* io objects are allocated from here.
*/
mempool_t *io_pool;
- mempool_t *rq_pool;
struct bio_set *bs;
unsigned queue_mode;
- /*
- * We must use a mempool of dm_mpath_io structs so that we
- * can resubmit bios on error.
- */
- mempool_t *mpio_pool;
-
struct mutex work_mutex;
struct work_struct trigger_event;
typedef int (*action_fn) (struct pgpath *pgpath);
-static struct kmem_cache *_mpio_cache;
-
static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
static void trigger_event(struct work_struct *work);
static void activate_path(struct work_struct *work);
init_waitqueue_head(&m->pg_init_wait);
mutex_init(&m->work_mutex);
- m->mpio_pool = NULL;
m->queue_mode = DM_TYPE_NONE;
m->ti = ti;
m->queue_mode = DM_TYPE_MQ_REQUEST_BASED;
else
m->queue_mode = DM_TYPE_REQUEST_BASED;
- }
-
- if (m->queue_mode == DM_TYPE_REQUEST_BASED) {
- unsigned min_ios = dm_get_reserved_rq_based_ios();
-
- m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
- if (!m->mpio_pool)
- return -ENOMEM;
- }
- else if (m->queue_mode == DM_TYPE_BIO_BASED) {
+ } else if (m->queue_mode == DM_TYPE_BIO_BASED) {
INIT_WORK(&m->process_queued_bios, process_queued_bios);
/*
* bio-based doesn't support any direct scsi_dh management;
kfree(m->hw_handler_name);
kfree(m->hw_handler_params);
- mempool_destroy(m->mpio_pool);
kfree(m);
}
return info->ptr;
}
-static struct dm_mpath_io *set_mpio(struct multipath *m, union map_info *info)
-{
- struct dm_mpath_io *mpio;
-
- if (!m->mpio_pool) {
- /* Use blk-mq pdu memory requested via per_io_data_size */
- mpio = get_mpio(info);
- memset(mpio, 0, sizeof(*mpio));
- return mpio;
- }
-
- mpio = mempool_alloc(m->mpio_pool, GFP_ATOMIC);
- if (!mpio)
- return NULL;
-
- memset(mpio, 0, sizeof(*mpio));
- info->ptr = mpio;
-
- return mpio;
-}
-
-static void clear_request_fn_mpio(struct multipath *m, union map_info *info)
-{
- /* Only needed for non blk-mq (.request_fn) multipath */
- if (m->mpio_pool) {
- struct dm_mpath_io *mpio = info->ptr;
-
- info->ptr = NULL;
- mempool_free(mpio, m->mpio_pool);
- }
-}
-
static size_t multipath_per_bio_data_size(void)
{
return sizeof(struct dm_mpath_io) + sizeof(struct dm_bio_details);
/*
* Map cloned requests (request-based multipath)
*/
-static int __multipath_map(struct dm_target *ti, struct request *clone,
- union map_info *map_context,
- struct request *rq, struct request **__clone)
+static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
+ union map_info *map_context,
+ struct request **__clone)
{
struct multipath *m = ti->private;
int r = DM_MAPIO_REQUEUE;
- size_t nr_bytes = clone ? blk_rq_bytes(clone) : blk_rq_bytes(rq);
+ size_t nr_bytes = blk_rq_bytes(rq);
struct pgpath *pgpath;
struct block_device *bdev;
- struct dm_mpath_io *mpio;
+ struct dm_mpath_io *mpio = get_mpio(map_context);
+ struct request *clone;
/* Do we need to select a new pgpath? */
pgpath = lockless_dereference(m->current_pgpath);
return r;
}
- mpio = set_mpio(m, map_context);
- if (!mpio)
- /* ENOMEM, requeue */
- return r;
-
+ memset(mpio, 0, sizeof(*mpio));
mpio->pgpath = pgpath;
mpio->nr_bytes = nr_bytes;
bdev = pgpath->path.dev->bdev;
- if (clone) {
- /*
- * Old request-based interface: allocated clone is passed in.
- * Used by: .request_fn stacked on .request_fn path(s).
- */
- clone->q = bdev_get_queue(bdev);
- clone->rq_disk = bdev->bd_disk;
- clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
- } else {
- /*
- * blk-mq request-based interface; used by both:
- * .request_fn stacked on blk-mq path(s) and
- * blk-mq stacked on blk-mq path(s).
