Merge tag 'block-5.6-2020-02-05' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:
 "Some later arrivals, but all fixes at this point:

   - bcache fix series (Coly)

   - Series of BFQ fixes (Paolo)

   - NVMe pull request from Keith with a few minor NVMe fixes

   - Various little tweaks"

* tag 'block-5.6-2020-02-05' of git://git.kernel.dk/linux-block: (23 commits)
  nvmet: update AEN list and array at one place
  nvmet: Fix controller use after free
  nvmet: Fix error print message at nvmet_install_queue function
  brd: check and limit max_part par
  nvme-pci: remove nvmeq->tags
  nvmet: fix dsm failure when payload does not match sgl descriptor
  nvmet: Pass lockdep expression to RCU lists
  block, bfq: clarify the goal of bfq_split_bfqq()
  block, bfq: get a ref to a group when adding it to a service tree
  block, bfq: remove ifdefs from around gets/puts of bfq groups
  block, bfq: extend incomplete name of field on_st
  block, bfq: get extra ref to prevent a queue from being freed during a group move
  block, bfq: do not insert oom queue into position tree
  block, bfq: do not plug I/O for bfq_queues with no proc refs
  bcache: check return value of prio_read()
  bcache: fix incorrect data type usage in btree_flush_write()
  bcache: add readahead cache policy options via sysfs interface
  bcache: explicity type cast in bset_bkey_last()
  bcache: fix memory corruption in bch_cache_accounting_clear()
  xen/blkfront: limit allocated memory size to actual use case
  ...

MAINTAINERS

@@ -14947,8 +14947,8 @@ S:	Maintained
 F:	drivers/mmc/host/sdhci-omap.c
 
 SECURE ENCRYPTING DEVICE (SED) OPAL DRIVER
-M:	Scott Bauer <scott.bauer@intel.com>
 M:	Jonathan Derrick <jonathan.derrick@intel.com>
+M:	Revanth Rajashekar <revanth.rajashekar@intel.com>
 L:	linux-block@vger.kernel.org
 S:	Supported
 F:	block/sed*

block/bfq-cgroup.c

@@ -332,7 +332,7 @@ static void bfqg_put(struct bfq_group *bfqg)
 		kfree(bfqg);
 }
 
-static void bfqg_and_blkg_get(struct bfq_group *bfqg)
+void bfqg_and_blkg_get(struct bfq_group *bfqg)
 {
 	/* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
 	bfqg_get(bfqg);
@@ -651,9 +651,15 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
 				false, BFQQE_PREEMPTED);
 
+	/*
+	 * get extra reference to prevent bfqq from being freed in
+	 * next possible deactivate
+	 */
+	bfqq->ref++;
+
 	if (bfq_bfqq_busy(bfqq))
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
-	else if (entity->on_st)
+	else if (entity->on_st_or_in_serv)
 		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
 	bfqg_and_blkg_put(bfqq_group(bfqq));
 
@@ -670,6 +676,8 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 
 	if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
 		bfq_schedule_dispatch(bfqd);
+	/* release extra ref taken above */
+	bfq_put_queue(bfqq);
 }
 
 /**
@@ -1398,6 +1406,10 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
 	return bfqq->bfqd->root_group;
 }
 
+void bfqg_and_blkg_get(struct bfq_group *bfqg) {}
+
+void bfqg_and_blkg_put(struct bfq_group *bfqg) {}
+
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 {
 	struct bfq_group *bfqg;

block/bfq-iosched.c

@@ -613,6 +613,10 @@ bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 		bfqq->pos_root = NULL;
 	}
 
+	/* oom_bfqq does not participate in queue merging */
+	if (bfqq == &bfqd->oom_bfqq)
+		return;
+
 	/*
 	 * bfqq cannot be merged any longer (see comments in
 	 * bfq_setup_cooperator): no point in adding bfqq into the
@@ -1055,7 +1059,7 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 
 static int bfqq_process_refs(struct bfq_queue *bfqq)
 {
-	return bfqq->ref - bfqq->allocated - bfqq->entity.on_st -
+	return bfqq->ref - bfqq->allocated - bfqq->entity.on_st_or_in_serv -
 		(bfqq->weight_counter != NULL);
 }
 
