* 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.
struct nested_call_node {
struct list_head llink;
void *cookie;
- int cpu;
+ void *ctx;
};
/*
*/
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;
* @nproc: Nested call core function pointer.
* @priv: Opaque data to be passed to the @nproc callback.
* @cookie: Cookie to be used to identify this nested call.
+ * @ctx: This instance context.
*
* Returns: Returns the code returned by the @nproc callback, or -1 if
* the maximum recursion limit has been exceeded.
*/
static int ep_call_nested(struct nested_calls *ncalls, int max_nests,
int (*nproc)(void *, void *, int), void *priv,
- void *cookie)
+ void *cookie, void *ctx)
{
int error, call_nests = 0;
unsigned long flags;
- int this_cpu = get_cpu();
struct list_head *lsthead = &ncalls->tasks_call_list;
struct nested_call_node *tncur;
struct nested_call_node tnode;
* very much limited.
*/
list_for_each_entry(tncur, lsthead, llink) {
- if (tncur->cpu == this_cpu &&
+ if (tncur->ctx == ctx &&
(tncur->cookie == cookie || ++call_nests > max_nests)) {
/*
* Ops ... loop detected or maximum nest level reached.
}
/* Add the current task and cookie to the list */
- tnode.cpu = this_cpu;
+ tnode.ctx = ctx;
tnode.cookie = cookie;
list_add(&tnode.llink, lsthead);
/* Remove the current task from the list */
spin_lock_irqsave(&ncalls->lock, flags);
list_del(&tnode.llink);
- out_unlock:
+out_unlock:
spin_unlock_irqrestore(&ncalls->lock, flags);
- put_cpu();
return error;
}
*/
static void ep_poll_safewake(wait_queue_head_t *wq)
{
+ int this_cpu = get_cpu();
+
ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS,
- ep_poll_wakeup_proc, NULL, wq);
+ ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);
+
+ put_cpu();
}
/*
* could re-enter here.
*/
pollflags = ep_call_nested(&poll_readywalk_ncalls, EP_MAX_NESTS,
- ep_poll_readyevents_proc, ep, ep);
+ ep_poll_readyevents_proc, ep, ep, current);
return pollflags != -1 ? pollflags : 0;
}
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.
*/
struct epoll_event __user *, event)
{
int error;
+ int did_lock_epmutex = 0;
struct file *file, *tfile;
struct eventpoll *ep;
struct epitem *epi;
*/
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);
/*
mutex_unlock(&ep->mtx);
error_tgt_fput:
+ if (unlikely(did_lock_epmutex))
+ mutex_unlock(&epmutex);
+
fput(tfile);
error_fput:
fput(file);
max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) /
EP_ITEM_COST;
+ /*
+ * 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);