Merge tag 'for-6.7/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Various fixes for the DM delay target to address regressions
   introduced during the 6.7 merge window

 - Fixes to both DM bufio and the verity target for no-sleep mode,
   to address sleeping while atomic issues

 - Update DM crypt target in response to the treewide change that
   made MAX_ORDER inclusive

* tag 'for-6.7/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm-crypt: start allocating with MAX_ORDER
  dm-verity: don't use blocking calls from tasklets
  dm-bufio: fix no-sleep mode
  dm-delay: avoid duplicate logic
  dm-delay: fix bugs introduced by kthread mode
  dm-delay: fix a race between delay_presuspend and delay_bio

6 files changed, 130 insertions, 100 deletions

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 62eb27639c9b85..f03d7dba270c52 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -254,7 +254,7 @@ enum evict_result {
 
 typedef enum evict_result (*le_predicate)(struct lru_entry *le, void *context);
 
-static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context)
+static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context, bool no_sleep)
 {
 	unsigned long tested = 0;
 	struct list_head *h = lru->cursor;
@@ -295,7 +295,8 @@ static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *con
 
 		h = h->next;
 
-		cond_resched();
+		if (!no_sleep)
+			cond_resched();
 	}
 
 	return NULL;
@@ -382,7 +383,10 @@ struct dm_buffer {
  */
 
 struct buffer_tree {
-	struct rw_semaphore lock;
+	union {
+		struct rw_semaphore lock;
+		rwlock_t spinlock;
+	} u;
 	struct rb_root root;
 } ____cacheline_aligned_in_smp;
 
@@ -393,9 +397,12 @@ struct dm_buffer_cache {
 	 * on the locks.
 	 */
 	unsigned int num_locks;
+	bool no_sleep;
 	struct buffer_tree trees[];
 };
 
+static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled);
+
 static inline unsigned int cache_index(sector_t block, unsigned int num_locks)
 {
 	return dm_hash_locks_index(block, num_locks);
@@ -403,22 +410,34 @@ static inline unsigned int cache_index(sector_t block, unsigned int num_locks)
 
 static inline void cache_read_lock(struct dm_buffer_cache *bc, sector_t block)
 {
-	down_read(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		read_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		down_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 static inline void cache_read_unlock(struct dm_buffer_cache *bc, sector_t block)
 {
-	up_read(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		read_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		up_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 static inline void cache_write_lock(struct dm_buffer_cache *bc, sector_t block)
 {
-	down_write(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		write_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		down_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 static inline void cache_write_unlock(struct dm_buffer_cache *bc, sector_t block)
 {
-	up_write(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		write_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		up_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 /*
@@ -442,18 +461,32 @@ static void lh_init(struct lock_history *lh, struct dm_buffer_cache *cache, bool
 
 static void __lh_lock(struct lock_history *lh, unsigned int index)
 {
-	if (lh->write)
-		down_write(&lh->cache->trees[index].lock);
-	else
-		down_read(&lh->cache->trees[index].lock);
+	if (lh->write) {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			write_lock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			down_write(&lh->cache->trees[index].u.lock);
+	} else {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			read_lock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			down_read(&lh->cache->trees[index].u.lock);
+	}
 }
 
 static void __lh_unlock(struct lock_history *lh, unsigned int index)
 {
-	if (lh->write)
-		up_write(&lh->cache->trees[index].lock);
-	else
-		up_read(&lh->cache->trees[index].lock);
+	if (lh->write) {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			write_unlock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			up_write(&lh->cache->trees[index].u.lock);
+	} else {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			read_unlock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			up_read(&lh->cache->trees[index].u.lock);
+	}
 }
 
 /*
@@ -502,14 +535,18 @@ static struct dm_buffer *list_to_buffer(struct list_head *l)
 	return le_to_buffer(le);
 }
 
-static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks)
+static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks, bool no_sleep)
 {
 	unsigned int i;
 
 	bc->num_locks = num_locks;
+	bc->no_sleep = no_sleep;
 
 	for (i = 0; i < bc->num_locks; i++) {
-		init_rwsem(&bc->trees[i].lock);
+		if (no_sleep)
+			rwlock_init(&bc->trees[i].u.spinlock);
+		else
+			init_rwsem(&bc->trees[i].u.lock);
 		bc->trees[i].root = RB_ROOT;
 	}
 
@@ -648,7 +685,7 @@ static struct dm_buffer *__cache_evict(struct dm_buffer_cache *bc, int list_mode
 	struct lru_entry *le;
 	struct dm_buffer *b;
 