@@ -3443,6 +3447,10 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
 static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd,
 						 struct bfq_queue *bfqq)
 {
+	/* No point in idling for bfqq if it won't get requests any longer */
+	if (unlikely(!bfqq_process_refs(bfqq)))
+		return false;
+
 	return (bfqq->wr_coeff > 1 &&
 		(bfqd->wr_busy_queues <
 		 bfq_tot_busy_queues(bfqd) ||
@@ -4076,6 +4084,10 @@ static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd,
 		bfqq_sequential_and_IO_bound,
 		idling_boosts_thr;
 
+	/* No point in idling for bfqq if it won't get requests any longer */
+	if (unlikely(!bfqq_process_refs(bfqq)))
+		return false;
+
 	bfqq_sequential_and_IO_bound = !BFQQ_SEEKY(bfqq) &&
 		bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_has_short_ttime(bfqq);
 
@@ -4169,6 +4181,10 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq)
 	struct bfq_data *bfqd = bfqq->bfqd;
 	bool idling_boosts_thr_with_no_issue, idling_needed_for_service_guar;
 
+	/* No point in idling for bfqq if it won't get requests any longer */
+	if (unlikely(!bfqq_process_refs(bfqq)))
+		return false;
+
 	if (unlikely(bfqd->strict_guarantees))
 		return true;
 
@@ -4809,9 +4825,7 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 {
 	struct bfq_queue *item;
 	struct hlist_node *n;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	struct bfq_group *bfqg = bfqq_group(bfqq);
-#endif
 
 	if (bfqq->bfqd)
 		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
@@ -4884,9 +4898,7 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 		bfqq->bfqd->last_completed_rq_bfqq = NULL;
 
 	kmem_cache_free(bfq_pool, bfqq);
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	bfqg_and_blkg_put(bfqg);
-#endif
 }
 
 static void bfq_put_cooperator(struct bfq_queue *bfqq)
@@ -5967,6 +5979,8 @@ static void bfq_finish_requeue_request(struct request *rq)
 }
 
 /*
+ * Removes the association between the current task and bfqq, assuming
+ * that bic points to the bfq iocontext of the task.
  * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
  * was the last process referring to that bfqq.
  */
@@ -6374,10 +6388,10 @@ static void bfq_exit_queue(struct elevator_queue *e)
 
 	hrtimer_cancel(&bfqd->idle_slice_timer);
 
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	/* release oom-queue reference to root group */
 	bfqg_and_blkg_put(bfqd->root_group);
 
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
 #else
 	spin_lock_irq(&bfqd->lock);

block/bfq-iosched.h

@@ -150,7 +150,7 @@ struct bfq_entity {
 	 * Flag, true if the entity is on a tree (either the active or
 	 * the idle one of its service_tree) or is in service.
 	 */
-	bool on_st;
+	bool on_st_or_in_serv;
 
 	/* B-WF2Q+ start and finish timestamps [sectors/weight] */
 	u64 start, finish;
@@ -921,6 +921,7 @@ struct bfq_group {
 
 #else
 struct bfq_group {
+	struct bfq_entity entity;
 	struct bfq_sched_data sched_data;
 
 	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
@@ -984,6 +985,7 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
 struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
+void bfqg_and_blkg_get(struct bfq_group *bfqg);
 void bfqg_and_blkg_put(struct bfq_group *bfqg);
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED

block/bfq-wf2q.c

@@ -533,7 +533,9 @@ static void bfq_get_entity(struct bfq_entity *entity)
 		bfqq->ref++;
 		bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
 			     bfqq, bfqq->ref);
-	}
+	} else
+		bfqg_and_blkg_get(container_of(entity, struct bfq_group,
+					       entity));
 }
 
 /**
@@ -645,10 +647,16 @@ static void bfq_forget_entity(struct bfq_service_tree *st,
 {
 	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
 
-	entity->on_st = false;
+	entity->on_st_or_in_serv = false;
 	st->wsum -= entity->weight;
-	if (bfqq && !is_in_service)
+	if (is_in_service)
+		return;
+
+	if (bfqq)
 		bfq_put_queue(bfqq);
+	else
+		bfqg_and_blkg_put(container_of(entity, struct bfq_group,
+					       entity));
 }
 
 /**
@@ -999,7 +1007,7 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
 		 */
 		bfq_get_entity(entity);
 
-		entity->on_st = true;
+		entity->on_st_or_in_serv = true;
 	}
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
@@ -1165,7 +1173,10 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
 	struct bfq_service_tree *st;
 	bool is_in_service;
 
