Merge tag 'perf_urgent_for_v5.18_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Borislav Petkov:

 - A couple of fixes to cgroup-related handling of perf events

 - A couple of fixes to event encoding on Sapphire Rapids

 - Pass event caps of inherited events so that perf doesn't fail wrongly
   at fork()

 - Add support for a new Raptor Lake CPU

* tag 'perf_urgent_for_v5.18_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/core: Always set cpuctx cgrp when enable cgroup event
  perf/core: Fix perf_cgroup_switch()
  perf/core: Use perf_cgroup_info->active to check if cgroup is active
  perf/core: Don't pass task around when ctx sched in
  perf/x86/intel: Update the FRONTEND MSR mask on Sapphire Rapids
  perf/x86/intel: Don't extend the pseudo-encoding to GP counters
  perf/core: Inherit event_caps
  perf/x86/uncore: Add Raptor Lake uncore support
  perf/x86/msr: Add Raptor Lake CPU support
  perf/x86/cstate: Add Raptor Lake support
  perf/x86: Add Intel Raptor Lake support

1 files changed, 55 insertions, 157 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index cfde994ce61c..23bb19716ad3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -574,8 +574,7 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
 			      enum event_type_t event_type);
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type,
-			     struct task_struct *task);
+			     enum event_type_t event_type);
 
 static void update_context_time(struct perf_event_context *ctx);
 static u64 perf_event_time(struct perf_event *event);
@@ -781,7 +780,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx,
 static inline void update_cgrp_time_from_event(struct perf_event *event)
 {
 	struct perf_cgroup_info *info;
-	struct perf_cgroup *cgrp;
 
 	/*
 	 * ensure we access cgroup data only when needed and
@@ -790,21 +788,19 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	if (!is_cgroup_event(event))
 		return;
 
-	cgrp = perf_cgroup_from_task(current, event->ctx);
+	info = this_cpu_ptr(event->cgrp->info);
 	/*
 	 * Do not update time when cgroup is not active
 	 */
-	if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) {
-		info = this_cpu_ptr(event->cgrp->info);
+	if (info->active)
 		__update_cgrp_time(info, perf_clock(), true);
-	}
 }
 
 static inline void
-perf_cgroup_set_timestamp(struct task_struct *task,
-			  struct perf_event_context *ctx)
+perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx)
 {
-	struct perf_cgroup *cgrp;
+	struct perf_event_context *ctx = &cpuctx->ctx;
+	struct perf_cgroup *cgrp = cpuctx->cgrp;
 	struct perf_cgroup_info *info;
 	struct cgroup_subsys_state *css;
 
@@ -813,10 +809,10 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 	 * ensure we do not access cgroup data
 	 * unless we have the cgroup pinned (css_get)
 	 */
-	if (!task || !ctx->nr_cgroups)
+	if (!cgrp)
 		return;
 
-	cgrp = perf_cgroup_from_task(task, ctx);
+	WARN_ON_ONCE(!ctx->nr_cgroups);
 
 	for (css = &cgrp->css; css; css = css->parent) {
 		cgrp = container_of(css, struct perf_cgroup, css);
@@ -828,17 +824,12 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 
 static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
 
-#define PERF_CGROUP_SWOUT	0x1 /* cgroup switch out every event */
-#define PERF_CGROUP_SWIN	0x2 /* cgroup switch in events based on task */
-
 /*
  * reschedule events based on the cgroup constraint of task.
- *
- * mode SWOUT : schedule out everything
- * mode SWIN : schedule in based on cgroup for next
  */
-static void perf_cgroup_switch(struct task_struct *task, int mode)
+static void perf_cgroup_switch(struct task_struct *task)
 {
+	struct perf_cgroup *cgrp;
 	struct perf_cpu_context *cpuctx, *tmp;
 	struct list_head *list;
 	unsigned long flags;
@@ -849,35 +840,31 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
 	 */
 	local_irq_save(flags);
 
+	cgrp = perf_cgroup_from_task(task, NULL);
+
 	list = this_cpu_ptr(&cgrp_cpuctx_list);
 	list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) {
 		WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+		if (READ_ONCE(cpuctx->cgrp) == cgrp)
+			continue;
 
 		perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 		perf_pmu_disable(cpuctx->ctx.pmu);
 
-		if (mode & PERF_CGROUP_SWOUT) {
-			cpu_ctx_sched_out(cpuctx, EVENT_ALL);
-			/*
-			 * must not be done before ctxswout due
-			 * to event_filter_match() in event_sched_out()
-			 */
-			cpuctx->cgrp = NULL;
-		}
+		cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+		/*
+		 * must not be done before ctxswout due
+		 * to update_cgrp_time_from_cpuctx() in
+		 * ctx_sched_out()
+		 */
+		cpuctx->cgrp = cgrp;
+		/*
+		 * set cgrp before ctxsw in to allow
+		 * perf_cgroup_set_timestamp() in ctx_sched_in()
+		 * to not have to pass task around
+		 */
+		cpu_ctx_sched_in(cpuctx, EVENT_ALL);
 
