From bce38cd53e5ddba9cb6d708c4ef3d04a4016ec7e Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:20:51 +0100
Subject: perf: Add generic taken branch sampling support

This patch adds the ability to sample taken branches to the
perf_event interface.

The ability to capture taken branches is very useful for all
sorts of analysis. For instance, basic block profiling, call
counts, statistical call graph.

This new capability requires hardware assist and as such may
not be available on all HW platforms. On Intel x86 it is
implemented on top of the Last Branch Record (LBR) facility.

To enable taken branches sampling, the PERF_SAMPLE_BRANCH_STACK
bit must be set in attr->sample_type.

Sampled taken branches may be filtered by type and/or priv
levels.

The patch adds a new field, called branch_sample_type, to the
perf_event_attr structure. It contains a bitmask of filters
to apply to the sampled taken branches.

Filters may be implemented in HW. If the HW filter does not exist
or is not good enough, some arch may also implement a SW filter.

The following generic filters are currently defined:
- PERF_SAMPLE_USER
  only branches whose targets are at the user level

- PERF_SAMPLE_KERNEL
  only branches whose targets are at the kernel level

- PERF_SAMPLE_HV
  only branches whose targets are at the hypervisor level

- PERF_SAMPLE_ANY
  any type of branches (subject to priv levels filters)

- PERF_SAMPLE_ANY_CALL
  any call branches (may incl. syscall on some arch)

- PERF_SAMPLE_ANY_RET
  any return branches (may incl. syscall returns on some arch)

- PERF_SAMPLE_IND_CALL
  indirect call branches

Obviously filter may be combined. The priv level bits are optional.
If not provided, the priv level of the associated event are used. It
is possible to collect branches at a priv level different from the
associated event. Use of kernel, hv priv levels is subject to permissions
and availability (hv).

The number of taken branch records present in each sample may vary based
on HW, the type of sampled branches, the executed code. Therefore
each sample contains the number of taken branches it contains.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-2-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 47a7e63bfe5..309d0cc6916 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -142,9 +142,11 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
 
-		cpuc->lbr_entries[i].from  = msr_lastbranch.from;
-		cpuc->lbr_entries[i].to    = msr_lastbranch.to;
-		cpuc->lbr_entries[i].flags = 0;
+		cpuc->lbr_entries[i].from	= msr_lastbranch.from;
+		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
+		cpuc->lbr_entries[i].mispred	= 0;
+		cpuc->lbr_entries[i].predicted	= 0;
+		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
 }
@@ -165,19 +167,22 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		unsigned long lbr_idx = (tos - i) & mask;
-		u64 from, to, flags = 0;
+		u64 from, to, mis = 0, pred = 0;
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
 		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
 		if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
-			flags = !!(from & LBR_FROM_FLAG_MISPRED);
+			mis = !!(from & LBR_FROM_FLAG_MISPRED);
+			pred = !mis;
 			from = (u64)((((s64)from) << 1) >> 1);
 		}
 
-		cpuc->lbr_entries[i].from  = from;
-		cpuc->lbr_entries[i].to    = to;
-		cpuc->lbr_entries[i].flags = flags;
+		cpuc->lbr_entries[i].from	= from;
+		cpuc->lbr_entries[i].to		= to;
+		cpuc->lbr_entries[i].mispred	= mis;
+		cpuc->lbr_entries[i].predicted	= pred;
+		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
 }
-- 
cgit v1.2.3


From 225ce53910edc3c2322b1e4f2ed049a9196cd0b3 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:20:52 +0100
Subject: perf/x86: Add Intel LBR MSR definitions

This patch adds the LBR definitions for NHM/WSM/SNB and Core.
It also adds the definitions for the architected LBR MSR:
LBR_SELECT, LBRT_TOS.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-3-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/msr-index.h           |  7 +++++++
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 18 +++++++++---------
 2 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a6962d9161a..ccb805966f6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -56,6 +56,13 @@
 #define MSR_OFFCORE_RSP_0		0x000001a6
 #define MSR_OFFCORE_RSP_1		0x000001a7
 
+#define MSR_LBR_SELECT			0x000001c8
+#define MSR_LBR_TOS			0x000001c9
+#define MSR_LBR_NHM_FROM		0x00000680
+#define MSR_LBR_NHM_TO			0x000006c0
+#define MSR_LBR_CORE_FROM		0x00000040
+#define MSR_LBR_CORE_TO			0x00000060
+
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 309d0cc6916..6710a5116eb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -203,23 +203,23 @@ void intel_pmu_lbr_read(void)
 void intel_pmu_lbr_init_core(void)
 {
 	x86_pmu.lbr_nr     = 4;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x40;
-	x86_pmu.lbr_to     = 0x60;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
 }
 
 void intel_pmu_lbr_init_nhm(void)
 {
 	x86_pmu.lbr_nr     = 16;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x680;
-	x86_pmu.lbr_to     = 0x6c0;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_NHM_TO;
 }
 
 void intel_pmu_lbr_init_atom(void)
 {
 	x86_pmu.lbr_nr	   = 8;
-	x86_pmu.lbr_tos    = 0x01c9;
-	x86_pmu.lbr_from   = 0x40;
-	x86_pmu.lbr_to     = 0x60;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
 }
-- 
cgit v1.2.3


From b36817e8863090f1f24e538106ca50fa1d9e4003 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:20:53 +0100
Subject: perf/x86: Add Intel LBR sharing logic

The Intel LBR on some recent processor is capable
of filtering branches by type. The filter is configurable
via the LBR_SELECT MSR register.

There are limitation on how this register can be used.

On Nehalem/Westmere, the LBR_SELECT is shared by the two HT threads
when HT is on. It is private to each core when HT is off.

On SandyBridge, the LBR_SELECT register is private to each thread
when HT is on. It is private to each core when HT is off.

The kernel must manage the sharing of LBR_SELECT. It allows
multiple users on the same logical CPU to use LBR_SELECT as
long as they program it with the same value. Across sibling
CPUs (HT threads), the same restriction applies on NHM/WSM.

This patch implements this sharing logic by leveraging the
mechanism put in place for managing the offcore_response
shared MSR.

