Merge branch 'for-4.16/block' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block IO related changes for the
  4.16 kernel. Nothing major in this pull request, but a good amount of
  improvements and fixes all over the map. This contains:

   - BFQ improvements, fixes, and cleanups from Angelo, Chiara, and
     Paolo.

   - Support for SMR zones for deadline and mq-deadline from Damien and
     Christoph.

   - Set of fixes for bcache by way of Michael Lyle, including fixes
     from himself, Kent, Rui, Tang, and Coly.

   - Series from Matias for lightnvm with fixes from Hans Holmberg,
     Javier, and Matias. Mostly centered around pblk, and the removing
     rrpc 1.2 in preparation for supporting 2.0.

   - A couple of NVMe pull requests from Christoph. Nothing major in
     here, just fixes and cleanups, and support for command tracing from
     Johannes.

   - Support for blk-throttle for tracking reads and writes separately.
     From Joseph Qi. A few cleanups/fixes also for blk-throttle from
     Weiping.

   - Series from Mike Snitzer that enables dm to register its queue more
     logically, something that's alwways been problematic on dm since
     it's a stacked device.

   - Series from Ming cleaning up some of the bio accessor use, in
     preparation for supporting multipage bvecs.

   - Various fixes from Ming closing up holes around queue mapping and
     quiescing.

   - BSD partition fix from Richard Narron, fixing a problem where we
     can't mount newer (10/11) FreeBSD partitions.

   - Series from Tejun reworking blk-mq timeout handling. The previous
     scheme relied on atomic bits, but it had races where we would think
     a request had timed out if it to reused at the wrong time.

   - null_blk now supports faking timeouts, to enable us to better
     exercise and test that functionality separately. From me.

   - Kill the separate atomic poll bit in the request struct. After
     this, we don't use the atomic bits on blk-mq anymore at all. From
     me.

   - sgl_alloc/free helpers from Bart.

   - Heavily contended tag case scalability improvement from me.

   - Various little fixes and cleanups from Arnd, Bart, Corentin,
     Douglas, Eryu, Goldwyn, and myself"

* 'for-4.16/block' of git://git.kernel.dk/linux-block: (186 commits)
  block: remove smart1,2.h
  nvme: add tracepoint for nvme_complete_rq
  nvme: add tracepoint for nvme_setup_cmd
  nvme-pci: introduce RECONNECTING state to mark initializing procedure
  nvme-rdma: remove redundant boolean for inline_data
  nvme: don't free uuid pointer before printing it
  nvme-pci: Suspend queues after deleting them
  bsg: use pr_debug instead of hand crafted macros
  blk-mq-debugfs: don't allow write on attributes with seq_operations set
  nvme-pci: Fix queue double allocations
  block: Set BIO_TRACE_COMPLETION on new bio during split
  blk-throttle: use queue_is_rq_based
  block: Remove kblockd_schedule_delayed_work{,_on}()
  blk-mq: Avoid that blk_mq_delay_run_hw_queue() introduces unintended delays
  blk-mq: Rename blk_mq_request_direct_issue() into blk_mq_request_issue_directly()
  lib/scatterlist: Fix chaining support in sgl_alloc_order()
  blk-throttle: track read and write request individually
  block: add bdev_read_only() checks to common helpers
  block: fail op_is_write() requests to read-only partitions
  blk-throttle: export io_serviced_recursive, io_service_bytes_recursive
  ...

block/bfq-cgroup.c

@@ -775,10 +775,11 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	unsigned long flags;
 	int i;
 
+	spin_lock_irqsave(&bfqd->lock, flags);
+
 	if (!entity) /* root group */
-		return;
+		goto put_async_queues;
 
-	spin_lock_irqsave(&bfqd->lock, flags);
 	/*
 	 * Empty all service_trees belonging to this group before
 	 * deactivating the group itself.
@@ -809,6 +810,8 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	}
 
 	__bfq_deactivate_entity(entity, false);
+
+put_async_queues:
 	bfq_put_async_queues(bfqd, bfqg);
 
 	spin_unlock_irqrestore(&bfqd->lock, flags);

block/bfq-iosched.h

@@ -337,6 +337,11 @@ struct bfq_queue {
 	 * last transition from idle to backlogged.
 	 */
 	unsigned long service_from_backlogged;
+	/*
+	 * Cumulative service received from the @bfq_queue since its
+	 * last transition to weight-raised state.
+	 */
+	unsigned long service_from_wr;
 
 	/*
 	 * Value of wr start time when switching to soft rt
@@ -344,6 +349,8 @@ struct bfq_queue {
 	unsigned long wr_start_at_switch_to_srt;
 
 	unsigned long split_time; /* time of last split */
+
+	unsigned long first_IO_time; /* time of first I/O for this queue */
 };
 
 /**
@@ -627,6 +634,18 @@ struct bfq_data {
 	struct bfq_io_cq *bio_bic;
 	/* bfqq associated with the task issuing current bio for merging */
 	struct bfq_queue *bio_bfqq;
+
+	/*
+	 * Cached sbitmap shift, used to compute depth limits in
+	 * bfq_update_depths.
+	 */
+	unsigned int sb_shift;
+
+	/*
+	 * Depth limits used in bfq_limit_depth (see comments on the
+	 * function)
+	 */
+	unsigned int word_depths[2][2];
 };
 
 enum bfqq_state_flags {

block/bfq-wf2q.c

@@ -835,6 +835,13 @@ void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
 	struct bfq_entity *entity = &bfqq->entity;
 	struct bfq_service_tree *st;
 
+	if (!bfqq->service_from_backlogged)
+		bfqq->first_IO_time = jiffies;
+
+	if (bfqq->wr_coeff > 1)
+		bfqq->service_from_wr += served;
+
+	bfqq->service_from_backlogged += served;
 	for_each_entity(entity) {
 		st = bfq_entity_service_tree(entity);
 

block/bio-integrity.c

@@ -374,7 +374,6 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 /**
  * __bio_integrity_endio - Integrity I/O completion function
  * @bio:	Protected bio
- * @error:	Pointer to errno
  *
  * Description: Completion for integrity I/O
  *

block/bio.c

@@ -970,34 +970,6 @@ void bio_advance(struct bio *bio, unsigned bytes)
 }
 EXPORT_SYMBOL(bio_advance);
 
-/**
- * bio_alloc_pages - allocates a single page for each bvec in a bio
- * @bio: bio to allocate pages for
- * @gfp_mask: flags for allocation
- *
- * Allocates pages up to @bio->bi_vcnt.
- *
- * Returns 0 on success, -ENOMEM on failure. On failure, any allocated pages are
- * freed.
- */
-int bio_alloc_pages(struct bio *bio, gfp_t gfp_mask)
-{
-	int i;
-	struct bio_vec *bv;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		bv->bv_page = alloc_page(gfp_mask);
-		if (!bv->bv_page) {
-			while (--bv >= bio->bi_io_vec)
-				__free_page(bv->bv_page);
-			return -ENOMEM;
-		}
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(bio_alloc_pages);
-
 /**
  * bio_copy_data - copy contents of data buffers from one chain of bios to
  * another
@@ -1838,7 +1810,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	bio_advance(bio, split->bi_iter.bi_size);
 
 	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
-		bio_set_flag(bio, BIO_TRACE_COMPLETION);
+		bio_set_flag(split, BIO_TRACE_COMPLETION);
 
 	return split;
 }

block/blk-core.c

@@ -126,6 +126,8 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
 	rq->part = NULL;
+	seqcount_init(&rq->gstate_seq);
+	u64_stats_init(&rq->aborted_gstate_sync);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -699,6 +701,15 @@ void blk_cleanup_queue(struct request_queue *q)
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 
+	/*
+	 * make sure all in-progress dispatch are completed because
+	 * blk_freeze_queue() can only complete all requests, and
+	 * dispatch may still be in-progress since we dispatch requests
+	 * from more than one contexts
+	 */
+	if (q->mq_ops)
+		blk_mq_quiesce_queue(q);
+
 	/* for synchronous bio-based driver finish in-flight integrity i/o */
 	blk_flush_integrity();
 
@@ -1646,6 +1657,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 
 	lockdep_assert_held(q->queue_lock);
 
+	blk_req_zone_write_unlock(req);
 	blk_pm_put_request(req);
 
 	elv_completed_request(q, req);
@@ -2055,6 +2067,21 @@ static inline bool should_fail_request(struct hd_struct *part,
 
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
+static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
+{
+	if (part->policy && op_is_write(bio_op(bio))) {
+		char b[BDEVNAME_SIZE];
+
+		printk(KERN_ERR
+		       "generic_make_request: Trying to write "
+			"to read-only block-device %s (partno %d)\n",
+			bio_devname(bio, b), part->partno);
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Remap block n of partition p to block n+start(p) of the disk.
  */
@@ -2063,27 +2090,28 @@ static inline int blk_partition_remap(struct bio *bio)
 	struct hd_struct *p;
 	int ret = 0;
 
+	rcu_read_lock();
+	p = __disk_get_part(bio->bi_disk, bio->bi_partno);
+	if (unlikely(!p || should_fail_request(p, bio->bi_iter.bi_size) ||
+		     bio_check_ro(bio, p))) {
+		ret = -EIO;
+		goto out;
+	}
+
 	/*
 	 * Zone reset does not include bi_size so bio_sectors() is always 0.
 	 * Include a test for the reset op code and perform the remap if needed.
 	 */
-	if (!bio->bi_partno ||
-	    (!bio_sectors(bio) && bio_op(bio) != REQ_OP_ZONE_RESET))
-		return 0;
+	if (!bio_sectors(bio) && bio_op(bio) != REQ_OP_ZONE_RESET)
+		goto out;
 
-	rcu_read_lock();
-	p = __disk_get_part(bio->bi_disk, bio->bi_partno);
-	if (likely(p && !should_fail_request(p, bio->bi_iter.bi_size))) {
-		bio->bi_iter.bi_sector += p->start_sect;
-		bio->bi_partno = 0;
-		trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
-				bio->bi_iter.bi_sector - p->start_sect);
-	} else {
-		printk("%s: fail for partition %d\n", __func__, bio->bi_partno);
-		ret = -EIO;
-	}
-	rcu_read_unlock();
+	bio->bi_iter.bi_sector += p->start_sect;
+	bio->bi_partno = 0;
+	trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
+			      bio->bi_iter.bi_sector - p->start_sect);
 
+out:
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -2142,15 +2170,19 @@ generic_make_request_checks(struct bio *bio)
 	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
 	 * if queue is not a request based queue.
 	 */
-
 	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
 		goto not_supported;
 
 	if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
 		goto end_io;
 
-	if (blk_partition_remap(bio))
-		goto end_io;
+	if (!bio->bi_partno) {
+		if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0)))
+			goto end_io;
+	} else {
+		if (blk_partition_remap(bio))
+			goto end_io;
+	}
 
 	if (bio_check_eod(bio, nr_sectors))
 		goto end_io;
@@ -2493,8 +2525,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 		 * bypass a potential scheduler on the bottom device for
 		 * insert.
 		 */
-		blk_mq_request_bypass_insert(rq, true);
-		return BLK_STS_OK;
+		return blk_mq_request_issue_directly(rq);
 	}
 
 	spin_lock_irqsave(q->queue_lock, flags);
@@ -2846,7 +2877,7 @@ void blk_start_request(struct request *req)
 		wbt_issue(req->q->rq_wb, &req->issue_stat);
 	}
 
