summaryrefslogtreecommitdiff
path: root/drivers/block/rbd.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block/rbd.c')
-rw-r--r--drivers/block/rbd.c82
1 files changed, 36 insertions, 46 deletions
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 12b5d53ec856..faafd7ff43d6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -362,7 +362,7 @@ enum rbd_watch_state {
enum rbd_lock_state {
RBD_LOCK_STATE_UNLOCKED,
RBD_LOCK_STATE_LOCKED,
- RBD_LOCK_STATE_RELEASING,
+ RBD_LOCK_STATE_QUIESCING,
};
/* WatchNotify::ClientId */
@@ -422,7 +422,7 @@ struct rbd_device {
struct list_head running_list;
struct completion acquire_wait;
int acquire_err;
- struct completion releasing_wait;
+ struct completion quiescing_wait;
spinlock_t object_map_lock;
u8 *object_map;
@@ -525,7 +525,7 @@ static bool __rbd_is_lock_owner(struct rbd_device *rbd_dev)
lockdep_assert_held(&rbd_dev->lock_rwsem);
return rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED ||
- rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING;
+ rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING;
}
static bool rbd_is_lock_owner(struct rbd_device *rbd_dev)
@@ -575,7 +575,7 @@ static const struct attribute_group rbd_bus_group = {
};
__ATTRIBUTE_GROUPS(rbd_bus);
-static struct bus_type rbd_bus_type = {
+static const struct bus_type rbd_bus_type = {
.name = "rbd",
.bus_groups = rbd_bus_groups,
};
@@ -3457,13 +3457,14 @@ static void rbd_lock_del_request(struct rbd_img_request *img_req)
lockdep_assert_held(&rbd_dev->lock_rwsem);
spin_lock(&rbd_dev->lock_lists_lock);
if (!list_empty(&img_req->lock_item)) {
+ rbd_assert(!list_empty(&rbd_dev->running_list));
list_del_init(&img_req->lock_item);
- need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
+ need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING &&
list_empty(&rbd_dev->running_list));
}
spin_unlock(&rbd_dev->lock_lists_lock);
if (need_wakeup)
- complete(&rbd_dev->releasing_wait);
+ complete(&rbd_dev->quiescing_wait);
}
static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
@@ -3476,11 +3477,6 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
if (rbd_lock_add_request(img_req))
return 1;
- if (rbd_dev->opts->exclusive) {
- WARN_ON(1); /* lock got released? */
- return -EROFS;
- }
-
/*
* Note the use of mod_delayed_work() in rbd_acquire_lock()
* and cancel_delayed_work() in wake_lock_waiters().
@@ -4181,16 +4177,16 @@ static bool rbd_quiesce_lock(struct rbd_device *rbd_dev)
/*
* Ensure that all in-flight IO is flushed.
*/
- rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING;
- rbd_assert(!completion_done(&rbd_dev->releasing_wait));
+ rbd_dev->lock_state = RBD_LOCK_STATE_QUIESCING;
+ rbd_assert(!completion_done(&rbd_dev->quiescing_wait));
if (list_empty(&rbd_dev->running_list))
return true;
up_write(&rbd_dev->lock_rwsem);
- wait_for_completion(&rbd_dev->releasing_wait);
+ wait_for_completion(&rbd_dev->quiescing_wait);
down_write(&rbd_dev->lock_rwsem);
- if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING)
+ if (rbd_dev->lock_state != RBD_LOCK_STATE_QUIESCING)
return false;
rbd_assert(list_empty(&rbd_dev->running_list));
@@ -4601,6 +4597,10 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev)
rbd_warn(rbd_dev, "failed to update lock cookie: %d",
ret);
+ if (rbd_dev->opts->exclusive)
+ rbd_warn(rbd_dev,
+ "temporarily releasing lock on exclusive mapping");
+
/*
* Lock cookie cannot be updated on older OSDs, so do
* a manual release and queue an acquire.
