Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block into for-3.18

This is to receive 0a30288da1ae ("blk-mq, percpu_ref: implement a
kludge for SCSI blk-mq stall during probe") which implements
__percpu_ref_kill_expedited() to work around SCSI blk-mq stall.  The
commit reverted and patches to implement proper fix will be added.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>

4 files changed, 30 insertions, 10 deletions

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 1af40ee209e2..7130505c2425 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -895,8 +895,8 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg)
 	struct cache *cache = mg->cache;
 
 	if (mg->writeback) {
-		cell_defer(cache, mg->old_ocell, false);
 		clear_dirty(cache, mg->old_oblock, mg->cblock);
+		cell_defer(cache, mg->old_ocell, false);
 		cleanup_migration(mg);
 		return;
 
@@ -951,13 +951,13 @@ static void migration_success_post_commit(struct dm_cache_migration *mg)
 		}
 
 	} else {
+		clear_dirty(cache, mg->new_oblock, mg->cblock);
 		if (mg->requeue_holder)
 			cell_defer(cache, mg->new_ocell, true);
 		else {
 			bio_endio(mg->new_ocell->holder, 0);
 			cell_defer(cache, mg->new_ocell, false);
 		}
-		clear_dirty(cache, mg->new_oblock, mg->cblock);
 		cleanup_migration(mg);
 	}
 }
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 2785007e0e46..cd15e0801228 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1688,6 +1688,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	unsigned int key_size, opt_params;
 	unsigned long long tmpll;
 	int ret;
+	size_t iv_size_padding;
 	struct dm_arg_set as;
 	const char *opt_string;
 	char dummy;
@@ -1724,20 +1725,32 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	cc->dmreq_start = sizeof(struct ablkcipher_request);
 	cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc));
-	cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment());
-	cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) &
-			   ~(crypto_tfm_ctx_alignment() - 1);
+	cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
+
+	if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) {
+		/* Allocate the padding exactly */
+		iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request))
+				& crypto_ablkcipher_alignmask(any_tfm(cc));
+	} else {
+		/*
+		 * If the cipher requires greater alignment than kmalloc
+		 * alignment, we don't know the exact position of the
+		 * initialization vector. We must assume worst case.
+		 */
+		iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc));
+	}
 
 	cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start +
-			sizeof(struct dm_crypt_request) + cc->iv_size);
+			sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size);
 	if (!cc->req_pool) {
 		ti->error = "Cannot allocate crypt request mempool";
 		goto bad;
 	}
 
 	cc->per_bio_data_size = ti->per_bio_data_size =
-				sizeof(struct dm_crypt_io) + cc->dmreq_start +
-				sizeof(struct dm_crypt_request) + cc->iv_size;
+		ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start +
+		      sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size,
+		      ARCH_KMALLOC_MINALIGN);
 
 	cc->page_pool = mempool_create_page_pool(MIN_POOL_PAGES, 0);
 	if (!cc->page_pool) {
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index b08c18871323..6703751d87d7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2953,6 +2953,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 		 */
 		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
 			end_reshape(conf);
+			close_sync(conf);
 			return 0;
 		}
 
@@ -3081,6 +3082,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			}
 
 			r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+			r10_bio->state = 0;
 			raise_barrier(conf, rb2 != NULL);
 			atomic_set(&r10_bio->remaining, 0);
 
@@ -3269,6 +3271,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (sync_blocks < max_sync)
 			max_sync = sync_blocks;
 		r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+		r10_bio->state = 0;
 
 		r10_bio->mddev = mddev;
 		atomic_set(&r10_bio->remaining, 0);
@@ -4384,6 +4387,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 read_more:
 	/* Now schedule reads for blocks from sector_nr to last */
 	r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+	r10_bio->state = 0;
 	raise_barrier(conf, sectors_done != 0);
 	atomic_set(&r10_bio->remaining, 0);
 	r10_bio->mddev = mddev;
@@ -4398,6 +4402,7 @@ read_more:
 		 * on all the target devices.
 		 */
 		// FIXME
+		mempool_free(r10_bio, conf->r10buf_pool);
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		return sectors_done;
 	}
@@ -4410,7 +4415,7 @@ read_more:
 	read_bio->bi_private = r10_bio;
 	read_bio->bi_end_io = end_sync_read;
 	read_bio->bi_rw = READ;
-	read_bio->bi_flags &= ~(BIO_POOL_MASK - 1);
+	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
 	read_bio->bi_flags |= 1 << BIO_UPTODATE;
 	read_bio->bi_vcnt = 0;
 	read_bio->bi_iter.bi_size = 0;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 6234b2e84587..183588b11fc1 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2922,7 +2922,7 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
 	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) &&
 	      !test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
 	     (sh->raid_conf->level == 6 && s->failed && s->to_write &&
-	      s->to_write < sh->raid_conf->raid_disks - 2 &&
+	      s->to_write - s->non_overwrite < sh->raid_conf->raid_disks - 2 &&
 	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) {
 		/* we would like to get this block, possibly by computing it,
 		 * otherwise read it if the backing disk is insync
@@ -3817,6 +3817,8 @@ static void handle_stripe(struct stripe_head *sh)
 				set_bit(R5_Wantwrite, &dev->flags);
 				if (prexor)
 					continue;
+				if (s.failed > 1)
+					continue;
 				if (!test_bit(R5_Insync, &dev->flags) ||
 				    ((i == sh->pd_idx || i == sh->qd_idx)  &&
 				     s.failed == 0))