[PATCH v4 4/4] perf/core,x86: synchronize PMU task contexts on optimized context switches

[Alexey Budankov <alexey.budankov@linux.intel.com>]

Install Intel specific PMU task context synchronization adapter and
extend optimized context switch path with PMU specific task context
synchronization to fix LBR callstack virtualization on context switches.

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
---
 arch/x86/events/intel/core.c |  7 +++++++
 kernel/events/core.c         | 13 +++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index bbf6588d47ee..b9f518aa478e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3820,6 +3820,12 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx,
 	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
+static void intel_pmu_sync_task_ctx(struct x86_perf_task_context *one,
+				    struct x86_perf_task_context *another)
+{
+	intel_pmu_lbr_sync_task_ctx(one, another);
+}
+
 static int intel_pmu_check_period(struct perf_event *event, u64 value)
 {
 	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
@@ -3955,6 +3961,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
+	.sync_task_ctx		= intel_pmu_sync_task_ctx,
 
 	.check_period		= intel_pmu_check_period,
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f9a5d4356562..51d4138b06f7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3204,11 +3204,24 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 		raw_spin_lock(&ctx->lock);
 		raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
 		if (context_equiv(ctx, next_ctx)) {
+			struct pmu *pmu = ctx->pmu;
+
 			WRITE_ONCE(ctx->task, next);
 			WRITE_ONCE(next_ctx->task, task);
 
 			swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
 
+			/*
+			 * PMU specific parts of task perf context can require
+			 * additional synchronization which makes sense only if
+			 * both next_ctx->task_ctx_data and ctx->task_ctx_data
+			 * pointers are allocated. As an example of such
+			 * synchronization see implementation details of Intel
+			 * LBR call stack data profiling;
+			 */
+			if (ctx->task_ctx_data && next_ctx->task_ctx_data)
+				pmu->sync_task_ctx(next_ctx->task_ctx_data,
+						   ctx->task_ctx_data);
 			/*
 			 * RCU_INIT_POINTER here is safe because we've not
 			 * modified the ctx and the above modification of
-- 
2.20.1