Merge tag 'v4.12-rc5' into for-4.13/block

We've already got a few conflicts and upcoming work depends on some of the
changes that have gone into mainline as regression fixes for this series.

Pull in 4.12-rc5 to resolve these conflicts and make it easier on down stream
trees to continue working on 4.13 changes.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

16 files changed, 65 insertions, 48 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index bf7419a56454..f4eace5ea184 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -485,10 +485,10 @@ void bitmap_print_sb(struct bitmap *bitmap)
 	pr_debug("         magic: %08x\n", le32_to_cpu(sb->magic));
 	pr_debug("       version: %d\n", le32_to_cpu(sb->version));
 	pr_debug("          uuid: %08x.%08x.%08x.%08x\n",
-		 *(__u32 *)(sb->uuid+0),
-		 *(__u32 *)(sb->uuid+4),
-		 *(__u32 *)(sb->uuid+8),
-		 *(__u32 *)(sb->uuid+12));
+		 le32_to_cpu(*(__u32 *)(sb->uuid+0)),
+		 le32_to_cpu(*(__u32 *)(sb->uuid+4)),
+		 le32_to_cpu(*(__u32 *)(sb->uuid+8)),
+		 le32_to_cpu(*(__u32 *)(sb->uuid+12)));
 	pr_debug("        events: %llu\n",
 		 (unsigned long long) le64_to_cpu(sb->events));
 	pr_debug("events cleared: %llu\n",
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 0902d2fd1743..850ff6c67994 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1336,7 +1336,7 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c)
 {
 	struct dm_io_request io_req = {
 		.bi_op = REQ_OP_WRITE,
-		.bi_op_flags = REQ_PREFLUSH,
+		.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.addr = NULL,
 		.client = c->dm_io,
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index ccc6ef4d00b9..339af38459fc 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -783,7 +783,8 @@ static void write_journal(struct dm_integrity_c *ic, unsigned commit_start, unsi
 			for (i = 0; i < commit_sections; i++)
 				rw_section_mac(ic, commit_start + i, true);
 		}
-		rw_journal(ic, REQ_OP_WRITE, REQ_FUA, commit_start, commit_sections, &io_comp);
+		rw_journal(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, commit_start,
+			   commit_sections, &io_comp);
 	} else {
 		unsigned to_end;
 		io_comp.in_flight = (atomic_t)ATOMIC_INIT(2);
@@ -2374,21 +2375,6 @@ static void dm_integrity_set(struct dm_target *ti, struct dm_integrity_c *ic)
 	blk_queue_max_integrity_segments(disk->queue, UINT_MAX);
 }
 
-/* FIXME: use new kvmalloc */
-static void *dm_integrity_kvmalloc(size_t size, gfp_t gfp)
-{
-	void *ptr = NULL;
-
-	if (size <= PAGE_SIZE)
-		ptr = kmalloc(size, GFP_KERNEL | gfp);
-	if (!ptr && size <= KMALLOC_MAX_SIZE)
-		ptr = kmalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | gfp);
-	if (!ptr)
-		ptr = __vmalloc(size, GFP_KERNEL | gfp, PAGE_KERNEL);
-
-	return ptr;
-}
-
 static void dm_integrity_free_page_list(struct dm_integrity_c *ic, struct page_list *pl)
 {
 	unsigned i;
@@ -2407,7 +2393,7 @@ static struct page_list *dm_integrity_alloc_page_list(struct dm_integrity_c *ic)
 	struct page_list *pl;
 	unsigned i;
 
-	pl = dm_integrity_kvmalloc(page_list_desc_size, __GFP_ZERO);
+	pl = kvmalloc(page_list_desc_size, GFP_KERNEL | __GFP_ZERO);
 	if (!pl)
 		return NULL;
 
@@ -2437,7 +2423,7 @@ static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_int
 	struct scatterlist **sl;
 	unsigned i;
 
-	sl = dm_integrity_kvmalloc(ic->journal_sections * sizeof(struct scatterlist *), __GFP_ZERO);
+	sl = kvmalloc(ic->journal_sections * sizeof(struct scatterlist *), GFP_KERNEL | __GFP_ZERO);
 	if (!sl)
 		return NULL;
 
@@ -2453,7 +2439,7 @@ static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_int
 
 		n_pages = (end_index - start_index + 1);
 
-		s = dm_integrity_kvmalloc(n_pages * sizeof(struct scatterlist), 0);
+		s = kvmalloc(n_pages * sizeof(struct scatterlist), GFP_KERNEL);
 		if (!s) {
 			dm_integrity_free_journal_scatterlist(ic, sl);
 			return NULL;
@@ -2617,7 +2603,7 @@ static int create_journal(struct dm_integrity_c *ic, char **error)
 				goto bad;
 			}
 
