dm integrity: fix integrity recalculation that is improperly skipped

commit 5df96f2b9f58a5d2dc1f30fe7de75e197f2c25f2 upstream.

Commit adc0daad366b62ca1bce3e2958a40b0b71a8b8b3 ("dm: report suspended
device during destroy") broke integrity recalculation.

The problem is dm_suspended() returns true not only during suspend,
but also during resume. So 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.

To fix this race condition, add a function dm_post_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+
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 20 insertions, 2 deletions

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 56248773a9e0..1f63084ef329 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -2298,7 +2298,7 @@ static void integrity_writer(struct work_struct *w)
 	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_post_suspending(ic->ti)) && !ic->meta_dev)
 		return;
 
 	spin_lock_irq(&ic->endio_wait.lock);
@@ -2359,7 +2359,7 @@ static void integrity_recalc(struct work_struct *w)
 
 next_chunk:
 
-	if (unlikely(dm_suspended(ic->ti)))
+	if (unlikely(dm_post_suspending(ic->ti)))
 		goto unlock_ret;
 
 	range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3cf5b354568e..67da442cbab1 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -141,6 +141,7 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr);
 #define DMF_NOFLUSH_SUSPENDING 5
 #define DMF_DEFERRED_REMOVE 6
 #define DMF_SUSPENDED_INTERNALLY 7
+#define DMF_POST_SUSPENDING 8
 
 #define DM_NUMA_NODE NUMA_NO_NODE
 static int dm_numa_node = DM_NUMA_NODE;
@@ -2390,6 +2391,7 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 	if (!dm_suspended_md(md)) {
 		dm_table_presuspend_targets(map);
 		set_bit(DMF_SUSPENDED, &md->flags);
+		set_bit(DMF_POST_SUSPENDING, &md->flags);
 		dm_table_postsuspend_targets(map);
 	}
 	/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
@@ -2712,7 +2714,9 @@ retry:
 	if (r)
 		goto out_unlock;
 
+	set_bit(DMF_POST_SUSPENDING, &md->flags);
 	dm_table_postsuspend_targets(map);
+	clear_bit(DMF_POST_SUSPENDING, &md->flags);
 
 out_unlock:
 	mutex_unlock(&md->suspend_lock);
@@ -2809,7 +2813,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla
 	(void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE,
 			    DMF_SUSPENDED_INTERNALLY);
 
+	set_bit(DMF_POST_SUSPENDING, &md->flags);
 	dm_table_postsuspend_targets(map);
+	clear_bit(DMF_POST_SUSPENDING, &md->flags);
 }
 
 static void __dm_internal_resume(struct mapped_device *md)
@@ -2970,6 +2976,11 @@ int dm_suspended_md(struct mapped_device *md)
 	return test_bit(DMF_SUSPENDED, &md->flags);
 }
 
+static int dm_post_suspending_md(struct mapped_device *md)
+{
+	return test_bit(DMF_POST_SUSPENDING, &md->flags);
+}
+
 int dm_suspended_internally_md(struct mapped_device *md)
 {
 	return test_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
@@ -2986,6 +2997,12 @@ int dm_suspended(struct dm_target *ti)
 }
 EXPORT_SYMBOL_GPL(dm_suspended);
 
+int dm_post_suspending(struct dm_target *ti)
+{
+	return dm_post_suspending_md(dm_table_get_md(ti->table));
+}
+EXPORT_SYMBOL_GPL(dm_post_suspending);
+
 int dm_noflush_suspending(struct dm_target *ti)
 {
 	return __noflush_suspending(dm_table_get_md(ti->table));
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 399ad8632356..e4e1f5c1f492 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -420,6 +420,7 @@ const char *dm_device_name(struct mapped_device *md);
 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_post_suspending(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
 void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
 void dm_remap_zone_report(struct dm_target *ti, sector_t start,