Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 199 insertions, 157 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4082d0161b..b2a6aec118 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2284,26 +2284,24 @@ event_sched_out(struct perf_event *event, struct perf_event_context *ctx)
 	}
 
 	if (event->pending_sigtrap) {
-		bool dec = true;
-
 		event->pending_sigtrap = 0;
 		if (state != PERF_EVENT_STATE_OFF &&
-		    !event->pending_work) {
+		    !event->pending_work &&
+		    !task_work_add(current, &event->pending_task, TWA_RESUME)) {
 			event->pending_work = 1;
-			dec = false;
-			WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount));
-			task_work_add(current, &event->pending_task, TWA_RESUME);
-		}
-		if (dec)
+		} else {
 			local_dec(&event->ctx->nr_pending);
+		}
 	}
 
 	perf_event_set_state(event, state);
 
 	if (!is_software_event(event))
 		cpc->active_oncpu--;
-	if (event->attr.freq && event->attr.sample_freq)
+	if (event->attr.freq && event->attr.sample_freq) {
 		ctx->nr_freq--;
+		epc->nr_freq--;
+	}
 	if (event->attr.exclusive || !cpc->active_oncpu)
 		cpc->exclusive = 0;
 
@@ -2558,9 +2556,10 @@ event_sched_in(struct perf_event *event, struct perf_event_context *ctx)
 
 	if (!is_software_event(event))
 		cpc->active_oncpu++;
-	if (event->attr.freq && event->attr.sample_freq)
+	if (event->attr.freq && event->attr.sample_freq) {
 		ctx->nr_freq++;
-
+		epc->nr_freq++;
+	}
 	if (event->attr.exclusive)
 		cpc->exclusive = 1;
 
@@ -4123,30 +4122,14 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count, bo
 	}
 }
 
-/*
- * combine freq adjustment with unthrottling to avoid two passes over the
- * events. At the same time, make sure, having freq events does not change
- * the rate of unthrottling as that would introduce bias.
- */
-static void
-perf_adjust_freq_unthr_context(struct perf_event_context *ctx, bool unthrottle)
+static void perf_adjust_freq_unthr_events(struct list_head *event_list)
 {
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	u64 now, period = TICK_NSEC;
 	s64 delta;
 
-	/*
-	 * only need to iterate over all events iff:
-	 * - context have events in frequency mode (needs freq adjust)
-	 * - there are events to unthrottle on this cpu
-	 */
-	if (!(ctx->nr_freq || unthrottle))
-		return;
-
-	raw_spin_lock(&ctx->lock);
-
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+	list_for_each_entry(event, event_list, active_list) {
 		if (event->state != PERF_EVENT_STATE_ACTIVE)
 			continue;
 
@@ -4154,18 +4137,17 @@ perf_adjust_freq_unthr_context(struct perf_event_context *ctx, bool unthrottle)
 		if (!event_filter_match(event))
 			continue;
 
-		perf_pmu_disable(event->pmu);
-
 		hwc = &event->hw;
 
 		if (hwc->interrupts == MAX_INTERRUPTS) {
 			hwc->interrupts = 0;
 			perf_log_throttle(event, 1);
-			event->pmu->start(event, 0);
+			if (!event->attr.freq || !event->attr.sample_freq)
+				event->pmu->start(event, 0);
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
-			goto next;
+			continue;
 
 		/*
 		 * stop the event and update event->count
@@ -4187,8 +4169,41 @@ perf_adjust_freq_unthr_context(struct perf_event_context *ctx, bool unthrottle)
 			perf_adjust_period(event, period, delta, false);
 
 		event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
-	next:
-		perf_pmu_enable(event->pmu);
+	}
+}
+
+/*
+ * combine freq adjustment with unthrottling to avoid two passes over the
+ * events. At the same time, make sure, having freq events does not change
+ * the rate of unthrottling as that would introduce bias.
+ */
+static void
+perf_adjust_freq_unthr_context(struct perf_event_context *ctx, bool unthrottle)
+{
+	struct perf_event_pmu_context *pmu_ctx;
+
+	/*
+	 * only need to iterate over all events iff:
+	 * - context have events in frequency mode (needs freq adjust)
+	 * - there are events to unthrottle on this cpu
+	 */
+	if (!(ctx->nr_freq || unthrottle))
+		return;
+
+	raw_spin_lock(&ctx->lock);
+
+	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+		if (!(pmu_ctx->nr_freq || unthrottle))
+			continue;
+		if (!perf_pmu_ctx_is_active(pmu_ctx))
+			continue;
+		if (pmu_ctx->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT)
+			continue;
+
+		perf_pmu_disable(pmu_ctx->pmu);
+		perf_adjust_freq_unthr_events(&pmu_ctx->pinned_active);
+		perf_adjust_freq_unthr_events(&pmu_ctx->flexible_active);
+		perf_pmu_enable(pmu_ctx->pmu);
 	}
 
