char p = left->branch_info->flags.predicted !=
+					right->branch_info->flags.predicted;
+
+	return mp || p;
+}
+
+static int hist_entry__mispredict_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width){
+	static const char *out = "N/A";
+
+	if (self->branch_info->flags.predicted)
+		out = "N";
+	else if (self->branch_info->flags.mispred)
+		out = "Y";
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+struct sort_entry sort_mispredict = {
+	.se_header	= "Branch Mispredicted",
+	.se_cmp		= sort__mispredict_cmp,
+	.se_snprintf	= hist_entry__mispredict_snprintf,
+	.se_width_idx	= HISTC_MISPREDICT,
+};
+
 struct sort_dimension {
 	const char		*name;
 	struct sort_entry	*entry;
 	int			taken;
 };
 
+#define DIM(d, n, func) [d] = { .name = n, .entry = &(func) }
+
 static struct sort_dimension sort_dimensions[] = {
-	{ .name = "pid",	.entry = &sort_thread,	},
-	{ .name = "comm",	.entry = &sort_comm,	},
-	{ .name = "dso",	.entry = &sort_dso,	},
-	{ .name = "symbol",	.entry = &sort_sym,	},
-	{ .name = "parent",	.entry = &sort_parent,	},
-	{ .name = "cpu",	.entry = &sort_cpu,	},
+	DIM(SORT_PID, "pid", sort_thread),
+	DIM(SORT_COMM, "comm", sort_comm),
+	DIM(SORT_DSO, "dso", sort_dso),
+	DIM(SORT_DSO_FROM, "dso_from", sort_dso_from),
+	DIM(SORT_DSO_TO, "dso_to", sort_dso_to),
+	DIM(SORT_SYM, "symbol", sort_sym),
+	DIM(SORT_SYM_TO, "symbol_from", sort_sym_from),
+	DIM(SORT_SYM_FROM, "symbol_to", sort_sym_to),
+	DIM(SORT_PARENT, "parent", sort_parent),
+	DIM(SORT_CPU, "cpu", sort_cpu),
+	DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
 };
 
 int sort_dimension__add(const char *tok)
@@ -270,7 +447,6 @@ int sort_dimension__add(const char *tok)
 
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
-
 		if (sd->entry == &sort_parent) {
 			int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
 			if (ret) {
@@ -302,6 +478,16 @@ int sort_dimension__add(const char *tok)
 				sort__first_dimension = SORT_PARENT;
 			else if (!strcmp(sd->name, "cpu"))
 				sort__first_dimension = SORT_CPU;
+			else if (!strcmp(sd->name, "symbol_from"))
+				sort__first_dimension = SORT_SYM_FROM;
+			else if (!strcmp(sd->name, "symbol_to"))
+				sort__first_dimension = SORT_SYM_TO;
+			else if (!strcmp(sd->name, "dso_from"))
+				sort__first_dimension = SORT_DSO_FROM;
+			else if (!strcmp(sd->name, "dso_to"))
+				sort__first_dimension = SORT_DSO_TO;
+			else if (!strcmp(sd->name, "mispredict"))
+				sort__first_dimension = SORT_MISPREDICT;
 		}
 
 		list_add_tail(&sd->entry->list, &hist_entry__sort_list);
@@ -309,7 +495,6 @@ int sort_dimension__add(const char *tok)
 
 		return 0;
 	}
-
 	return -ESRCH;
 }
 

tools/perf/util/sort.h

@@ -31,11 +31,16 @@ extern const char *parent_pattern;
 extern const char default_sort_order[];
 extern int sort__need_collapse;
 extern int sort__has_parent;
+extern int sort__branch_mode;
 extern char *field_sep;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
 extern struct sort_entry sort_sym;
 extern struct sort_entry sort_parent;
+extern struct sort_entry sort_dso_from;
+extern struct sort_entry sort_dso_to;
+extern struct sort_entry sort_sym_from;
+extern struct sort_entry sort_sym_to;
 extern enum sort_type sort__first_dimension;
 
