[PATCH 00/15] perf, x86: Haswell LBR call stack support

[PATCH 00/15] perf, x86: Haswell LBR call stack support

[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. This feature can be disabled/enabled through an
attribute file in the cpu pmu sysfs directory.

The LBR call stack has following known limitations
 - Zero length calls are not filtered out by hardware
 - Exception handing such as setjmp/longjmp will have calls/returns not
   match
 - Pushing different return address onto the stack will have calls/returns
   not match
 - If callstack is deeper than the LBR, only the last entries are captured

Change since previous version
 - split change into more patches
 - introduce context switch callback and use it to flush LBR
 - use the context switch callback to save/restore LBR
 - dynamic allocate memory area for storing LBR stack, always switch the
   memory area during context switch
 - disable this feature by default

[PATCH 01/15] 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.
PERF_SAMPLE_BRANCH_MAX is 1024 at present, so each lbr_sel_map
uses 4096 bytes. If we use bit shift as index, each lbr_sel_map
only uses 40 bytes.

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 fd00bb2..745f6fb 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -459,6 +459,10 @@ 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 d82d155..1ae2ec5 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
@@ -400,14 +396,14 @@ 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;
 
@@ -662,33 +658,33 @@ 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 e1802d6..4d8c438 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -151,20 +151,36 @@ 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

[PATCH 02/15] 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 745f6fb..1213641 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -460,7 +460,10 @@ 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_)						\
@@ -695,6 +698,8 @@ 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 0fa4f24..b477bfc 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2506,7 +2506,7 @@ __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 1ae2ec5..1bb844e 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);
 }
 
@@ -346,7 +356,7 @@ 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;
@@ -380,11 +390,21 @@ 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;
 }
 
 /*
@@ -414,7 +434,7 @@ 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;
 }
@@ -432,7 +452,9 @@ 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
@@ -687,6 +709,19 @@ 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)
 {
@@ -743,6 +778,20 @@ 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

[PATCH 03/15] perf, core: Introduce pmu context switch callback

[Yan, Zheng]

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

The callback is invoked when process is scheduled in/out. To avoid
unnecessary overhead, the callback can be enabled/disabled.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.c |  7 +++++
 arch/x86/kernel/cpu/perf_event.h |  4 +++
 include/linux/perf_event.h       |  8 ++++++
 kernel/events/core.c             | 59 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 78 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8e13293..6703d17 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1846,6 +1846,12 @@ static const struct attribute_group *x86_pmu_attr_groups[] = {
 	NULL,
 };
 
+static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	if (x86_pmu.sched_task)
+		x86_pmu.sched_task(ctx, sched_in);
+}
+
 static void x86_pmu_flush_branch_stack(void)
 {
 	if (x86_pmu.flush_branch_stack)
@@ -1879,6 +1885,7 @@ static struct pmu pmu = {
 
 	.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 1213641..5eb3a58 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -417,6 +417,8 @@ struct x86_pmu {
 
 	void		(*check_microcode)(void);
 	void		(*flush_branch_stack)(void);
+	void		(*sched_task)(struct perf_event_context *ctx,
+				      bool sched_in);
 
 	/*
 	 * Intel Arch Perfmon v2+
@@ -678,6 +680,8 @@ 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/include/linux/perf_event.h b/include/linux/perf_event.h
index 8f4a70f..6a3e603 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -251,6 +251,12 @@ struct pmu {
 	 * flush branch stack on context-switches (needed in cpu-wide mode)
 	 */
 	void (*flush_branch_stack)	(void);
+
+	/*
+	 * PMU callback for context-switches. optional
+	 */
+	void (*sched_task)		(struct perf_event_context *ctx,
+					 bool sched_in);
 };
 
 /**
@@ -546,6 +552,8 @@ 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 403b781..11c63d6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -141,6 +141,7 @@ 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;
@@ -2327,6 +2328,59 @@ unlock:
 	}
 }
 
+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);
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
 #define for_each_task_context_nr(ctxn)					\
 	for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++)
 
@@ -2346,6 +2400,9 @@ 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);
 
@@ -2605,6 +2662,8 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	/* 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)
-- 
1.8.1.4

[PATCH 04/15] perf, x86: Use context switch callback to flush LBR stack

[Yan, Zheng]

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

Enable pmu context switch callback if LBR is used. Use the callback
to flush LBR stack when process is scheduled in.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.c           |  7 ---
 arch/x86/kernel/cpu/perf_event.h           |  2 -
 arch/x86/kernel/cpu/perf_event_intel.c     | 14 +-----
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 32 +++++++++-----
 include/linux/perf_event.h                 |  5 ---
 kernel/events/core.c                       | 71 ------------------------------
 6 files changed, 21 insertions(+), 110 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6703d17..69e2095 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1852,12 +1852,6 @@ static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
 		x86_pmu.sched_task(ctx, sched_in);
 }
 
