Merge tag 'perf-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance event updates from Ingo Molnar:
 - Add AMD Unified Memory Controller (UMC) events introduced with Zen 4
 - Simplify & clean up the uncore management code
 - Fall back from RDPMC to RDMSR on certain uncore PMUs
 - Improve per-package and cstate event reading
 - Extend the Intel ref-cycles event to GP counters
 - Fix Intel MTL event constraints
 - Improve the Intel hybrid CPU handling code
 - Micro-optimize the RAPL code
 - Optimize perf_cgroup_switch()
 - Improve large AUX area error handling
 - Misc fixes and cleanups

* tag 'perf-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  perf/x86/amd/uncore: Pass through error code for initialization failures, instead of -ENODEV
  perf/x86/amd/uncore: Fix uninitialized return value in amd_uncore_init()
  x86/cpu: Fix the AMD Fam 17h, Fam 19h, Zen2 and Zen4 MSR enumerations
  perf: Optimize perf_cgroup_switch()
  perf/x86/amd/uncore: Add memory controller support
  perf/x86/amd/uncore: Add group exclusivity
  perf/x86/amd/uncore: Use rdmsr if rdpmc is unavailable
  perf/x86/amd/uncore: Move discovery and registration
  perf/x86/amd/uncore: Refactor uncore management
  perf/core: Allow reading package events from perf_event_read_local
  perf/x86/cstate: Allow reading the package statistics from local CPU
  perf/x86/intel/pt: Fix kernel-doc comments
  perf/x86/rapl: Annotate 'struct rapl_pmus' with __counted_by
  perf/core: Rename perf_proc_update_handler() -> perf_event_max_sample_rate_handler(), for readability
  perf/x86/rapl: Fix "Using plain integer as NULL pointer" Sparse warning
  perf/x86/rapl: Use local64_try_cmpxchg in rapl_event_update()
  perf/x86/rapl: Stop doing cpu_relax() in the local64_cmpxchg() loop in rapl_event_update()
  perf/core: Bail out early if the request AUX area is out of bound
  perf/x86/intel: Extend the ref-cycles event to GP counters
  perf/x86/intel: Fix broken fixed event constraints extension
  ...

2 files changed, 83 insertions, 60 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index a2f2a9525d72..683dc086ef10 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -375,6 +375,7 @@ enum event_type_t {
 	EVENT_TIME = 0x4,
 	/* see ctx_resched() for details */
 	EVENT_CPU = 0x8,
+	EVENT_CGROUP = 0x10,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
@@ -449,8 +450,8 @@ static void update_perf_cpu_limits(void)
 
 static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc);
 
-int perf_proc_update_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos)
+int perf_event_max_sample_rate_handler(struct ctl_table *table, int write,
+				       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
 	int perf_cpu = sysctl_perf_cpu_time_max_percent;
@@ -684,20 +685,26 @@ do {									\
 	___p;								\
 })
 
-static void perf_ctx_disable(struct perf_event_context *ctx)
+static void perf_ctx_disable(struct perf_event_context *ctx, bool cgroup)
 {
 	struct perf_event_pmu_context *pmu_ctx;
 
-	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry)
+	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+		if (cgroup && !pmu_ctx->nr_cgroups)
+			continue;
 		perf_pmu_disable(pmu_ctx->pmu);
+	}
 }
 
-static void perf_ctx_enable(struct perf_event_context *ctx)
+static void perf_ctx_enable(struct perf_event_context *ctx, bool cgroup)
 {
 	struct perf_event_pmu_context *pmu_ctx;
 
-	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry)
+	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+		if (cgroup && !pmu_ctx->nr_cgroups)
+			continue;
 		perf_pmu_enable(pmu_ctx->pmu);
+	}
 }
 
 static void ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type);
@@ -856,9 +863,9 @@ static void perf_cgroup_switch(struct task_struct *task)
 		return;
 
 	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
-	perf_ctx_disable(&cpuctx->ctx);
+	perf_ctx_disable(&cpuctx->ctx, true);
 
-	ctx_sched_out(&cpuctx->ctx, EVENT_ALL);
+	ctx_sched_out(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP);
 	/*
 	 * must not be done before ctxswout due
 	 * to update_cgrp_time_from_cpuctx() in
@@ -870,9 +877,9 @@ static void perf_cgroup_switch(struct task_struct *task)
 	 * perf_cgroup_set_timestamp() in ctx_sched_in()
 	 * to not have to pass task around
 	 */
-	ctx_sched_in(&cpuctx->ctx, EVENT_ALL);
+	ctx_sched_in(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP);
 
-	perf_ctx_enable(&cpuctx->ctx);
+	perf_ctx_enable(&cpuctx->ctx, true);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
@@ -965,6 +972,8 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct
 	if (!is_cgroup_event(event))
 		return;
 
+	event->pmu_ctx->nr_cgroups++;
+
 	/*
 	 * Because cgroup events are always per-cpu events,
 	 * @ctx == &cpuctx->ctx.
@@ -985,6 +994,8 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c
 	if (!is_cgroup_event(event))
 		return;
 
