Merge tag 'v4.19-rc6' into for-4.20/block

Merge -rc6 in, for two reasons:

1) Resolve a trivial conflict in the blk-mq-tag.c documentation
2) A few important regression fixes went into upstream directly, so
   they aren't in the 4.20 branch.

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

* tag 'v4.19-rc6': (780 commits)
  Linux 4.19-rc6
  MAINTAINERS: fix reference to moved drivers/{misc => auxdisplay}/panel.c
  cpufreq: qcom-kryo: Fix section annotations
  perf/core: Add sanity check to deal with pinned event failure
  xen/blkfront: correct purging of persistent grants
  Revert "xen/blkfront: When purging persistent grants, keep them in the buffer"
  selftests/powerpc: Fix Makefiles for headers_install change
  blk-mq: I/O and timer unplugs are inverted in blktrace
  dax: Fix deadlock in dax_lock_mapping_entry()
  x86/boot: Fix kexec booting failure in the SEV bit detection code
  bcache: add separate workqueue for journal_write to avoid deadlock
  drm/amd/display: Fix Edid emulation for linux
  drm/amd/display: Fix Vega10 lightup on S3 resume
  drm/amdgpu: Fix vce work queue was not cancelled when suspend
  Revert "drm/panel: Add device_link from panel device to DRM device"
  xen/blkfront: When purging persistent grants, keep them in the buffer
  clocksource/drivers/timer-atmel-pit: Properly handle error cases
  block: fix deadline elevator drain for zoned block devices
  ACPI / hotplug / PCI: Don't scan for non-hotplug bridges if slot is not bridge
  drm/syncobj: Don't leak fences when WAIT_FOR_SUBMIT is set
  ...

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

13 files changed, 217 insertions, 125 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 83504dd8100a..954dad29e6e8 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -965,6 +965,7 @@ void bch_prio_write(struct cache *ca);
 void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
 
 extern struct workqueue_struct *bcache_wq;
+extern struct workqueue_struct *bch_journal_wq;
 extern struct mutex bch_register_lock;
 extern struct list_head bch_cache_sets;
 
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 6116bbf870d8..522c7426f3a0 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -485,7 +485,7 @@ static void do_journal_discard(struct cache *ca)
 
 		closure_get(&ca->set->cl);
 		INIT_WORK(&ja->discard_work, journal_discard_work);
-		schedule_work(&ja->discard_work);
+		queue_work(bch_journal_wq, &ja->discard_work);
 	}
 }
 
@@ -592,7 +592,7 @@ static void journal_write_done(struct closure *cl)
 		: &j->w[0];
 
 	__closure_wake_up(&w->wait);
-	continue_at_nobarrier(cl, journal_write, system_wq);
+	continue_at_nobarrier(cl, journal_write, bch_journal_wq);
 }
 
 static void journal_write_unlock(struct closure *cl)
@@ -627,7 +627,7 @@ static void journal_write_unlocked(struct closure *cl)
 		spin_unlock(&c->journal.lock);
 
 		btree_flush_write(c);
-		continue_at(cl, journal_write, system_wq);
+		continue_at(cl, journal_write, bch_journal_wq);
 		return;
 	}
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 94c756c66bd7..30ba9aeb5ee8 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -47,6 +47,7 @@ static int bcache_major;
 static DEFINE_IDA(bcache_device_idx);
 static wait_queue_head_t unregister_wait;
 struct workqueue_struct *bcache_wq;
+struct workqueue_struct *bch_journal_wq;
 
 #define BTREE_MAX_PAGES		(256 * 1024 / PAGE_SIZE)
 /* limitation of partitions number on single bcache device */
@@ -2341,6 +2342,9 @@ static void bcache_exit(void)
 		kobject_put(bcache_kobj);
 	if (bcache_wq)
 		destroy_workqueue(bcache_wq);
+	if (bch_journal_wq)
+		destroy_workqueue(bch_journal_wq);
+
 	if (bcache_major)
 		unregister_blkdev(bcache_major, "bcache");
 	unregister_reboot_notifier(&reboot);
@@ -2370,6 +2374,10 @@ static int __init bcache_init(void)
 	if (!bcache_wq)
 		goto err;
 