- */
- clone = blk_mq_alloc_request(bdev_get_queue(bdev),
- rq_data_dir(rq), BLK_MQ_REQ_NOWAIT);
- if (IS_ERR(clone)) {
- /* EBUSY, ENODEV or EWOULDBLOCK: requeue */
- clear_request_fn_mpio(m, map_context);
- return r;
- }
- clone->bio = clone->biotail = NULL;
- clone->rq_disk = bdev->bd_disk;
- clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
- *__clone = clone;
+ clone = blk_get_request(bdev_get_queue(bdev),
+ rq->cmd_flags | REQ_NOMERGE,
+ GFP_ATOMIC);
+ if (IS_ERR(clone)) {
+ /* EBUSY, ENODEV or EWOULDBLOCK: requeue */
+ return r;
}
+ clone->bio = clone->biotail = NULL;
+ clone->rq_disk = bdev->bd_disk;
+ clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+ *__clone = clone;
if (pgpath->pg->ps.type->start_io)
pgpath->pg->ps.type->start_io(&pgpath->pg->ps,
return DM_MAPIO_REMAPPED;
}
-static int multipath_map(struct dm_target *ti, struct request *clone,
- union map_info *map_context)
-{
- return __multipath_map(ti, clone, map_context, NULL, NULL);
-}
-
-static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
- union map_info *map_context,
- struct request **clone)
-{
- return __multipath_map(ti, NULL, map_context, rq, clone);
-}
-
static void multipath_release_clone(struct request *clone)
{
- blk_mq_free_request(clone);
+ blk_put_request(clone);
}
/*
ti->num_write_same_bios = 1;
if (m->queue_mode == DM_TYPE_BIO_BASED)
ti->per_io_data_size = multipath_per_bio_data_size();
- else if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED)
+ else
ti->per_io_data_size = sizeof(struct dm_mpath_io);
return 0;
if (ps->type->end_io)
ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
}
- clear_request_fn_mpio(m, map_context);
return r;
}
.module = THIS_MODULE,
.ctr = multipath_ctr,
.dtr = multipath_dtr,
- .map_rq = multipath_map,
.clone_and_map_rq = multipath_clone_and_map,
.release_clone_rq = multipath_release_clone,
.rq_end_io = multipath_end_io,
{
int r;
- /* allocate a slab for the dm_mpath_ios */
- _mpio_cache = KMEM_CACHE(dm_mpath_io, 0);
- if (!_mpio_cache)
- return -ENOMEM;
-
r = dm_register_target(&multipath_target);
if (r < 0) {
DMERR("request-based register failed %d", r);
bad_alloc_kmultipathd:
dm_unregister_target(&multipath_target);
bad_register_target:
- kmem_cache_destroy(_mpio_cache);
-
return r;
}
destroy_workqueue(kmultipathd);
dm_unregister_target(&multipath_target);
- kmem_cache_destroy(_mpio_cache);
}
module_init(dm_multipath_init);
dm_mq_stop_queue(q);
}
-static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
- gfp_t gfp_mask)
-{
- return mempool_alloc(md->io_pool, gfp_mask);
-}
-
-static void free_old_rq_tio(struct dm_rq_target_io *tio)
-{
- mempool_free(tio, tio->md->io_pool);
-}
-
-static struct request *alloc_old_clone_request(struct mapped_device *md,
- gfp_t gfp_mask)
-{
- return mempool_alloc(md->rq_pool, gfp_mask);
-}
-
-static void free_old_clone_request(struct mapped_device *md, struct request *rq)
-{
- mempool_free(rq, md->rq_pool);
-}
-
/*
* Partial completion handling for request-based dm
*/
static struct dm_rq_target_io *tio_from_request(struct request *rq)
{
- return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
+ return blk_mq_rq_to_pdu(rq);
}
static void rq_end_stats(struct mapped_device *md, struct request *orig)
dm_put(md);
}
-static void free_rq_clone(struct request *clone)
-{
- struct dm_rq_target_io *tio = clone->end_io_data;
- struct mapped_device *md = tio->md;
-
- blk_rq_unprep_clone(clone);
-
- /*
- * It is possible for a clone_old_rq() allocated clone to
- * get passed in -- it may not yet have a request_queue.