 /**
@@ -72,6 +77,7 @@ struct hist_entry {
 		struct hist_entry *pair;
 		struct rb_root	  sorted_chain;
 	};
+	struct branch_info	*branch_info;
 	struct callchain_root	callchain[0];
 };
 
@@ -82,6 +88,11 @@ enum sort_type {
 	SORT_SYM,
 	SORT_PARENT,
 	SORT_CPU,
+	SORT_DSO_FROM,
+	SORT_DSO_TO,
+	SORT_SYM_FROM,
+	SORT_SYM_TO,
+	SORT_MISPREDICT,
 };
 
 /*

tools/perf/util/symbol.h

@@ -5,6 +5,7 @@
 #include <stdbool.h>
 #include <stdint.h>
 #include "map.h"
+#include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
@@ -96,7 +97,11 @@ struct symbol_conf {
 			*col_width_list_str;
        struct strlist	*dso_list,
 			*comm_list,
-			*sym_list;
+			*sym_list,
+			*dso_from_list,
+			*dso_to_list,
+			*sym_from_list,
+			*sym_to_list;
 	const char	*symfs;
 };
 
@@ -120,6 +125,19 @@ struct map_symbol {
 	bool	      has_children;
 };
 
+struct addr_map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+	u64	      addr;
+	u64	      al_addr;
+};
+
+struct branch_info {
+	struct addr_map_symbol from;
+	struct addr_map_symbol to;
+	struct branch_flags flags;
+};
+
 struct addr_location {
 	struct thread *thread;
 	struct map    *map;

tools/perf/util/ui/browsers/hists.c

@@ -805,8 +805,11 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
 		self->hists = hists;
 		self->b.refresh = hist_browser__refresh;
 		self->b.seek = ui_browser__hists_seek;
-		self->b.use_navkeypressed = true,
-		self->has_symbols = sort_sym.list.next != NULL;
+		self->b.use_navkeypressed = true;
+		if (sort__branch_mode == 1)
+			self->has_symbols = sort_sym_from.list.next != NULL;
+		else
+			self->has_symbols = sort_sym.list.next != NULL;
 	}
 
 	return self;
@@ -853,6 +856,16 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size,
 	return printed;
 }
 
+static inline void free_popup_options(char **options, int n)
+{
+	int i;
+
+	for (i = 0; i < n; ++i) {
+		free(options[i]);
+		options[i] = NULL;
+	}
+}
+
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    const char *helpline, const char *ev_name,
 				    bool left_exits,
@@ -861,7 +874,10 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 {
 	struct hists *self = &evsel->hists;
 	struct hist_browser *browser = hist_browser__new(self);
+	struct branch_info *bi;
 	struct pstack *fstack;
+	char *options[16];
+	int nr_options = 0;
 	int key = -1;
 
 	if (browser == NULL)
@@ -873,13 +889,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 	ui_helpline__push(helpline);
 
+	memset(options, 0, sizeof(options));
+
 	while (1) {
 		const struct thread *thread = NULL;
 		const struct dso *dso = NULL;
-		char *options[16];
-		int nr_options = 0, choice = 0, i,
+		int choice = 0,
 		    annotate = -2, zoom_dso = -2, zoom_thread = -2,
-		    browse_map = -2;
+		    annotate_f = -2, annotate_t = -2, browse_map = -2;
+
+		nr_options = 0;
 
 		key = hist_browser__run(browser, ev_name, timer, arg, delay_secs);
 
@@ -887,7 +906,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			thread = hist_browser__selected_thread(browser);
 			dso = browser->selection->map ? browser->selection->map->dso : NULL;
 		}
-
 		switch (key) {
 		case K_TAB:
 		case K_UNTAB:
@@ -902,7 +920,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			if (!browser->has_symbols) {
 				ui_browser__warning(&browser->b, delay_secs * 2,
 			"Annotation is only available for symbolic views, "
-			"include \"sym\" in --sort to use it.");
+			"include \"sym*\" in --sort to use it.");
 				continue;
 			}
 
