1 files changed, 241 insertions, 51 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1087bbeb152b..8ca0ab9faaa4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -175,8 +175,13 @@ static struct srcu_struct pmus_srcu;
  *   0 - disallow raw tracepoint access for unpriv
  *   1 - disallow cpu events for unpriv
  *   2 - disallow kernel profiling for unpriv
+ *   3 - disallow all unpriv perf event use
  */
+#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT
+int sysctl_perf_event_paranoid __read_mostly = 3;
+#else
 int sysctl_perf_event_paranoid __read_mostly = 1;
+#endif
 
 /* Minimum for 512 kiB + 1 user control page */
 int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
@@ -946,6 +951,7 @@ static void put_ctx(struct perf_event_context *ctx)
  * function.
  *
  * Lock order:
+ *    cred_guard_mutex
  *	task_struct::perf_event_mutex
  *	  perf_event_context::mutex
  *	    perf_event_context::lock
@@ -1538,12 +1544,33 @@ static int __init perf_workqueue_init(void)
 
 core_initcall(perf_workqueue_init);
 
-static inline int pmu_filter_match(struct perf_event *event)
+static inline int __pmu_filter_match(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
 	return pmu->filter_match ? pmu->filter_match(event) : 1;
 }
 
+/*
+ * Check whether we should attempt to schedule an event group based on
+ * PMU-specific filtering. An event group can consist of HW and SW events,
+ * potentially with a SW leader, so we must check all the filters, to
+ * determine whether a group is schedulable:
+ */
+static inline int pmu_filter_match(struct perf_event *event)
+{
+	struct perf_event *child;
+
+	if (!__pmu_filter_match(event))
+		return 0;
+
+	list_for_each_entry(child, &event->sibling_list, group_entry) {
+		if (!__pmu_filter_match(child))
+			return 0;
+	}
+
+	return 1;
+}
+
 static inline int
 event_filter_match(struct perf_event *event)
 {
@@ -1580,14 +1607,14 @@ event_sched_out(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
+	event->tstamp_stopped = tstamp;
+	event->pmu->del(event, 0);
+	event->oncpu = -1;
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-	event->tstamp_stopped = tstamp;
-	event->pmu->del(event, 0);
-	event->oncpu = -1;
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu--;
@@ -1884,8 +1911,13 @@ event_sched_in(struct perf_event *event,
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
 
-	event->state = PERF_EVENT_STATE_ACTIVE;
-	event->oncpu = smp_processor_id();
+	WRITE_ONCE(event->oncpu, smp_processor_id());
+	/*
+	 * Order event::oncpu write to happen before the ACTIVE state
+	 * is visible.
+	 */
+	smp_wmb();
+	WRITE_ONCE(event->state, PERF_EVENT_STATE_ACTIVE);
 
 	/*
 	 * Unthrottle events, since we scheduled we might have missed several
@@ -2366,6 +2398,29 @@ void perf_event_enable(struct perf_event *event)
 }
 EXPORT_SYMBOL_GPL(perf_event_enable);
 
+static int __perf_event_stop(void *info)
+{
+	struct perf_event *event = info;
+
+	/* for AUX events, our job is done if the event is already inactive */
+	if (READ_ONCE(event->state) != PERF_EVENT_STATE_ACTIVE)
+		return 0;
+
+	/* matches smp_wmb() in event_sched_in() */
+	smp_rmb();
+
+	/*
+	 * There is a window with interrupts enabled before we get here,
+	 * so we need to check again lest we try to stop another CPU's event.
+	 */
+	if (READ_ONCE(event->oncpu) != smp_processor_id())
+		return -EAGAIN;
+
+	event->pmu->stop(event, PERF_EF_UPDATE);
+
+	return 0;
+}
+
 static int _perf_event_refresh(struct perf_event *event, int refresh)
 {
 	/*
@@ -3418,7 +3473,6 @@ static struct task_struct *
 find_lively_task_by_vpid(pid_t vpid)
 {
 	struct task_struct *task;
-	int err;
 
 	rcu_read_lock();
 	if (!vpid)
@@ -3432,16 +3486,7 @@ find_lively_task_by_vpid(pid_t vpid)
 	if (!task)
 		return ERR_PTR(-ESRCH);
 