We modify __intel_shared_reg_get_constraints() to cause
x86_get_event_constraint() to be called because LBR may
be associated with events that may be counter constrained.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-4-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/perf_event.c       |  4 ++
 arch/x86/kernel/cpu/perf_event.h       |  4 ++
 arch/x86/kernel/cpu/perf_event_intel.c | 70 +++++++++++++++++++++-------------
 3 files changed, 52 insertions(+), 26 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index f8bddb5b060..377931354ac 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -426,6 +426,10 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	/* mark unused */
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
 
+	/* mark not used */
+	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
+
 	return x86_pmu.hw_config(event);
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 82db83b5c3b..9b9c580a7ab 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -33,6 +33,7 @@ enum extra_reg_type {
 
 	EXTRA_REG_RSP_0 = 0,	/* offcore_response_0 */
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
+	EXTRA_REG_LBR   = 2,	/* lbr_select */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
@@ -130,6 +131,7 @@ struct cpu_hw_events {
 	void				*lbr_context;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
+	struct er_account		*lbr_sel;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -342,6 +344,8 @@ struct x86_pmu {
 	 */
 	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
 	int		lbr_nr;			   /* hardware stack size */
+	u64		lbr_sel_mask;		   /* LBR_SELECT valid bits */
+	const int	*lbr_sel_map;		   /* lbr_select mappings */
 
 	/*
 	 * Extra registers for events
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3bd37bdf1b8..97f7bb58751 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1123,17 +1123,17 @@ static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
  */
 static struct event_constraint *
 __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
-				   struct perf_event *event)
+				   struct perf_event *event,
+				   struct hw_perf_event_extra *reg)
 {
 	struct event_constraint *c = &emptyconstraint;
-	struct hw_perf_event_extra *reg = &event->hw.extra_reg;
 	struct er_account *era;
 	unsigned long flags;
 	int orig_idx = reg->idx;
 
 	/* already allocated shared msr */
 	if (reg->alloc)
-		return &unconstrained;
+		return NULL; /* call x86_get_event_constraint() */
 
 again:
 	era = &cpuc->shared_regs->regs[reg->idx];
@@ -1156,14 +1156,10 @@ again:
 		reg->alloc = 1;
 
 		/*
-		 * All events using extra_reg are unconstrained.
-		 * Avoids calling x86_get_event_constraints()
-		 *
-		 * Must revisit if extra_reg controlling events
-		 * ever have constraints. Worst case we go through
-		 * the regular event constraint table.
+		 * need to call x86_get_event_constraint()
+		 * to check if associated event has constraints
 		 */
-		c = &unconstrained;
+		c = NULL;
 	} else if (intel_try_alt_er(event, orig_idx)) {
 		raw_spin_unlock_irqrestore(&era->lock, flags);
 		goto again;
@@ -1200,11 +1196,23 @@ static struct event_constraint *
 intel_shared_regs_constraints(struct cpu_hw_events *cpuc,
 			      struct perf_event *event)
 {
-	struct event_constraint *c = NULL;
-
-	if (event->hw.extra_reg.idx != EXTRA_REG_NONE)
-		c = __intel_shared_reg_get_constraints(cpuc, event);
-
+	struct event_constraint *c = NULL, *d;
+	struct hw_perf_event_extra *xreg, *breg;
+
+	xreg = &event->hw.extra_reg;
+	if (xreg->idx != EXTRA_REG_NONE) {
+		c = __intel_shared_reg_get_constraints(cpuc, event, xreg);
+		if (c == &emptyconstraint)
+			return c;
+	}
+	breg = &event->hw.branch_reg;
+	if (breg->idx != EXTRA_REG_NONE) {
+		d = __intel_shared_reg_get_constraints(cpuc, event, breg);
+		if (d == &emptyconstraint) {
+			__intel_shared_reg_put_constraints(cpuc, xreg);
+			c = d;
+		}
+	}
 	return c;
 }
 
@@ -1252,6 +1260,10 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
 	reg = &event->hw.extra_reg;
 	if (reg->idx != EXTRA_REG_NONE)
 		__intel_shared_reg_put_constraints(cpuc, reg);
+
+	reg = &event->hw.branch_reg;
+	if (reg->idx != EXTRA_REG_NONE)
+		__intel_shared_reg_put_constraints(cpuc, reg);
 }
 
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
@@ -1431,7 +1443,7 @@ static int intel_pmu_cpu_prepare(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 
-	if (!x86_pmu.extra_regs)
+	if (!(x86_pmu.extra_regs || x86_pmu.lbr_sel_map))
 		return NOTIFY_OK;
 
 	cpuc->shared_regs = allocate_shared_regs(cpu);
@@ -1453,22 +1465,28 @@ static void intel_pmu_cpu_starting(int cpu)
 	 */
 	intel_pmu_lbr_reset();
 
-	if (!cpuc->shared_regs || (x86_pmu.er_flags & ERF_NO_HT_SHARING))
+	cpuc->lbr_sel = NULL;
+
+	if (!cpuc->shared_regs)
 		return;
 
-	for_each_cpu(i, topology_thread_cpumask(cpu)) {
-		struct intel_shared_regs *pc;
+	if (!(x86_pmu.er_flags & ERF_NO_HT_SHARING)) {
+		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+			struct intel_shared_regs *pc;
 
-		pc = per_cpu(cpu_hw_events, i).shared_regs;
-		if (pc && pc->core_id == core_id) {
-			cpuc->kfree_on_online = cpuc->shared_regs;
-			cpuc->shared_regs = pc;
-			break;
+			pc = per_cpu(cpu_hw_events, i).shared_regs;
+			if (pc && pc->core_id == core_id) {
+				cpuc->kfree_on_online = cpuc->shared_regs;
+				cpuc->shared_regs = pc;
+				break;
+			}
 		}
+		cpuc->shared_regs->core_id = core_id;
+		cpuc->shared_regs->refcnt++;
 	}
 
-	cpuc->shared_regs->core_id = core_id;
-	cpuc->shared_regs->refcnt++;
+	if (x86_pmu.lbr_sel_map)
+		cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
 }
 
 static void intel_pmu_cpu_dying(int cpu)
-- 
cgit v1.2.3


From ff3fb511ba377e8a0a7f553cc352237f70d08121 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:20:54 +0100
Subject: perf/x86: Sync branch stack sampling with precise_sampling

If precise sampling is enabled on Intel x86 then perf_event uses PEBS.
To correct for the off-by-one error of PEBS, perf_event uses LBR when
precise_sample > 1.

On Intel x86 PERF_SAMPLE_BRANCH_STACK is implemented using LBR,
therefore both features must be coordinated as they may not
configure LBR the same way.

For PEBS, LBR needs to capture all branches at the priv level of
the associated event.

This patch checks that the branch type and priv level of BRANCH_STACK
is compatible with that of the PEBS LBR requirement, thereby allowing:

   $ perf record -b any,u -e instructions:upp ....