-	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
+	BUG_ON(blk_rq_is_complete(req));
 	blk_add_timer(req);
 }
 EXPORT_SYMBOL(blk_start_request);
@@ -3415,20 +3446,6 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork,
 }
 EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
 
-int kblockd_schedule_delayed_work(struct delayed_work *dwork,
-				  unsigned long delay)
-{
-	return queue_delayed_work(kblockd_workqueue, dwork, delay);
-}
-EXPORT_SYMBOL(kblockd_schedule_delayed_work);
-
-int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
-				     unsigned long delay)
-{
-	return queue_delayed_work_on(cpu, kblockd_workqueue, dwork, delay);
-}
-EXPORT_SYMBOL(kblockd_schedule_delayed_work_on);
-
 /**
  * blk_start_plug - initialize blk_plug and track it inside the task_struct
  * @plug:	The &struct blk_plug that needs to be initialized

block/blk-exec.c

@@ -61,7 +61,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_sched_insert_request(rq, at_head, true, false, false);
+		blk_mq_sched_insert_request(rq, at_head, true, false);
 		return;
 	}
 

block/blk-lib.c

@@ -37,6 +37,9 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	if (!q)
 		return -ENXIO;
 
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
 	if (flags & BLKDEV_DISCARD_SECURE) {
 		if (!blk_queue_secure_erase(q))
 			return -EOPNOTSUPP;
@@ -156,6 +159,9 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	if (!q)
 		return -ENXIO;
 
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
 	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
@@ -233,6 +239,9 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 	if (!q)
 		return -ENXIO;
 
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
 	/* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */
 	max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev);
 
@@ -287,6 +296,9 @@ static int __blkdev_issue_zero_pages(struct block_device *bdev,
 	if (!q)
 		return -ENXIO;
 
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
 	while (nr_sects != 0) {
 		bio = next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects),
 			       gfp_mask);

block/blk-map.c

@@ -119,7 +119,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
 	struct bio *bio = NULL;
 	struct iov_iter i;
-	int ret;
+	int ret = -EINVAL;
 
 	if (!iter_is_iovec(iter))
 		goto fail;
@@ -148,7 +148,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	__blk_rq_unmap_user(bio);
 fail:
 	rq->bio = NULL;
-	return -EINVAL;
+	return ret;
 }
 EXPORT_SYMBOL(blk_rq_map_user_iov);
 

block/blk-merge.c

@@ -128,9 +128,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 				nsegs++;
 				sectors = max_sectors;
 			}
-			if (sectors)
-				goto split;
-			/* Make this single bvec as the 1st segment */
+			goto split;
 		}
 
 		if (bvprvp && blk_queue_cluster(q)) {
@@ -146,22 +144,21 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			bvprvp = &bvprv;
 			sectors += bv.bv_len >> 9;
 
-			if (nsegs == 1 && seg_size > front_seg_size)
-				front_seg_size = seg_size;
 			continue;
 		}
 new_segment:
 		if (nsegs == queue_max_segments(q))
 			goto split;
 
+		if (nsegs == 1 && seg_size > front_seg_size)
+			front_seg_size = seg_size;
+
 		nsegs++;
 		bvprv = bv;
 		bvprvp = &bvprv;
 		seg_size = bv.bv_len;
 		sectors += bv.bv_len >> 9;
 
-		if (nsegs == 1 && seg_size > front_seg_size)
-			front_seg_size = seg_size;
 	}
 
 	do_split = false;
@@ -174,6 +171,8 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			bio = new;
 	}
 
+	if (nsegs == 1 && seg_size > front_seg_size)
+		front_seg_size = seg_size;
 	bio->bi_seg_front_size = front_seg_size;
 	if (seg_size > bio->bi_seg_back_size)
 		bio->bi_seg_back_size = seg_size;

block/blk-mq-debugfs.c

@@ -289,17 +289,12 @@ static const char *const rqf_name[] = {
 	RQF_NAME(HASHED),
 	RQF_NAME(STATS),
 	RQF_NAME(SPECIAL_PAYLOAD),
+	RQF_NAME(ZONE_WRITE_LOCKED),
+	RQF_NAME(MQ_TIMEOUT_EXPIRED),
+	RQF_NAME(MQ_POLL_SLEPT),
 };
 #undef RQF_NAME
 
-#define RQAF_NAME(name) [REQ_ATOM_##name] = #name
-static const char *const rqaf_name[] = {
-	RQAF_NAME(COMPLETE),
-	RQAF_NAME(STARTED),
-	RQAF_NAME(POLL_SLEPT),
-};
-#undef RQAF_NAME
-
 int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 {
 	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
@@ -316,8 +311,7 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 	seq_puts(m, ", .rq_flags=");
 	blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
 		       ARRAY_SIZE(rqf_name));
-	seq_puts(m, ", .atomic_flags=");
-	blk_flags_show(m, rq->atomic_flags, rqaf_name, ARRAY_SIZE(rqaf_name));
+	seq_printf(m, ", complete=%d", blk_rq_is_complete(rq));
 	seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
 		   rq->internal_tag);
 	if (mq_ops->show_rq)
@@ -409,7 +403,7 @@ static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved)
 	const struct show_busy_params *params = data;
 
 	if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx &&
-	    test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+	    blk_mq_rq_state(rq) != MQ_RQ_IDLE)
 		__blk_mq_debugfs_rq_show(params->m,
 					 list_entry_rq(&rq->queuelist));
 }
@@ -703,7 +697,11 @@ static ssize_t blk_mq_debugfs_write(struct file *file, const char __user *buf,
 	const struct blk_mq_debugfs_attr *attr = m->private;
 	void *data = d_inode(file->f_path.dentry->d_parent)->i_private;
 
-	if (!attr->write)
+	/*
+	 * Attributes that only implement .seq_ops are read-only and 'attr' is
+	 * the same with 'data' in this case.
+	 */
+	if (attr == data || !attr->write)
 		return -EPERM;
 
 	return attr->write(data, buf, count, ppos);

block/blk-mq-sched.c

@@ -172,7 +172,6 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
 	WRITE_ONCE(hctx->dispatch_from, ctx);
 }
 
-/* return true if hw queue need to be run again */
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 {
 	struct request_queue *q = hctx->queue;
@@ -428,7 +427,7 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
 }
 
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
-				 bool run_queue, bool async, bool can_block)
+				 bool run_queue, bool async)
 {
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;

block/blk-mq-sched.h

@@ -18,7 +18,7 @@ bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
 void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
 
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
-				 bool run_queue, bool async, bool can_block);
+				 bool run_queue, bool async);
 void blk_mq_sched_insert_requests(struct request_queue *q,
 				  struct blk_mq_ctx *ctx,
 				  struct list_head *list, bool run_queue_async);

block/blk-mq-sysfs.c

@@ -248,7 +248,7 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 	return ret;
 }
 
-static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
+void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
@@ -265,13 +265,6 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 	q->mq_sysfs_init_done = false;
 }
 
-void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
-{
-	mutex_lock(&q->sysfs_lock);
-	__blk_mq_unregister_dev(dev, q);
-	mutex_unlock(&q->sysfs_lock);
-}
-
 void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
 {
 	kobject_init(&hctx->kobj, &blk_mq_hw_ktype);

block/blk-mq-tag.c

@@ -134,12 +134,6 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	ws = bt_wait_ptr(bt, data->hctx);
 	drop_ctx = data->ctx == NULL;
 	do {
-		prepare_to_wait(&ws->wait, &wait, TASK_UNINTERRUPTIBLE);
-
-		tag = __blk_mq_get_tag(data, bt);
-		if (tag != -1)
-			break;
-
 		/*
 		 * We're out of tags on this hardware queue, kick any
 		 * pending IO submits before going to sleep waiting for
@@ -155,6 +149,13 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 		if (tag != -1)
 			break;
 
+		prepare_to_wait_exclusive(&ws->wait, &wait,
+						TASK_UNINTERRUPTIBLE);
+
+		tag = __blk_mq_get_tag(data, bt);
+		if (tag != -1)
+			break;
+
 		if (data->ctx)
 			blk_mq_put_ctx(data->ctx);
 

block/blk-mq.h

@@ -27,6 +27,20 @@ struct blk_mq_ctx {
 	struct kobject		kobj;
 } ____cacheline_aligned_in_smp;
 
+/*
+ * Bits for request->gstate.  The lower two bits carry MQ_RQ_* state value
+ * and the upper bits the generation number.
+ */
+enum mq_rq_state {
+	MQ_RQ_IDLE		= 0,
+	MQ_RQ_IN_FLIGHT		= 1,
+	MQ_RQ_COMPLETE		= 2,
+
+	MQ_RQ_STATE_BITS	= 2,
+	MQ_RQ_STATE_MASK	= (1 << MQ_RQ_STATE_BITS) - 1,
+	MQ_RQ_GEN_INC		= 1 << MQ_RQ_STATE_BITS,
+};
+
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
@@ -60,6 +74,9 @@ void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
 
+/* Used by blk_insert_cloned_request() to issue request directly */
+blk_status_t blk_mq_request_issue_directly(struct request *rq);
+
 /*
  * CPU -> queue mappings
  */
@@ -81,10 +98,41 @@ extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
-extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
-
 void blk_mq_release(struct request_queue *q);
 
+/**
+ * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
+ * @rq: target request.
+ */
+static inline int blk_mq_rq_state(struct request *rq)
+{
+	return READ_ONCE(rq->gstate) & MQ_RQ_STATE_MASK;
+}
+
+/**
+ * blk_mq_rq_update_state() - set the current MQ_RQ_* state of a request
+ * @rq: target request.
+ * @state: new state to set.
+ *
+ * Set @rq's state to @state.  The caller is responsible for ensuring that
+ * there are no other updaters.  A request can transition into IN_FLIGHT
+ * only from IDLE and doing so increments the generation number.
+ */
+static inline void blk_mq_rq_update_state(struct request *rq,
+					  enum mq_rq_state state)
+{
+	u64 old_val = READ_ONCE(rq->gstate);
+	u64 new_val = (old_val & ~MQ_RQ_STATE_MASK) | state;
+
+	if (state == MQ_RQ_IN_FLIGHT) {
+		WARN_ON_ONCE((old_val & MQ_RQ_STATE_MASK) != MQ_RQ_IDLE);
+		new_val += MQ_RQ_GEN_INC;
+	}
+
+	/* avoid exposing interim values */
+	WRITE_ONCE(rq->gstate, new_val);
+}
+
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {

block/blk-sysfs.c

@@ -853,6 +853,10 @@ struct kobj_type blk_queue_ktype = {
 	.release	= blk_release_queue,
 };
 
+/**
+ * blk_register_queue - register a block layer queue with sysfs
+ * @disk: Disk of which the request queue should be registered with sysfs.
+ */
 int blk_register_queue(struct gendisk *disk)
 {
 	int ret;
@@ -909,11 +913,12 @@ int blk_register_queue(struct gendisk *disk)
 	if (q->request_fn || (q->mq_ops && q->elevator)) {
 		ret = elv_register_queue(q);
 		if (ret) {
+			mutex_unlock(&q->sysfs_lock);
 			kobject_uevent(&q->kobj, KOBJ_REMOVE);
 			kobject_del(&q->kobj);
 			blk_trace_remove_sysfs(dev);
 			kobject_put(&dev->kobj);
-			goto unlock;
+			return ret;
 		}
 	}
 	ret = 0;
@@ -921,7 +926,15 @@ int blk_register_queue(struct gendisk *disk)
 	mutex_unlock(&q->sysfs_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(blk_register_queue);
 
