summaryrefslogtreecommitdiffstats
path: root/drivers/md/dm.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/dm.c')
-rw-r--r--drivers/md/dm.c96
1 files changed, 70 insertions, 26 deletions
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f4ffd1eb8f44..268edf402bbb 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -810,7 +810,6 @@ static void dec_pending(struct dm_io *io, int error)
queue_io(md, bio);
} else {
/* done with normal IO or empty flush */
- trace_block_bio_complete(md->queue, bio, io_error);
bio->bi_error = io_error;
bio_endio(bio);
}
@@ -825,6 +824,14 @@ void disable_write_same(struct mapped_device *md)
limits->max_write_same_sectors = 0;
}
+void disable_write_zeroes(struct mapped_device *md)
+{
+ struct queue_limits *limits = dm_get_queue_limits(md);
+
+ /* device doesn't really support WRITE ZEROES, disable it */
+ limits->max_write_zeroes_sectors = 0;
+}
+
static void clone_endio(struct bio *bio)
{
int error = bio->bi_error;
@@ -851,9 +858,14 @@ static void clone_endio(struct bio *bio)
}
}
- if (unlikely(r == -EREMOTEIO && (bio_op(bio) == REQ_OP_WRITE_SAME) &&
- !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors))
- disable_write_same(md);
+ if (unlikely(r == -EREMOTEIO)) {
+ if (bio_op(bio) == REQ_OP_WRITE_SAME &&
+ !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)
+ disable_write_same(md);
+ if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+ !bdev_get_queue(bio->bi_bdev)->limits.max_write_zeroes_sectors)
+ disable_write_zeroes(md);
+ }
free_tio(tio);
dec_pending(io, error);
@@ -989,26 +1001,29 @@ static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
struct dm_offload *o = container_of(cb, struct dm_offload, cb);
struct bio_list list;
struct bio *bio;
+ int i;
INIT_LIST_HEAD(&o->cb.list);
if (unlikely(!current->bio_list))
return;
- list = *current->bio_list;
- bio_list_init(current->bio_list);
-
- while ((bio = bio_list_pop(&list))) {
- struct bio_set *bs = bio->bi_pool;
- if (unlikely(!bs) || bs == fs_bio_set) {
- bio_list_add(current->bio_list, bio);
- continue;
+ for (i = 0; i < 2; i++) {
+ list = current->bio_list[i];
+ bio_list_init(&current->bio_list[i]);
+
+ while ((bio = bio_list_pop(&list))) {
+ struct bio_set *bs = bio->bi_pool;
+ if (unlikely(!bs) || bs == fs_bio_set) {
+ bio_list_add(&current->bio_list[i], bio);
+ continue;
+ }
+
+ spin_lock(&bs->rescue_lock);
+ bio_list_add(&bs->rescue_list, bio);
+ queue_work(bs->rescue_workqueue, &bs->rescue_work);
+ spin_unlock(&bs->rescue_lock);
}
-
- spin_lock(&bs->rescue_lock);
- bio_list_add(&bs->rescue_list, bio);
- queue_work(bs->rescue_workqueue, &bs->rescue_work);
- spin_unlock(&bs->rescue_lock);
}
}
@@ -1089,8 +1104,18 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
__bio_clone_fast(clone, bio);
- if (bio_integrity(bio)) {
- int r = bio_integrity_clone(clone, bio, GFP_NOIO);
+ if (unlikely(bio_integrity(bio) != NULL)) {
+ int r;
+
+ if (unlikely(!dm_target_has_integrity(tio->ti->type) &&
+ !dm_target_passes_integrity(tio->ti->type))) {
+ DMWARN("%s: the target %s doesn't support integrity data.",
+ dm_device_name(tio->io->md),
+ tio->ti->type->name);
+ return -EIO;
+ }
+
+ r = bio_integrity_clone(clone, bio, GFP_NOIO);
if (r < 0)
return r;
}
@@ -1098,7 +1123,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
clone->bi_iter.bi_size = to_bytes(len);
- if (bio_integrity(bio))
+ if (unlikely(bio_integrity(bio) != NULL))
bio_integrity_trim(clone, 0, len);
return 0;
@@ -1199,6 +1224,11 @@ static unsigned get_num_write_same_bios(struct dm_target *ti)
return ti->num_write_same_bios;
}
+static unsigned get_num_write_zeroes_bios(struct dm_target *ti)
+{
+ return ti->num_write_zeroes_bios;
+}
+
typedef bool (*is_split_required_fn)(struct dm_target *ti);
static bool is_split_required_for_discard(struct dm_target *ti)
@@ -1253,6 +1283,11 @@ static int __send_write_same(struct clone_info *ci)
return __send_changing_extent_only(ci, get_num_write_same_bios, NULL);
}
+static int __send_write_zeroes(struct clone_info *ci)
+{
+ return __send_changing_extent_only(ci, get_num_write_zeroes_bios, NULL);
+}
+
/*
* Select the correct strategy for processing a non-flush bio.