+	bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
+	if (!bch_journal_wq)
+		goto err;
+
 	bcache_kobj = kobject_create_and_add("bcache", fs_kobj);
 	if (!bcache_kobj)
 		goto err;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index f266c81f396f..0481223b1deb 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -332,7 +332,7 @@ static int crypt_iv_essiv_init(struct crypt_config *cc)
 	int err;
 
 	desc->tfm = essiv->hash_tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->flags = 0;
 
 	err = crypto_shash_digest(desc, cc->key, cc->key_size, essiv->salt);
 	shash_desc_zero(desc);
@@ -606,7 +606,7 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
 	int i, r;
 
 	desc->tfm = lmk->hash_tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->flags = 0;
 
 	r = crypto_shash_init(desc);
 	if (r)
@@ -768,7 +768,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 
 	/* calculate crc32 for every 32bit part and xor it */
 	desc->tfm = tcw->crc32_tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->flags = 0;
 	for (i = 0; i < 4; i++) {
 		r = crypto_shash_init(desc);
 		if (r)
@@ -1251,7 +1251,7 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc,
 	 * requests if driver request queue is full.
 	 */
 	skcipher_request_set_callback(ctx->r.req,
-	    CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+	    CRYPTO_TFM_REQ_MAY_BACKLOG,
 	    kcryptd_async_done, dmreq_of_req(cc, ctx->r.req));
 }
 
@@ -1268,7 +1268,7 @@ static void crypt_alloc_req_aead(struct crypt_config *cc,
 	 * requests if driver request queue is full.
 	 */
 	aead_request_set_callback(ctx->r.req_aead,
-	    CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+	    CRYPTO_TFM_REQ_MAY_BACKLOG,
 	    kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead));
 }
 
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 378878599466..89ccb64342de 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -532,7 +532,7 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result
 	unsigned j, size;
 
 	desc->tfm = ic->journal_mac;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->flags = 0;
 
 	r = crypto_shash_init(desc);
 	if (unlikely(r)) {
@@ -676,7 +676,7 @@ static void complete_journal_encrypt(struct crypto_async_request *req, int err)
 static bool do_crypt(bool encrypt, struct skcipher_request *req, struct journal_completion *comp)
 {
 	int r;
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				      complete_journal_encrypt, comp);
 	if (likely(encrypt))
 		r = crypto_skcipher_encrypt(req);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index cae689de75fd..5ba067fa0c72 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010-2011 Neil Brown
- * Copyright (C) 2010-2017 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2010-2018 Red Hat, Inc. All rights reserved.
  *
  * This file is released under the GPL.
  */
@@ -29,9 +29,6 @@
  */
 #define	MIN_RAID456_JOURNAL_SPACE (4*2048)
 
-/* Global list of all raid sets */
-static LIST_HEAD(raid_sets);
-
 static bool devices_handle_discard_safely = false;
 
 /*
@@ -227,7 +224,6 @@ struct rs_layout {
 
 struct raid_set {
 	struct dm_target *ti;
-	struct list_head list;
 
 	uint32_t stripe_cache_entries;
 	unsigned long ctr_flags;
@@ -273,19 +269,6 @@ static void rs_config_restore(struct raid_set *rs, struct rs_layout *l)
 	mddev->new_chunk_sectors = l->new_chunk_sectors;
 }
 
-/* Find any raid_set in active slot for @rs on global list */
-static struct raid_set *rs_find_active(struct raid_set *rs)
-{
-	struct raid_set *r;
-	struct mapped_device *md = dm_table_get_md(rs->ti->table);
-
-	list_for_each_entry(r, &raid_sets, list)
-		if (r != rs && dm_table_get_md(r->ti->table) == md)
-			return r;
-
-	return NULL;
-}
-
 /* raid10 algorithms (i.e. formats) */
 #define	ALGORITHM_RAID10_DEFAULT	0
 #define	ALGORITHM_RAID10_NEAR		1
@@ -764,7 +747,6 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r
 
 	mddev_init(&rs->md);
 
-	INIT_LIST_HEAD(&rs->list);
 	rs->raid_disks = raid_devs;
 	rs->delta_disks = 0;
 
@@ -782,9 +764,6 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r
 	for (i = 0; i < raid_devs; i++)
 		md_rdev_init(&rs->dev[i].rdev);
 
-	/* Add @rs to global list. */
-	list_add(&rs->list, &raid_sets);
-
 	/*
 	 * Remaining items to be initialized by further RAID params:
 	 *  rs->md.persistent
@@ -797,7 +776,7 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r
 	return rs;
 }
 
-/* Free all @rs allocations and remove it from global list. */
+/* Free all @rs allocations */
 static void raid_set_free(struct raid_set *rs)
 {
 	int i;
@@ -815,8 +794,6 @@ static void raid_set_free(struct raid_set *rs)
 			dm_put_device(rs->ti, rs->dev[i].data_dev);
 	}
 
-	list_del(&rs->list);
-
 	kfree(rs);
 }
 
@@ -2649,7 +2626,7 @@ static int rs_adjust_data_offsets(struct raid_set *rs)
 		return 0;
 	}
 
-	/* HM FIXME: get InSync raid_dev? */
+	/* HM FIXME: get In_Sync raid_dev? */
 	rdev = &rs->dev[0].rdev;
 
 	if (rs->delta_disks < 0) {
@@ -3149,6 +3126,11 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
 		rs_set_new(rs);
 	} else if (rs_is_recovering(rs)) {
+		/* Rebuild particular devices */
+		if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) {
+			set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+			rs_setup_recovery(rs, MaxSector);
+		}
 		/* A recovering raid set may be resized */
 		; /* skip setup rs */
 	} else if (rs_is_reshaping(rs)) {
@@ -3242,6 +3224,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	/* Start raid set read-only and assumed clean to change in raid_resume() */
 	rs->md.ro = 1;
 	rs->md.in_sync = 1;
+
+	/* Keep array frozen */
 	set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
 
 	/* Has to be held on running the array */
@@ -3265,7 +3249,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	rs->callbacks.congested_fn = raid_is_congested;
 	dm_table_add_target_callbacks(ti->table, &rs->callbacks);
 
-	/* If raid4/5/6 journal mode explictely requested (only possible with journal dev) -> set it */
+	/* If raid4/5/6 journal mode explicitly requested (only possible with journal dev) -> set it */
 	if (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags)) {
 		r = r5c_journal_mode_set(&rs->md, rs->journal_dev.mode);
 		if (r) {
@@ -3350,32 +3334,53 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_SUBMITTED;
 }
 
-/* Return string describing the current sync action of @mddev */
-static const char *decipher_sync_action(struct mddev *mddev, unsigned long recovery)
+/* Return sync state string for @state */
+enum sync_state { st_frozen, st_reshape, st_resync, st_check, st_repair, st_recover, st_idle };
+static const char *sync_str(enum sync_state state)
+{
+	/* Has to be in above sync_state order! */
+	static const char *sync_strs[] = {
+		"frozen",
+		"reshape",
+		"resync",
+		"check",
+		"repair",
+		"recover",
+		"idle"
+	};
+
+	return __within_range(state, 0, ARRAY_SIZE(sync_strs) - 1) ? sync_strs[state] : "undef";
+};
+
+/* Return enum sync_state for @mddev derived from @recovery flags */
+static const enum sync_state decipher_sync_action(struct mddev *mddev, unsigned long recovery)
 {
 	if (test_bit(MD_RECOVERY_FROZEN, &recovery))
-		return "frozen";
+		return st_frozen;
 
-	/* The MD sync thread can be done with io but still be running */
+	/* The MD sync thread can be done with io or be interrupted but still be running */
 	if (!test_bit(MD_RECOVERY_DONE, &recovery) &&
 	    (test_bit(MD_RECOVERY_RUNNING, &recovery) ||
 	     (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &recovery)))) {
 		if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
-			return "reshape";
+			return st_reshape;
 
 		if (test_bit(MD_RECOVERY_SYNC, &recovery)) {
 			if (!test_bit(MD_RECOVERY_REQUESTED, &recovery))
-				return "resync";
-			else if (test_bit(MD_RECOVERY_CHECK, &recovery))
-				return "check";
-			return "repair";
+				return st_resync;
+			if (test_bit(MD_RECOVERY_CHECK, &recovery))
+				return st_check;
+			return st_repair;
 		}
 
 		if (test_bit(MD_RECOVERY_RECOVER, &recovery))
-			return "recover";
+			return st_recover;
+
+		if (mddev->reshape_position != MaxSector)
+			return st_reshape;
 	}
 
-	return "idle";
+	return st_idle;
 }
 
 /*
@@ -3409,6 +3414,7 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 				sector_t resync_max_sectors)
 {
 	sector_t r;
+	enum sync_state state;
 	struct mddev *mddev = &rs->md;
 
 	clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
@@ -3419,20 +3425,14 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 		set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 
 	} else {
-		if (!test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags) &&
-		    !test_bit(MD_RECOVERY_INTR, &recovery) &&
-		    (test_bit(MD_RECOVERY_NEEDED, &recovery) ||
-		     test_bit(MD_RECOVERY_RESHAPE, &recovery) ||
-		     test_bit(MD_RECOVERY_RUNNING, &recovery)))
-			r = mddev->curr_resync_completed;
-		else
+		state = decipher_sync_action(mddev, recovery);
+
+		if (state == st_idle && !test_bit(MD_RECOVERY_INTR, &recovery))
 			r = mddev->recovery_cp;
+		else
+			r = mddev->curr_resync_completed;
 
-		if (r >= resync_max_sectors &&
-		    (!test_bit(MD_RECOVERY_REQUESTED, &recovery) ||
-		     (!test_bit(MD_RECOVERY_FROZEN, &recovery) &&
-		      !test_bit(MD_RECOVERY_NEEDED, &recovery) &&
-		      !test_bit(MD_RECOVERY_RUNNING, &recovery)))) {
+		if (state == st_idle && r >= resync_max_sectors) {
 			/*
 			 * Sync complete.
 			 */
@@ -3440,24 +3440,20 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 			if (test_bit(MD_RECOVERY_RECOVER, &recovery))
 				set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 
-		} else if (test_bit(MD_RECOVERY_RECOVER, &recovery)) {
+		} else if (state == st_recover)
 			/*
 			 * In case we are recovering, the array is not in sync
 			 * and health chars should show the recovering legs.
 			 */
 			;
-
-		} else if (test_bit(MD_RECOVERY_SYNC, &recovery) &&
-			   !test_bit(MD_RECOVERY_REQUESTED, &recovery)) {
+		else if (state == st_resync)
 			/*
 			 * If "resync" is occurring, the raid set
 			 * is or may be out of sync hence the health
 			 * characters shall be 'a'.
 			 */
 			set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
-
-		} else if (test_bit(MD_RECOVERY_RESHAPE, &recovery) &&
-			   !test_bit(MD_RECOVERY_REQUESTED, &recovery)) {
+		else if (state == st_reshape)
 			/*
 			 * If "reshape" is occurring, the raid set
 			 * is or may be out of sync hence the health
@@ -3465,7 +3461,7 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 			 */
 			set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
 
-		} else if (test_bit(MD_RECOVERY_REQUESTED, &recovery)) {
+		else if (state == st_check || state == st_repair)
 			/*
 			 * If "check" or "repair" is occurring, the raid set has
 			 * undergone an initial sync and the health characters
@@ -3473,12 +3469,12 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 			 */
 			set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 
-		} else {
+		else {
 			struct md_rdev *rdev;
 
