dm: allocate requests in target when stacking on blk-mq devices

For blk-mq request-based DM the responsibility of allocating a cloned
request is transfered from DM core to the target type.  Doing so
enables the cloned request to be allocated from the appropriate
blk-mq request_queue's pool (only the DM target, e.g. multipath, can
know which block device to send a given cloned request to).

Care was taken to preserve compatibility with old-style block request
completion that requires request-based DM _not_ acquire the clone
request's queue lock in the completion path.  As such, there are now 2
different request-based DM target_type interfaces:
1) the original .map_rq() interface will continue to be used for
   non-blk-mq devices -- the preallocated clone request is passed in
   from DM core.
2) a new .clone_and_map_rq() and .release_clone_rq() will be used for
   blk-mq devices -- blk_get_request() and blk_put_request() are used
   respectively from these hooks.

dm_table_set_type() was updated to detect if the request-based target is
being stacked on blk-mq devices, if so DM_TYPE_MQ_REQUEST_BASED is set.
DM core disallows switching the DM table's type after it is set.  This
means that there is no mixing of non-blk-mq and blk-mq devices within
the same request-based DM table.

[This patch was started by Keith and later heavily modified by Mike]

Tested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

7 files changed, 185 insertions, 48 deletions

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 2552b88f8953..863fc8c1ac06 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -11,6 +11,7 @@
 #include "dm-path-selector.h"
 #include "dm-uevent.h"
 
+#include <linux/blkdev.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/mempool.h>
@@ -378,12 +379,13 @@ static int __must_push_back(struct multipath *m)
 /*
  * Map cloned requests
  */
-static int multipath_map(struct dm_target *ti, struct request *clone,
-                         union map_info *map_context)
+static int __multipath_map(struct dm_target *ti, struct request *clone,
+                           union map_info *map_context,
+                           struct request *rq, struct request **__clone)
 {
         struct multipath *m = (struct multipath *) ti->private;
         int r = DM_MAPIO_REQUEUE;
-        size_t nr_bytes = blk_rq_bytes(clone);
+        size_t nr_bytes = clone ? blk_rq_bytes(clone) : blk_rq_bytes(rq);
         struct pgpath *pgpath;
         struct block_device *bdev;
         struct dm_mpath_io *mpio;
@@ -416,12 +418,25 @@ static int multipath_map(struct dm_target *ti, struct request *clone,
 
         bdev = pgpath->path.dev->bdev;
 
-        clone->q = bdev_get_queue(bdev);
-        clone->rq_disk = bdev->bd_disk;
-        clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-
         spin_unlock_irq(&m->lock);
 
+        if (clone) {
+                /* Old request-based interface: allocated clone is passed in */
+                clone->q = bdev_get_queue(bdev);
+                clone->rq_disk = bdev->bd_disk;
+                clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+        } else {
+                /* blk-mq request-based interface */
+                *__clone = blk_get_request(bdev_get_queue(bdev),
+                                           rq_data_dir(rq), GFP_KERNEL);
+                if (IS_ERR(*__clone))
+                        /* ENOMEM, requeue */
+                        return r;
+                (*__clone)->bio = (*__clone)->biotail = NULL;
+                (*__clone)->rq_disk = bdev->bd_disk;
+                (*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+        }
+
         if (pgpath->pg->ps.type->start_io)
                 pgpath->pg->ps.type->start_io(&pgpath->pg->ps,
                                               &pgpath->path,
@@ -434,6 +449,24 @@ out_unlock:
         return r;
 }
 
