1 files changed, 120 insertions, 11 deletions

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8cf07242067..4a09af9e9a6 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -63,6 +63,13 @@
  * cleanup path and it is also acquired by eventpoll_release_file()
  * if a file has been pushed inside an epoll set and it is then
  * close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL).
+ * It is also acquired when inserting an epoll fd onto another epoll
+ * fd. We do this so that we walk the epoll tree and ensure that this
+ * insertion does not create a cycle of epoll file descriptors, which
+ * could lead to deadlock. We need a global mutex to prevent two
+ * simultaneous inserts (A into B and B into A) from racing and
+ * constructing a cycle without either insert observing that it is
+ * going to.
  * It is possible to drop the "ep->mtx" and to use the global
  * mutex "epmutex" (together with "ep->lock") to have it working,
  * but having "ep->mtx" will make the interface more scalable.
@@ -217,13 +224,16 @@ struct ep_send_events_data {
  * Configuration options available inside /proc/sys/fs/epoll/
  */
 /* Maximum number of epoll watched descriptors, per user */
-static int max_user_watches __read_mostly;
+static long max_user_watches __read_mostly;
 
 /*
  * This mutex is used to serialize ep_free() and eventpoll_release_file().
  */
 static DEFINE_MUTEX(epmutex);
 
+/* Used to check for epoll file descriptor inclusion loops */
+static struct nested_calls poll_loop_ncalls;
+
 /* Used for safe wake up implementation */
 static struct nested_calls poll_safewake_ncalls;
 
@@ -240,16 +250,18 @@ static struct kmem_cache *pwq_cache __read_mostly;
 
 #include <linux/sysctl.h>
 
-static int zero;
+static long zero;
+static long long_max = LONG_MAX;
 
 ctl_table epoll_table[] = {
 	{
 		.procname	= "max_user_watches",
 		.data		= &max_user_watches,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(max_user_watches),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &zero,
+		.extra2		= &long_max,
 	},
 	{ }
 };
@@ -561,7 +573,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 	/* At this point it is safe to free the eventpoll item */
 	kmem_cache_free(epi_cache, epi);
 
-	atomic_dec(&ep->user->epoll_watches);
+	atomic_long_dec(&ep->user->epoll_watches);
 
 	return 0;
 }
@@ -898,11 +910,12 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 {
 	int error, revents, pwake = 0;
 	unsigned long flags;
+	long user_watches;
 	struct epitem *epi;
 	struct ep_pqueue epq;
 
-	if (unlikely(atomic_read(&ep->user->epoll_watches) >=
-		     max_user_watches))
+	user_watches = atomic_long_read(&ep->user->epoll_watches);
+	if (unlikely(user_watches >= max_user_watches))
 		return -ENOSPC;
 	if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
 		return -ENOMEM;
@@ -966,7 +979,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 
 	spin_unlock_irqrestore(&ep->lock, flags);
 
-	atomic_inc(&ep->user->epoll_watches);
+	atomic_long_inc(&ep->user->epoll_watches);
 
 	/* We have to call this outside the lock */
 	if (pwake)
@@ -1111,6 +1124,17 @@ static int ep_send_events(struct eventpoll *ep,
 	return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
 }
 
+static inline struct timespec ep_set_mstimeout(long ms)
+{
+	struct timespec now, ts = {
+		.tv_sec = ms / MSEC_PER_SEC,
+		.tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC),
+	};
+
+	ktime_get_ts(&now);
+	return timespec_add_safe(now, ts);
+}
+
 static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		   int maxevents, long timeout)
 {
@@ -1118,12 +1142,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	unsigned long flags;
 	long slack;
 	wait_queue_t wait;
-	struct timespec end_time;
 	ktime_t expires, *to = NULL;
 
 	if (timeout > 0) {
-		ktime_get_ts(&end_time);
-		timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC);
+		struct timespec end_time = ep_set_mstimeout(timeout);
+
 		slack = select_estimate_accuracy(&end_time);
 		to = &expires;
 		*to = timespec_to_ktime(end_time);
@@ -1185,6 +1208,62 @@ retry:
 	return res;
 }
 