+/**
+ * blk_unregister_queue - counterpart of blk_register_queue()
+ * @disk: Disk of which the request queue should be unregistered from sysfs.
+ *
+ * Note: the caller is responsible for guaranteeing that this function is called
+ * after blk_register_queue() has finished.
+ */
 void blk_unregister_queue(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
@@ -929,21 +942,39 @@ void blk_unregister_queue(struct gendisk *disk)
 	if (WARN_ON(!q))
 		return;
 
-	mutex_lock(&q->sysfs_lock);
-	queue_flag_clear_unlocked(QUEUE_FLAG_REGISTERED, q);
-	mutex_unlock(&q->sysfs_lock);
+	/* Return early if disk->queue was never registered. */
+	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+		return;
 
-	wbt_exit(q);
+	/*
+	 * Since sysfs_remove_dir() prevents adding new directory entries
+	 * before removal of existing entries starts, protect against
+	 * concurrent elv_iosched_store() calls.
+	 */
+	mutex_lock(&q->sysfs_lock);
 
+	spin_lock_irq(q->queue_lock);
+	queue_flag_clear(QUEUE_FLAG_REGISTERED, q);
+	spin_unlock_irq(q->queue_lock);
 
+	/*
+	 * Remove the sysfs attributes before unregistering the queue data
+	 * structures that can be modified through sysfs.
+	 */
 	if (q->mq_ops)
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
-
-	if (q->request_fn || (q->mq_ops && q->elevator))
-		elv_unregister_queue(q);
+	mutex_unlock(&q->sysfs_lock);
 
 	kobject_uevent(&q->kobj, KOBJ_REMOVE);
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
+
+	wbt_exit(q);
+
+	mutex_lock(&q->sysfs_lock);
+	if (q->request_fn || (q->mq_ops && q->elevator))
+		elv_unregister_queue(q);
+	mutex_unlock(&q->sysfs_lock);
+
 	kobject_put(&disk_to_dev(disk)->kobj);
 }

block/blk-throttle.c

@@ -216,9 +216,9 @@ struct throtl_data
 
 	unsigned int scale;
 
-	struct latency_bucket tmp_buckets[LATENCY_BUCKET_SIZE];
-	struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
-	struct latency_bucket __percpu *latency_buckets;
+	struct latency_bucket tmp_buckets[2][LATENCY_BUCKET_SIZE];
+	struct avg_latency_bucket avg_buckets[2][LATENCY_BUCKET_SIZE];
+	struct latency_bucket __percpu *latency_buckets[2];
 	unsigned long last_calculate_time;
 	unsigned long filtered_latency;
 
@@ -1510,11 +1510,21 @@ static struct cftype throtl_legacy_files[] = {
 		.private = (unsigned long)&blkcg_policy_throtl,
 		.seq_show = blkg_print_stat_bytes,
 	},
+	{
+		.name = "throttle.io_service_bytes_recursive",
+		.private = (unsigned long)&blkcg_policy_throtl,
+		.seq_show = blkg_print_stat_bytes_recursive,
+	},
 	{
 		.name = "throttle.io_serviced",
 		.private = (unsigned long)&blkcg_policy_throtl,
 		.seq_show = blkg_print_stat_ios,
 	},
+	{
+		.name = "throttle.io_serviced_recursive",
+		.private = (unsigned long)&blkcg_policy_throtl,
+		.seq_show = blkg_print_stat_ios_recursive,
+	},
 	{ }	/* terminate */
 };
 
@@ -2040,10 +2050,10 @@ static void blk_throtl_update_idletime(struct throtl_grp *tg)
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 static void throtl_update_latency_buckets(struct throtl_data *td)
 {
-	struct avg_latency_bucket avg_latency[LATENCY_BUCKET_SIZE];
-	int i, cpu;
-	unsigned long last_latency = 0;
-	unsigned long latency;
+	struct avg_latency_bucket avg_latency[2][LATENCY_BUCKET_SIZE];
+	int i, cpu, rw;
+	unsigned long last_latency[2] = { 0 };
+	unsigned long latency[2];
 
 	if (!blk_queue_nonrot(td->queue))
 		return;
@@ -2052,56 +2062,67 @@ static void throtl_update_latency_buckets(struct throtl_data *td)
 	td->last_calculate_time = jiffies;
 
 	memset(avg_latency, 0, sizeof(avg_latency));
-	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
-		struct latency_bucket *tmp = &td->tmp_buckets[i];
-
-		for_each_possible_cpu(cpu) {
-			struct latency_bucket *bucket;
-
-			/* this isn't race free, but ok in practice */
-			bucket = per_cpu_ptr(td->latency_buckets, cpu);
-			tmp->total_latency += bucket[i].total_latency;
-			tmp->samples += bucket[i].samples;
-			bucket[i].total_latency = 0;
-			bucket[i].samples = 0;
-		}
+	for (rw = READ; rw <= WRITE; rw++) {
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+			struct latency_bucket *tmp = &td->tmp_buckets[rw][i];
+
+			for_each_possible_cpu(cpu) {
+				struct latency_bucket *bucket;
+
+				/* this isn't race free, but ok in practice */
+				bucket = per_cpu_ptr(td->latency_buckets[rw],
+					cpu);
+				tmp->total_latency += bucket[i].total_latency;
+				tmp->samples += bucket[i].samples;
+				bucket[i].total_latency = 0;
+				bucket[i].samples = 0;
+			}
 
-		if (tmp->samples >= 32) {
-			int samples = tmp->samples;
+			if (tmp->samples >= 32) {
+				int samples = tmp->samples;
 
-			latency = tmp->total_latency;
+				latency[rw] = tmp->total_latency;
 
-			tmp->total_latency = 0;
-			tmp->samples = 0;
-			latency /= samples;
-			if (latency == 0)
-				continue;
-			avg_latency[i].latency = latency;
+				tmp->total_latency = 0;
+				tmp->samples = 0;
+				latency[rw] /= samples;
+				if (latency[rw] == 0)
+					continue;
+				avg_latency[rw][i].latency = latency[rw];
+			}
 		}
 	}
 
-	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
-		if (!avg_latency[i].latency) {
-			if (td->avg_buckets[i].latency < last_latency)
-				td->avg_buckets[i].latency = last_latency;
-			continue;
-		}
+	for (rw = READ; rw <= WRITE; rw++) {
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+			if (!avg_latency[rw][i].latency) {
+				if (td->avg_buckets[rw][i].latency < last_latency[rw])
+					td->avg_buckets[rw][i].latency =
+						last_latency[rw];
+				continue;
+			}
 
-		if (!td->avg_buckets[i].valid)
-			latency = avg_latency[i].latency;
-		else
-			latency = (td->avg_buckets[i].latency * 7 +
-				avg_latency[i].latency) >> 3;
+			if (!td->avg_buckets[rw][i].valid)
+				latency[rw] = avg_latency[rw][i].latency;
+			else
+				latency[rw] = (td->avg_buckets[rw][i].latency * 7 +
+					avg_latency[rw][i].latency) >> 3;
 
-		td->avg_buckets[i].latency = max(latency, last_latency);
-		td->avg_buckets[i].valid = true;
-		last_latency = td->avg_buckets[i].latency;
+			td->avg_buckets[rw][i].latency = max(latency[rw],
+				last_latency[rw]);
+			td->avg_buckets[rw][i].valid = true;
+			last_latency[rw] = td->avg_buckets[rw][i].latency;
+		}
 	}
 
 	for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
 		throtl_log(&td->service_queue,
-			"Latency bucket %d: latency=%ld, valid=%d", i,
-			td->avg_buckets[i].latency, td->avg_buckets[i].valid);
+			"Latency bucket %d: read latency=%ld, read valid=%d, "
+			"write latency=%ld, write valid=%d", i,
+			td->avg_buckets[READ][i].latency,
+			td->avg_buckets[READ][i].valid,
+			td->avg_buckets[WRITE][i].latency,
+			td->avg_buckets[WRITE][i].valid);
 }
 #else
 static inline void throtl_update_latency_buckets(struct throtl_data *td)
@@ -2242,16 +2263,17 @@ static void throtl_track_latency(struct throtl_data *td, sector_t size,
 	struct latency_bucket *latency;
 	int index;
 
-	if (!td || td->limit_index != LIMIT_LOW || op != REQ_OP_READ ||
+	if (!td || td->limit_index != LIMIT_LOW ||
+	    !(op == REQ_OP_READ || op == REQ_OP_WRITE) ||
 	    !blk_queue_nonrot(td->queue))
 		return;
 
 	index = request_bucket_index(size);
 
-	latency = get_cpu_ptr(td->latency_buckets);
+	latency = get_cpu_ptr(td->latency_buckets[op]);
 	latency[index].total_latency += time;
 	latency[index].samples++;
-	put_cpu_ptr(td->latency_buckets);
+	put_cpu_ptr(td->latency_buckets[op]);
 }
 
 void blk_throtl_stat_add(struct request *rq, u64 time_ns)
@@ -2270,6 +2292,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 	unsigned long finish_time;
 	unsigned long start_time;
 	unsigned long lat;
+	int rw = bio_data_dir(bio);
 
 	tg = bio->bi_cg_private;
 	if (!tg)
@@ -2298,7 +2321,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 
 		bucket = request_bucket_index(
 			blk_stat_size(&bio->bi_issue_stat));
-		threshold = tg->td->avg_buckets[bucket].latency +
+		threshold = tg->td->avg_buckets[rw][bucket].latency +
 			tg->latency_target;
 		if (lat > threshold)
 			tg->bad_bio_cnt++;
@@ -2391,9 +2414,16 @@ int blk_throtl_init(struct request_queue *q)
 	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
 	if (!td)
 		return -ENOMEM;
-	td->latency_buckets = __alloc_percpu(sizeof(struct latency_bucket) *
+	td->latency_buckets[READ] = __alloc_percpu(sizeof(struct latency_bucket) *
 		LATENCY_BUCKET_SIZE, __alignof__(u64));
-	if (!td->latency_buckets) {
+	if (!td->latency_buckets[READ]) {
+		kfree(td);
+		return -ENOMEM;
+	}
+	td->latency_buckets[WRITE] = __alloc_percpu(sizeof(struct latency_bucket) *
+		LATENCY_BUCKET_SIZE, __alignof__(u64));
+	if (!td->latency_buckets[WRITE]) {
+		free_percpu(td->latency_buckets[READ]);
 		kfree(td);
 		return -ENOMEM;
 	}
@@ -2412,7 +2442,8 @@ int blk_throtl_init(struct request_queue *q)
 	/* activate policy */
 	ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
 	if (ret) {
-		free_percpu(td->latency_buckets);
+		free_percpu(td->latency_buckets[READ]);
+		free_percpu(td->latency_buckets[WRITE]);
 		kfree(td);
 	}
 	return ret;
@@ -2423,7 +2454,8 @@ void blk_throtl_exit(struct request_queue *q)
 	BUG_ON(!q->td);
 	throtl_shutdown_wq(q);
 	blkcg_deactivate_policy(q, &blkcg_policy_throtl);
-	free_percpu(q->td->latency_buckets);
+	free_percpu(q->td->latency_buckets[READ]);
+	free_percpu(q->td->latency_buckets[WRITE]);
 	kfree(q->td);
 }
 