 	raw_spin_unlock(&ctx->lock);
@@ -5187,9 +5202,35 @@ static bool exclusive_event_installable(struct perf_event *event,
 static void perf_addr_filters_splice(struct perf_event *event,
 				       struct list_head *head);
 
+static void perf_pending_task_sync(struct perf_event *event)
+{
+	struct callback_head *head = &event->pending_task;
+
+	if (!event->pending_work)
+		return;
+	/*
+	 * If the task is queued to the current task's queue, we
+	 * obviously can't wait for it to complete. Simply cancel it.
+	 */
+	if (task_work_cancel(current, head)) {
+		event->pending_work = 0;
+		local_dec(&event->ctx->nr_pending);
+		return;
+	}
+
+	/*
+	 * All accesses related to the event are within the same
+	 * non-preemptible section in perf_pending_task(). The RCU
+	 * grace period before the event is freed will make sure all
+	 * those accesses are complete by then.
+	 */
+	rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE);
+}
+
 static void _free_event(struct perf_event *event)
 {
 	irq_work_sync(&event->pending_irq);
+	perf_pending_task_sync(event);
 
 	unaccount_event(event);
 
@@ -6490,6 +6531,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			return -EINVAL;
 
 		nr_pages = vma_size / PAGE_SIZE;
+		if (nr_pages > INT_MAX)
+			return -ENOMEM;
 
 		mutex_lock(&event->mmap_mutex);
 		ret = -EINVAL;
@@ -6697,14 +6740,6 @@ static const struct file_operations perf_fops = {
  * to user-space before waking everybody up.
  */
 
-static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
-{
-	/* only the parent has fasync state */
-	if (event->parent)
-		event = event->parent;
-	return &event->fasync;
-}
-
 void perf_event_wakeup(struct perf_event *event)
 {
 	ring_buffer_wakeup(event);
@@ -6821,23 +6856,27 @@ static void perf_pending_task(struct callback_head *head)
 	int rctx;
 
 	/*
+	 * All accesses to the event must belong to the same implicit RCU read-side
+	 * critical section as the ->pending_work reset. See comment in
+	 * perf_pending_task_sync().
+	 */
+	preempt_disable_notrace();
+	/*
 	 * If we 'fail' here, that's OK, it means recursion is already disabled
 	 * and we won't recurse 'further'.
 	 */
-	preempt_disable_notrace();
 	rctx = perf_swevent_get_recursion_context();
 
 	if (event->pending_work) {
 		event->pending_work = 0;
 		perf_sigtrap(event);
 		local_dec(&event->ctx->nr_pending);
+		rcuwait_wake_up(&event->pending_work_wait);
 	}
 
 	if (rctx >= 0)
 		perf_swevent_put_recursion_context(rctx);
 	preempt_enable_notrace();
-
-	put_event(event);
 }
 
 #ifdef CONFIG_GUEST_PERF_EVENTS
@@ -7552,7 +7591,7 @@ static u64 perf_get_pgtable_size(struct mm_struct *mm, unsigned long addr)
 {
 	u64 size = 0;
 
-#ifdef CONFIG_HAVE_FAST_GUP
+#ifdef CONFIG_HAVE_GUP_FAST
 	pgd_t *pgdp, pgd;
 	p4d_t *p4dp, p4d;
 	pud_t *pudp, pud;
@@ -7600,7 +7639,7 @@ again:
 	if (pte_present(pte))
 		size = pte_leaf_size(pte);
 	pte_unmap(ptep);
-#endif /* CONFIG_HAVE_FAST_GUP */
+#endif /* CONFIG_HAVE_GUP_FAST */
 
 	return size;
 }
@@ -9291,21 +9330,19 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
 	bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
 	int i;
 