-			sg = dm_integrity_kvmalloc((ic->journal_pages + 1) * sizeof(struct scatterlist), 0);
+			sg = kvmalloc((ic->journal_pages + 1) * sizeof(struct scatterlist), GFP_KERNEL);
 			if (!sg) {
 				*error = "Unable to allocate sg list";
 				r = -ENOMEM;
@@ -2673,7 +2659,7 @@ static int create_journal(struct dm_integrity_c *ic, char **error)
 				r = -ENOMEM;
 				goto bad;
 			}
-			ic->sk_requests = dm_integrity_kvmalloc(ic->journal_sections * sizeof(struct skcipher_request *), __GFP_ZERO);
+			ic->sk_requests = kvmalloc(ic->journal_sections * sizeof(struct skcipher_request *), GFP_KERNEL | __GFP_ZERO);
 			if (!ic->sk_requests) {
 				*error = "Unable to allocate sk requests";
 				r = -ENOMEM;
@@ -2740,7 +2726,7 @@ retest_commit_id:
 		r = -ENOMEM;
 		goto bad;
 	}
-	ic->journal_tree = dm_integrity_kvmalloc(journal_tree_size, 0);
+	ic->journal_tree = kvmalloc(journal_tree_size, GFP_KERNEL);
 	if (!ic->journal_tree) {
 		*error = "Could not allocate memory for journal tree";
 		r = -ENOMEM;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 0555b4410e05..41852ae287a5 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1710,12 +1710,13 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
 	}
 
 	/*
-	 * Try to avoid low memory issues when a device is suspended.
+	 * Use __GFP_HIGH to avoid low memory issues when a device is
+	 * suspended and the ioctl is needed to resume it.
 	 * Use kmalloc() rather than vmalloc() when we can.
 	 */
 	dmi = NULL;
 	noio_flag = memalloc_noio_save();
-	dmi = kvmalloc(param_kernel->data_size, GFP_KERNEL);
+	dmi = kvmalloc(param_kernel->data_size, GFP_KERNEL | __GFP_HIGH);
 	memalloc_noio_restore(noio_flag);
 
 	if (!dmi) {
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 0822e4a6f67d..3ab584b686e0 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -260,7 +260,7 @@ static int mirror_flush(struct dm_target *ti)
 	struct mirror *m;
 	struct dm_io_request io_req = {
 		.bi_op = REQ_OP_WRITE,
-		.bi_op_flags = REQ_PREFLUSH,
+		.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.addr = NULL,
 		.client = ms->io_client,
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index b93476c3ba3f..c5534d294773 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -741,7 +741,8 @@ static void persistent_commit_exception(struct dm_exception_store *store,
 	/*
 	 * Commit exceptions to disk.
 	 */
-	if (ps->valid && area_io(ps, REQ_OP_WRITE, REQ_PREFLUSH | REQ_FUA))
+	if (ps->valid && area_io(ps, REQ_OP_WRITE,
+				 REQ_PREFLUSH | REQ_FUA | REQ_SYNC))
 		ps->valid = 0;
 
 	/*
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 2dca66eb67e1..b46705ebf01f 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -166,7 +166,7 @@ static int verity_hash_init(struct dm_verity *v, struct ahash_request *req,
 		return r;
 	}
 
-	if (likely(v->version >= 1))
+	if (likely(v->salt_size && (v->version >= 1)))
 		r = verity_hash_update(v, req, v->salt, v->salt_size, res);
 
 	return r;
@@ -177,7 +177,7 @@ static int verity_hash_final(struct dm_verity *v, struct ahash_request *req,
 {
 	int r;
 
-	if (unlikely(!v->version)) {
+	if (unlikely(v->salt_size && (!v->version))) {
 		r = verity_hash_update(v, req, v->salt, v->salt_size, res);
 
 		if (r < 0) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f38f9dd5cbdd..c4b74f7398ac 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1663,7 +1663,7 @@ static struct mapped_device *alloc_dev(int minor)
 
 	bio_init(&md->flush_bio, NULL, 0);
 	md->flush_bio.bi_bdev = md->bdev;
-	md->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+	md->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
 
 	dm_stats_init(&md->stats);
 
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 7299ce2f08a8..03082e17c65c 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -1311,8 +1311,10 @@ static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev)
 	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
 	lock_comm(cinfo, 1);
 	ret = __sendmsg(cinfo, &cmsg);
-	if (ret)
+	if (ret) {
+		unlock_comm(cinfo);
 		return ret;
+	}
 	cinfo->no_new_dev_lockres->flags |= DLM_LKF_NOQUEUE;
 	ret = dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_EX);
 	cinfo->no_new_dev_lockres->flags &= ~DLM_LKF_NOQUEUE;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 6452e83fd650..833cc7082034 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -765,7 +765,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 	    test_bit(FailFast, &rdev->flags) &&
 	    !test_bit(LastDev, &rdev->flags))
 		ff = MD_FAILFAST;
-	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_FUA | ff;
+	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA | ff;
 
 	atomic_inc(&mddev->pending_writes);
 	submit_bio(bio);
@@ -5174,6 +5174,18 @@ static void mddev_delayed_delete(struct work_struct *ws)
 
 static void no_op(struct percpu_ref *r) {}
 
+int mddev_init_writes_pending(struct mddev *mddev)
+{
+	if (mddev->writes_pending.percpu_count_ptr)
+		return 0;
+	if (percpu_ref_init(&mddev->writes_pending, no_op, 0, GFP_KERNEL) < 0)
+		return -ENOMEM;
+	/* We want to start with the refcount at zero */
+	percpu_ref_put(&mddev->writes_pending);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mddev_init_writes_pending);
+
 static int md_alloc(dev_t dev, char *name)
 {
 	/*
@@ -5239,10 +5251,6 @@ static int md_alloc(dev_t dev, char *name)
 	blk_queue_make_request(mddev->queue, md_make_request);
 	blk_set_stacking_limits(&mddev->queue->limits);
 
