Merge branch 'for-4.2/core' of git://git.kernel.dk/linux-block

Pull core block IO update from Jens Axboe:
 "Nothing really major in here, mostly a collection of smaller
  optimizations and cleanups, mixed with various fixes.  In more detail,
  this contains:

   - Addition of policy specific data to blkcg for block cgroups.  From
     Arianna Avanzini.

   - Various cleanups around command types from Christoph.

   - Cleanup of the suspend block I/O path from Christoph.

   - Plugging updates from Shaohua and Jeff Moyer, for blk-mq.

   - Eliminating atomic inc/dec of both remaining IO count and reference
     count in a bio.  From me.

   - Fixes for SG gap and chunk size support for data-less (discards)
     IO, so we can merge these better.  From me.

   - Small restructuring of blk-mq shared tag support, freeing drivers
     from iterating hardware queues.  From Keith Busch.

   - A few cfq-iosched tweaks, from Tahsin Erdogan and me.  Makes the
     IOPS mode the default for non-rotational storage"

* 'for-4.2/core' of git://git.kernel.dk/linux-block: (35 commits)
  cfq-iosched: fix other locations where blkcg_to_cfqgd() can return NULL
  cfq-iosched: fix sysfs oops when attempting to read unconfigured weights
  cfq-iosched: move group scheduling functions under ifdef
  cfq-iosched: fix the setting of IOPS mode on SSDs
  blktrace: Add blktrace.c to BLOCK LAYER in MAINTAINERS file
  block, cgroup: implement policy-specific per-blkcg data
  block: Make CFQ default to IOPS mode on SSDs
  block: add blk_set_queue_dying() to blkdev.h
  blk-mq: Shared tag enhancements
  block: don't honor chunk sizes for data-less IO
  block: only honor SG gap prevention for merges that contain data
  block: fix returnvar.cocci warnings
  block, dm: don't copy bios for request clones
  block: remove management of bi_remaining when restoring original bi_end_io
  block: replace trylock with mutex_lock in blkdev_reread_part()
  block: export blkdev_reread_part() and __blkdev_reread_part()
  suspend: simplify block I/O handling
  block: collapse bio bit space
  block: remove unused BIO_RW_BLOCK and BIO_EOF flags
  block: remove BIO_EOPNOTSUPP
  ...

MAINTAINERS

@@ -2075,6 +2075,7 @@ M:	Jens Axboe <axboe@kernel.dk>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 S:	Maintained
 F:	block/
+F:	kernel/trace/blktrace.c
 
 BLOCK2MTD DRIVER
 M:	Joern Engel <joern@lazybastard.org>

block/bio-integrity.c

@@ -361,7 +361,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
-	bio_endio_nodec(bio, error);
+	bio_endio(bio, error);
 }
 
 /**
@@ -388,7 +388,7 @@ void bio_integrity_endio(struct bio *bio, int error)
 	 */
 	if (error) {
 		bio->bi_end_io = bip->bip_end_io;
-		bio_endio_nodec(bio, error);
+		bio_endio(bio, error);
 
 		return;
 	}

block/bio.c

@@ -270,8 +270,8 @@ void bio_init(struct bio *bio)
 {
 	memset(bio, 0, sizeof(*bio));
 	bio->bi_flags = 1 << BIO_UPTODATE;
-	atomic_set(&bio->bi_remaining, 1);
+	atomic_set(&bio->__bi_remaining, 1);
-	atomic_set(&bio->bi_cnt, 1);
+	atomic_set(&bio->__bi_cnt, 1);
 }
 EXPORT_SYMBOL(bio_init);
 
@@ -292,8 +292,8 @@ void bio_reset(struct bio *bio)
 	__bio_free(bio);
 
 	memset(bio, 0, BIO_RESET_BYTES);
-	bio->bi_flags = flags|(1 << BIO_UPTODATE);
+	bio->bi_flags = flags | (1 << BIO_UPTODATE);
-	atomic_set(&bio->bi_remaining, 1);
+	atomic_set(&bio->__bi_remaining, 1);
 }
 EXPORT_SYMBOL(bio_reset);
 
@@ -303,6 +303,17 @@ static void bio_chain_endio(struct bio *bio, int error)
 	bio_put(bio);
 }
 
+/*
+ * Increment chain count for the bio. Make sure the CHAIN flag update
+ * is visible before the raised count.
+ */
+static inline void bio_inc_remaining(struct bio *bio)
+{
+	bio->bi_flags |= (1 << BIO_CHAIN);
+	smp_mb__before_atomic();
+	atomic_inc(&bio->__bi_remaining);
+}
+
 /**
  * bio_chain - chain bio completions
  * @bio: the target bio
@@ -320,7 +331,7 @@ void bio_chain(struct bio *bio, struct bio *parent)
 
 	bio->bi_private = parent;
 	bio->bi_end_io	= bio_chain_endio;
-	atomic_inc(&parent->bi_remaining);
+	bio_inc_remaining(parent);
 }
 EXPORT_SYMBOL(bio_chain);
 
@@ -524,13 +535,17 @@ EXPORT_SYMBOL(zero_fill_bio);
  **/
 void bio_put(struct bio *bio)
 {
-	BIO_BUG_ON(!atomic_read(&bio->bi_cnt));
+	if (!bio_flagged(bio, BIO_REFFED))
-
-	/*
-	 * last put frees it
-	 */
-	if (atomic_dec_and_test(&bio->bi_cnt))
 		bio_free(bio);
+	else {
+		BIO_BUG_ON(!atomic_read(&bio->__bi_cnt));
+
+		/*
+		 * last put frees it
+		 */
+		if (atomic_dec_and_test(&bio->__bi_cnt))
+			bio_free(bio);
+	}
 }
 EXPORT_SYMBOL(bio_put);
 
@@ -1741,6 +1756,25 @@ void bio_flush_dcache_pages(struct bio *bi)
 EXPORT_SYMBOL(bio_flush_dcache_pages);
 #endif
 
+static inline bool bio_remaining_done(struct bio *bio)
+{
+	/*
+	 * If we're not chaining, then ->__bi_remaining is always 1 and
+	 * we always end io on the first invocation.
+	 */
+	if (!bio_flagged(bio, BIO_CHAIN))
+		return true;
+
+	BUG_ON(atomic_read(&bio->__bi_remaining) <= 0);
+
+	if (atomic_dec_and_test(&bio->__bi_remaining)) {
+		clear_bit(BIO_CHAIN, &bio->bi_flags);
+		return true;
+	}
+
+	return false;
+}
+
 /**
  * bio_endio - end I/O on a bio
  * @bio:	bio
@@ -1758,15 +1792,13 @@ EXPORT_SYMBOL(bio_flush_dcache_pages);
 void bio_endio(struct bio *bio, int error)
 {
 	while (bio) {
-		BUG_ON(atomic_read(&bio->bi_remaining) <= 0);
-
 		if (error)
 			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 			error = -EIO;
 
-		if (!atomic_dec_and_test(&bio->bi_remaining))
+		if (unlikely(!bio_remaining_done(bio)))
-			return;
+			break;
 
 		/*
 		 * Need to have a real endio function for chained bios,
@@ -1789,21 +1821,6 @@ void bio_endio(struct bio *bio, int error)
 }
 EXPORT_SYMBOL(bio_endio);
 
-/**
- * bio_endio_nodec - end I/O on a bio, without decrementing bi_remaining
- * @bio:	bio
- * @error:	error, if any
- *
- * For code that has saved and restored bi_end_io; thing hard before using this
- * function, probably you should've cloned the entire bio.
- **/
-void bio_endio_nodec(struct bio *bio, int error)
-{
-	atomic_inc(&bio->bi_remaining);
-	bio_endio(bio, error);
-}
-EXPORT_SYMBOL(bio_endio_nodec);
-
 /**
  * bio_split - split a bio
  * @bio:	bio to split

block/blk-cgroup.c

@@ -9,6 +9,10 @@
  *
  * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
  * 	              Nauman Rafique <nauman@google.com>
+ *
+ * For policy-specific per-blkcg data:
+ * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *                    Arianna Avanzini <avanzini.arianna@gmail.com>
  */
 #include <linux/ioprio.h>
 #include <linux/kdev_t.h>
@@ -26,8 +30,7 @@
 
 static DEFINE_MUTEX(blkcg_pol_mutex);
 
-struct blkcg blkcg_root = { .cfq_weight = 2 * CFQ_WEIGHT_DEFAULT,
+struct blkcg blkcg_root;
-			    .cfq_leaf_weight = 2 * CFQ_WEIGHT_DEFAULT, };
 EXPORT_SYMBOL_GPL(blkcg_root);
 
 static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
@@ -823,6 +826,8 @@ static struct cgroup_subsys_state *
 blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct blkcg *blkcg;
+	struct cgroup_subsys_state *ret;
+	int i;
 
 	if (!parent_css) {
 		blkcg = &blkcg_root;
@@ -830,17 +835,49 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 	}
 
 	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
-	if (!blkcg)
+	if (!blkcg) {
-		return ERR_PTR(-ENOMEM);
+		ret = ERR_PTR(-ENOMEM);
+		goto free_blkcg;
+	}
+
+	for (i = 0; i < BLKCG_MAX_POLS ; i++) {
+		struct blkcg_policy *pol = blkcg_policy[i];
+		struct blkcg_policy_data *cpd;
+
+		/*
+		 * If the policy hasn't been attached yet, wait for it
+		 * to be attached before doing anything else. Otherwise,
+		 * check if the policy requires any specific per-cgroup
+		 * data: if it does, allocate and initialize it.
+		 */
+		if (!pol || !pol->cpd_size)
+			continue;
+
+		BUG_ON(blkcg->pd[i]);
+		cpd = kzalloc(pol->cpd_size, GFP_KERNEL);
+		if (!cpd) {
+			ret = ERR_PTR(-ENOMEM);
+			goto free_pd_blkcg;
+		}
+		blkcg->pd[i] = cpd;
+		cpd->plid = i;
+		pol->cpd_init_fn(blkcg);
+	}
 
-	blkcg->cfq_weight = CFQ_WEIGHT_DEFAULT;
-	blkcg->cfq_leaf_weight = CFQ_WEIGHT_DEFAULT;
 done:
 	spin_lock_init(&blkcg->lock);
 	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC);
 	INIT_HLIST_HEAD(&blkcg->blkg_list);
 
 	return &blkcg->css;
+
+free_pd_blkcg:
+	for (i--; i >= 0; i--)
+		kfree(blkcg->pd[i]);
+
+free_blkcg:
+	kfree(blkcg);
+	return ret;
 }
 
 /**
@@ -958,8 +995,10 @@ int blkcg_activate_policy(struct request_queue *q,
 			  const struct blkcg_policy *pol)
 {
 	LIST_HEAD(pds);
+	LIST_HEAD(cpds);
 	struct blkcg_gq *blkg, *new_blkg;
-	struct blkg_policy_data *pd, *n;
+	struct blkg_policy_data *pd, *nd;
+	struct blkcg_policy_data *cpd, *cnd;
 	int cnt = 0, ret;
 	bool preloaded;
 
@@ -1003,7 +1042,10 @@ int blkcg_activate_policy(struct request_queue *q,
 
 	spin_unlock_irq(q->queue_lock);
 
-	/* allocate policy_data for all existing blkgs */
+	/*
+	 * Allocate per-blkg and per-blkcg policy data
+	 * for all existing blkgs.
+	 */
 	while (cnt--) {
 		pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
 		if (!pd) {
@@ -1011,26 +1053,50 @@ int blkcg_activate_policy(struct request_queue *q,
 			goto out_free;
 		}
 		list_add_tail(&pd->alloc_node, &pds);
+
+		if (!pol->cpd_size)
+			continue;
+		cpd = kzalloc_node(pol->cpd_size, GFP_KERNEL, q->node);
+		if (!cpd) {
+			ret = -ENOMEM;
+			goto out_free;
+		}
+		list_add_tail(&cpd->alloc_node, &cpds);
 	}
 
 	/*
-	 * Install the allocated pds.  With @q bypassing, no new blkg
+	 * Install the allocated pds and cpds. With @q bypassing, no new blkg
 	 * should have been created while the queue lock was dropped.
 	 */
 	spin_lock_irq(q->queue_lock);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
-		if (WARN_ON(list_empty(&pds))) {
+		if (WARN_ON(list_empty(&pds)) ||
+		    WARN_ON(pol->cpd_size && list_empty(&cpds))) {
 			/* umm... this shouldn't happen, just abort */
 			ret = -ENOMEM;
 			goto out_unlock;
 		}
+		cpd = list_first_entry(&cpds, struct blkcg_policy_data,
+				       alloc_node);
+		list_del_init(&cpd->alloc_node);
 		pd = list_first_entry(&pds, struct blkg_policy_data, alloc_node);
 		list_del_init(&pd->alloc_node);
 
 		/* grab blkcg lock too while installing @pd on @blkg */
 		spin_lock(&blkg->blkcg->lock);
 
+		if (!pol->cpd_size)
+			goto no_cpd;
+		if (!blkg->blkcg->pd[pol->plid]) {
+			/* Per-policy per-blkcg data */
+			blkg->blkcg->pd[pol->plid] = cpd;
+			cpd->plid = pol->plid;
+			pol->cpd_init_fn(blkg->blkcg);
+		} else { /* must free it as it has already been extracted */
+			kfree(cpd);
+		}
+no_cpd:
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
@@ -1045,8 +1111,10 @@ out_unlock:
 	spin_unlock_irq(q->queue_lock);
 out_free:
 	blk_queue_bypass_end(q);
-	list_for_each_entry_safe(pd, n, &pds, alloc_node)
+	list_for_each_entry_safe(pd, nd, &pds, alloc_node)
 		kfree(pd);
+	list_for_each_entry_safe(cpd, cnd, &cpds, alloc_node)
+		kfree(cpd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blkcg_activate_policy);
@@ -1087,6 +1155,8 @@ void blkcg_deactivate_policy(struct request_queue *q,
 
 		kfree(blkg->pd[pol->plid]);
 		blkg->pd[pol->plid] = NULL;
+		kfree(blkg->blkcg->pd[pol->plid]);
+		blkg->blkcg->pd[pol->plid] = NULL;
 
 		spin_unlock(&blkg->blkcg->lock);
 	}

block/blk-cgroup.h

@@ -23,11 +23,6 @@
 /* Max limits for throttle policy */
 #define THROTL_IOPS_MAX		UINT_MAX
 
