[RFC PATCH 0/7] perf, x86: Reduce lbr_sel_map size

[RFC PATCH 0/7] perf, x86: Reduce lbr_sel_map size

[Yan, Zheng]

From: "Yan, Zheng" <zheng.z.yan@intel.com>

Haswell has a new feature that utilizes the existing Last Branch Record
facility to record call chains. When the feature is enabled, function
call will be collected as normal, but as return instructions are executed
the last captured branch record is popped from the on-chip LBR registers.
The LBR call stack facility can help perf to get call chains of progam 
without frame pointer. When perf tool requests PERF_SAMPLE_CALLCHAIN +
PERF_SAMPLE_BRANCH_USER, this feature is dynamically enabled by default.
This feature can be disabled/enabled through an attribute file in the cpu
pmu sysfs directory.

The main change since previous patch series is:
 Patch 3 introduces PMU context switch callback, and uses the callback to
 unify the flush branch stack codeo.

 Patch 4 uses the context switch callback to save/restore the LBR stack.

Regards
Yan, Zheng

[RFC PATCH 1/7] perf, x86: Reduce lbr_sel_map size

[Yan, Zheng]

From: "Yan, Zheng" <zheng.z.yan@intel.com>

The index of lbr_sel_map is bit value of perf branch_sample_type.
We can reduce lbr_sel_map size by using bit shift as index.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.h           |  4 +++
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 50 ++++++++++++++----------------
 include/uapi/linux/perf_event.h            | 42 +++++++++++++++++--------
 3 files changed, 56 insertions(+), 40 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index ce84ede..da338c7 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -458,6 +458,10 @@ struct x86_pmu {
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
 };
 
+enum {
+	PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE = PERF_SAMPLE_BRANCH_MAX_SHIFT,
+};
+
 #define x86_add_quirk(func_)						\
 do {									\
 	static struct x86_pmu_quirk __quirk __initdata = {		\
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index d5be06a..1e74cc4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -69,10 +69,6 @@ static enum {
 #define LBR_FROM_FLAG_IN_TX    (1ULL << 62)
 #define LBR_FROM_FLAG_ABORT    (1ULL << 61)
 
-#define for_each_branch_sample_type(x) \
-	for ((x) = PERF_SAMPLE_BRANCH_USER; \
-	     (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
-
 /*
  * x86control flow change classification
  * x86control flow changes include branches, interrupts, traps, faults
@@ -387,14 +383,14 @@ 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;
+	u64 mask = 0, v;
+	int i;
 
-	for_each_branch_sample_type(m) {
-		if (!(br_type & m))
+	for (i = 0; i < PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE; i++) {
+		if (!(br_type & (1ULL << i)))
 			continue;
 
-		v = x86_pmu.lbr_sel_map[m];
+		v = x86_pmu.lbr_sel_map[i];
 		if (v == LBR_NOT_SUPP)
 			return -EOPNOTSUPP;
 
@@ -649,33 +645,33 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 /*
  * 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,
+static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= 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] =
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] =
 	 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,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = 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,
+static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
+						| LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
 };
 
 /* core */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index ca1d90b..ef708d2 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -150,20 +150,36 @@ enum perf_event_sample_format {
  * 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_shift {
+	PERF_SAMPLE_BRANCH_USER_SHIFT		= 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL_SHIFT		= 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV_SHIFT		= 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY_SHIFT		= 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT	= 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT	= 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL_SHIFT	= 6, /* indirect calls */
+	PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT	= 7, /* transaction aborts */
+	PERF_SAMPLE_BRANCH_IN_TX_SHIFT		= 8, /* in transaction */
+	PERF_SAMPLE_BRANCH_NO_TX_SHIFT		= 9, /* not in transaction */
+
+	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
+};
+
 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_ABORT_TX	= 1U << 7, /* transaction aborts */
-	PERF_SAMPLE_BRANCH_IN_TX	= 1U << 8, /* in transaction */
-	PERF_SAMPLE_BRANCH_NO_TX	= 1U << 9, /* not in transaction */
-
-	PERF_SAMPLE_BRANCH_MAX		= 1U << 10, /* non-ABI */
+	PERF_SAMPLE_BRANCH_USER         = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT,
+	PERF_SAMPLE_BRANCH_KERNEL       = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT,
+	PERF_SAMPLE_BRANCH_HV           = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT,
+
+	PERF_SAMPLE_BRANCH_ANY          = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_CALL     = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_RETURN   = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT,
+	PERF_SAMPLE_BRANCH_IND_CALL     = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ABORT_TX     = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_IN_TX        = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_NO_TX        = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT,
+
+	PERF_SAMPLE_BRANCH_MAX          = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
-- 
1.8.1.4

[RFC PATCH 2/7] perf, x86: Basic Haswell LBR call stack support

[Yan, Zheng]

From: "Yan, Zheng" <zheng.z.yan@intel.com>

The new HSW call stack feature provides a facility such that
unfiltered call data will be collected as normal, but as return
instructions are executed the last captured branch record is
popped from the LBR stack. Thus, branch information relative to
leaf functions will not be captured, while preserving the call
stack information of the main line execution path.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.h           |  7 ++-
 arch/x86/kernel/cpu/perf_event_intel.c     |  2 +-
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 93 +++++++++++++++++++++++-------
 3 files changed, 78 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index da338c7..9be984d 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -459,7 +459,10 @@ struct x86_pmu {
 };
 
 enum {
-	PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE = PERF_SAMPLE_BRANCH_MAX_SHIFT,
+	PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = PERF_SAMPLE_BRANCH_MAX_SHIFT,
+	PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE,
+
+	PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT,
 };
 
