summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/Kconfig1
-rw-r--r--drivers/md/dm-bufio.c2
-rw-r--r--drivers/md/dm-crypt.c2
-rw-r--r--drivers/md/dm-flakey.c2
-rw-r--r--drivers/md/dm-integrity.c11
-rw-r--r--drivers/md/dm-raid.c3
-rw-r--r--drivers/md/dm.c4
-rw-r--r--drivers/md/md.c155
-rw-r--r--drivers/md/raid5.c4
9 files changed, 101 insertions, 83 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 2a8b081bce7d..3ff87cb4dc49 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -660,6 +660,7 @@ config DM_ZONED
config DM_AUDIT
bool "DM audit events"
+ depends on BLK_DEV_DM
depends on AUDIT
help
Generate audit events for device-mapper.
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index f03d7dba270c..13c65b7e1ed6 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1170,7 +1170,7 @@ static void __cache_size_refresh(void)
* If the allocation may fail we use __get_free_pages. Memory fragmentation
* won't have a fatal effect here, but it just causes flushes of some other
* buffers and more I/O will be performed. Don't use __get_free_pages if it
- * always fails (i.e. order > MAX_ORDER).
+ * always fails (i.e. order > MAX_PAGE_ORDER).
*
* If the allocation shouldn't fail we use __vmalloc. This is only for the
* initial reserve allocation, so there's no risk of wasting all vmalloc
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 2ae8560b6a14..855b482cbff1 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1673,7 +1673,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size)
unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
unsigned int remaining_size;
- unsigned int order = MAX_ORDER;
+ unsigned int order = MAX_PAGE_ORDER;
retry:
if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index f57fb821528d..7916ed9f10e8 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -434,7 +434,7 @@ static struct bio *clone_bio(struct dm_target *ti, struct flakey_c *fc, struct b
remaining_size = size;
- order = MAX_ORDER;
+ order = MAX_PAGE_ORDER;
while (remaining_size) {
struct page *pages;
unsigned size_to_add, to_copy;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index e85c688fd91e..c5f03aab4552 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1755,11 +1755,12 @@ static void integrity_metadata(struct work_struct *w)
sectors_to_process = dio->range.n_sectors;
__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
+ struct bio_vec bv_copy = bv;
unsigned int pos;
char *mem, *checksums_ptr;
again:
- mem = bvec_kmap_local(&bv);
+ mem = bvec_kmap_local(&bv_copy);
pos = 0;
checksums_ptr = checksums;
do {
@@ -1768,7 +1769,7 @@ again:
sectors_to_process -= ic->sectors_per_block;
pos += ic->sectors_per_block << SECTOR_SHIFT;
sector += ic->sectors_per_block;
- } while (pos < bv.bv_len && sectors_to_process && checksums != checksums_onstack);
+ } while (pos < bv_copy.bv_len && sectors_to_process && checksums != checksums_onstack);
kunmap_local(mem);
r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset,
@@ -1793,9 +1794,9 @@ again:
if (!sectors_to_process)
break;
- if (unlikely(pos < bv.bv_len)) {
- bv.bv_offset += pos;
- bv.bv_len -= pos;
+ if (unlikely(pos < bv_copy.bv_len)) {
+ bv_copy.bv_offset += pos;
+ bv_copy.bv_len -= pos;
goto again;
}
}
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 91ebdcc6e9a8..eb009d6bb03a 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3317,6 +3317,9 @@ static void raid_dtr(struct dm_target *ti)
mddev_lock_nointr(&rs->md);
md_stop(&rs->md);
mddev_unlock(&rs->md);
+
+ if (work_pending(&rs->md.event_work))
+ flush_work(&rs->md.event_work);
raid_set_free(rs);
}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 23c32cd1f1d8..8dcabf84d866 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2675,7 +2675,7 @@ static int lock_fs(struct mapped_device *md)
WARN_ON(test_bit(DMF_FROZEN, &md->flags));
- r = freeze_bdev(md->disk->part0);
+ r = bdev_freeze(md->disk->part0);
if (!r)
set_bit(DMF_FROZEN, &md->flags);
return r;
@@ -2685,7 +2685,7 @@ static void unlock_fs(struct mapped_device *md)
{
if (!test_bit(DMF_FROZEN, &md->flags))
return;
- thaw_bdev(md->disk->part0);
+ bdev_thaw(md->disk->part0);
clear_bit(DMF_FROZEN, &md->flags);
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index c94373d64f2c..9bdd57324c37 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -82,6 +82,14 @@ static struct module *md_cluster_mod;
static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
static struct workqueue_struct *md_wq;
+
+/*
+ * This workqueue is used for sync_work to register new sync_thread, and for
+ * del_work to remove rdev, and for event_work that is only set by dm-raid.
