On Mon, Sep 25, 2017 at 01:29:18PM -0700, Bart Van Assche wrote:
> Some people use the md driver on laptops and use the suspend and
> resume functionality. Since it is essential that submitting of
> new I/O requests stops before device quiescing starts, make the
> md resync and reshape threads freezable.
>
> Signed-off-by: Bart Van Assche <bart.vanassche@xxxxxxx>
> Cc: Shaohua Li <shli@xxxxxxxxxx>
> Cc: linux-raid@xxxxxxxxxxxxxxx
> Cc: Ming Lei <ming.lei@xxxxxxxxxx>
> Cc: Christoph Hellwig <hch@xxxxxx>
> Cc: Hannes Reinecke <hare@xxxxxxxx>
> Cc: Johannes Thumshirn <jthumshirn@xxxxxxx>
> ---
> drivers/md/md.c | 21 +++++++++++++--------
> 1 file changed, 13 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 08fcaebc61bd..26a12bd0db65 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -66,6 +66,7 @@
> #include <linux/raid/md_u.h>
> #include <linux/slab.h>
> #include <linux/percpu-refcount.h>
> +#include <linux/freezer.h>
>
> #include <trace/events/block.h>
> #include "md.h"
> @@ -7424,6 +7425,7 @@ static int md_thread(void *arg)
> */
>
> allow_signal(SIGKILL);
> + set_freezable();
> while (!kthread_should_stop()) {
>
> /* We need to wait INTERRUPTIBLE so that
> @@ -7434,7 +7436,7 @@ static int md_thread(void *arg)
> if (signal_pending(current))
> flush_signals(current);
>
> - wait_event_interruptible_timeout
> + wait_event_freezable_timeout
> (thread->wqueue,
> test_bit(THREAD_WAKEUP, &thread->flags)
> || kthread_should_stop() || kthread_should_park(),
> @@ -8133,6 +8135,8 @@ void md_do_sync(struct md_thread *thread)
> return;
> }
>
> + set_freezable();
> +
> if (mddev_is_clustered(mddev)) {
> ret = md_cluster_ops->resync_start(mddev);
> if (ret)
> @@ -8324,7 +8328,7 @@ void md_do_sync(struct md_thread *thread)
> mddev->curr_resync_completed > mddev->resync_max
> )) {
> /* time to update curr_resync_completed */
> - wait_event(mddev->recovery_wait,
> + wait_event_freezable(mddev->recovery_wait,
> atomic_read(&mddev->recovery_active) == 0);
> mddev->curr_resync_completed = j;
> if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
> @@ -8342,10 +8346,10 @@ void md_do_sync(struct md_thread *thread)
> * to avoid triggering warnings.
> */
> flush_signals(current); /* just in case */
> - wait_event_interruptible(mddev->recovery_wait,
> - mddev->resync_max > j
> - || test_bit(MD_RECOVERY_INTR,
> - &mddev->recovery));
> + wait_event_freezable(mddev->recovery_wait,
> + mddev->resync_max > j ||
> + test_bit(MD_RECOVERY_INTR,
> + &mddev->recovery));
> }
>
> if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
> @@ -8421,7 +8425,7 @@ void md_do_sync(struct md_thread *thread)
> * Give other IO more of a chance.
> * The faster the devices, the less we wait.
> */
> - wait_event(mddev->recovery_wait,
> + wait_event_freezable(mddev->recovery_wait,
> !atomic_read(&mddev->recovery_active));
> }
> }
> @@ -8433,7 +8437,8 @@ void md_do_sync(struct md_thread *thread)
> * this also signals 'finished resyncing' to md_stop
> */
> blk_finish_plug(&plug);
> - wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
> + wait_event_freezable(mddev->recovery_wait,
> + !atomic_read(&mddev->recovery_active));
>
> if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
> !test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
> --
> 2.14.1
>
Just test this patch a bit and the following failure of freezing task
is triggered during suspend:
[ 38.903513] PM: suspend entry (deep)
[ 38.904443] PM: Syncing filesystems ... done.
[ 38.983591] Freezing user space processes ... (elapsed 0.002 seconds) done.
[ 38.987522] OOM killer disabled.
[ 38.987962] Freezing remaining freezable tasks ...
[ 58.998872] Freezing of tasks failed after 20.008 seconds (1 tasks refusing to freeze, wq_busy=0):
[ 59.002539] md127_resync D 0 1618 2 0x80000000
[ 59.004954] Call Trace:
[ 59.006162] __schedule+0x41f/0xa50
[ 59.007704] schedule+0x3d/0x90
[ 59.009305] raid1_sync_request+0x2da/0xd10 [raid1]
[ 59.011505] ? remove_wait_queue+0x70/0x70
[ 59.013352] md_do_sync+0xdfa/0x12c0
[ 59.014955] ? remove_wait_queue+0x70/0x70
[ 59.016336] md_thread+0x1a8/0x1e0
[ 59.016770] ? md_thread+0x1a8/0x1e0
[ 59.017250] kthread+0x155/0x190
[ 59.017662] ? sync_speed_show+0xa0/0xa0
[ 59.018217] ? kthread_create_on_node+0x70/0x70
[ 59.018858] ret_from_fork+0x2a/0x40
[ 59.019403] Restarting kernel threads ... done.
[ 59.024586] OOM killer enabled.
[ 59.025124] Restarting tasks ... done.
[ 59.045906] PM: suspend exit
[ 97.919428] systemd-journald[227]: Sent WATCHDOG=1 notification.
[ 101.002695] md: md127: data-check done.
--
Ming