- * This is known to occur if the error target replaces
- * a multipath target that has a request_fn queue stacked
- * on blk-mq queue(s).
- */
- if (clone->q && clone->q->mq_ops)
- /* stacked on blk-mq queue(s) */
- tio->ti->type->release_clone_rq(clone);
- else if (!md->queue->mq_ops)
- /* request_fn queue stacked on request_fn queue(s) */
- free_old_clone_request(md, clone);
-
- if (!md->queue->mq_ops)
- free_old_rq_tio(tio);
-}
-
/*
* Complete the clone and the original request.
* Must be called without clone's queue lock held,
struct mapped_device *md = tio->md;
struct request *rq = tio->orig;
- free_rq_clone(clone);
+ blk_rq_unprep_clone(clone);
+ tio->ti->type->release_clone_rq(clone);
+
rq_end_stats(md, rq);
if (!rq->q->mq_ops)
blk_end_request_all(rq, error);
rq_completed(md, rw, true);
}
-static void dm_unprep_request(struct request *rq)
-{
- struct dm_rq_target_io *tio = tio_from_request(rq);
- struct request *clone = tio->clone;
-
- if (!rq->q->mq_ops) {
- rq->special = NULL;
- rq->rq_flags &= ~RQF_DONTPREP;
- }
-
- if (clone)
- free_rq_clone(clone);
- else if (!tio->md->queue->mq_ops)
- free_old_rq_tio(tio);
-}
-
/*
* Requeue the original request of a clone.
*/
int rw = rq_data_dir(rq);
rq_end_stats(md, rq);
- dm_unprep_request(rq);
+ if (tio->clone) {
+ blk_rq_unprep_clone(tio->clone);
+ tio->ti->type->release_clone_rq(tio->clone);
+ }
if (!rq->q->mq_ops)
dm_old_requeue_request(rq);
if (!clone) {
rq_end_stats(tio->md, rq);
rw = rq_data_dir(rq);
- if (!rq->q->mq_ops) {
+ if (!rq->q->mq_ops)
blk_end_request_all(rq, tio->error);
- rq_completed(tio->md, rw, false);
- free_old_rq_tio(tio);
- } else {
+ else
blk_mq_end_request(rq, tio->error);
- rq_completed(tio->md, rw, false);
- }
+ rq_completed(tio->md, rw, false);
return;
}
{
struct dm_rq_target_io *tio = clone->end_io_data;
- if (!clone->q->mq_ops) {
- /*
- * For just cleaning up the information of the queue in which
- * the clone was dispatched.
- * The clone is *NOT* freed actually here because it is alloced
- * from dm own mempool (RQF_ALLOCED isn't set).
- */
- __blk_put_request(clone->q, clone);
- }
-
/*
* Actual request completion is done in a softirq context which doesn't
* hold the clone's queue lock. Otherwise, deadlock could occur because:
return 0;
}
-static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
- struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
- /*
- * Create clone for use with .request_fn request_queue
- */
- struct request *clone;
-
- clone = alloc_old_clone_request(md, gfp_mask);
- if (!clone)
- return NULL;
-
- blk_rq_init(NULL, clone);
- if (setup_clone(clone, rq, tio, gfp_mask)) {
- /* -ENOMEM */
- free_old_clone_request(md, clone);
- return NULL;
- }
-
- return clone;
-}
-
static void map_tio_request(struct kthread_work *work);
static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
kthread_init_work(&tio->work, map_tio_request);
}
-static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
- struct mapped_device *md,
- gfp_t gfp_mask)
-{
- struct dm_rq_target_io *tio;
- int srcu_idx;
- struct dm_table *table;
-
- tio = alloc_old_rq_tio(md, gfp_mask);
- if (!tio)
- return NULL;
-
- init_tio(tio, rq, md);
-
- table = dm_get_live_table(md, &srcu_idx);
- /*
- * Must clone a request if this .request_fn DM device
- * is stacked on .request_fn device(s).
- */
- if (!dm_table_all_blk_mq_devices(table)) {
- if (!clone_old_rq(rq, md, tio, gfp_mask)) {
- dm_put_live_table(md, srcu_idx);
- free_old_rq_tio(tio);
- return NULL;
- }
- }
- dm_put_live_table(md, srcu_idx);
-
- return tio;
-}
-
-/*
- * Called with the queue lock held.