-static void x86_pmu_flush_branch_stack(void)
-{
-	if (x86_pmu.flush_branch_stack)
-		x86_pmu.flush_branch_stack();
-}
-
 void perf_check_microcode(void)
 {
 	if (x86_pmu.check_microcode)
@@ -1884,7 +1878,6 @@ 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,
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 5eb3a58..3ef4b79 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 +415,6 @@ 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);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index b477bfc..84a1c09 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 1bb844e..c33bf84c 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 6a3e603..96cb88b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -248,11 +248,6 @@ struct pmu {
 	int (*event_idx)		(struct perf_event *event); /*optional */
 
 	/*
-	 * flush branch stack on context-switches (needed in cpu-wide mode)
-	 */
-	void (*flush_branch_stack)	(void);
-
-	/*
 	 * PMU callback for context-switches. optional
 	 */
 	void (*sched_task)		(struct perf_event_context *ctx,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 11c63d6..fc97ed6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -140,7 +140,6 @@ 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;
@@ -2567,65 +2566,6 @@ 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
@@ -2659,9 +2599,6 @@ 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);
 }
@@ -3226,10 +3163,6 @@ 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));
 }
@@ -6642,10 +6575,6 @@ 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

[PATCH 05/15] perf, core: Optimize context switch callback invoking

[Yan, Zheng]

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

So far only CPU pmu uses context switch callback and it is the
first registered pmu. So we can avoid iterating the whole pmu list.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 kernel/events/core.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index fc97ed6..c281265 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2373,6 +2373,10 @@ static void perf_pmu_sched_task(struct task_struct *prev,
 		perf_pmu_enable(pmu);
 
 		perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+
+		/* so far only CPU pmu uses context switch callback */
+		if (++count >= __get_cpu_var(perf_sched_cb_usages))
+			break;
 	}
 
 	rcu_read_unlock();
@@ -6492,7 +6496,7 @@ 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);
-- 
1.8.1.4

[PATCH 06/15] perf, core: PMU specific data for perf task context

[Yan, Zheng]

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

allow allocating PMU specific data for perf task context

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 include/linux/perf_event.h |  5 +++++
 kernel/events/core.c       | 19 ++++++++++++++++++-
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 96cb88b..147f9d3 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);
+	/*
+	 * PMU specific data size
+	 */
+	size_t				task_ctx_size;
 };
 
 /**
@@ -496,6 +500,7 @@ 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 c281265..6499dae 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -882,6 +882,15 @@ 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);
+	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 +898,7 @@ 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);
 	}
 }
 
@@ -3025,6 +3034,14 @@ alloc_perf_context(struct pmu *pmu, struct task_struct *task)
 	if (!ctx)
 		return NULL;
 
+	if (task && pmu->task_ctx_size > 0) {
+		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

[PATCH 07/15] perf, core: Always swtich pmu specific data during context switch

[Yan, Zheng]

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

Swtich pmu specific data even if switching perf task conext is
optimized out.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 kernel/events/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6499dae..974f7c7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2318,6 +2318,8 @@ 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);
-- 
1.8.1.4

[PATCH 08/15] perf, x86: Allocate memory for saving LBR stack

[Yan, Zheng]

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

Allocate memory for perf task context, use the memory to save
LBR stack.

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 | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 69e2095..2e43f1b 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 3ef4b79..3ed9629 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -459,6 +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;
+	int lbr_stack_state;
+};
+
 enum {
 	PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = PERF_SAMPLE_BRANCH_MAX_SHIFT,
 	PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE,
-- 
1.8.1.4

[PATCH 09/15] perf: Track system-wide LBR users and LBR callstack users

[Yan, Zheng]

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

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.h           |  1 +
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 25 ++++++++++++++++++++++++-
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 3ed9629..bcc8e1f 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;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index c33bf84c..f57960d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -201,15 +201,29 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 		intel_pmu_lbr_reset();
 }
 
+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);
@@ -217,11 +231,20 @@ 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);
 
-- 
1.8.1.4

[PATCH 10/15] 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.

Don't save/restore the LBR stack if task has no perf event context
or there are system-wide users of LBR stack. Flush the LBR stack
instead.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 83 +++++++++++++++++++++++++-----
 1 file changed, 69 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index f57960d..80bb097 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -187,18 +187,85 @@ 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;
+}
+
+enum {
+	LBR_UNINIT,
+	LBR_NONE,
+	LBR_VALID,
+};
+
+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_state = LBR_NONE;
+}
+
+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_state = LBR_VALID;
+}
+
+
 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_callstack_users ||
+		    task_ctx->lbr_stack_state != LBR_VALID)
+			intel_pmu_lbr_reset();
+		else
+			__intel_pmu_lbr_restore(task_ctx);
+	} else if (task_ctx) {
+		if (task_ctx->lbr_callstack_users &&
+		    task_ctx->lbr_stack_state != LBR_UNINIT)
+			__intel_pmu_lbr_save(task_ctx);
+		else
+			task_ctx->lbr_stack_state = LBR_NONE;
+	}
 }
 
 static inline bool branch_user_callstack(unsigned br_sel)
@@ -271,18 +338,6 @@ 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;
-- 
1.8.1.4

