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
  ...

Author: torvalds

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.c

@@ -337,13 +337,20 @@ 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
 	 */
 	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-iosched.h

@@ -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/bfq-wf2q.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-integrity.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/bio.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-core.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-exec.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-lib.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);