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

Pull block layer fixes from Jens Axboe:
"A small collection of fixes that should go in before -rc1. The pull
request contains:

- A two patch fix for a regression with block enabled tagging caused
by a commit in the initial pull request. One patch is from Martin
and ensures that SCSI doesn't truncate 64-bit block flags, the
other one is from me and prevents us from double using struct
request queuelist for both completion and busy tags. This caused
anything from a boot crash for some, to crashes under load.

- A blk-mq fix for a potential soft stall when hot unplugging CPUs
with busy IO.

- percpu_counter fix is listed in here, that caused a suspend issue
with virtio-blk due to percpu counters having an inconsistent state
during CPU removal. Andrew sent this in separately a few days ago,
but it's here. JFYI.

- A few fixes for block integrity from Martin.

- A ratelimit fix for loop from Mike Galbraith, to avoid spewing too
much in error cases"

* 'for-linus' of git://git.kernel.dk/linux-block:
block: fix regression with block enabled tagging
scsi: Make sure cmd_flags are 64-bit
block: Ensure we only enable integrity metadata for reads and writes
block: Fix integrity verification
block: Fix for_each_bvec()
drivers/block/loop.c: ratelimit error messages
blk-mq: fix potential stall during CPU unplug with IO pending
percpu_counter: fix bad counter state during suspend

block/blk-core.c

···
 		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);

block/blk-mq.c

···
 			       unsigned int cpu)
 {
 	struct blk_mq_hw_ctx *hctx = data;
+	struct request_queue *q = hctx->queue;
 	struct blk_mq_ctx *ctx;
 	LIST_HEAD(tmp);
 
···
 	/*
 	 * 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)) {
···
 	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)) {
···
 		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,

block/blk-softirq.c

···
 	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);
 	}
 }
···
 
 	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);
···
 		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,
···
 		 * 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;

block/blk.h

···
 /*
  * 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);

block/elevator.c

···
 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)
···
 
 	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)

drivers/block/loop.c

···
 	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;
···
 		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;
···
 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;
 }
···
 		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;
 	}

drivers/scsi/scsi_lib.c

···
  */
 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;
···
 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;

fs/bio-integrity.c

···
  */
 int bio_integrity_enabled(struct bio *bio)
 {
+	if (!bio_is_rw(bio))
+		return 0;
+
 	/* Already protected? */
 	if (bio_integrity(bio))
 		return 0;
···
 {
 	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)
···
 	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);
···
 			}
 		}
 
-		sectors = bv.bv_len / bi->sector_size;
+		sectors = bv->bv_len / bi->sector_size;
 		sector += sectors;
 		prot_buf += sectors * bi->tuple_size;
 

include/linux/bio.h

···
 }
 
 #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))
 
 

include/linux/blk_types.h

···
 	__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 */
 };
 
···
 #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 */

include/linux/blkdev.h

···
 	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

include/scsi/scsi_device.h

···
 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,