diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 58402f6c1620..a7ab350bce98 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -391,7 +391,7 @@ struct cpu_hw_events {
 /* Check flags and event code/umask, and set the HSW N/A flag */
 #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
 	__EVENT_CONSTRAINT(code, n, 			\
-			  INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
 
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 61f25775eb1f..33b4b677bf6e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -232,7 +232,7 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
-	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5854fcf7f05a..39cf4a40aa4c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4225,7 +4225,14 @@ retry:
 		goto retry;
 	}
 
-	__perf_event_period(&pe);
+	if (event->attr.freq) {
+		event->attr.sample_freq = value;
+	} else {
+		event->attr.sample_period = value;
+		event->hw.sample_period = value;
+	}
+
+	local64_set(&event->hw.period_left, 0);
 	raw_spin_unlock_irq(&ctx->lock);
 
 	return 0;
@@ -5675,6 +5682,17 @@ perf_event_aux_ctx(struct perf_event_context *ctx,
 	}
 }
 
+static void
+perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data,
+			struct perf_event_context *task_ctx)
+{
+	rcu_read_lock();
+	preempt_disable();
+	perf_event_aux_ctx(task_ctx, output, data);
+	preempt_enable();
+	rcu_read_unlock();
+}
+
 static void
 perf_event_aux(perf_event_aux_output_cb output, void *data,
 	       struct perf_event_context *task_ctx)
@@ -5684,14 +5702,23 @@ perf_event_aux(perf_event_aux_output_cb output, void *data,
 	struct pmu *pmu;
 	int ctxn;
 
+	/*
+	 * If we have task_ctx != NULL we only notify
+	 * the task context itself. The task_ctx is set
+	 * only for EXIT events before releasing task
+	 * context.
+	 */
+	if (task_ctx) {
+		perf_event_aux_task_ctx(output, data, task_ctx);
+		return;
+	}
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
 		if (cpuctx->unique_pmu != pmu)
 			goto next;
 		perf_event_aux_ctx(&cpuctx->ctx, output, data);
-		if (task_ctx)
-			goto next;
 		ctxn = pmu->task_ctx_nr;
 		if (ctxn < 0)
 			goto next;
@@ -5701,12 +5728,6 @@ perf_event_aux(perf_event_aux_output_cb output, void *data,
 next:
 		put_cpu_ptr(pmu->pmu_cpu_context);
 	}
-
-	if (task_ctx) {
-		preempt_disable();
-		perf_event_aux_ctx(task_ctx, output, data);
-		preempt_enable();
-	}
 	rcu_read_unlock();
 }
 
@@ -8796,10 +8817,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	struct perf_event_context *child_ctx, *clone_ctx = NULL;
 	unsigned long flags;
 
-	if (likely(!child->perf_event_ctxp[ctxn])) {
-		perf_event_task(child, NULL, 0);
+	if (likely(!child->perf_event_ctxp[ctxn]))
 		return;
-	}
 
 	local_irq_save(flags);
 	/*
@@ -8883,6 +8902,14 @@ void perf_event_exit_task(struct task_struct *child)
 
 	for_each_task_context_nr(ctxn)
 		perf_event_exit_task_context(child, ctxn);
+
+	/*
+	 * The perf_event_exit_task_context calls perf_event_task
+	 * with child's task_ctx, which generates EXIT events for
+	 * child contexts and sets child->perf_event_ctxp[] to NULL.
+	 * At this point we need to send EXIT events to cpu contexts.
+	 */
+	perf_event_task(child, NULL, 0);
 }
 
 static void perf_free_event(struct perf_event *event,