From: Jan Kara jack@suse.cz
stable inclusion from linux-4.19.227 commit 6717900f775a6129a7b4d03ba4922218d8bf1caa
--------------------------------
commit 68514dacf2715d11b91ca50d88de047c086fea9c upstream.
A task can end up indefinitely sleeping in do_select() -> poll_schedule_timeout() when the following race happens:
TASK1 (thread1) TASK2 TASK1 (thread2) do_select() setup poll_wqueues table with 'fd' write data to 'fd' pollwake() table->triggered = 1 closes 'fd' thread1 is waiting for poll_schedule_timeout() - sees table->triggered table->triggered = 0 return -EINTR loop back in do_select()
But at this point when TASK1 loops back, the fdget() in the setup of poll_wqueues fails. So now so we never find 'fd' is ready for reading and sleep in poll_schedule_timeout() indefinitely.
Treat an fd that got closed as a fd on which some event happened. This makes sure cannot block indefinitely in do_select().
Another option would be to return -EBADF in this case but that has a potential of subtly breaking applications that excercise this behavior and it happens to work for them. So returning fd as active seems like a safer choice.
Suggested-by: Linus Torvalds torvalds@linux-foundation.org CC: stable@vger.kernel.org Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yongqiang Liu liuyongqiang13@huawei.com Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- fs/select.c | 63 ++++++++++++++++++++++++++++------------------------- 1 file changed, 33 insertions(+), 30 deletions(-)
diff --git a/fs/select.c b/fs/select.c index b684f0dd6db8..67e4be14c00c 100644 --- a/fs/select.c +++ b/fs/select.c @@ -458,9 +458,11 @@ static int max_select_fd(unsigned long n, fd_set_bits *fds) return max; }
-#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR) -#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR) -#define POLLEX_SET (EPOLLPRI) +#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR |\ + EPOLLNVAL) +#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR |\ + EPOLLNVAL) +#define POLLEX_SET (EPOLLPRI | EPOLLNVAL)
static inline void wait_key_set(poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, @@ -527,6 +529,7 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) break; if (!(bit & all_bits)) continue; + mask = EPOLLNVAL; f = fdget(i); if (f.file) { wait_key_set(wait, in, out, bit, @@ -534,34 +537,34 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) mask = vfs_poll(f.file, wait);
fdput(f); - if ((mask & POLLIN_SET) && (in & bit)) { - res_in |= bit; - retval++; - wait->_qproc = NULL; - } - if ((mask & POLLOUT_SET) && (out & bit)) { - res_out |= bit; - retval++; - wait->_qproc = NULL; - } - if ((mask & POLLEX_SET) && (ex & bit)) { - res_ex |= bit; - retval++; - wait->_qproc = NULL; - } - /* got something, stop busy polling */ - if (retval) { - can_busy_loop = false; - busy_flag = 0; - - /* - * only remember a returned - * POLL_BUSY_LOOP if we asked for it - */ - } else if (busy_flag & mask) - can_busy_loop = true; - } + if ((mask & POLLIN_SET) && (in & bit)) { + res_in |= bit; + retval++; + wait->_qproc = NULL; + } + if ((mask & POLLOUT_SET) && (out & bit)) { + res_out |= bit; + retval++; + wait->_qproc = NULL; + } + if ((mask & POLLEX_SET) && (ex & bit)) { + res_ex |= bit; + retval++; + wait->_qproc = NULL; + } + /* got something, stop busy polling */ + if (retval) { + can_busy_loop = false; + busy_flag = 0; + + /* + * only remember a returned + * POLL_BUSY_LOOP if we asked for it + */ + } else if (busy_flag & mask) + can_busy_loop = true; + } if (res_in) *rinp = res_in;