 #define x86_add_quirk(func_)						\
@@ -694,6 +697,8 @@ void intel_pmu_lbr_init_atom(void);
 
 void intel_pmu_lbr_init_snb(void);
 
+void intel_pmu_lbr_init_hsw(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 int p4_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 353b7a3..b300594 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2505,7 +2505,7 @@ __init int intel_pmu_init(void)
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 
-		intel_pmu_lbr_init_snb();
+		intel_pmu_lbr_init_hsw();
 
 		x86_pmu.event_constraints = intel_hsw_event_constraints;
 		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 1e74cc4..11911db 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -39,6 +39,7 @@ static enum {
 #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_CALL_STACK_BIT	9 /* enable call stack */
 
 #define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
 #define LBR_USER	(1 << LBR_USER_BIT)
@@ -49,6 +50,7 @@ static enum {
 #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_CALL_STACK	(1 << LBR_CALL_STACK_BIT)
 
 #define LBR_PLM (LBR_KERNEL | LBR_USER)
 
@@ -74,24 +76,25 @@ static enum {
  * 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 */
-	X86_BR_ABORT    = 1 << 12,/* transaction abort */
-	X86_BR_IN_TX    = 1 << 13,/* in transaction */
-	X86_BR_NO_TX    = 1 << 14,/* not in transaction */
+	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 */
+	X86_BR_ABORT		= 1 << 12,/* transaction abort */
+	X86_BR_IN_TX		= 1 << 13,/* in transaction */
+	X86_BR_NO_TX		= 1 << 14,/* not in transaction */
+	X86_BR_CALL_STACK	= 1 << 15,/* call stack */
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@ -135,7 +138,14 @@ static void __intel_pmu_lbr_enable(void)
 		wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-	debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	debugctl |= DEBUGCTLMSR_LBR;
+	/*
+	 * LBR callstack does not work well with FREEZE_LBRS_ON_PMI.
+	 * If FREEZE_LBRS_ON_PMI is set, PMI near call/return instructions
+	 * may cause superfluous increase/decrease of LBR_TOS.
+	 */
+	if (!cpuc->lbr_sel || !(cpuc->lbr_sel->config & LBR_CALL_STACK))
+		debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 }
 
@@ -333,7 +343,7 @@ void intel_pmu_lbr_read(void)
  * - 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)
+static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 {
 	u64 br_type = event->attr.branch_sample_type;
 	int mask = 0;
@@ -367,11 +377,21 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 	if (br_type & PERF_SAMPLE_BRANCH_NO_TX)
 		mask |= X86_BR_NO_TX;
 
+	if (br_type & PERF_SAMPLE_BRANCH_CALL_STACK) {
+		if (!x86_pmu.lbr_sel_map)
+			return -EOPNOTSUPP;
+		if (mask & ~(X86_BR_USER | X86_BR_KERNEL))
+			return -EINVAL;
+		mask |= X86_BR_CALL | X86_BR_IND_CALL | X86_BR_RET |
+			X86_BR_CALL_STACK;
+	}
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
 	 */
 	event->hw.branch_reg.reg = mask;
+	return 0;
 }
 
 /*
@@ -401,7 +421,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 	reg->idx = EXTRA_REG_LBR;
 
 	/* LBR_SELECT operates in suppress mode so invert mask */
-	reg->config = ~mask & x86_pmu.lbr_sel_mask;
+	reg->config = mask ^ x86_pmu.lbr_sel_mask;
 
 	return 0;
 }
@@ -419,7 +439,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event)
 	/*
 	 * setup SW LBR filter
 	 */
-	intel_pmu_setup_sw_lbr_filter(event);
+	ret = intel_pmu_setup_sw_lbr_filter(event);
+	if (ret)
+		return ret;
 
 	/*
 	 * setup HW LBR filter, if any
@@ -674,6 +696,19 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = {
 	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
 };
 
+static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
+						| LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
+	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
+						| LBR_RETURN | LBR_CALL_STACK,
+};
+
 /* core */
 void intel_pmu_lbr_init_core(void)
 {
@@ -730,6 +765,20 @@ void intel_pmu_lbr_init_snb(void)
 	pr_cont("16-deep LBR, ");
 }
 
+/* haswell */
+void intel_pmu_lbr_init_hsw(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  = hsw_lbr_sel_map;
+
+	pr_cont("16-deep LBR, ");
+}
+
 /* atom */
 void intel_pmu_lbr_init_atom(void)
 {
-- 
1.8.1.4

[RFC PATCH 3/7] perf, core: replace flush_branch_stack with ctxsw callback

[Yan, Zheng]

From: "Yan, Zheng" <zheng.z.yan@intel.com>

Replace the flush_branch_stack pmu callback with generic context
switch callback. x86 specific perf codes use the callback to
flush branch stack.