-/* CFQ specific, out here for blkcg->cfq_weight */
-#define CFQ_WEIGHT_MIN		10
-#define CFQ_WEIGHT_MAX		1000
-#define CFQ_WEIGHT_DEFAULT	500
-
 #ifdef CONFIG_BLK_CGROUP
 
 enum blkg_rwstat_type {
@@ -50,9 +45,7 @@ struct blkcg {
 	struct blkcg_gq			*blkg_hint;
 	struct hlist_head		blkg_list;
 
-	/* TODO: per-policy storage in blkcg */
+	struct blkcg_policy_data	*pd[BLKCG_MAX_POLS];
-	unsigned int			cfq_weight;	/* belongs to cfq */
-	unsigned int			cfq_leaf_weight;
 };
 
 struct blkg_stat {
@@ -87,6 +80,24 @@ struct blkg_policy_data {
 	struct list_head		alloc_node;
 };
 
+/*
+ * Policies that need to keep per-blkcg data which is independent
+ * from any request_queue associated to it must specify its size
+ * with the cpd_size field of the blkcg_policy structure and
+ * embed a blkcg_policy_data in it. blkcg core allocates
+ * policy-specific per-blkcg structures lazily the first time
+ * they are actually needed, so it handles them together with
+ * blkgs. cpd_init() is invoked to let each policy handle
+ * per-blkcg data.
+ */
+struct blkcg_policy_data {
+	/* the policy id this per-policy data belongs to */
+	int				plid;
+
+	/* used during policy activation */
+	struct list_head		alloc_node;
+};
+
 /* association between a blk cgroup and a request queue */
 struct blkcg_gq {
 	/* Pointer to the associated request_queue */
@@ -112,6 +123,7 @@ struct blkcg_gq {
 	struct rcu_head			rcu_head;
 };
 
+typedef void (blkcg_pol_init_cpd_fn)(const struct blkcg *blkcg);
 typedef void (blkcg_pol_init_pd_fn)(struct blkcg_gq *blkg);
 typedef void (blkcg_pol_online_pd_fn)(struct blkcg_gq *blkg);
 typedef void (blkcg_pol_offline_pd_fn)(struct blkcg_gq *blkg);
@@ -122,10 +134,13 @@ struct blkcg_policy {
 	int				plid;
 	/* policy specific private data size */
 	size_t				pd_size;
+	/* policy specific per-blkcg data size */
+	size_t				cpd_size;
 	/* cgroup files for the policy */
 	struct cftype			*cftypes;
 
 	/* operations */
+	blkcg_pol_init_cpd_fn		*cpd_init_fn;
 	blkcg_pol_init_pd_fn		*pd_init_fn;
 	blkcg_pol_online_pd_fn		*pd_online_fn;
 	blkcg_pol_offline_pd_fn		*pd_offline_fn;
@@ -218,6 +233,12 @@ static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
 	return blkg ? blkg->pd[pol->plid] : NULL;
 }
 
+static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg,
+						     struct blkcg_policy *pol)
+{
+	return blkcg ? blkcg->pd[pol->plid] : NULL;
+}
+
 /**
  * pdata_to_blkg - get blkg associated with policy private data
  * @pd: policy private data of interest
@@ -564,6 +585,9 @@ struct blkcg;
 struct blkg_policy_data {
 };
 
+struct blkcg_policy_data {
+};
+
 struct blkcg_gq {
 };
 

block/blk-core.c

@@ -117,7 +117,7 @@ EXPORT_SYMBOL(blk_rq_init);
 static void req_bio_endio(struct request *rq, struct bio *bio,
 			  unsigned int nbytes, int error)
 {
-	if (error)
+	if (error && !(rq->cmd_flags & REQ_CLONE))
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
 	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 		error = -EIO;
@@ -128,7 +128,8 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+	if (bio->bi_iter.bi_size == 0 &&
+	    !(rq->cmd_flags & (REQ_FLUSH_SEQ|REQ_CLONE)))
 		bio_endio(bio, error);
 }
 
@@ -285,6 +286,7 @@ inline void __blk_run_queue_uncond(struct request_queue *q)
 	q->request_fn(q);
 	q->request_fn_active--;
 }
+EXPORT_SYMBOL_GPL(__blk_run_queue_uncond);
 
 /**
  * __blk_run_queue - run a single device queue
@@ -1525,7 +1527,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
  * Caller must ensure !blk_queue_nomerges(q) beforehand.
  */
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
-			    unsigned int *request_count)
+			    unsigned int *request_count,
+			    struct request **same_queue_rq)
 {
 	struct blk_plug *plug;
 	struct request *rq;
@@ -1545,8 +1548,16 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	list_for_each_entry_reverse(rq, plug_list, queuelist) {
 		int el_ret;
 
-		if (rq->q == q)
+		if (rq->q == q) {
 			(*request_count)++;
+			/*
+			 * Only blk-mq multiple hardware queues case checks the
+			 * rq in the same queue, there should be only one such
+			 * rq in a queue
+			 **/
+			if (same_queue_rq)
+				*same_queue_rq = rq;
+		}
 
 		if (rq->q != q || !blk_rq_merge_ok(rq, bio))
 			continue;
@@ -1611,7 +1622,7 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 * any locks.
 	 */
 	if (!blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count))
+	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
 		return;
 
 	spin_lock_irq(q->queue_lock);
@@ -1718,8 +1729,6 @@ static void handle_bad_sector(struct bio *bio)
 			bio->bi_rw,
 			(unsigned long long)bio_end_sector(bio),
 			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
-
-	set_bit(BIO_EOF, &bio->bi_flags);
 }
 
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -2904,95 +2913,22 @@ int blk_lld_busy(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_lld_busy);
 
-/**
+void blk_rq_prep_clone(struct request *dst, struct request *src)
- * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
- * @rq: the clone request to be cleaned up
- *
- * Description:
- *     Free all bios in @rq for a cloned request.
- */
-void blk_rq_unprep_clone(struct request *rq)
-{
-	struct bio *bio;
-
-	while ((bio = rq->bio) != NULL) {
-		rq->bio = bio->bi_next;
-
-		bio_put(bio);
-	}
-}
-EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
-
-/*
- * Copy attributes of the original request to the clone request.
- * The actual data parts (e.g. ->cmd, ->sense) are not copied.
- */
-static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
+	dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK);
+	dst->cmd_flags |= REQ_NOMERGE | REQ_CLONE;
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
 	dst->nr_phys_segments = src->nr_phys_segments;
 	dst->ioprio = src->ioprio;
 	dst->extra_len = src->extra_len;
-}
+	dst->bio = src->bio;
-
+	dst->biotail = src->biotail;
-/**
+	dst->cmd = src->cmd;
- * blk_rq_prep_clone - Helper function to setup clone request
+	dst->cmd_len = src->cmd_len;
- * @rq: the request to be setup
+	dst->sense = src->sense;
- * @rq_src: original request to be cloned
- * @bs: bio_set that bios for clone are allocated from
- * @gfp_mask: memory allocation mask for bio
- * @bio_ctr: setup function to be called for each clone bio.
- *           Returns %0 for success, non %0 for failure.
- * @data: private data to be passed to @bio_ctr
- *
- * Description:
- *     Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
- *     The actual data parts of @rq_src (e.g. ->cmd, ->sense)
- *     are not copied, and copying such parts is the caller's responsibility.
- *     Also, pages which the original bios are pointing to are not copied
- *     and the cloned bios just point same pages.
- *     So cloned bios must be completed before original bios, which means
- *     the caller must complete @rq before @rq_src.
- */
-int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
-		      struct bio_set *bs, gfp_t gfp_mask,
-		      int (*bio_ctr)(struct bio *, struct bio *, void *),
-		      void *data)
-{
-	struct bio *bio, *bio_src;
-
-	if (!bs)
-		bs = fs_bio_set;
-
-	__rq_for_each_bio(bio_src, rq_src) {
-		bio = bio_clone_fast(bio_src, gfp_mask, bs);
-		if (!bio)
-			goto free_and_out;
-
-		if (bio_ctr && bio_ctr(bio, bio_src, data))
-			goto free_and_out;
-
-		if (rq->bio) {
-			rq->biotail->bi_next = bio;
-			rq->biotail = bio;
-		} else
-			rq->bio = rq->biotail = bio;
-	}
-
-	__blk_rq_prep_clone(rq, rq_src);
-
-	return 0;
-
-free_and_out:
-	if (bio)
-		bio_put(bio);
-	blk_rq_unprep_clone(rq);
-
-	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
 
@@ -3034,21 +2970,20 @@ void blk_start_plug(struct blk_plug *plug)
 {
 	struct task_struct *tsk = current;
 
+	/*
+	 * If this is a nested plug, don't actually assign it.
+	 */
+	if (tsk->plug)
+		return;
+
 	INIT_LIST_HEAD(&plug->list);
 	INIT_LIST_HEAD(&plug->mq_list);
 	INIT_LIST_HEAD(&plug->cb_list);
-
 	/*
-	 * If this is a nested plug, don't actually assign it. It will be
+	 * Store ordering should not be needed here, since a potential
-	 * flushed on its own.
+	 * preempt will imply a full memory barrier
 	 */
-	if (!tsk->plug) {
+	tsk->plug = plug;
-		/*
-		 * Store ordering should not be needed here, since a potential
-		 * preempt will imply a full memory barrier
-		 */
-		tsk->plug = plug;
-	}
 }
 EXPORT_SYMBOL(blk_start_plug);
 
@@ -3195,10 +3130,11 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 
 void blk_finish_plug(struct blk_plug *plug)
 {
+	if (plug != current->plug)
+		return;
 	blk_flush_plug_list(plug, false);
 
-	if (plug == current->plug)
+	current->plug = NULL;
-		current->plug = NULL;
 }
 EXPORT_SYMBOL(blk_finish_plug);
 

block/blk-exec.c

@@ -53,7 +53,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 			   rq_end_io_fn *done)
 {
 	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
-	bool is_pm_resume;
 
 	WARN_ON(irqs_disabled());
 	WARN_ON(rq->cmd_type == REQ_TYPE_FS);
@@ -70,12 +69,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 		return;
 	}
 
-	/*
-	 * need to check this before __blk_run_queue(), because rq can
-	 * be freed before that returns.
-	 */
-	is_pm_resume = rq->cmd_type == REQ_TYPE_PM_RESUME;
-
 	spin_lock_irq(q->queue_lock);
 
 	if (unlikely(blk_queue_dying(q))) {
@@ -88,9 +81,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	__elv_add_request(q, rq, where);
 	__blk_run_queue(q);
-	/* the queue is stopped so it won't be run */
-	if (is_pm_resume)
-		__blk_run_queue_uncond(q);
 	spin_unlock_irq(q->queue_lock);
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);

block/blk-merge.c

@@ -589,7 +589,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	    !blk_write_same_mergeable(rq->bio, bio))
 		return false;
 
-	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
+	/* Only check gaps if the bio carries data */
+	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) && bio_has_data(bio)) {
 		struct bio_vec *bprev;
 
 		bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];

block/blk-mq-tag.c

@@ -438,6 +438,39 @@ static void bt_for_each(struct blk_mq_hw_ctx *hctx,
 	}
 }
 
+static void bt_tags_for_each(struct blk_mq_tags *tags,
+		struct blk_mq_bitmap_tags *bt, unsigned int off,
+		busy_tag_iter_fn *fn, void *data, bool reserved)
+{
+	struct request *rq;
+	int bit, i;
+
+	if (!tags->rqs)
+		return;
+	for (i = 0; i < bt->map_nr; i++) {
+		struct blk_align_bitmap *bm = &bt->map[i];
+
+		for (bit = find_first_bit(&bm->word, bm->depth);
+		     bit < bm->depth;
+		     bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
+			rq = blk_mq_tag_to_rq(tags, off + bit);
+			fn(rq, data, reserved);
+		}
+
+		off += (1 << bt->bits_per_word);
+	}
+}
+
+void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
+		void *priv)
+{
+	if (tags->nr_reserved_tags)
+		bt_tags_for_each(tags, &tags->breserved_tags, 0, fn, priv, true);
+	bt_tags_for_each(tags, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
+			false);
+}
+EXPORT_SYMBOL(blk_mq_all_tag_busy_iter);
+
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
 		void *priv)
 {
@@ -580,6 +613,11 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	if (!tags)
 		return NULL;
 
+	if (!zalloc_cpumask_var(&tags->cpumask, GFP_KERNEL)) {
+		kfree(tags);
+		return NULL;
+	}
+
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 

block/blk-mq-tag.h

@@ -44,6 +44,7 @@ struct blk_mq_tags {
 	struct list_head page_list;
 
 	int alloc_policy;
+	cpumask_var_t cpumask;
 };
 
 

block/blk-mq.c

@@ -89,7 +89,8 @@ static int blk_mq_queue_enter(struct request_queue *q, gfp_t gfp)
 			return -EBUSY;
 
 		ret = wait_event_interruptible(q->mq_freeze_wq,
-				!q->mq_freeze_depth || blk_queue_dying(q));
+				!atomic_read(&q->mq_freeze_depth) ||
+				blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
 		if (ret)
@@ -112,13 +113,10 @@ static void blk_mq_usage_counter_release(struct percpu_ref *ref)
 
 void blk_mq_freeze_queue_start(struct request_queue *q)
 {
-	bool freeze;
+	int freeze_depth;
 
-	spin_lock_irq(q->queue_lock);
+	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
-	freeze = !q->mq_freeze_depth++;
+	if (freeze_depth == 1) {
-	spin_unlock_irq(q->queue_lock);
-
-	if (freeze) {
 		percpu_ref_kill(&q->mq_usage_counter);
 		blk_mq_run_hw_queues(q, false);
 	}
@@ -143,13 +141,11 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
 void blk_mq_unfreeze_queue(struct request_queue *q)
 {
-	bool wake;
+	int freeze_depth;
 
-	spin_lock_irq(q->queue_lock);
+	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
-	wake = !--q->mq_freeze_depth;
+	WARN_ON_ONCE(freeze_depth < 0);
-	WARN_ON_ONCE(q->mq_freeze_depth < 0);
+	if (!freeze_depth) {
-	spin_unlock_irq(q->queue_lock);
-	if (wake) {
 		percpu_ref_reinit(&q->mq_usage_counter);
 		wake_up_all(&q->mq_freeze_wq);
 	}
@@ -1237,6 +1233,38 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	return rq;
 }
 
