tty: fix stall caused by missing memory barrier in drivers/tty/n_tty.c
Subsystems (2)
cover tty: fix stall caused by missing memory barrier in drivers/tty/n_tty.c
Hello,
Please consider including upstream commit e81107d4c6bd098878af9796b24edc8d4a9524fd in the next v3.13.y-ckt release. This commit was included mainline as of v4.3-rc5. It has been tested and confirmed to resolve http://bugs.launchpad.net/bugs/1512815 .
commit e81107d4c6bd098878af9796b24edc8d4a9524fd
Author: Kosuke Tatsukawa <[email protected]> Date: Fri Oct 2 08:27:05 2015 +0000
tty: fix stall caused by missing memory barrier in drivers/tty/n_tty.c
Commit e81107d4 does not apply cleanly to v3.13.y-ckt, so I performed a backport, which is in email 1/1.
Sincerely,
Joseph Salisbury
Kosuke Tatsukawa (1):
tty: fix stall caused by missing memory barrier in drivers/tty/n_tty.c
drivers/tty/n_tty.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)
Signature · 1 line
1.9.1
PATCH 1/1 tty: fix stall caused by missing memory barrier in drivers/tty/n_tty.c
From: Kosuke Tatsukawa <[email protected]>
commit e81107d4c6bd098878af9796b24edc8d4a9524fd upstream.
My colleague ran into a program stall on a x86_64 server, where n_tty_read() was waiting for data even if there was data in the buffer in the pty. kernel stack for the stuck process looks like below.
#0 [ffff88303d107b58] __schedule at ffffffff815c4b20
#1 [ffff88303d107bd0] schedule at ffffffff815c513e
#2 [ffff88303d107bf0] schedule_timeout at ffffffff815c7818 #3 [ffff88303d107ca0] wait_woken at ffffffff81096bd2
#4 [ffff88303d107ce0] n_tty_read at ffffffff8136fa23
#5 [ffff88303d107dd0] tty_read at ffffffff81368013
#6 [ffff88303d107e20] __vfs_read at ffffffff811a3704
#7 [ffff88303d107ec0] vfs_read at ffffffff811a3a57
#8 [ffff88303d107f00] sys_read at ffffffff811a4306
#9 [ffff88303d107f50] entry_SYSCALL_64_fastpath at ffffffff815c86d7
There seems to be two problems causing this issue.
First, in drivers/tty/n_tty.c, __receive_buf() stores the data and updates ldata->commit_head using smp_store_release() and then checks the wait queue using waitqueue_active(). However, since there is no memory barrier, __receive_buf() could return without calling wake_up_interactive_poll(), and at the same time, n_tty_read() could start to wait in wait_woken() as in the following chart.
__receive_buf() n_tty_read()
------------------------------------------------------------------------
if (waitqueue_active(&tty->read_wait))
/* Memory operations issued after the
RELEASE may be completed before the
RELEASE operation has completed */
add_wait_queue(&tty->read_wait, &wait);
...
if (!input_available_p(tty, 0)) {
smp_store_release(&ldata->commit_head,
ldata->read_head);
...
timeout = wait_woken(&wait,
TASK_INTERRUPTIBLE, timeout);------------------------------------------------------------------------
The second problem is that n_tty_read() also lacks a memory barrier call and could also cause __receive_buf() to return without calling wake_up_interactive_poll(), and n_tty_read() to wait in wait_woken() as in the chart below.
__receive_buf() n_tty_read()
------------------------------------------------------------------------
spin_lock_irqsave(&q->lock, flags);
/* from add_wait_queue() */
...
if (!input_available_p(tty, 0)) {
/* Memory operations issued after the
RELEASE may be completed before the
RELEASE operation has completed */
smp_store_release(&ldata->commit_head,
ldata->read_head);
if (waitqueue_active(&tty->read_wait))
__add_wait_queue(q, wait);
spin_unlock_irqrestore(&q->lock,flags);
/* from add_wait_queue() */
...
timeout = wait_woken(&wait,
TASK_INTERRUPTIBLE, timeout);------------------------------------------------------------------------
There are also other places in drivers/tty/n_tty.c which have similar calls to waitqueue_active(), so instead of adding many memory barrier calls, this patch simply removes the call to waitqueue_active(), leaving just wake_up*() behind.
This fixes both problems because, even though the memory access before or after the spinlocks in both wake_up*() and add_wait_queue() can sneak into the critical section, it cannot go past it and the critical section assures that they will be serialized (please see "INTER-CPU ACQUIRING BARRIER EFFECTS" in Documentation/memory-barriers.txt for a better explanation). Moreover, the resulting code is much simpler.
Latency measurement using a ping-pong test over a pty doesn't show any visible performance drop.
[jsalisbury: Backported to 3.13.y:
- Use wake_up_interruptible(), not wake_up_interruptible_poll()
- There are only two spurious uses of waitqueue_active() to remove]
--- drivers/tty/n_tty.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)
drivers/tty/n_tty.c +2 -4
@@ -1385,8 +1385,7 @@ handle_newline:put_tty_queue (c, ldata); ldata->canon_head = ldata->read_head;kill_fasync (&tty->fasync,SIGIO ,POLL_IN ); -if (waitqueue_active (&tty->read_wait)) -wake_up_interruptible (&tty->read_wait); +wake_up_interruptible (&tty->read_wait);return 0 ; } }
@@ -1671,8 +1670,7 @@ static void __receive_buf(struct tty_struct *tty, const unsigned char *cp,if ((!ldata->icanon && (read_cnt (ldata) >= ldata->minimum_to_wake)) ||L_EXTPROC (tty)) {kill_fasync (&tty->fasync,SIGIO ,POLL_IN ); -if (waitqueue_active (&tty->read_wait)) -wake_up_interruptible (&tty->read_wait); +wake_up_interruptible (&tty->read_wait); } }
Signature · 1 line
1.9.1
Quoted 6 lines · Joseph Salisbury
Hello,
Please consider including upstream commit
e81107d4c6bd098878af9796b24edc8d4a9524fdin the next v3.13.y-ckt release. This commit was included mainline as of v4.3-rc5. It has been tested and confirmed to resolve http://bugs.launchpad.net/bugs/1512815 .
Quoted 8 lines
commit
e81107d4c6bd098878af9796b24edc8d4a9524fdAuthor: Kosuke Tatsukawa <[email protected]> Date: Fri Oct 2 08:27:05 2015 +0000tty: fix stall caused by missing memory barrier in
drivers/tty/n_tty.cCommit
e81107d4does not apply cleanly to v3.13.y-ckt, so I performed a backport, which is in email 1/1.
Thanks very much Joseph. Queued for 3.13-stable.
-Kamal
Quoted 14 lines
Sincerely,
Joseph Salisbury
Kosuke Tatsukawa (1):
tty: fix stall caused by missing memory barrier indrivers/tty/n_tty.cdrivers/tty/n_tty.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)