+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_put_request(clone);
+}
+
 /*
  * If we run out of usable paths, should we queue I/O or error it?
  */
@@ -1670,11 +1703,13 @@ out:
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
         .name = "multipath",
-        .version = {1, 7, 0},
+        .version = {1, 8, 0},
         .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,
         .presuspend = multipath_presuspend,
         .postsuspend = multipath_postsuspend,
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 3afae9e062f8..2d7e373955f3 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -827,6 +827,7 @@ static int dm_table_set_type(struct dm_table *t)
 {
         unsigned i;
         unsigned bio_based = 0, request_based = 0, hybrid = 0;
+        bool use_blk_mq = false;
         struct dm_target *tgt;
         struct dm_dev_internal *dd;
         struct list_head *devices;
@@ -872,11 +873,26 @@ static int dm_table_set_type(struct dm_table *t)
         /* Non-request-stackable devices can't be used for request-based dm */
         devices = dm_table_get_devices(t);
         list_for_each_entry(dd, devices, list) {
-                if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev->bdev))) {
-                        DMWARN("table load rejected: including"
-                               " non-request-stackable devices");
+                struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
+
+                if (!blk_queue_stackable(q)) {
+                        DMERR("table load rejected: including"
+                              " non-request-stackable devices");
                         return -EINVAL;
                 }
+
+                if (q->mq_ops)
+                        use_blk_mq = true;
+        }
+
+        if (use_blk_mq) {
+                /* verify _all_ devices in the table are blk-mq devices */
+                list_for_each_entry(dd, devices, list)
+                        if (!bdev_get_queue(dd->dm_dev->bdev)->mq_ops) {
+                                DMERR("table load rejected: not all devices"
+                                      " are blk-mq request-stackable");
+                                return -EINVAL;
+                        }
         }
 
         /*
@@ -890,7 +906,7 @@ static int dm_table_set_type(struct dm_table *t)
                 return -EINVAL;
         }
 
-        t->type = DM_TYPE_REQUEST_BASED;
+        t->type = !use_blk_mq ? DM_TYPE_REQUEST_BASED : DM_TYPE_MQ_REQUEST_BASED;
 
         return 0;
 }
@@ -907,7 +923,15 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
 
 bool dm_table_request_based(struct dm_table *t)
 {
-        return dm_table_get_type(t) == DM_TYPE_REQUEST_BASED;
+        unsigned table_type = dm_table_get_type(t);
+
+        return (table_type == DM_TYPE_REQUEST_BASED ||
+                table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
+bool dm_table_mq_request_based(struct dm_table *t)
+{
+        return dm_table_get_type(t) == DM_TYPE_MQ_REQUEST_BASED;
 }
 
 static int dm_table_alloc_md_mempools(struct dm_table *t)
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 242e3cec397a..925ec1b15e75 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -137,13 +137,26 @@ static int io_err_map_rq(struct dm_target *ti, struct request *clone,
         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)
+{
+        return -EIO;
+}
+
+static void io_err_release_clone_rq(struct request *clone)
+{
+}
+
 static struct target_type error_target = {
         .name = "error",
-        .version = {1, 2, 0},
+        .version = {1, 3, 0},
         .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,
 };
 
 int __init dm_target_init(void)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ae1219893948..549b815999a1 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1044,7 +1044,10 @@ static void free_rq_clone(struct request *clone)
         struct dm_rq_target_io *tio = clone->end_io_data;
 
         blk_rq_unprep_clone(clone);
-        free_clone_request(tio->md, clone);
+        if (clone->q && clone->q->mq_ops)
+                tio->ti->type->release_clone_rq(clone);
+        else
+                free_clone_request(tio->md, clone);
         free_rq_tio(tio);
 }
 
@@ -1086,7 +1089,8 @@ static void dm_unprep_request(struct request *rq)
         rq->special = NULL;
         rq->cmd_flags &= ~REQ_DONTPREP;
 
-        free_rq_clone(clone);
+        if (clone)
+                free_rq_clone(clone);
 }
 
 /*
@@ -1185,6 +1189,13 @@ static void dm_softirq_done(struct request *rq)
         struct dm_rq_target_io *tio = rq->special;
         struct request *clone = tio->clone;
 
+        if (!clone) {
+                blk_end_request_all(rq, tio->error);
+                rq_completed(tio->md, rq_data_dir(rq), false);
+                free_rq_tio(tio);
+                return;
+        }
+
         if (rq->cmd_flags & REQ_FAILED)
                 mapped = false;
 
@@ -1207,7 +1218,7 @@ static void dm_complete_request(struct request *rq, int error)
  * Complete the not-mapped clone and the original request with the error status
  * through softirq context.
  * Target's rq_end_io() function isn't called.
- * This may be used when the target's map_rq() function fails.
+ * This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
  */
 static void dm_kill_unmapped_request(struct request *rq, int error)
 {
@@ -1222,13 +1233,15 @@ static void end_clone_request(struct request *clone, int error)
 {
         struct dm_rq_target_io *tio = clone->end_io_data;
 
-        /*
-         * 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 and REQ_ALLOCED isn't set in clone->cmd_flags.
-         */
-        __blk_put_request(clone->q, clone);
+        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 (REQ_ALLOCED isn't set).
+                 */
+                __blk_put_request(clone->q, clone);
+        }
 
         /*
          * Actual request completion is done in a softirq context which doesn't
@@ -1789,6 +1802,8 @@ static struct dm_rq_target_io *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_rq_tio(md, gfp_mask);
         if (!tio)
@@ -1802,10 +1817,15 @@ static struct dm_rq_target_io *prep_tio(struct request *rq,
         memset(&tio->info, 0, sizeof(tio->info));
         init_kthread_work(&tio->work, map_tio_request);
 
-        if (!clone_rq(rq, md, tio, gfp_mask)) {
-                free_rq_tio(tio);
-                return NULL;
+        table = dm_get_live_table(md, &srcu_idx);
+        if (!dm_table_mq_request_based(table)) {
+                if (!clone_rq(rq, md, tio, gfp_mask)) {
+                        dm_put_live_table(md, srcu_idx);
+                        free_rq_tio(tio);
+                        return NULL;
+                }
         }
+        dm_put_live_table(md, srcu_idx);
 
         return tio;
 }
@@ -1835,17 +1855,36 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq)
 
 /*
  * Returns:
- * 0  : the request has been processed (not requeued)
- * !0 : the request has been requeued
+ * 0                : the request has been processed
+ * DM_MAPIO_REQUEUE : the original request needs to be requeued
+ * < 0              : the request was completed due to failure
  */
 static int map_request(struct dm_target *ti, struct request *rq,
                        struct mapped_device *md)
 {
-        int r, requeued = 0;
+        int r;
         struct dm_rq_target_io *tio = rq->special;
-        struct request *clone = tio->clone;
+        struct request *clone = NULL;
+
+        if (tio->clone) {
+                clone = tio->clone;
+                r = ti->type->map_rq(ti, clone, &tio->info);
+        } 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 (IS_ERR(clone))
+                        return DM_MAPIO_REQUEUE;
+                if (setup_clone(clone, rq, tio, GFP_KERNEL)) {
+                        /* -ENOMEM */
+                        ti->type->release_clone_rq(clone);
+                        return DM_MAPIO_REQUEUE;
+                }
+        }
 
-        r = ti->type->map_rq(ti, clone, &tio->info);
         switch (r) {
         case DM_MAPIO_SUBMITTED:
                 /* The target has taken the I/O to submit by itself later */
@@ -1859,7 +1898,6 @@ static int map_request(struct dm_target *ti, struct request *rq,
         case DM_MAPIO_REQUEUE:
                 /* The target wants to requeue the I/O */
                 dm_requeue_unmapped_request(clone);
-                requeued = 1;
                 break;
         default:
                 if (r > 0) {
@@ -1869,17 +1907,20 @@ static int map_request(struct dm_target *ti, struct request *rq,
 
                 /* The target wants to complete the I/O */
                 dm_kill_unmapped_request(rq, r);
-                break;
+                return r;
         }
 
-        return requeued;
+        return 0;
 }
 
 static void map_tio_request(struct kthread_work *work)
 {
         struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
+        struct request *rq = tio->orig;
+        struct mapped_device *md = tio->md;
 