But:

   $ perf record -b any_call,u -e instructions:upp

Is not possible.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-5-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/perf_event.c | 60 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 377931354ac..cea56748327 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -353,6 +353,36 @@ int x86_setup_perfctr(struct perf_event *event)
 	return 0;
 }
 
+/*
+ * check that branch_sample_type is compatible with
+ * settings needed for precise_ip > 1 which implies
+ * using the LBR to capture ALL taken branches at the
+ * priv levels of the measurement
+ */
+static inline int precise_br_compat(struct perf_event *event)
+{
+	u64 m = event->attr.branch_sample_type;
+	u64 b = 0;
+
+	/* must capture all branches */
+	if (!(m & PERF_SAMPLE_BRANCH_ANY))
+		return 0;
+
+	m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_user)
+		b |= PERF_SAMPLE_BRANCH_USER;
+
+	if (!event->attr.exclude_kernel)
+		b |= PERF_SAMPLE_BRANCH_KERNEL;
+
+	/*
+	 * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86
+	 */
+
+	return m == b;
+}
+
 int x86_pmu_hw_config(struct perf_event *event)
 {
 	if (event->attr.precise_ip) {
@@ -369,6 +399,36 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+		/*
+		 * check that PEBS LBR correction does not conflict with
+		 * whatever the user is asking with attr->branch_sample_type
+		 */
+		if (event->attr.precise_ip > 1) {
+			u64 *br_type = &event->attr.branch_sample_type;
+
+			if (has_branch_stack(event)) {
+				if (!precise_br_compat(event))
+					return -EOPNOTSUPP;
+
+				/* branch_sample_type is compatible */
+
+			} else {
+				/*
+				 * user did not specify  branch_sample_type
+				 *
+				 * For PEBS fixups, we capture all
+				 * the branches at the priv level of the
+				 * event.
+				 */
+				*br_type = PERF_SAMPLE_BRANCH_ANY;
+
+				if (!event->attr.exclude_user)
+					*br_type |= PERF_SAMPLE_BRANCH_USER;
+
+				if (!event->attr.exclude_kernel)
+					*br_type |= PERF_SAMPLE_BRANCH_KERNEL;
+			}
+		}
 	}
 
 	/*
-- 
cgit v1.2.3


From c5cc2cd906ea9fe73e3c93f9ad824996faa278cc Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:20:55 +0100
Subject: perf/x86: Add Intel LBR mappings for PERF_SAMPLE_BRANCH filters

This patch adds the mappings from the generic PERF_SAMPLE_BRANCH_*
filters to the actual Intel x86LBR filters, whenever they exist.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-6-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/perf_event.h           |   2 +
 arch/x86/kernel/cpu/perf_event_intel.c     |   2 +-
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 103 ++++++++++++++++++++++++++++-
 3 files changed, 104 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 9b9c580a7ab..4e948976aef 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -539,6 +539,8 @@ void intel_pmu_lbr_init_nhm(void);
 
 void intel_pmu_lbr_init_atom(void);
 
+void intel_pmu_lbr_init_snb(void);
+
 int p4_pmu_init(void);
 
 int p6_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 97f7bb58751..b0db0169244 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1757,7 +1757,7 @@ __init int intel_pmu_init(void)
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
-		intel_pmu_lbr_init_nhm();
+		intel_pmu_lbr_init_snb();
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 6710a5116eb..e54a063b286 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -13,6 +13,49 @@ enum {
 	LBR_FORMAT_EIP_FLAGS	= 0x03,
 };
 
+/*
+ * Intel LBR_SELECT bits
+ * Intel Vol3a, April 2011, Section 16.7 Table 16-10
+ *
+ * Hardware branch filter (not available on all CPUs)
+ */
+#define LBR_KERNEL_BIT		0 /* do not capture at ring0 */
+#define LBR_USER_BIT		1 /* do not capture at ring > 0 */
+#define LBR_JCC_BIT		2 /* do not capture conditional branches */
+#define LBR_REL_CALL_BIT	3 /* do not capture relative calls */
+#define LBR_IND_CALL_BIT	4 /* do not capture indirect calls */
+#define LBR_RETURN_BIT		5 /* do not capture near returns */
+#define LBR_IND_JMP_BIT		6 /* do not capture indirect jumps */
+#define LBR_REL_JMP_BIT		7 /* do not capture relative jumps */
+#define LBR_FAR_BIT		8 /* do not capture far branches */
+
+#define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
+#define LBR_USER	(1 << LBR_USER_BIT)
+#define LBR_JCC		(1 << LBR_JCC_BIT)
+#define LBR_REL_CALL	(1 << LBR_REL_CALL_BIT)
+#define LBR_IND_CALL	(1 << LBR_IND_CALL_BIT)
+#define LBR_RETURN	(1 << LBR_RETURN_BIT)
+#define LBR_REL_JMP	(1 << LBR_REL_JMP_BIT)
+#define LBR_IND_JMP	(1 << LBR_IND_JMP_BIT)
+#define LBR_FAR		(1 << LBR_FAR_BIT)
+
+#define LBR_PLM (LBR_KERNEL | LBR_USER)
+
+#define LBR_SEL_MASK	0x1ff	/* valid bits in LBR_SELECT */
+#define LBR_NOT_SUPP	-1	/* LBR filter not supported */
+#define LBR_IGN		0	/* ignored */
+
+#define LBR_ANY		 \
+	(LBR_JCC	|\
+	 LBR_REL_CALL	|\
+	 LBR_IND_CALL	|\
+	 LBR_RETURN	|\
+	 LBR_REL_JMP	|\
+	 LBR_IND_JMP	|\
+	 LBR_FAR)
+
+#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
+
 /*
  * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
  * otherwise it becomes near impossible to get a reliable stack.
@@ -151,8 +194,6 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 	cpuc->lbr_stack.nr = i;
 }
 
-#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
-
 /*
  * Due to lack of segmentation in Linux the effective address (offset)
  * is the same as the linear address, allowing us to merge the LIP and EIP
@@ -200,26 +241,84 @@ void intel_pmu_lbr_read(void)
 		intel_pmu_lbr_read_64(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,
+	/*
+	 * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
+	 */
+	[PERF_SAMPLE_BRANCH_ANY_CALL] =
+	 LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
+	/*
+	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
+	 */
+	[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
+};
+
+static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
+	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL]	= LBR_REL_CALL | LBR_IND_CALL
+					| LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL]	= LBR_IND_CALL,
+};
+
+/* core */
 void intel_pmu_lbr_init_core(void)
 {
 	x86_pmu.lbr_nr     = 4;
 	x86_pmu.lbr_tos    = MSR_LBR_TOS;
 	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
 	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	pr_cont("4-deep LBR, ");
 }
 
+/* nehalem/westmere */
 void intel_pmu_lbr_init_nhm(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  = nhm_lbr_sel_map;
+
+	pr_cont("16-deep LBR, ");
 }
 
+/* sandy bridge */
+void intel_pmu_lbr_init_snb(void)
+{
+	x86_pmu.lbr_nr	 = 16;
+	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
+	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+	pr_cont("16-deep LBR, ");
+}
+
+/* atom */
 void intel_pmu_lbr_init_atom(void)
 {
 	x86_pmu.lbr_nr	   = 8;
 	x86_pmu.lbr_tos    = MSR_LBR_TOS;
 	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
 	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	pr_cont("8-deep LBR, ");
 }
-- 
cgit v1.2.3


From 88c9a65e13f393fd60d8b9e9c659a34f9e39967d Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:20:56 +0100
Subject: perf/x86: Disable LBR support for older Intel Atom processors

The patch adds a restriction for Intel Atom LBR support. Only
steppings 10 (PineView) and more recent are supported. Older models
do not have a functional LBR. Their LBR does not freeze on PMU
interrupt which makes LBR unusable in the context of perf_events.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-7-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index e54a063b286..07f0ff88e44 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -315,6 +315,16 @@ void intel_pmu_lbr_init_snb(void)
 /* atom */
 void intel_pmu_lbr_init_atom(void)
 {
+	/*
+	 * only models starting at stepping 10 seems
+	 * to have an operational LBR which can freeze
+	 * on PMU interrupt
+	 */
+	if (boot_cpu_data.x86_mask < 10) {
+		pr_cont("LBR disabled due to erratum");
+		return;
+	}
+
 	x86_pmu.lbr_nr	   = 8;
 	x86_pmu.lbr_tos    = MSR_LBR_TOS;
 	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
-- 
cgit v1.2.3


From 60ce0fbd072695866cb27b729690ab59dce705a5 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:20:57 +0100
Subject: perf/x86: Implement PERF_SAMPLE_BRANCH for Intel CPUs

This patch implements PERF_SAMPLE_BRANCH support for Intel
x86processors. It connects PERF_SAMPLE_BRANCH to the actual LBR.