+static int blk_mq_direct_issue_request(struct request *rq)
+{
+	int ret;
+	struct request_queue *q = rq->q;
+	struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q,
+			rq->mq_ctx->cpu);
+	struct blk_mq_queue_data bd = {
+		.rq = rq,
+		.list = NULL,
+		.last = 1
+	};
+
+	/*
+	 * For OK queue, we are done. For error, kill it. Any other
+	 * error (busy), just add it to our list as we previously
+	 * would have done
+	 */
+	ret = q->mq_ops->queue_rq(hctx, &bd);
+	if (ret == BLK_MQ_RQ_QUEUE_OK)
+		return 0;
+	else {
+		__blk_mq_requeue_request(rq);
+
+		if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+			return 0;
+		}
+		return -1;
+	}
+}
+
 /*
  * Multiple hardware queue variant. This will not use per-process plugs,
  * but will attempt to bypass the hctx queueing if we can go straight to
@@ -1248,6 +1276,9 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
 	struct blk_map_ctx data;
 	struct request *rq;
+	unsigned int request_count = 0;
+	struct blk_plug *plug;
+	struct request *same_queue_rq = NULL;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1256,6 +1287,10 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		return;
 	}
 
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
+		return;
+
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
 		return;
@@ -1266,38 +1301,42 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		goto run_queue;
 	}
 
+	plug = current->plug;
 	/*
 	 * If the driver supports defer issued based on 'last', then
 	 * queue it up like normal since we can potentially save some
 	 * CPU this way.
 	 */
-	if (is_sync && !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
+	if (((plug && !blk_queue_nomerges(q)) || is_sync) &&
-		struct blk_mq_queue_data bd = {
+	    !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
-			.rq = rq,
+		struct request *old_rq = NULL;
-			.list = NULL,
-			.last = 1
-		};
-		int ret;
 
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
-		 * For OK queue, we are done. For error, kill it. Any other
+		 * we do limited pluging. If bio can be merged, do merge.
-		 * error (busy), just add it to our list as we previously
+		 * Otherwise the existing request in the plug list will be
-		 * would have done
+		 * issued. So the plug list will have one request at most
 		 */
-		ret = q->mq_ops->queue_rq(data.hctx, &bd);
+		if (plug) {
-		if (ret == BLK_MQ_RQ_QUEUE_OK)
+			/*
-			goto done;
+			 * The plug list might get flushed before this. If that
-		else {
+			 * happens, same_queue_rq is invalid and plug list is empty
-			__blk_mq_requeue_request(rq);
+			 **/
-
+			if (same_queue_rq && !list_empty(&plug->mq_list)) {
-			if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
+				old_rq = same_queue_rq;
-				rq->errors = -EIO;
+				list_del_init(&old_rq->queuelist);
-				blk_mq_end_request(rq, rq->errors);
-				goto done;
 			}
-		}
+			list_add_tail(&rq->queuelist, &plug->mq_list);
+		} else /* is_sync */
+			old_rq = rq;
+		blk_mq_put_ctx(data.ctx);
+		if (!old_rq)
+			return;
+		if (!blk_mq_direct_issue_request(old_rq))
+			return;
+		blk_mq_insert_request(old_rq, false, true, true);
+		return;
 	}
 
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
@@ -1310,7 +1349,6 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
-done:
 	blk_mq_put_ctx(data.ctx);
 }
 
@@ -1322,16 +1360,11 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = rw_is_sync(bio->bi_rw);
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
-	unsigned int use_plug, request_count = 0;
+	struct blk_plug *plug;
+	unsigned int request_count = 0;
 	struct blk_map_ctx data;
 	struct request *rq;
 
-	/*
-	 * If we have multiple hardware queues, just go directly to
-	 * one of those for sync IO.
-	 */
-	use_plug = !is_flush_fua && !is_sync;
-
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
@@ -1339,8 +1372,8 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		return;
 	}
 
-	if (use_plug && !blk_queue_nomerges(q) &&
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count))
+	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
 		return;
 
 	rq = blk_mq_map_request(q, bio, &data);
@@ -1358,21 +1391,18 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	 * utilize that to temporarily store requests until the task is
 	 * either done or scheduled away.
 	 */
-	if (use_plug) {
+	plug = current->plug;
-		struct blk_plug *plug = current->plug;
+	if (plug) {
-
+		blk_mq_bio_to_request(rq, bio);
-		if (plug) {
+		if (list_empty(&plug->mq_list))
-			blk_mq_bio_to_request(rq, bio);
+			trace_block_plug(q);
-			if (list_empty(&plug->mq_list))
+		else if (request_count >= BLK_MAX_REQUEST_COUNT) {
-				trace_block_plug(q);
+			blk_flush_plug_list(plug, false);
-			else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+			trace_block_plug(q);
-				blk_flush_plug_list(plug, false);
-				trace_block_plug(q);
-			}
-			list_add_tail(&rq->queuelist, &plug->mq_list);
-			blk_mq_put_ctx(data.ctx);
-			return;
 		}
+		list_add_tail(&rq->queuelist, &plug->mq_list);
+		blk_mq_put_ctx(data.ctx);
+		return;
 	}
 
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
@@ -1508,7 +1538,6 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 			i++;
 		}
 	}
-
 	return tags;
 
 fail:
@@ -1792,6 +1821,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 
 		hctx = q->mq_ops->map_queue(q, i);
 		cpumask_set_cpu(i, hctx->cpumask);
+		cpumask_set_cpu(i, hctx->tags->cpumask);
 		ctx->index_hw = hctx->nr_ctx;
 		hctx->ctxs[hctx->nr_ctx++] = ctx;
 	}
@@ -2056,7 +2086,7 @@ void blk_mq_free_queue(struct request_queue *q)
 /* Basically redo blk_mq_init_queue with queue frozen */
 static void blk_mq_queue_reinit(struct request_queue *q)
 {
-	WARN_ON_ONCE(!q->mq_freeze_depth);
+	WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
 
 	blk_mq_sysfs_unregister(q);
 
@@ -2173,6 +2203,12 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 	return 0;
 }
 
+struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags)
+{
+	return tags->cpumask;
+}
+EXPORT_SYMBOL_GPL(blk_mq_tags_cpumask);
+
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -2234,8 +2270,10 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 	int i;
 
 	for (i = 0; i < set->nr_hw_queues; i++) {
-		if (set->tags[i])
+		if (set->tags[i]) {
 			blk_mq_free_rq_map(set, set->tags[i], i);
+			free_cpumask_var(set->tags[i]->cpumask);
+		}
 	}
 
 	kfree(set->tags);

block/blk.h

@@ -78,7 +78,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 			    struct bio *bio);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
-			    unsigned int *request_count);
+			    unsigned int *request_count,
+			    struct request **same_queue_rq);
 
 void blk_account_io_start(struct request *req, bool new_io);
 void blk_account_io_completion(struct request *req, unsigned int bytes);
@@ -193,8 +194,6 @@ int blk_try_merge(struct request *rq, struct bio *bio);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
-void __blk_run_queue_uncond(struct request_queue *q);
-
 int blk_dev_init(void);
 
 

block/bounce.c

@@ -128,9 +128,6 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
 	struct bio_vec *bvec, *org_vec;
 	int i;
 
-	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
-		set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
-
 	/*
 	 * free up bounce indirect pages used
 	 */

block/cfq-iosched.c

@@ -67,6 +67,11 @@ static struct kmem_cache *cfq_pool;
 #define sample_valid(samples)	((samples) > 80)
 #define rb_entry_cfqg(node)	rb_entry((node), struct cfq_group, rb_node)
 
+/* blkio-related constants */
+#define CFQ_WEIGHT_MIN          10
+#define CFQ_WEIGHT_MAX          1000
+#define CFQ_WEIGHT_DEFAULT      500
+
 struct cfq_ttime {
 	unsigned long last_end_request;
 
@@ -212,6 +217,15 @@ struct cfqg_stats {
 #endif	/* CONFIG_CFQ_GROUP_IOSCHED */
 };
 
+/* Per-cgroup data */
+struct cfq_group_data {
+	/* must be the first member */
+	struct blkcg_policy_data pd;
+
+	unsigned int weight;
+	unsigned int leaf_weight;
+};
+
 /* This is per cgroup per device grouping structure */
 struct cfq_group {
 	/* must be the first member */
@@ -446,16 +460,6 @@ CFQ_CFQQ_FNS(deep);
 CFQ_CFQQ_FNS(wait_busy);
 #undef CFQ_CFQQ_FNS
 
-static inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd)
-{
-	return pd ? container_of(pd, struct cfq_group, pd) : NULL;
-}
-
-static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg)
-{
-	return pd_to_blkg(&cfqg->pd);
-}
-
 #if defined(CONFIG_CFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
 
 /* cfqg stats flags */
@@ -600,6 +604,22 @@ static inline void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg) { }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 
+static inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd)
+{
+	return pd ? container_of(pd, struct cfq_group, pd) : NULL;
+}
+
+static struct cfq_group_data
+*cpd_to_cfqgd(struct blkcg_policy_data *cpd)
+{
+	return cpd ? container_of(cpd, struct cfq_group_data, pd) : NULL;
+}
+
+static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg)
+{
+	return pd_to_blkg(&cfqg->pd);
+}
+
 static struct blkcg_policy blkcg_policy_cfq;
 
 static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
@@ -607,6 +627,11 @@ static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
 	return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq));
 }
 
+static struct cfq_group_data *blkcg_to_cfqgd(struct blkcg *blkcg)
+{
+	return cpd_to_cfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_cfq));
+}
+
 static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg)
 {
 	struct blkcg_gq *pblkg = cfqg_to_blkg(cfqg)->parent;
@@ -1544,13 +1569,28 @@ static void cfqg_stats_init(struct cfqg_stats *stats)
 #endif
 }
 
+static void cfq_cpd_init(const struct blkcg *blkcg)
+{
+	struct cfq_group_data *cgd =
+		cpd_to_cfqgd(blkcg->pd[blkcg_policy_cfq.plid]);
+
+	if (blkcg == &blkcg_root) {
+		cgd->weight = 2 * CFQ_WEIGHT_DEFAULT;
+		cgd->leaf_weight = 2 * CFQ_WEIGHT_DEFAULT;
+	} else {
+		cgd->weight = CFQ_WEIGHT_DEFAULT;
+		cgd->leaf_weight = CFQ_WEIGHT_DEFAULT;
+	}
+}
+
 static void cfq_pd_init(struct blkcg_gq *blkg)
 {
 	struct cfq_group *cfqg = blkg_to_cfqg(blkg);
+	struct cfq_group_data *cgd = blkcg_to_cfqgd(blkg->blkcg);
 
 	cfq_init_cfqg_base(cfqg);
-	cfqg->weight = blkg->blkcg->cfq_weight;
+	cfqg->weight = cgd->weight;
-	cfqg->leaf_weight = blkg->blkcg->cfq_leaf_weight;
+	cfqg->leaf_weight = cgd->leaf_weight;
 	cfqg_stats_init(&cfqg->stats);
 	cfqg_stats_init(&cfqg->dead_stats);
 }
@@ -1673,13 +1713,27 @@ static int cfqg_print_leaf_weight_device(struct seq_file *sf, void *v)
 
 static int cfq_print_weight(struct seq_file *sf, void *v)
 {
-	seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_weight);
+	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+	struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg);
+	unsigned int val = 0;
+
+	if (cgd)
+		val = cgd->weight;
+
+	seq_printf(sf, "%u\n", val);
 	return 0;
 }
 
 static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
 {
-	seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_leaf_weight);
+	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+	struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg);
+	unsigned int val = 0;
+
+	if (cgd)
+		val = cgd->leaf_weight;
+
+	seq_printf(sf, "%u\n", val);
 	return 0;
 }
 
@@ -1690,6 +1744,7 @@ static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
 	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct cfq_group *cfqg;
+	struct cfq_group_data *cfqgd;
 	int ret;
 
 	ret = blkg_conf_prep(blkcg, &blkcg_policy_cfq, buf, &ctx);
@@ -1698,17 +1753,22 @@ static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
 
 	ret = -EINVAL;
 	cfqg = blkg_to_cfqg(ctx.blkg);
+	cfqgd = blkcg_to_cfqgd(blkcg);
+	if (!cfqg || !cfqgd)
+		goto err;
+
 	if (!ctx.v || (ctx.v >= CFQ_WEIGHT_MIN && ctx.v <= CFQ_WEIGHT_MAX)) {
 		if (!is_leaf_weight) {
 			cfqg->dev_weight = ctx.v;
-			cfqg->new_weight = ctx.v ?: blkcg->cfq_weight;
+			cfqg->new_weight = ctx.v ?: cfqgd->weight;
 		} else {
 			cfqg->dev_leaf_weight = ctx.v;
-			cfqg->new_leaf_weight = ctx.v ?: blkcg->cfq_leaf_weight;
+			cfqg->new_leaf_weight = ctx.v ?: cfqgd->leaf_weight;
 		}
 		ret = 0;
 	}
 
+err:
 	blkg_conf_finish(&ctx);
 	return ret ?: nbytes;
 }
@@ -1730,16 +1790,23 @@ static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
+	struct cfq_group_data *cfqgd;
+	int ret = 0;
 
 	if (val < CFQ_WEIGHT_MIN || val > CFQ_WEIGHT_MAX)
 		return -EINVAL;
 
 	spin_lock_irq(&blkcg->lock);
+	cfqgd = blkcg_to_cfqgd(blkcg);
+	if (!cfqgd) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	if (!is_leaf_weight)
-		blkcg->cfq_weight = val;
+		cfqgd->weight = val;
 	else
-		blkcg->cfq_leaf_weight = val;
+		cfqgd->leaf_weight = val;
 
 	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
 		struct cfq_group *cfqg = blkg_to_cfqg(blkg);
@@ -1749,15 +1816,16 @@ static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
 
 		if (!is_leaf_weight) {
 			if (!cfqg->dev_weight)
-				cfqg->new_weight = blkcg->cfq_weight;
+				cfqg->new_weight = cfqgd->weight;
 		} else {
 			if (!cfqg->dev_leaf_weight)
-				cfqg->new_leaf_weight = blkcg->cfq_leaf_weight;
+				cfqg->new_leaf_weight = cfqgd->leaf_weight;
 		}
 	}
 
+out:
 	spin_unlock_irq(&blkcg->lock);
-	return 0;
+	return ret;
 }
 
 static int cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
@@ -4477,6 +4545,18 @@ out_free:
 	return ret;
 }
 
