Merge branch 'for-4.3/core' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "This first core part of the block IO changes contains:

   - Cleanup of the bio IO error signaling from Christoph.  We used to
     rely on the uptodate bit and passing around of an error, now we
     store the error in the bio itself.

   - Improvement of the above from myself, by shrinking the bio size
     down again to fit in two cachelines on x86-64.

   - Revert of the max_hw_sectors cap removal from a revision again,
     from Jeff Moyer.  This caused performance regressions in various
     tests.  Reinstate the limit, bump it to a more reasonable size
     instead.

   - Make /sys/block/<dev>/queue/discard_max_bytes writeable, by me.
     Most devices have huge trim limits, which can cause nasty latencies
     when deleting files.  Enable the admin to configure the size down.
     We will look into having a more sane default instead of UINT_MAX
     sectors.

   - Improvement of the SGP gaps logic from Keith Busch.

   - Enable the block core to handle arbitrarily sized bios, which
     enables a nice simplification of bio_add_page() (which is an IO hot
     path).  From Kent.

   - Improvements to the partition io stats accounting, making it
     faster.  From Ming Lei.

   - Also from Ming Lei, a basic fixup for overflow of the sysfs pending
     file in blk-mq, as well as a fix for a blk-mq timeout race
     condition.

   - Ming Lin has been carrying Kents above mentioned patches forward
     for a while, and testing them.  Ming also did a few fixes around
     that.

   - Sasha Levin found and fixed a use-after-free problem introduced by
     the bio->bi_error changes from Christoph.

   - Small blk cgroup cleanup from Viresh Kumar"

* 'for-4.3/core' of git://git.kernel.dk/linux-block: (26 commits)
  blk: Fix bio_io_vec index when checking bvec gaps
  block: Replace SG_GAPS with new queue limits mask
  block: bump BLK_DEF_MAX_SECTORS to 2560
  Revert "block: remove artifical max_hw_sectors cap"
  blk-mq: fix race between timeout and freeing request
  blk-mq: fix buffer overflow when reading sysfs file of 'pending'
  Documentation: update notes in biovecs about arbitrarily sized bios
  block: remove bio_get_nr_vecs()
  fs: use helper bio_add_page() instead of open coding on bi_io_vec
  block: kill merge_bvec_fn() completely
  md/raid5: get rid of bio_fits_rdev()
  md/raid5: split bio for chunk_aligned_read
  block: remove split code in blkdev_issue_{discard,write_same}
  btrfs: remove bio splitting and merge_bvec_fn() calls
  bcache: remove driver private bio splitting code
  block: simplify bio_add_page()
  block: make generic_make_request handle arbitrarily sized bios
  blk-cgroup: Drop unlikely before IS_ERR(_OR_NULL)
  block: don't access bio->bi_error after bio_put()
  block: shrink struct bio down to 2 cache lines again
  ...

1 files changed, 31 insertions, 151 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 38c58e19cfce..b0fce2ebf7ad 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -101,7 +101,7 @@ static int _enough(struct r10conf *conf, int previous, int ignore);
 static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 				int *skipped);
 static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
-static void end_reshape_write(struct bio *bio, int error);
+static void end_reshape_write(struct bio *bio);
 static void end_reshape(struct r10conf *conf);
 
 static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
@@ -307,9 +307,9 @@ static void raid_end_bio_io(struct r10bio *r10_bio)
 	} else
 		done = 1;
 	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		bio->bi_error = -EIO;
 	if (done) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		/*
 		 * Wake up any possible resync thread that waits for the device
 		 * to go idle.
@@ -358,9 +358,9 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
 	return r10_bio->devs[slot].devnum;
 }
 
-static void raid10_end_read_request(struct bio *bio, int error)
+static void raid10_end_read_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r10bio *r10_bio = bio->bi_private;
 	int slot, dev;
 	struct md_rdev *rdev;
@@ -438,9 +438,8 @@ static void one_write_done(struct r10bio *r10_bio)
 	}
 }
 