-	if (percpu_ref_init(&mddev->writes_pending, no_op, 0, GFP_KERNEL) < 0)
-		goto abort;
-	/* We want to start with the refcount at zero */
-	percpu_ref_put(&mddev->writes_pending);
 	disk = alloc_disk(1 << shift);
 	if (!disk) {
 		blk_cleanup_queue(mddev->queue);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 11f15146ce51..0fa1de42c42b 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -648,6 +648,7 @@ extern void md_unregister_thread(struct md_thread **threadp);
 extern void md_wakeup_thread(struct md_thread *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
+extern int mddev_init_writes_pending(struct mddev *mddev);
 extern void md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 94b87c4d0f7b..a1a3cf0293df 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3063,6 +3063,8 @@ static int raid1_run(struct mddev *mddev)
 			mdname(mddev));
 		return -EIO;
 	}
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
 	/*
 	 * copy the already verified devices into our private RAID1
 	 * bookkeeping area. [whatever we allocate in run(),
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 89ad1cd29037..3178273a7253 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3611,6 +3611,9 @@ static int raid10_run(struct mddev *mddev)
 	int first = 1;
 	bool discard_supported = false;
 
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
+
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
 		if (IS_ERR(conf))
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 3ed6a0d89db8..3746c9c27e54 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1782,7 +1782,7 @@ static int r5l_log_write_empty_meta_block(struct r5l_log *log, sector_t pos,
 	mb->checksum = cpu_to_le32(crc32c_le(log->uuid_checksum,
 					     mb, PAGE_SIZE));
 	if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, REQ_OP_WRITE,
-			  REQ_FUA, false)) {
+			  REQ_SYNC | REQ_FUA, false)) {
 		__free_page(page);
 		return -EIO;
 	}
@@ -2388,7 +2388,7 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 		mb->checksum = cpu_to_le32(crc32c_le(log->uuid_checksum,
 						     mb, PAGE_SIZE));
 		sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page,
-			     REQ_OP_WRITE, REQ_FUA, false);
+			     REQ_OP_WRITE, REQ_SYNC | REQ_FUA, false);
 		sh->log_start = ctx->pos;
 		list_add_tail(&sh->r5c, &log->stripe_in_journal_list);
 		atomic_inc(&log->stripe_in_journal_count);
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index 09e04be34e5f..e709ada0bf09 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -907,8 +907,8 @@ static int ppl_write_empty_header(struct ppl_log *log)
 	pplhdr->checksum = cpu_to_le32(~crc32c_le(~0, pplhdr, PAGE_SIZE));
 
 	if (!sync_page_io(rdev, rdev->ppl.sector - rdev->data_offset,
-			  PPL_HEADER_SIZE, page, REQ_OP_WRITE | REQ_FUA, 0,
-			  false)) {
+			  PPL_HEADER_SIZE, page, REQ_OP_WRITE | REQ_SYNC |
+			  REQ_FUA, 0, false)) {
 		md_error(rdev->mddev, rdev);
 		ret = -EIO;
 	}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e1bdc320f664..7171bfd48223 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4085,10 +4085,15 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
 			set_bit(STRIPE_INSYNC, &sh->state);
 		else {
 			atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
-			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) {
 				/* don't try to repair!! */
 				set_bit(STRIPE_INSYNC, &sh->state);
-			else {
+				pr_warn_ratelimited("%s: mismatch sector in range "
+						    "%llu-%llu\n", mdname(conf->mddev),
+						    (unsigned long long) sh->sector,
+						    (unsigned long long) sh->sector +
+						    STRIPE_SECTORS);
+			} else {
 				sh->check_state = check_state_compute_run;
 				set_bit(STRIPE_COMPUTE_RUN, &sh->state);
 				set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
@@ -4237,10 +4242,15 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
 			}
 		} else {
 			atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
-			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) {
 				/* don't try to repair!! */
 				set_bit(STRIPE_INSYNC, &sh->state);
-			else {
+				pr_warn_ratelimited("%s: mismatch sector in range "
+						    "%llu-%llu\n", mdname(conf->mddev),
+						    (unsigned long long) sh->sector,
+						    (unsigned long long) sh->sector +
+						    STRIPE_SECTORS);
+			} else {
 				int *target = &sh->ops.target;
 
 				sh->ops.target = -1;
@@ -7108,6 +7118,9 @@ static int raid5_run(struct mddev *mddev)
 	long long min_offset_diff = 0;
 	int first = 1;
 
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
+
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
 			  mdname(mddev));