+/**
+ * ep_loop_check_proc - Callback function to be passed to the @ep_call_nested()
+ *                      API, to verify that adding an epoll file inside another
+ *                      epoll structure, does not violate the constraints, in
+ *                      terms of closed loops, or too deep chains (which can
+ *                      result in excessive stack usage).
+ *
+ * @priv: Pointer to the epoll file to be currently checked.
+ * @cookie: Original cookie for this call. This is the top-of-the-chain epoll
+ *          data structure pointer.
+ * @call_nests: Current dept of the @ep_call_nested() call stack.
+ *
+ * Returns: Returns zero if adding the epoll @file inside current epoll
+ *          structure @ep does not violate the constraints, or -1 otherwise.
+ */
+static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
+{
+	int error = 0;
+	struct file *file = priv;
+	struct eventpoll *ep = file->private_data;
+	struct rb_node *rbp;
+	struct epitem *epi;
+
+	mutex_lock(&ep->mtx);
+	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+		epi = rb_entry(rbp, struct epitem, rbn);
+		if (unlikely(is_file_epoll(epi->ffd.file))) {
+			error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+					       ep_loop_check_proc, epi->ffd.file,
+					       epi->ffd.file->private_data, current);
+			if (error != 0)
+				break;
+		}
+	}
+	mutex_unlock(&ep->mtx);
+
+	return error;
+}
+
+/**
+ * ep_loop_check - Performs a check to verify that adding an epoll file (@file)
+ *                 another epoll file (represented by @ep) does not create
+ *                 closed loops or too deep chains.
+ *
+ * @ep: Pointer to the epoll private data structure.
+ * @file: Pointer to the epoll file to be checked.
+ *
+ * Returns: Returns zero if adding the epoll @file inside current epoll
+ *          structure @ep does not violate the constraints, or -1 otherwise.
+ */
+static int ep_loop_check(struct eventpoll *ep, struct file *file)
+{
+	return ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+			      ep_loop_check_proc, file, ep, current);
+}
+
 /*
  * Open an eventpoll file descriptor.
  */
@@ -1233,6 +1312,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		struct epoll_event __user *, event)
 {
 	int error;
+	int did_lock_epmutex = 0;
 	struct file *file, *tfile;
 	struct eventpoll *ep;
 	struct epitem *epi;
@@ -1274,6 +1354,25 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 */
 	ep = file->private_data;
 
+	/*
+	 * When we insert an epoll file descriptor, inside another epoll file
+	 * descriptor, there is the change of creating closed loops, which are
+	 * better be handled here, than in more critical paths.
+	 *
+	 * We hold epmutex across the loop check and the insert in this case, in
+	 * order to prevent two separate inserts from racing and each doing the
+	 * insert "at the same time" such that ep_loop_check passes on both
+	 * before either one does the insert, thereby creating a cycle.
+	 */
+	if (unlikely(is_file_epoll(tfile) && op == EPOLL_CTL_ADD)) {
+		mutex_lock(&epmutex);
+		did_lock_epmutex = 1;
+		error = -ELOOP;
+		if (ep_loop_check(ep, tfile) != 0)
+			goto error_tgt_fput;
+	}
+
+
 	mutex_lock(&ep->mtx);
 
 	/*
@@ -1309,6 +1408,9 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	mutex_unlock(&ep->mtx);
 
 error_tgt_fput:
+	if (unlikely(did_lock_epmutex))
+		mutex_unlock(&epmutex);
+
 	fput(tfile);
 error_fput:
 	fput(file);
@@ -1426,6 +1528,13 @@ static int __init eventpoll_init(void)
 	 */
 	max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) /
 		EP_ITEM_COST;
+	BUG_ON(max_user_watches < 0);
+
+	/*
+	 * Initialize the structure used to perform epoll file descriptor
+	 * inclusion loops checks.
+	 */
+	ep_nested_calls_init(&poll_loop_ncalls);
 
 	/* Initialize the structure used to perform safe poll wait head wake ups */
 	ep_nested_calls_init(&poll_safewake_ncalls);