-static void raid10_end_write_request(struct bio *bio, int error)
+static void raid10_end_write_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	int dev;
 	int dec_rdev = 1;
@@ -460,7 +459,7 @@ static void raid10_end_write_request(struct bio *bio, int error)
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (repl)
 			/* Never record new bad blocks to replacement,
 			 * just fail it.
@@ -672,93 +671,6 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
 	return (vchunk << geo->chunk_shift) + offset;
 }
 
-/**
- *	raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
- *	@mddev: the md device
- *	@bvm: properties of new bio
- *	@biovec: the request that could be merged to it.
- *
- *	Return amount of bytes we can accept at this offset
- *	This requires checking for end-of-chunk if near_copies != raid_disks,
- *	and for subordinate merge_bvec_fns if merge_check_needed.
- */
-static int raid10_mergeable_bvec(struct mddev *mddev,
-				 struct bvec_merge_data *bvm,
-				 struct bio_vec *biovec)
-{
-	struct r10conf *conf = mddev->private;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int max;
-	unsigned int chunk_sectors;
-	unsigned int bio_sectors = bvm->bi_size >> 9;
-	struct geom *geo = &conf->geo;
-
-	chunk_sectors = (conf->geo.chunk_mask & conf->prev.chunk_mask) + 1;
-	if (conf->reshape_progress != MaxSector &&
-	    ((sector >= conf->reshape_progress) !=
-	     conf->mddev->reshape_backwards))
-		geo = &conf->prev;
-
-	if (geo->near_copies < geo->raid_disks) {
-		max = (chunk_sectors - ((sector & (chunk_sectors - 1))
-					+ bio_sectors)) << 9;
-		if (max < 0)
-			/* bio_add cannot handle a negative return */
-			max = 0;
-		if (max <= biovec->bv_len && bio_sectors == 0)
-			return biovec->bv_len;
-	} else
-		max = biovec->bv_len;
-
-	if (mddev->merge_check_needed) {
-		struct {
-			struct r10bio r10_bio;
-			struct r10dev devs[conf->copies];
-		} on_stack;
-		struct r10bio *r10_bio = &on_stack.r10_bio;
-		int s;
-		if (conf->reshape_progress != MaxSector) {
-			/* Cannot give any guidance during reshape */
-			if (max <= biovec->bv_len && bio_sectors == 0)
-				return biovec->bv_len;
-			return 0;
-		}
-		r10_bio->sector = sector;
-		raid10_find_phys(conf, r10_bio);
-		rcu_read_lock();
-		for (s = 0; s < conf->copies; s++) {
-			int disk = r10_bio->devs[s].devnum;
-			struct md_rdev *rdev = rcu_dereference(
-				conf->mirrors[disk].rdev);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = r10_bio->devs[s].addr
-						+ rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-			rdev = rcu_dereference(conf->mirrors[disk].replacement);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = r10_bio->devs[s].addr
-						+ rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-		}
-		rcu_read_unlock();
-	}
-	return max;
-}
-
 /*
  * This routine returns the disk from which the requested read should
  * be done. There is a per-array 'next expected sequential IO' sector
@@ -821,12 +733,10 @@ retry:
 		disk = r10_bio->devs[slot].devnum;
 		rdev = rcu_dereference(conf->mirrors[disk].replacement);
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags) ||
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
 			rdev = rcu_dereference(conf->mirrors[disk].rdev);
 		if (rdev == NULL ||
-		    test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags))
+		    test_bit(Faulty, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
@@ -957,7 +867,7 @@ static void flush_pending_writes(struct r10conf *conf)
 			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			else
 				generic_make_request(bio);
 			bio = next;
@@ -1133,7 +1043,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
-			bio_endio(bio, 0);
+			bio_endio(bio);
 		else
 			generic_make_request(bio);
 		bio = next;
@@ -1217,7 +1127,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	 * non-zero, then it is the number of not-completed requests.
 	 */
 	bio->bi_phys_segments = 0;
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	if (rw == READ) {
 		/*
@@ -1326,11 +1236,9 @@ retry_write:
 			blocked_rdev = rrdev;
 			break;
 		}
-		if (rdev && (test_bit(Faulty, &rdev->flags)
-			     || test_bit(Unmerged, &rdev->flags)))
+		if (rdev && (test_bit(Faulty, &rdev->flags)))
 			rdev = NULL;
-		if (rrdev && (test_bit(Faulty, &rrdev->flags)
-			      || test_bit(Unmerged, &rrdev->flags)))
+		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
 			rrdev = NULL;
 