The patch adds the hooks in the PMU irq handler to save the LBR
on counter overflow for both regular and PEBS modes.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-8-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/perf_event.h           |  2 +
 arch/x86/kernel/cpu/perf_event_intel.c     | 35 ++++++++++++
 arch/x86/kernel/cpu/perf_event_intel_ds.c  | 10 ++--
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 86 +++++++++++++++++++++++++++++-
 4 files changed, 125 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 4e948976aef..ef7419cbd13 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -541,6 +541,8 @@ void intel_pmu_lbr_init_atom(void);
 
 void intel_pmu_lbr_init_snb(void);
 
+int intel_pmu_setup_lbr_filter(struct perf_event *event);
+
 int p4_pmu_init(void);
 
 int p6_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index b0db0169244..7cc1e2dcc4d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -727,6 +727,19 @@ static __initconst const u64 atom_hw_cache_event_ids
  },
 };
 
+static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
+{
+	/* user explicitly requested branch sampling */
+	if (has_branch_stack(event))
+		return true;
+
+	/* implicit branch sampling to correct PEBS skid */
+	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
+		return true;
+
+	return false;
+}
+
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -881,6 +894,13 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 
+	/*
+	 * must disable before any actual event
+	 * because any event may be combined with LBR
+	 */
+	if (intel_pmu_needs_lbr_smpl(event))
+		intel_pmu_lbr_disable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
@@ -935,6 +955,12 @@ static void intel_pmu_enable_event(struct perf_event *event)
 		intel_pmu_enable_bts(hwc->config);
 		return;
 	}
+	/*
+	 * must enabled before any actual event
+	 * because any event may be combined with LBR
+	 */
+	if (intel_pmu_needs_lbr_smpl(event))
+		intel_pmu_lbr_enable(event);
 
 	if (event->attr.exclude_host)
 		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
@@ -1057,6 +1083,9 @@ again:
 
 		data.period = event->hw.last_period;
 
+		if (has_branch_stack(event))
+			data.br_stack = &cpuc->lbr_stack;
+
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
@@ -1305,6 +1334,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		event->hw.config = alt_config;
 	}
 
+	if (intel_pmu_needs_lbr_smpl(event)) {
+		ret = intel_pmu_setup_lbr_filter(event);
+		if (ret)
+			return ret;
+	}
+
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index d6bd49faa40..ee7e3c8d9d6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -439,9 +439,6 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
-
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
-		intel_pmu_lbr_enable(event);
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -454,9 +451,6 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
 	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
-
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
-		intel_pmu_lbr_disable(event);
 }
 
 void intel_pmu_pebs_enable_all(void)
@@ -572,6 +566,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * both formats and we don't use the other fields in this
 	 * routine.
 	 */
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct pebs_record_core *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
@@ -602,6 +597,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	else
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
+	if (has_branch_stack(event))
+		data.br_stack = &cpuc->lbr_stack;
+
 	if (perf_event_overflow(event, &data, &regs))
 		x86_pmu_stop(event, 0);
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 07f0ff88e44..d0fb864ff2b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -56,6 +56,10 @@ enum {
 
 #define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
 
+#define for_each_branch_sample_type(x) \
+	for ((x) = PERF_SAMPLE_BRANCH_USER; \
+	     (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
+
 /*
  * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
  * otherwise it becomes near impossible to get a reliable stack.
@@ -64,6 +68,10 @@ enum {
 static void __intel_pmu_lbr_enable(void)
 {
 	u64 debugctl;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (cpuc->lbr_sel)
+		wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 	debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
@@ -119,7 +127,6 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 	 * Reset the LBR stack if we changed task context to
 	 * avoid data leaks.
 	 */
-
 	if (event->ctx->task && cpuc->lbr_context != event->ctx) {
 		intel_pmu_lbr_reset();
 		cpuc->lbr_context = event->ctx;
@@ -138,8 +145,11 @@ void intel_pmu_lbr_disable(struct perf_event *event)
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 
-	if (cpuc->enabled && !cpuc->lbr_users)
+	if (cpuc->enabled && !cpuc->lbr_users) {
 		__intel_pmu_lbr_disable();
+		/* avoid stale pointer */
+		cpuc->lbr_context = NULL;
+	}
 }
 
 void intel_pmu_lbr_enable_all(void)
@@ -158,6 +168,9 @@ void intel_pmu_lbr_disable_all(void)
 		__intel_pmu_lbr_disable();
 }
 
+/*
+ * TOS = most recently recorded branch
+ */
 static inline u64 intel_pmu_lbr_tos(void)
 {
 	u64 tos;
@@ -241,6 +254,75 @@ void intel_pmu_lbr_read(void)
 		intel_pmu_lbr_read_64(cpuc);
 }
 
+/*
+ * setup the HW LBR filter
+ * Used only when available, may not be enough to disambiguate
+ * all branches, may need the help of the SW filter
+ */
+static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg;
+	u64 br_type = event->attr.branch_sample_type;
+	u64 mask = 0, m;
+	u64 v;
+
+	for_each_branch_sample_type(m) {
+		if (!(br_type & m))
+			continue;
+
+		v = x86_pmu.lbr_sel_map[m];
+		if (v == LBR_NOT_SUPP)
+			return -EOPNOTSUPP;
+		mask |= v;
+
+		if (m == PERF_SAMPLE_BRANCH_ANY)
+			break;
+	}
+	reg = &event->hw.branch_reg;
+	reg->idx = EXTRA_REG_LBR;
+
+	/* LBR_SELECT operates in suppress mode so invert mask */
+	reg->config = ~mask & x86_pmu.lbr_sel_mask;
+
+	return 0;
+}
+
+/*
+ * all the bits supported on some flavor of x86LBR
+ * we ignore BRANCH_HV because it is not supported
+ */
+#define PERF_SAMPLE_BRANCH_X86_ALL	\
+	(PERF_SAMPLE_BRANCH_ANY		|\
+	 PERF_SAMPLE_BRANCH_USER	|\
+	 PERF_SAMPLE_BRANCH_KERNEL)
+
+int intel_pmu_setup_lbr_filter(struct perf_event *event)
+{
+	u64 br_type = event->attr.branch_sample_type;
+
+	/*
+	 * no LBR on this PMU
+	 */
+	if (!x86_pmu.lbr_nr)
+		return -EOPNOTSUPP;
+
+	/*
+	 * if no LBR HW filter, users can only
+	 * capture all branches
+	 */
+	if (!x86_pmu.lbr_sel_map) {
+		if (br_type != PERF_SAMPLE_BRANCH_X86_ALL)
+			return -EOPNOTSUPP;
+		return 0;
+	}
+	/*
+	 * we ignore branch priv levels we do not
+	 * know about: BRANCH_HV
+	 */
+
+	return intel_pmu_setup_hw_lbr_filter(event);
+}
+
 /*
  * Map interface branch filters onto LBR filters
  */
-- 
cgit v1.2.3


From 3e702ff6d1ea12dcf1c798ecb61e7f3a1579df42 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:20:58 +0100
Subject: perf/x86: Add LBR software filter support for Intel CPUs

This patch adds an internal sofware filter to complement
the (optional) LBR hardware filter.