-	if (!entity->on_st) /* entity never activated, or already inactive */
+	if (!entity->on_st_or_in_serv) /*
+					* entity never activated, or
+					* already inactive
+					*/
 		return false;
 
 	/*
@@ -1620,7 +1631,7 @@ bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 	 * service tree either, then release the service reference to
 	 * the queue it represents (taken with bfq_get_entity).
 	 */
-	if (!in_serv_entity->on_st) {
+	if (!in_serv_entity->on_st_or_in_serv) {
 		/*
 		 * If no process is referencing in_serv_bfqq any
 		 * longer, then the service reference may be the only

drivers/block/brd.c

@@ -473,6 +473,25 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data)
 	return kobj;
 }
 
+static inline void brd_check_and_reset_par(void)
+{
+	if (unlikely(!max_part))
+		max_part = 1;
+
+	/*
+	 * make sure 'max_part' can be divided exactly by (1U << MINORBITS),
+	 * otherwise, it is possiable to get same dev_t when adding partitions.
+	 */
+	if ((1U << MINORBITS) % max_part != 0)
+		max_part = 1UL << fls(max_part);
+
+	if (max_part > DISK_MAX_PARTS) {
+		pr_info("brd: max_part can't be larger than %d, reset max_part = %d.\n",
+			DISK_MAX_PARTS, DISK_MAX_PARTS);
+		max_part = DISK_MAX_PARTS;
+	}
+}
+
 static int __init brd_init(void)
 {
 	struct brd_device *brd, *next;
@@ -496,8 +515,7 @@ static int __init brd_init(void)
 	if (register_blkdev(RAMDISK_MAJOR, "ramdisk"))
 		return -EIO;
 
-	if (unlikely(!max_part))
-		max_part = 1;
+	brd_check_and_reset_par();
 
 	for (i = 0; i < rd_nr; i++) {
 		brd = brd_alloc(i);

drivers/block/drbd/drbd_int.h

@@ -622,7 +622,7 @@ struct fifo_buffer {
 	int total; /* sum of all values */
 	int values[0];
 };
-extern struct fifo_buffer *fifo_alloc(int fifo_size);
+extern struct fifo_buffer *fifo_alloc(unsigned int fifo_size);
 
 /* flag bits per connection */
 enum {

drivers/block/drbd/drbd_nl.c

@@ -1575,7 +1575,8 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 	struct drbd_device *device;
 	struct disk_conf *new_disk_conf, *old_disk_conf;
 	struct fifo_buffer *old_plan = NULL, *new_plan = NULL;
-	int err, fifo_size;
+	int err;
+	unsigned int fifo_size;
 
 	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)

drivers/block/drbd/drbd_receiver.c

@@ -3887,7 +3887,7 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i
 	struct disk_conf *old_disk_conf = NULL, *new_disk_conf = NULL;
 	const int apv = connection->agreed_pro_version;
 	struct fifo_buffer *old_plan = NULL, *new_plan = NULL;
-	int fifo_size = 0;
+	unsigned int fifo_size = 0;
 	int err;
 
 	peer_device = conn_peer_device(connection, pi->vnr);

drivers/block/drbd/drbd_worker.c

@@ -482,11 +482,11 @@ static void fifo_add_val(struct fifo_buffer *fb, int value)
 		fb->values[i] += value;
 }
 
-struct fifo_buffer *fifo_alloc(int fifo_size)
+struct fifo_buffer *fifo_alloc(unsigned int fifo_size)
 {
 	struct fifo_buffer *fb;
 
-	fb = kzalloc(sizeof(struct fifo_buffer) + sizeof(int) * fifo_size, GFP_NOIO);
+	fb = kzalloc(struct_size(fb, values, fifo_size), GFP_NOIO);
 	if (!fb)
 		return NULL;
 

drivers/block/nbd.c

@@ -1265,6 +1265,16 @@ static int nbd_start_device(struct nbd_device *nbd)
 		args = kzalloc(sizeof(*args), GFP_KERNEL);
 		if (!args) {
 			sock_shutdown(nbd);
+			/*
+			 * If num_connections is m (2 < m),
+			 * and NO.1 ~ NO.n(1 < n < m) kzallocs are successful.
+			 * But NO.(n + 1) failed. We still have n recv threads.
+			 * So, add flush_workqueue here to prevent recv threads
+			 * dropping the last config_refs and trying to destroy
+			 * the workqueue from inside the workqueue.
+			 */
+			if (i)
+				flush_workqueue(nbd->recv_workq);
 			return -ENOMEM;
 		}
 		sk_set_memalloc(config->socks[i]->sock->sk);

drivers/block/xen-blkfront.c

@@ -151,9 +151,6 @@ MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the
 #define BLK_RING_SIZE(info)	\
 	__CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * (info)->nr_ring_pages)
 