@@ -2441,15 +2473,17 @@ void blk_throtl_register_queue(struct request_queue *q)
 	} else {
 		td->throtl_slice = DFL_THROTL_SLICE_HD;
 		td->filtered_latency = LATENCY_FILTERED_HD;
-		for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
-			td->avg_buckets[i].latency = DFL_HD_BASELINE_LATENCY;
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+			td->avg_buckets[READ][i].latency = DFL_HD_BASELINE_LATENCY;
+			td->avg_buckets[WRITE][i].latency = DFL_HD_BASELINE_LATENCY;
+		}
 	}
 #ifndef CONFIG_BLK_DEV_THROTTLING_LOW
 	/* if no low limit, use previous default */
 	td->throtl_slice = DFL_THROTL_SLICE_HD;
 #endif
 
-	td->track_bio_latency = !q->mq_ops && !q->request_fn;
+	td->track_bio_latency = !queue_is_rq_based(q);
 	if (!td->track_bio_latency)
 		blk_stat_enable_accounting(q);
 }

block/blk-timeout.c

@@ -112,7 +112,9 @@ static void blk_rq_timed_out(struct request *req)
 static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
 			  unsigned int *next_set)
 {
-	if (time_after_eq(jiffies, rq->deadline)) {
+	const unsigned long deadline = blk_rq_deadline(rq);
+
+	if (time_after_eq(jiffies, deadline)) {
 		list_del_init(&rq->timeout_list);
 
 		/*
@@ -120,8 +122,8 @@ static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout
 		 */
 		if (!blk_mark_rq_complete(rq))
 			blk_rq_timed_out(rq);
-	} else if (!*next_set || time_after(*next_timeout, rq->deadline)) {
-		*next_timeout = rq->deadline;
+	} else if (!*next_set || time_after(*next_timeout, deadline)) {
+		*next_timeout = deadline;
 		*next_set = 1;
 	}
 }
@@ -156,12 +158,17 @@ void blk_timeout_work(struct work_struct *work)
  */
 void blk_abort_request(struct request *req)
 {
-	if (blk_mark_rq_complete(req))
-		return;
-
 	if (req->q->mq_ops) {
-		blk_mq_rq_timed_out(req, false);
+		/*
+		 * All we need to ensure is that timeout scan takes place
+		 * immediately and that scan sees the new timeout value.
+		 * No need for fancy synchronizations.
+		 */
+		blk_rq_set_deadline(req, jiffies);
+		mod_timer(&req->q->timeout, 0);
 	} else {
+		if (blk_mark_rq_complete(req))
+			return;
 		blk_delete_timer(req);
 		blk_rq_timed_out(req);
 	}
@@ -208,7 +215,8 @@ void blk_add_timer(struct request *req)
 	if (!req->timeout)
 		req->timeout = q->rq_timeout;
 
-	WRITE_ONCE(req->deadline, jiffies + req->timeout);
+	blk_rq_set_deadline(req, jiffies + req->timeout);
+	req->rq_flags &= ~RQF_MQ_TIMEOUT_EXPIRED;
 
 	/*
 	 * Only the non-mq case needs to add the request to a protected list.
@@ -222,7 +230,7 @@ void blk_add_timer(struct request *req)
 	 * than an existing one, modify the timer. Round up to next nearest
 	 * second.
 	 */
-	expiry = blk_rq_timeout(round_jiffies_up(req->deadline));
+	expiry = blk_rq_timeout(round_jiffies_up(blk_rq_deadline(req)));
 
 	if (!timer_pending(&q->timeout) ||
 	    time_before(expiry, q->timeout.expires)) {

block/blk-zoned.c

@@ -21,6 +21,48 @@ static inline sector_t blk_zone_start(struct request_queue *q,
 	return sector & ~zone_mask;
 }
 
+/*
+ * Return true if a request is a write requests that needs zone write locking.
+ */
+bool blk_req_needs_zone_write_lock(struct request *rq)
+{
+	if (!rq->q->seq_zones_wlock)
+		return false;
+
+	if (blk_rq_is_passthrough(rq))
+		return false;
+
+	switch (req_op(rq)) {
+	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_WRITE_SAME:
+	case REQ_OP_WRITE:
+		return blk_rq_zone_is_seq(rq);
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock);
+
+void __blk_req_zone_write_lock(struct request *rq)
+{
+	if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
+					  rq->q->seq_zones_wlock)))
+		return;
+
+	WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
+	rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;
+}
+EXPORT_SYMBOL_GPL(__blk_req_zone_write_lock);
+
+void __blk_req_zone_write_unlock(struct request *rq)
+{
+	rq->rq_flags &= ~RQF_ZONE_WRITE_LOCKED;
+	if (rq->q->seq_zones_wlock)
+		WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq),
+						 rq->q->seq_zones_wlock));
+}
+EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
+
 /*
  * Check that a zone report belongs to the partition.
  * If yes, fix its start sector and write pointer, copy it in the

block/blk.h

@@ -119,34 +119,24 @@ void blk_account_io_start(struct request *req, bool new_io);
 void blk_account_io_completion(struct request *req, unsigned int bytes);
 void blk_account_io_done(struct request *req);
 
-/*
- * Internal atomic flags for request handling
- */
-enum rq_atomic_flags {
-	/*
-	 * Keep these two bits first - not because we depend on the
-	 * value of them, but we do depend on them being in the same
-	 * byte of storage to ensure ordering on writes. Keeping them
-	 * first will achieve that nicely.
-	 */
-	REQ_ATOM_COMPLETE = 0,
-	REQ_ATOM_STARTED,
-
-	REQ_ATOM_POLL_SLEPT,
-};
-
 /*
  * EH timer and IO completion will both attempt to 'grab' the request, make
- * sure that only one of them succeeds
+ * sure that only one of them succeeds. Steal the bottom bit of the
+ * __deadline field for this.
  */
 static inline int blk_mark_rq_complete(struct request *rq)
 {
-	return test_and_set_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
+	return test_and_set_bit(0, &rq->__deadline);
 }
 
 static inline void blk_clear_rq_complete(struct request *rq)
 {
-	clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
+	clear_bit(0, &rq->__deadline);
+}
+
+static inline bool blk_rq_is_complete(struct request *rq)
+{
+	return test_bit(0, &rq->__deadline);
 }
 
 /*
@@ -172,6 +162,9 @@ static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq
 		e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
 }
 
+int elv_register_queue(struct request_queue *q);
+void elv_unregister_queue(struct request_queue *q);
+
 struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
 
 #ifdef CONFIG_FAIL_IO_TIMEOUT
@@ -245,6 +238,21 @@ static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 		q->last_merge = NULL;
 }
 
+/*
+ * Steal a bit from this field for legacy IO path atomic IO marking. Note that
+ * setting the deadline clears the bottom bit, potentially clearing the
+ * completed bit. The user has to be OK with this (current ones are fine).
+ */
+static inline void blk_rq_set_deadline(struct request *rq, unsigned long time)
+{
+	rq->__deadline = time & ~0x1UL;
+}
+
+static inline unsigned long blk_rq_deadline(struct request *rq)
+{
+	return rq->__deadline & ~0x1UL;
+}
+
 /*
  * Internal io_context interface
  */

block/bounce.c

@@ -113,45 +113,50 @@ int init_emergency_isa_pool(void)
 static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 {
 	unsigned char *vfrom;
-	struct bio_vec tovec, *fromvec = from->bi_io_vec;
+	struct bio_vec tovec, fromvec;
 	struct bvec_iter iter;
+	/*
+	 * The bio of @from is created by bounce, so we can iterate
+	 * its bvec from start to end, but the @from->bi_iter can't be
+	 * trusted because it might be changed by splitting.
+	 */
+	struct bvec_iter from_iter = BVEC_ITER_ALL_INIT;
 
 	bio_for_each_segment(tovec, to, iter) {
-		if (tovec.bv_page != fromvec->bv_page) {
+		fromvec = bio_iter_iovec(from, from_iter);
+		if (tovec.bv_page != fromvec.bv_page) {
 			/*
 			 * fromvec->bv_offset and fromvec->bv_len might have
 			 * been modified by the block layer, so use the original
 			 * copy, bounce_copy_vec already uses tovec->bv_len
 			 */
-			vfrom = page_address(fromvec->bv_page) +
+			vfrom = page_address(fromvec.bv_page) +
 				tovec.bv_offset;
 
 			bounce_copy_vec(&tovec, vfrom);
 			flush_dcache_page(tovec.bv_page);
 		}
-
-		fromvec++;
+		bio_advance_iter(from, &from_iter, tovec.bv_len);
 	}
 }
 
 static void bounce_end_io(struct bio *bio, mempool_t *pool)
 {
 	struct bio *bio_orig = bio->bi_private;
-	struct bio_vec *bvec, *org_vec;
+	struct bio_vec *bvec, orig_vec;
 	int i;
-	int start = bio_orig->bi_iter.bi_idx;
+	struct bvec_iter orig_iter = bio_orig->bi_iter;
 
 	/*
 	 * free up bounce indirect pages used
 	 */
 	bio_for_each_segment_all(bvec, bio, i) {
-		org_vec = bio_orig->bi_io_vec + i + start;
-
-		if (bvec->bv_page == org_vec->bv_page)
-			continue;
-
-		dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
-		mempool_free(bvec->bv_page, pool);
+		orig_vec = bio_iter_iovec(bio_orig, orig_iter);
+		if (bvec->bv_page != orig_vec.bv_page) {
+			dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
+			mempool_free(bvec->bv_page, pool);
+		}
+		bio_advance_iter(bio_orig, &orig_iter, orig_vec.bv_len);
 	}
 
 	bio_orig->bi_status = bio->bi_status;

block/bsg-lib.c

@@ -30,7 +30,7 @@
 
 /**
  * bsg_teardown_job - routine to teardown a bsg job
- * @job: bsg_job that is to be torn down
+ * @kref: kref inside bsg_job that is to be torn down
  */
 static void bsg_teardown_job(struct kref *kref)
 {
@@ -251,6 +251,7 @@ static void bsg_exit_rq(struct request_queue *q, struct request *req)
  * @name: device to give bsg device
  * @job_fn: bsg job handler
  * @dd_job_size: size of LLD data needed for each job
+ * @release: @dev release function
  */
 struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 		bsg_job_fn *job_fn, int dd_job_size,

block/bsg.c

@@ -32,6 +32,9 @@
 #define BSG_DESCRIPTION	"Block layer SCSI generic (bsg) driver"
 #define BSG_VERSION	"0.4"
 
+#define bsg_dbg(bd, fmt, ...) \
+	pr_debug("%s: " fmt, (bd)->name, ##__VA_ARGS__)
+
 struct bsg_device {
 	struct request_queue *queue;
 	spinlock_t lock;
@@ -55,14 +58,6 @@ enum {
 #define BSG_DEFAULT_CMDS	64
 #define BSG_MAX_DEVS		32768
 
-#undef BSG_DEBUG
-
-#ifdef BSG_DEBUG
-#define dprintk(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ##args)
-#else
-#define dprintk(fmt, args...)
-#endif
-
 static DEFINE_MUTEX(bsg_mutex);
 static DEFINE_IDR(bsg_minor_idr);
 
