This is a note to let you know that I've just added the patch titled
epoll: be better about file lifetimes
to the 6.8-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
epoll-be-better-about-file-lifetimes.patch
and it can be found in the queue-6.8 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 0385671ecc332810d1bd350ed1a28a1c3ff1b12a
Author: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Date: Fri May 3 13:36:09 2024 -0700
epoll: be better about file lifetimes
[ Upstream commit 4efaa5acf0a1d2b5947f98abb3acf8bfd966422b ]
epoll can call out to vfs_poll() with a file pointer that may race with
the last 'fput()'. That would make f_count go down to zero, and while
the ep->mtx locking means that the resulting file pointer tear-down will
be blocked until the poll returns, it means that f_count is already
dead, and any use of it won't actually get a reference to the file any
more: it's dead regardless.
Make sure we have a valid ref on the file pointer before we call down to
vfs_poll() from the epoll routines.
Link: https://lore.kernel.org/lkml/0000000000002d631f0615918f1e@xxxxxxxxxx/
Reported-by: syzbot+045b454ab35fd82a35fb@xxxxxxxxxxxxxxxxxxxxxxxxx
Reviewed-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3534d36a14740..c5a9a483fb538 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -875,6 +875,34 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep
return res;
}
+/*
+ * The ffd.file pointer may be in the process of being torn down due to
+ * being closed, but we may not have finished eventpoll_release() yet.
+ *
+ * Normally, even with the atomic_long_inc_not_zero, the file may have
+ * been free'd and then gotten re-allocated to something else (since
+ * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU).
+ *
+ * But for epoll, users hold the ep->mtx mutex, and as such any file in
+ * the process of being free'd will block in eventpoll_release_file()
+ * and thus the underlying file allocation will not be free'd, and the
+ * file re-use cannot happen.
+ *
+ * For the same reason we can avoid a rcu_read_lock() around the
+ * operation - 'ffd.file' cannot go away even if the refcount has
+ * reached zero (but we must still not call out to ->poll() functions
+ * etc).
+ */
+static struct file *epi_fget(const struct epitem *epi)
+{
+ struct file *file;
+
+ file = epi->ffd.file;
+ if (!atomic_long_inc_not_zero(&file->f_count))
+ file = NULL;
+ return file;
+}
+
/*
* Differs from ep_eventpoll_poll() in that internal callers already have
* the ep->mtx so we need to start from depth=1, such that mutex_lock_nested()
@@ -883,14 +911,22 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep
static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
int depth)
{
- struct file *file = epi->ffd.file;
+ struct file *file = epi_fget(epi);
__poll_t res;
+ /*
+ * We could return EPOLLERR | EPOLLHUP or something, but let's
+ * treat this more as "file doesn't exist, poll didn't happen".
+ */
+ if (!file)
+ return 0;
+
pt->_key = epi->event.events;
if (!is_file_epoll(file))
res = vfs_poll(file, pt);
else
res = __ep_eventpoll_poll(file, pt, depth);
+ fput(file);
return res & epi->event.events;
}