-	le = lru_evict(&bc->lru[list_mode], __evict_pred, &w);
+	le = lru_evict(&bc->lru[list_mode], __evict_pred, &w, bc->no_sleep);
 	if (!le)
 		return NULL;
 
@@ -702,7 +739,7 @@ static void __cache_mark_many(struct dm_buffer_cache *bc, int old_mode, int new_
 	struct evict_wrapper w = {.lh = lh, .pred = pred, .context = context};
 
 	while (true) {
-		le = lru_evict(&bc->lru[old_mode], __evict_pred, &w);
+		le = lru_evict(&bc->lru[old_mode], __evict_pred, &w, bc->no_sleep);
 		if (!le)
 			break;
 
@@ -915,10 +952,11 @@ static void cache_remove_range(struct dm_buffer_cache *bc,
 {
 	unsigned int i;
 
+	BUG_ON(bc->no_sleep);
 	for (i = 0; i < bc->num_locks; i++) {
-		down_write(&bc->trees[i].lock);
+		down_write(&bc->trees[i].u.lock);
 		__remove_range(bc, &bc->trees[i].root, begin, end, pred, release);
-		up_write(&bc->trees[i].lock);
+		up_write(&bc->trees[i].u.lock);
 	}
 }
 
@@ -979,8 +1017,6 @@ struct dm_bufio_client {
 	struct dm_buffer_cache cache; /* must be last member */
 };
 
-static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled);
-
 /*----------------------------------------------------------------*/
 
 #define dm_bufio_in_request()	(!!current->bio_list)
@@ -1871,7 +1907,8 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
 	if (need_submit)
 		submit_io(b, REQ_OP_READ, read_endio);
 
-	wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
+	if (nf != NF_GET)	/* we already tested this condition above */
+		wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
 
 	if (b->read_error) {
 		int error = blk_status_to_errno(b->read_error);
@@ -2421,7 +2458,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 		r = -ENOMEM;
 		goto bad_client;
 	}
-	cache_init(&c->cache, num_locks);
+	cache_init(&c->cache, num_locks, (flags & DM_BUFIO_CLIENT_NO_SLEEP) != 0);
 
 	c->bdev = bdev;
 	c->block_size = block_size;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 6de107aff33194..2ae8560b6a14ad 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1673,7 +1673,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size)
 	unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
 	unsigned int remaining_size;
-	unsigned int order = MAX_ORDER - 1;
+	unsigned int order = MAX_ORDER;
 
 retry:
 	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index efd510984e2593..5eabdb06c6498b 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -33,7 +33,7 @@ struct delay_c {
 	struct work_struct flush_expired_bios;
 	struct list_head delayed_bios;
 	struct task_struct *worker;
-	atomic_t may_delay;
+	bool may_delay;
 
 	struct delay_class read;
 	struct delay_class write;
@@ -73,39 +73,6 @@ static inline bool delay_is_fast(struct delay_c *dc)
 	return !!dc->worker;
 }
 
-static void flush_delayed_bios_fast(struct delay_c *dc, bool flush_all)
-{
-	struct dm_delay_info *delayed, *next;
-
-	mutex_lock(&delayed_bios_lock);
-	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
-		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
-			struct bio *bio = dm_bio_from_per_bio_data(delayed,
-						sizeof(struct dm_delay_info));
-			list_del(&delayed->list);
-			dm_submit_bio_remap(bio, NULL);
-			delayed->class->ops--;
-		}
-	}
-	mutex_unlock(&delayed_bios_lock);
-}
-
-static int flush_worker_fn(void *data)
-{
-	struct delay_c *dc = data;
-
-	while (1) {
-		flush_delayed_bios_fast(dc, false);
-		if (unlikely(list_empty(&dc->delayed_bios))) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			schedule();
-		} else
-			cond_resched();
-	}
-
-	return 0;
-}
-
 static void flush_bios(struct bio *bio)
 {
 	struct bio *n;
@@ -118,36 +85,61 @@ static void flush_bios(struct bio *bio)
 	}
 }
 
-static struct bio *flush_delayed_bios(struct delay_c *dc, bool flush_all)
+static void flush_delayed_bios(struct delay_c *dc, bool flush_all)
 {
 	struct dm_delay_info *delayed, *next;
+	struct bio_list flush_bio_list;
 	unsigned long next_expires = 0;
-	unsigned long start_timer = 0;
-	struct bio_list flush_bios = { };
+	bool start_timer = false;
+	bio_list_init(&flush_bio_list);
 
 	mutex_lock(&delayed_bios_lock);
 	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
+		cond_resched();
 		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
 			struct bio *bio = dm_bio_from_per_bio_data(delayed,
 						sizeof(struct dm_delay_info));
 			list_del(&delayed->list);
-			bio_list_add(&flush_bios, bio);
+			bio_list_add(&flush_bio_list, bio);
 			delayed->class->ops--;
 			continue;
 		}
 