@@ -123,7 +118,7 @@ static struct bsg_command *bsg_alloc_command(struct bsg_device *bd)
 
 	bc->bd = bd;
 	INIT_LIST_HEAD(&bc->list);
-	dprintk("%s: returning free cmd %p\n", bd->name, bc);
+	bsg_dbg(bd, "returning free cmd %p\n", bc);
 	return bc;
 out:
 	spin_unlock_irq(&bd->lock);
@@ -222,7 +217,8 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t mode)
 	if (!bcd->class_dev)
 		return ERR_PTR(-ENXIO);
 
-	dprintk("map hdr %llx/%u %llx/%u\n", (unsigned long long) hdr->dout_xferp,
+	bsg_dbg(bd, "map hdr %llx/%u %llx/%u\n",
+		(unsigned long long) hdr->dout_xferp,
 		hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp,
 		hdr->din_xfer_len);
 
@@ -299,8 +295,8 @@ static void bsg_rq_end_io(struct request *rq, blk_status_t status)
 	struct bsg_device *bd = bc->bd;
 	unsigned long flags;
 
-	dprintk("%s: finished rq %p bc %p, bio %p\n",
-		bd->name, rq, bc, bc->bio);
+	bsg_dbg(bd, "finished rq %p bc %p, bio %p\n",
+		rq, bc, bc->bio);
 
 	bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration);
 
@@ -333,7 +329,7 @@ static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 	list_add_tail(&bc->list, &bd->busy_list);
 	spin_unlock_irq(&bd->lock);
 
-	dprintk("%s: queueing rq %p, bc %p\n", bd->name, rq, bc);
+	bsg_dbg(bd, "queueing rq %p, bc %p\n", rq, bc);
 
 	rq->end_io_data = bc;
 	blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io);
@@ -379,7 +375,7 @@ static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd)
 		}
 	} while (1);
 
-	dprintk("%s: returning done %p\n", bd->name, bc);
+	bsg_dbg(bd, "returning done %p\n", bc);
 
 	return bc;
 }
@@ -390,7 +386,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	struct scsi_request *req = scsi_req(rq);
 	int ret = 0;
 
-	dprintk("rq %p bio %p 0x%x\n", rq, bio, req->result);
+	pr_debug("rq %p bio %p 0x%x\n", rq, bio, req->result);
 	/*
 	 * fill in all the output members
 	 */
@@ -469,7 +465,7 @@ static int bsg_complete_all_commands(struct bsg_device *bd)
 	struct bsg_command *bc;
 	int ret, tret;
 
-	dprintk("%s: entered\n", bd->name);
+	bsg_dbg(bd, "entered\n");
 
 	/*
 	 * wait for all commands to complete
@@ -572,7 +568,7 @@ bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	int ret;
 	ssize_t bytes_read;
 
-	dprintk("%s: read %zd bytes\n", bd->name, count);
+	bsg_dbg(bd, "read %zd bytes\n", count);
 
 	bsg_set_block(bd, file);
 
@@ -646,7 +642,7 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	ssize_t bytes_written;
 	int ret;
 
-	dprintk("%s: write %zd bytes\n", bd->name, count);
+	bsg_dbg(bd, "write %zd bytes\n", count);
 
 	if (unlikely(uaccess_kernel()))
 		return -EINVAL;
@@ -664,7 +660,7 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	if (!bytes_written || err_block_err(ret))
 		bytes_written = ret;
 
-	dprintk("%s: returning %zd\n", bd->name, bytes_written);
+	bsg_dbg(bd, "returning %zd\n", bytes_written);
 	return bytes_written;
 }
 
@@ -717,7 +713,7 @@ static int bsg_put_device(struct bsg_device *bd)
 	hlist_del(&bd->dev_list);
 	mutex_unlock(&bsg_mutex);
 
-	dprintk("%s: tearing down\n", bd->name);
+	bsg_dbg(bd, "tearing down\n");
 
 	/*
 	 * close can always block
@@ -744,9 +740,7 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 					 struct file *file)
 {
 	struct bsg_device *bd;
-#ifdef BSG_DEBUG
 	unsigned char buf[32];
-#endif
 
 	if (!blk_queue_scsi_passthrough(rq)) {
 		WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
@@ -771,7 +765,7 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 	hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
 
 	strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1);
-	dprintk("bound to <%s>, max queue %d\n",
+	bsg_dbg(bd, "bound to <%s>, max queue %d\n",
 		format_dev_t(buf, inode->i_rdev), bd->max_queue);
 
 	mutex_unlock(&bsg_mutex);

block/deadline-iosched.c

@@ -50,8 +50,6 @@ struct deadline_data {
 	int front_merges;
 };
 
-static void deadline_move_request(struct deadline_data *, struct request *);
-
 static inline struct rb_root *
 deadline_rb_root(struct deadline_data *dd, struct request *rq)
 {
@@ -100,6 +98,12 @@ deadline_add_request(struct request_queue *q, struct request *rq)
 	struct deadline_data *dd = q->elevator->elevator_data;
 	const int data_dir = rq_data_dir(rq);
 
+	/*
+	 * This may be a requeue of a write request that has locked its
+	 * target zone. If it is the case, this releases the zone lock.
+	 */
+	blk_req_zone_write_unlock(rq);
+
 	deadline_add_rq_rb(dd, rq);
 
 	/*
@@ -190,6 +194,12 @@ deadline_move_to_dispatch(struct deadline_data *dd, struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
+	/*
+	 * For a zoned block device, write requests must write lock their
+	 * target zone.
+	 */
+	blk_req_zone_write_lock(rq);
+
 	deadline_remove_request(q, rq);
 	elv_dispatch_add_tail(q, rq);
 }
@@ -230,6 +240,69 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 	return 0;
 }
 
+/*
+ * For the specified data direction, return the next request to dispatch using
+ * arrival ordered lists.
+ */
+static struct request *
+deadline_fifo_request(struct deadline_data *dd, int data_dir)
+{
+	struct request *rq;
+
+	if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE))
+		return NULL;
+
+	if (list_empty(&dd->fifo_list[data_dir]))
+		return NULL;
+
+	rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+	if (data_dir == READ || !blk_queue_is_zoned(rq->q))
+		return rq;
+
+	/*
+	 * Look for a write request that can be dispatched, that is one with
+	 * an unlocked target zone.
+	 */
+	list_for_each_entry(rq, &dd->fifo_list[WRITE], queuelist) {
+		if (blk_req_can_dispatch_to_zone(rq))
+			return rq;
+	}
+
+	return NULL;
+}
+
+/*
+ * For the specified data direction, return the next request to dispatch using
+ * sector position sorted lists.
+ */
+static struct request *
+deadline_next_request(struct deadline_data *dd, int data_dir)
+{
+	struct request *rq;
+
+	if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE))
+		return NULL;
+
+	rq = dd->next_rq[data_dir];
+	if (!rq)
+		return NULL;
+
+	if (data_dir == READ || !blk_queue_is_zoned(rq->q))
+		return rq;
+
+	/*
+	 * Look for a write request that can be dispatched, that is one with
+	 * an unlocked target zone.
+	 */
+	while (rq) {
+		if (blk_req_can_dispatch_to_zone(rq))
+			return rq;
+		rq = deadline_latter_request(rq);
+	}
+
+	return NULL;
+}
+
 /*
  * deadline_dispatch_requests selects the best request according to
  * read/write expire, fifo_batch, etc
@@ -239,16 +312,15 @@ static int deadline_dispatch_requests(struct request_queue *q, int force)
 	struct deadline_data *dd = q->elevator->elevator_data;
 	const int reads = !list_empty(&dd->fifo_list[READ]);
 	const int writes = !list_empty(&dd->fifo_list[WRITE]);
-	struct request *rq;
+	struct request *rq, *next_rq;
 	int data_dir;
 
 	/*
 	 * batches are currently reads XOR writes
 	 */
-	if (dd->next_rq[WRITE])
-		rq = dd->next_rq[WRITE];
-	else
-		rq = dd->next_rq[READ];
+	rq = deadline_next_request(dd, WRITE);
+	if (!rq)
+		rq = deadline_next_request(dd, READ);
 
 	if (rq && dd->batching < dd->fifo_batch)
 		/* we have a next request are still entitled to batch */
@@ -262,7 +334,8 @@ static int deadline_dispatch_requests(struct request_queue *q, int force)
 	if (reads) {
 		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));
 
-		if (writes && (dd->starved++ >= dd->writes_starved))
+		if (deadline_fifo_request(dd, WRITE) &&
+		    (dd->starved++ >= dd->writes_starved))
 			goto dispatch_writes;
 
 		data_dir = READ;
@@ -291,21 +364,29 @@ static int deadline_dispatch_requests(struct request_queue *q, int force)
 	/*
 	 * we are not running a batch, find best request for selected data_dir
 	 */
-	if (deadline_check_fifo(dd, data_dir) || !dd->next_rq[data_dir]) {
+	next_rq = deadline_next_request(dd, data_dir);
+	if (deadline_check_fifo(dd, data_dir) || !next_rq) {
 		/*
 		 * A deadline has expired, the last request was in the other
 		 * direction, or we have run out of higher-sectored requests.
 		 * Start again from the request with the earliest expiry time.
 		 */
-		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+		rq = deadline_fifo_request(dd, data_dir);
 	} else {
 		/*
 		 * The last req was the same dir and we have a next request in
 		 * sort order. No expired requests so continue on from here.
 		 */
-		rq = dd->next_rq[data_dir];
+		rq = next_rq;
 	}
 
+	/*
+	 * For a zoned block device, if we only have writes queued and none of
+	 * them can be dispatched, rq will be NULL.
+	 */
+	if (!rq)
+		return 0;
+
 	dd->batching = 0;
 
 dispatch_request:
@@ -318,6 +399,16 @@ static int deadline_dispatch_requests(struct request_queue *q, int force)
 	return 1;
 }
 
+/*
+ * For zoned block devices, write unlock the target zone of completed
+ * write requests.
+ */
+static void
+deadline_completed_request(struct request_queue *q, struct request *rq)
+{
+	blk_req_zone_write_unlock(rq);
+}
+
 static void deadline_exit_queue(struct elevator_queue *e)
 {
 	struct deadline_data *dd = e->elevator_data;
@@ -439,6 +530,7 @@ static struct elevator_type iosched_deadline = {
 		.elevator_merged_fn =		deadline_merged_request,
 		.elevator_merge_req_fn =	deadline_merged_requests,
 		.elevator_dispatch_fn =		deadline_dispatch_requests,
+		.elevator_completed_req_fn =	deadline_completed_request,
 		.elevator_add_req_fn =		deadline_add_request,
 		.elevator_former_req_fn =	elv_rb_former_request,
 		.elevator_latter_req_fn =	elv_rb_latter_request,

block/elevator.c

@@ -869,6 +869,8 @@ int elv_register_queue(struct request_queue *q)
 	struct elevator_queue *e = q->elevator;
 	int error;
 
+	lockdep_assert_held(&q->sysfs_lock);
+
 	error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
 	if (!error) {
 		struct elv_fs_entry *attr = e->type->elevator_attrs;
@@ -886,10 +888,11 @@ int elv_register_queue(struct request_queue *q)
 	}
 	return error;
 }
-EXPORT_SYMBOL(elv_register_queue);
 
 void elv_unregister_queue(struct request_queue *q)
 {
+	lockdep_assert_held(&q->sysfs_lock);
+
 	if (q) {
 		struct elevator_queue *e = q->elevator;
 
