1 files changed, 157 insertions, 45 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index fb9b3b53febb..0006c492cd31 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -951,6 +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
@@ -1543,12 +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)
 {
@@ -3423,7 +3445,6 @@ static struct task_struct *
 find_lively_task_by_vpid(pid_t vpid)
 {
 	struct task_struct *task;
-	int err;
 
 	rcu_read_lock();
 	if (!vpid)
@@ -3437,16 +3458,7 @@ 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);
-
 }
 
 /*
@@ -6032,6 +6044,27 @@ 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;
@@ -6058,27 +6091,6 @@ 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) {
@@ -6403,6 +6415,21 @@ static void perf_log_itrace_start(struct perf_event *event)
 	perf_output_end(&handle);
 }
 
+static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+	/*
+	 * Due to interrupt latency (AKA "skid"), we may enter the
+	 * kernel before taking an overflow, even if the PMU is only
+	 * counting user events.
+	 * To avoid leaking information to userspace, we must always
+	 * reject kernel samples when exclude_kernel is set.
+	 */
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return false;
+
+	return true;
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -6450,6 +6477,12 @@ static int __perf_event_overflow(struct perf_event *event,
 	}
 
 	/*
+	 * For security, drop the skid kernel samples if necessary.
+	 */
+	if (!sample_is_allowed(event, regs))
+		return ret;
+
+	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */
@@ -7115,7 +7148,7 @@ 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);
 	}
 }
 
@@ -8243,6 +8276,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
 	return 0;
 }
 
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+			     struct perf_event_context *ctx)
+{
+	struct perf_event_context *gctx;
+
+again:
+	rcu_read_lock();
+	gctx = READ_ONCE(group_leader->ctx);
+	if (!atomic_inc_not_zero(&gctx->refcount)) {
+		rcu_read_unlock();
+		goto again;
+	}
+	rcu_read_unlock();
+
+	mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+	if (group_leader->ctx != gctx) {
+		mutex_unlock(&ctx->mutex);
+		mutex_unlock(&gctx->mutex);
+		put_ctx(gctx);
+		goto again;
+	}
+
+	return gctx;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -8336,6 +8400,24 @@ 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;
 
@@ -8343,7 +8425,7 @@ 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)) {
@@ -8402,11 +8484,6 @@ 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):
 	 */
@@ -8469,8 +8546,26 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (move_group) {
-		gctx = group_leader->ctx;
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+		gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
+		/*
+		 * Check if we raced against another sys_perf_event_open() call
+		 * moving the software group underneath us.
+		 */
+		if (!(group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
+			/*
+			 * If someone moved the group out from under us, check
+			 * if this new event wound up on the same ctx, if so
+			 * its the regular !move_group case, otherwise fail.
+			 */
+			if (gctx != ctx) {
+				err = -EINVAL;
+				goto err_locked;
+			} else {
+				perf_event_ctx_unlock(group_leader, gctx);
+				move_group = 0;
+			}
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
@@ -8494,6 +8589,11 @@ 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
@@ -8560,9 +8660,14 @@ SYSCALL_DEFINE5(perf_event_open,
 	perf_unpin_context(ctx);
 
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 
+	if (task) {
+		mutex_unlock(&task->signal->cred_guard_mutex);
+		put_task_struct(task);
+	}
+
 	put_online_cpus();
 
 	event->owner = current;
@@ -8583,7 +8688,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 err_locked:
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 /* err_file: */
 	fput(event_file);
@@ -8597,6 +8702,9 @@ err_alloc:
 	 */
 	if (!event_file)
 		free_event(event);
+err_cred:
+	if (task)
+		mutex_unlock(&task->signal->cred_guard_mutex);
 err_cpus:
 	put_online_cpus();
 err_task:
@@ -8876,6 +8984,9 @@ 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)
 {
@@ -9197,7 +9308,7 @@ 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;
 	}
 
 	/*
@@ -9213,7 +9324,7 @@ 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);
@@ -9241,6 +9352,7 @@ 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);