-		if (mode & PERF_CGROUP_SWIN) {
-			WARN_ON_ONCE(cpuctx->cgrp);
-			/*
-			 * set cgrp before ctxsw in to allow
-			 * event_filter_match() to not have to pass
-			 * task around
-			 * we pass the cpuctx->ctx to perf_cgroup_from_task()
-			 * because cgorup events are only per-cpu
-			 */
-			cpuctx->cgrp = perf_cgroup_from_task(task,
-							     &cpuctx->ctx);
-			cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
-		}
 		perf_pmu_enable(cpuctx->ctx.pmu);
 		perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 	}
@@ -885,58 +872,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
 	local_irq_restore(flags);
 }
 
-static inline void perf_cgroup_sched_out(struct task_struct *task,
-					 struct task_struct *next)
-{
-	struct perf_cgroup *cgrp1;
-	struct perf_cgroup *cgrp2 = NULL;
-
-	rcu_read_lock();
-	/*
-	 * we come here when we know perf_cgroup_events > 0
-	 * we do not need to pass the ctx here because we know
-	 * we are holding the rcu lock
-	 */
-	cgrp1 = perf_cgroup_from_task(task, NULL);
-	cgrp2 = perf_cgroup_from_task(next, NULL);
-
-	/*
-	 * only schedule out current cgroup events if we know
-	 * that we are switching to a different cgroup. Otherwise,
-	 * do no touch the cgroup events.
-	 */
-	if (cgrp1 != cgrp2)
-		perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
-
-	rcu_read_unlock();
-}
-
-static inline void perf_cgroup_sched_in(struct task_struct *prev,
-					struct task_struct *task)
-{
-	struct perf_cgroup *cgrp1;
-	struct perf_cgroup *cgrp2 = NULL;
-
-	rcu_read_lock();
-	/*
-	 * we come here when we know perf_cgroup_events > 0
-	 * we do not need to pass the ctx here because we know
-	 * we are holding the rcu lock
-	 */
-	cgrp1 = perf_cgroup_from_task(task, NULL);
-	cgrp2 = perf_cgroup_from_task(prev, NULL);
-
-	/*
-	 * only need to schedule in cgroup events if we are changing
-	 * cgroup during ctxsw. Cgroup events were not scheduled
-	 * out of ctxsw out if that was not the case.
-	 */
-	if (cgrp1 != cgrp2)
-		perf_cgroup_switch(task, PERF_CGROUP_SWIN);
-
-	rcu_read_unlock();
-}
-
 static int perf_cgroup_ensure_storage(struct perf_event *event,
 				struct cgroup_subsys_state *css)
 {
@@ -1032,22 +967,10 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct
 	 */
 	cpuctx = container_of(ctx, struct perf_cpu_context, ctx);
 
-	/*
-	 * Since setting cpuctx->cgrp is conditional on the current @cgrp
-	 * matching the event's cgroup, we must do this for every new event,
-	 * because if the first would mismatch, the second would not try again
-	 * and we would leave cpuctx->cgrp unset.
-	 */
-	if (ctx->is_active && !cpuctx->cgrp) {
-		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
-
-		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
-			cpuctx->cgrp = cgrp;
-	}
-
 	if (ctx->nr_cgroups++)
 		return;
 
+	cpuctx->cgrp = perf_cgroup_from_task(current, ctx);
 	list_add(&cpuctx->cgrp_cpuctx_entry,
 			per_cpu_ptr(&cgrp_cpuctx_list, event->cpu));
 }
@@ -1069,9 +992,7 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c
 	if (--ctx->nr_cgroups)
 		return;
 
-	if (ctx->is_active && cpuctx->cgrp)
-		cpuctx->cgrp = NULL;
-
+	cpuctx->cgrp = NULL;
 	list_del(&cpuctx->cgrp_cpuctx_entry);
 }
 
@@ -1100,16 +1021,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx,
 {
 }
 
-static inline void perf_cgroup_sched_out(struct task_struct *task,
-					 struct task_struct *next)
-{
-}
-
-static inline void perf_cgroup_sched_in(struct task_struct *prev,
-					struct task_struct *task)
-{
-}
-
 static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
 				      struct perf_event_attr *attr,
 				      struct perf_event *group_leader)
@@ -1118,13 +1029,7 @@ static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
 }
 
 static inline void
-perf_cgroup_set_timestamp(struct task_struct *task,
-			  struct perf_event_context *ctx)
-{
-}
-
-static inline void
-perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
+perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx)
 {
 }
 
@@ -1147,6 +1052,10 @@ static inline void
 perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx)
 {
 }
+
+static void perf_cgroup_switch(struct task_struct *task)
+{
+}
 #endif
 