+static void cfq_registered_queue(struct request_queue *q)
+{
+	struct elevator_queue *e = q->elevator;
+	struct cfq_data *cfqd = e->elevator_data;
+
+	/*
+	 * Default to IOPS mode with no idling for SSDs
+	 */
+	if (blk_queue_nonrot(q))
+		cfqd->cfq_slice_idle = 0;
+}
+
 /*
  * sysfs parts below -->
  */
@@ -4592,6 +4672,7 @@ static struct elevator_type iosched_cfq = {
 		.elevator_may_queue_fn =	cfq_may_queue,
 		.elevator_init_fn =		cfq_init_queue,
 		.elevator_exit_fn =		cfq_exit_queue,
+		.elevator_registered_fn =	cfq_registered_queue,
 	},
 	.icq_size	=	sizeof(struct cfq_io_cq),
 	.icq_align	=	__alignof__(struct cfq_io_cq),
@@ -4603,8 +4684,10 @@ static struct elevator_type iosched_cfq = {
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 static struct blkcg_policy blkcg_policy_cfq = {
 	.pd_size		= sizeof(struct cfq_group),
+	.cpd_size		= sizeof(struct cfq_group_data),
 	.cftypes		= cfq_blkcg_files,
 
+	.cpd_init_fn		= cfq_cpd_init,
 	.pd_init_fn		= cfq_pd_init,
 	.pd_offline_fn		= cfq_pd_offline,
 	.pd_reset_stats_fn	= cfq_pd_reset_stats,

block/elevator.c

@@ -806,6 +806,8 @@ int elv_register_queue(struct request_queue *q)
 		}
 		kobject_uevent(&e->kobj, KOBJ_ADD);
 		e->registered = 1;
+		if (e->type->ops.elevator_registered_fn)
+			e->type->ops.elevator_registered_fn(q);
 	}
 	return error;
 }

block/ioctl.c

@@ -150,21 +150,48 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 	}
 }
 
-static int blkdev_reread_part(struct block_device *bdev)
+/*
+ * This is an exported API for the block driver, and will not
+ * acquire bd_mutex. This API should be used in case that
+ * caller has held bd_mutex already.
+ */
+int __blkdev_reread_part(struct block_device *bdev)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	int res;
 
 	if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains)
 		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
-	if (!mutex_trylock(&bdev->bd_mutex))
+
-		return -EBUSY;
+	lockdep_assert_held(&bdev->bd_mutex);
-	res = rescan_partitions(disk, bdev);
+
+	return rescan_partitions(disk, bdev);
+}
+EXPORT_SYMBOL(__blkdev_reread_part);
+
+/*
+ * This is an exported API for the block driver, and will
+ * try to acquire bd_mutex. If bd_mutex has been held already
+ * in current context, please call __blkdev_reread_part().
+ *
+ * Make sure the held locks in current context aren't required
+ * in open()/close() handler and I/O path for avoiding ABBA deadlock:
+ * - bd_mutex is held before calling block driver's open/close
+ *   handler
+ * - reading partition table may submit I/O to the block device
+ */
+int blkdev_reread_part(struct block_device *bdev)
+{
+	int res;
+
+	mutex_lock(&bdev->bd_mutex);
+	res = __blkdev_reread_part(bdev);
 	mutex_unlock(&bdev->bd_mutex);
+
 	return res;
 }
+EXPORT_SYMBOL(blkdev_reread_part);
 
 static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 			     uint64_t len, int secure)

drivers/block/nbd.c

@@ -230,29 +230,40 @@ static int nbd_send_req(struct nbd_device *nbd, struct request *req)
 	int result, flags;
 	struct nbd_request request;
 	unsigned long size = blk_rq_bytes(req);
+	u32 type;
+
+	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+		type = NBD_CMD_DISC;
+	else if (req->cmd_flags & REQ_DISCARD)
+		type = NBD_CMD_TRIM;
+	else if (req->cmd_flags & REQ_FLUSH)
+		type = NBD_CMD_FLUSH;
+	else if (rq_data_dir(req) == WRITE)
+		type = NBD_CMD_WRITE;
+	else
+		type = NBD_CMD_READ;
 
 	memset(&request, 0, sizeof(request));
 	request.magic = htonl(NBD_REQUEST_MAGIC);
-	request.type = htonl(nbd_cmd(req));
+	request.type = htonl(type);
-
+	if (type != NBD_CMD_FLUSH && type != NBD_CMD_DISC) {
-	if (nbd_cmd(req) != NBD_CMD_FLUSH && nbd_cmd(req) != NBD_CMD_DISC) {
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
 		request.len = htonl(size);
 	}
 	memcpy(request.handle, &req, sizeof(req));
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
-		req, nbdcmd_to_ascii(nbd_cmd(req)),
+		req, nbdcmd_to_ascii(type),
 		(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
 	result = sock_xmit(nbd, 1, &request, sizeof(request),
-			(nbd_cmd(req) == NBD_CMD_WRITE) ? MSG_MORE : 0);
+			(type == NBD_CMD_WRITE) ? MSG_MORE : 0);
 	if (result <= 0) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Send control failed (result %d)\n", result);
 		return -EIO;
 	}
 
-	if (nbd_cmd(req) == NBD_CMD_WRITE) {
+	if (type == NBD_CMD_WRITE) {
 		struct req_iterator iter;
 		struct bio_vec bvec;
 		/*
@@ -352,7 +363,7 @@ static struct request *nbd_read_stat(struct nbd_device *nbd)
 	}
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req);
-	if (nbd_cmd(req) == NBD_CMD_READ) {
+	if (rq_data_dir(req) != WRITE) {
 		struct req_iterator iter;
 		struct bio_vec bvec;
 
@@ -452,23 +463,11 @@ static void nbd_handle_req(struct nbd_device *nbd, struct request *req)
 	if (req->cmd_type != REQ_TYPE_FS)
 		goto error_out;
 
-	nbd_cmd(req) = NBD_CMD_READ;
+	if (rq_data_dir(req) == WRITE &&
-	if (rq_data_dir(req) == WRITE) {
+	    (nbd->flags & NBD_FLAG_READ_ONLY)) {
-		if ((req->cmd_flags & REQ_DISCARD)) {
+		dev_err(disk_to_dev(nbd->disk),
-			WARN_ON(!(nbd->flags & NBD_FLAG_SEND_TRIM));
+			"Write on read-only\n");
-			nbd_cmd(req) = NBD_CMD_TRIM;
+		goto error_out;
-		} else
-			nbd_cmd(req) = NBD_CMD_WRITE;
-		if (nbd->flags & NBD_FLAG_READ_ONLY) {
-			dev_err(disk_to_dev(nbd->disk),
-				"Write on read-only\n");
-			goto error_out;
-		}
-	}
-
-	if (req->cmd_flags & REQ_FLUSH) {
-		BUG_ON(unlikely(blk_rq_sectors(req)));
-		nbd_cmd(req) = NBD_CMD_FLUSH;
 	}
 
 	req->errors = 0;
@@ -592,8 +591,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		fsync_bdev(bdev);
 		mutex_lock(&nbd->tx_lock);
 		blk_rq_init(NULL, &sreq);
-		sreq.cmd_type = REQ_TYPE_SPECIAL;
+		sreq.cmd_type = REQ_TYPE_DRV_PRIV;
-		nbd_cmd(&sreq) = NBD_CMD_DISC;
 
 		/* Check again after getting mutex back.  */
 		if (!nbd->sock)

drivers/block/paride/pd.c

@@ -442,7 +442,7 @@ static char *pd_buf;		/* buffer for request in progress */
 
 static enum action do_pd_io_start(void)
 {
-	if (pd_req->cmd_type == REQ_TYPE_SPECIAL) {
+	if (pd_req->cmd_type == REQ_TYPE_DRV_PRIV) {
 		phase = pd_special;
 		return pd_special();
 	}
@@ -725,7 +725,7 @@ static int pd_special_command(struct pd_unit *disk,
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->special = func;
 
 	err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);

drivers/block/sx8.c

@@ -620,7 +620,7 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx)
 	spin_unlock_irq(&host->lock);
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
-	crq->rq->cmd_type = REQ_TYPE_SPECIAL;
+	crq->rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	crq->rq->special = crq;
 	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 
@@ -661,7 +661,7 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func)
 	crq->msg_bucket = (u32) rc;
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
-	crq->rq->cmd_type = REQ_TYPE_SPECIAL;
+	crq->rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	crq->rq->special = crq;
 	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 

drivers/block/virtio_blk.c

@@ -124,7 +124,7 @@ static inline void virtblk_request_done(struct request *req)
 		req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
 		req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
 		req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
-	} else if (req->cmd_type == REQ_TYPE_SPECIAL) {
+	} else if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
 		req->errors = (error != 0);
 	}
 
@@ -188,7 +188,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 			vbr->out_hdr.sector = 0;
 			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 			break;
-		case REQ_TYPE_SPECIAL:
+		case REQ_TYPE_DRV_PRIV:
 			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
 			vbr->out_hdr.sector = 0;
 			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
@@ -251,7 +251,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 		return PTR_ERR(req);
 	}
 
-	req->cmd_type = REQ_TYPE_SPECIAL;
+	req->cmd_type = REQ_TYPE_DRV_PRIV;
 	err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
 	blk_put_request(req);
 

drivers/ide/ide-atapi.c

@@ -93,7 +93,7 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 	int error;
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->special = (char *)pc;
 
 	if (buf && bufflen) {
@@ -191,7 +191,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 
 	BUG_ON(sense_len > sizeof(*sense));
 
-	if (rq->cmd_type == REQ_TYPE_SENSE || drive->sense_rq_armed)
+	if (rq->cmd_type == REQ_TYPE_ATA_SENSE || drive->sense_rq_armed)
 		return;
 
 	memset(sense, 0, sizeof(*sense));
@@ -210,7 +210,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 	sense_rq->rq_disk = rq->rq_disk;
 	sense_rq->cmd[0] = GPCMD_REQUEST_SENSE;
 	sense_rq->cmd[4] = cmd_len;
-	sense_rq->cmd_type = REQ_TYPE_SENSE;
+	sense_rq->cmd_type = REQ_TYPE_ATA_SENSE;
 	sense_rq->cmd_flags |= REQ_PREEMPT;
 
 	if (drive->media == ide_tape)
@@ -310,7 +310,7 @@ int ide_cd_get_xferlen(struct request *rq)
 	switch (rq->cmd_type) {
 	case REQ_TYPE_FS:
 		return 32768;
-	case REQ_TYPE_SENSE:
+	case REQ_TYPE_ATA_SENSE:
 	case REQ_TYPE_BLOCK_PC:
 	case REQ_TYPE_ATA_PC:
 		return blk_rq_bytes(rq);
@@ -477,7 +477,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		if (uptodate == 0)
 			drive->failed_pc = NULL;
 
-		if (rq->cmd_type == REQ_TYPE_SPECIAL) {
+		if (rq->cmd_type == REQ_TYPE_DRV_PRIV) {
 			rq->errors = 0;
 			error = 0;
 		} else {

drivers/ide/ide-cd.c

@@ -210,7 +210,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
 {
 	/*
-	 * For REQ_TYPE_SENSE, "rq->special" points to the original
+	 * For REQ_TYPE_ATA_SENSE, "rq->special" points to the original
 	 * failed request.  Also, the sense data should be read
 	 * directly from rq which might be different from the original
 	 * sense buffer if it got copied during mapping.
@@ -285,7 +285,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 				  "stat 0x%x",
 				  rq->cmd[0], rq->cmd_type, err, stat);
 
-	if (rq->cmd_type == REQ_TYPE_SENSE) {
+	if (rq->cmd_type == REQ_TYPE_ATA_SENSE) {
 		/*
 		 * We got an error trying to get sense info from the drive
 		 * (probably while trying to recover from a former error).
@@ -526,7 +526,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	ide_expiry_t *expiry = NULL;
 	int dma_error = 0, dma, thislen, uptodate = 0;
 	int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0;
-	int sense = (rq->cmd_type == REQ_TYPE_SENSE);
+	int sense = (rq->cmd_type == REQ_TYPE_ATA_SENSE);
 	unsigned int timeout;
 	u16 len;
 	u8 ireason, stat;
@@ -791,7 +791,7 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 		if (cdrom_start_rw(drive, rq) == ide_stopped)
 			goto out_end;
 		break;
-	case REQ_TYPE_SENSE:
+	case REQ_TYPE_ATA_SENSE:
 	case REQ_TYPE_BLOCK_PC:
 	case REQ_TYPE_ATA_PC:
 		if (!rq->timeout)
@@ -799,7 +799,7 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 
 		cdrom_do_block_pc(drive, rq);
 		break;
-	case REQ_TYPE_SPECIAL:
+	case REQ_TYPE_DRV_PRIV:
 		/* right now this can only be a reset... */
 		uptodate = 1;
 		goto out_end;

drivers/ide/ide-cd_ioctl.c

@@ -304,7 +304,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	int ret;
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd_flags = REQ_QUIET;
 	ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);
 	blk_put_request(rq);

drivers/ide/ide-devsets.c

@@ -166,7 +166,7 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 		return setting->set(drive, arg);
 
 	rq = blk_get_request(q, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd_len = 5;
 	rq->cmd[0] = REQ_DEVSET_EXEC;
 	*(int *)&rq->cmd[1] = arg;

drivers/ide/ide-eh.c

@@ -129,7 +129,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
 
 			if (cmd)
 				ide_complete_cmd(drive, cmd, stat, err);
-		} else if (blk_pm_request(rq)) {
+		} else if (ata_pm_request(rq)) {
 			rq->errors = 1;
 			ide_complete_pm_rq(drive, rq);
 			return ide_stopped;
@@ -147,7 +147,7 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
 {
 	struct request *rq = drive->hwif->rq;
 
-	if (rq && rq->cmd_type == REQ_TYPE_SPECIAL &&
+	if (rq && rq->cmd_type == REQ_TYPE_DRV_PRIV &&
 	    rq->cmd[0] == REQ_DRIVE_RESET) {
 		if (err <= 0 && rq->errors == 0)
 			rq->errors = -EIO;

drivers/ide/ide-floppy.c

@@ -97,7 +97,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc)
 			       "Aborting request!\n");
 	}
 
-	if (rq->cmd_type == REQ_TYPE_SPECIAL)
+	if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
 		rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
 
 	return uptodate;
@@ -246,7 +246,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		} else
 			printk(KERN_ERR PFX "%s: I/O error\n", drive->name);
 