The software filter is necessary:

 - as a substitute when there is no HW LBR filter (e.g., Atom, Core)
 - to complement HW LBR filter in case of errata (e.g., Nehalem/Westmere)
 - to provide finer grain filtering (e.g., all processors)

Sometimes the LBR HW filter cannot distinguish between two types
of branches. For instance, to capture syscall as CALLS, it is necessary
to enable the LBR_FAR filter which will also capture JMP instructions.
Thus, a second pass is necessary to filter those out, this is what the
SW filter can do.

The SW filter is built on top of the internal x86 disassembler. It
is a best effort filter especially for user level code. It is subject
to the availability of the text page of the program.

The SW filter is enabled on all Intel processors. It is bypassed
when the user is capturing all branches at all priv levels.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-9-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/perf_event.h           |  10 +
 arch/x86/kernel/cpu/perf_event_intel_ds.c  |  12 +-
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 332 +++++++++++++++++++++++++++--
 3 files changed, 321 insertions(+), 33 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index ef7419cbd13..f104c054dc5 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -132,6 +132,7 @@ struct cpu_hw_events {
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
+	u64				br_sel;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -459,6 +460,15 @@ extern struct event_constraint emptyconstraint;
 
 extern struct event_constraint unconstrained;
 
+static inline bool kernel_ip(unsigned long ip)
+{
+#ifdef CONFIG_X86_32
+	return ip > PAGE_OFFSET;
+#else
+	return (long)ip < 0;
+#endif
+}
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index ee7e3c8d9d6..7f64df19e7d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -3,6 +3,7 @@
 #include <linux/slab.h>
 
 #include <asm/perf_event.h>
+#include <asm/insn.h>
 
 #include "perf_event.h"
 
@@ -469,17 +470,6 @@ void intel_pmu_pebs_disable_all(void)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 }
 
-#include <asm/insn.h>
-
-static inline bool kernel_ip(unsigned long ip)
-{
-#ifdef CONFIG_X86_32
-	return ip > PAGE_OFFSET;
-#else
-	return (long)ip < 0;
-#endif
-}
-
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index d0fb864ff2b..520b4265fcd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -3,6 +3,7 @@
 
 #include <asm/perf_event.h>
 #include <asm/msr.h>
+#include <asm/insn.h>
 
 #include "perf_event.h"
 
@@ -60,6 +61,53 @@ enum {
 	for ((x) = PERF_SAMPLE_BRANCH_USER; \
 	     (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
 
+/*
+ * x86control flow change classification
+ * x86control flow changes include branches, interrupts, traps, faults
+ */
+enum {
+	X86_BR_NONE     = 0,      /* unknown */
+
+	X86_BR_USER     = 1 << 0, /* branch target is user */
+	X86_BR_KERNEL   = 1 << 1, /* branch target is kernel */
+
+	X86_BR_CALL     = 1 << 2, /* call */
+	X86_BR_RET      = 1 << 3, /* return */
+	X86_BR_SYSCALL  = 1 << 4, /* syscall */
+	X86_BR_SYSRET   = 1 << 5, /* syscall return */
+	X86_BR_INT      = 1 << 6, /* sw interrupt */
+	X86_BR_IRET     = 1 << 7, /* return from interrupt */
+	X86_BR_JCC      = 1 << 8, /* conditional */
+	X86_BR_JMP      = 1 << 9, /* jump */
+	X86_BR_IRQ      = 1 << 10,/* hw interrupt or trap or fault */
+	X86_BR_IND_CALL = 1 << 11,/* indirect calls */
+};
+
+#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
+
+#define X86_BR_ANY       \
+	(X86_BR_CALL    |\
+	 X86_BR_RET     |\
+	 X86_BR_SYSCALL |\
+	 X86_BR_SYSRET  |\
+	 X86_BR_INT     |\
+	 X86_BR_IRET    |\
+	 X86_BR_JCC     |\
+	 X86_BR_JMP	 |\
+	 X86_BR_IRQ	 |\
+	 X86_BR_IND_CALL)
+
+#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
+
+#define X86_BR_ANY_CALL		 \
+	(X86_BR_CALL		|\
+	 X86_BR_IND_CALL	|\
+	 X86_BR_SYSCALL		|\
+	 X86_BR_IRQ		|\
+	 X86_BR_INT)
+
+static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
+
 /*
  * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
  * otherwise it becomes near impossible to get a reliable stack.
@@ -131,6 +179,7 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 		intel_pmu_lbr_reset();
 		cpuc->lbr_context = event->ctx;
 	}
+	cpuc->br_sel = event->hw.branch_reg.reg;
 
 	cpuc->lbr_users++;
 }
@@ -252,6 +301,44 @@ void intel_pmu_lbr_read(void)
 		intel_pmu_lbr_read_32(cpuc);
 	else
 		intel_pmu_lbr_read_64(cpuc);
+
+	intel_pmu_lbr_filter(cpuc);
+}
+
+/*
+ * SW filter is used:
+ * - in case there is no HW filter
+ * - in case the HW filter has errata or limitations
+ */
+static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
+{
+	u64 br_type = event->attr.branch_sample_type;
+	int mask = 0;
+
+	if (br_type & PERF_SAMPLE_BRANCH_USER)
+		mask |= X86_BR_USER;
+
+	if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
+		mask |= X86_BR_KERNEL;
+
+	/* we ignore BRANCH_HV here */
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY)
+		mask |= X86_BR_ANY;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL)
+		mask |= X86_BR_ANY_CALL;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+		mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET;
+
+	if (br_type & PERF_SAMPLE_BRANCH_IND_CALL)
+		mask |= X86_BR_IND_CALL;
+	/*
+	 * stash actual user request into reg, it may
+	 * be used by fixup code for some CPU
+	 */
+	event->hw.branch_reg.reg = mask;
 }
 
 /*
@@ -273,10 +360,9 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 		v = x86_pmu.lbr_sel_map[m];
 		if (v == LBR_NOT_SUPP)
 			return -EOPNOTSUPP;
-		mask |= v;
 