-	/* Reuse ptrace permission checks for now. */
-	err = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
-		goto errout;
-
 	return task;
-errout:
-	put_task_struct(task);
-	return ERR_PTR(err);
-
 }
 
 /*
@@ -3701,6 +3746,9 @@ static void __free_event(struct perf_event *event)
 	if (event->destroy)
 		event->destroy(event);
 
+	if (event->pmu->free_drv_configs)
+		event->pmu->free_drv_configs(event);
+
 	if (event->ctx)
 		put_ctx(event->ctx);
 
@@ -4253,6 +4301,8 @@ static int perf_event_set_output(struct perf_event *event,
 				 struct perf_event *output_event);
 static int perf_event_set_filter(struct perf_event *event, void __user *arg);
 static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd);
+static int perf_event_drv_configs(struct perf_event *event,
+				  void __user *arg);
 
 static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg)
 {
@@ -4309,6 +4359,9 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 	case PERF_EVENT_IOC_SET_BPF:
 		return perf_event_set_bpf_prog(event, arg);
 
+	case PERF_EVENT_IOC_SET_DRV_CONFIGS:
+		return perf_event_drv_configs(event, (void __user *)arg);
+
 	default:
 		return -ENOTTY;
 	}
@@ -4341,6 +4394,7 @@ static long perf_compat_ioctl(struct file *file, unsigned int cmd,
 	switch (_IOC_NR(cmd)) {
 	case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
 	case _IOC_NR(PERF_EVENT_IOC_ID):
+	case _IOC_NR(PERF_EVENT_IOC_SET_DRV_CONFIGS):
 		/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
 		if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
 			cmd &= ~IOCSIZE_MASK;
@@ -4625,6 +4679,8 @@ static void perf_mmap_open(struct vm_area_struct *vma)
 		event->pmu->event_mapped(event);
 }
 
+static void perf_pmu_output_stop(struct perf_event *event);
+
 /*
  * A buffer can be mmap()ed multiple times; either directly through the same
  * event, or through other events by use of perf_event_set_output().
@@ -4652,10 +4708,22 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	 */
 	if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff &&
 	    atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) {
+		/*
+		 * Stop all AUX events that are writing to this buffer,
+		 * so that we can free its AUX pages and corresponding PMU
+		 * data. Note that after rb::aux_mmap_count dropped to zero,
+		 * they won't start any more (see perf_aux_output_begin()).
+		 */
+		perf_pmu_output_stop(event);
+
+		/* now it's safe to free the pages */
 		atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
 		vma->vm_mm->pinned_vm -= rb->aux_mmap_locked;
 
+		/* this has to be the last one */
 		rb_free_aux(rb);
+		WARN_ON_ONCE(atomic_read(&rb->aux_refcount));
+
 		mutex_unlock(&event->mmap_mutex);
 	}
 
