diff options
Diffstat (limited to 'recipes-kernel/linux/files/0001-tty-don-t-deadlock-while-flushing-workqueue-quark.patch')
| -rw-r--r-- | recipes-kernel/linux/files/0001-tty-don-t-deadlock-while-flushing-workqueue-quark.patch | 142 |
1 files changed, 142 insertions, 0 deletions
diff --git a/recipes-kernel/linux/files/0001-tty-don-t-deadlock-while-flushing-workqueue-quark.patch b/recipes-kernel/linux/files/0001-tty-don-t-deadlock-while-flushing-workqueue-quark.patch new file mode 100644 index 0000000..4d0fd37 --- /dev/null +++ b/recipes-kernel/linux/files/0001-tty-don-t-deadlock-while-flushing-workqueue-quark.patch @@ -0,0 +1,142 @@ +From xxxx Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 25 Dec 2012 23:02:48 +0100 +Subject: [PATCH 01/21] tty: don't deadlock while flushing workqueue + +Since commit 89c8d91e31f2 ("tty: localise the lock") I see a dead lock +in one of my dummy_hcd + g_nokia test cases. The first run was usually +okay, the second often resulted in a splat by lockdep and the third was +usually a dead lock. +Lockdep complained about tty->hangup_work and tty->legacy_mutex taken +both ways: +| ====================================================== +| [ INFO: possible circular locking dependency detected ] +| 3.7.0-rc6+ #204 Not tainted +| ------------------------------------------------------- +| kworker/2:1/35 is trying to acquire lock: +| (&tty->legacy_mutex){+.+.+.}, at: [<c14051e6>] tty_lock_nested+0x36/0x80 +| +| but task is already holding lock: +| ((&tty->hangup_work)){+.+...}, at: [<c104f6e4>] process_one_work+0x124/0x5e0 +| +| which lock already depends on the new lock. +| +| the existing dependency chain (in reverse order) is: +| +| -> #2 ((&tty->hangup_work)){+.+...}: +| [<c107fe74>] lock_acquire+0x84/0x190 +| [<c104d82d>] flush_work+0x3d/0x240 +| [<c12e6986>] tty_ldisc_flush_works+0x16/0x30 +| [<c12e7861>] tty_ldisc_release+0x21/0x70 +| [<c12e0dfc>] tty_release+0x35c/0x470 +| [<c1105e28>] __fput+0xd8/0x270 +| [<c1105fcd>] ____fput+0xd/0x10 +| [<c1051dd9>] task_work_run+0xb9/0xf0 +| [<c1002a51>] do_notify_resume+0x51/0x80 +| [<c140550a>] work_notifysig+0x35/0x3b +| +| -> #1 (&tty->legacy_mutex/1){+.+...}: +| [<c107fe74>] lock_acquire+0x84/0x190 +| [<c140276c>] mutex_lock_nested+0x6c/0x2f0 +| [<c14051e6>] tty_lock_nested+0x36/0x80 +| [<c1405279>] tty_lock_pair+0x29/0x70 +| [<c12e0bb8>] tty_release+0x118/0x470 +| [<c1105e28>] __fput+0xd8/0x270 +| [<c1105fcd>] ____fput+0xd/0x10 +| [<c1051dd9>] task_work_run+0xb9/0xf0 +| [<c1002a51>] do_notify_resume+0x51/0x80 +| [<c140550a>] work_notifysig+0x35/0x3b +| +| -> #0 (&tty->legacy_mutex){+.+.+.}: +| [<c107f3c9>] __lock_acquire+0x1189/0x16a0 +| [<c107fe74>] lock_acquire+0x84/0x190 +| [<c140276c>] mutex_lock_nested+0x6c/0x2f0 +| [<c14051e6>] tty_lock_nested+0x36/0x80 +| [<c140523f>] tty_lock+0xf/0x20 +| [<c12df8e4>] __tty_hangup+0x54/0x410 +| [<c12dfcb2>] do_tty_hangup+0x12/0x20 +| [<c104f763>] process_one_work+0x1a3/0x5e0 +| [<c104fec9>] worker_thread+0x119/0x3a0 +| [<c1055084>] kthread+0x94/0xa0 +| [<c140ca37>] ret_from_kernel_thread+0x1b/0x28 +| +|other info that might help us debug this: +| +|Chain exists of: +| &tty->legacy_mutex --> &tty->legacy_mutex/1 --> (&tty->hangup_work) +| +| Possible unsafe locking scenario: +| +| CPU0 CPU1 +| ---- ---- +| lock((&tty->hangup_work)); +| lock(&tty->legacy_mutex/1); +| lock((&tty->hangup_work)); +| lock(&tty->legacy_mutex); +| +| *** DEADLOCK *** + +Before the path mentioned tty_ldisc_release() look like this: + +| tty_ldisc_halt(tty); +| tty_ldisc_flush_works(tty); +| tty_lock(); + +As it can be seen, it first flushes the workqueue and then grabs the +tty_lock. Now we grab the lock first: + +| tty_lock_pair(tty, o_tty); +| tty_ldisc_halt(tty); +| tty_ldisc_flush_works(tty); + +so lockdep's complaint seems valid. + +The earlier version of this patch took the ldisc_mutex since the other +user of tty_ldisc_flush_works() (tty_set_ldisc()) did this. +Peter Hurley then said that it is should not be requried. Since it +wasn't done earlier, I dropped this part. +The code under tty_ldisc_kill() was executed earlier with the tty lock +taken so it is taken again. + +I was able to reproduce the deadlock on v3.8-rc1, this patch fixes the +problem in my testcase. I didn't notice any problems so far. + +Cc: Alan Cox <alan@linux.intel.com> +Cc: Peter Hurley <peter@hurleysoftware.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> +(cherry picked from commit 852e4a8152b427c3f318bb0e1b5e938d64dcdc32) +--- + drivers/tty/tty_ldisc.c | 10 +++++----- + 1 files changed, 5 insertions(+), 5 deletions(-) + +diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c +index c578229..78f1be2 100644 +--- a/drivers/tty/tty_ldisc.c ++++ b/drivers/tty/tty_ldisc.c +@@ -934,17 +934,17 @@ void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty) + * race with the set_ldisc code path. + */ + +- tty_lock_pair(tty, o_tty); + tty_ldisc_halt(tty); +- tty_ldisc_flush_works(tty); +- if (o_tty) { ++ if (o_tty) + tty_ldisc_halt(o_tty); ++ ++ tty_ldisc_flush_works(tty); ++ if (o_tty) + tty_ldisc_flush_works(o_tty); +- } + ++ tty_lock_pair(tty, o_tty); + /* This will need doing differently if we need to lock */ + tty_ldisc_kill(tty); +- + if (o_tty) + tty_ldisc_kill(o_tty); + +-- +1.7.4.1 + |