To avoid unnecessary overhead, the context switch callback can be
enabled/disabled.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.c           |   8 +-
 arch/x86/kernel/cpu/perf_event.h           |   6 +-
 arch/x86/kernel/cpu/perf_event_intel.c     |  14 +--
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |  32 ++++---
 include/linux/perf_event.h                 |   7 +-
 kernel/events/core.c                       | 135 ++++++++++++++---------------
 6 files changed, 97 insertions(+), 105 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8355c84..b96aea8 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1846,10 +1846,10 @@ static const struct attribute_group *x86_pmu_attr_groups[] = {
 	NULL,
 };
 
-static void x86_pmu_flush_branch_stack(void)
+static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
-	if (x86_pmu.flush_branch_stack)
-		x86_pmu.flush_branch_stack();
+	if (x86_pmu.sched_task)
+		x86_pmu.sched_task(ctx, sched_in);
 }
 
 void perf_check_microcode(void)
@@ -1878,7 +1878,7 @@ static struct pmu pmu = {
 	.commit_txn		= x86_pmu_commit_txn,
 
 	.event_idx		= x86_pmu_event_idx,
-	.flush_branch_stack	= x86_pmu_flush_branch_stack,
+	.sched_task		= x86_pmu_sched_task,
 };
 
 void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 9be984d..62f6ee8 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -150,7 +150,6 @@ struct cpu_hw_events {
 	 * Intel LBR bits
 	 */
 	int				lbr_users;
-	void				*lbr_context;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
@@ -416,7 +415,8 @@ struct x86_pmu {
 	void		(*cpu_dead)(int cpu);
 
 	void		(*check_microcode)(void);
-	void		(*flush_branch_stack)(void);
+	void		(*sched_task)(struct perf_event_context *ctx,
+				     bool sched_in);
 
 	/*
 	 * Intel Arch Perfmon v2+
@@ -677,6 +677,8 @@ void intel_pmu_pebs_disable_all(void);
 
 void intel_ds_init(void);
 
+void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
+
 void intel_pmu_lbr_reset(void);
 
 void intel_pmu_lbr_enable(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index b300594..92b132e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2038,18 +2038,6 @@ static void intel_pmu_cpu_dying(int cpu)
 	fini_debug_store_on_cpu(cpu);
 }
 
-static void intel_pmu_flush_branch_stack(void)
-{
-	/*
-	 * Intel LBR does not tag entries with the
-	 * PID of the current task, then we need to
-	 * flush it on ctxsw
-	 * For now, we simply reset it
-	 */
-	if (x86_pmu.lbr_nr)
-		intel_pmu_lbr_reset();
-}
-
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -2101,7 +2089,7 @@ 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,
+	.sched_task		= intel_pmu_lbr_sched_task,
 };
 
 static __init void intel_clovertown_quirk(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 11911db..468ac1d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -187,24 +187,32 @@ void intel_pmu_lbr_reset(void)
 		intel_pmu_lbr_reset_64();
 }
 
-void intel_pmu_lbr_enable(struct perf_event *event)
+void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-
 	if (!x86_pmu.lbr_nr)
 		return;
 
 	/*
-	 * Reset the LBR stack if we changed task context to
-	 * avoid data leaks.
+	 * It is 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.
 	 */
-	if (event->ctx->task && cpuc->lbr_context != event->ctx) {
+	if (sched_in)
 		intel_pmu_lbr_reset();
-		cpuc->lbr_context = event->ctx;
-	}
+}
+
+void intel_pmu_lbr_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!x86_pmu.lbr_nr)
+		return;
+
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
 	cpuc->lbr_users++;
+	if (cpuc->lbr_users == 1)
+		perf_sched_cb_enable(event->ctx->pmu);
 }
 
 void intel_pmu_lbr_disable(struct perf_event *event)
@@ -217,10 +225,10 @@ 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) {
-		__intel_pmu_lbr_disable();
-		/* avoid stale pointer */
-		cpuc->lbr_context = NULL;
+	if (!cpuc->lbr_users) {
+		perf_sched_cb_disable(event->ctx->pmu);
+		if (cpuc->enabled)
+			__intel_pmu_lbr_disable();
 	}
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 866e85c..991bcf5 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -248,9 +248,10 @@ struct pmu {
 	int (*event_idx)		(struct perf_event *event); /*optional */
 
 	/*
-	 * flush branch stack on context-switches (needed in cpu-wide mode)
+	 * PMU callback for context-switches. optional
 	 */
-	void (*flush_branch_stack)	(void);
+	void (*sched_task)		(struct perf_event_context *ctx,
+					 bool sched_in); /*optional */
 };
 
 /**
@@ -521,6 +522,8 @@ extern void perf_event_delayed_put(struct task_struct *task);
 extern void perf_event_print_debug(void);
 extern void perf_pmu_disable(struct pmu *pmu);
 extern void perf_pmu_enable(struct pmu *pmu);
+extern void perf_sched_cb_disable(struct pmu *pmu);
+extern void perf_sched_cb_enable(struct pmu *pmu);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
 extern int perf_event_refresh(struct perf_event *event, int refresh);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dd236b6..a6e11fd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -140,7 +140,7 @@ 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 DEFINE_PER_CPU(int, perf_sched_cb_usages);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -2297,6 +2297,62 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	}
 }
 
+void perf_sched_cb_disable(struct pmu *pmu)
+{
+	__get_cpu_var(perf_sched_cb_usages)--;
+}
+
+void perf_sched_cb_enable(struct pmu *pmu)
+{
+	__get_cpu_var(perf_sched_cb_usages)++;
+}
+
+/*
+ * This function provides the context switch callback to the lower code
+ * layer. It is invoked ONLY when the context switch callback is enabled.
+ */
+static void perf_pmu_sched_task(struct task_struct *prev,
+				struct task_struct *next,
+				bool sched_in)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+	int count = 0;
+
+	if (prev == next)
+		return;
+
+	local_irq_save(flags);
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		if (!pmu->sched_task)
+			continue;
+
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+		pmu = cpuctx->ctx.pmu;
+
+		perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+		perf_pmu_disable(pmu);
+
+		pmu->sched_task(cpuctx->task_ctx, sched_in);
+
+		perf_pmu_enable(pmu);
+
+		perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+
+		if (++count >= __get_cpu_var(perf_sched_cb_usages))
+			break;
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
 #define for_each_task_context_nr(ctxn)					\
 	for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++)
 