@@ -900,7 +903,6 @@ void elv_unregister_queue(struct request_queue *q)
 		wbt_enable_default(q);
 	}
 }
-EXPORT_SYMBOL(elv_unregister_queue);
 
 int elv_register(struct elevator_type *e)
 {
@@ -967,7 +969,10 @@ static int elevator_switch_mq(struct request_queue *q,
 {
 	int ret;
 
+	lockdep_assert_held(&q->sysfs_lock);
+
 	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
 
 	if (q->elevator) {
 		if (q->elevator->registered)
@@ -994,6 +999,7 @@ static int elevator_switch_mq(struct request_queue *q,
 		blk_add_trace_msg(q, "elv switch: none");
 
 out:
+	blk_mq_unquiesce_queue(q);
 	blk_mq_unfreeze_queue(q);
 	return ret;
 }
@@ -1010,6 +1016,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	bool old_registered = false;
 	int err;
 
+	lockdep_assert_held(&q->sysfs_lock);
+
 	if (q->mq_ops)
 		return elevator_switch_mq(q, new_e);
 

block/genhd.c

@@ -629,16 +629,18 @@ static void register_disk(struct device *parent, struct gendisk *disk)
 }
 
 /**
- * device_add_disk - add partitioning information to kernel list
+ * __device_add_disk - add disk information to kernel list
  * @parent: parent device for the disk
  * @disk: per-device partitioning information
+ * @register_queue: register the queue if set to true
  *
  * This function registers the partitioning information in @disk
  * with the kernel.
  *
  * FIXME: error handling
  */
-void device_add_disk(struct device *parent, struct gendisk *disk)
+static void __device_add_disk(struct device *parent, struct gendisk *disk,
+			      bool register_queue)
 {
 	dev_t devt;
 	int retval;
@@ -682,7 +684,8 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 				    exact_match, exact_lock, disk);
 	}
 	register_disk(parent, disk);
-	blk_register_queue(disk);
+	if (register_queue)
+		blk_register_queue(disk);
 
 	/*
 	 * Take an extra ref on queue which will be put on disk_release()
@@ -693,8 +696,19 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 	disk_add_events(disk);
 	blk_integrity_add(disk);
 }
+
+void device_add_disk(struct device *parent, struct gendisk *disk)
+{
+	__device_add_disk(parent, disk, true);
+}
 EXPORT_SYMBOL(device_add_disk);
 
+void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk)
+{
+	__device_add_disk(parent, disk, false);
+}
+EXPORT_SYMBOL(device_add_disk_no_queue_reg);
+
 void del_gendisk(struct gendisk *disk)
 {
 	struct disk_part_iter piter;
@@ -725,7 +739,8 @@ void del_gendisk(struct gendisk *disk)
 		 * Unregister bdi before releasing device numbers (as they can
 		 * get reused and we'd get clashes in sysfs).
 		 */
-		bdi_unregister(disk->queue->backing_dev_info);
+		if (!(disk->flags & GENHD_FL_HIDDEN))
+			bdi_unregister(disk->queue->backing_dev_info);
 		blk_unregister_queue(disk);
 	} else {
 		WARN_ON(1);

block/mq-deadline.c

@@ -59,6 +59,7 @@ struct deadline_data {
 	int front_merges;
 
 	spinlock_t lock;
+	spinlock_t zone_lock;
 	struct list_head dispatch;
 };
 
@@ -191,14 +192,84 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 	return 0;
 }
 
+/*
+ * For the specified data direction, return the next request to
+ * dispatch using arrival ordered lists.
+ */
+static struct request *
+deadline_fifo_request(struct deadline_data *dd, int data_dir)
+{
+	struct request *rq;
+	unsigned long flags;
+
+	if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE))
+		return NULL;
+
+	if (list_empty(&dd->fifo_list[data_dir]))
+		return NULL;
+
+	rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+	if (data_dir == READ || !blk_queue_is_zoned(rq->q))
+		return rq;
+
+	/*
+	 * Look for a write request that can be dispatched, that is one with
+	 * an unlocked target zone.
+	 */
+	spin_lock_irqsave(&dd->zone_lock, flags);
+	list_for_each_entry(rq, &dd->fifo_list[WRITE], queuelist) {
+		if (blk_req_can_dispatch_to_zone(rq))
+			goto out;
+	}
+	rq = NULL;
+out:
+	spin_unlock_irqrestore(&dd->zone_lock, flags);
+
+	return rq;
+}
+
+/*
+ * For the specified data direction, return the next request to
+ * dispatch using sector position sorted lists.
+ */
+static struct request *
+deadline_next_request(struct deadline_data *dd, int data_dir)
+{
+	struct request *rq;
+	unsigned long flags;
+
+	if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE))
+		return NULL;
+
+	rq = dd->next_rq[data_dir];
+	if (!rq)
+		return NULL;
+
+	if (data_dir == READ || !blk_queue_is_zoned(rq->q))
+		return rq;
+
+	/*
+	 * Look for a write request that can be dispatched, that is one with
+	 * an unlocked target zone.
+	 */
+	spin_lock_irqsave(&dd->zone_lock, flags);
+	while (rq) {
+		if (blk_req_can_dispatch_to_zone(rq))
+			break;
+		rq = deadline_latter_request(rq);
+	}
+	spin_unlock_irqrestore(&dd->zone_lock, flags);
+
+	return rq;
+}
+
 /*
  * deadline_dispatch_requests selects the best request according to
  * read/write expire, fifo_batch, etc
  */
-static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
+static struct request *__dd_dispatch_request(struct deadline_data *dd)
 {
-	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
-	struct request *rq;
+	struct request *rq, *next_rq;
 	bool reads, writes;
 	int data_dir;
 
@@ -214,10 +285,9 @@ static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	/*
 	 * batches are currently reads XOR writes
 	 */
-	if (dd->next_rq[WRITE])
-		rq = dd->next_rq[WRITE];
-	else
-		rq = dd->next_rq[READ];
+	rq = deadline_next_request(dd, WRITE);
+	if (!rq)
+		rq = deadline_next_request(dd, READ);
 
 	if (rq && dd->batching < dd->fifo_batch)
 		/* we have a next request are still entitled to batch */
@@ -231,7 +301,8 @@ static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	if (reads) {
 		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));
 
-		if (writes && (dd->starved++ >= dd->writes_starved))
+		if (deadline_fifo_request(dd, WRITE) &&
+		    (dd->starved++ >= dd->writes_starved))
 			goto dispatch_writes;
 
 		data_dir = READ;
@@ -260,21 +331,29 @@ static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	/*
 	 * we are not running a batch, find best request for selected data_dir
 	 */
-	if (deadline_check_fifo(dd, data_dir) || !dd->next_rq[data_dir]) {
+	next_rq = deadline_next_request(dd, data_dir);
+	if (deadline_check_fifo(dd, data_dir) || !next_rq) {
 		/*
 		 * A deadline has expired, the last request was in the other
 		 * direction, or we have run out of higher-sectored requests.
 		 * Start again from the request with the earliest expiry time.
 		 */
-		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+		rq = deadline_fifo_request(dd, data_dir);
 	} else {
 		/*
 		 * The last req was the same dir and we have a next request in
 		 * sort order. No expired requests so continue on from here.
 		 */
-		rq = dd->next_rq[data_dir];
+		rq = next_rq;
 	}
 
+	/*
+	 * For a zoned block device, if we only have writes queued and none of
+	 * them can be dispatched, rq will be NULL.
+	 */
+	if (!rq)
+		return NULL;
+
 	dd->batching = 0;
 
 dispatch_request:
@@ -284,17 +363,27 @@ static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	dd->batching++;
 	deadline_move_request(dd, rq);
 done:
+	/*
+	 * If the request needs its target zone locked, do it.
+	 */
+	blk_req_zone_write_lock(rq);
 	rq->rq_flags |= RQF_STARTED;
 	return rq;
 }
 
+/*
+ * One confusing aspect here is that we get called for a specific
+ * hardware queue, but we return a request that may not be for a
+ * different hardware queue. This is because mq-deadline has shared
+ * state for all hardware queues, in terms of sorting, FIFOs, etc.
+ */
 static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
 	struct request *rq;
 
 	spin_lock(&dd->lock);
-	rq = __dd_dispatch_request(hctx);
+	rq = __dd_dispatch_request(dd);
 	spin_unlock(&dd->lock);
 
 	return rq;
@@ -339,6 +428,7 @@ static int dd_init_queue(struct request_queue *q, struct elevator_type *e)
 	dd->front_merges = 1;
 	dd->fifo_batch = fifo_batch;
 	spin_lock_init(&dd->lock);
+	spin_lock_init(&dd->zone_lock);
 	INIT_LIST_HEAD(&dd->dispatch);
 
 	q->elevator = eq;
@@ -395,6 +485,12 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	struct deadline_data *dd = q->elevator->elevator_data;
 	const int data_dir = rq_data_dir(rq);
 
+	/*
+	 * This may be a requeue of a write request that has locked its
+	 * target zone. If it is the case, this releases the zone lock.
+	 */
+	blk_req_zone_write_unlock(rq);
+
 	if (blk_mq_sched_try_insert_merge(q, rq))
 		return;
 
@@ -439,6 +535,26 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 	spin_unlock(&dd->lock);
 }
 
+/*
+ * For zoned block devices, write unlock the target zone of
+ * completed write requests. Do this while holding the zone lock
+ * spinlock so that the zone is never unlocked while deadline_fifo_request()
+ * while deadline_next_request() are executing.
+ */
+static void dd_completed_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	if (blk_queue_is_zoned(q)) {
+		struct deadline_data *dd = q->elevator->elevator_data;
+		unsigned long flags;
+
+		spin_lock_irqsave(&dd->zone_lock, flags);
+		blk_req_zone_write_unlock(rq);
+		spin_unlock_irqrestore(&dd->zone_lock, flags);
+	}
+}
+
 static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
@@ -640,6 +756,7 @@ static struct elevator_type mq_deadline = {
 	.ops.mq = {
 		.insert_requests	= dd_insert_requests,
 		.dispatch_request	= dd_dispatch_request,
+		.completed_request	= dd_completed_request,
 		.next_request		= elv_rb_latter_request,
 		.former_request		= elv_rb_former_request,
 		.bio_merge		= dd_bio_merge,

block/partitions/msdos.c

@@ -301,7 +301,9 @@ static void parse_bsd(struct parsed_partitions *state,
 			continue;
 		bsd_start = le32_to_cpu(p->p_offset);
 		bsd_size = le32_to_cpu(p->p_size);
-		if (memcmp(flavour, "bsd\0", 4) == 0)
+		/* FreeBSD has relative offset if C partition offset is zero */
+		if (memcmp(flavour, "bsd\0", 4) == 0 &&
+		    le32_to_cpu(l->d_partitions[2].p_offset) == 0)
 			bsd_start += offset;
 		if (offset == bsd_start && size == bsd_size)
 			/* full parent partition, we have it already */

block/scsi_ioctl.c

@@ -384,9 +384,10 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 
 /**
  * sg_scsi_ioctl  --  handle deprecated SCSI_IOCTL_SEND_COMMAND ioctl
- * @file:	file this ioctl operates on (optional)
  * @q:		request queue to send scsi commands down
  * @disk:	gendisk to operate on (option)
+ * @mode:	mode used to open the file through which the ioctl has been
+ *		submitted
  * @sic:	userspace structure describing the command to perform
  *
  * Send down the scsi command described by @sic to the device below
@@ -415,10 +416,10 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
  *      Positive numbers returned are the compacted SCSI error codes (4
  *      bytes in one int) where the lowest byte is the SCSI status.
  */
-#define OMAX_SB_LEN 16          /* For backward compatibility */
 int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		struct scsi_ioctl_command __user *sic)
 {
+	enum { OMAX_SB_LEN = 16 };	/* For backward compatibility */
 	struct request *rq;
 	struct scsi_request *req;
 	int err;
@@ -692,38 +693,9 @@ int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd)
 	if (bd && bd == bd->bd_contains)
 		return 0;
 