 			/*
 			 * We are idle and recovery is needed, prevent 'A' chars race
-			 * caused by components still set to in-sync by constrcuctor.
+			 * caused by components still set to in-sync by constructor.
 			 */
 			if (test_bit(MD_RECOVERY_NEEDED, &recovery))
 				set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
@@ -3542,7 +3538,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 		progress = rs_get_progress(rs, recovery, resync_max_sectors);
 		resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ?
 				    atomic64_read(&mddev->resync_mismatches) : 0;
-		sync_action = decipher_sync_action(&rs->md, recovery);
+		sync_action = sync_str(decipher_sync_action(&rs->md, recovery));
 
 		/* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */
 		for (i = 0; i < rs->raid_disks; i++)
@@ -3892,14 +3888,13 @@ static int rs_start_reshape(struct raid_set *rs)
 	struct mddev *mddev = &rs->md;
 	struct md_personality *pers = mddev->pers;
 
+	/* Don't allow the sync thread to work until the table gets reloaded. */
+	set_bit(MD_RECOVERY_WAIT, &mddev->recovery);
+
 	r = rs_setup_reshape(rs);
 	if (r)
 		return r;
 
-	/* Need to be resumed to be able to start reshape, recovery is frozen until raid_resume() though */
-	if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags))
-		mddev_resume(mddev);
-
 	/*
 	 * Check any reshape constraints enforced by the personalility
 	 *
@@ -3923,10 +3918,6 @@ static int rs_start_reshape(struct raid_set *rs)
 		}
 	}
 
-	/* Suspend because a resume will happen in raid_resume() */
-	set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags);
-	mddev_suspend(mddev);
-
 	/*
 	 * Now reshape got set up, update superblocks to
 	 * reflect the fact so that a table reload will
@@ -3947,29 +3938,6 @@ static int raid_preresume(struct dm_target *ti)
 	if (test_and_set_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags))
 		return 0;
 
-	if (!test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) {
-		struct raid_set *rs_active = rs_find_active(rs);
-
-		if (rs_active) {
-			/*
-			 * In case no rebuilds have been requested
-			 * and an active table slot exists, copy
-			 * current resynchonization completed and
-			 * reshape position pointers across from
-			 * suspended raid set in the active slot.
-			 *
-			 * This resumes the new mapping at current
-			 * offsets to continue recover/reshape without
-			 * necessarily redoing a raid set partially or
-			 * causing data corruption in case of a reshape.
-			 */
-			if (rs_active->md.curr_resync_completed != MaxSector)
-				mddev->curr_resync_completed = rs_active->md.curr_resync_completed;
-			if (rs_active->md.reshape_position != MaxSector)
-				mddev->reshape_position = rs_active->md.reshape_position;
-		}
-	}
-
 	/*
 	 * The superblocks need to be updated on disk if the
 	 * array is new or new devices got added (thus zeroed
@@ -4046,7 +4014,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 13, 2},
+	.version = {1, 14, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 72142021b5c9..74f6770c70b1 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -189,6 +189,12 @@ struct dm_pool_metadata {
 	sector_t data_block_size;
 
 	/*
+	 * We reserve a section of the metadata for commit overhead.
+	 * All reported space does *not* include this.
+	 */
+	dm_block_t metadata_reserve;
+
+	/*
 	 * Set if a transaction has to be aborted but the attempt to roll back
 	 * to the previous (good) transaction failed.  The only pool metadata
 	 * operation possible in this state is the closing of the device.
@@ -816,6 +822,22 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	return dm_tm_commit(pmd->tm, sblock);
 }
 