@@ -2316,6 +2372,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
+	if (__get_cpu_var(perf_sched_cb_usages))
+		perf_pmu_sched_task(task, next, false);
+
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
 
@@ -2480,65 +2539,6 @@ 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
@@ -2572,9 +2572,8 @@ 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);
+	if (__get_cpu_var(perf_sched_cb_usages))
+		perf_pmu_sched_task(prev, task, true);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -3137,10 +3136,6 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu)
 	if (event->parent)
 		return;
 
-	if (has_branch_stack(event)) {
-		if (!(event->attach_state & PERF_ATTACH_TASK))
-			atomic_dec(&per_cpu(perf_branch_stack_events, cpu));
-	}
 	if (is_cgroup_event(event))
 		atomic_dec(&per_cpu(perf_cgroup_events, cpu));
 }
@@ -6447,7 +6442,7 @@ got_cpu_context:
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
-	list_add_rcu(&pmu->entry, &pmus);
+	list_add_tail_rcu(&pmu->entry, &pmus);
 	ret = 0;
 unlock:
 	mutex_unlock(&pmus_lock);
@@ -6530,10 +6525,6 @@ static void account_event_cpu(struct perf_event *event, int cpu)
 	if (event->parent)
 		return;
 
-	if (has_branch_stack(event)) {
-		if (!(event->attach_state & PERF_ATTACH_TASK))
-			atomic_inc(&per_cpu(perf_branch_stack_events, cpu));
-	}
 	if (is_cgroup_event(event))
 		atomic_inc(&per_cpu(perf_cgroup_events, cpu));
 }
-- 
1.8.1.4

[RFC PATCH 4/7] perf, x86: Save/resotre LBR stack during context switch

[Yan, Zheng]

From: "Yan, Zheng" <zheng.z.yan@intel.com>

When the LBR call stack is enabled, it is necessary to save/restore
the LBR stack on context switch. The solution is saving/restoring
the LBR stack to/from task's perf event context.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.c           |   1 +
 arch/x86/kernel/cpu/perf_event.h           |   8 +++
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 101 ++++++++++++++++++++++++-----
 include/linux/perf_event.h                 |   5 ++
 kernel/events/core.c                       |  22 ++++++-
 5 files changed, 121 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b96aea8..d29d852 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1879,6 +1879,7 @@ static struct pmu pmu = {
 
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
+	.task_ctx_size          = sizeof(struct x86_perf_task_context),
 };
 
 void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 62f6ee8..b1d2fa9 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -150,6 +150,7 @@ struct cpu_hw_events {
 	 * Intel LBR bits
 	 */
 	int				lbr_users;
+	int				lbr_sys_users;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
@@ -458,6 +459,13 @@ struct x86_pmu {
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
 };
 
+struct x86_perf_task_context {
+	u64 lbr_from[MAX_LBR_ENTRIES];
+	u64 lbr_to[MAX_LBR_ENTRIES];
+	int lbr_callstack_users;
+	bool lbr_stack_saved;
+};
+
 enum {
 	PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = PERF_SAMPLE_BRANCH_MAX_SHIFT,
 	PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 468ac1d..a160891 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -187,29 +187,103 @@ void intel_pmu_lbr_reset(void)
 		intel_pmu_lbr_reset_64();
 }
 
+/*
+ * TOS = most recently recorded branch
+ */
+static inline u64 intel_pmu_lbr_tos(void)
+{
+	u64 tos;
+
+	rdmsrl(x86_pmu.lbr_tos, tos);
+
+	return tos;
+}
+
+static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
+{
+	int i;
+	unsigned lbr_idx, mask = x86_pmu.lbr_nr - 1;
+	u64 tos = intel_pmu_lbr_tos();
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		lbr_idx = (tos - i) & mask;
+		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
+		wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+	}
+	task_ctx->lbr_stack_saved = false;
+}
+
+static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
+{
+	int i;
+	unsigned lbr_idx, mask = x86_pmu.lbr_nr - 1;
+	u64 tos = intel_pmu_lbr_tos();
+
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		lbr_idx = (tos - i) & mask;
+		rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
+		rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+	}
+	task_ctx->lbr_stack_saved = true;
+}
+
+
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
+	struct cpu_hw_events *cpuc;
+	struct x86_perf_task_context *task_ctx;
+
 	if (!x86_pmu.lbr_nr)
 		return;
+	
+	cpuc = &__get_cpu_var(cpu_hw_events);
+	task_ctx = ctx ? ctx->task_ctx_data : NULL;
+
 
 	/*
 	 * It is 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.
 	 */
-	if (sched_in)
-		intel_pmu_lbr_reset();
+	if (sched_in) {
+		if (cpuc->lbr_sys_users > 0 ||
+		    !task_ctx ||
+		    !task_ctx->lbr_stack_saved ||
+		    !task_ctx->lbr_callstack_users)
+			intel_pmu_lbr_reset();
+		else
+			__intel_pmu_lbr_restore(task_ctx);
+	} else if (task_ctx) {
+		if (task_ctx->lbr_callstack_users)
+			__intel_pmu_lbr_save(task_ctx);
+		else
+			task_ctx->lbr_stack_saved = false;
+	}
+}
+
+static inline bool branch_user_callstack(unsigned br_sel)
+{
+	return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK);
 }
 
 void intel_pmu_lbr_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct x86_perf_task_context *task_ctx;
 
 	if (!x86_pmu.lbr_nr)
 		return;
 