@@ -972,12 +990,34 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		if (!browser->has_symbols)
 			goto add_exit_option;
 
-		if (browser->selection != NULL &&
-		    browser->selection->sym != NULL &&
-		    !browser->selection->map->dso->annotate_warned &&
-		    asprintf(&options[nr_options], "Annotate %s",
-			     browser->selection->sym->name) > 0)
-			annotate = nr_options++;
+		if (sort__branch_mode == 1) {
+			bi = browser->he_selection->branch_info;
+			if (browser->selection != NULL &&
+			    bi &&
+			    bi->from.sym != NULL &&
+			    !bi->from.map->dso->annotate_warned &&
+				asprintf(&options[nr_options], "Annotate %s",
+					 bi->from.sym->name) > 0)
+				annotate_f = nr_options++;
+
+			if (browser->selection != NULL &&
+			    bi &&
+			    bi->to.sym != NULL &&
+			    !bi->to.map->dso->annotate_warned &&
+			    (bi->to.sym != bi->from.sym ||
+			     bi->to.map->dso != bi->from.map->dso) &&
+				asprintf(&options[nr_options], "Annotate %s",
+					 bi->to.sym->name) > 0)
+				annotate_t = nr_options++;
+		} else {
+
+			if (browser->selection != NULL &&
+			    browser->selection->sym != NULL &&
+			    !browser->selection->map->dso->annotate_warned &&
+				asprintf(&options[nr_options], "Annotate %s",
+					 browser->selection->sym->name) > 0)
+				annotate = nr_options++;
+		}
 
 		if (thread != NULL &&
 		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
@@ -998,25 +1038,39 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			browse_map = nr_options++;
 add_exit_option:
 		options[nr_options++] = (char *)"Exit";
-
+retry_popup_menu:
 		choice = ui__popup_menu(nr_options, options);
 
-		for (i = 0; i < nr_options - 1; ++i)
-			free(options[i]);
-
 		if (choice == nr_options - 1)
 			break;
 
-		if (choice == -1)
+		if (choice == -1) {
+			free_popup_options(options, nr_options - 1);
 			continue;
+		}
 
-		if (choice == annotate) {
+		if (choice == annotate || choice == annotate_t || choice == annotate_f) {
 			struct hist_entry *he;
 			int err;
 do_annotate:
 			he = hist_browser__selected_entry(browser);
 			if (he == NULL)
 				continue;
+
+			/*
+			 * we stash the branch_info symbol + map into the
+			 * the ms so we don't have to rewrite all the annotation
+			 * code to use branch_info.
+			 * in branch mode, the ms struct is not used
+			 */
+			if (choice == annotate_f) {
+				he->ms.sym = he->branch_info->from.sym;
+				he->ms.map = he->branch_info->from.map;
+			}  else if (choice == annotate_t) {
+				he->ms.sym = he->branch_info->to.sym;
+				he->ms.map = he->branch_info->to.map;
+			}
+
 			/*
 			 * Don't let this be freed, say, by hists__decay_entry.
 			 */
@@ -1024,9 +1078,18 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			err = hist_entry__tui_annotate(he, evsel->idx,
 						       timer, arg, delay_secs);
 			he->used = false;
+			/*
+			 * offer option to annotate the other branch source or target
+			 * (if they exists) when returning from annotate
+			 */
+			if ((err == 'q' || err == CTRL('c'))
+			    && annotate_t != -2 && annotate_f != -2)
+				goto retry_popup_menu;
+
 			ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
 			if (err)
 				ui_browser__handle_resize(&browser->b);
+
 		} else if (choice == browse_map)
 			map__browse(browser->selection->map);
 		else if (choice == zoom_dso) {
@@ -1072,6 +1135,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	pstack__delete(fstack);
 out:
 	hist_browser__delete(browser);
+	free_popup_options(options, nr_options - 1);
 	return key;
 }