-	/* Actually none of these is particularly useful on a partition,
-	 * but they are safe.
-	 */
-	switch (cmd) {
-	case SCSI_IOCTL_GET_IDLUN:
-	case SCSI_IOCTL_GET_BUS_NUMBER:
-	case SCSI_IOCTL_GET_PCI:
-	case SCSI_IOCTL_PROBE_HOST:
-	case SG_GET_VERSION_NUM:
-	case SG_SET_TIMEOUT:
-	case SG_GET_TIMEOUT:
-	case SG_GET_RESERVED_SIZE:
-	case SG_SET_RESERVED_SIZE:
-	case SG_EMULATED_HOST:
-		return 0;
-	case CDROM_GET_CAPABILITY:
-		/* Keep this until we remove the printk below.  udev sends it
-		 * and we do not want to spam dmesg about it.   CD-ROMs do
-		 * not have partitions, so we get here only for disks.
-		 */
-		return -ENOIOCTLCMD;
-	default:
-		break;
-	}
-
 	if (capable(CAP_SYS_RAWIO))
 		return 0;
 
-	/* In particular, rule out all resets and host-specific ioctls.  */
-	printk_ratelimited(KERN_WARNING
-			   "%s: sending ioctl %x to a partition!\n", current->comm, cmd);
-
 	return -ENOIOCTLCMD;
 }
 EXPORT_SYMBOL(scsi_verify_blk_ioctl);

crypto/Kconfig

@@ -106,6 +106,7 @@ config CRYPTO_KPP
 config CRYPTO_ACOMP2
 	tristate
 	select CRYPTO_ALGAPI2
+	select SGL_ALLOC
 
 config CRYPTO_ACOMP
 	tristate

crypto/scompress.c

@@ -140,53 +140,6 @@ static int crypto_scomp_init_tfm(struct crypto_tfm *tfm)
 	return ret;
 }
 
-static void crypto_scomp_sg_free(struct scatterlist *sgl)
-{
-	int i, n;
-	struct page *page;
-
-	if (!sgl)
-		return;
-
-	n = sg_nents(sgl);
-	for_each_sg(sgl, sgl, n, i) {
-		page = sg_page(sgl);
-		if (page)
-			__free_page(page);
-	}
-
-	kfree(sgl);
-}
-
-static struct scatterlist *crypto_scomp_sg_alloc(size_t size, gfp_t gfp)
-{
-	struct scatterlist *sgl;
-	struct page *page;
-	int i, n;
-
-	n = ((size - 1) >> PAGE_SHIFT) + 1;
-
-	sgl = kmalloc_array(n, sizeof(struct scatterlist), gfp);
-	if (!sgl)
-		return NULL;
-
-	sg_init_table(sgl, n);
-
-	for (i = 0; i < n; i++) {
-		page = alloc_page(gfp);
-		if (!page)
-			goto err;
-		sg_set_page(sgl + i, page, PAGE_SIZE, 0);
-	}
-
-	return sgl;
-
-err:
-	sg_mark_end(sgl + i);
-	crypto_scomp_sg_free(sgl);
-	return NULL;
-}
-
 static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 {
 	struct crypto_acomp *tfm = crypto_acomp_reqtfm(req);
@@ -220,7 +173,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 					      scratch_dst, &req->dlen, *ctx);
 	if (!ret) {
 		if (!req->dst) {
-			req->dst = crypto_scomp_sg_alloc(req->dlen, GFP_ATOMIC);
+			req->dst = sgl_alloc(req->dlen, GFP_ATOMIC, NULL);
 			if (!req->dst)
 				goto out;
 		}
@@ -274,7 +227,7 @@ int crypto_init_scomp_ops_async(struct crypto_tfm *tfm)
 
 	crt->compress = scomp_acomp_compress;
 	crt->decompress = scomp_acomp_decompress;
-	crt->dst_free = crypto_scomp_sg_free;
+	crt->dst_free = sgl_free;
 	crt->reqsize = sizeof(void *);
 
 	return 0;

drivers/block/Kconfig

@@ -20,6 +20,10 @@ config BLK_DEV_NULL_BLK
 	tristate "Null test block driver"
 	select CONFIGFS_FS
 
+config BLK_DEV_NULL_BLK_FAULT_INJECTION
+	bool "Support fault injection for Null test block driver"
+	depends on BLK_DEV_NULL_BLK && FAULT_INJECTION
+
 config BLK_DEV_FD
 	tristate "Normal floppy disk support"
 	depends on ARCH_MAY_HAVE_PC_FDC

drivers/block/aoe/aoe.h

@@ -112,8 +112,7 @@ enum frame_flags {
 struct frame {
 	struct list_head head;
 	u32 tag;
-	struct timeval sent;	/* high-res time packet was sent */
-	u32 sent_jiffs;		/* low-res jiffies-based sent time */
+	ktime_t sent;			/* high-res time packet was sent */
 	ulong waited;
 	ulong waited_total;
 	struct aoetgt *t;		/* parent target I belong to */

drivers/block/aoe/aoecmd.c

@@ -398,8 +398,7 @@ aoecmd_ata_rw(struct aoedev *d)
 
 	skb = skb_clone(f->skb, GFP_ATOMIC);
 	if (skb) {
-		do_gettimeofday(&f->sent);
-		f->sent_jiffs = (u32) jiffies;
+		f->sent = ktime_get();
 		__skb_queue_head_init(&queue);
 		__skb_queue_tail(&queue, skb);
 		aoenet_xmit(&queue);
@@ -489,8 +488,7 @@ resend(struct aoedev *d, struct frame *f)
 	skb = skb_clone(skb, GFP_ATOMIC);
 	if (skb == NULL)
 		return;
-	do_gettimeofday(&f->sent);
-	f->sent_jiffs = (u32) jiffies;
+	f->sent = ktime_get();
 	__skb_queue_head_init(&queue);
 	__skb_queue_tail(&queue, skb);
 	aoenet_xmit(&queue);
@@ -499,33 +497,17 @@ resend(struct aoedev *d, struct frame *f)
 static int
 tsince_hr(struct frame *f)
 {
-	struct timeval now;
-	int n;
+	u64 delta = ktime_to_ns(ktime_sub(ktime_get(), f->sent));
 
-	do_gettimeofday(&now);
-	n = now.tv_usec - f->sent.tv_usec;
-	n += (now.tv_sec - f->sent.tv_sec) * USEC_PER_SEC;
+	/* delta is normally under 4.2 seconds, avoid 64-bit division */
+	if (likely(delta <= UINT_MAX))
+		return (u32)delta / NSEC_PER_USEC;
 
-	if (n < 0)
-		n = -n;
+	/* avoid overflow after 71 minutes */
+	if (delta > ((u64)INT_MAX * NSEC_PER_USEC))
+		return INT_MAX;
 
-	/* For relatively long periods, use jiffies to avoid
-	 * discrepancies caused by updates to the system time.
-	 *
-	 * On system with HZ of 1000, 32-bits is over 49 days
-	 * worth of jiffies, or over 71 minutes worth of usecs.
-	 *
-	 * Jiffies overflow is handled by subtraction of unsigned ints:
-	 * (gdb) print (unsigned) 2 - (unsigned) 0xfffffffe
-	 * $3 = 4
-	 * (gdb)
-	 */
-	if (n > USEC_PER_SEC / 4) {
-		n = ((u32) jiffies) - f->sent_jiffs;
-		n *= USEC_PER_SEC / HZ;
-	}
-
-	return n;
+	return div_u64(delta, NSEC_PER_USEC);
 }
 
 static int
@@ -589,7 +571,6 @@ reassign_frame(struct frame *f)
 	nf->waited = 0;
 	nf->waited_total = f->waited_total;
 	nf->sent = f->sent;
-	nf->sent_jiffs = f->sent_jiffs;
 	f->skb = skb;
 
 	return nf;
@@ -633,8 +614,7 @@ probe(struct aoetgt *t)
 
 	skb = skb_clone(f->skb, GFP_ATOMIC);
 	if (skb) {
-		do_gettimeofday(&f->sent);
-		f->sent_jiffs = (u32) jiffies;
+		f->sent = ktime_get();
 		__skb_queue_head_init(&queue);
 		__skb_queue_tail(&queue, skb);
 		aoenet_xmit(&queue);
@@ -1432,10 +1412,8 @@ aoecmd_ata_id(struct aoedev *d)
 	d->timer.function = rexmit_timer;
 
 	skb = skb_clone(skb, GFP_ATOMIC);
-	if (skb) {
-		do_gettimeofday(&f->sent);
-		f->sent_jiffs = (u32) jiffies;
-	}
+	if (skb)
+		f->sent = ktime_get();
 
 	return skb;
 }

drivers/block/drbd/drbd_bitmap.c

@@ -953,7 +953,7 @@ static void drbd_bm_endio(struct bio *bio)
 	struct drbd_bm_aio_ctx *ctx = bio->bi_private;
 	struct drbd_device *device = ctx->device;
 	struct drbd_bitmap *b = device->bitmap;
-	unsigned int idx = bm_page_to_idx(bio->bi_io_vec[0].bv_page);
+	unsigned int idx = bm_page_to_idx(bio_first_page_all(bio));
 
 	if ((ctx->flags & BM_AIO_COPY_PAGES) == 0 &&
 	    !bm_test_page_unchanged(b->bm_pages[idx]))

drivers/block/pktcdvd.c

@@ -2579,14 +2579,14 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	bdev = bdget(dev);
 	if (!bdev)
 		return -ENOMEM;
+	ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL);
+	if (ret)
+		return ret;
 	if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) {
 		WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
-		bdput(bdev);
+		blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
 		return -EINVAL;
 	}
-	ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL);
-	if (ret)
-		return ret;
 
 	/* This is safe, since we have a reference from open(). */
 	__module_get(THIS_MODULE);
@@ -2745,7 +2745,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	pd->pkt_dev = MKDEV(pktdev_major, idx);
 	ret = pkt_new_dev(pd, dev);
 	if (ret)
-		goto out_new_dev;
+		goto out_mem2;
 
 	/* inherit events of the host device */
 	disk->events = pd->bdev->bd_disk->events;
@@ -2763,8 +2763,6 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	mutex_unlock(&ctl_mutex);
 	return 0;
 
-out_new_dev:
-	blk_cleanup_queue(disk->queue);
 out_mem2:
 	put_disk(disk);
 out_mem:

drivers/block/zram/zram_drv.c

@@ -430,7 +430,7 @@ static void put_entry_bdev(struct zram *zram, unsigned long entry)
 
 static void zram_page_end_io(struct bio *bio)
 {
-	struct page *page = bio->bi_io_vec[0].bv_page;
+	struct page *page = bio_first_page_all(bio);
 
 	page_endio(page, op_is_write(bio_op(bio)),
 			blk_status_to_errno(bio->bi_status));

drivers/lightnvm/Kconfig

@@ -27,13 +27,6 @@ config NVM_DEBUG
 
 	It is required to create/remove targets without IOCTLs.
 