-		if (m == PERF_SAMPLE_BRANCH_ANY)
-			break;
+		if (v != LBR_IGN)
+			mask |= v;
 	}
 	reg = &event->hw.branch_reg;
 	reg->idx = EXTRA_REG_LBR;
@@ -287,18 +373,9 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 	return 0;
 }
 
-/*
- * all the bits supported on some flavor of x86LBR
- * we ignore BRANCH_HV because it is not supported
- */
-#define PERF_SAMPLE_BRANCH_X86_ALL	\
-	(PERF_SAMPLE_BRANCH_ANY		|\
-	 PERF_SAMPLE_BRANCH_USER	|\
-	 PERF_SAMPLE_BRANCH_KERNEL)
-
 int intel_pmu_setup_lbr_filter(struct perf_event *event)
 {
-	u64 br_type = event->attr.branch_sample_type;
+	int ret = 0;
 
 	/*
 	 * no LBR on this PMU
@@ -307,20 +384,210 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event)
 		return -EOPNOTSUPP;
 
 	/*
-	 * if no LBR HW filter, users can only
-	 * capture all branches
+	 * setup SW LBR filter
 	 */
-	if (!x86_pmu.lbr_sel_map) {
-		if (br_type != PERF_SAMPLE_BRANCH_X86_ALL)
-			return -EOPNOTSUPP;
-		return 0;
+	intel_pmu_setup_sw_lbr_filter(event);
+
+	/*
+	 * setup HW LBR filter, if any
+	 */
+	if (x86_pmu.lbr_sel_map)
+		ret = intel_pmu_setup_hw_lbr_filter(event);
+
+	return ret;
+}
+
+/*
+ * return the type of control flow change at address "from"
+ * intruction is not necessarily a branch (in case of interrupt).
+ *
+ * The branch type returned also includes the priv level of the
+ * target of the control flow change (X86_BR_USER, X86_BR_KERNEL).
+ *
+ * If a branch type is unknown OR the instruction cannot be
+ * decoded (e.g., text page not present), then X86_BR_NONE is
+ * returned.
+ */
+static int branch_type(unsigned long from, unsigned long to)
+{
+	struct insn insn;
+	void *addr;
+	int bytes, size = MAX_INSN_SIZE;
+	int ret = X86_BR_NONE;
+	int ext, to_plm, from_plm;
+	u8 buf[MAX_INSN_SIZE];
+	int is64 = 0;
+
+	to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
+	from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER;
+
+	/*
+	 * maybe zero if lbr did not fill up after a reset by the time
+	 * we get a PMU interrupt
+	 */
+	if (from == 0 || to == 0)
+		return X86_BR_NONE;
+
+	if (from_plm == X86_BR_USER) {
+		/*
+		 * can happen if measuring at the user level only
+		 * and we interrupt in a kernel thread, e.g., idle.
+		 */
+		if (!current->mm)
+			return X86_BR_NONE;
+
+		/* may fail if text not present */
+		bytes = copy_from_user_nmi(buf, (void __user *)from, size);
+		if (bytes != size)
+			return X86_BR_NONE;
+
+		addr = buf;
+	} else
+		addr = (void *)from;
+
+	/*
+	 * decoder needs to know the ABI especially
+	 * on 64-bit systems running 32-bit apps
+	 */
+#ifdef CONFIG_X86_64
+	is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
+#endif
+	insn_init(&insn, addr, is64);
+	insn_get_opcode(&insn);
+
+	switch (insn.opcode.bytes[0]) {
+	case 0xf:
+		switch (insn.opcode.bytes[1]) {
+		case 0x05: /* syscall */
+		case 0x34: /* sysenter */
+			ret = X86_BR_SYSCALL;
+			break;
+		case 0x07: /* sysret */
+		case 0x35: /* sysexit */
+			ret = X86_BR_SYSRET;
+			break;
+		case 0x80 ... 0x8f: /* conditional */
+			ret = X86_BR_JCC;
+			break;
+		default:
+			ret = X86_BR_NONE;
+		}
+		break;
+	case 0x70 ... 0x7f: /* conditional */
+		ret = X86_BR_JCC;
+		break;
+	case 0xc2: /* near ret */
+	case 0xc3: /* near ret */
+	case 0xca: /* far ret */
+	case 0xcb: /* far ret */
+		ret = X86_BR_RET;
+		break;
+	case 0xcf: /* iret */
+		ret = X86_BR_IRET;
+		break;
+	case 0xcc ... 0xce: /* int */
+		ret = X86_BR_INT;
+		break;
+	case 0xe8: /* call near rel */
+	case 0x9a: /* call far absolute */
+		ret = X86_BR_CALL;
+		break;
+	case 0xe0 ... 0xe3: /* loop jmp */
+		ret = X86_BR_JCC;
+		break;
+	case 0xe9 ... 0xeb: /* jmp */
+		ret = X86_BR_JMP;
+		break;
+	case 0xff: /* call near absolute, call far absolute ind */
+		insn_get_modrm(&insn);
+		ext = (insn.modrm.bytes[0] >> 3) & 0x7;
+		switch (ext) {
+		case 2: /* near ind call */
+		case 3: /* far ind call */
+			ret = X86_BR_IND_CALL;
+			break;
+		case 4:
+		case 5:
+			ret = X86_BR_JMP;
+			break;
+		}
+		break;
+	default:
+		ret = X86_BR_NONE;
 	}
 	/*
-	 * we ignore branch priv levels we do not
-	 * know about: BRANCH_HV
+	 * interrupts, traps, faults (and thus ring transition) may
+	 * occur on any instructions. Thus, to classify them correctly,
+	 * we need to first look at the from and to priv levels. If they
+	 * are different and to is in the kernel, then it indicates
+	 * a ring transition. If the from instruction is not a ring
+	 * transition instr (syscall, systenter, int), then it means
+	 * it was a irq, trap or fault.
+	 *
+	 * we have no way of detecting kernel to kernel faults.
+	 */
+	if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL
+	    && ret != X86_BR_SYSCALL && ret != X86_BR_INT)
+		ret = X86_BR_IRQ;
+
+	/*
+	 * branch priv level determined by target as
+	 * is done by HW when LBR_SELECT is implemented
 	 */
+	if (ret != X86_BR_NONE)
+		ret |= to_plm;
 