*/
@@ -1267,6 +1302,8 @@ static int __split_and_process_non_flush(struct clone_info *ci)
return __send_discard(ci);
else if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
return __send_write_same(ci);
+ else if (unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES))
+ return __send_write_zeroes(ci);
ti = dm_table_find_target(ci->map, ci->sector);
if (!dm_target_is_valid(ti))
@@ -1688,6 +1725,8 @@ static void event_callback(void *context)
*/
static void __set_size(struct mapped_device *md, sector_t size)
{
+ lockdep_assert_held(&md->suspend_lock);
+
set_capacity(md->disk, size);
i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
@@ -1795,13 +1834,13 @@ void dm_unlock_md_type(struct mapped_device *md)
mutex_unlock(&md->type_lock);
}
-void dm_set_md_type(struct mapped_device *md, unsigned type)
+void dm_set_md_type(struct mapped_device *md, enum dm_queue_mode type)
{
BUG_ON(!mutex_is_locked(&md->type_lock));
md->type = type;
}
-unsigned dm_get_md_type(struct mapped_device *md)
+enum dm_queue_mode dm_get_md_type(struct mapped_device *md)
{
return md->type;
}
@@ -1828,7 +1867,7 @@ EXPORT_SYMBOL_GPL(dm_get_queue_limits);
int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
{
int r;
- unsigned type = dm_get_md_type(md);
+ enum dm_queue_mode type = dm_get_md_type(md);
switch (type) {
case DM_TYPE_REQUEST_BASED:
@@ -1859,6 +1898,9 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
if (type == DM_TYPE_DAX_BIO_BASED)
queue_flag_set_unlocked(QUEUE_FLAG_DAX, md->queue);
break;
+ case DM_TYPE_NONE:
+ WARN_ON_ONCE(true);
+ break;
}
return 0;
@@ -2137,8 +2179,6 @@ static void unlock_fs(struct mapped_device *md)
* If __dm_suspend returns 0, the device is completely quiescent
* now. There is no request-processing activity. All new requests
* are being added to md->deferred list.
- *
- * Caller must hold md->suspend_lock
*/
static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
unsigned suspend_flags, long task_state,
@@ -2156,6 +2196,8 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
*/
if (noflush)
set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
+ else
+ pr_debug("%s: suspending with flush\n", dm_device_name(md));
/*
* This gets reverted if there's an error later and the targets
@@ -2354,6 +2396,8 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla
{
struct dm_table *map = NULL;
+ lockdep_assert_held(&md->suspend_lock);
+
if (md->internal_suspend_count++)
return; /* nested internal suspend */
@@ -2544,7 +2588,7 @@ int dm_noflush_suspending(struct dm_target *ti)
}
EXPORT_SYMBOL_GPL(dm_noflush_suspending);
-struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type,
+struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_queue_mode type,
unsigned integrity, unsigned per_io_data_size)
{
struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);
OpenPOWER on IntegriCloud