diff --git a/block/blk-core.c b/block/blk-core.c
index 34d7c196338b..a0e3096c4bb5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1307,7 +1307,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 		struct request_list *rl = blk_rq_rl(req);
 
 		BUG_ON(!list_empty(&req->queuelist));
-		BUG_ON(!hlist_unhashed(&req->hash));
+		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
 		freed_request(rl, flags);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b1bcc619d0ea..1d2a9bdbee57 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -956,6 +956,7 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
 			       unsigned int cpu)
 {
 	struct blk_mq_hw_ctx *hctx = data;
+	struct request_queue *q = hctx->queue;
 	struct blk_mq_ctx *ctx;
 	LIST_HEAD(tmp);
 
@@ -965,7 +966,7 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
 	/*
 	 * Move ctx entries to new CPU, if this one is going away.
 	 */
-	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
+	ctx = __blk_mq_get_ctx(q, cpu);
 
 	spin_lock(&ctx->lock);
 	if (!list_empty(&ctx->rq_list)) {
@@ -977,7 +978,7 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
 	if (list_empty(&tmp))
 		return;
 
-	ctx = blk_mq_get_ctx(hctx->queue);
+	ctx = blk_mq_get_ctx(q);
 	spin_lock(&ctx->lock);
 
 	while (!list_empty(&tmp)) {
@@ -988,10 +989,13 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
 		list_move_tail(&rq->queuelist, &ctx->rq_list);
 	}
 
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 
 	spin_unlock(&ctx->lock);
 	blk_mq_put_ctx(ctx);
+
+	blk_mq_run_hw_queue(hctx, true);
 }
 
 static int blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index ebd6b6f1bdeb..53b1737e978d 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -30,8 +30,8 @@ static void blk_done_softirq(struct softirq_action *h)
 	while (!list_empty(&local_list)) {
 		struct request *rq;
 
-		rq = list_entry(local_list.next, struct request, queuelist);
-		list_del_init(&rq->queuelist);
+		rq = list_entry(local_list.next, struct request, ipi_list);
+		list_del_init(&rq->ipi_list);
 		rq->q->softirq_done_fn(rq);
 	}
 }
@@ -45,14 +45,9 @@ static void trigger_softirq(void *data)
 
 	local_irq_save(flags);
 	list = this_cpu_ptr(&blk_cpu_done);
-	/*
-	 * We reuse queuelist for a list of requests to process. Since the
-	 * queuelist is used by the block layer only for requests waiting to be
-	 * submitted to the device it is unused now.
-	 */
-	list_add_tail(&rq->queuelist, list);
+	list_add_tail(&rq->ipi_list, list);
 
-	if (list->next == &rq->queuelist)
+	if (list->next == &rq->ipi_list)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 
 	local_irq_restore(flags);
@@ -141,7 +136,7 @@ void __blk_complete_request(struct request *req)
 		struct list_head *list;
 do_local:
 		list = this_cpu_ptr(&blk_cpu_done);
-		list_add_tail(&req->queuelist, list);
+		list_add_tail(&req->ipi_list, list);
 
 		/*
 		 * if the list only contains our just added request,
@@ -149,7 +144,7 @@ do_local:
 		 * entries there, someone already raised the irq but it
 		 * hasn't run yet.
 		 */
-		if (list->next == &req->queuelist)
+		if (list->next == &req->ipi_list)
 			raise_softirq_irqoff(BLOCK_SOFTIRQ);
 	} else if (raise_blk_irq(ccpu, req))
 		goto do_local;
diff --git a/block/blk.h b/block/blk.h
index d23b415b8a28..1d880f1f957f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -78,7 +78,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
 /*
  * Internal elevator interface
  */
-#define ELV_ON_HASH(rq) hash_hashed(&(rq)->hash)
+#define ELV_ON_HASH(rq) ((rq)->cmd_flags & REQ_HASHED)
 
 void blk_insert_flush(struct request *rq);
 void blk_abort_flushes(struct request_queue *q);
diff --git a/block/elevator.c b/block/elevator.c
index 42c45a7d6714..1e01b66a0b92 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -247,6 +247,7 @@ EXPORT_SYMBOL(elevator_exit);
 static inline void __elv_rqhash_del(struct request *rq)
 {
 	hash_del(&rq->hash);
+	rq->cmd_flags &= ~REQ_HASHED;
 }
 
 static void elv_rqhash_del(struct request_queue *q, struct request *rq)
@@ -261,6 +262,7 @@ static void elv_rqhash_add(struct request_queue *q, struct request *rq)
 
 	BUG_ON(ELV_ON_HASH(rq));
 	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
+	rq->cmd_flags |= REQ_HASHED;
 }
 
 static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 66e8c3b94ef3..f70a230a2945 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -237,7 +237,7 @@ static int __do_lo_send_write(struct file *file,
 	file_end_write(file);
 	if (likely(bw == len))
 		return 0;
-	printk(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
+	printk_ratelimited(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
 			(unsigned long long)pos, len);
 	if (bw >= 0)
 		bw = -EIO;
@@ -277,7 +277,7 @@ static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
 		return __do_lo_send_write(lo->lo_backing_file,
 				page_address(page), bvec->bv_len,
 				pos);
-	printk(KERN_ERR "loop: Transfer error at byte offset %llu, "
+	printk_ratelimited(KERN_ERR "loop: Transfer error at byte offset %llu, "
 			"length %i.\n", (unsigned long long)pos, bvec->bv_len);
 	if (ret > 0)
 		ret = -EIO;
@@ -316,7 +316,7 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
 out:
 	return ret;
 fail:
-	printk(KERN_ERR "loop: Failed to allocate temporary page for write.\n");
+	printk_ratelimited(KERN_ERR "loop: Failed to allocate temporary page for write.\n");
 	ret = -ENOMEM;
 	goto out;
 }
@@ -345,7 +345,7 @@ lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		size = p->bsize;
 