-		if (rq->cmd_type == REQ_TYPE_SPECIAL) {
+		if (rq->cmd_type == REQ_TYPE_DRV_PRIV) {
 			rq->errors = 0;
 			ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 			return ide_stopped;
@@ -265,8 +265,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		pc = &floppy->queued_pc;
 		idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block);
 		break;
-	case REQ_TYPE_SPECIAL:
+	case REQ_TYPE_DRV_PRIV:
-	case REQ_TYPE_SENSE:
+	case REQ_TYPE_ATA_SENSE:
 		pc = (struct ide_atapi_pc *)rq->special;
 		break;
 	case REQ_TYPE_BLOCK_PC:

drivers/ide/ide-io.c

@@ -135,7 +135,7 @@ EXPORT_SYMBOL(ide_complete_rq);
 
 void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 {
-	u8 drv_req = (rq->cmd_type == REQ_TYPE_SPECIAL) && rq->rq_disk;
+	u8 drv_req = (rq->cmd_type == REQ_TYPE_DRV_PRIV) && rq->rq_disk;
 	u8 media = drive->media;
 
 	drive->failed_pc = NULL;
@@ -320,7 +320,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 		goto kill_rq;
 	}
 
-	if (blk_pm_request(rq))
+	if (ata_pm_request(rq))
 		ide_check_pm_state(drive, rq);
 
 	drive->hwif->tp_ops->dev_select(drive);
@@ -342,8 +342,8 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 
 		if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE)
 			return execute_drive_cmd(drive, rq);
-		else if (blk_pm_request(rq)) {
+		else if (ata_pm_request(rq)) {
-			struct request_pm_state *pm = rq->special;
+			struct ide_pm_state *pm = rq->special;
 #ifdef DEBUG_PM
 			printk("%s: start_power_step(step: %d)\n",
 				drive->name, pm->pm_step);
@@ -353,7 +353,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 			    pm->pm_step == IDE_PM_COMPLETED)
 				ide_complete_pm_rq(drive, rq);
 			return startstop;
-		} else if (!rq->rq_disk && rq->cmd_type == REQ_TYPE_SPECIAL)
+		} else if (!rq->rq_disk && rq->cmd_type == REQ_TYPE_DRV_PRIV)
 			/*
 			 * TODO: Once all ULDs have been modified to
 			 * check for specific op codes rather than
@@ -538,7 +538,7 @@ repeat:
 		 * state machine.
 		 */
 		if ((drive->dev_flags & IDE_DFLAG_BLOCKED) &&
-		    blk_pm_request(rq) == 0 &&
+		    ata_pm_request(rq) == 0 &&
 		    (rq->cmd_flags & REQ_PREEMPT) == 0) {
 			/* there should be no pending command at this point */
 			ide_unlock_port(hwif);

drivers/ide/ide-ioctls.c

@@ -222,7 +222,7 @@ static int generic_drive_reset(ide_drive_t *drive)
 	int ret = 0;
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd_len = 1;
 	rq->cmd[0] = REQ_DRIVE_RESET;
 	if (blk_execute_rq(drive->queue, NULL, rq, 1))

drivers/ide/ide-park.c

@@ -34,7 +34,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	rq = blk_get_request(q, READ, __GFP_WAIT);
 	rq->cmd[0] = REQ_PARK_HEADS;
 	rq->cmd_len = 1;
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->special = &timeout;
 	rc = blk_execute_rq(q, NULL, rq, 1);
 	blk_put_request(rq);
@@ -51,7 +51,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 
 	rq->cmd[0] = REQ_UNPARK_HEADS;
 	rq->cmd_len = 1;
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
 
 out:

drivers/ide/ide-pm.c

@@ -8,7 +8,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	ide_drive_t *pair = ide_get_pair_dev(drive);
 	ide_hwif_t *hwif = drive->hwif;
 	struct request *rq;
-	struct request_pm_state rqpm;
+	struct ide_pm_state rqpm;
 	int ret;
 
 	if (ide_port_acpi(hwif)) {
@@ -19,7 +19,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_PM_SUSPEND;
+	rq->cmd_type = REQ_TYPE_ATA_PM_SUSPEND;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_SUSPEND;
 	if (mesg.event == PM_EVENT_PRETHAW)
@@ -38,13 +38,43 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	return ret;
 }
 
+static void ide_end_sync_rq(struct request *rq, int error)
+{
+	complete(rq->end_io_data);
+}
+
+static int ide_pm_execute_rq(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	rq->end_io_data = &wait;
+	rq->end_io = ide_end_sync_rq;
+
+	spin_lock_irq(q->queue_lock);
+	if (unlikely(blk_queue_dying(q))) {
+		rq->cmd_flags |= REQ_QUIET;
+		rq->errors = -ENXIO;
+		__blk_end_request_all(rq, rq->errors);
+		spin_unlock_irq(q->queue_lock);
+		return -ENXIO;
+	}
+	__elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
+	__blk_run_queue_uncond(q);
+	spin_unlock_irq(q->queue_lock);
+
+	wait_for_completion_io(&wait);
+
+	return rq->errors ? -EIO : 0;
+}
+
 int generic_ide_resume(struct device *dev)
 {
 	ide_drive_t *drive = to_ide_device(dev);
 	ide_drive_t *pair = ide_get_pair_dev(drive);
 	ide_hwif_t *hwif = drive->hwif;
 	struct request *rq;
-	struct request_pm_state rqpm;
+	struct ide_pm_state rqpm;
 	int err;
 
 	if (ide_port_acpi(hwif)) {
@@ -59,13 +89,13 @@ int generic_ide_resume(struct device *dev)
 
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_PM_RESUME;
+	rq->cmd_type = REQ_TYPE_ATA_PM_RESUME;
 	rq->cmd_flags |= REQ_PREEMPT;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_RESUME;
 	rqpm.pm_state = PM_EVENT_ON;
 
-	err = blk_execute_rq(drive->queue, NULL, rq, 1);
+	err = ide_pm_execute_rq(rq);
 	blk_put_request(rq);
 
 	if (err == 0 && dev->driver) {
@@ -80,7 +110,7 @@ int generic_ide_resume(struct device *dev)
 
 void ide_complete_power_step(ide_drive_t *drive, struct request *rq)
 {
-	struct request_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = rq->special;
 
 #ifdef DEBUG_PM
 	printk(KERN_INFO "%s: complete_power_step(step: %d)\n",
@@ -110,7 +140,7 @@ void ide_complete_power_step(ide_drive_t *drive, struct request *rq)
 
 ide_startstop_t ide_start_power_step(ide_drive_t *drive, struct request *rq)
 {
-	struct request_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = rq->special;
 	struct ide_cmd cmd = { };
 
 	switch (pm->pm_step) {
@@ -182,7 +212,7 @@ out_do_tf:
 void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 {
 	struct request_queue *q = drive->queue;
-	struct request_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = rq->special;
 	unsigned long flags;
 
 	ide_complete_power_step(drive, rq);
@@ -191,10 +221,10 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 
 #ifdef DEBUG_PM
 	printk("%s: completing PM request, %s\n", drive->name,
-	       (rq->cmd_type == REQ_TYPE_PM_SUSPEND) ? "suspend" : "resume");
+	       (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND) ? "suspend" : "resume");
 #endif
 	spin_lock_irqsave(q->queue_lock, flags);
-	if (rq->cmd_type == REQ_TYPE_PM_SUSPEND)
+	if (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND)
 		blk_stop_queue(q);
 	else
 		drive->dev_flags &= ~IDE_DFLAG_BLOCKED;
@@ -208,13 +238,13 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 
 void ide_check_pm_state(ide_drive_t *drive, struct request *rq)
 {
-	struct request_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = rq->special;
 
-	if (rq->cmd_type == REQ_TYPE_PM_SUSPEND &&
+	if (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND &&
 	    pm->pm_step == IDE_PM_START_SUSPEND)
 		/* Mark drive blocked when starting the suspend sequence. */
 		drive->dev_flags |= IDE_DFLAG_BLOCKED;
-	else if (rq->cmd_type == REQ_TYPE_PM_RESUME &&
+	else if (rq->cmd_type == REQ_TYPE_ATA_PM_RESUME &&
 		 pm->pm_step == IDE_PM_START_RESUME) {
 		/*
 		 * The first thing we do on wakeup is to wait for BSY bit to

drivers/ide/ide-tape.c

@@ -576,8 +576,8 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		      rq->cmd[0], (unsigned long long)blk_rq_pos(rq),
 		      blk_rq_sectors(rq));
 
-	BUG_ON(!(rq->cmd_type == REQ_TYPE_SPECIAL ||
+	BUG_ON(!(rq->cmd_type == REQ_TYPE_DRV_PRIV ||
-		 rq->cmd_type == REQ_TYPE_SENSE));
+		 rq->cmd_type == REQ_TYPE_ATA_SENSE));
 
 	/* Retry a failed packet command */
 	if (drive->failed_pc && drive->pc->c[0] == REQUEST_SENSE) {
@@ -853,7 +853,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	BUG_ON(size < 0 || size % tape->blk_size);
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd[13] = cmd;
 	rq->rq_disk = tape->disk;
 	rq->__sector = tape->first_frame;

drivers/ide/ide-taskfile.c

@@ -186,7 +186,7 @@ static ide_startstop_t task_no_data_intr(ide_drive_t *drive)
 	    tf->command == ATA_CMD_CHK_POWER) {
 		struct request *rq = hwif->rq;
 
-		if (blk_pm_request(rq))
+		if (ata_pm_request(rq))
 			ide_complete_pm_rq(drive, rq);
 		else
 			ide_finish_cmd(drive, cmd, stat);

drivers/md/bcache/io.c

@@ -55,7 +55,7 @@ static void bch_bio_submit_split_done(struct closure *cl)
 
 	s->bio->bi_end_io = s->bi_end_io;
 	s->bio->bi_private = s->bi_private;
-	bio_endio_nodec(s->bio, 0);
+	bio_endio(s->bio, 0);
 
 	closure_debug_destroy(&s->cl);
 	mempool_free(s, s->p->bio_split_hook);

drivers/md/bcache/request.c

@@ -619,7 +619,7 @@ static void do_bio_hook(struct search *s, struct bio *orig_bio)
 	bio->bi_end_io		= request_endio;
 	bio->bi_private		= &s->cl;
 
-	atomic_set(&bio->bi_cnt, 3);
+	bio_cnt_set(bio, 3);
 }
 
 static void search_free(struct closure *cl)

drivers/md/dm-cache-target.c

@@ -86,12 +86,6 @@ static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio)
 {
 	bio->bi_end_io = h->bi_end_io;
 	bio->bi_private = h->bi_private;
-
-	/*
-	 * Must bump bi_remaining to allow bio to complete with
-	 * restored bi_end_io.
-	 */
-	atomic_inc(&bio->bi_remaining);
 }
 
 /*----------------------------------------------------------------*/

drivers/md/dm-raid1.c

@@ -1254,8 +1254,6 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 			dm_bio_restore(bd, bio);
 			bio_record->details.bi_bdev = NULL;
 
-			atomic_inc(&bio->bi_remaining);
-
 			queue_bio(ms, bio, rw);
 			return DM_ENDIO_INCOMPLETE;
 		}

drivers/md/dm-snap.c

@@ -1478,7 +1478,6 @@ out:
 	if (full_bio) {
 		full_bio->bi_end_io = pe->full_bio_end_io;
 		full_bio->bi_private = pe->full_bio_private;
-		atomic_inc(&full_bio->bi_remaining);
 	}
 	increment_pending_exceptions_done_count();
 

drivers/md/dm-table.c

@@ -942,21 +942,28 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 {
 	unsigned type = dm_table_get_type(t);
 	unsigned per_bio_data_size = 0;
-	struct dm_target *tgt;
 	unsigned i;
 
-	if (unlikely(type == DM_TYPE_NONE)) {
+	switch (type) {
+	case DM_TYPE_BIO_BASED:
+		for (i = 0; i < t->num_targets; i++) {
+			struct dm_target *tgt = t->targets + i;
+
+			per_bio_data_size = max(per_bio_data_size,
+						tgt->per_bio_data_size);
+		}
+		t->mempools = dm_alloc_bio_mempools(t->integrity_supported,
+						    per_bio_data_size);
+		break;
+	case DM_TYPE_REQUEST_BASED:
+	case DM_TYPE_MQ_REQUEST_BASED:
+		t->mempools = dm_alloc_rq_mempools(md, type);
+		break;
+	default:
 		DMWARN("no table type is set, can't allocate mempools");
 		return -EINVAL;
 	}
 
-	if (type == DM_TYPE_BIO_BASED)
-		for (i = 0; i < t->num_targets; i++) {
-			tgt = t->targets + i;
-			per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size);
-		}
-
-	t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported, per_bio_data_size);
 	if (!t->mempools)
 		return -ENOMEM;
 

drivers/md/dm-thin.c

@@ -793,10 +793,9 @@ static void inc_remap_and_issue_cell(struct thin_c *tc,
 
 static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
 {
-	if (m->bio) {
+	if (m->bio)
 		m->bio->bi_end_io = m->saved_bi_end_io;
-		atomic_inc(&m->bio->bi_remaining);
+
-	}
 	cell_error(m->tc->pool, m->cell);
 	list_del(&m->list);
 	mempool_free(m, m->tc->pool->mapping_pool);
@@ -810,10 +809,8 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 	int r;
 
 	bio = m->bio;
-	if (bio) {
+	if (bio)
 		bio->bi_end_io = m->saved_bi_end_io;
-		atomic_inc(&bio->bi_remaining);
-	}
 
 	if (m->err) {
 		cell_error(pool, m->cell);

drivers/md/dm-verity.c

@@ -459,7 +459,7 @@ static void verity_finish_io(struct dm_verity_io *io, int error)
 	bio->bi_end_io = io->orig_bi_end_io;
 	bio->bi_private = io->orig_bi_private;
 
-	bio_endio_nodec(bio, error);
+	bio_endio(bio, error);
 }
 
 static void verity_work(struct work_struct *w)

drivers/md/dm.c

@@ -990,57 +990,6 @@ static void clone_endio(struct bio *bio, int error)
 	dec_pending(io, error);
 }
 
