Merge tag 'for-5.3/block-20190708' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main block updates for 5.3. Nothing earth shattering or
  major in here, just fixes, additions, and improvements all over the
  map. This contains:

   - Series of documentation fixes (Bart)

   - Optimization of the blk-mq ctx get/put (Bart)

   - null_blk removal race condition fix (Bob)

   - req/bio_op() cleanups (Chaitanya)

   - Series cleaning up the segment accounting, and request/bio mapping
     (Christoph)

   - Series cleaning up the page getting/putting for bios (Christoph)

   - block cgroup cleanups and moving it to where it is used (Christoph)

   - block cgroup fixes (Tejun)

   - Series of fixes and improvements to bcache, most notably a write
     deadlock fix (Coly)

   - blk-iolatency STS_AGAIN and accounting fixes (Dennis)

   - Series of improvements and fixes to BFQ (Douglas, Paolo)

   - debugfs_create() return value check removal for drbd (Greg)

   - Use struct_size(), where appropriate (Gustavo)

   - Two lighnvm fixes (Heiner, Geert)

   - MD fixes, including a read balance and corruption fix (Guoqing,
     Marcos, Xiao, Yufen)

   - block opal shadow mbr additions (Jonas, Revanth)

   - sbitmap compare-and-exhange improvemnts (Pavel)

   - Fix for potential bio->bi_size overflow (Ming)

   - NVMe pull requests:
       - improved PCIe suspent support (Keith Busch)
       - error injection support for the admin queue (Akinobu Mita)
       - Fibre Channel discovery improvements (James Smart)
       - tracing improvements including nvmetc tracing support (Minwoo Im)
       - misc fixes and cleanups (Anton Eidelman, Minwoo Im, Chaitanya
         Kulkarni)"

   - Various little fixes and improvements to drivers and core"

* tag 'for-5.3/block-20190708' of git://git.kernel.dk/linux-block: (153 commits)
  blk-iolatency: fix STS_AGAIN handling
  block: nr_phys_segments needs to be zero for REQ_OP_WRITE_ZEROES
  blk-mq: simplify blk_mq_make_request()
  blk-mq: remove blk_mq_put_ctx()
  sbitmap: Replace cmpxchg with xchg
  block: fix .bi_size overflow
  block: sed-opal: check size of shadow mbr
  block: sed-opal: ioctl for writing to shadow mbr
  block: sed-opal: add ioctl for done-mark of shadow mbr
  block: never take page references for ITER_BVEC
  direct-io: use bio_release_pages in dio_bio_complete
  block_dev: use bio_release_pages in bio_unmap_user
  block_dev: use bio_release_pages in blkdev_bio_end_io
  iomap: use bio_release_pages in iomap_dio_bio_end_io
  block: use bio_release_pages in bio_map_user_iov
  block: use bio_release_pages in bio_unmap_user
  block: optionally mark pages dirty in bio_release_pages
  block: move the BIO_NO_PAGE_REF check into bio_release_pages
  block: skd_main.c: Remove call to memset after dma_alloc_coherent
  block: mtip32xx: Remove call to memset after dma_alloc_coherent
  ...

1 files changed, 38 insertions, 48 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index aea11476fee6..8a1354a08a1a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -64,31 +64,6 @@
  *    [B A] [D C]    [B A] [E C D]
  */
 
-/*
- * Number of guaranteed r10bios in case of extreme VM load:
- */
-#define	NR_RAID10_BIOS 256
-
-/* when we get a read error on a read-only array, we redirect to another
- * device without failing the first device, or trying to over-write to
- * correct the read error.  To keep track of bad blocks on a per-bio
- * level, we store IO_BLOCKED in the appropriate 'bios' pointer
- */
-#define IO_BLOCKED ((struct bio *)1)
-/* When we successfully write to a known bad-block, we need to remove the
- * bad-block marking which must be done from process context.  So we record
- * the success by setting devs[n].bio to IO_MADE_GOOD
- */
-#define IO_MADE_GOOD ((struct bio *)2)
-
-#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
-
-/* When there are this many requests queued to be written by
- * the raid10 thread, we become 'congested' to provide back-pressure
- * for writeback.
- */
-static int max_queued_requests = 1024;
-
 static void allow_barrier(struct r10conf *conf);
 static void lower_barrier(struct r10conf *conf);
 static int _enough(struct r10conf *conf, int previous, int ignore);
@@ -123,11 +98,6 @@ static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
 	return kzalloc(size, gfp_flags);
 }
 
-static void r10bio_pool_free(void *r10_bio, void *data)
-{
-	kfree(r10_bio);
-}
-
 #define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
 /* amount of memory to reserve for resync requests */
 #define RESYNC_WINDOW (1024*1024)
@@ -233,7 +203,7 @@ out_free_bio:
 	}
 	kfree(rps);
 out_free_r10bio:
-	r10bio_pool_free(r10_bio, conf);
+	rbio_pool_free(r10_bio, conf);
 	return NULL;
 }
 