+	event->pmu_ctx->nr_cgroups--;
+
 	/*
 	 * Because cgroup events are always per-cpu events,
 	 * @ctx == &cpuctx->ctx.
@@ -2679,9 +2690,9 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 
 	event_type &= EVENT_ALL;
 
-	perf_ctx_disable(&cpuctx->ctx);
+	perf_ctx_disable(&cpuctx->ctx, false);
 	if (task_ctx) {
-		perf_ctx_disable(task_ctx);
+		perf_ctx_disable(task_ctx, false);
 		task_ctx_sched_out(task_ctx, event_type);
 	}
 
@@ -2699,9 +2710,9 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 
 	perf_event_sched_in(cpuctx, task_ctx);
 
-	perf_ctx_enable(&cpuctx->ctx);
+	perf_ctx_enable(&cpuctx->ctx, false);
 	if (task_ctx)
-		perf_ctx_enable(task_ctx);
+		perf_ctx_enable(task_ctx, false);
 }
 
 void perf_pmu_resched(struct pmu *pmu)
@@ -3246,6 +3257,9 @@ ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type)
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
 	struct perf_event_pmu_context *pmu_ctx;
 	int is_active = ctx->is_active;
+	bool cgroup = event_type & EVENT_CGROUP;
+
+	event_type &= ~EVENT_CGROUP;
 
 	lockdep_assert_held(&ctx->lock);
 
@@ -3292,8 +3306,11 @@ ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type)
 
 	is_active ^= ctx->is_active; /* changed bits */
 
-	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry)
+	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+		if (cgroup && !pmu_ctx->nr_cgroups)
+			continue;
 		__pmu_ctx_sched_out(pmu_ctx, is_active);
+	}
 }
 
 /*
@@ -3484,7 +3501,7 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next)
 		raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
 		if (context_equiv(ctx, next_ctx)) {
 
-			perf_ctx_disable(ctx);
+			perf_ctx_disable(ctx, false);
 
 			/* PMIs are disabled; ctx->nr_pending is stable. */
 			if (local_read(&ctx->nr_pending) ||
@@ -3504,7 +3521,7 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next)
 			perf_ctx_sched_task_cb(ctx, false);
 			perf_event_swap_task_ctx_data(ctx, next_ctx);
 
-			perf_ctx_enable(ctx);
+			perf_ctx_enable(ctx, false);
 
 			/*
 			 * RCU_INIT_POINTER here is safe because we've not
@@ -3528,13 +3545,13 @@ unlock:
 
 	if (do_switch) {
 		raw_spin_lock(&ctx->lock);
-		perf_ctx_disable(ctx);
+		perf_ctx_disable(ctx, false);
 
 inside_switch:
 		perf_ctx_sched_task_cb(ctx, false);
 		task_ctx_sched_out(ctx, EVENT_ALL);
 
-		perf_ctx_enable(ctx);
+		perf_ctx_enable(ctx, false);
 		raw_spin_unlock(&ctx->lock);
 	}
 }
@@ -3820,47 +3837,32 @@ static int merge_sched_in(struct perf_event *event, void *data)
 	return 0;
 }
 
-static void ctx_pinned_sched_in(struct perf_event_context *ctx, struct pmu *pmu)
+static void pmu_groups_sched_in(struct perf_event_context *ctx,
+				struct perf_event_groups *groups,
+				struct pmu *pmu)
 {
-	struct perf_event_pmu_context *pmu_ctx;
 	int can_add_hw = 1;
-
-	if (pmu) {
-		visit_groups_merge(ctx, &ctx->pinned_groups,
-				   smp_processor_id(), pmu,
-				   merge_sched_in, &can_add_hw);
-	} else {
-		list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
-			can_add_hw = 1;
-			visit_groups_merge(ctx, &ctx->pinned_groups,
-					   smp_processor_id(), pmu_ctx->pmu,
-					   merge_sched_in, &can_add_hw);
-		}
-	}
+	visit_groups_merge(ctx, groups, smp_processor_id(), pmu,
+			   merge_sched_in, &can_add_hw);
 }
 
-static void ctx_flexible_sched_in(struct perf_event_context *ctx, struct pmu *pmu)
+static void ctx_groups_sched_in(struct perf_event_context *ctx,
+				struct perf_event_groups *groups,
+				bool cgroup)
 {
 	struct perf_event_pmu_context *pmu_ctx;
-	int can_add_hw = 1;
 
-	if (pmu) {
-		visit_groups_merge(ctx, &ctx->flexible_groups,
-				   smp_processor_id(), pmu,
-				   merge_sched_in, &can_add_hw);
-	} else {
-		list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
-			can_add_hw = 1;
-			visit_groups_merge(ctx, &ctx->flexible_groups,
-					   smp_processor_id(), pmu_ctx->pmu,
-					   merge_sched_in, &can_add_hw);
-		}
+	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+		if (cgroup && !pmu_ctx->nr_cgroups)
+			continue;
+		pmu_groups_sched_in(ctx, groups, pmu_ctx->pmu);
 	}
 }
 