- */
-static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
-{
- struct mapped_device *md = q->queuedata;
- struct dm_rq_target_io *tio;
-
- if (unlikely(rq->special)) {
- DMWARN("Already has something in rq->special.");
- return BLKPREP_KILL;
- }
-
- tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
- if (!tio)
- return BLKPREP_DEFER;
-
- rq->special = tio;
- rq->rq_flags |= RQF_DONTPREP;
-
- return BLKPREP_OK;
-}
-
/*
* Returns:
* DM_MAPIO_* : the request has been processed as indicated
struct request *rq = tio->orig;
struct request *clone = NULL;
- if (tio->clone) {
- clone = tio->clone;
- r = ti->type->map_rq(ti, clone, &tio->info);
- if (r == DM_MAPIO_DELAY_REQUEUE)
- return DM_MAPIO_REQUEUE; /* .request_fn requeue is always immediate */
- } else {
- r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
- if (r < 0) {
- /* The target wants to complete the I/O */
- dm_kill_unmapped_request(rq, r);
- return r;
- }
- if (r == DM_MAPIO_REMAPPED &&
- setup_clone(clone, rq, tio, GFP_ATOMIC)) {
- /* -ENOMEM */
- ti->type->release_clone_rq(clone);
- return DM_MAPIO_REQUEUE;
- }
- }
-
+ r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
switch (r) {
case DM_MAPIO_SUBMITTED:
/* The target has taken the I/O to submit by itself later */
break;
case DM_MAPIO_REMAPPED:
+ if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
+ /* -ENOMEM */
+ ti->type->release_clone_rq(clone);
+ return DM_MAPIO_REQUEUE;
+ }
+
/* The target has remapped the I/O so dispatch it */
trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
blk_rq_pos(rq));
dm_get(md);
}
+static int __dm_rq_init_rq(struct mapped_device *md, struct request *rq)
+{
+ struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
+
+ /*
+ * Must initialize md member of tio, otherwise it won't
+ * be available in dm_mq_queue_rq.
+ */
+ tio->md = md;
+
+ if (md->init_tio_pdu) {
+ /* target-specific per-io data is immediately after the tio */
+ tio->info.ptr = tio + 1;
+ }
+
+ return 0;
+}
+
+static int dm_rq_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
+{
+ return __dm_rq_init_rq(q->rq_alloc_data, rq);
+}
+
static void map_tio_request(struct kthread_work *work)
{
struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
dm_start_request(md, rq);
tio = tio_from_request(rq);
+ init_tio(tio, rq, md);
/* Establish tio->ti before queuing work (map_tio_request) */
tio->ti = ti;
kthread_queue_work(&md->kworker, &tio->work);
/*
* Fully initialize a .request_fn request-based queue.
*/
-int dm_old_init_request_queue(struct mapped_device *md)
+int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t)
{
+ struct dm_target *immutable_tgt;
+
/* Fully initialize the queue */
+ md->queue->cmd_size = sizeof(struct dm_rq_target_io);
+ md->queue->rq_alloc_data = md;
md->queue->request_fn = dm_old_request_fn;
+ md->queue->init_rq_fn = dm_rq_init_rq;
+
+ immutable_tgt = dm_table_get_immutable_target(t);
+ if (immutable_tgt && immutable_tgt->per_io_data_size) {
+ /* any target-specific per-io data is immediately after the tio */
+ md->queue->cmd_size += immutable_tgt->per_io_data_size;
+ md->init_tio_pdu = true;
+ }
if (blk_init_allocated_queue(md->queue) < 0)
return -EINVAL;
dm_init_normal_md_queue(md);
blk_queue_softirq_done(md->queue, dm_softirq_done);
- blk_queue_prep_rq(md->queue, dm_old_prep_fn);
/* Initialize the request-based DM worker thread */
kthread_init_worker(&md->kworker);
unsigned int hctx_idx, unsigned int request_idx,
unsigned int numa_node)
{
- struct mapped_device *md = data;
- struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
-
- /*
- * Must initialize md member of tio, otherwise it won't
- * be available in dm_mq_queue_rq.