@@ -261,7 +231,7 @@ static void r10buf_pool_free(void *__r10_bio, void *data)
 	/* resync pages array stored in the 1st bio's .bi_private */
 	kfree(rp);
 
-	r10bio_pool_free(r10bio, conf);
+	rbio_pool_free(r10bio, conf);
 }
 
 static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio)
@@ -737,15 +707,19 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 	int sectors = r10_bio->sectors;
 	int best_good_sectors;
 	sector_t new_distance, best_dist;
-	struct md_rdev *best_rdev, *rdev = NULL;
+	struct md_rdev *best_dist_rdev, *best_pending_rdev, *rdev = NULL;
 	int do_balance;
-	int best_slot;
+	int best_dist_slot, best_pending_slot;
+	bool has_nonrot_disk = false;
+	unsigned int min_pending;
 	struct geom *geo = &conf->geo;
 
 	raid10_find_phys(conf, r10_bio);
 	rcu_read_lock();
-	best_slot = -1;
-	best_rdev = NULL;
+	best_dist_slot = -1;
+	min_pending = UINT_MAX;
+	best_dist_rdev = NULL;
+	best_pending_rdev = NULL;
 	best_dist = MaxSector;
 	best_good_sectors = 0;
 	do_balance = 1;
@@ -767,6 +741,8 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 		sector_t first_bad;
 		int bad_sectors;
 		sector_t dev_sector;
+		unsigned int pending;
+		bool nonrot;
 
 		if (r10_bio->devs[slot].bio == IO_BLOCKED)
 			continue;
@@ -803,8 +779,8 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 					first_bad - dev_sector;
 				if (good_sectors > best_good_sectors) {
 					best_good_sectors = good_sectors;
-					best_slot = slot;
-					best_rdev = rdev;
+					best_dist_slot = slot;
+					best_dist_rdev = rdev;
 				}
 				if (!do_balance)
 					/* Must read from here */
@@ -817,14 +793,23 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 		if (!do_balance)
 			break;
 
-		if (best_slot >= 0)
+		nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
+		has_nonrot_disk |= nonrot;
+		pending = atomic_read(&rdev->nr_pending);
+		if (min_pending > pending && nonrot) {
+			min_pending = pending;
+			best_pending_slot = slot;
+			best_pending_rdev = rdev;
+		}
+
+		if (best_dist_slot >= 0)
 			/* At least 2 disks to choose from so failfast is OK */
 			set_bit(R10BIO_FailFast, &r10_bio->state);
 		/* This optimisation is debatable, and completely destroys
 		 * sequential read speed for 'far copies' arrays.  So only
 		 * keep it for 'near' arrays, and review those later.
 		 */
-		if (geo->near_copies > 1 && !atomic_read(&rdev->nr_pending))
+		if (geo->near_copies > 1 && !pending)
 			new_distance = 0;
 
 		/* for far > 1 always use the lowest address */
@@ -833,15 +818,21 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 		else
 			new_distance = abs(r10_bio->devs[slot].addr -
 					   conf->mirrors[disk].head_position);
+
 		if (new_distance < best_dist) {
 			best_dist = new_distance;
-			best_slot = slot;
-			best_rdev = rdev;
+			best_dist_slot = slot;
+			best_dist_rdev = rdev;
 		}
 	}
 	if (slot >= conf->copies) {
-		slot = best_slot;
-		rdev = best_rdev;
+		if (has_nonrot_disk) {
+			slot = best_pending_slot;
+			rdev = best_pending_rdev;
+		} else {
+			slot = best_dist_slot;
+			rdev = best_dist_rdev;
+		}
 	}
 
 	if (slot >= 0) {
@@ -3675,8 +3666,8 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 
 	conf->geo = geo;
 	conf->copies = copies;
-	err = mempool_init(&conf->r10bio_pool, NR_RAID10_BIOS, r10bio_pool_alloc,
-			   r10bio_pool_free, conf);
+	err = mempool_init(&conf->r10bio_pool, NR_RAID_BIOS, r10bio_pool_alloc,
+			   rbio_pool_free, conf);
 	if (err)
 		goto out;
 
@@ -4780,8 +4771,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
 	int idx = 0;
 	struct page **pages;
 
-	r10b = kmalloc(sizeof(*r10b) +
-	       sizeof(struct r10dev) * conf->copies, GFP_NOIO);
+	r10b = kmalloc(struct_size(r10b, devs, conf->copies), GFP_NOIO);
 	if (!r10b) {
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		return -ENOMEM;