+ *
+ * Noted that sync_work will grab reconfig_mutex, hence never flush this
+ * workqueue whith reconfig_mutex grabbed.
+ */
static struct workqueue_struct *md_misc_wq;
struct workqueue_struct *md_bitmap_wq;
@@ -490,7 +498,7 @@ int mddev_suspend(struct mddev *mddev, bool interruptible)
}
EXPORT_SYMBOL_GPL(mddev_suspend);
-void mddev_resume(struct mddev *mddev)
+static void __mddev_resume(struct mddev *mddev, bool recovery_needed)
{
lockdep_assert_not_held(&mddev->reconfig_mutex);
@@ -507,12 +515,18 @@ void mddev_resume(struct mddev *mddev)
percpu_ref_resurrect(&mddev->active_io);
wake_up(&mddev->sb_wait);
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ if (recovery_needed)
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
mutex_unlock(&mddev->suspend_mutex);
}
+
+void mddev_resume(struct mddev *mddev)
+{
+ return __mddev_resume(mddev, true);
+}
EXPORT_SYMBOL_GPL(mddev_resume);
/*
@@ -4840,25 +4854,29 @@ action_show(struct mddev *mddev, char *page)
return sprintf(page, "%s\n", type);
}
-static void stop_sync_thread(struct mddev *mddev)
+/**
+ * stop_sync_thread() - wait for sync_thread to stop if it's running.
+ * @mddev: the array.
+ * @locked: if set, reconfig_mutex will still be held after this function
+ * return; if not set, reconfig_mutex will be released after this
+ * function return.
+ * @check_seq: if set, only wait for curent running sync_thread to stop, noted
+ * that new sync_thread can still start.
+ */
+static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
{
- if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
- return;
+ int sync_seq;
- if (mddev_lock(mddev))
- return;
+ if (check_seq)
+ sync_seq = atomic_read(&mddev->sync_seq);
- /*
- * Check again in case MD_RECOVERY_RUNNING is cleared before lock is
- * held.
- */
if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
- mddev_unlock(mddev);
+ if (!locked)
+ mddev_unlock(mddev);
return;
}
- if (work_pending(&mddev->del_work))
- flush_workqueue(md_misc_wq);
+ mddev_unlock(mddev);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
/*
@@ -4866,21 +4884,28 @@ static void stop_sync_thread(struct mddev *mddev)
* never happen
*/
md_wakeup_thread_directly(mddev->sync_thread);
+ if (work_pending(&mddev->sync_work))
+ flush_work(&mddev->sync_work);
- mddev_unlock(mddev);
+ wait_event(resync_wait,
+ !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+ (check_seq && sync_seq != atomic_read(&mddev->sync_seq)));
+
+ if (locked)
+ mddev_lock_nointr(mddev);
}
static void idle_sync_thread(struct mddev *mddev)
{
- int sync_seq = atomic_read(&mddev->sync_seq);
-
mutex_lock(&mddev->sync_mutex);
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- stop_sync_thread(mddev);
- wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) ||
- !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+ if (mddev_lock(mddev)) {
+ mutex_unlock(&mddev->sync_mutex);
+ return;
+ }
+ stop_sync_thread(mddev, false, true);
mutex_unlock(&mddev->sync_mutex);
}
@@ -4888,11 +4913,13 @@ static void frozen_sync_thread(struct mddev *mddev)
{
mutex_lock(&mddev->sync_mutex);
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- stop_sync_thread(mddev);
- wait_event(resync_wait, mddev->sync_thread == NULL &&
- !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+ if (mddev_lock(mddev)) {
+ mutex_unlock(&mddev->sync_mutex);
+ return;
+ }
+ stop_sync_thread(mddev, false, false);
mutex_unlock(&mddev->sync_mutex);
}
@@ -6264,14 +6291,7 @@ static void md_clean(struct mddev *mddev)
static void __md_stop_writes(struct mddev *mddev)
{
- set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- if (work_pending(&mddev->del_work))
- flush_workqueue(md_misc_wq);
- if (mddev->sync_thread) {
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_reap_sync_thread(mddev);
- }
-
+ stop_sync_thread(mddev, true, false);
del_timer_sync(&mddev->safemode_timer);
if (mddev->pers && mddev->pers->quiesce) {
@@ -6318,9 +6338,6 @@ static void __md_stop(struct mddev *mddev)
struct md_personality *pers = mddev->pers;
md_bitmap_destroy(mddev);
mddev_detach(mddev);
- /* Ensure ->event_work is done */