+	cpuc = &__get_cpu_var(cpu_hw_events);
+	task_ctx = event->ctx ? event->ctx->task_ctx_data : NULL;
+
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
+	if (!(event->attach_state & PERF_ATTACH_TASK))
+		cpuc->lbr_sys_users++;
+	else if (branch_user_callstack(cpuc->br_sel))
+		task_ctx->lbr_callstack_users++;
+
 	cpuc->lbr_users++;
 	if (cpuc->lbr_users == 1)
 		perf_sched_cb_enable(event->ctx->pmu);
@@ -217,10 +291,19 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 
 void intel_pmu_lbr_disable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc;
+	struct x86_perf_task_context *task_ctx;
 
 	if (!x86_pmu.lbr_nr)
 		return;
+	
+	cpuc = &__get_cpu_var(cpu_hw_events);
+	task_ctx = event->ctx ? event->ctx->task_ctx_data : NULL;
+
+	if (!(event->attach_state & PERF_ATTACH_TASK))
+		cpuc->lbr_sys_users--;
+	else if (branch_user_callstack(cpuc->br_sel))
+		task_ctx->lbr_callstack_users--;
 
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
@@ -248,18 +331,6 @@ 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;
-
-	rdmsrl(x86_pmu.lbr_tos, tos);
-
-	return tos;
-}
-
 static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 {
 	unsigned long mask = x86_pmu.lbr_nr - 1;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 991bcf5..23471c2 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -252,6 +252,10 @@ struct pmu {
 	 */
 	void (*sched_task)		(struct perf_event_context *ctx,
 					 bool sched_in); /*optional */
+	/*
+	 * PMU specific data size
+	 */
+	size_t				task_ctx_size;
 };
 
 /**
@@ -471,6 +475,7 @@ struct perf_event_context {
 	int				pin_count;
 	int				nr_cgroups;	 /* cgroup evts */
 	int				nr_branch_stack; /* branch_stack evt */
+	void				*task_ctx_data; /* pmu specific data */
 	struct rcu_head			rcu_head;
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a6e11fd..89ce4f9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -882,6 +882,16 @@ static void get_ctx(struct perf_event_context *ctx)
 	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
 }
 
+static void free_ctx(struct rcu_head *head)
+{
+	struct perf_event_context *ctx;
+
+	ctx = container_of(head, struct perf_event_context, rcu_head);
+	if (ctx->task_ctx_data)
+		kfree(ctx->task_ctx_data);
+	kfree(ctx);
+}
+
 static void put_ctx(struct perf_event_context *ctx)
 {
 	if (atomic_dec_and_test(&ctx->refcount)) {
@@ -889,7 +899,7 @@ static void put_ctx(struct perf_event_context *ctx)
 			put_ctx(ctx->parent_ctx);
 		if (ctx->task)
 			put_task_struct(ctx->task);
-		kfree_rcu(ctx, rcu_head);
+		call_rcu(&ctx->rcu_head, free_ctx);
 	}
 }
 
@@ -2280,6 +2290,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 			next->perf_event_ctxp[ctxn] = ctx;
 			ctx->task = next;
 			next_ctx->task = task;
+			ctx->task_ctx_data = xchg(&next_ctx->task_ctx_data,
+						  ctx->task_ctx_data);
 			do_switch = 0;
 
 			perf_event_sync_stat(ctx, next_ctx);
@@ -2994,6 +3006,14 @@ alloc_perf_context(struct pmu *pmu, struct task_struct *task)
 	if (!ctx)
 		return NULL;
 
+	if (pmu->task_ctx_size) {
+		ctx->task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+		if (!ctx->task_ctx_data) {
+			kfree(ctx);
+			return NULL;
+		}
+	}
+
 	__perf_event_init_context(ctx);
 	if (task) {
 		ctx->task = task;
-- 
1.8.1.4

[RFC PATCH 5/7] perf, core: Pass perf_sample_data to perf_callchain()

[Yan, Zheng]

From: "Yan, Zheng" <zheng.z.yan@intel.com>

New Intel CPU can record call chains by using existing last branch
record facility. perf_callchain_user() can make use of the call
chains recorded by hardware in case of there is no frame pointer.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/arm/kernel/perf_event.c     | 4 ++--
 arch/powerpc/perf/callchain.c    | 4 ++--
 arch/sparc/kernel/perf_event.c   | 4 ++--
 arch/x86/kernel/cpu/perf_event.c | 4 ++--
 include/linux/perf_event.h       | 3 ++-
 kernel/events/callchain.c        | 8 +++++---
 kernel/events/core.c             | 2 +-
 kernel/events/internal.h         | 3 ++-
 8 files changed, 18 insertions(+), 14 deletions(-)

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index e186ee1..3a6e52c 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -567,8 +567,8 @@ user_backtrace(struct frame_tail __user *tail,
 	return buftail.fp - 1;
 }
 
-void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry *entry,
+			 struct pt_regs *regs, struct perf_sample_data *data)
 {
 	struct frame_tail __user *tail;
 
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 74d1e78..b379ebc 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -482,8 +482,8 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 	}
 }
 