-/*
- * Partial completion handling for request-based dm
- */
-static void end_clone_bio(struct bio *clone, int error)
-{
-	struct dm_rq_clone_bio_info *info =
-		container_of(clone, struct dm_rq_clone_bio_info, clone);
-	struct dm_rq_target_io *tio = info->tio;
-	struct bio *bio = info->orig;
-	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
-
-	bio_put(clone);
-
-	if (tio->error)
-		/*
-		 * An error has already been detected on the request.
-		 * Once error occurred, just let clone->end_io() handle
-		 * the remainder.
-		 */
-		return;
-	else if (error) {
-		/*
-		 * Don't notice the error to the upper layer yet.
-		 * The error handling decision is made by the target driver,
-		 * when the request is completed.
-		 */
-		tio->error = error;
-		return;
-	}
-
-	/*
-	 * I/O for the bio successfully completed.
-	 * Notice the data completion to the upper layer.
-	 */
-
-	/*
-	 * bios are processed from the head of the list.
-	 * So the completing bio should always be rq->bio.
-	 * If it's not, something wrong is happening.
-	 */
-	if (tio->orig->bio != bio)
-		DMERR("bio completion is going in the middle of the request");
-
-	/*
-	 * Update the original request.
-	 * Do not use blk_end_request() here, because it may complete
-	 * the original request before the clone, and break the ordering.
-	 */
-	blk_update_request(tio->orig, 0, nr_bytes);
-}
-
 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);
@@ -1087,8 +1036,6 @@ 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);
-
 	if (md->type == DM_TYPE_MQ_REQUEST_BASED)
 		/* stacked on blk-mq queue(s) */
 		tio->ti->type->release_clone_rq(clone);
@@ -1827,39 +1774,13 @@ static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
 		dm_complete_request(rq, r);
 }
 
-static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
+static void setup_clone(struct request *clone, struct request *rq,
-				 void *data)
+		        struct dm_rq_target_io *tio)
 {
-	struct dm_rq_target_io *tio = data;
+	blk_rq_prep_clone(clone, rq);
-	struct dm_rq_clone_bio_info *info =
-		container_of(bio, struct dm_rq_clone_bio_info, clone);
-
-	info->orig = bio_orig;
-	info->tio = tio;
-	bio->bi_end_io = end_clone_bio;
-
-	return 0;
-}
-
-static int setup_clone(struct request *clone, struct request *rq,
-		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
-	int r;
-
-	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
-			      dm_rq_bio_constructor, tio);
-	if (r)
-		return r;
-
-	clone->cmd = rq->cmd;
-	clone->cmd_len = rq->cmd_len;
-	clone->sense = rq->sense;
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
-
 	tio->clone = clone;
-
-	return 0;
 }
 
 static struct request *clone_rq(struct request *rq, struct mapped_device *md,
@@ -1880,12 +1801,7 @@ static struct request *clone_rq(struct request *rq, struct mapped_device *md,
 		clone = tio->clone;
 
 	blk_rq_init(NULL, clone);
-	if (setup_clone(clone, rq, tio, gfp_mask)) {
+	setup_clone(clone, rq, tio);
-		/* -ENOMEM */
-		if (alloc_clone)
-			free_clone_request(md, clone);
-		return NULL;
-	}
 
 	return clone;
 }
@@ -1979,11 +1895,7 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
 		}
 		if (r != DM_MAPIO_REMAPPED)
 			return r;
-		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
+		setup_clone(clone, rq, tio);
-			/* -ENOMEM */
-			ti->type->release_clone_rq(clone);
-			return DM_MAPIO_REQUEUE;
-		}
 	}
 
 	switch (r) {
@@ -2437,8 +2349,6 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 		goto out;
 	}
 
-	BUG_ON(!p || md->io_pool || md->rq_pool || md->bs);
-
 	md->io_pool = p->io_pool;
 	p->io_pool = NULL;
 	md->rq_pool = p->rq_pool;
@@ -3544,48 +3454,23 @@ 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_bio_mempools(unsigned integrity,
-					    unsigned integrity, unsigned per_bio_data_size)
+					     unsigned per_bio_data_size)
 {
-	struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL);
+	struct dm_md_mempools *pools;
-	struct kmem_cache *cachep = NULL;
+	unsigned int pool_size = dm_get_reserved_bio_based_ios();
-	unsigned int pool_size = 0;
 	unsigned int front_pad;
 
+	pools = kzalloc(sizeof(*pools), GFP_KERNEL);
 	if (!pools)
 		return NULL;
 
-	type = filter_md_type(type, md);
+	front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) +
+		offsetof(struct dm_target_io, clone);
 
-	switch (type) {
+	pools->io_pool = mempool_create_slab_pool(pool_size, _io_cache);
-	case DM_TYPE_BIO_BASED:
+	if (!pools->io_pool)
-		cachep = _io_cache;
+		goto out;
-		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);
-		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();
-		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);
-		break;
-	default:
-		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)
@@ -3595,10 +3480,34 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 		goto out;
 
 	return pools;
-
 out:
 	dm_free_md_mempools(pools);
+	return NULL;
+}
 
+struct dm_md_mempools *dm_alloc_rq_mempools(struct mapped_device *md,
+					    unsigned type)
+{
+	unsigned int pool_size = dm_get_reserved_rq_based_ios();
+	struct dm_md_mempools *pools;
+
+	pools = kzalloc(sizeof(*pools), GFP_KERNEL);
+	if (!pools)
+		return NULL;
+
+	if (filter_md_type(type, md) == DM_TYPE_REQUEST_BASED) {
+		pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
+		if (!pools->rq_pool)
+			goto out;
+	}
+
+	pools->io_pool = mempool_create_slab_pool(pool_size, _rq_tio_cache);
+	if (!pools->io_pool)
+		goto out;
+
+	return pools;
+out:
+	dm_free_md_mempools(pools);
 	return NULL;
 }
 

drivers/md/dm.h

@@ -222,8 +222,9 @@ void dm_kcopyd_exit(void);
 /*
  * Mempool operations
  */
-struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type,
+struct dm_md_mempools *dm_alloc_bio_mempools(unsigned integrity,
-					    unsigned integrity, unsigned per_bio_data_size);
+					     unsigned per_bio_data_size);
+struct dm_md_mempools *dm_alloc_rq_mempools(struct mapped_device *md, unsigned type);
 void dm_free_md_mempools(struct dm_md_mempools *pools);
 
 /*

fs/btrfs/disk-io.c

@@ -1745,7 +1745,7 @@ static void end_workqueue_fn(struct btrfs_work *work)
 	bio->bi_private = end_io_wq->private;
 	bio->bi_end_io = end_io_wq->end_io;
 	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
-	bio_endio_nodec(bio, error);
+	bio_endio(bio, error);
 }
 
 static int cleaner_kthread(void *arg)
@@ -3269,11 +3269,8 @@ static int write_dev_supers(struct btrfs_device *device,
  */
 static void btrfs_end_empty_barrier(struct bio *bio, int err)
 {
-	if (err) {
+	if (err)
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
 	if (bio->bi_private)
 		complete(bio->bi_private);
 	bio_put(bio);
@@ -3301,11 +3298,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 
 		wait_for_completion(&device->flush_wait);
 
-		if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
+		if (!bio_flagged(bio, BIO_UPTODATE)) {
-			printk_in_rcu("BTRFS: disabling barriers on dev %s\n",
-				      rcu_str_deref(device->name));
-			device->nobarriers = 1;
-		} else if (!bio_flagged(bio, BIO_UPTODATE)) {
 			ret = -EIO;
 			btrfs_dev_stat_inc_and_print(device,
 				BTRFS_DEV_STAT_FLUSH_ERRS);

fs/btrfs/extent_io.c

@@ -2767,8 +2767,6 @@ static int __must_check submit_one_bio(int rw, struct bio *bio,
 	else
 		btrfsic_submit_bio(rw, bio);
 
-	if (bio_flagged(bio, BIO_EOPNOTSUPP))
-		ret = -EOPNOTSUPP;
 	bio_put(bio);
 	return ret;
 }

fs/btrfs/volumes.c

@@ -345,7 +345,7 @@ loop_lock:
 		    waitqueue_active(&fs_info->async_submit_wait))
 			wake_up(&fs_info->async_submit_wait);
 
-		BUG_ON(atomic_read(&cur->bi_cnt) == 0);
+		BUG_ON(atomic_read(&cur->__bi_cnt) == 0);
 
 		/*
 		 * if we're doing the sync list, record that our
@@ -5586,10 +5586,10 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 
 static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio, int err)
 {
-	if (likely(bbio->flags & BTRFS_BIO_ORIG_BIO_SUBMITTED))
+	bio->bi_private = bbio->private;
-		bio_endio_nodec(bio, err);
+	bio->bi_end_io = bbio->end_io;
-	else
+	bio_endio(bio, err);
-		bio_endio(bio, err);
+
 	btrfs_put_bbio(bbio);
 }
 
@@ -5633,8 +5633,6 @@ static void btrfs_end_bio(struct bio *bio, int err)
 			bio = bbio->orig_bio;
 		}
 
-		bio->bi_private = bbio->private;
-		bio->bi_end_io = bbio->end_io;
 		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
 		/* only send an error to the higher layers if it is
 		 * beyond the tolerance of the btrfs bio
@@ -5816,8 +5814,6 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
 		/* Shoud be the original bio. */
 		WARN_ON(bio != bbio->orig_bio);
 
-		bio->bi_private = bbio->private;
-		bio->bi_end_io = bbio->end_io;
 		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
 		bio->bi_iter.bi_sector = logical >> 9;
 
@@ -5898,10 +5894,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 		if (dev_nr < total_devs - 1) {
 			bio = btrfs_bio_clone(first_bio, GFP_NOFS);
 			BUG_ON(!bio); /* -ENOMEM */
-		} else {
+		} else
 			bio = first_bio;
-			bbio->flags |= BTRFS_BIO_ORIG_BIO_SUBMITTED;
-		}
 
 		submit_stripe_bio(root, bbio, bio,
 				  bbio->stripes[dev_nr].physical, dev_nr, rw,

fs/btrfs/volumes.h

@@ -292,8 +292,6 @@ struct btrfs_bio_stripe {
 struct btrfs_bio;
 typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
 
-#define BTRFS_BIO_ORIG_BIO_SUBMITTED	(1 << 0)
-
 struct btrfs_bio {
 	atomic_t refs;
 	atomic_t stripes_pending;

fs/buffer.c

@@ -2938,10 +2938,6 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
 {
 	struct buffer_head *bh = bio->bi_private;
 
-	if (err == -EOPNOTSUPP) {
-		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-	}
-
 	if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags)))
 		set_bit(BH_Quiet, &bh->b_state);
 
@@ -3000,7 +2996,6 @@ void guard_bio_eod(int rw, struct bio *bio)
 int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 {
 	struct bio *bio;
-	int ret = 0;
 
 	BUG_ON(!buffer_locked(bh));
 	BUG_ON(!buffer_mapped(bh));
@@ -3041,14 +3036,8 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 	if (buffer_prio(bh))
 		rw |= REQ_PRIO;
 
-	bio_get(bio);
 	submit_bio(rw, bio);
-
+	return 0;
-	if (bio_flagged(bio, BIO_EOPNOTSUPP))
-		ret = -EOPNOTSUPP;
-
-	bio_put(bio);
-	return ret;
 }
 EXPORT_SYMBOL_GPL(_submit_bh);
 

fs/ext4/page-io.c

@@ -359,7 +359,6 @@ void ext4_io_submit(struct ext4_io_submit *io)
 	if (bio) {
 		bio_get(io->io_bio);
 		submit_bio(io->io_op, io->io_bio);
-		BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP));
 		bio_put(io->io_bio);
 	}
 	io->io_bio = NULL;

fs/nilfs2/segbuf.c

@@ -343,11 +343,6 @@ static void nilfs_end_bio_write(struct bio *bio, int err)
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct nilfs_segment_buffer *segbuf = bio->bi_private;
 
-	if (err == -EOPNOTSUPP) {
-		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		/* to be detected by nilfs_segbuf_submit_bio() */
-	}
-
 	if (!uptodate)
 		atomic_inc(&segbuf->sb_err);
 
@@ -374,15 +369,8 @@ static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
 
 	bio->bi_end_io = nilfs_end_bio_write;
 	bio->bi_private = segbuf;
-	bio_get(bio);
 	submit_bio(mode, bio);
 	segbuf->sb_nbio++;
-	if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
-		bio_put(bio);
-		err = -EOPNOTSUPP;
-		goto failed;
-	}
-	bio_put(bio);
 
 	wi->bio = NULL;
 	wi->rest_blocks -= wi->end - wi->start;

fs/xfs/xfs_aops.c

@@ -356,7 +356,6 @@ xfs_end_bio(
 {
 	xfs_ioend_t		*ioend = bio->bi_private;
 
-	ASSERT(atomic_read(&bio->bi_cnt) >= 1);
 	ioend->io_error = test_bit(BIO_UPTODATE, &bio->bi_flags) ? 0 : error;
 
 	/* Toss bio and pass work off to an xfsdatad thread */

include/linux/bio.h

@@ -290,7 +290,21 @@ static inline unsigned bio_segments(struct bio *bio)
  * returns. and then bio would be freed memory when if (bio->bi_flags ...)
  * runs
  */
-#define bio_get(bio)	atomic_inc(&(bio)->bi_cnt)
+static inline void bio_get(struct bio *bio)
+{
+	bio->bi_flags |= (1 << BIO_REFFED);
+	smp_mb__before_atomic();
+	atomic_inc(&bio->__bi_cnt);
+}
+
+static inline void bio_cnt_set(struct bio *bio, unsigned int count)
+{
+	if (count != 1) {
+		bio->bi_flags |= (1 << BIO_REFFED);
+		smp_mb__before_atomic();
+	}
+	atomic_set(&bio->__bi_cnt, count);
+}
 
 enum bip_flags {
 	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
@@ -413,7 +427,6 @@ static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
 }
 
 extern void bio_endio(struct bio *, int);
-extern void bio_endio_nodec(struct bio *, int);
 struct request_queue;
 extern int bio_phys_segments(struct request_queue *, struct bio *);
 

include/linux/blk-mq.h

@@ -96,6 +96,7 @@ typedef void (exit_request_fn)(void *, struct request *, unsigned int,
 
 typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
 		bool);
+typedef void (busy_tag_iter_fn)(struct request *, void *, bool);
 
 struct blk_mq_ops {
 	/*
@@ -182,6 +183,7 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		gfp_t gfp, bool reserved);
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
+struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags);
 
 enum {
 	BLK_MQ_UNIQUE_TAG_BITS = 16,
@@ -224,6 +226,8 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
 		void *priv);
+void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
+		void *priv);
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_mq_freeze_queue_start(struct request_queue *q);

include/linux/blk_types.h

@@ -65,7 +65,7 @@ struct bio {
 	unsigned int		bi_seg_front_size;
 	unsigned int		bi_seg_back_size;
 
