aboutsummaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/dm-bufio.c12
-rw-r--r--drivers/md/dm-raid.c11
-rw-r--r--drivers/md/dm-thin.c16
-rw-r--r--drivers/md/md.c4
-rw-r--r--drivers/md/persistent-data/dm-btree-internal.h6
-rw-r--r--drivers/md/persistent-data/dm-btree-spine.c2
-rw-r--r--drivers/md/persistent-data/dm-btree.c24
7 files changed, 46 insertions, 29 deletions
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index ca1621b49453..a1cebf745b22 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1448,9 +1448,9 @@ static void drop_buffers(struct dm_bufio_client *c)
/*
* Test if the buffer is unused and too old, and commit it.
- * At if noio is set, we must not do any I/O because we hold
- * dm_bufio_clients_lock and we would risk deadlock if the I/O gets rerouted to
- * different bufio client.
+ * And if GFP_NOFS is used, we must not do any I/O because we hold
+ * dm_bufio_clients_lock and we would risk deadlock if the I/O gets
+ * rerouted to different bufio client.
*/
static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp,
unsigned long max_jiffies)
@@ -1458,7 +1458,7 @@ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp,
if (jiffies - b->last_accessed < max_jiffies)
return 0;
- if (!(gfp & __GFP_IO)) {
+ if (!(gfp & __GFP_FS)) {
if (test_bit(B_READING, &b->state) ||
test_bit(B_WRITING, &b->state) ||
test_bit(B_DIRTY, &b->state))
@@ -1500,7 +1500,7 @@ dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
unsigned long freed;
c = container_of(shrink, struct dm_bufio_client, shrinker);
- if (sc->gfp_mask & __GFP_IO)
+ if (sc->gfp_mask & __GFP_FS)
dm_bufio_lock(c);
else if (!dm_bufio_trylock(c))
return SHRINK_STOP;
@@ -1517,7 +1517,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
unsigned long count;
c = container_of(shrink, struct dm_bufio_client, shrinker);
- if (sc->gfp_mask & __GFP_IO)
+ if (sc->gfp_mask & __GFP_FS)
dm_bufio_lock(c);
else if (!dm_bufio_trylock(c))
return 0;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 4880b69e2e9e..59715389b3cf 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -785,8 +785,7 @@ struct dm_raid_superblock {
__le32 layout;
__le32 stripe_sectors;
- __u8 pad[452]; /* Round struct to 512 bytes. */
- /* Always set to 0 when writing. */
+ /* Remainder of a logical block is zero-filled when writing (see super_sync()). */
} __packed;
static int read_disk_sb(struct md_rdev *rdev, int size)
@@ -823,7 +822,7 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
test_bit(Faulty, &(rs->dev[i].rdev.flags)))
failed_devices |= (1ULL << i);
- memset(sb, 0, sizeof(*sb));
+ memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
sb->magic = cpu_to_le32(DM_RAID_MAGIC);
sb->features = cpu_to_le32(0); /* No features yet */
@@ -858,7 +857,11 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
uint64_t events_sb, events_refsb;
rdev->sb_start = 0;
- rdev->sb_size = sizeof(*sb);
+ rdev->sb_size = bdev_logical_block_size(rdev->meta_bdev);
+ if (rdev->sb_size < sizeof(*sb) || rdev->sb_size > PAGE_SIZE) {
+ DMERR("superblock size of a logical block is no longer valid");
+ return -EINVAL;
+ }
ret = read_disk_sb(rdev, rdev->sb_size);
if (ret)
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 359af3a519b5..37f2648c112b 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -1704,6 +1704,14 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
return DM_MAPIO_SUBMITTED;
}
+ /*
+ * We must hold the virtual cell before doing the lookup, otherwise
+ * there's a race with discard.
+ */
+ build_virtual_key(tc->td, block, &key);
+ if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result))
+ return DM_MAPIO_SUBMITTED;
+
r = dm_thin_find_block(td, block, 0, &result);
/*
@@ -1727,13 +1735,10 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
* shared flag will be set in their case.