-		if (!start_timer) {
-			start_timer = 1;
-			next_expires = delayed->expires;
-		} else
-			next_expires = min(next_expires, delayed->expires);
+		if (!delay_is_fast(dc)) {
+			if (!start_timer) {
+				start_timer = true;
+				next_expires = delayed->expires;
+			} else {
+				next_expires = min(next_expires, delayed->expires);
+			}
+		}
 	}
 	mutex_unlock(&delayed_bios_lock);
 
 	if (start_timer)
 		queue_timeout(dc, next_expires);
 
-	return bio_list_get(&flush_bios);
+	flush_bios(bio_list_get(&flush_bio_list));
+}
+
+static int flush_worker_fn(void *data)
+{
+	struct delay_c *dc = data;
+
+	while (!kthread_should_stop()) {
+		flush_delayed_bios(dc, false);
+		mutex_lock(&delayed_bios_lock);
+		if (unlikely(list_empty(&dc->delayed_bios))) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			mutex_unlock(&delayed_bios_lock);
+			schedule();
+		} else {
+			mutex_unlock(&delayed_bios_lock);
+			cond_resched();
+		}
+	}
+
+	return 0;
 }
 
 static void flush_expired_bios(struct work_struct *work)
@@ -155,10 +147,7 @@ static void flush_expired_bios(struct work_struct *work)
 	struct delay_c *dc;
 
 	dc = container_of(work, struct delay_c, flush_expired_bios);
-	if (delay_is_fast(dc))
-		flush_delayed_bios_fast(dc, false);
-	else
-		flush_bios(flush_delayed_bios(dc, false));
+	flush_delayed_bios(dc, false);
 }
 
 static void delay_dtr(struct dm_target *ti)
@@ -177,8 +166,7 @@ static void delay_dtr(struct dm_target *ti)
 	if (dc->worker)
 		kthread_stop(dc->worker);
 
-	if (!delay_is_fast(dc))
-		mutex_destroy(&dc->timer_lock);
+	mutex_destroy(&dc->timer_lock);
 
 	kfree(dc);
 }
@@ -236,7 +224,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->private = dc;
 	INIT_LIST_HEAD(&dc->delayed_bios);
-	atomic_set(&dc->may_delay, 1);
+	mutex_init(&dc->timer_lock);
+	dc->may_delay = true;
 	dc->argc = argc;
 
 	ret = delay_class_ctr(ti, &dc->read, argv);
@@ -282,12 +271,12 @@ out:
 					    "dm-delay-flush-worker");
 		if (IS_ERR(dc->worker)) {
 			ret = PTR_ERR(dc->worker);
+			dc->worker = NULL;
 			goto bad;
 		}
 	} else {
 		timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
 		INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
-		mutex_init(&dc->timer_lock);
 		dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
 		if (!dc->kdelayd_wq) {
 			ret = -EINVAL;
@@ -312,7 +301,7 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	struct dm_delay_info *delayed;
 	unsigned long expires = 0;
 
-	if (!c->delay || !atomic_read(&dc->may_delay))
+	if (!c->delay)
 		return DM_MAPIO_REMAPPED;
 
 	delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info));
@@ -321,6 +310,10 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	delayed->expires = expires = jiffies + msecs_to_jiffies(c->delay);
 
 	mutex_lock(&delayed_bios_lock);
+	if (unlikely(!dc->may_delay)) {
+		mutex_unlock(&delayed_bios_lock);
+		return DM_MAPIO_REMAPPED;
+	}
 	c->ops++;
 	list_add_tail(&delayed->list, &dc->delayed_bios);
 	mutex_unlock(&delayed_bios_lock);
@@ -337,21 +330,20 @@ static void delay_presuspend(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	atomic_set(&dc->may_delay, 0);
+	mutex_lock(&delayed_bios_lock);
+	dc->may_delay = false;
+	mutex_unlock(&delayed_bios_lock);
 