-	atomic_t		bi_remaining;
+	atomic_t		__bi_remaining;
 
 	bio_end_io_t		*bi_end_io;
 
@@ -92,7 +92,7 @@ struct bio {
 
 	unsigned short		bi_max_vecs;	/* max bvl_vecs we can hold */
 
-	atomic_t		bi_cnt;		/* pin count */
+	atomic_t		__bi_cnt;	/* pin count */
 
 	struct bio_vec		*bi_io_vec;	/* the actual vec list */
 
@@ -112,16 +112,15 @@ struct bio {
  * bio flags
  */
 #define BIO_UPTODATE	0	/* ok after I/O completion */
-#define BIO_RW_BLOCK	1	/* RW_AHEAD set, and read/write would block */
+#define BIO_SEG_VALID	1	/* bi_phys_segments valid */
-#define BIO_EOF		2	/* out-out-bounds error */
+#define BIO_CLONED	2	/* doesn't own data */
-#define BIO_SEG_VALID	3	/* bi_phys_segments valid */
+#define BIO_BOUNCED	3	/* bio is a bounce bio */
-#define BIO_CLONED	4	/* doesn't own data */
+#define BIO_USER_MAPPED 4	/* contains user pages */
-#define BIO_BOUNCED	5	/* bio is a bounce bio */
+#define BIO_NULL_MAPPED 5	/* contains invalid user pages */
-#define BIO_USER_MAPPED 6	/* contains user pages */
+#define BIO_QUIET	6	/* Make BIO Quiet */
-#define BIO_EOPNOTSUPP	7	/* not supported */
+#define BIO_SNAP_STABLE	7	/* bio data must be snapshotted during write */
-#define BIO_NULL_MAPPED 8	/* contains invalid user pages */
+#define BIO_CHAIN	8	/* chained bio, ->bi_remaining in effect */
-#define BIO_QUIET	9	/* Make BIO Quiet */
+#define BIO_REFFED	9	/* bio has elevated ->bi_cnt */
-#define BIO_SNAP_STABLE	10	/* bio data must be snapshotted during write */
 
 /*
  * Flags starting here get preserved by bio_reset() - this includes
@@ -193,6 +192,7 @@ enum rq_flag_bits {
 	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_MQ_INFLIGHT,	/* track inflight for MQ */
 	__REQ_NO_TIMEOUT,	/* requests may never expire */
+	__REQ_CLONE,		/* cloned bios */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -247,5 +247,6 @@ enum rq_flag_bits {
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
 #define REQ_NO_TIMEOUT		(1ULL << __REQ_NO_TIMEOUT)
+#define REQ_CLONE		(1ULL << __REQ_CLONE)
 
 #endif /* __LINUX_BLK_TYPES_H */

include/linux/blkdev.h

@@ -30,7 +30,6 @@ struct scsi_ioctl_command;
 
 struct request_queue;
 struct elevator_queue;
-struct request_pm_state;
 struct blk_trace;
 struct request;
 struct sg_io_hdr;
@@ -75,18 +74,7 @@ struct request_list {
 enum rq_cmd_type_bits {
 	REQ_TYPE_FS		= 1,	/* fs request */
 	REQ_TYPE_BLOCK_PC,		/* scsi command */
-	REQ_TYPE_SENSE,			/* sense request */
+	REQ_TYPE_DRV_PRIV,		/* driver defined types from here */
-	REQ_TYPE_PM_SUSPEND,		/* suspend request */
-	REQ_TYPE_PM_RESUME,		/* resume request */
-	REQ_TYPE_PM_SHUTDOWN,		/* shutdown request */
-	REQ_TYPE_SPECIAL,		/* driver defined type */
-	/*
-	 * for ATA/ATAPI devices. this really doesn't belong here, ide should
-	 * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver
-	 * private REQ_LB opcodes to differentiate what type of request this is
-	 */
-	REQ_TYPE_ATA_TASKFILE,
-	REQ_TYPE_ATA_PC,
 };
 
 #define BLK_MAX_CDB	16
@@ -108,7 +96,7 @@ struct request {
 	struct blk_mq_ctx *mq_ctx;
 
 	u64 cmd_flags;
-	enum rq_cmd_type_bits cmd_type;
+	unsigned cmd_type;
 	unsigned long atomic_flags;
 
 	int cpu;
@@ -216,19 +204,6 @@ static inline unsigned short req_get_ioprio(struct request *req)
 	return req->ioprio;
 }
 
-/*
- * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME
- * requests. Some step values could eventually be made generic.
- */
-struct request_pm_state
-{
-	/* PM state machine step value, currently driver specific */
-	int	pm_step;
-	/* requested PM state value (S1, S2, S3, S4, ...) */
-	u32	pm_state;
-	void*	data;		/* for driver use */
-};
-
 #include <linux/elevator.h>
 
 struct blk_queue_ctx;
@@ -469,7 +444,7 @@ struct request_queue {
 	struct mutex		sysfs_lock;
 
 	int			bypass_depth;
-	int			mq_freeze_depth;
+	atomic_t		mq_freeze_depth;
 
 #if defined(CONFIG_BLK_DEV_BSG)
 	bsg_job_fn		*bsg_job_fn;
@@ -610,10 +585,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 	(((rq)->cmd_flags & REQ_STARTED) && \
 	 ((rq)->cmd_type == REQ_TYPE_FS))
 
-#define blk_pm_request(rq)	\
-	((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \
-	 (rq)->cmd_type == REQ_TYPE_PM_RESUME)
-
 #define blk_rq_cpu_valid(rq)	((rq)->cpu != -1)
 #define blk_bidi_rq(rq)		((rq)->next_rq != NULL)
 /* rq->queuelist of dequeued request must be list_empty() */
@@ -804,11 +775,7 @@ extern void blk_add_request_payload(struct request *rq, struct page *page,
 		unsigned int len);
 extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
 extern int blk_lld_busy(struct request_queue *q);
-extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
+extern void blk_rq_prep_clone(struct request *rq, struct request *rq_src);
-			     struct bio_set *bs, gfp_t gfp_mask,
-			     int (*bio_ctr)(struct bio *, struct bio *, void *),
-			     void *data);
-extern void blk_rq_unprep_clone(struct request *rq);
 extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
@@ -845,6 +812,7 @@ extern void blk_stop_queue(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
 extern void __blk_stop_queue(struct request_queue *q);
 extern void __blk_run_queue(struct request_queue *q);
+extern void __blk_run_queue_uncond(struct request_queue *q);
 extern void blk_run_queue(struct request_queue *);
 extern void blk_run_queue_async(struct request_queue *q);
 extern int blk_rq_map_user(struct request_queue *, struct request *,
@@ -933,7 +901,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 	if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
 		return q->limits.max_hw_sectors;
 
-	if (!q->limits.chunk_sectors)
+	if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD))
 		return blk_queue_get_max_sectors(q, rq->cmd_flags);
 
 	return min(blk_max_size_offset(q, blk_rq_pos(rq)),
@@ -1054,6 +1022,7 @@ bool __must_check blk_get_queue(struct request_queue *);
 struct request_queue *blk_alloc_queue(gfp_t);
 struct request_queue *blk_alloc_queue_node(gfp_t, int);
 extern void blk_put_queue(struct request_queue *);
+extern void blk_set_queue_dying(struct request_queue *);
 
 /*
  * block layer runtime pm functions

include/linux/elevator.h

@@ -39,6 +39,7 @@ typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct reques
 typedef int (elevator_init_fn) (struct request_queue *,
 				struct elevator_type *e);
 typedef void (elevator_exit_fn) (struct elevator_queue *);
+typedef void (elevator_registered_fn) (struct request_queue *);
 
 struct elevator_ops
 {
@@ -68,6 +69,7 @@ struct elevator_ops
 
 	elevator_init_fn *elevator_init_fn;
 	elevator_exit_fn *elevator_exit_fn;
+	elevator_registered_fn *elevator_registered_fn;
 };
 
 #define ELV_NAME_MAX	(16)

include/linux/fs.h

@@ -2280,6 +2280,9 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
 					      void *holder);
 extern void blkdev_put(struct block_device *bdev, fmode_t mode);
+extern int __blkdev_reread_part(struct block_device *bdev);
+extern int blkdev_reread_part(struct block_device *bdev);
+
 #ifdef CONFIG_SYSFS
 extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
 extern void bd_unlink_disk_holder(struct block_device *bdev,

include/linux/ide.h

@@ -39,6 +39,19 @@
 
 struct device;
 
+/* IDE-specific values for req->cmd_type */
+enum ata_cmd_type_bits {
+	REQ_TYPE_ATA_TASKFILE = REQ_TYPE_DRV_PRIV + 1,
+	REQ_TYPE_ATA_PC,
+	REQ_TYPE_ATA_SENSE,	/* sense request */
+	REQ_TYPE_ATA_PM_SUSPEND,/* suspend request */
+	REQ_TYPE_ATA_PM_RESUME,	/* resume request */
+};
+
+#define ata_pm_request(rq)	\
+	((rq)->cmd_type == REQ_TYPE_ATA_PM_SUSPEND || \
+	 (rq)->cmd_type == REQ_TYPE_ATA_PM_RESUME)
+
 /* Error codes returned in rq->errors to the higher part of the driver. */
 enum {
 	IDE_DRV_ERROR_GENERAL	= 101,
@@ -1314,6 +1327,19 @@ struct ide_port_info {
 	u8			udma_mask;
 };
 
+/*
+ * State information carried for REQ_TYPE_ATA_PM_SUSPEND and REQ_TYPE_ATA_PM_RESUME
+ * requests.
+ */
+struct ide_pm_state {
+	/* PM state machine step value, currently driver specific */
+	int	pm_step;
+	/* requested PM state value (S1, S2, S3, S4, ...) */
+	u32	pm_state;
+	void*	data;		/* for driver use */
+};
+
+
 int ide_pci_init_one(struct pci_dev *, const struct ide_port_info *, void *);
 int ide_pci_init_two(struct pci_dev *, struct pci_dev *,
 		     const struct ide_port_info *, void *);
@@ -1551,4 +1577,5 @@ static inline void ide_set_drivedata(ide_drive_t *drive, void *data)
 #define ide_host_for_each_port(i, port, host) \
 	for ((i) = 0; ((port) = (host)->ports[i]) || (i) < MAX_HOST_PORTS; (i)++)
 
+
 #endif /* _IDE_H */

include/linux/swap.h

@@ -377,7 +377,6 @@ extern void end_swap_bio_write(struct bio *bio, int err);
 extern int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	void (*end_write_func)(struct bio *, int));
 extern int swap_set_page_dirty(struct page *page);
-extern void end_swap_bio_read(struct bio *bio, int err);
 
 int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
 		unsigned long nr_pages, sector_t start_block);

include/uapi/linux/nbd.h

@@ -44,8 +44,6 @@ enum {
 /* there is a gap here to match userspace */
 #define NBD_FLAG_SEND_TRIM    (1 << 5) /* send trim/discard */
 
-#define nbd_cmd(req) ((req)->cmd[0])
-
 /* userspace doesn't need the nbd_device structure */
 
 /* These are sent over the network in the request/reply magic fields */

kernel/power/Makefile

@@ -7,8 +7,7 @@ obj-$(CONFIG_VT_CONSOLE_SLEEP)	+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
-obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o \
+obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o
-				   block_io.o
 obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
 obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
 

kernel/power/block_io.c

@@ -1,103 +0,0 @@
-/*
- * This file provides functions for block I/O operations on swap/file.
- *
- * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
- * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
- *
- * This file is released under the GPLv2.
- */
-
-#include <linux/bio.h>
-#include <linux/kernel.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-
-#include "power.h"
-
-/**
- *	submit - submit BIO request.
- *	@rw:	READ or WRITE.
- *	@off	physical offset of page.
- *	@page:	page we're reading or writing.
- *	@bio_chain: list of pending biod (for async reading)
- *
- *	Straight from the textbook - allocate and initialize the bio.
- *	If we're reading, make sure the page is marked as dirty.
- *	Then submit it and, if @bio_chain == NULL, wait.
- */
-static int submit(int rw, struct block_device *bdev, sector_t sector,
-		struct page *page, struct bio **bio_chain)
-{
-	const int bio_rw = rw | REQ_SYNC;
-	struct bio *bio;
-
-	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
-	bio->bi_iter.bi_sector = sector;
-	bio->bi_bdev = bdev;
-	bio->bi_end_io = end_swap_bio_read;
-
-	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
-		printk(KERN_ERR "PM: Adding page to bio failed at %llu\n",
-			(unsigned long long)sector);
-		bio_put(bio);
-		return -EFAULT;
-	}
-
-	lock_page(page);
-	bio_get(bio);
-
-	if (bio_chain == NULL) {
-		submit_bio(bio_rw, bio);
-		wait_on_page_locked(page);
-		if (rw == READ)
-			bio_set_pages_dirty(bio);
-		bio_put(bio);
-	} else {
-		if (rw == READ)
-			get_page(page);	/* These pages are freed later */
-		bio->bi_private = *bio_chain;
-		*bio_chain = bio;
-		submit_bio(bio_rw, bio);
-	}
-	return 0;
-}
-
-int hib_bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
-{
-	return submit(READ, hib_resume_bdev, page_off * (PAGE_SIZE >> 9),
-			virt_to_page(addr), bio_chain);
-}
-
-int hib_bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
-{
-	return submit(WRITE, hib_resume_bdev, page_off * (PAGE_SIZE >> 9),
-			virt_to_page(addr), bio_chain);
-}
-
-int hib_wait_on_bio_chain(struct bio **bio_chain)
-{
-	struct bio *bio;
-	struct bio *next_bio;
-	int ret = 0;
-
-	if (bio_chain == NULL)
-		return 0;
-
-	bio = *bio_chain;
-	if (bio == NULL)
-		return 0;
-	while (bio) {
-		struct page *page;
-
-		next_bio = bio->bi_private;
-		page = bio->bi_io_vec[0].bv_page;
-		wait_on_page_locked(page);
-		if (!PageUptodate(page) || PageError(page))
-			ret = -EIO;
-		put_page(page);
-		bio_put(bio);
-		bio = next_bio;
-	}
-	*bio_chain = NULL;
-	return ret;
-}

kernel/power/power.h

@@ -163,15 +163,6 @@ extern void swsusp_close(fmode_t);
 extern int swsusp_unmark(void);
 #endif
 