-	if (prog->aux->func_cnt == 0) {
-		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
-				   (u64)(unsigned long)prog->bpf_func,
-				   prog->jited_len, unregister,
-				   prog->aux->ksym.name);
-	} else {
-		for (i = 0; i < prog->aux->func_cnt; i++) {
-			struct bpf_prog *subprog = prog->aux->func[i];
-
-			perf_event_ksymbol(
-				PERF_RECORD_KSYMBOL_TYPE_BPF,
-				(u64)(unsigned long)subprog->bpf_func,
-				subprog->jited_len, unregister,
-				subprog->aux->ksym.name);
-		}
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
+			   (u64)(unsigned long)prog->bpf_func,
+			   prog->jited_len, unregister,
+			   prog->aux->ksym.name);
+
+	for (i = 1; i < prog->aux->func_cnt; i++) {
+		struct bpf_prog *subprog = prog->aux->func[i];
+
+		perf_event_ksymbol(
+			PERF_RECORD_KSYMBOL_TYPE_BPF,
+			(u64)(unsigned long)subprog->bpf_func,
+			subprog->jited_len, unregister,
+			subprog->aux->ksym.name);
 	}
 }
 
@@ -9557,6 +9594,100 @@ static inline bool sample_is_allowed(struct perf_event *event, struct pt_regs *r
 	return true;
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+static int bpf_overflow_handler(struct perf_event *event,
+				struct perf_sample_data *data,
+				struct pt_regs *regs)
+{
+	struct bpf_perf_event_data_kern ctx = {
+		.data = data,
+		.event = event,
+	};
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	ctx.regs = perf_arch_bpf_user_pt_regs(regs);
+	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1))
+		goto out;
+	rcu_read_lock();
+	prog = READ_ONCE(event->prog);
+	if (prog) {
+		perf_prepare_sample(data, event, regs);
+		ret = bpf_prog_run(prog, &ctx);
+	}
+	rcu_read_unlock();
+out:
+	__this_cpu_dec(bpf_prog_active);
+
+	return ret;
+}
+
+static inline int perf_event_set_bpf_handler(struct perf_event *event,
+					     struct bpf_prog *prog,
+					     u64 bpf_cookie)
+{
+	if (event->overflow_handler_context)
+		/* hw breakpoint or kernel counter */
+		return -EINVAL;
+
+	if (event->prog)
+		return -EEXIST;
+
+	if (prog->type != BPF_PROG_TYPE_PERF_EVENT)
+		return -EINVAL;
+
+	if (event->attr.precise_ip &&
+	    prog->call_get_stack &&
+	    (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) ||
+	     event->attr.exclude_callchain_kernel ||
+	     event->attr.exclude_callchain_user)) {
+		/*
+		 * On perf_event with precise_ip, calling bpf_get_stack()
+		 * may trigger unwinder warnings and occasional crashes.
+		 * bpf_get_[stack|stackid] works around this issue by using
+		 * callchain attached to perf_sample_data. If the
+		 * perf_event does not full (kernel and user) callchain
+		 * attached to perf_sample_data, do not allow attaching BPF
+		 * program that calls bpf_get_[stack|stackid].
+		 */
+		return -EPROTO;
+	}
+
+	event->prog = prog;
+	event->bpf_cookie = bpf_cookie;
+	return 0;
+}
+
+static inline void perf_event_free_bpf_handler(struct perf_event *event)
+{
+	struct bpf_prog *prog = event->prog;
+
+	if (!prog)
+		return;
+
+	event->prog = NULL;
+	bpf_prog_put(prog);
+}
+#else
+static inline int bpf_overflow_handler(struct perf_event *event,
+				       struct perf_sample_data *data,
+				       struct pt_regs *regs)
+{
+	return 1;
+}
+
+static inline int perf_event_set_bpf_handler(struct perf_event *event,
+					     struct bpf_prog *prog,
+					     u64 bpf_cookie)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void perf_event_free_bpf_handler(struct perf_event *event)
+{
+}
+#endif
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -9577,6 +9708,9 @@ static int __perf_event_overflow(struct perf_event *event,
 
 	ret = __perf_event_account_interrupt(event, throttle);
 