@@ -5726,6 +5794,80 @@ next:
 	rcu_read_unlock();
 }
 
+struct remote_output {
+	struct ring_buffer	*rb;
+	int			err;
+};
+
+static void __perf_event_output_stop(struct perf_event *event, void *data)
+{
+	struct perf_event *parent = event->parent;
+	struct remote_output *ro = data;
+	struct ring_buffer *rb = ro->rb;
+
+	if (!has_aux(event))
+		return;
+
+	if (!parent)
+		parent = event;
+
+	/*
+	 * In case of inheritance, it will be the parent that links to the
+	 * ring-buffer, but it will be the child that's actually using it:
+	 */
+	if (rcu_dereference(parent->rb) == rb)
+		ro->err = __perf_event_stop(event);
+}
+
+static int __perf_pmu_output_stop(void *info)
+{
+	struct perf_event *event = info;
+	struct pmu *pmu = event->pmu;
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+	struct remote_output ro = {
+		.rb	= event->rb,
+	};
+
+	rcu_read_lock();
+	perf_event_aux_ctx(&cpuctx->ctx, __perf_event_output_stop, &ro);
+	if (cpuctx->task_ctx)
+		perf_event_aux_ctx(cpuctx->task_ctx, __perf_event_output_stop,
+				   &ro);
+	rcu_read_unlock();
+
+	return ro.err;
+}
+
+static void perf_pmu_output_stop(struct perf_event *event)
+{
+	struct perf_event *iter;
+	int err, cpu;
+
+restart:
+	rcu_read_lock();
+	list_for_each_entry_rcu(iter, &event->rb->event_list, rb_entry) {
+		/*
+		 * For per-CPU events, we need to make sure that neither they
+		 * nor their children are running; for cpu==-1 events it's
+		 * sufficient to stop the event itself if it's active, since
+		 * it can't have children.
+		 */
+		cpu = iter->cpu;
+		if (cpu == -1)
+			cpu = READ_ONCE(iter->oncpu);
+
+		if (cpu == -1)
+			continue;
+
+		err = cpu_function_call(cpu, __perf_pmu_output_stop, event);
+		if (err == -EAGAIN) {
+			rcu_read_unlock();
+			goto restart;
+		}
+	}
+	rcu_read_unlock();
+}
+
 /*
  * task tracking -- fork/exit
  *
@@ -6027,6 +6169,27 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	char *buf = NULL;
 	char *name;
 
+	if (vma->vm_flags & VM_READ)
+		prot |= PROT_READ;
+	if (vma->vm_flags & VM_WRITE)
+		prot |= PROT_WRITE;
+	if (vma->vm_flags & VM_EXEC)
+		prot |= PROT_EXEC;
+
+	if (vma->vm_flags & VM_MAYSHARE)
+		flags = MAP_SHARED;
+	else
+		flags = MAP_PRIVATE;
+
+	if (vma->vm_flags & VM_DENYWRITE)
+		flags |= MAP_DENYWRITE;
+	if (vma->vm_flags & VM_MAYEXEC)
+		flags |= MAP_EXECUTABLE;
+	if (vma->vm_flags & VM_LOCKED)
+		flags |= MAP_LOCKED;
+	if (vma->vm_flags & VM_HUGETLB)
+		flags |= MAP_HUGETLB;
+
 	if (file) {
 		struct inode *inode;
 		dev_t dev;
@@ -6053,27 +6216,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		maj = MAJOR(dev);
 		min = MINOR(dev);
 
-		if (vma->vm_flags & VM_READ)
-			prot |= PROT_READ;
-		if (vma->vm_flags & VM_WRITE)
-			prot |= PROT_WRITE;
-		if (vma->vm_flags & VM_EXEC)
-			prot |= PROT_EXEC;
-
-		if (vma->vm_flags & VM_MAYSHARE)
-			flags = MAP_SHARED;
-		else
-			flags = MAP_PRIVATE;
-
-		if (vma->vm_flags & VM_DENYWRITE)
-			flags |= MAP_DENYWRITE;
-		if (vma->vm_flags & VM_MAYEXEC)
-			flags |= MAP_EXECUTABLE;
-		if (vma->vm_flags & VM_LOCKED)
-			flags |= MAP_LOCKED;
-		if (vma->vm_flags & VM_HUGETLB)
-			flags |= MAP_HUGETLB;
-
 		goto got_name;
 	} else {
 		if (vma->vm_ops && vma->vm_ops->name) {
@@ -7110,7 +7252,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 	prog = event->tp_event->prog;
 	if (prog) {
 		event->tp_event->prog = NULL;
-		bpf_prog_put(prog);
+		bpf_prog_put_rcu(prog);
 	}
 }
 
@@ -7152,6 +7294,15 @@ void perf_bp_event(struct perf_event *bp, void *data)
 }
 #endif
 
