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>

3 files changed, 28 insertions, 7 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index cea5674..0a18d16 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 f104c05..74387c1 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 7cc1e2d..6627089 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)