From 6628bc74f1aa9c35dd386320bf7ec04f12edb1b3 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Fri, 27 Aug 2010 09:15:09 +0200 Subject: writeback: do not lose wakeup events when forking bdi threads This patch fixes the following issue: INFO: task mount.nfs4:1120 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount.nfs4 D 00000000fffc6a21 0 1120 1119 0x00000000 ffff880235643948 0000000000000046 ffffffff00000000 ffffffff00000000 ffff880235643fd8 ffff880235314760 00000000001d44c0 ffff880235643fd8 00000000001d44c0 00000000001d44c0 00000000001d44c0 00000000001d44c0 Call Trace: [] schedule_timeout+0x34/0xf1 [] ? wait_for_common+0x3f/0x130 [] ? trace_hardirqs_on+0xd/0xf [] wait_for_common+0xd2/0x130 [] ? default_wake_function+0x0/0xf [] ? _raw_spin_unlock+0x26/0x2a [] wait_for_completion+0x18/0x1a [] sync_inodes_sb+0xca/0x1bc [] __sync_filesystem+0x47/0x7e [] sync_filesystem+0x47/0x4b [] generic_shutdown_super+0x22/0xd2 [] kill_anon_super+0x11/0x4f [] nfs4_kill_super+0x3f/0x72 [nfs] [] deactivate_locked_super+0x21/0x41 [] deactivate_super+0x40/0x45 [] mntput_no_expire+0xb8/0xed [] release_mounts+0x9a/0xb0 [] put_mnt_ns+0x6a/0x7b [] nfs_follow_remote_path+0x19a/0x296 [nfs] [] nfs4_try_mount+0x75/0xaf [nfs] [] nfs4_get_sb+0x276/0x2ff [nfs] [] vfs_kern_mount+0xb8/0x196 [] do_kern_mount+0x48/0xe8 [] do_mount+0x771/0x7e8 [] sys_mount+0x83/0xbd [] system_call_fastpath+0x16/0x1b The reason of this hang was a race condition: when the flusher thread is forking a bdi thread, we use 'kthread_run()', so we run it _before_ we make it visible in 'bdi->wb.task'. The bdi thread runs, does all works, and goes sleep. 'bdi->wb.task' is still NULL. And this is a dangerous time window. If at this time someone queues a work for this bdi, he does not see the bdi thread and wakes up the forker thread instead! But the forker has already forked this bdi thread, but just did not make it visible yet! The result is that we lose the wake up event for this bdi thread and the NFS4 code waits forever. To fix the problem, we should use 'ktrhead_create()' for creating bdi threads, then make them visible in 'bdi->wb.task', and only after this wake them up. This is exactly what this patch does. Signed-off-by: Artem Bityutskiy Signed-off-by: Jens Axboe --- mm/backing-dev.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index eaa4a5bbe063..c2bf86f470ed 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -445,8 +445,8 @@ static int bdi_forker_thread(void *ptr) switch (action) { case FORK_THREAD: __set_current_state(TASK_RUNNING); - task = kthread_run(bdi_writeback_thread, &bdi->wb, "flush-%s", - dev_name(bdi->dev)); + task = kthread_create(bdi_writeback_thread, &bdi->wb, + "flush-%s", dev_name(bdi->dev)); if (IS_ERR(task)) { /* * If thread creation fails, force writeout of @@ -457,10 +457,13 @@ static int bdi_forker_thread(void *ptr) /* * The spinlock makes sure we do not lose * wake-ups when racing with 'bdi_queue_work()'. + * And as soon as the bdi thread is visible, we + * can start it. */ spin_lock_bh(&bdi->wb_lock); bdi->wb.task = task; spin_unlock_bh(&bdi->wb_lock); + wake_up_process(task); } break; -- cgit v1.2.3-59-g8ed1b