+	if (event->prog && !bpf_overflow_handler(event, data, regs))
+		return ret;
+
 	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
@@ -10435,97 +10569,6 @@ static void perf_event_free_filter(struct perf_event *event)
 	ftrace_profile_free_filter(event);
 }
 
-#ifdef CONFIG_BPF_SYSCALL
-static void bpf_overflow_handler(struct perf_event *event,
-				 struct perf_sample_data *data,
-				 struct pt_regs *regs)
-{
-	struct bpf_perf_event_data_kern ctx = {
-		.data = data,
-		.event = event,
-	};
-	struct bpf_prog *prog;
-	int ret = 0;
-
-	ctx.regs = perf_arch_bpf_user_pt_regs(regs);
-	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1))
-		goto out;
-	rcu_read_lock();
-	prog = READ_ONCE(event->prog);
-	if (prog) {
-		perf_prepare_sample(data, event, regs);
-		ret = bpf_prog_run(prog, &ctx);
-	}
-	rcu_read_unlock();
-out:
-	__this_cpu_dec(bpf_prog_active);
-	if (!ret)
-		return;
-
-	event->orig_overflow_handler(event, data, regs);
-}
-
-static int perf_event_set_bpf_handler(struct perf_event *event,
-				      struct bpf_prog *prog,
-				      u64 bpf_cookie)
-{
-	if (event->overflow_handler_context)
-		/* hw breakpoint or kernel counter */
-		return -EINVAL;
-
-	if (event->prog)
-		return -EEXIST;
-
-	if (prog->type != BPF_PROG_TYPE_PERF_EVENT)
-		return -EINVAL;
-
-	if (event->attr.precise_ip &&
-	    prog->call_get_stack &&
-	    (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) ||
-	     event->attr.exclude_callchain_kernel ||
-	     event->attr.exclude_callchain_user)) {
-		/*
-		 * On perf_event with precise_ip, calling bpf_get_stack()
-		 * may trigger unwinder warnings and occasional crashes.
-		 * bpf_get_[stack|stackid] works around this issue by using
-		 * callchain attached to perf_sample_data. If the
-		 * perf_event does not full (kernel and user) callchain
-		 * attached to perf_sample_data, do not allow attaching BPF
-		 * program that calls bpf_get_[stack|stackid].
-		 */
-		return -EPROTO;
-	}
-
-	event->prog = prog;
-	event->bpf_cookie = bpf_cookie;
-	event->orig_overflow_handler = READ_ONCE(event->overflow_handler);
-	WRITE_ONCE(event->overflow_handler, bpf_overflow_handler);
-	return 0;
-}
-
-static void perf_event_free_bpf_handler(struct perf_event *event)
-{
-	struct bpf_prog *prog = event->prog;
-
-	if (!prog)
-		return;
-
-	WRITE_ONCE(event->overflow_handler, event->orig_overflow_handler);
-	event->prog = NULL;
-	bpf_prog_put(prog);
-}
-#else
-static int perf_event_set_bpf_handler(struct perf_event *event,
-				      struct bpf_prog *prog,
-				      u64 bpf_cookie)
-{
-	return -EOPNOTSUPP;
-}
-static void perf_event_free_bpf_handler(struct perf_event *event)
-{
-}
-#endif
-
 /*
  * returns true if the event is a tracepoint, or a kprobe/upprobe created
  * with perf_event_open()
@@ -11945,6 +11988,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending_irq, perf_pending_irq);
 	init_task_work(&event->pending_task, perf_pending_task);
+	rcuwait_init(&event->pending_work_wait);
 
 	mutex_init(&event->mmap_mutex);
 	raw_spin_lock_init(&event->addr_filters.lock);
@@ -11984,13 +12028,11 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		overflow_handler = parent_event->overflow_handler;
 		context = parent_event->overflow_handler_context;
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_EVENT_TRACING)
-		if (overflow_handler == bpf_overflow_handler) {
+		if (parent_event->prog) {
 			struct bpf_prog *prog = parent_event->prog;
 
 			bpf_prog_inc(prog);
 			event->prog = prog;
-			event->orig_overflow_handler =
-				parent_event->orig_overflow_handler;
 		}
 #endif
 	}