- */
- tio->md = md;
-
- if (md->init_tio_pdu) {
- /* target-specific per-io data is immediately after the tio */
- tio->info.ptr = tio + 1;
- }
-
- return 0;
+ return __dm_rq_init_rq(data, rq);
}
static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
bool dm_use_blk_mq_default(void);
bool dm_use_blk_mq(struct mapped_device *md);
-int dm_old_init_request_queue(struct mapped_device *md);
+int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t);
int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t);
void dm_mq_cleanup_mapped_device(struct mapped_device *md);
return -EIO;
}
-static int io_err_map_rq(struct dm_target *ti, struct request *clone,
- union map_info *map_context)
-{
- return -EIO;
-}
-
static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq,
union map_info *map_context,
struct request **clone)
.ctr = io_err_ctr,
.dtr = io_err_dtr,
.map = io_err_map,
- .map_rq = io_err_map_rq,
.clone_and_map_rq = io_err_clone_and_map_rq,
.release_clone_rq = io_err_release_clone_rq,
.direct_access = io_err_direct_access,
*/
struct dm_md_mempools {
mempool_t *io_pool;
- mempool_t *rq_pool;
struct bio_set *bs;
};
if (md->kworker_task)
kthread_stop(md->kworker_task);
mempool_destroy(md->io_pool);
- mempool_destroy(md->rq_pool);
if (md->bs)
bioset_free(md->bs);
goto out;
}
- BUG_ON(!p || md->io_pool || md->rq_pool || md->bs);
+ BUG_ON(!p || md->io_pool || md->bs);
md->io_pool = p->io_pool;
p->io_pool = NULL;
- md->rq_pool = p->rq_pool;
- p->rq_pool = NULL;
md->bs = p->bs;
p->bs = NULL;
switch (type) {
case DM_TYPE_REQUEST_BASED:
- r = dm_old_init_request_queue(md);
+ r = dm_old_init_request_queue(md, t);
if (r) {
DMERR("Cannot initialize queue for request-based mapped device");
return r;
unsigned integrity, unsigned per_io_data_size)
{
struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);
- struct kmem_cache *cachep = NULL;
unsigned int pool_size = 0;
unsigned int front_pad;
switch (type) {
case DM_TYPE_BIO_BASED:
case DM_TYPE_DAX_BIO_BASED:
- cachep = _io_cache;
pool_size = dm_get_reserved_bio_based_ios();
front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
+
+ pools->io_pool = mempool_create_slab_pool(pool_size, _io_cache);
+ if (!pools->io_pool)
+ goto out;
break;
case DM_TYPE_REQUEST_BASED:
- cachep = _rq_tio_cache;
- pool_size = dm_get_reserved_rq_based_ios();
- pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
- if (!pools->rq_pool)
- goto out;
- /* fall through to setup remaining rq-based pools */
case DM_TYPE_MQ_REQUEST_BASED:
- if (!pool_size)
- pool_size = dm_get_reserved_rq_based_ios();
+ pool_size = dm_get_reserved_rq_based_ios();
front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
/* per_io_data_size is used for blk-mq pdu at queue allocation */
break;
BUG();
}
- if (cachep) {
- pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
- if (!pools->io_pool)
- goto out;
- }
-
pools->bs = bioset_create_nobvec(pool_size, front_pad);
if (!pools->bs)
goto out;
return;
mempool_destroy(pools->io_pool);
- mempool_destroy(pools->rq_pool);
if (pools->bs)
bioset_free(pools->bs);
/*
* To check whether the target type is request-based or not (bio-based).
*/
-#define dm_target_request_based(t) (((t)->type->map_rq != NULL) || \
- ((t)->type->clone_and_map_rq != NULL))
+#define dm_target_request_based(t) ((t)->type->clone_and_map_rq != NULL)
/*
* To check whether the target type is a hybrid (capable of being
* = 2: The target wants to push back the io
*/
typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio);
-typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone,
- union map_info *map_context);
typedef int (*dm_clone_and_map_request_fn) (struct dm_target *ti,
struct request *rq,
union map_info *map_context,
dm_ctr_fn ctr;
dm_dtr_fn dtr;
dm_map_fn map;
- dm_map_request_fn map_rq;
dm_clone_and_map_request_fn clone_and_map_rq;
dm_release_clone_request_fn release_clone_rq;
dm_endio_fn end_io;