1 files changed, 119 insertions, 50 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index e3589c4287cb..5d4a54f50826 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -966,22 +966,20 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 {
 	struct perf_cgroup *cgrp;
 	struct cgroup_subsys_state *css;
-	struct fd f = fdget(fd);
+	CLASS(fd, f)(fd);
 	int ret = 0;
 
-	if (!fd_file(f))
+	if (fd_empty(f))
 		return -EBADF;
 
 	css = css_tryget_online_from_dir(fd_file(f)->f_path.dentry,
 					 &perf_event_cgrp_subsys);
-	if (IS_ERR(css)) {
-		ret = PTR_ERR(css);
-		goto out;
-	}
+	if (IS_ERR(css))
+		return PTR_ERR(css);
 
 	ret = perf_cgroup_ensure_storage(event, css);
 	if (ret)
-		goto out;
+		return ret;
 
 	cgrp = container_of(css, struct perf_cgroup, css);
 	event->cgrp = cgrp;
@@ -995,8 +993,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 		perf_detach_cgroup(event);
 		ret = -EINVAL;
 	}
-out:
-	fdput(f);
 	return ret;
 }
 
@@ -2146,7 +2142,7 @@ static void perf_put_aux_event(struct perf_event *event)
 
 static bool perf_need_aux_event(struct perf_event *event)
 {
-	return !!event->attr.aux_output || !!event->attr.aux_sample_size;
+	return event->attr.aux_output || has_aux_action(event);
 }
 
 static int perf_get_aux_event(struct perf_event *event,
@@ -2171,6 +2167,10 @@ static int perf_get_aux_event(struct perf_event *event,
 	    !perf_aux_output_match(event, group_leader))
 		return 0;
 
+	if ((event->attr.aux_pause || event->attr.aux_resume) &&
+	    !(group_leader->pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
+		return 0;
+
 	if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux)
 		return 0;
 
@@ -5998,18 +5998,9 @@ EXPORT_SYMBOL_GPL(perf_event_period);
 
 static const struct file_operations perf_fops;
 
-static inline int perf_fget_light(int fd, struct fd *p)
+static inline bool is_perf_file(struct fd f)
 {
-	struct fd f = fdget(fd);
-	if (!fd_file(f))
-		return -EBADF;
-
-	if (fd_file(f)->f_op != &perf_fops) {
-		fdput(f);
-		return -EBADF;
-	}
-	*p = f;
-	return 0;
+	return !fd_empty(f) && fd_file(f)->f_op == &perf_fops;
 }
 
 static int perf_event_set_output(struct perf_event *event,
@@ -6057,20 +6048,14 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 
 	case PERF_EVENT_IOC_SET_OUTPUT:
 	{
-		int ret;
+		CLASS(fd, output)(arg);	     // arg == -1 => empty
+		struct perf_event *output_event = NULL;
 		if (arg != -1) {
-			struct perf_event *output_event;
-			struct fd output;
-			ret = perf_fget_light(arg, &output);
-			if (ret)
-				return ret;
+			if (!is_perf_file(output))
+				return -EBADF;
 			output_event = fd_file(output)->private_data;
-			ret = perf_event_set_output(event, output_event);
-			fdput(output);
-		} else {
-			ret = perf_event_set_output(event, NULL);
 		}
-		return ret;
+		return perf_event_set_output(event, output_event);
 	}
 
 	case PERF_EVENT_IOC_SET_FILTER:
@@ -7022,6 +7007,29 @@ void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
 EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
 #endif
 
+static bool should_sample_guest(struct perf_event *event)
+{
+	return !event->attr.exclude_guest && perf_guest_state();
+}
+
+unsigned long perf_misc_flags(struct perf_event *event,
+			      struct pt_regs *regs)
+{
+	if (should_sample_guest(event))
+		return perf_arch_guest_misc_flags(regs);
+
+	return perf_arch_misc_flags(regs);
+}
+
+unsigned long perf_instruction_pointer(struct perf_event *event,
+				       struct pt_regs *regs)
+{
+	if (should_sample_guest(event))
+		return perf_guest_get_ip();
+
+	return perf_arch_instruction_pointer(regs);
+}
+
 static void
 perf_output_sample_regs(struct perf_output_handle *handle,
 			struct pt_regs *regs, u64 mask)
@@ -7839,7 +7847,7 @@ void perf_prepare_sample(struct perf_sample_data *data,
 	__perf_event_header__init_id(data, event, filtered_sample_type);
 
 	if (filtered_sample_type & PERF_SAMPLE_IP) {
-		data->ip = perf_instruction_pointer(regs);
+		data->ip = perf_instruction_pointer(event, regs);
 		data->sample_flags |= PERF_SAMPLE_IP;
 	}
 
@@ -8003,7 +8011,7 @@ void perf_prepare_header(struct perf_event_header *header,
 {
 	header->type = PERF_RECORD_SAMPLE;
 	header->size = perf_sample_data_size(data, event);
-	header->misc = perf_misc_flags(regs);
+	header->misc = perf_misc_flags(event, regs);
 
 	/*
 	 * If you're adding more sample types here, you likely need to do
@@ -8016,6 +8024,49 @@ void perf_prepare_header(struct perf_event_header *header,
 	WARN_ON_ONCE(header->size & 7);
 }
 
