dm integrity: fix integrity recalculation that is improperly skipped

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>

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 81dc5ff0890956545c97c8f2f4c176a8c650c0ca..a83a1de1e03fa8edfb04f4081429342f1b79a8f8 100644 (file)
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -2420,7 +2420,7 @@ 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);
@@ -2481,7 +2481,7 @@ 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 52449afd58ebb76ab6e14c9a6fa18e486639c199..5b9de2f71bb076e53a40913c18ea8d4675938570 100644 (file)
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -143,6 +143,7 @@ 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;
@@ -2408,6 +2409,7 @@ 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 */
@@ -2766,7 +2768,9 @@ 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);
@@ -2863,7 +2867,9 @@ 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)
@@ -3024,6 +3030,11 @@ 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);
@@ -3040,6 +3051,12 @@ 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 8750f2dc5613ab838faf72a09db5a724603547c8..73dec4b5d5be1928ff708f2e31ff70dc97ec4255 100644 (file)
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -426,6 +426,7 @@ 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);
 union map_info *dm_get_rq_mapinfo(struct request *rq);