-static void __pmu_ctx_sched_in(struct perf_event_context *ctx, struct pmu *pmu)
+static void __pmu_ctx_sched_in(struct perf_event_context *ctx,
+			       struct pmu *pmu)
 {
-	ctx_flexible_sched_in(ctx, pmu);
+	pmu_groups_sched_in(ctx, &ctx->flexible_groups, pmu);
 }
 
 static void
@@ -3868,6 +3870,9 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
 	int is_active = ctx->is_active;
+	bool cgroup = event_type & EVENT_CGROUP;
+
+	event_type &= ~EVENT_CGROUP;
 
 	lockdep_assert_held(&ctx->lock);
 
@@ -3900,11 +3905,11 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
 	 * in order to give them the best chance of going on.
 	 */
 	if (is_active & EVENT_PINNED)
-		ctx_pinned_sched_in(ctx, NULL);
+		ctx_groups_sched_in(ctx, &ctx->pinned_groups, cgroup);
 
 	/* Then walk through the lower prio flexible groups */
 	if (is_active & EVENT_FLEXIBLE)
-		ctx_flexible_sched_in(ctx, NULL);
+		ctx_groups_sched_in(ctx, &ctx->flexible_groups, cgroup);
 }
 
 static void perf_event_context_sched_in(struct task_struct *task)
@@ -3919,11 +3924,11 @@ static void perf_event_context_sched_in(struct task_struct *task)
 
 	if (cpuctx->task_ctx == ctx) {
 		perf_ctx_lock(cpuctx, ctx);
-		perf_ctx_disable(ctx);
+		perf_ctx_disable(ctx, false);
 
 		perf_ctx_sched_task_cb(ctx, true);
 
-		perf_ctx_enable(ctx);
+		perf_ctx_enable(ctx, false);
 		perf_ctx_unlock(cpuctx, ctx);
 		goto rcu_unlock;
 	}
@@ -3936,7 +3941,7 @@ static void perf_event_context_sched_in(struct task_struct *task)
 	if (!ctx->nr_events)
 		goto unlock;
 
-	perf_ctx_disable(ctx);
+	perf_ctx_disable(ctx, false);
 	/*
 	 * We want to keep the following priority order:
 	 * cpu pinned (that don't need to move), task pinned,
@@ -3946,7 +3951,7 @@ static void perf_event_context_sched_in(struct task_struct *task)
 	 * events, no need to flip the cpuctx's events around.
 	 */
 	if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) {
-		perf_ctx_disable(&cpuctx->ctx);
+		perf_ctx_disable(&cpuctx->ctx, false);
 		ctx_sched_out(&cpuctx->ctx, EVENT_FLEXIBLE);
 	}
 
@@ -3955,9 +3960,9 @@ static void perf_event_context_sched_in(struct task_struct *task)
 	perf_ctx_sched_task_cb(cpuctx->task_ctx, true);
 
 	if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree))
-		perf_ctx_enable(&cpuctx->ctx);
+		perf_ctx_enable(&cpuctx->ctx, false);
 
-	perf_ctx_enable(ctx);
+	perf_ctx_enable(ctx, false);
 
 unlock:
 	perf_ctx_unlock(cpuctx, ctx);
@@ -4427,6 +4432,9 @@ static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
 	u16 local_pkg, event_pkg;
 
+	if ((unsigned)event_cpu >= nr_cpu_ids)
+		return event_cpu;
+
 	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
 		int local_cpu = smp_processor_id();
 
@@ -4529,6 +4537,8 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 			  u64 *enabled, u64 *running)
 {
 	unsigned long flags;
+	int event_oncpu;
+	int event_cpu;
 	int ret = 0;
 
 	/*
@@ -4553,15 +4563,22 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 		goto out;
 	}
 
+	/*
+	 * Get the event CPU numbers, and adjust them to local if the event is
+	 * a per-package event that can be read locally
+	 */
+	event_oncpu = __perf_event_read_cpu(event, event->oncpu);
+	event_cpu = __perf_event_read_cpu(event, event->cpu);
+
 	/* If this is a per-CPU event, it must be for this CPU */
 	if (!(event->attach_state & PERF_ATTACH_TASK) &&
-	    event->cpu != smp_processor_id()) {
+	    event_cpu != smp_processor_id()) {
 		ret = -EINVAL;
 		goto out;
 	}
 
 	/* If this is a pinned event it must be running on this CPU */
-	if (event->attr.pinned && event->oncpu != smp_processor_id()) {
+	if (event->attr.pinned && event_oncpu != smp_processor_id()) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -4571,7 +4588,7 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 	 * or local to this CPU. Furthermore it means its ACTIVE (otherwise
 	 * oncpu == -1).
 	 */
-	if (event->oncpu == smp_processor_id())
+	if (event_oncpu == smp_processor_id())
 		event->pmu->read(event);
 
 	*value = local64_read(&event->count);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index fb1e180b5f0a..e8d82c2f07d0 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -700,6 +700,12 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
 		watermark = 0;
 	}
 
+	/*
+	 * kcalloc_node() is unable to allocate buffer if the size is larger
+	 * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case.
+	 */
+	if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER)
+		return -ENOMEM;
 	rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL,
 				     node);
 	if (!rb->aux_pages)