-        map_request(tio->ti, tio->orig, tio->md);
+        if (map_request(tio->ti, rq, md) == DM_MAPIO_REQUEUE)
+                dm_requeue_unmapped_original_request(md, rq);
 }
 
 static void dm_start_request(struct mapped_device *md, struct request *orig)
@@ -2459,6 +2500,14 @@ unsigned dm_get_md_type(struct mapped_device *md)
         return md->type;
 }
 
+static bool dm_md_type_request_based(struct mapped_device *md)
+{
+        unsigned table_type = dm_get_md_type(md);
+
+        return (table_type == DM_TYPE_REQUEST_BASED ||
+                table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
 struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
 {
         return md->immutable_target_type;
@@ -2511,8 +2560,7 @@ static int dm_init_request_based_queue(struct mapped_device *md)
  */
 int dm_setup_md_queue(struct mapped_device *md)
 {
-        if ((dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) &&
-            !dm_init_request_based_queue(md)) {
+        if (dm_md_type_request_based(md) && !dm_init_request_based_queue(md)) {
                 DMWARN("Cannot initialize queue for request-based mapped device");
                 return -EINVAL;
         }
@@ -3184,27 +3232,35 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u
 {
         struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL);
         struct kmem_cache *cachep;
-        unsigned int pool_size;
+        unsigned int pool_size = 0;
         unsigned int front_pad;
 
         if (!pools)
                 return NULL;
 
-        if (type == DM_TYPE_BIO_BASED) {
+        switch (type) {
+        case DM_TYPE_BIO_BASED:
                 cachep = _io_cache;
                 pool_size = dm_get_reserved_bio_based_ios();
                 front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
-        } else if (type == DM_TYPE_REQUEST_BASED) {
-                cachep = _rq_tio_cache;
+                break;
+        case DM_TYPE_REQUEST_BASED:
                 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:
+                cachep = _rq_tio_cache;
+                if (!pool_size)
+                        pool_size = dm_get_reserved_rq_based_ios();
                 front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
                 /* per_bio_data_size is not used. See __bind_mempools(). */
                 WARN_ON(per_bio_data_size != 0);
-        } else
+                break;
+        default:
                 goto out;
+        }
 
         pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
         if (!pools->io_pool)
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 84b0f9e4ba6c..84d79784b866 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -34,9 +34,10 @@
 /*
  * Type of table and mapped_device's mempool
  */
-#define DM_TYPE_NONE            0
-#define DM_TYPE_BIO_BASED       1
-#define DM_TYPE_REQUEST_BASED   2
+#define DM_TYPE_NONE                    0
+#define DM_TYPE_BIO_BASED               1
+#define DM_TYPE_REQUEST_BASED           2
+#define DM_TYPE_MQ_REQUEST_BASED        3
 
 /*
  * List of devices that a metadevice uses and should open/close.
@@ -73,6 +74,7 @@ int dm_table_any_busy_target(struct dm_table *t);
 unsigned dm_table_get_type(struct dm_table *t);
 struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
+bool dm_table_mq_request_based(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
 
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 19296fba58e8..2646aed1d3fe 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -48,6 +48,11 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti);
 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,
+                                            struct request **clone);
+typedef void (*dm_release_clone_request_fn) (struct request *clone);
 
 /*
  * Returns:
@@ -143,6 +148,8 @@ struct target_type {
         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;
         dm_request_endio_fn rq_end_io;
         dm_presuspend_fn presuspend;
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index a570d7b5796c..889f3a5b7b18 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY     _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR        4
-#define DM_VERSION_MINOR        29
+#define DM_VERSION_MINOR        30
 #define DM_VERSION_PATCHLEVEL   0
-#define DM_VERSION_EXTRA        "-ioctl (2014-10-28)"
+#define DM_VERSION_EXTRA        "-ioctl (2014-12-22)"
 
 /* Status bits */
 #define DM_READONLY_FLAG        (1 << 0) /* In/Out */