*/
thin_defer_bio(tc, bio);
+ cell_defer_no_holder_no_free(tc, &cell1);
return DM_MAPIO_SUBMITTED;
}
- build_virtual_key(tc->td, block, &key);
- if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result))
- return DM_MAPIO_SUBMITTED;
-
build_data_key(tc->td, result.block, &key);
if (dm_bio_detain(tc->pool->prison, &key, bio, &cell2, &cell_result)) {
cell_defer_no_holder_no_free(tc, &cell1);
@@ -1754,6 +1759,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
* of doing so.
*/
handle_unserviceable_bio(tc->pool, bio);
+ cell_defer_no_holder_no_free(tc, &cell1);
return DM_MAPIO_SUBMITTED;
}
/* fall through */
@@ -1764,6 +1770,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
* provide the hint to load the metadata into cache.
*/
thin_defer_bio(tc, bio);
+ cell_defer_no_holder_no_free(tc, &cell1);
return DM_MAPIO_SUBMITTED;
default:
@@ -1773,6 +1780,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
* pool is switched to fail-io mode.
*/
bio_io_error(bio);
+ cell_defer_no_holder_no_free(tc, &cell1);
return DM_MAPIO_SUBMITTED;
}
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 73aedcb639c0..40959ee73583 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5333,6 +5333,7 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
printk("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;
@@ -5347,6 +5348,8 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
mddev->ro = 1;
set_disk_ro(mddev->gendisk, 1);
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;
}
@@ -5390,6 +5393,7 @@ static int do_md_stop(struct mddev * mddev, int mode,
mutex_unlock(&mddev->open_mutex);
if (did_freeze) {
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
return -EBUSY;
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index 37d367bb9aa8..bf2b80d5c470 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -42,6 +42,12 @@ struct btree_node {
} __packed;
+/*
+ * Locks a block using the btree node validator.
+ */
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+ struct dm_block **result);
+
void inc_children(struct dm_transaction_manager *tm, struct btree_node *n,
struct dm_btree_value_type *vt);
diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
index cf9fd676ae44..1b5e13ec7f96 100644
--- a/drivers/md/persistent-data/dm-btree-spine.c
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -92,7 +92,7 @@ struct dm_block_validator btree_node_validator = {
/*----------------------------------------------------------------*/
-static int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
struct dm_block **result)
{
return dm_tm_read_lock(info->tm, b, &btree_node_validator, result);
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 416060c25709..200ac12a1d40 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -847,22 +847,26 @@ EXPORT_SYMBOL_GPL(dm_btree_find_lowest_key);
* FIXME: We shouldn't use a recursive algorithm when we have limited stack
* space. Also this only works for single level trees.
*/
-static int walk_node(struct ro_spine *s, dm_block_t block,
+static int walk_node(struct dm_btree_info *info, dm_block_t block,
int (*fn)(void *context, uint64_t *keys, void *leaf),
void *context)
{
int r;
unsigned i, nr;
+ struct dm_block *node;
struct btree_node *n;
uint64_t keys;
- r = ro_step(s, block);
- n = ro_node(s);
+ r = bn_read_lock(info, block, &node);
+ if (r)
+ return r;
+
+ n = dm_block_data(node);
nr = le32_to_cpu(n->header.nr_entries);
for (i = 0; i < nr; i++) {
if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) {
- r = walk_node(s, value64(n, i), fn, context);
+ r = walk_node(info, value64(n, i), fn, context);
if (r)
goto out;
} else {
@@ -874,7 +878,7 @@ static int walk_node(struct ro_spine *s, dm_block_t block,
}
out:
- ro_pop(s);
+ dm_tm_unlock(info->tm, node);
return r;
}
@@ -882,15 +886,7 @@ int dm_btree_walk(struct dm_btree_info *info, dm_block_t root,
int (*fn)(void *context, uint64_t *keys, void *leaf),
void *context)
{
- int r;
- struct ro_spine spine;
-
BUG_ON(info->levels > 1);
-
- init_ro_spine(&spine, info);
- r = walk_node(&spine, root, fn, context);
- exit_ro_spine(&spine);
-
- return r;
+ return walk_node(info, root, fn, context);
}
EXPORT_SYMBOL_GPL(dm_btree_walk);
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-28 08:16:54 +0000