-#define BLK_MAX_RING_SIZE	\
-	__CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * XENBUS_MAX_RING_GRANTS)
-
 /*
  * ring-ref%u i=(-1UL) would take 11 characters + 'ring-ref' is 8, so 19
  * characters are enough. Define to 20 to keep consistent with backend.
@@ -177,12 +174,12 @@ struct blkfront_ring_info {
 	unsigned int evtchn, irq;
 	struct work_struct work;
 	struct gnttab_free_callback callback;
-	struct blk_shadow shadow[BLK_MAX_RING_SIZE];
 	struct list_head indirect_pages;
 	struct list_head grants;
 	unsigned int persistent_gnts_c;
 	unsigned long shadow_free;
 	struct blkfront_info *dev_info;
+	struct blk_shadow shadow[];
 };
 
 /*
@@ -1915,7 +1912,8 @@ static int negotiate_mq(struct blkfront_info *info)
 		info->nr_rings = 1;
 
 	info->rinfo = kvcalloc(info->nr_rings,
-			       sizeof(struct blkfront_ring_info),
+			       struct_size(info->rinfo, shadow,
+					   BLK_RING_SIZE(info)),
 			       GFP_KERNEL);
 	if (!info->rinfo) {
 		xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure");

drivers/md/bcache/bcache.h

@@ -330,6 +330,9 @@ struct cached_dev {
 	 */
 	atomic_t		has_dirty;
 
+#define BCH_CACHE_READA_ALL		0
+#define BCH_CACHE_READA_META_ONLY	1
+	unsigned int		cache_readahead_policy;
 	struct bch_ratelimit	writeback_rate;
 	struct delayed_work	writeback_rate_update;
 

drivers/md/bcache/bset.h

@@ -397,7 +397,8 @@ void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *state);
 
 /* Bkey utility code */
 
-#define bset_bkey_last(i)	bkey_idx((struct bkey *) (i)->d, (i)->keys)
+#define bset_bkey_last(i)	bkey_idx((struct bkey *) (i)->d, \
+					 (unsigned int)(i)->keys)
 
 static inline struct bkey *bset_bkey_idx(struct bset *i, unsigned int idx)
 {

drivers/md/bcache/journal.c

@@ -422,7 +422,8 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list)
 static void btree_flush_write(struct cache_set *c)
 {
 	struct btree *b, *t, *btree_nodes[BTREE_FLUSH_NR];
-	unsigned int i, nr, ref_nr;
+	unsigned int i, nr;
+	int ref_nr;
 	atomic_t *fifo_front_p, *now_fifo_front_p;
 	size_t mask;
 

drivers/md/bcache/request.c

@@ -379,13 +379,20 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 		goto skip;
 
 	/*
-	 * Flag for bypass if the IO is for read-ahead or background,
-	 * unless the read-ahead request is for metadata
+	 * If the bio is for read-ahead or background IO, bypass it or
+	 * not depends on the following situations,
+	 * - If the IO is for meta data, always cache it and no bypass
+	 * - If the IO is not meta data, check dc->cache_reada_policy,
+	 *      BCH_CACHE_READA_ALL: cache it and not bypass
+	 *      BCH_CACHE_READA_META_ONLY: not cache it and bypass
+	 * That is, read-ahead request for metadata always get cached
 	 * (eg, for gfs2 or xfs).
 	 */
-	if (bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND) &&
-	    !(bio->bi_opf & (REQ_META|REQ_PRIO)))
-		goto skip;
+	if ((bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND))) {
+		if (!(bio->bi_opf & (REQ_META|REQ_PRIO)) &&
+		    (dc->cache_readahead_policy != BCH_CACHE_READA_ALL))
+			goto skip;
+	}
 
 	if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
 	    bio_sectors(bio) & (c->sb.block_size - 1)) {