+static void __set_metadata_reserve(struct dm_pool_metadata *pmd)
+{
+	int r;
+	dm_block_t total;
+	dm_block_t max_blocks = 4096; /* 16M */
+
+	r = dm_sm_get_nr_blocks(pmd->metadata_sm, &total);
+	if (r) {
+		DMERR("could not get size of metadata device");
+		pmd->metadata_reserve = max_blocks;
+	} else {
+		sector_div(total, 10);
+		pmd->metadata_reserve = min(max_blocks, total);
+	}
+}
+
 struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
 					       sector_t data_block_size,
 					       bool format_device)
@@ -849,6 +871,8 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
 		return ERR_PTR(r);
 	}
 
+	__set_metadata_reserve(pmd);
+
 	return pmd;
 }
 
@@ -1820,6 +1844,13 @@ int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd,
 	down_read(&pmd->root_lock);
 	if (!pmd->fail_io)
 		r = dm_sm_get_nr_free(pmd->metadata_sm, result);
+
+	if (!r) {
+		if (*result < pmd->metadata_reserve)
+			*result = 0;
+		else
+			*result -= pmd->metadata_reserve;
+	}
 	up_read(&pmd->root_lock);
 
 	return r;
@@ -1932,8 +1963,11 @@ int dm_pool_resize_metadata_dev(struct dm_pool_metadata *pmd, dm_block_t new_cou
 	int r = -EINVAL;
 
 	down_write(&pmd->root_lock);
-	if (!pmd->fail_io)
+	if (!pmd->fail_io) {
 		r = __resize_space_map(pmd->metadata_sm, new_count);
+		if (!r)
+			__set_metadata_reserve(pmd);
+	}
 	up_write(&pmd->root_lock);
 
 	return r;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 7bd60a150f8f..aaf1ad481ee8 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -200,7 +200,13 @@ struct dm_thin_new_mapping;
 enum pool_mode {
 	PM_WRITE,		/* metadata may be changed */
 	PM_OUT_OF_DATA_SPACE,	/* metadata may be changed, though data may not be allocated */
+
+	/*
+	 * Like READ_ONLY, except may switch back to WRITE on metadata resize. Reported as READ_ONLY.
+	 */
+	PM_OUT_OF_METADATA_SPACE,
 	PM_READ_ONLY,		/* metadata may not be changed */
+
 	PM_FAIL,		/* all I/O fails */
 };
 
@@ -1371,7 +1377,35 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
 
 static void requeue_bios(struct pool *pool);
 
-static void check_for_space(struct pool *pool)
+static bool is_read_only_pool_mode(enum pool_mode mode)
+{
+	return (mode == PM_OUT_OF_METADATA_SPACE || mode == PM_READ_ONLY);
+}
+
+static bool is_read_only(struct pool *pool)
+{
+	return is_read_only_pool_mode(get_pool_mode(pool));
+}
+
+static void check_for_metadata_space(struct pool *pool)
+{
+	int r;
+	const char *ooms_reason = NULL;
+	dm_block_t nr_free;
+
+	r = dm_pool_get_free_metadata_block_count(pool->pmd, &nr_free);
+	if (r)
+		ooms_reason = "Could not get free metadata blocks";
+	else if (!nr_free)
+		ooms_reason = "No free metadata blocks";
+
+	if (ooms_reason && !is_read_only(pool)) {
+		DMERR("%s", ooms_reason);
+		set_pool_mode(pool, PM_OUT_OF_METADATA_SPACE);
+	}
+}
+
+static void check_for_data_space(struct pool *pool)
 {
 	int r;
 	dm_block_t nr_free;
@@ -1397,14 +1431,16 @@ static int commit(struct pool *pool)
 {
 	int r;
 
-	if (get_pool_mode(pool) >= PM_READ_ONLY)
+	if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE)
 		return -EINVAL;
 
 	r = dm_pool_commit_metadata(pool->pmd);
 	if (r)
 		metadata_operation_failed(pool, "dm_pool_commit_metadata", r);
-	else
-		check_for_space(pool);
+	else {
+		check_for_metadata_space(pool);
+		check_for_data_space(pool);
+	}
 
 	return r;
 }
@@ -1470,6 +1506,19 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
 		return r;
 	}
 