-/* kernel/power/block_io.c */
-extern struct block_device *hib_resume_bdev;
-
-extern int hib_bio_read_page(pgoff_t page_off, void *addr,
-		struct bio **bio_chain);
-extern int hib_bio_write_page(pgoff_t page_off, void *addr,
-		struct bio **bio_chain);
-extern int hib_wait_on_bio_chain(struct bio **bio_chain);
-
 struct timeval;
 /* kernel/power/swsusp.c */
 extern void swsusp_show_speed(ktime_t, ktime_t, unsigned int, char *);

kernel/power/swap.c

@@ -212,7 +212,84 @@ int swsusp_swap_in_use(void)
  */
 
 static unsigned short root_swap = 0xffff;
-struct block_device *hib_resume_bdev;
+static struct block_device *hib_resume_bdev;
+
+struct hib_bio_batch {
+	atomic_t		count;
+	wait_queue_head_t	wait;
+	int			error;
+};
+
+static void hib_init_batch(struct hib_bio_batch *hb)
+{
+	atomic_set(&hb->count, 0);
+	init_waitqueue_head(&hb->wait);
+	hb->error = 0;
+}
+
+static void hib_end_io(struct bio *bio, int error)
+{
+	struct hib_bio_batch *hb = bio->bi_private;
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct page *page = bio->bi_io_vec[0].bv_page;
+
+	if (!uptodate || error) {
+		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
+				imajor(bio->bi_bdev->bd_inode),
+				iminor(bio->bi_bdev->bd_inode),
+				(unsigned long long)bio->bi_iter.bi_sector);
+
+		if (!error)
+			error = -EIO;
+	}
+
+	if (bio_data_dir(bio) == WRITE)
+		put_page(page);
+
+	if (error && !hb->error)
+		hb->error = error;
+	if (atomic_dec_and_test(&hb->count))
+		wake_up(&hb->wait);
+
+	bio_put(bio);
+}
+
+static int hib_submit_io(int rw, pgoff_t page_off, void *addr,
+		struct hib_bio_batch *hb)
+{
+	struct page *page = virt_to_page(addr);
+	struct bio *bio;
+	int error = 0;
+
+	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
+	bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
+	bio->bi_bdev = hib_resume_bdev;
+
+	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+		printk(KERN_ERR "PM: Adding page to bio failed at %llu\n",
+			(unsigned long long)bio->bi_iter.bi_sector);
+		bio_put(bio);
+		return -EFAULT;
+	}
+
+	if (hb) {
+		bio->bi_end_io = hib_end_io;
+		bio->bi_private = hb;
+		atomic_inc(&hb->count);
+		submit_bio(rw, bio);
+	} else {
+		error = submit_bio_wait(rw, bio);
+		bio_put(bio);
+	}
+
+	return error;
+}
+
+static int hib_wait_io(struct hib_bio_batch *hb)
+{
+	wait_event(hb->wait, atomic_read(&hb->count) == 0);
+	return hb->error;
+}
 
 /*
  * Saving part
@@ -222,7 +299,7 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 {
 	int error;
 
-	hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL);
+	hib_submit_io(READ_SYNC, swsusp_resume_block, swsusp_header, NULL);
 	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
 	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
@@ -231,7 +308,7 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 		swsusp_header->flags = flags;
 		if (flags & SF_CRC32_MODE)
 			swsusp_header->crc32 = handle->crc32;
-		error = hib_bio_write_page(swsusp_resume_block,
+		error = hib_submit_io(WRITE_SYNC, swsusp_resume_block,
 					swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "PM: Swap header not found!\n");
@@ -271,10 +348,10 @@ static int swsusp_swap_check(void)
  *	write_page - Write one page to given swap location.
  *	@buf:		Address we're writing.
  *	@offset:	Offset of the swap page we're writing to.
- *	@bio_chain:	Link the next write BIO here
+ *	@hb:		bio completion batch
  */
 
-static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
+static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
 {
 	void *src;
 	int ret;
@@ -282,13 +359,13 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 	if (!offset)
 		return -ENOSPC;
 
-	if (bio_chain) {
+	if (hb) {
 		src = (void *)__get_free_page(__GFP_WAIT | __GFP_NOWARN |
 		                              __GFP_NORETRY);
 		if (src) {
 			copy_page(src, buf);
 		} else {
-			ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */
+			ret = hib_wait_io(hb); /* Free pages */
 			if (ret)
 				return ret;
 			src = (void *)__get_free_page(__GFP_WAIT |
@@ -298,14 +375,14 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 				copy_page(src, buf);
 			} else {
 				WARN_ON_ONCE(1);
-				bio_chain = NULL;	/* Go synchronous */
+				hb = NULL;	/* Go synchronous */
 				src = buf;
 			}
 		}
 	} else {
 		src = buf;
 	}
-	return hib_bio_write_page(offset, src, bio_chain);
+	return hib_submit_io(WRITE_SYNC, offset, src, hb);
 }
 
 static void release_swap_writer(struct swap_map_handle *handle)
@@ -348,7 +425,7 @@ err_close:
 }
 
 static int swap_write_page(struct swap_map_handle *handle, void *buf,
-				struct bio **bio_chain)
+		struct hib_bio_batch *hb)
 {
 	int error = 0;
 	sector_t offset;
@@ -356,7 +433,7 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 	if (!handle->cur)
 		return -EINVAL;
 	offset = alloc_swapdev_block(root_swap);
-	error = write_page(buf, offset, bio_chain);
+	error = write_page(buf, offset, hb);
 	if (error)
 		return error;
 	handle->cur->entries[handle->k++] = offset;
@@ -365,15 +442,15 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		if (!offset)
 			return -ENOSPC;
 		handle->cur->next_swap = offset;
-		error = write_page(handle->cur, handle->cur_swap, bio_chain);
+		error = write_page(handle->cur, handle->cur_swap, hb);
 		if (error)
 			goto out;
 		clear_page(handle->cur);
 		handle->cur_swap = offset;
 		handle->k = 0;
 
-		if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
+		if (hb && low_free_pages() <= handle->reqd_free_pages) {
-			error = hib_wait_on_bio_chain(bio_chain);
+			error = hib_wait_io(hb);
 			if (error)
 				goto out;
 			/*
@@ -445,23 +522,24 @@ static int save_image(struct swap_map_handle *handle,
 	int ret;
 	int nr_pages;
 	int err2;
-	struct bio *bio;
+	struct hib_bio_batch hb;
 	ktime_t start;
 	ktime_t stop;
 
+	hib_init_batch(&hb);
+
 	printk(KERN_INFO "PM: Saving image data pages (%u pages)...\n",
 		nr_to_write);
 	m = nr_to_write / 10;
 	if (!m)
 		m = 1;
 	nr_pages = 0;
-	bio = NULL;
 	start = ktime_get();
 	while (1) {
 		ret = snapshot_read_next(snapshot);
 		if (ret <= 0)
 			break;
-		ret = swap_write_page(handle, data_of(*snapshot), &bio);
+		ret = swap_write_page(handle, data_of(*snapshot), &hb);
 		if (ret)
 			break;
 		if (!(nr_pages % m))
@@ -469,7 +547,7 @@ static int save_image(struct swap_map_handle *handle,
 			       nr_pages / m * 10);
 		nr_pages++;
 	}
-	err2 = hib_wait_on_bio_chain(&bio);
+	err2 = hib_wait_io(&hb);
 	stop = ktime_get();
 	if (!ret)
 		ret = err2;
@@ -580,7 +658,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	int ret = 0;
 	int nr_pages;
 	int err2;
-	struct bio *bio;
+	struct hib_bio_batch hb;
 	ktime_t start;
 	ktime_t stop;
 	size_t off;
@@ -589,6 +667,8 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	struct cmp_data *data = NULL;
 	struct crc_data *crc = NULL;
 
+	hib_init_batch(&hb);
+
 	/*
 	 * We'll limit the number of threads for compression to limit memory
 	 * footprint.
@@ -674,7 +754,6 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	if (!m)
 		m = 1;
 	nr_pages = 0;
-	bio = NULL;
 	start = ktime_get();
 	for (;;) {
 		for (thr = 0; thr < nr_threads; thr++) {
@@ -748,7 +827,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 			     off += PAGE_SIZE) {
 				memcpy(page, data[thr].cmp + off, PAGE_SIZE);
 
-				ret = swap_write_page(handle, page, &bio);
+				ret = swap_write_page(handle, page, &hb);
 				if (ret)
 					goto out_finish;
 			}
@@ -759,7 +838,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	}
 
 out_finish:
-	err2 = hib_wait_on_bio_chain(&bio);
+	err2 = hib_wait_io(&hb);
 	stop = ktime_get();
 	if (!ret)
 		ret = err2;
@@ -906,7 +985,7 @@ static int get_swap_reader(struct swap_map_handle *handle,
 			return -ENOMEM;
 		}
 
-		error = hib_bio_read_page(offset, tmp->map, NULL);
+		error = hib_submit_io(READ_SYNC, offset, tmp->map, NULL);
 		if (error) {
 			release_swap_reader(handle);
 			return error;
@@ -919,7 +998,7 @@ static int get_swap_reader(struct swap_map_handle *handle,
 }
 
 static int swap_read_page(struct swap_map_handle *handle, void *buf,
-				struct bio **bio_chain)
+		struct hib_bio_batch *hb)
 {
 	sector_t offset;
 	int error;
@@ -930,7 +1009,7 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf,
 	offset = handle->cur->entries[handle->k];
 	if (!offset)
 		return -EFAULT;
-	error = hib_bio_read_page(offset, buf, bio_chain);
+	error = hib_submit_io(READ_SYNC, offset, buf, hb);
 	if (error)
 		return error;
 	if (++handle->k >= MAP_PAGE_ENTRIES) {
@@ -968,27 +1047,28 @@ static int load_image(struct swap_map_handle *handle,
 	int ret = 0;
 	ktime_t start;
 	ktime_t stop;
-	struct bio *bio;
+	struct hib_bio_batch hb;
 	int err2;
 	unsigned nr_pages;
 
+	hib_init_batch(&hb);
+
 	printk(KERN_INFO "PM: Loading image data pages (%u pages)...\n",
 		nr_to_read);
 	m = nr_to_read / 10;
 	if (!m)
 		m = 1;
 	nr_pages = 0;
-	bio = NULL;
 	start = ktime_get();
 	for ( ; ; ) {
 		ret = snapshot_write_next(snapshot);
 		if (ret <= 0)
 			break;
-		ret = swap_read_page(handle, data_of(*snapshot), &bio);
+		ret = swap_read_page(handle, data_of(*snapshot), &hb);
 		if (ret)
 			break;
 		if (snapshot->sync_read)
-			ret = hib_wait_on_bio_chain(&bio);
+			ret = hib_wait_io(&hb);
 		if (ret)
 			break;
 		if (!(nr_pages % m))
@@ -996,7 +1076,7 @@ static int load_image(struct swap_map_handle *handle,
 			       nr_pages / m * 10);
 		nr_pages++;
 	}
-	err2 = hib_wait_on_bio_chain(&bio);
+	err2 = hib_wait_io(&hb);
 	stop = ktime_get();
 	if (!ret)
 		ret = err2;
@@ -1067,7 +1147,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	unsigned int m;
 	int ret = 0;
 	int eof = 0;
-	struct bio *bio;
+	struct hib_bio_batch hb;
 	ktime_t start;
 	ktime_t stop;
 	unsigned nr_pages;
@@ -1080,6 +1160,8 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	struct dec_data *data = NULL;
 	struct crc_data *crc = NULL;
 
+	hib_init_batch(&hb);
+
 	/*
 	 * We'll limit the number of threads for decompression to limit memory
 	 * footprint.
@@ -1190,7 +1272,6 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	if (!m)
 		m = 1;
 	nr_pages = 0;
-	bio = NULL;
 	start = ktime_get();
 
 	ret = snapshot_write_next(snapshot);
@@ -1199,7 +1280,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 
 	for(;;) {
 		for (i = 0; !eof && i < want; i++) {
-			ret = swap_read_page(handle, page[ring], &bio);
+			ret = swap_read_page(handle, page[ring], &hb);
 			if (ret) {
 				/*
 				 * On real read error, finish. On end of data,
@@ -1226,7 +1307,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 			if (!asked)
 				break;
 
-			ret = hib_wait_on_bio_chain(&bio);
+			ret = hib_wait_io(&hb);
 			if (ret)
 				goto out_finish;
 			have += asked;
@@ -1281,7 +1362,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 		 * Wait for more data while we are decompressing.
 		 */
 		if (have < LZO_CMP_PAGES && asked) {
-			ret = hib_wait_on_bio_chain(&bio);
+			ret = hib_wait_io(&hb);
 			if (ret)
 				goto out_finish;
 			have += asked;
@@ -1430,7 +1511,7 @@ int swsusp_check(void)
 	if (!IS_ERR(hib_resume_bdev)) {
 		set_blocksize(hib_resume_bdev, PAGE_SIZE);
 		clear_page(swsusp_header);
-		error = hib_bio_read_page(swsusp_resume_block,
+		error = hib_submit_io(READ_SYNC, swsusp_resume_block,
 					swsusp_header, NULL);
 		if (error)
 			goto put;
@@ -1438,7 +1519,7 @@ int swsusp_check(void)
 		if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) {
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
-			error = hib_bio_write_page(swsusp_resume_block,
+			error = hib_submit_io(WRITE_SYNC, swsusp_resume_block,
 						swsusp_header, NULL);
 		} else {
 			error = -EINVAL;
@@ -1482,10 +1563,10 @@ int swsusp_unmark(void)
 {
 	int error;
 
-	hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL);
+	hib_submit_io(READ_SYNC, swsusp_resume_block, swsusp_header, NULL);
 	if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10);
-		error = hib_bio_write_page(swsusp_resume_block,
+		error = hib_submit_io(WRITE_SYNC, swsusp_resume_block,
 					swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "PM: Cannot find swsusp signature!\n");

mm/page_io.c

@@ -69,7 +69,7 @@ void end_swap_bio_write(struct bio *bio, int err)
 	bio_put(bio);
 }
 
-void end_swap_bio_read(struct bio *bio, int err)
+static void end_swap_bio_read(struct bio *bio, int err)
 {
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct page *page = bio->bi_io_vec[0].bv_page;