 		r10_bio->devs[i].bio = NULL;
@@ -1777,7 +1685,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int mirror;
 	int first = 0;
 	int last = conf->geo.raid_disks - 1;
-	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
@@ -1790,11 +1697,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
-	if (q->merge_bvec_fn) {
-		set_bit(Unmerged, &rdev->flags);
-		mddev->merge_check_needed = 1;
-	}
-
 	if (rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
@@ -1833,19 +1735,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		rcu_assign_pointer(p->rdev, rdev);
 		break;
 	}
-	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
-		/* Some requests might not have seen this new
-		 * merge_bvec_fn.  We must wait for them to complete
-		 * before merging the device fully.
-		 * First we make sure any code which has tested
-		 * our function has submitted the request, then
-		 * we wait for all outstanding requests to complete.
-		 */
-		synchronize_sched();
-		freeze_array(conf, 0);
-		unfreeze_array(conf);
-		clear_bit(Unmerged, &rdev->flags);
-	}
 	md_integrity_add_rdev(rdev, mddev);
 	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
@@ -1916,7 +1805,7 @@ abort:
 	return err;
 }
 
-static void end_sync_read(struct bio *bio, int error)
+static void end_sync_read(struct bio *bio)
 {
 	struct r10bio *r10_bio = bio->bi_private;
 	struct r10conf *conf = r10_bio->mddev->private;
@@ -1928,7 +1817,7 @@ static void end_sync_read(struct bio *bio, int error)
 	} else
 		d = find_bio_disk(conf, r10_bio, bio, NULL, NULL);
 
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (!bio->bi_error)
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
 	else
 		/* The write handler will notice the lack of
@@ -1977,9 +1866,8 @@ static void end_sync_request(struct r10bio *r10_bio)
 	}
 }
 
-static void end_sync_write(struct bio *bio, int error)
+static void end_sync_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
@@ -1996,7 +1884,7 @@ static void end_sync_write(struct bio *bio, int error)
 	else
 		rdev = conf->mirrors[d].rdev;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (repl)
 			md_error(mddev, rdev);
 		else {
@@ -2044,7 +1932,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 
 	/* find the first device with a block */
 	for (i=0; i<conf->copies; i++)
-		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags))
+		if (!r10_bio->devs[i].bio->bi_error)
 			break;
 