+static void __perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+	if (pause) {
+		if (!event->hw.aux_paused) {
+			event->hw.aux_paused = 1;
+			event->pmu->stop(event, PERF_EF_PAUSE);
+		}
+	} else {
+		if (event->hw.aux_paused) {
+			event->hw.aux_paused = 0;
+			event->pmu->start(event, PERF_EF_RESUME);
+		}
+	}
+}
+
+static void perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+	struct perf_buffer *rb;
+
+	if (WARN_ON_ONCE(!event))
+		return;
+
+	rb = ring_buffer_get(event);
+	if (!rb)
+		return;
+
+	scoped_guard (irqsave) {
+		/*
+		 * Guard against self-recursion here. Another event could trip
+		 * this same from NMI context.
+		 */
+		if (READ_ONCE(rb->aux_in_pause_resume))
+			break;
+
+		WRITE_ONCE(rb->aux_in_pause_resume, 1);
+		barrier();
+		__perf_event_aux_pause(event, pause);
+		barrier();
+		WRITE_ONCE(rb->aux_in_pause_resume, 0);
+	}
+	ring_buffer_put(rb);
+}
+
 static __always_inline int
 __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
@@ -9251,7 +9302,7 @@ static void perf_event_switch(struct task_struct *task,
 		},
 	};
 
-	if (!sched_in && task->on_rq) {
+	if (!sched_in && task_is_runnable(task)) {
 		switch_event.event_id.header.misc |=
 				PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
 	}
@@ -9818,9 +9869,12 @@ static int __perf_event_overflow(struct perf_event *event,
 
 	ret = __perf_event_account_interrupt(event, throttle);
 
+	if (event->attr.aux_pause)
+		perf_event_aux_pause(event->aux_event, true);
+
 	if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT &&
 	    !bpf_overflow_handler(event, data, regs))
-		return ret;
+		goto out;
 
 	/*
 	 * XXX event_limit might not quite work as expected on inherited
@@ -9882,6 +9936,9 @@ static int __perf_event_overflow(struct perf_event *event,
 		event->pending_wakeup = 1;
 		irq_work_queue(&event->pending_irq);
 	}
+out:
+	if (event->attr.aux_resume)
+		perf_event_aux_pause(event->aux_event, false);
 
 	return ret;
 }
@@ -12273,11 +12330,25 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	}
 
 	if (event->attr.aux_output &&
-	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+	    (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
+	     event->attr.aux_pause || event->attr.aux_resume)) {
 		err = -EOPNOTSUPP;
 		goto err_pmu;
 	}
 
+	if (event->attr.aux_pause && event->attr.aux_resume) {
+		err = -EINVAL;
+		goto err_pmu;
+	}
+
+	if (event->attr.aux_start_paused) {
+		if (!(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
+			err = -EOPNOTSUPP;
+			goto err_pmu;
+		}
+		event->hw.aux_paused = 1;
+	}
+
 	if (cgroup_fd != -1) {
 		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
 		if (err)
@@ -12664,7 +12735,6 @@ SYSCALL_DEFINE5(perf_event_open,
 	struct perf_event_attr attr;
 	struct perf_event_context *ctx;
 	struct file *event_file = NULL;
-	struct fd group = EMPTY_FD;
 	struct task_struct *task = NULL;
 	struct pmu *pmu;
 	int event_fd;
@@ -12735,10 +12805,12 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (event_fd < 0)
 		return event_fd;
 
+	CLASS(fd, group)(group_fd);     // group_fd == -1 => empty
 	if (group_fd != -1) {
-		err = perf_fget_light(group_fd, &group);
-		if (err)
+		if (!is_perf_file(group)) {
+			err = -EBADF;
 			goto err_fd;
+		}
 		group_leader = fd_file(group)->private_data;
 		if (flags & PERF_FLAG_FD_OUTPUT)
 			output_event = group_leader;
@@ -12750,7 +12822,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		task = find_lively_task_by_vpid(pid);
 		if (IS_ERR(task)) {
 			err = PTR_ERR(task);
-			goto err_group_fd;
+			goto err_fd;
 		}
 	}
 
@@ -13017,12 +13089,11 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&current->perf_event_mutex);
 
 	/*
-	 * Drop the reference on the group_event after placing the
-	 * new event on the sibling_list. This ensures destruction
-	 * of the group leader will find the pointer to itself in
-	 * perf_group_detach().
+	 * File reference in group guarantees that group_leader has been
+	 * kept alive until we place the new event on the sibling_list.
+	 * This ensures destruction of the group leader will find
+	 * the pointer to itself in perf_group_detach().
 	 */
-	fdput(group);
 	fd_install(event_fd, event_file);
 	return event_fd;
 
@@ -13041,8 +13112,6 @@ err_alloc:
 err_task:
 	if (task)
 		put_task_struct(task);
-err_group_fd:
-	fdput(group);
 err_fd:
 	put_unused_fd(event_fd);
 	return err;
@@ -13073,7 +13142,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	 * Grouping is not supported for kernel events, neither is 'AUX',
 	 * make sure the caller's intentions are adjusted.
 	 */
-	if (attr->aux_output)
+	if (attr->aux_output || attr->aux_action)
 		return ERR_PTR(-EINVAL);
 
 	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
@@ -13959,7 +14028,7 @@ static void perf_event_clear_cpumask(unsigned int cpu)
 	}
 
 	/* migrate */
-	list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) {
+	list_for_each_entry(pmu, &pmus, entry) {
 		if (pmu->scope == PERF_PMU_SCOPE_NONE ||
 		    WARN_ON_ONCE(pmu->scope >= PERF_PMU_MAX_SCOPE))
 			continue;