@@ -4949,16 +4949,21 @@ static const struct blk_mq_ops rbd_mq_ops = {
static int rbd_init_disk(struct rbd_device *rbd_dev)
{
struct gendisk *disk;
- struct request_queue *q;
unsigned int objset_bytes =
rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
+ struct queue_limits lim = {
+ .max_hw_sectors = objset_bytes >> SECTOR_SHIFT,
+ .io_opt = objset_bytes,
+ .io_min = rbd_dev->opts->alloc_size,
+ .max_segments = USHRT_MAX,
+ .max_segment_size = UINT_MAX,
+ };
int err;
memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set));
rbd_dev->tag_set.ops = &rbd_mq_ops;
rbd_dev->tag_set.queue_depth = rbd_dev->opts->queue_depth;
rbd_dev->tag_set.numa_node = NUMA_NO_NODE;
- rbd_dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
rbd_dev->tag_set.nr_hw_queues = num_present_cpus();
rbd_dev->tag_set.cmd_size = sizeof(struct rbd_img_request);
@@ -4966,12 +4971,20 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
if (err)
return err;
- disk = blk_mq_alloc_disk(&rbd_dev->tag_set, rbd_dev);
+ if (rbd_dev->opts->trim) {
+ lim.discard_granularity = rbd_dev->opts->alloc_size;
+ lim.max_hw_discard_sectors = objset_bytes >> SECTOR_SHIFT;
+ lim.max_write_zeroes_sectors = objset_bytes >> SECTOR_SHIFT;
+ }
+
+ if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
+ lim.features |= BLK_FEAT_STABLE_WRITES;
+
+ disk = blk_mq_alloc_disk(&rbd_dev->tag_set, &lim, rbd_dev);
if (IS_ERR(disk)) {
err = PTR_ERR(disk);
goto out_tag_set;
}
- q = disk->queue;
snprintf(disk->disk_name, sizeof(disk->disk_name), RBD_DRV_NAME "%d",
rbd_dev->dev_id);
@@ -4983,26 +4996,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
disk->minors = RBD_MINORS_PER_MAJOR;
disk->fops = &rbd_bd_ops;
disk->private_data = rbd_dev;
-
- blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
- /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
-
- blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT);
- q->limits.max_sectors = queue_max_hw_sectors(q);
- blk_queue_max_segments(q, USHRT_MAX);
- blk_queue_max_segment_size(q, UINT_MAX);
- blk_queue_io_min(q, rbd_dev->opts->alloc_size);
- blk_queue_io_opt(q, rbd_dev->opts->alloc_size);
-
- if (rbd_dev->opts->trim) {
- q->limits.discard_granularity = rbd_dev->opts->alloc_size;
- blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
- blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
- }
-
- if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
-
rbd_dev->disk = disk;
return 0;
@@ -5382,7 +5375,7 @@ static struct rbd_device *__rbd_dev_create(struct rbd_spec *spec)
INIT_LIST_HEAD(&rbd_dev->acquiring_list);
INIT_LIST_HEAD(&rbd_dev->running_list);
init_completion(&rbd_dev->acquire_wait);
- init_completion(&rbd_dev->releasing_wait);
+ init_completion(&rbd_dev->quiescing_wait);
spin_lock_init(&rbd_dev->object_map_lock);
@@ -6588,11 +6581,6 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
if (ret)
return ret;
- /*
- * The lock may have been released by now, unless automatic lock
- * transitions are disabled.
- */
- rbd_assert(!rbd_dev->opts->exclusive || rbd_is_lock_owner(rbd_dev));
return 0;
}
@@ -7293,8 +7281,10 @@ static ssize_t do_rbd_remove(const char *buf, size_t count)
* Prevent new IO from being queued and wait for existing
* IO to complete/fail.
*/
- blk_mq_freeze_queue(rbd_dev->disk->queue);
+ unsigned int memflags = blk_mq_freeze_queue(rbd_dev->disk->queue);
+
blk_mark_disk_dead(rbd_dev->disk);
+ blk_mq_unfreeze_queue(rbd_dev->disk->queue, memflags);
}
del_gendisk(rbd_dev->disk);
generated by cgit (git 2.34.1) at 2025-08-02 08:09:38 +0000