+	r = dm_pool_get_free_metadata_block_count(pool->pmd, &free_blocks);
+	if (r) {
+		metadata_operation_failed(pool, "dm_pool_get_free_metadata_block_count", r);
+		return r;
+	}
+
+	if (!free_blocks) {
+		/* Let's commit before we use up the metadata reserve. */
+		r = commit(pool);
+		if (r)
+			return r;
+	}
+
 	return 0;
 }
 
@@ -1501,6 +1550,7 @@ static blk_status_t should_error_unserviceable_bio(struct pool *pool)
 	case PM_OUT_OF_DATA_SPACE:
 		return pool->pf.error_if_no_space ? BLK_STS_NOSPC : 0;
 
+	case PM_OUT_OF_METADATA_SPACE:
 	case PM_READ_ONLY:
 	case PM_FAIL:
 		return BLK_STS_IOERR;
@@ -2464,8 +2514,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		error_retry_list(pool);
 		break;
 
+	case PM_OUT_OF_METADATA_SPACE:
 	case PM_READ_ONLY:
-		if (old_mode != new_mode)
+		if (!is_read_only_pool_mode(old_mode))
 			notify_of_pool_mode_change(pool, "read-only");
 		dm_pool_metadata_read_only(pool->pmd);
 		pool->process_bio = process_bio_read_only;
@@ -3403,6 +3454,10 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit)
 		DMINFO("%s: growing the metadata device from %llu to %llu blocks",
 		       dm_device_name(pool->pool_md),
 		       sb_metadata_dev_size, metadata_dev_size);
+
+		if (get_pool_mode(pool) == PM_OUT_OF_METADATA_SPACE)
+			set_pool_mode(pool, PM_WRITE);
+
 		r = dm_pool_resize_metadata_dev(pool->pmd, metadata_dev_size);
 		if (r) {
 			metadata_operation_failed(pool, "dm_pool_resize_metadata_dev", r);
@@ -3707,7 +3762,7 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv,
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
 
-	if (get_pool_mode(pool) >= PM_READ_ONLY) {
+	if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE) {
 		DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode",
 		      dm_device_name(pool->pool_md));
 		return -EOPNOTSUPP;
@@ -3781,6 +3836,7 @@ static void pool_status(struct dm_target *ti, status_type_t type,
 	dm_block_t nr_blocks_data;
 	dm_block_t nr_blocks_metadata;
 	dm_block_t held_root;
+	enum pool_mode mode;
 	char buf[BDEVNAME_SIZE];
 	char buf2[BDEVNAME_SIZE];
 	struct pool_c *pt = ti->private;
@@ -3851,9 +3907,10 @@ static void pool_status(struct dm_target *ti, status_type_t type,
 		else
 			DMEMIT("- ");
 
-		if (pool->pf.mode == PM_OUT_OF_DATA_SPACE)
+		mode = get_pool_mode(pool);
+		if (mode == PM_OUT_OF_DATA_SPACE)
 			DMEMIT("out_of_data_space ");
-		else if (pool->pf.mode == PM_READ_ONLY)
+		else if (is_read_only_pool_mode(mode))
 			DMEMIT("ro ");
 		else
 			DMEMIT("rw ");
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 12decdbd722d..fc65f0dedf7f 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -99,10 +99,26 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req,
 {
 	struct scatterlist sg;
 
-	sg_init_one(&sg, data, len);
-	ahash_request_set_crypt(req, &sg, NULL, len);
-
-	return crypto_wait_req(crypto_ahash_update(req), wait);
+	if (likely(!is_vmalloc_addr(data))) {
+		sg_init_one(&sg, data, len);
+		ahash_request_set_crypt(req, &sg, NULL, len);
+		return crypto_wait_req(crypto_ahash_update(req), wait);
+	} else {
+		do {
+			int r;
+			size_t this_step = min_t(size_t, len, PAGE_SIZE - offset_in_page(data));
+			flush_kernel_vmap_range((void *)data, this_step);
+			sg_init_table(&sg, 1);
+			sg_set_page(&sg, vmalloc_to_page(data), this_step, offset_in_page(data));
+			ahash_request_set_crypt(req, &sg, NULL, this_step);
+			r = crypto_wait_req(crypto_ahash_update(req), wait);
+			if (unlikely(r))
+				return r;
+			data += this_step;
+			len -= this_step;
+		} while (len);
+		return 0;
+	}
 }
 