+static int perf_event_drv_configs(struct perf_event *event,
+				  void __user *arg)
+{
+	if (!event->pmu->get_drv_configs)
+		return -EINVAL;
+
+	return event->pmu->get_drv_configs(event, arg);
+}
+
 /*
  * hrtimer based swevent callback
  */
@@ -7888,6 +8039,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->sibling_list);
 	INIT_LIST_HEAD(&event->rb_entry);
 	INIT_LIST_HEAD(&event->active_entry);
+	INIT_LIST_HEAD(&event->drv_configs);
 	INIT_HLIST_NODE(&event->hlist_entry);
 
 
@@ -7979,6 +8131,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		}
 	}
 
+	/* symmetric to unaccount_event() in _free_event() */
+	account_event(event);
+
 	return event;
 
 err_per_task:
@@ -8265,6 +8420,9 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
+	if (perf_paranoid_any() && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	err = perf_copy_attr(attr_uptr, &attr);
 	if (err)
 		return err;
@@ -8325,6 +8483,24 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	get_online_cpus();
 
+	if (task) {
+		err = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
+		if (err)
+			goto err_cpus;
+
+		/*
+		 * Reuse ptrace permission checks for now.
+		 *
+		 * We must hold cred_guard_mutex across this and any potential
+		 * perf_install_in_context() call for this new event to
+		 * serialize against exec() altering our credentials (and the
+		 * perf_event_exit_task() that could imply).
+		 */
+		err = -EACCES;
+		if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+			goto err_cred;
+	}
+
 	if (flags & PERF_FLAG_PID_CGROUP)
 		cgroup_fd = pid;
 
@@ -8332,7 +8508,7 @@ SYSCALL_DEFINE5(perf_event_open,
 				 NULL, NULL, cgroup_fd);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
-		goto err_cpus;
+		goto err_cred;
 	}
 
 	if (is_sampling_event(event)) {
@@ -8342,8 +8518,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
-	account_event(event);
-
 	/*
 	 * Special case software events and allow them to be part of
 	 * any hardware group.
@@ -8393,11 +8567,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_context;
 	}
 
-	if (task) {
-		put_task_struct(task);
-		task = NULL;
-	}
-
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
@@ -8456,6 +8625,7 @@ SYSCALL_DEFINE5(perf_event_open,
 					f_flags);
 	if (IS_ERR(event_file)) {
 		err = PTR_ERR(event_file);
+		event_file = NULL;
 		goto err_context;
 	}
 
@@ -8485,6 +8655,11 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 
+	/*
+	 * This is the point on no return; we cannot fail hereafter. This is
+	 * where we start modifying current state.
+	 */
+
 	if (move_group) {
 		/*
 		 * See perf_event_ctx_lock() for comments on the details
@@ -8554,6 +8729,11 @@ SYSCALL_DEFINE5(perf_event_open,
 		mutex_unlock(&gctx->mutex);
 	mutex_unlock(&ctx->mutex);
 
+	if (task) {
+		mutex_unlock(&task->signal->cred_guard_mutex);
+		put_task_struct(task);
+	}
+
 	put_online_cpus();
 
 	event->owner = current;
@@ -8582,7 +8762,15 @@ err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
-	free_event(event);
+	/*
+	 * If event_file is set, the fput() above will have called ->release()
+	 * and that will take care of freeing the event.
+	 */
+	if (!event_file)
+		free_event(event);
+err_cred:
+	if (task)
+		mutex_unlock(&task->signal->cred_guard_mutex);
 err_cpus:
 	put_online_cpus();
 err_task:
@@ -8626,8 +8814,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	/* Mark owner so we could distinguish it from user events. */
 	event->owner = EVENT_OWNER_KERNEL;
 
-	account_event(event);
-
 	ctx = find_get_context(event->pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
@@ -8864,6 +9050,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 
 /*
  * When a child task exits, feed back event values to parent events.
+ *
+ * Can be called with cred_guard_mutex held when called from
+ * install_exec_creds().
  */
 void perf_event_exit_task(struct task_struct *child)
 {
@@ -9185,7 +9374,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	/*
@@ -9201,7 +9390,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
@@ -9229,6 +9418,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 	}
 
 	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+out_unlock:
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);