-config NVM_RRPC
-	tristate "Round-robin Hybrid Open-Channel SSD target"
-	---help---
-	Allows an open-channel SSD to be exposed as a block device to the
-	host. The target is implemented using a linear mapping table and
-	cost-based garbage collection. It is optimized for 4K IO sizes.
-
 config NVM_PBLK
 	tristate "Physical Block Device Open-Channel SSD target"
 	---help---

drivers/lightnvm/Makefile

@@ -4,7 +4,6 @@
 #
 
 obj-$(CONFIG_NVM)		:= core.o
-obj-$(CONFIG_NVM_RRPC)		+= rrpc.o
 obj-$(CONFIG_NVM_PBLK)		+= pblk.o
 pblk-y				:= pblk-init.o pblk-core.o pblk-rb.o \
 				   pblk-write.o pblk-cache.o pblk-read.o \

drivers/lightnvm/pblk-cache.c

@@ -19,12 +19,16 @@
 
 int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
 {
+	struct request_queue *q = pblk->dev->q;
 	struct pblk_w_ctx w_ctx;
 	sector_t lba = pblk_get_lba(bio);
+	unsigned long start_time = jiffies;
 	unsigned int bpos, pos;
 	int nr_entries = pblk_get_secs(bio);
 	int i, ret;
 
+	generic_start_io_acct(q, WRITE, bio_sectors(bio), &pblk->disk->part0);
+
 	/* Update the write buffer head (mem) with the entries that we can
 	 * write. The write in itself cannot fail, so there is no need to
 	 * rollback from here on.
@@ -67,6 +71,7 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
 	pblk_rl_inserted(&pblk->rl, nr_entries);
 
 out:
+	generic_end_io_acct(q, WRITE, &pblk->disk->part0, start_time);
 	pblk_write_should_kick(pblk);
 	return ret;
 }

drivers/lightnvm/pblk-core.c

@@ -32,8 +32,8 @@ static void pblk_line_mark_bb(struct work_struct *work)
 		struct pblk_line *line;
 		int pos;
 
-		line = &pblk->lines[pblk_dev_ppa_to_line(*ppa)];
-		pos = pblk_dev_ppa_to_pos(&dev->geo, *ppa);
+		line = &pblk->lines[pblk_ppa_to_line(*ppa)];
+		pos = pblk_ppa_to_pos(&dev->geo, *ppa);
 
 		pr_err("pblk: failed to mark bb, line:%d, pos:%d\n",
 				line->id, pos);
@@ -48,7 +48,7 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
-	int pos = pblk_dev_ppa_to_pos(geo, *ppa);
+	int pos = pblk_ppa_to_pos(geo, *ppa);
 
 	pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
 	atomic_long_inc(&pblk->erase_failed);
@@ -66,7 +66,7 @@ static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	struct pblk_line *line;
 
-	line = &pblk->lines[pblk_dev_ppa_to_line(rqd->ppa_addr)];
+	line = &pblk->lines[pblk_ppa_to_line(rqd->ppa_addr)];
 	atomic_dec(&line->left_seblks);
 
 	if (rqd->error) {
@@ -144,7 +144,7 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
 	BUG_ON(pblk_ppa_empty(ppa));
 #endif
 
-	line_id = pblk_tgt_ppa_to_line(ppa);
+	line_id = pblk_ppa_to_line(ppa);
 	line = &pblk->lines[line_id];
 	paddr = pblk_dev_ppa_to_line_addr(pblk, ppa);
 
@@ -650,7 +650,7 @@ static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
 	} else {
 		for (i = 0; i < rqd.nr_ppas; ) {
 			struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, id);
-			int pos = pblk_dev_ppa_to_pos(geo, ppa);
+			int pos = pblk_ppa_to_pos(geo, ppa);
 			int read_type = PBLK_READ_RANDOM;
 
 			if (pblk_io_aligned(pblk, rq_ppas))
@@ -668,7 +668,7 @@ static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
 				}
 
 				ppa = addr_to_gen_ppa(pblk, paddr, id);
-				pos = pblk_dev_ppa_to_pos(geo, ppa);
+				pos = pblk_ppa_to_pos(geo, ppa);
 			}
 
 			if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
@@ -742,7 +742,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 		cmd_op = NVM_OP_PWRITE;
 		flags = pblk_set_progr_mode(pblk, PBLK_WRITE);
 		lba_list = emeta_to_lbas(pblk, line->emeta->buf);
-	} else if (dir == PBLK_READ) {
+	} else if (dir == PBLK_READ_RECOV || dir == PBLK_READ) {
 		bio_op = REQ_OP_READ;
 		cmd_op = NVM_OP_PREAD;
 		flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
@@ -802,7 +802,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	if (rqd.error) {
 		if (dir == PBLK_WRITE)
 			pblk_log_write_err(pblk, &rqd);
-		else
+		else if (dir == PBLK_READ)
 			pblk_log_read_err(pblk, &rqd);
 	}
 
@@ -816,7 +816,7 @@ int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line)
 {
 	u64 bpaddr = pblk_line_smeta_start(pblk, line);
 
-	return pblk_line_submit_smeta_io(pblk, line, bpaddr, PBLK_READ);
+	return pblk_line_submit_smeta_io(pblk, line, bpaddr, PBLK_READ_RECOV);
 }
 
 int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line,
@@ -854,8 +854,8 @@ static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_geo *geo = &dev->geo;
 
 		pr_err("pblk: could not sync erase line:%d,blk:%d\n",
-					pblk_dev_ppa_to_line(ppa),
-					pblk_dev_ppa_to_pos(geo, ppa));
+					pblk_ppa_to_line(ppa),
+					pblk_ppa_to_pos(geo, ppa));
 
 		rqd.error = ret;
 		goto out;
@@ -979,7 +979,7 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
 
 	/* Start metadata */
 	smeta_buf->seq_nr = cpu_to_le64(line->seq_nr);
-	smeta_buf->window_wr_lun = cpu_to_le32(geo->nr_luns);
+	smeta_buf->window_wr_lun = cpu_to_le32(geo->all_luns);
 
 	/* Fill metadata among lines */
 	if (cur) {
@@ -1032,7 +1032,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 							lm->sec_per_line);
 		bitmap_or(line->map_bitmap, line->map_bitmap, l_mg->bb_aux,
 							lm->sec_per_line);
-		line->sec_in_line -= geo->sec_per_blk;
+		line->sec_in_line -= geo->sec_per_chk;
 		if (bit >= lm->emeta_bb)
 			nr_bb++;
 	}
@@ -1145,7 +1145,7 @@ int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line)
 	}
 	spin_unlock(&l_mg->free_lock);
 
-	pblk_rl_free_lines_dec(&pblk->rl, line);
+	pblk_rl_free_lines_dec(&pblk->rl, line, true);
 
 	if (!pblk_line_init_bb(pblk, line, 0)) {
 		list_add(&line->list, &l_mg->free_list);
@@ -1233,7 +1233,7 @@ static struct pblk_line *pblk_line_retry(struct pblk *pblk,
 	l_mg->data_line = retry_line;
 	spin_unlock(&l_mg->free_lock);
 
-	pblk_rl_free_lines_dec(&pblk->rl, retry_line);
+	pblk_rl_free_lines_dec(&pblk->rl, line, false);
 
 	if (pblk_line_erase(pblk, retry_line))
 		goto retry;
@@ -1252,7 +1252,6 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line *line;
-	int is_next = 0;
 
 	spin_lock(&l_mg->free_lock);
 	line = pblk_line_get(pblk);
@@ -1280,7 +1279,6 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
 	} else {
 		l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
 		l_mg->data_next->type = PBLK_LINETYPE_DATA;
-		is_next = 1;
 	}
 	spin_unlock(&l_mg->free_lock);
 
@@ -1290,10 +1288,6 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
 			return NULL;
 	}
 
-	pblk_rl_free_lines_dec(&pblk->rl, line);
-	if (is_next)
-		pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
-
 retry_setup:
 	if (!pblk_line_init_metadata(pblk, line, NULL)) {
 		line = pblk_line_retry(pblk, line);
@@ -1311,6 +1305,8 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
 		goto retry_setup;
 	}
 
+	pblk_rl_free_lines_dec(&pblk->rl, line, true);
+
 	return line;
 }
 
@@ -1395,7 +1391,6 @@ struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line *cur, *new = NULL;
 	unsigned int left_seblks;
-	int is_next = 0;
 
 	cur = l_mg->data_line;
 	new = l_mg->data_next;
@@ -1444,6 +1439,8 @@ struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
 		goto retry_setup;
 	}
 
+	pblk_rl_free_lines_dec(&pblk->rl, new, true);
+
 	/* Allocate next line for preparation */
 	spin_lock(&l_mg->free_lock);
 	l_mg->data_next = pblk_line_get(pblk);
@@ -1457,13 +1454,9 @@ struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
 	} else {
 		l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
 		l_mg->data_next->type = PBLK_LINETYPE_DATA;
-		is_next = 1;
 	}
 	spin_unlock(&l_mg->free_lock);
 
-	if (is_next)
-		pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
-
 out:
 	return new;
 }
@@ -1561,8 +1554,8 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_geo *geo = &dev->geo;
 
 		pr_err("pblk: could not async erase line:%d,blk:%d\n",
-					pblk_dev_ppa_to_line(ppa),
-					pblk_dev_ppa_to_pos(geo, ppa));
+					pblk_ppa_to_line(ppa),
+					pblk_ppa_to_pos(geo, ppa));
 	}
 
 	return err;
@@ -1746,7 +1739,7 @@ void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
 	struct pblk_lun *rlun;
-	int nr_luns = geo->nr_luns;
+	int nr_luns = geo->all_luns;
 	int bit = -1;
 
 	while ((bit = find_next_bit(lun_bitmap, nr_luns, bit + 1)) < nr_luns) {
@@ -1884,7 +1877,7 @@ void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
 
 		/* If the L2P entry maps to a line, the reference is valid */
 		if (!pblk_ppa_empty(ppa) && !pblk_addr_in_cache(ppa)) {
-			int line_id = pblk_dev_ppa_to_line(ppa);
+			int line_id = pblk_ppa_to_line(ppa);
 			struct pblk_line *line = &pblk->lines[line_id];
 
 			kref_get(&line->ref);

drivers/lightnvm/pblk-map.c

@@ -146,7 +146,7 @@ void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
 		return;
 
 	/* Erase blocks that are bad in this line but might not be in next */
-	if (unlikely(ppa_empty(*erase_ppa)) &&
+	if (unlikely(pblk_ppa_empty(*erase_ppa)) &&
 			bitmap_weight(d_line->blk_bitmap, lm->blk_per_line)) {
 		int bit = -1;
 

drivers/md/bcache/util.h

@@ -558,6 +558,7 @@ static inline unsigned fract_exp_two(unsigned x, unsigned fract_bits)
 }
 
 void bch_bio_map(struct bio *bio, void *base);
+int bch_bio_alloc_pages(struct bio *bio, gfp_t gfp_mask);
 
 static inline sector_t bdev_sectors(struct block_device *bdev)
 {