diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index bbf6588d47ee3b992d9163e19438e856250350f9..dc64b16e6b719b0d8f89227b17ec965bb2dc4586 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_swap_task_ctx(struct perf_event_context *prev,
+				    struct perf_event_context *next)
+{
+	intel_pmu_lbr_swap_task_ctx(prev, next);
+}
+
 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,
+	.swap_task_ctx		= intel_pmu_swap_task_ctx,
 
 	.check_period		= intel_pmu_check_period,
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0940c8810be06def24509bad14af37dc6e06fd9c..f48d38b55e7b20d167211e81cd02a5238df0da77 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3204,10 +3204,21 @@ 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. As an example of such
+			 * synchronization see implementation details of Intel
+			 * LBR call stack data profiling;
+			 */
+			if (pmu->swap_task_ctx)
+				pmu->swap_task_ctx(ctx, next_ctx);
+			else
+				swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
 
 			/*
 			 * RCU_INIT_POINTER here is safe because we've not