On Wed, 22 Jul 2020, Mikulas Patocka wrote:
>
>
> On Wed, 22 Jul 2020, Mike Snitzer wrote:
>
> > On Wed, Jul 22 2020 at 2:46pm -0400,
> > Mikulas Patocka <mpatocka@xxxxxxxxxx> wrote:
> >
> > > Hi Mike
> > >
> > > Please submit this to Linus and to RHEL-8.
> > >
> > > Mikulas
> > >
> > >
> > >
> > > From: Mikulas Patocka <mpatocka@xxxxxxxxxx>
> > >
> > > The patch adc0daad366b62ca1bce3e2958a40b0b71a8b8b3 broke recalculation on
> > > dm-integrity. The patch replaces a private variable "suspending" with a
> > > call to "dm_suspended".
> > >
> > > The problem is that dm_suspended returns true not only during suspend, but
> > > also during resume. This race condition could occur:
> > > 1. dm_integrity_resume calls queue_work(ic->recalc_wq, &ic->recalc_work)
> > > 2. integrity_recalc (&ic->recalc_work) preempts the current thread
> > > 3. integrity_recalc calls if (unlikely(dm_suspended(ic->ti))) goto unlock_ret;
> > > 4. integrity_recalc exits and no recalculating is done.
> > >
> > > In order to fix this race condition, we stop using dm_suspended and start
> > > using the variable "suspending" (that is only set during suspend, not
> > > during resume).
> > >
> > > Signed-off-by: Mikulas Patocka <mpatocka@xxxxxxxxxx>
> > > Fixes: adc0daad366b ("dm: report suspended device during destroy")
> > > Cc: stable@xxxxxxxxxxxxxxx # v4.18+
> >
> > OK, but why not add a dm_suspending() to DM core? Could be other
> > future targets would like this same info right? I don't see harm in
> > elevating it.
> >
> > Mike
>
> Yes - it may be possible to add this.
>
> Mikulas
From: Mikulas Patocka <mpatocka@xxxxxxxxxx>
The patch adc0daad366b62ca1bce3e2958a40b0b71a8b8b3 broke recalculation on
dm-integrity. The patch replaces a private variable "suspending" with a
call to "dm_suspended".
The problem is that dm_suspended returns true not only during suspend, but
also during resume. This race condition could occur:
1. dm_integrity_resume calls queue_work(ic->recalc_wq, &ic->recalc_work)
2. integrity_recalc (&ic->recalc_work) preempts the current thread
3. integrity_recalc calls if (unlikely(dm_suspended(ic->ti))) goto unlock_ret;
4. integrity_recalc exits and no recalculating is done.
In order to fix this race condition, we add a function dm_suspending that
is only true during the postsuspend phase and use it instead of
dm_suspended.
Signed-off-by: Mikulas Patocka <mpatocka redhat com>
Fixes: adc0daad366b ("dm: report suspended device during destroy")
Cc: stable vger kernel org # v4.18+
Index: rhel8/drivers/md/dm.c
===================================================================
--- rhel8.orig/drivers/md/dm.c
+++ rhel8/drivers/md/dm.c
@@ -140,6 +140,7 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_
#define DMF_NOFLUSH_SUSPENDING 5
#define DMF_DEFERRED_REMOVE 6
#define DMF_SUSPENDED_INTERNALLY 7
+#define DMF_SUSPENDING 8
#define DM_NUMA_NODE NUMA_NO_NODE
static int dm_numa_node = DM_NUMA_NODE;
@@ -2379,6 +2380,7 @@ static void __dm_destroy(struct mapped_d
if (!dm_suspended_md(md)) {
dm_table_presuspend_targets(map);
set_bit(DMF_SUSPENDED, &md->flags);
+ set_bit(DMF_SUSPENDING, &md->flags);
dm_table_postsuspend_targets(map);
}
/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
@@ -2701,7 +2703,9 @@ retry:
if (r)
goto out_unlock;
+ set_bit(DMF_SUSPENDING, &md->flags);
dm_table_postsuspend_targets(map);
+ clear_bit(DMF_SUSPENDING, &md->flags);
out_unlock:
mutex_unlock(&md->suspend_lock);
@@ -2798,7 +2802,9 @@ static void __dm_internal_suspend(struct
(void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE,
DMF_SUSPENDED_INTERNALLY);
+ set_bit(DMF_SUSPENDING, &md->flags);
dm_table_postsuspend_targets(map);
+ clear_bit(DMF_SUSPENDING, &md->flags);
}
static void __dm_internal_resume(struct mapped_device *md)
@@ -2951,6 +2957,11 @@ int dm_suspended_md(struct mapped_device
return test_bit(DMF_SUSPENDED, &md->flags);
}
+static int dm_suspending_md(struct mapped_device *md)
+{
+ return test_bit(DMF_SUSPENDING, &md->flags);
+}
+
int dm_suspended_internally_md(struct mapped_device *md)
{
return test_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
@@ -2967,6 +2978,12 @@ int dm_suspended(struct dm_target *ti)
}
EXPORT_SYMBOL_GPL(dm_suspended);
+int dm_suspending(struct dm_target *ti)
+{
+ return dm_suspending_md(dm_table_get_md(ti->table));
+}
+EXPORT_SYMBOL_GPL(dm_suspending);
+
int dm_noflush_suspending(struct dm_target *ti)
{
return __noflush_suspending(dm_table_get_md(ti->table));
Index: rhel8/drivers/md/dm-integrity.c
===================================================================
--- rhel8.orig/drivers/md/dm-integrity.c
+++ rhel8/drivers/md/dm-integrity.c
@@ -2428,7 +2428,7 @@ static void integrity_writer(struct work
unsigned prev_free_sectors;
/* the following test is not needed, but it tests the replay code */
- if (unlikely(dm_suspended(ic->ti)) && !ic->meta_dev)
+ if (unlikely(dm_suspending(ic->ti)) && !ic->meta_dev)
return;
spin_lock_irq(&ic->endio_wait.lock);
@@ -2489,7 +2489,7 @@ static void integrity_recalc(struct work
next_chunk:
- if (unlikely(dm_suspended(ic->ti)))
+ if (unlikely(dm_suspending(ic->ti)))
goto unlock_ret;
range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
Index: rhel8/include/linux/device-mapper.h
===================================================================
--- rhel8.orig/include/linux/device-mapper.h
+++ rhel8/include/linux/device-mapper.h
@@ -426,6 +426,7 @@ const char *dm_device_name(struct mapped
int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid);
struct gendisk *dm_disk(struct mapped_device *md);
int dm_suspended(struct dm_target *ti);
+int dm_suspending(struct dm_target *ti);
int dm_noflush_suspending(struct dm_target *ti);
void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
union map_info *dm_get_rq_mapinfo(struct request *rq);
--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/dm-devel