-void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry *entry,
+			 struct pt_regs *regs, struct perf_sample_data *data)
 {
 	if (current_is_64bit())
 		perf_callchain_user_64(entry, regs);
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b5c38fa..cba0306 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1785,8 +1785,8 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry *entry,
+			 struct pt_regs *regs, struct perf_sample_data *data)
 {
 	perf_callchain_store(entry, regs->tpc);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index d29d852..aff0832 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2014,8 +2014,8 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 }
 #endif
 
-void
-perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry *entry,
+			 struct pt_regs *regs, struct perf_sample_data *data)
 {
 	struct stack_frame frame;
 	const void __user *fp;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 23471c2..ca3463c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -679,7 +679,8 @@ extern void perf_event_fork(struct task_struct *tsk);
 /* Callchains */
 DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
 
-extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs);
+extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs,
+				struct perf_sample_data *data);
 extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs);
 
 static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 97b67df..19d497c 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -30,7 +30,8 @@ __weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
 }
 
 __weak void perf_callchain_user(struct perf_callchain_entry *entry,
-				struct pt_regs *regs)
+				struct pt_regs *regs,
+				struct perf_sample_data *data)
 {
 }
 
@@ -157,7 +158,8 @@ put_callchain_entry(int rctx)
 }
 
 struct perf_callchain_entry *
-perf_callchain(struct perf_event *event, struct pt_regs *regs)
+perf_callchain(struct perf_event *event, struct pt_regs *regs,
+	       struct perf_sample_data *data)
 {
 	int rctx;
 	struct perf_callchain_entry *entry;
@@ -198,7 +200,7 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 				goto exit_put;
 
 			perf_callchain_store(entry, PERF_CONTEXT_USER);
-			perf_callchain_user(entry, regs);
+			perf_callchain_user(entry, regs, data);
 		}
 	}
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 89ce4f9..ccd0f54 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4602,7 +4602,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int size = 1;
 
-		data->callchain = perf_callchain(event, regs);
+		data->callchain = perf_callchain(event, regs, data);
 
 		if (data->callchain)
 			size += data->callchain->nr;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index ca65997..0e939e6 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -130,7 +130,8 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
 
 /* Callchain handling */
 extern struct perf_callchain_entry *
-perf_callchain(struct perf_event *event, struct pt_regs *regs);
+perf_callchain(struct perf_event *event, struct pt_regs *regs,
+	       struct perf_sample_data *data);
 extern int get_callchain_buffers(void);
 extern void put_callchain_buffers(void);
 
-- 
1.8.1.4

[RFC PATCH 6/7] perf, x86: Use LBR call stack to get user callchain

[Yan, Zheng]

From: "Yan, Zheng" <zheng.z.yan@intel.com>

Try enabling the LBR call stack feature if event request recording
callchain. Try utilizing the LBR call stack to get user callchain
in case of there is no frame pointer.

This patch also adds a cpu pmu attribute to enable/disable this
feature.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.c           | 128 +++++++++++++++++++++--------
 arch/x86/kernel/cpu/perf_event.h           |   7 ++
 arch/x86/kernel/cpu/perf_event_intel.c     |  20 ++---
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |   3 +
 include/linux/perf_event.h                 |   6 ++
 kernel/events/core.c                       |  11 ++-
 6 files changed, 126 insertions(+), 49 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index aff0832..119e0af 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -399,37 +399,49 @@ 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 && x86_pmu.intel_cap.pebs_format < 2) {
+		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;
+		}
+	} else if ((event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
+		   !has_branch_stack(event) &&
+		   x86_pmu.attr_lbr_callstack &&
+		   !event->attr.exclude_user &&
+		   (event->attach_state & PERF_ATTACH_TASK)) {
 		/*
-		 * check that PEBS LBR correction does not conflict with
-		 * whatever the user is asking with attr->branch_sample_type
+		 * user did not specify branch_sample_type,
+		 * try using the LBR call stack facility to
+		 * record call chains of user program.
 		 */
-		if (event->attr.precise_ip > 1 &&
-		    x86_pmu.intel_cap.pebs_format < 2) {
-			u64 *br_type = &event->attr.branch_sample_type;
-
-			if (has_branch_stack(event)) {
-				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;
-			}
-		}
+		event->attr.branch_sample_type =
+			PERF_SAMPLE_BRANCH_USER |
+			PERF_SAMPLE_BRANCH_CALL_STACK;
 	}
 
 	/*
@@ -1828,10 +1840,34 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
 	return count;
 }
 
+static ssize_t get_attr_lbr_callstack(struct device *cdev,
+				      struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, 40, "%d\n", x86_pmu.attr_lbr_callstack);
+}
+
+static ssize_t set_attr_lbr_callstack(struct device *cdev,
+				      struct device_attribute *attr,
+				      const char *buf, size_t count)
+{
+	unsigned long val = simple_strtoul(buf, NULL, 0);
+
+	if (x86_pmu.attr_lbr_callstack != !!val) {
+		if (val && !x86_pmu_has_lbr_callstack())
+			return -EOPNOTSUPP;
+		x86_pmu.attr_lbr_callstack = !!val;
+	}
+	return count;
+}
+
 static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc);
+static DEVICE_ATTR(lbr_callstack, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH,
+		   get_attr_lbr_callstack, set_attr_lbr_callstack);
+
 
 static struct attribute *x86_pmu_attrs[] = {
 	&dev_attr_rdpmc.attr,
+	&dev_attr_lbr_callstack.attr,
 	NULL,
 };
 
