Merge tag 'perf_urgent_for_v5.12-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Borislav Petkov:

 - Make sure PMU internal buffers are flushed for per-CPU events too and
   properly handle PID/TID for large PEBS.

 - Handle the case properly when there's no PMU and therefore return an
   empty list of perf MSRs for VMX to switch instead of reading random
   garbage from the stack.

* tag 'perf_urgent_for_v5.12-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/perf: Use RET0 as default for guest_get_msrs to handle "no PMU" case
  perf/x86/intel: Set PERF_ATTACH_SCHED_CB for large PEBS and LBR
  perf/core: Flush PMU internal buffers for per-CPU events

5 files changed, 51 insertions, 15 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6ddeed3cd2acb1..18df1712969554 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -81,7 +81,11 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx);
 DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs,   *x86_pmu.drain_pebs);
 DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
 
-DEFINE_STATIC_CALL_NULL(x86_pmu_guest_get_msrs,  *x86_pmu.guest_get_msrs);
+/*
+ * This one is magic, it will get called even when PMU init fails (because
+ * there is no PMU), in which case it should simply return NULL.
+ */
+DEFINE_STATIC_CALL_RET0(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs);
 
 u64 __read_mostly hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -1944,13 +1948,6 @@ static void _x86_pmu_read(struct perf_event *event)
 	x86_perf_event_update(event);
 }
 
-static inline struct perf_guest_switch_msr *
-perf_guest_get_msrs_nop(int *nr)
-{
-	*nr = 0;
-	return NULL;
-}
-
 static int __init init_hw_perf_events(void)
 {
 	struct x86_pmu_quirk *quirk;
@@ -2025,7 +2022,7 @@ static int __init init_hw_perf_events(void)
 		x86_pmu.read = _x86_pmu_read;
 
 	if (!x86_pmu.guest_get_msrs)
-		x86_pmu.guest_get_msrs = perf_guest_get_msrs_nop;
+		x86_pmu.guest_get_msrs = (void *)&__static_call_return0;
 
 	x86_pmu_static_call_update();
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 5bac48d5c18e86..7bbb5bb98d8cd3 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3662,8 +3662,10 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
-			      ~intel_pmu_large_pebs_flags(event)))
+			      ~intel_pmu_large_pebs_flags(event))) {
 				event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
+				event->attach_state |= PERF_ATTACH_SCHED_CB;
+			}
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
@@ -3676,6 +3678,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		ret = intel_pmu_setup_lbr_filter(event);
 		if (ret)
 			return ret;
+		event->attach_state |= PERF_ATTACH_SCHED_CB;
 
 		/*
 		 * BTS is set up earlier in this path, so don't account twice
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 50810d4714628c..32cf8287d4a773 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6580,8 +6580,8 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 	int i, nr_msrs;
 	struct perf_guest_switch_msr *msrs;
 
+	/* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */
 	msrs = perf_guest_get_msrs(&nr_msrs);
-
 	if (!msrs)
 		return;
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fab42cfbd35025..3f7f89ea5e512b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -606,6 +606,7 @@ struct swevent_hlist {
 #define PERF_ATTACH_TASK	0x04
 #define PERF_ATTACH_TASK_DATA	0x08
 #define PERF_ATTACH_ITRACE	0x10
+#define PERF_ATTACH_SCHED_CB	0x20
 
 struct perf_cgroup;
 struct perf_buffer;
@@ -872,6 +873,7 @@ struct perf_cpu_context {
 	struct list_head		cgrp_cpuctx_entry;
 #endif
 
+	struct list_head		sched_cb_entry;
 	int				sched_cb_usage;
 
 	int				online;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0aeca5f3c0acce..03db40f6cba904 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -386,6 +386,7 @@ static DEFINE_MUTEX(perf_sched_mutex);
 static atomic_t perf_sched_count;
 
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -3461,11 +3462,16 @@ unlock:
 	}
 }
 
+static DEFINE_PER_CPU(struct list_head, sched_cb_list);
+
 void perf_sched_cb_dec(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	--cpuctx->sched_cb_usage;
+	this_cpu_dec(perf_sched_cb_usages);
+
+	if (!--cpuctx->sched_cb_usage)
+		list_del(&cpuctx->sched_cb_entry);
 }
 
 
@@ -3473,7 +3479,10 @@ void perf_sched_cb_inc(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	cpuctx->sched_cb_usage++;
+	if (!cpuctx->sched_cb_usage++)
+		list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
+
+	this_cpu_inc(perf_sched_cb_usages);
 }
 
 /*
@@ -3502,6 +3511,24 @@ static void __perf_pmu_sched_task(struct perf_cpu_context *cpuctx, bool sched_in
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
+static void perf_pmu_sched_task(struct task_struct *prev,
+				struct task_struct *next,
+				bool sched_in)
+{
+	struct perf_cpu_context *cpuctx;
+
+	if (prev == next)
+		return;
+
+	list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
+		/* will be handled in perf_event_context_sched_in/out */
+		if (cpuctx->task_ctx)
+			continue;
+
+		__perf_pmu_sched_task(cpuctx, sched_in);
+	}
+}
+
 static void perf_event_switch(struct task_struct *task,
 			      struct task_struct *next_prev, bool sched_in);
 
@@ -3524,6 +3551,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(task, next, false);
+
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, next, false);
 
@@ -3832,6 +3862,9 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, prev, true);
+
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(prev, task, true);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -4656,7 +4689,7 @@ static void unaccount_event(struct perf_event *event)
 	if (event->parent)
 		return;
 
-	if (event->attach_state & PERF_ATTACH_TASK)
+	if (event->attach_state & (PERF_ATTACH_TASK | PERF_ATTACH_SCHED_CB))
 		dec = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_dec(&nr_mmap_events);
@@ -11175,7 +11208,7 @@ static void account_event(struct perf_event *event)
 	if (event->parent)
 		return;
 
-	if (event->attach_state & PERF_ATTACH_TASK)
+	if (event->attach_state & (PERF_ATTACH_TASK | PERF_ATTACH_SCHED_CB))
 		inc = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_inc(&nr_mmap_events);
@@ -12972,6 +13005,7 @@ static void __init perf_event_init_all_cpus(void)
 #ifdef CONFIG_CGROUP_PERF
 		INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
 #endif
+		INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
 	}
 }