- if (mddev->event_work.func)
- flush_workqueue(md_misc_wq);
spin_lock(&mddev->lock);
mddev->pers = NULL;
spin_unlock(&mddev->lock);
@@ -6355,25 +6372,16 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
int err = 0;
int did_freeze = 0;
+ if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
+ return -EBUSY;
+
if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
did_freeze = 1;
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
- if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- /*
- * Thread might be blocked waiting for metadata update which will now
- * never happen
- */
- md_wakeup_thread_directly(mddev->sync_thread);
-
- if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
- return -EBUSY;
- mddev_unlock(mddev);
- wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
- &mddev->recovery));
+ stop_sync_thread(mddev, false, false);
wait_event(mddev->sb_wait,
!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
mddev_lock_nointr(mddev);
@@ -6383,29 +6391,30 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
mddev->sync_thread ||
test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
pr_warn("md: %s still in use.\n",mdname(mddev));
- if (did_freeze) {
- clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- md_wakeup_thread(mddev->thread);
- }
err = -EBUSY;
goto out;
}
+
if (mddev->pers) {
__md_stop_writes(mddev);
- err = -ENXIO;
- if (mddev->ro == MD_RDONLY)
+ if (mddev->ro == MD_RDONLY) {
+ err = -ENXIO;
goto out;
+ }
+
mddev->ro = MD_RDONLY;
set_disk_ro(mddev->gendisk, 1);
+ }
+
+out:
+ if ((mddev->pers && !err) || did_freeze) {
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
sysfs_notify_dirent_safe(mddev->sysfs_state);
- err = 0;
}
-out:
+
mutex_unlock(&mddev->open_mutex);
return err;
}
@@ -6426,20 +6435,8 @@ static int do_md_stop(struct mddev *mddev, int mode,
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
- if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- /*
- * Thread might be blocked waiting for metadata update which will now
- * never happen
- */
- md_wakeup_thread_directly(mddev->sync_thread);
-
- mddev_unlock(mddev);
- wait_event(resync_wait, (mddev->sync_thread == NULL &&
- !test_bit(MD_RECOVERY_RUNNING,
- &mddev->recovery)));
- mddev_lock_nointr(mddev);
+ stop_sync_thread(mddev, true, false);
mutex_lock(&mddev->open_mutex);
if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
@@ -9403,7 +9400,15 @@ static void md_start_sync(struct work_struct *ws)
goto not_running;
}
- suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+ mddev_unlock(mddev);
+ /*
+ * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+ * not set it again. Otherwise, we may cause issue like this one:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=218200
+ * Therefore, use __mddev_resume(mddev, false).
+ */
+ if (suspend)
+ __mddev_resume(mddev, false);
md_wakeup_thread(mddev->sync_thread);
sysfs_notify_dirent_safe(mddev->sysfs_action);
md_new_event();
@@ -9415,7 +9420,15 @@ not_running:
clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
- suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+ mddev_unlock(mddev);
+ /*
+ * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+ * not set it again. Otherwise, we may cause issue like this one:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=218200
+ * Therefore, use __mddev_resume(mddev, false).
+ */
+ if (suspend)
+ __mddev_resume(mddev, false);
wake_up(&resync_wait);
if (test_and_clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index dc031d42f53b..26e1e8a5e941 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5892,11 +5892,11 @@ static bool stripe_ahead_of_reshape(struct mddev *mddev, struct r5conf *conf,
int dd_idx;
for (dd_idx = 0; dd_idx < sh->disks; dd_idx++) {
- if (dd_idx == sh->pd_idx)
+ if (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
continue;
min_sector = min(min_sector, sh->dev[dd_idx].sector);
- max_sector = min(max_sector, sh->dev[dd_idx].sector);
+ max_sector = max(max_sector, sh->dev[dd_idx].sector);
}
spin_lock_irq(&conf->device_lock);
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-31 14:17:49 +0300