-	if (delay_is_fast(dc))
-		flush_delayed_bios_fast(dc, true);
-	else {
+	if (!delay_is_fast(dc))
 		del_timer_sync(&dc->delay_timer);
-		flush_bios(flush_delayed_bios(dc, true));
-	}
+	flush_delayed_bios(dc, true);
 }
 
 static void delay_resume(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	atomic_set(&dc->may_delay, 1);
+	dc->may_delay = true;
 }
 
 static int delay_map(struct dm_target *ti, struct bio *bio)
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 3ef9f018da60ce..2099c755119e37 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -185,7 +185,7 @@ static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io,
 {
 	if (unlikely(verity_hash(v, verity_io_hash_req(v, io),
 				 data, 1 << v->data_dev_block_bits,
-				 verity_io_real_digest(v, io))))
+				 verity_io_real_digest(v, io), true)))
 		return 0;
 
 	return memcmp(verity_io_real_digest(v, io), want_digest,
@@ -386,7 +386,7 @@ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io,
 	/* Always re-validate the corrected block against the expected hash */
 	r = verity_hash(v, verity_io_hash_req(v, io), fio->output,
 			1 << v->data_dev_block_bits,
-			verity_io_real_digest(v, io));
+			verity_io_real_digest(v, io), true);
 	if (unlikely(r < 0))
 		return r;
 
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 26adcfea030229..e115fcfe723c98 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -135,20 +135,21 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req,
  * Wrapper for crypto_ahash_init, which handles verity salting.
  */
 static int verity_hash_init(struct dm_verity *v, struct ahash_request *req,
-				struct crypto_wait *wait)
+				struct crypto_wait *wait, bool may_sleep)
 {
 	int r;
 
 	ahash_request_set_tfm(req, v->tfm);
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP |
-					CRYPTO_TFM_REQ_MAY_BACKLOG,
-					crypto_req_done, (void *)wait);
+	ahash_request_set_callback(req,
+		may_sleep ? CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG : 0,
+		crypto_req_done, (void *)wait);
 	crypto_init_wait(wait);
 
 	r = crypto_wait_req(crypto_ahash_init(req), wait);
 
 	if (unlikely(r < 0)) {
-		DMERR("crypto_ahash_init failed: %d", r);
+		if (r != -ENOMEM)
+			DMERR("crypto_ahash_init failed: %d", r);
 		return r;
 	}
 
@@ -179,12 +180,12 @@ out:
 }
 
 int verity_hash(struct dm_verity *v, struct ahash_request *req,
-		const u8 *data, size_t len, u8 *digest)
+		const u8 *data, size_t len, u8 *digest, bool may_sleep)
 {
 	int r;
 	struct crypto_wait wait;
 
-	r = verity_hash_init(v, req, &wait);
+	r = verity_hash_init(v, req, &wait, may_sleep);
 	if (unlikely(r < 0))
 		goto out;
 
@@ -322,7 +323,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io,
 
 		r = verity_hash(v, verity_io_hash_req(v, io),
 				data, 1 << v->hash_dev_block_bits,
-				verity_io_real_digest(v, io));
+				verity_io_real_digest(v, io), !io->in_tasklet);
 		if (unlikely(r < 0))
 			goto release_ret_r;
 
@@ -556,7 +557,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 			continue;
 		}
 
-		r = verity_hash_init(v, req, &wait);
+		r = verity_hash_init(v, req, &wait, !io->in_tasklet);
 		if (unlikely(r < 0))
 			return r;
 
@@ -652,7 +653,7 @@ static void verity_tasklet(unsigned long data)
 
 	io->in_tasklet = true;
 	err = verity_verify_io(io);
-	if (err == -EAGAIN) {
+	if (err == -EAGAIN || err == -ENOMEM) {
 		/* fallback to retrying with work-queue */
 		INIT_WORK(&io->work, verity_work);
 		queue_work(io->v->verify_wq, &io->work);
@@ -1033,7 +1034,7 @@ static int verity_alloc_zero_digest(struct dm_verity *v)
 		goto out;
 
 	r = verity_hash(v, req, zero_data, 1 << v->data_dev_block_bits,
-			v->zero_digest);
+			v->zero_digest, true);
 
 out:
 	kfree(req);
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index 2f555b4203679a..f96f4e281ee4ac 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -128,7 +128,7 @@ extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 					      u8 *data, size_t len));
 
 extern int verity_hash(struct dm_verity *v, struct ahash_request *req,
-		       const u8 *data, size_t len, u8 *digest);
+		       const u8 *data, size_t len, u8 *digest, bool may_sleep);
 
 extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
 				 sector_t block, u8 *digest, bool *is_zero);