 	if (lo_do_transfer(lo, READ, page, buf->offset, p->page, p->offset, size, IV)) {
-		printk(KERN_ERR "loop: transfer error block %ld\n",
+		printk_ratelimited(KERN_ERR "loop: transfer error block %ld\n",
 		       page->index);
 		size = -EINVAL;
 	}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 5681c05ac506..65a123d9c676 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -184,7 +184,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
  */
 int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
-		 unsigned char *sense, int timeout, int retries, int flags,
+		 unsigned char *sense, int timeout, int retries, u64 flags,
 		 int *resid)
 {
 	struct request *req;
@@ -235,7 +235,7 @@ EXPORT_SYMBOL(scsi_execute);
 int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
 		     int data_direction, void *buffer, unsigned bufflen,
 		     struct scsi_sense_hdr *sshdr, int timeout, int retries,
-		     int *resid, int flags)
+		     int *resid, u64 flags)
 {
 	char *sense = NULL;
 	int result;
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 29696b78d1f4..1c2ce0c87711 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -182,6 +182,9 @@ static int bdev_integrity_enabled(struct block_device *bdev, int rw)
  */
 int bio_integrity_enabled(struct bio *bio)
 {
+	if (!bio_is_rw(bio))
+		return 0;
+
 	/* Already protected? */
 	if (bio_integrity(bio))
 		return 0;
@@ -309,10 +312,9 @@ static int bio_integrity_generate_verify(struct bio *bio, int operate)
 {
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	struct blk_integrity_exchg bix;
-	struct bio_vec bv;
-	struct bvec_iter iter;
+	struct bio_vec *bv;
 	sector_t sector;
-	unsigned int sectors, ret = 0;
+	unsigned int sectors, ret = 0, i;
 	void *prot_buf = bio->bi_integrity->bip_buf;
 
 	if (operate)
@@ -323,16 +325,16 @@ static int bio_integrity_generate_verify(struct bio *bio, int operate)
 	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
 	bix.sector_size = bi->sector_size;
 
-	bio_for_each_segment(bv, bio, iter) {
-		void *kaddr = kmap_atomic(bv.bv_page);
-		bix.data_buf = kaddr + bv.bv_offset;
-		bix.data_size = bv.bv_len;
+	bio_for_each_segment_all(bv, bio, i) {
+		void *kaddr = kmap_atomic(bv->bv_page);
+		bix.data_buf = kaddr + bv->bv_offset;
+		bix.data_size = bv->bv_len;
 		bix.prot_buf = prot_buf;
 		bix.sector = sector;
 
-		if (operate) {
+		if (operate)
 			bi->generate_fn(&bix);
-		} else {
+		else {
 			ret = bi->verify_fn(&bix);
 			if (ret) {
 				kunmap_atomic(kaddr);
@@ -340,7 +342,7 @@ static int bio_integrity_generate_verify(struct bio *bio, int operate)
 			}
 		}
 
-		sectors = bv.bv_len / bi->sector_size;
+		sectors = bv->bv_len / bi->sector_size;
 		sector += sectors;
 		prot_buf += sectors * bi->tuple_size;
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5a4d39b4686b..5aa372a7380c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -216,9 +216,9 @@ static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter,
 }
 
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
-	for ((iter) = start;						\
-	     (bvl) = bvec_iter_bvec((bio_vec), (iter)),			\
-		(iter).bi_size;						\
+	for (iter = (start);						\
+	     (iter).bi_size &&						\
+		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
 	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
 
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index bbc3a6c88fce..aa0eaa2d0bd8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -189,6 +189,7 @@ enum rq_flag_bits {
 	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_PM,		/* runtime pm request */
 	__REQ_END,		/* last of chain of requests */
+	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -241,5 +242,6 @@ enum rq_flag_bits {
 #define REQ_KERNEL		(1ULL << __REQ_KERNEL)
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_END			(1ULL << __REQ_END)
+#define REQ_HASHED		(1ULL << __REQ_HASHED)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1e1fa3f93d5f..99617cf7dd1a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -118,7 +118,18 @@ struct request {
 	struct bio *bio;
 	struct bio *biotail;
 
-	struct hlist_node hash;	/* merge hash */
+	/*
+	 * The hash is used inside the scheduler, and killed once the
+	 * request reaches the dispatch list. The ipi_list is only used
+	 * to queue the request for softirq completion, which is long
+	 * after the request has been unhashed (and even removed from
+	 * the dispatch list).
+	 */
+	union {
+		struct hlist_node hash;	/* merge hash */
+		struct list_head ipi_list;
+	};
+
 	/*
 	 * The rb_node is only used inside the io scheduler, requests
 	 * are pruned when moved to the dispatch queue. So let the
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 4e845b80efd3..5853c913d2b0 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -423,11 +423,11 @@ extern int scsi_is_target_device(const struct device *);
 extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 			int data_direction, void *buffer, unsigned bufflen,
 			unsigned char *sense, int timeout, int retries,
-			int flag, int *resid);
+			u64 flags, int *resid);
 extern int scsi_execute_req_flags(struct scsi_device *sdev,
 	const unsigned char *cmd, int data_direction, void *buffer,
 	unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout,
-	int retries, int *resid, int flags);
+	int retries, int *resid, u64 flags);
 static inline int scsi_execute_req(struct scsi_device *sdev,
 	const unsigned char *cmd, int data_direction, void *buffer,
 	unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout,