[PATCH v4 05/38] perf: Add generic exclude_guest support

[Mingwei Zhang]

From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>

Only KVM knows the exact time when a guest is entering/exiting. Expose
two interfaces to KVM to switch the ownership of the PMU resources.

All the pinned events must be scheduled in first. Extend the
perf_event_sched_in() helper to support extra flag, e.g., EVENT_GUEST.

Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Mingwei Zhang <mizhang@xxxxxxxxxx>
---
 include/linux/perf_event.h |  4 ++
 kernel/events/core.c       | 80 ++++++++++++++++++++++++++++++++++----
 2 files changed, 77 insertions(+), 7 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7bda1e20be12..37187ee8e226 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1822,6 +1822,8 @@ extern int perf_event_period(struct perf_event *event, u64 value);
 extern u64 perf_event_pause(struct perf_event *event, bool reset);
 int perf_get_mediated_pmu(void);
 void perf_put_mediated_pmu(void);
+void perf_guest_enter(void);
+void perf_guest_exit(void);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
 perf_aux_output_begin(struct perf_output_handle *handle,
@@ -1919,6 +1921,8 @@ static inline int perf_get_mediated_pmu(void)
 }
 
 static inline void perf_put_mediated_pmu(void)			{ }
+static inline void perf_guest_enter(void)			{ }
+static inline void perf_guest_exit(void)			{ }
 #endif
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7a2115b2c5c1..d05487d465c9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2827,14 +2827,15 @@ static void task_ctx_sched_out(struct perf_event_context *ctx,
 
 static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
 				struct perf_event_context *ctx,
-				struct pmu *pmu)
+				struct pmu *pmu,
+				enum event_type_t event_type)
 {
-	ctx_sched_in(&cpuctx->ctx, pmu, EVENT_PINNED);
+	ctx_sched_in(&cpuctx->ctx, pmu, EVENT_PINNED | event_type);
 	if (ctx)
-		 ctx_sched_in(ctx, pmu, EVENT_PINNED);
-	ctx_sched_in(&cpuctx->ctx, pmu, EVENT_FLEXIBLE);
+		ctx_sched_in(ctx, pmu, EVENT_PINNED | event_type);
+	ctx_sched_in(&cpuctx->ctx, pmu, EVENT_FLEXIBLE | event_type);
 	if (ctx)
-		 ctx_sched_in(ctx, pmu, EVENT_FLEXIBLE);
+		ctx_sched_in(ctx, pmu, EVENT_FLEXIBLE | event_type);
 }
 
 /*
@@ -2890,7 +2891,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 	else if (event_type & EVENT_PINNED)
 		ctx_sched_out(&cpuctx->ctx, pmu, EVENT_FLEXIBLE);
 
-	perf_event_sched_in(cpuctx, task_ctx, pmu);
+	perf_event_sched_in(cpuctx, task_ctx, pmu, 0);
 
 	for_each_epc(epc, &cpuctx->ctx, pmu, 0)
 		perf_pmu_enable(epc->pmu);
@@ -4188,7 +4189,7 @@ static void perf_event_context_sched_in(struct task_struct *task)
 		ctx_sched_out(&cpuctx->ctx, NULL, EVENT_FLEXIBLE);
 	}
 
-	perf_event_sched_in(cpuctx, ctx, NULL);
+	perf_event_sched_in(cpuctx, ctx, NULL, 0);
 
 	perf_ctx_sched_task_cb(cpuctx->task_ctx, true);
 
@@ -6040,6 +6041,71 @@ void perf_put_mediated_pmu(void)
 }
 EXPORT_SYMBOL_GPL(perf_put_mediated_pmu);
 
+static inline void perf_host_exit(struct perf_cpu_context *cpuctx)
+{
+	perf_ctx_disable(&cpuctx->ctx, EVENT_GUEST);
+	ctx_sched_out(&cpuctx->ctx, NULL, EVENT_GUEST);
+	perf_ctx_enable(&cpuctx->ctx, EVENT_GUEST);
+	if (cpuctx->task_ctx) {
+		perf_ctx_disable(cpuctx->task_ctx, EVENT_GUEST);
+		task_ctx_sched_out(cpuctx->task_ctx, NULL, EVENT_GUEST);
+		perf_ctx_enable(cpuctx->task_ctx, EVENT_GUEST);
+	}
+}
+
+/* When entering a guest, schedule out all exclude_guest events. */
+void perf_guest_enter(void)
+{
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
+
+	lockdep_assert_irqs_disabled();
+
+	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+	if (WARN_ON_ONCE(__this_cpu_read(perf_in_guest)))
+		goto unlock;
+
+	perf_host_exit(cpuctx);
+
+	__this_cpu_write(perf_in_guest, true);
+
+unlock:
+	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+}
+EXPORT_SYMBOL_GPL(perf_guest_enter);
+
+static inline void perf_host_enter(struct perf_cpu_context *cpuctx)
+{
+	perf_ctx_disable(&cpuctx->ctx, EVENT_GUEST);
+	if (cpuctx->task_ctx)
+		perf_ctx_disable(cpuctx->task_ctx, EVENT_GUEST);
+
+	perf_event_sched_in(cpuctx, cpuctx->task_ctx, NULL, EVENT_GUEST);
+
+	if (cpuctx->task_ctx)
+		perf_ctx_enable(cpuctx->task_ctx, EVENT_GUEST);
+	perf_ctx_enable(&cpuctx->ctx, EVENT_GUEST);
+}
+
+void perf_guest_exit(void)
+{
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
+
+	lockdep_assert_irqs_disabled();
+
+	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+	if (WARN_ON_ONCE(!__this_cpu_read(perf_in_guest)))
+		goto unlock;
+
+	perf_host_enter(cpuctx);
+
+	__this_cpu_write(perf_in_guest, false);
+unlock:
+	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+}
+EXPORT_SYMBOL_GPL(perf_guest_exit);
+
 /*
  * Holding the top-level event's child_mutex means that any
  * descendant process that has inherited this event will block
-- 
2.49.0.395.g12beb8f557-goog