[PATCH 11/15] perf, core: Simplify need branch stack check

[Yan, Zheng]

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

use event->attr.branch_sample_type to check if branch stack is needed.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 20 +++-----------------
 include/linux/perf_event.h             |  5 +++++
 kernel/events/core.c                   | 11 +++++++----
 3 files changed, 15 insertions(+), 21 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 84a1c09..722171c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1030,20 +1030,6 @@ static __initconst const u64 slm_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 &&
-	    x86_pmu.intel_cap.pebs_format < 2)
-		return true;
-
-	return false;
-}
-
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -1208,7 +1194,7 @@ 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 +1255,7 @@ 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)
@@ -1741,7 +1727,7 @@ 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/include/linux/perf_event.h b/include/linux/perf_event.h
index 147f9d3..0d88eb8 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -766,6 +766,11 @@ 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 974f7c7..e039dbc 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);
@@ -1302,7 +1302,7 @@ 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--;
@@ -3207,7 +3207,7 @@ 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);
@@ -6619,7 +6619,7 @@ 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);
@@ -6727,6 +6727,9 @@ 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

[PATCH 12/15] 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 bc3f2ef..fdcc654 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -566,8 +566,8 @@ 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 2e43f1b..49128e6 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2009,8 +2009,8 @@ 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 0d88eb8..c442276 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -709,7 +709,8 @@ 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 e039dbc..127b882 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4656,7 +4656,7 @@ 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 569b2187..cd18b64 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -147,7 +147,8 @@ 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

[PATCH 13/15] perf, x86: Use LBR call stack to get user callchain

[Yan, Zheng]

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

Try utilizing the LBR call stack to get user callchain in case of
there is no frame pointer

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.c           | 33 ++++++++++++++++++++++++++----
 arch/x86/kernel/cpu/perf_event_intel.c     | 12 ++++++++++-
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |  2 ++
 include/linux/perf_event.h                 |  1 +
 4 files changed, 43 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 49128e6..1509340 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1965,12 +1965,28 @@ 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) {
+		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;
@@ -1999,11 +2015,16 @@ 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;
 }
@@ -2033,12 +2054,12 @@ 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));
@@ -2051,6 +2072,10 @@ 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_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 722171c..e0f658a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1030,6 +1030,15 @@ static __initconst const u64 slm_hw_cache_event_ids
  },
 };
 
+static inline bool intel_pmu_needs_lbr_callstack(struct perf_event *event)
+{
+	if ((event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
+	    (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK))
+		return true;
+
+	return false;
+}
+
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -1398,7 +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))
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 80bb097..a879910 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -722,6 +722,8 @@ 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;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c442276..d2f0488 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 {
+	bool				user_callstack;
 	__u64				nr;
 	struct perf_branch_entry	entries[0];
 };
-- 
1.8.1.4

[PATCH 14/15] perf, x86: Enable LBR callstack when recording callchain

[Yan, Zheng]

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

Try enabling the LBR call stack feature if event requests recording
callchain. Also adds a cpu pmu attribute to enable/disable this
feature (disabled by default).

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.c | 94 +++++++++++++++++++++++++++-------------
 arch/x86/kernel/cpu/perf_event.h |  7 +++
 2 files changed, 72 insertions(+), 29 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 1509340..7fbb751 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,
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index bcc8e1f..f07cc04 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;
 
@@ -505,6 +506,12 @@ 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);
-- 
1.8.1.4

[PATCH 15/15] 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 a879910..56ff99d 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)
@@ -656,6 +659,12 @@ 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: [PATCH 04/15] perf, x86: Use context switch callback to flush LBR stack

[Ingo Molnar]

* Yan, Zheng <zheng.z.yan@intel.com> wrote:

> From: "Yan, Zheng" <zheng.z.yan@intel.com>
> 
> Enable pmu context switch callback if LBR is used. Use the callback
> to flush LBR stack when process is scheduled in.
> 
> Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

I see several fundamental problems with your series:

1)

Minimal changelogs like the ones in this series are completely 
unacceptable! You seem to be copying the changelog style of Andi 
Kleen: written to inform as little as possible.

Don't do that if you want your patches to get anywhere, instead adapt 
the akpm style:

 "Please update the changelog to describe the current behavior.

  Please also describe why you think that behavior should be changed.
  ie: what's the reason for this patch.
 "

2)

Also, there are frequent typos.

3)

Plus you didn't Cc: other perf maintainers like myself or Arnaldo.

4)

How can users actually make use of the changes you are doing? Cite 
actual perf analysis usecases in the 0/15 description and describe how 
your patches improve/enable all that.

Please fix all those problems and resend.

Thanks,

	Ingo