 /*
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 94329e03001e..0b2af6e74fc3 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -1276,18 +1276,18 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
 static int resync_finish(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
+	int ret = 0;
 
 	clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
-	dlm_unlock_sync(cinfo->resync_lockres);
 
 	/*
 	 * If resync thread is interrupted so we can't say resync is finished,
 	 * another node will launch resync thread to continue.
 	 */
-	if (test_bit(MD_CLOSING, &mddev->flags))
-		return 0;
-	else
-		return resync_info_update(mddev, 0, 0);
+	if (!test_bit(MD_CLOSING, &mddev->flags))
+		ret = resync_info_update(mddev, 0, 0);
+	dlm_unlock_sync(cinfo->resync_lockres);
+	return ret;
 }
 
 static int area_resyncing(struct mddev *mddev, int direction,
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 981898049491..d6f7978b4449 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4529,11 +4529,12 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 		allow_barrier(conf);
 	}
 
+	raise_barrier(conf, 0);
 read_more:
 	/* Now schedule reads for blocks from sector_nr to last */
 	r10_bio = raid10_alloc_init_r10buf(conf);
 	r10_bio->state = 0;
-	raise_barrier(conf, sectors_done != 0);
+	raise_barrier(conf, 1);
 	atomic_set(&r10_bio->remaining, 0);
 	r10_bio->mddev = mddev;
 	r10_bio->sector = sector_nr;
@@ -4629,6 +4630,8 @@ read_more:
 	if (sector_nr <= last)
 		goto read_more;
 
+	lower_barrier(conf);
+
 	/* Now that we have done the whole section we can
 	 * update reshape_progress
 	 */
diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h
index a001808a2b77..bfb811407061 100644
--- a/drivers/md/raid5-log.h
+++ b/drivers/md/raid5-log.h
@@ -46,6 +46,11 @@ extern int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add);
 extern void ppl_quiesce(struct r5conf *conf, int quiesce);
 extern int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio);
 
+static inline bool raid5_has_log(struct r5conf *conf)
+{
+	return test_bit(MD_HAS_JOURNAL, &conf->mddev->flags);
+}
+
 static inline bool raid5_has_ppl(struct r5conf *conf)
 {
 	return test_bit(MD_HAS_PPL, &conf->mddev->flags);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 4ce0d7502fad..e4e98f47865d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -733,7 +733,7 @@ static bool stripe_can_batch(struct stripe_head *sh)
 {
 	struct r5conf *conf = sh->raid_conf;
 
-	if (conf->log || raid5_has_ppl(conf))
+	if (raid5_has_log(conf) || raid5_has_ppl(conf))
 		return false;
 	return test_bit(STRIPE_BATCH_READY, &sh->state) &&
 		!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
@@ -7737,7 +7737,7 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors)
 	sector_t newsize;
 	struct r5conf *conf = mddev->private;
 
-	if (conf->log || raid5_has_ppl(conf))
+	if (raid5_has_log(conf) || raid5_has_ppl(conf))
 		return -EINVAL;
 	sectors &= ~((sector_t)conf->chunk_sectors - 1);
 	newsize = raid5_size(mddev, sectors, mddev->raid_disks);
@@ -7788,7 +7788,7 @@ static int check_reshape(struct mddev *mddev)
 {
 	struct r5conf *conf = mddev->private;
 
-	if (conf->log || raid5_has_ppl(conf))
+	if (raid5_has_log(conf) || raid5_has_ppl(conf))
 		return -EINVAL;
 	if (mddev->delta_disks == 0 &&
 	    mddev->new_layout == mddev->layout &&