-	return intel_pmu_setup_hw_lbr_filter(event);
+	return ret;
+}
+
+/*
+ * implement actual branch filter based on user demand.
+ * Hardware may not exactly satisfy that request, thus
+ * we need to inspect opcodes. Mismatched branches are
+ * discarded. Therefore, the number of branches returned
+ * in PERF_SAMPLE_BRANCH_STACK sample may vary.
+ */
+static void
+intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
+{
+	u64 from, to;
+	int br_sel = cpuc->br_sel;
+	int i, j, type;
+	bool compress = false;
+
+	/* if sampling all branches, then nothing to filter */
+	if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
+		return;
+
+	for (i = 0; i < cpuc->lbr_stack.nr; i++) {
+
+		from = cpuc->lbr_entries[i].from;
+		to = cpuc->lbr_entries[i].to;
+
+		type = branch_type(from, to);
+
+		/* if type does not correspond, then discard */
+		if (type == X86_BR_NONE || (br_sel & type) != type) {
+			cpuc->lbr_entries[i].from = 0;
+			compress = true;
+		}
+	}
+
+	if (!compress)
+		return;
+
+	/* remove all entries with from=0 */
+	for (i = 0; i < cpuc->lbr_stack.nr; ) {
+		if (!cpuc->lbr_entries[i].from) {
+			j = i;
+			while (++j < cpuc->lbr_stack.nr)
+				cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
+			cpuc->lbr_stack.nr--;
+			if (!cpuc->lbr_entries[i].from)
+				continue;
+		}
+		i++;
+	}
 }
 
 /*
@@ -363,6 +630,10 @@ void intel_pmu_lbr_init_core(void)
 	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
 	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
 
+	/*
+	 * SW branch filter usage:
+	 * - compensate for lack of HW filter
+	 */
 	pr_cont("4-deep LBR, ");
 }
 
@@ -377,6 +648,13 @@ void intel_pmu_lbr_init_nhm(void)
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;
 
+	/*
+	 * SW branch filter usage:
+	 * - workaround LBR_SEL errata (see above)
+	 * - support syscall, sysret capture.
+	 *   That requires LBR_FAR but that means far
+	 *   jmp need to be filtered out
+	 */
 	pr_cont("16-deep LBR, ");
 }
 
@@ -391,6 +669,12 @@ void intel_pmu_lbr_init_snb(void)
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
 
+	/*
+	 * SW branch filter usage:
+	 * - support syscall, sysret capture.
+	 *   That requires LBR_FAR but that means far
+	 *   jmp need to be filtered out
+	 */
 	pr_cont("16-deep LBR, ");
 }
 
@@ -412,5 +696,9 @@ void intel_pmu_lbr_init_atom(void)
 	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
 	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
 
+	/*
+	 * SW branch filter usage:
+	 * - compensate for lack of HW filter
+	 */
 	pr_cont("8-deep LBR, ");
 }
-- 
cgit v1.2.3


From 2481c5fa6db0237e4f0168f88913178b2b495b7c Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:20:59 +0100
Subject: perf: Disable PERF_SAMPLE_BRANCH_* when not supported

PERF_SAMPLE_BRANCH_* is disabled for:

 - SW events (sw counters, tracepoints)
 - HW breakpoints
 - ALL but Intel x86 architecture
 - AMD64 processors

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-10-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/alpha/kernel/perf_event.c       |  4 ++++
 arch/arm/kernel/perf_event.c         |  4 ++++
 arch/mips/kernel/perf_event_mipsxx.c |  4 ++++
 arch/powerpc/kernel/perf_event.c     |  4 ++++
 arch/sh/kernel/perf_event.c          |  4 ++++
 arch/sparc/kernel/perf_event.c       |  4 ++++
 arch/x86/kernel/cpu/perf_event_amd.c |  3 +++
 kernel/events/core.c                 | 24 ++++++++++++++++++++++++
 kernel/events/hw_breakpoint.c        |  6 ++++++
 9 files changed, 57 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 8143cd7cdbf..0dae252f7a3 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -685,6 +685,10 @@ static int alpha_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HARDWARE:
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 5bb91bf3d47..a23c42abc69 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -539,6 +539,10 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (armpmu->map_event(event) == -ENOENT)
 		return -ENOENT;
 
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index e3b897acfbc..811084f4e42 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -606,6 +606,10 @@ static int mipspmu_event_init(struct perf_event *event)
 {
 	int err = 0;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HARDWARE:
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index f04c2301725..c2e27ede07e 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1084,6 +1084,10 @@ static int power_pmu_event_init(struct perf_event *event)
 	if (!ppmu)
 		return -ENOENT;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 10b14e3a7eb..068b8a2759b 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -310,6 +310,10 @@ static int sh_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
 	case PERF_TYPE_HW_CACHE:
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 614da624330..8e16a4a2158 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1105,6 +1105,10 @@ static int sparc_pmu_event_init(struct perf_event *event)
 	if (atomic_read(&nmi_active) < 0)
 		return -ENODEV;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (attr->type) {
 	case PERF_TYPE_HARDWARE:
 		if (attr->config >= sparc_pmu->max_events)
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 67250a52430..dd002faff7a 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -139,6 +139,9 @@ static int amd_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (event->attr.exclude_host && event->attr.exclude_guest)
 		/*
 		 * When HO == GO == 1 the hardware treats that as GO == HO == 0
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5820efdf47c..242bb51c67f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5044,6 +5044,12 @@ static int perf_swevent_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_SOFTWARE)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event_id) {
 	case PERF_COUNT_SW_CPU_CLOCK:
 	case PERF_COUNT_SW_TASK_CLOCK:
@@ -5154,6 +5160,12 @@ static int perf_tp_event_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for tracepoint events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	err = perf_trace_init(event);
 	if (err)
 		return err;
@@ -5379,6 +5391,12 @@ static int cpu_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	perf_swevent_init_hrtimer(event);
 
 	return 0;
@@ -5453,6 +5471,12 @@ static int task_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	perf_swevent_init_hrtimer(event);
 
 	return 0;
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 3330022a7ac..bb38c4d3ee1 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -581,6 +581,12 @@ static int hw_breakpoint_event_init(struct perf_event *bp)
 	if (bp->attr.type != PERF_TYPE_BREAKPOINT)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for breakpoint events
+	 */
+	if (has_branch_stack(bp))
+		return -EOPNOTSUPP;
+
 	err = register_perf_hw_breakpoint(bp);
 	if (err)
 		return err;
-- 
cgit v1.2.3


From d010b3326cf06b3406cdd88af16dcf4e4b6fec2e Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Feb 2012 23:21:00 +0100
Subject: perf: Add callback to flush branch_stack on context switch

With branch stack sampling, it is possible to filter by priv levels.

In system-wide mode, that means it is possible to capture only user
level branches. The builtin SW LBR filter needs to disassemble code
based on LBR captured addresses. For that, it needs to know the task
the addresses are associated with. Because of context switches, the
content of the branch stack buffer may contain addresses from
different tasks.

We need a callback on context switch to either flush the branch stack
or save it. This patch adds a new callback in struct pmu which is called
during context switches. The callback is called only when necessary.
That is when a system-wide context has, at least, one event which
uses PERF_SAMPLE_BRANCH_STACK. The callback is never called for
per-thread context.