 /*
@@ -2713,8 +2622,7 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
-	     enum event_type_t event_type,
-	     struct task_struct *task);
+	     enum event_type_t event_type);
 
 static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
 			       struct perf_event_context *ctx,
@@ -2730,15 +2638,14 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
 }
 
 static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
-				struct perf_event_context *ctx,
-				struct task_struct *task)
+				struct perf_event_context *ctx)
 {
-	cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task);
+	cpu_ctx_sched_in(cpuctx, EVENT_PINNED);
 	if (ctx)
-		ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task);
-	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task);
+		ctx_sched_in(ctx, cpuctx, EVENT_PINNED);
+	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
-		ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
+		ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
 }
 
 /*
@@ -2788,7 +2695,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 	else if (ctx_event_type & EVENT_PINNED)
 		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
-	perf_event_sched_in(cpuctx, task_ctx, current);
+	perf_event_sched_in(cpuctx, task_ctx);
 	perf_pmu_enable(cpuctx->ctx.pmu);
 }
 
@@ -3011,7 +2918,7 @@ static void __perf_event_enable(struct perf_event *event,
 		return;
 
 	if (!event_filter_match(event)) {
-		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME);
 		return;
 	}
 
@@ -3020,7 +2927,7 @@ static void __perf_event_enable(struct perf_event *event,
 	 * then don't put it on unless the group is on.
 	 */
 	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) {
-		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME);
 		return;
 	}
 
@@ -3668,7 +3575,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
 	 * cgroup event are system-wide mode only
 	 */
 	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
-		perf_cgroup_sched_out(task, next);
+		perf_cgroup_switch(next);
 }
 
 /*
@@ -3865,8 +3772,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
-	     enum event_type_t event_type,
-	     struct task_struct *task)
+	     enum event_type_t event_type)
 {
 	int is_active = ctx->is_active;
 
@@ -3878,7 +3784,7 @@ ctx_sched_in(struct perf_event_context *ctx,
 	if (is_active ^ EVENT_TIME) {
 		/* start ctx time */
 		__update_context_time(ctx, false);
-		perf_cgroup_set_timestamp(task, ctx);
+		perf_cgroup_set_timestamp(cpuctx);
 		/*
 		 * CPU-release for the below ->is_active store,
 		 * see __load_acquire() in perf_event_time_now()
@@ -3909,12 +3815,11 @@ ctx_sched_in(struct perf_event_context *ctx,
 }
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type,
-			     struct task_struct *task)
+			     enum event_type_t event_type)
 {
 	struct perf_event_context *ctx = &cpuctx->ctx;
 
-	ctx_sched_in(ctx, cpuctx, event_type, task);
+	ctx_sched_in(ctx, cpuctx, event_type);
 }
 
 static void perf_event_context_sched_in(struct perf_event_context *ctx,
@@ -3956,7 +3861,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	 */
 	if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree))
 		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
-	perf_event_sched_in(cpuctx, ctx, task);
+	perf_event_sched_in(cpuctx, ctx);
 
 	if (cpuctx->sched_cb_usage && pmu->sched_task)
 		pmu->sched_task(cpuctx->task_ctx, true);
@@ -3984,16 +3889,6 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	struct perf_event_context *ctx;
 	int ctxn;
 
-	/*
-	 * If cgroup events exist on this CPU, then we need to check if we have
-	 * to switch in PMU state; cgroup event are system-wide mode only.
-	 *
-	 * Since cgroup events are CPU events, we must schedule these in before
-	 * we schedule in the task events.
-	 */
-	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
-		perf_cgroup_sched_in(prev, task);
-
 	for_each_task_context_nr(ctxn) {
 		ctx = task->perf_event_ctxp[ctxn];
 		if (likely(!ctx))
@@ -4267,7 +4162,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 	if (cpu_event)
 		rotate_ctx(&cpuctx->ctx, cpu_event);
 
-	perf_event_sched_in(cpuctx, task_ctx, current);
+	perf_event_sched_in(cpuctx, task_ctx);
 
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
@@ -4339,7 +4234,7 @@ static void perf_event_enable_on_exec(int ctxn)
 		clone_ctx = unclone_ctx(ctx);
 		ctx_resched(cpuctx, ctx, event_type);
 	} else {
-		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME);
 	}
 	perf_ctx_unlock(cpuctx, ctx);
 
@@ -11635,6 +11530,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	event->state		= PERF_EVENT_STATE_INACTIVE;
 
+	if (parent_event)
+		event->event_caps = parent_event->event_caps;
+
 	if (event->attr.sigtrap)
 		atomic_set(&event->event_limit, 1);
 
@@ -13562,7 +13460,7 @@ static int __perf_cgroup_move(void *info)
 {
 	struct task_struct *task = info;
 	rcu_read_lock();
-	perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+	perf_cgroup_switch(task);
 	rcu_read_unlock();
 	return 0;
 }