@@ -1970,12 +2006,29 @@ static unsigned long get_segment_base(unsigned int segment)
 	return get_desc_base(desc + idx);
 }
 
+static inline void
+perf_callchain_lbr_callstack(struct perf_callchain_entry *entry,
+			     struct perf_sample_data *data)
+{
+	struct perf_branch_stack *br_stack = data->br_stack;
+
+	if (br_stack && br_stack->user_callstack &&
+	    x86_pmu.attr_lbr_callstack) {
+		int i = 0;
+		while (i < br_stack->nr && entry->nr < PERF_MAX_STACK_DEPTH) {
+			perf_callchain_store(entry, br_stack->entries[i].from);
+			i++;
+		}
+	}
+}
+
 #ifdef CONFIG_COMPAT
 
 #include <asm/compat.h>
 
 static inline int
-perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_user32(struct perf_callchain_entry *entry,
+		      struct pt_regs *regs, struct perf_sample_data *data)
 {
 	/* 32-bit process in 64-bit kernel. */
 	unsigned long ss_base, cs_base;
@@ -2004,11 +2057,16 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		perf_callchain_store(entry, cs_base + frame.return_address);
 		fp = compat_ptr(ss_base + frame.next_frame);
 	}
+
+	if (fp == compat_ptr(regs->bp))
+		perf_callchain_lbr_callstack(entry, data);
+
 	return 1;
 }
 #else
 static inline int
-perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_user32(struct perf_callchain_entry *entry,
+		      struct pt_regs *regs, struct perf_sample_data *data)
 {
     return 0;
 }
@@ -2038,12 +2096,12 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 	if (!current->mm)
 		return;
 
-	if (perf_callchain_user32(regs, entry))
+	if (perf_callchain_user32(entry, regs, data))
 		return;
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		unsigned long bytes;
-		frame.next_frame	     = NULL;
+		frame.next_frame = NULL;
 		frame.return_address = 0;
 
 		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
@@ -2056,6 +2114,10 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 		perf_callchain_store(entry, frame.return_address);
 		fp = frame.next_frame;
 	}
+
+	/* try LBR callstack if there is no frame pointer */
+	if (fp == (void __user *)regs->bp)
+		perf_callchain_lbr_callstack(entry, data);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index b1d2fa9..940f43b 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -401,6 +401,7 @@ struct x86_pmu {
 	 * sysfs attrs
 	 */
 	int		attr_rdpmc;
+	int		attr_lbr_callstack;
 	struct attribute **format_attrs;
 	struct attribute **event_attrs;
 
@@ -504,6 +505,12 @@ static struct perf_pmu_events_attr event_attr_##v = {			\
 
 extern struct x86_pmu x86_pmu __read_mostly;
 
+static inline bool x86_pmu_has_lbr_callstack(void)
+{
+	return  x86_pmu.lbr_sel_map &&
+		x86_pmu.lbr_sel_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] > 0;
+}
+
 DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
 
 int x86_perf_event_set_period(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 92b132e..238c5fc 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1030,15 +1030,10 @@ static __initconst const u64 slm_hw_cache_event_ids
  },
 };
 
-static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
+static inline bool intel_pmu_needs_lbr_callstack(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 &&
-	    x86_pmu.intel_cap.pebs_format < 2)
+	if ((event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
+	    (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK))
 		return true;
 
 	return false;
@@ -1208,7 +1203,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	 * must disable before any actual event
 	 * because any event may be combined with LBR
 	 */
-	if (intel_pmu_needs_lbr_smpl(event))
+	if (needs_branch_stack(event))
 		intel_pmu_lbr_disable(event);
 
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
@@ -1269,7 +1264,7 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	 * must enabled before any actual event
 	 * because any event may be combined with LBR
 	 */
-	if (intel_pmu_needs_lbr_smpl(event))
+	if (needs_branch_stack(event))
 		intel_pmu_lbr_enable(event);
 
 	if (event->attr.exclude_host)
@@ -1412,7 +1407,8 @@ again:
 
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
-		if (has_branch_stack(event))
+		if (has_branch_stack(event) ||
+		    (event->ctx->task && intel_pmu_needs_lbr_callstack(event)))
 			data.br_stack = &cpuc->lbr_stack;
 
 		if (perf_event_overflow(event, &data, regs))
@@ -1741,7 +1737,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
 		x86_pmu.pebs_aliases(event);
 
-	if (intel_pmu_needs_lbr_smpl(event)) {
+	if (needs_branch_stack(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
 		if (ret)
 			return ret;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index a160891..7f42d25 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -702,6 +702,8 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 	int i, j, type;
 	bool compress = false;
 
+	cpuc->lbr_stack.user_callstack = branch_user_callstack(br_sel);
+
 	/* if sampling all branches, then nothing to filter */
 	if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
 		return;
@@ -854,6 +856,7 @@ void intel_pmu_lbr_init_hsw(void)
 
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
+	x86_pmu.attr_lbr_callstack = 1;
 
 	pr_cont("16-deep LBR, ");
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ca3463c..86ebaa5 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -74,6 +74,7 @@ struct perf_raw_record {
  * recent branch.
  */
 struct perf_branch_stack {
+	unsigned			user_callstack:1;
 	__u64				nr;
 	struct perf_branch_entry	entries[0];
 };
@@ -737,6 +738,11 @@ static inline bool has_branch_stack(struct perf_event *event)
 	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
 }
 