In this version, the Intel x86 code simply flushes (resets) the LBR
on context switches (fills it with zeroes). Those zeroed branches are
then filtered out by the SW filter.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-11-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/perf_event.c       | 21 ++++++---
 arch/x86/kernel/cpu/perf_event.h       |  1 +
 arch/x86/kernel/cpu/perf_event_intel.c | 13 ++++++
 include/linux/perf_event.h             |  9 +++-
 kernel/events/core.c                   | 85 ++++++++++++++++++++++++++++++++++
 5 files changed, 121 insertions(+), 8 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index cea56748327..0a18d16cb58 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1671,25 +1671,32 @@ static const struct attribute_group *x86_pmu_attr_groups[] = {
 	NULL,
 };
 
+static void x86_pmu_flush_branch_stack(void)
+{
+	if (x86_pmu.flush_branch_stack)
+		x86_pmu.flush_branch_stack();
+}
+
 static struct pmu pmu = {
-	.pmu_enable	= x86_pmu_enable,
-	.pmu_disable	= x86_pmu_disable,
+	.pmu_enable		= x86_pmu_enable,
+	.pmu_disable		= x86_pmu_disable,
 
 	.attr_groups	= x86_pmu_attr_groups,
 
 	.event_init	= x86_pmu_event_init,
 
-	.add		= x86_pmu_add,
-	.del		= x86_pmu_del,
-	.start		= x86_pmu_start,
-	.stop		= x86_pmu_stop,
-	.read		= x86_pmu_read,
+	.add			= x86_pmu_add,
+	.del			= x86_pmu_del,
+	.start			= x86_pmu_start,
+	.stop			= x86_pmu_stop,
+	.read			= x86_pmu_read,
 
 	.start_txn	= x86_pmu_start_txn,
 	.cancel_txn	= x86_pmu_cancel_txn,
 	.commit_txn	= x86_pmu_commit_txn,
 
 	.event_idx	= x86_pmu_event_idx,
+	.flush_branch_stack	= x86_pmu_flush_branch_stack,
 };
 
 void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index f104c054dc5..74387c12dc7 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -324,6 +324,7 @@ struct x86_pmu {
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
+	void		(*flush_branch_stack)(void);
 
 	/*
 	 * Intel Arch Perfmon v2+
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7cc1e2dcc4d..6627089232a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1539,6 +1539,18 @@ static void intel_pmu_cpu_dying(int cpu)
 	fini_debug_store_on_cpu(cpu);
 }
 
+static void intel_pmu_flush_branch_stack(void)
+{
+	/*
+	 * Intel LBR does not tag entries with the
+	 * PID of the current task, then we need to
+	 * flush it on ctxsw
+	 * For now, we simply reset it
+	 */
+	if (x86_pmu.lbr_nr)
+		intel_pmu_lbr_reset();
+}
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
@@ -1566,6 +1578,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.guest_get_msrs		= intel_guest_get_msrs,
+	.flush_branch_stack	= intel_pmu_flush_branch_stack,
 };
 
 static __init void intel_clovertown_quirk(void)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5fc494f4a09..fbbf5e59836 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -746,6 +746,11 @@ struct pmu {
 	 * if no implementation is provided it will default to: event->hw.idx + 1.
 	 */
 	int (*event_idx)		(struct perf_event *event); /*optional */
+
+	/*
+	 * flush branch stack on context-switches (needed in cpu-wide mode)
+	 */
+	void (*flush_branch_stack)	(void);
 };
 
 /**
@@ -979,7 +984,8 @@ struct perf_event_context {
 	u64				parent_gen;
 	u64				generation;
 	int				pin_count;
-	int				nr_cgroups; /* cgroup events present */
+	int				nr_cgroups;	 /* cgroup evts */
+	int				nr_branch_stack; /* branch_stack evt */
 	struct rcu_head			rcu_head;
 };
 
@@ -1044,6 +1050,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr,
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
 
+
 struct perf_sample_data {
 	u64				type;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 242bb51c67f..c61234b1a98 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -137,6 +137,7 @@ enum event_type_t {
  */
 struct static_key_deferred perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -888,6 +889,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (is_cgroup_event(event))
 		ctx->nr_cgroups++;
 
+	if (has_branch_stack(event))
+		ctx->nr_branch_stack++;
+
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	if (!ctx->nr_events)
 		perf_pmu_rotate_start(ctx->pmu);
@@ -1027,6 +1031,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 			cpuctx->cgrp = NULL;
 	}
 
+	if (has_branch_stack(event))
+		ctx->nr_branch_stack--;
+
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -2201,6 +2208,66 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	perf_pmu_rotate_start(ctx->pmu);
 }
 
+/*
+ * When sampling the branck stack in system-wide, it may be necessary
+ * to flush the stack on context switch. This happens when the branch
+ * stack does not tag its entries with the pid of the current task.
+ * Otherwise it becomes impossible to associate a branch entry with a
+ * task. This ambiguity is more likely to appear when the branch stack
+ * supports priv level filtering and the user sets it to monitor only
+ * at the user level (which could be a useful measurement in system-wide
+ * mode). In that case, the risk is high of having a branch stack with
+ * branch from multiple tasks. Flushing may mean dropping the existing
+ * entries or stashing them somewhere in the PMU specific code layer.
+ *
+ * This function provides the context switch callback to the lower code
+ * layer. It is invoked ONLY when there is at least one system-wide context
+ * with at least one active event using taken branch sampling.
+ */
+static void perf_branch_stack_sched_in(struct task_struct *prev,
+				       struct task_struct *task)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+
+	/* no need to flush branch stack if not changing task */
+	if (prev == task)
+		return;
+
+	local_irq_save(flags);
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+		/*
+		 * check if the context has at least one
+		 * event using PERF_SAMPLE_BRANCH_STACK
+		 */
+		if (cpuctx->ctx.nr_branch_stack > 0
+		    && pmu->flush_branch_stack) {
+
+			pmu = cpuctx->ctx.pmu;
+
+			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+			perf_pmu_disable(pmu);
+
+			pmu->flush_branch_stack();
+
+			perf_pmu_enable(pmu);
+
+			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+		}
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
 /*
  * Called from scheduler to add the events of the current task
  * with interrupts disabled.
@@ -2232,6 +2299,10 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	 */
 	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
 		perf_cgroup_sched_in(prev, task);
+
+	/* check for system-wide branch_stack events */
+	if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
+		perf_branch_stack_sched_in(prev, task);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -2798,6 +2869,14 @@ static void free_event(struct perf_event *event)
 			atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
 			static_key_slow_dec_deferred(&perf_sched_events);
 		}
+
+		if (has_branch_stack(event)) {
+			static_key_slow_dec_deferred(&perf_sched_events);
+			/* is system-wide event */
+			if (!(event->attach_state & PERF_ATTACH_TASK))
+				atomic_dec(&per_cpu(perf_branch_stack_events,
+						    event->cpu));
+		}
 	}
 
 	if (event->rb) {
@@ -5924,6 +6003,12 @@ done:
 				return ERR_PTR(err);
 			}
 		}
+		if (has_branch_stack(event)) {
+			static_key_slow_inc(&perf_sched_events.key);
+			if (!(event->attach_state & PERF_ATTACH_TASK))
+				atomic_inc(&per_cpu(perf_branch_stack_events,
+						    event->cpu));
+		}
 	}
 
 	return event;
-- 
cgit v1.2.3