 	if (i == conf->copies)
@@ -2064,7 +1952,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			continue;
 		if (i == first)
 			continue;
-		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags)) {
+		if (!r10_bio->devs[i].bio->bi_error) {
 			/* We know that the bi_io_vec layout is the same for
 			 * both 'first' and 'i', so we just compare them.
 			 * All vec entries are PAGE_SIZE;
@@ -2394,7 +2282,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
-			    !test_bit(Unmerged, &rdev->flags) &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
 					&first_bad, &bad_sectors) == 0) {
@@ -2448,7 +2335,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (!rdev ||
-			    test_bit(Unmerged, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
@@ -2706,8 +2592,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 			rdev = conf->mirrors[dev].rdev;
 			if (r10_bio->devs[m].bio == NULL)
 				continue;
-			if (test_bit(BIO_UPTODATE,
-				     &r10_bio->devs[m].bio->bi_flags)) {
+			if (!r10_bio->devs[m].bio->bi_error) {
 				rdev_clear_badblocks(
 					rdev,
 					r10_bio->devs[m].addr,
@@ -2722,8 +2607,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 			rdev = conf->mirrors[dev].replacement;
 			if (r10_bio->devs[m].repl_bio == NULL)
 				continue;
-			if (test_bit(BIO_UPTODATE,
-				     &r10_bio->devs[m].repl_bio->bi_flags)) {
+
+			if (!r10_bio->devs[m].repl_bio->bi_error) {
 				rdev_clear_badblocks(
 					rdev,
 					r10_bio->devs[m].addr,
@@ -2748,8 +2633,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 					r10_bio->devs[m].addr,
 					r10_bio->sectors, 0);
 				rdev_dec_pending(rdev, conf->mddev);
-			} else if (bio != NULL &&
-				   !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+			} else if (bio != NULL && bio->bi_error) {
 				if (!narrow_write_error(r10_bio, m)) {
 					md_error(conf->mddev, rdev);
 					set_bit(R10BIO_Degraded,
@@ -3263,7 +3147,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 
 			bio = r10_bio->devs[i].bio;
 			bio_reset(bio);
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 			if (conf->mirrors[d].rdev == NULL ||
 			    test_bit(Faulty, &conf->mirrors[d].rdev->flags))
 				continue;
@@ -3300,7 +3184,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			/* Need to set up for writing to the replacement */
 			bio = r10_bio->devs[i].repl_bio;
 			bio_reset(bio);
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 
 			sector = r10_bio->devs[i].addr;
 			atomic_inc(&conf->mirrors[d].rdev->nr_pending);
@@ -3357,7 +3241,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 				/* remove last page from this bio */
 				bio2->bi_vcnt--;
 				bio2->bi_iter.bi_size -= len;
-				__clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
+				bio_clear_flag(bio2, BIO_SEG_VALID);
 			}
 			goto bio_full;
 		}
@@ -3377,7 +3261,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 
 		if (bio->bi_end_io == end_sync_read) {
 			md_sync_acct(bio->bi_bdev, nr_sectors);
-			set_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = 0;
 			generic_make_request(bio);
 		}
 	}
@@ -3643,8 +3527,6 @@ static int run(struct mddev *mddev)
 			disk->rdev = rdev;
 		}
 		q = bdev_get_queue(rdev->bdev);
-		if (q->merge_bvec_fn)
-			mddev->merge_check_needed = 1;
 		diff = (rdev->new_data_offset - rdev->data_offset);
 		if (!mddev->reshape_backwards)
 			diff = -diff;
@@ -4382,7 +4264,7 @@ read_more:
 	read_bio->bi_end_io = end_sync_read;
 	read_bio->bi_rw = READ;
 	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
-	__set_bit(BIO_UPTODATE, &read_bio->bi_flags);
+	read_bio->bi_error = 0;
 	read_bio->bi_vcnt = 0;
 	read_bio->bi_iter.bi_size = 0;
 	r10_bio->master_bio = read_bio;
@@ -4439,7 +4321,7 @@ read_more:
 				/* Remove last page from this bio */
 				bio2->bi_vcnt--;
 				bio2->bi_iter.bi_size -= len;
-				__clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
+				bio_clear_flag(bio2, BIO_SEG_VALID);
 			}
 			goto bio_full;
 		}
@@ -4604,9 +4486,8 @@ static int handle_reshape_read_error(struct mddev *mddev,
 	return 0;
 }
 
-static void end_reshape_write(struct bio *bio, int error)
+static void end_reshape_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
@@ -4623,7 +4504,7 @@ static void end_reshape_write(struct bio *bio, int error)
 		rdev = conf->mirrors[d].rdev;
 	}
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		/* FIXME should record badblock */
 		md_error(mddev, rdev);
 	}
@@ -4700,7 +4581,6 @@ static struct md_personality raid10_personality =
 	.start_reshape	= raid10_start_reshape,
 	.finish_reshape	= raid10_finish_reshape,
 	.congested	= raid10_congested,
-	.mergeable_bvec	= raid10_mergeable_bvec,
 };
 
 static int __init raid_init(void)