+static inline bool needs_branch_stack(struct perf_event *event)
+{
+	return event->attr.branch_sample_type != 0;
+}
+
 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);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ccd0f54..438c29c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1137,7 +1137,7 @@ 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))
+	if (needs_branch_stack(event))
 		ctx->nr_branch_stack++;
 
 	list_add_rcu(&event->event_entry, &ctx->event_list);
@@ -1297,7 +1297,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 			cpuctx->cgrp = NULL;
 	}
 
-	if (has_branch_stack(event))
+	if (needs_branch_stack(event))
 		ctx->nr_branch_stack--;
 
 	ctx->nr_events--;
@@ -3177,7 +3177,7 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_freq_events);
 	if (is_cgroup_event(event))
 		static_key_slow_dec_deferred(&perf_sched_events);
-	if (has_branch_stack(event))
+	if (needs_branch_stack(event))
 		static_key_slow_dec_deferred(&perf_sched_events);
 
 	unaccount_event_cpu(event, event->cpu);
@@ -6566,7 +6566,7 @@ static void account_event(struct perf_event *event)
 		if (atomic_inc_return(&nr_freq_events) == 1)
 			tick_nohz_full_kick_all();
 	}
-	if (has_branch_stack(event))
+	if (needs_branch_stack(event))
 		static_key_slow_inc(&perf_sched_events.key);
 	if (is_cgroup_event(event))
 		static_key_slow_inc(&perf_sched_events.key);
@@ -6673,6 +6673,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
 		goto err_ns;
 
+	if (!has_branch_stack(event))
+		event->attr.branch_sample_type = 0;
+
 	pmu = perf_init_event(event);
 	if (!pmu)
 		goto err_ns;
-- 
1.8.1.4

[RFC PATCH 7/7] perf, x86: Discard zero length call entries in LBR call stack

[Yan, Zheng]

From: "Yan, Zheng" <zheng.z.yan@intel.com>

"Zero length call" uses the attribute of the call instruction to push
the immediate instruction pointer on to the stack and then pops off
that address into a register. This is accomplished without any matching
return instruction. It confuses the hardware and make the recorded call
stack incorrect. Try fixing the call stack by discarding zero length
call entries.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 7f42d25..3f9ab02 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -94,7 +94,8 @@ enum {
 	X86_BR_ABORT		= 1 << 12,/* transaction abort */
 	X86_BR_IN_TX		= 1 << 13,/* in transaction */
 	X86_BR_NO_TX		= 1 << 14,/* not in transaction */
-	X86_BR_CALL_STACK	= 1 << 15,/* call stack */
+	X86_BR_ZERO_CALL	= 1 << 15,/* zero length call */
+	X86_BR_CALL_STACK	= 1 << 16,/* call stack */
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@ -111,13 +112,15 @@ enum {
 	 X86_BR_JMP	 |\
 	 X86_BR_IRQ	 |\
 	 X86_BR_ABORT	 |\
-	 X86_BR_IND_CALL)
+	 X86_BR_IND_CALL |\
+	 X86_BR_ZERO_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_ZERO_CALL	|\
 	 X86_BR_SYSCALL		|\
 	 X86_BR_IRQ		|\
 	 X86_BR_INT)
@@ -636,6 +639,12 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 		ret = X86_BR_INT;
 		break;
 	case 0xe8: /* call near rel */
+		insn_get_immediate(&insn);
+		if (insn.immediate1.value == 0) {
+			/* zero length call */
+			ret = X86_BR_ZERO_CALL;
+			break;
+		}
 	case 0x9a: /* call far absolute */
 		ret = X86_BR_CALL;
 		break;
-- 
1.8.1.4

Re: [RFC PATCH 0/7] perf, x86: Reduce lbr_sel_map size

[Peter Zijlstra]

On Thu, Sep 26, 2013 at 04:28:06PM +0800, Yan, Zheng wrote:
> From: "Yan, Zheng" <zheng.z.yan@intel.com>
> 
> Haswell has a new feature that utilizes the existing Last Branch Record
> facility to record call chains. When the feature is enabled, function
> call will be collected as normal, but as return instructions are executed
> the last captured branch record is popped from the on-chip LBR registers.
> The LBR call stack facility can help perf to get call chains of progam 
> without frame pointer. When perf tool requests PERF_SAMPLE_CALLCHAIN +
> PERF_SAMPLE_BRANCH_USER, this feature is dynamically enabled by default.
> This feature can be disabled/enabled through an attribute file in the cpu
> pmu sysfs directory.
> 
> The main change since previous patch series is:
>  Patch 3 introduces PMU context switch callback, and uses the callback to
>  unify the flush branch stack codeo.
> 
>  Patch 4 uses the context switch callback to save/restore the LBR stack.

>From what I can tell this is the exact same drivel I rejected earlier.

Same shitty changelogs, same shitty code.

Do not waste my time like this.

Re: [RFC PATCH 0/7] perf, x86: Reduce lbr_sel_map size

[Andi Kleen]

> From what I can tell this is the exact same drivel I rejected earlier.

So what do you want changed?

-andi

Re: [RFC PATCH 0/7] perf, x86: Reduce lbr_sel_map size

[Peter Zijlstra]

On Fri, Oct 04, 2013 at 03:35:48PM +0200, Andi Kleen wrote:
> > From what I can tell this is the exact same drivel I rejected earlier.
> 
> So what do you want changed?

Maybe go read what I wrote last time? AFAICT there's nothing different
and the changelogs for sure don't say anything useful.