drivers/md/bcache/stats.c

@@ -109,9 +109,13 @@ int bch_cache_accounting_add_kobjs(struct cache_accounting *acc,
 
 void bch_cache_accounting_clear(struct cache_accounting *acc)
 {
-	memset(&acc->total.cache_hits,
-	       0,
-	       sizeof(struct cache_stats));
+	acc->total.cache_hits = 0;
+	acc->total.cache_misses = 0;
+	acc->total.cache_bypass_hits = 0;
+	acc->total.cache_bypass_misses = 0;
+	acc->total.cache_readaheads = 0;
+	acc->total.cache_miss_collisions = 0;
+	acc->total.sectors_bypassed = 0;
 }
 
 void bch_cache_accounting_destroy(struct cache_accounting *acc)

drivers/md/bcache/super.c

@@ -609,12 +609,13 @@ int bch_prio_write(struct cache *ca, bool wait)
 	return 0;
 }
 
-static void prio_read(struct cache *ca, uint64_t bucket)
+static int prio_read(struct cache *ca, uint64_t bucket)
 {
 	struct prio_set *p = ca->disk_buckets;
 	struct bucket_disk *d = p->data + prios_per_bucket(ca), *end = d;
 	struct bucket *b;
 	unsigned int bucket_nr = 0;
+	int ret = -EIO;
 
 	for (b = ca->buckets;
 	     b < ca->buckets + ca->sb.nbuckets;
@@ -627,11 +628,15 @@ static void prio_read(struct cache *ca, uint64_t bucket)
 			prio_io(ca, bucket, REQ_OP_READ, 0);
 
 			if (p->csum !=
-			    bch_crc64(&p->magic, bucket_bytes(ca) - 8))
+			    bch_crc64(&p->magic, bucket_bytes(ca) - 8)) {
 				pr_warn("bad csum reading priorities");
+				goto out;
+			}
 
-			if (p->magic != pset_magic(&ca->sb))
+			if (p->magic != pset_magic(&ca->sb)) {
 				pr_warn("bad magic reading priorities");
+				goto out;
+			}
 
 			bucket = p->next_bucket;
 			d = p->data;
@@ -640,6 +645,10 @@ static void prio_read(struct cache *ca, uint64_t bucket)
 		b->prio = le16_to_cpu(d->prio);
 		b->gen = b->last_gc = d->gen;
 	}
+
+	ret = 0;
+out:
+	return ret;
 }
 
 /* Bcache device */
@@ -1873,8 +1882,10 @@ static int run_cache_set(struct cache_set *c)
 		j = &list_entry(journal.prev, struct journal_replay, list)->j;
 
 		err = "IO error reading priorities";
-		for_each_cache(ca, c, i)
-			prio_read(ca, j->prio_bucket[ca->sb.nr_this_dev]);
+		for_each_cache(ca, c, i) {
+			if (prio_read(ca, j->prio_bucket[ca->sb.nr_this_dev]))
+				goto err;
+		}
 
 		/*
 		 * If prio_read() fails it'll call cache_set_error and we'll

drivers/md/bcache/sysfs.c

@@ -27,6 +27,12 @@ static const char * const bch_cache_modes[] = {
 	NULL
 };
 
+static const char * const bch_reada_cache_policies[] = {
+	"all",
+	"meta-only",
+	NULL
+};
+
 /* Default is 0 ("auto") */
 static const char * const bch_stop_on_failure_modes[] = {
 	"auto",
@@ -100,6 +106,7 @@ rw_attribute(congested_write_threshold_us);
 rw_attribute(sequential_cutoff);
 rw_attribute(data_csum);
 rw_attribute(cache_mode);
+rw_attribute(readahead_cache_policy);
 rw_attribute(stop_when_cache_set_failed);
 rw_attribute(writeback_metadata);
 rw_attribute(writeback_running);
@@ -168,6 +175,11 @@ SHOW(__bch_cached_dev)
 					       bch_cache_modes,
 					       BDEV_CACHE_MODE(&dc->sb));
 
+	if (attr == &sysfs_readahead_cache_policy)
+		return bch_snprint_string_list(buf, PAGE_SIZE,
+					      bch_reada_cache_policies,
+					      dc->cache_readahead_policy);
+
 	if (attr == &sysfs_stop_when_cache_set_failed)
 		return bch_snprint_string_list(buf, PAGE_SIZE,
 					       bch_stop_on_failure_modes,
@@ -353,6 +365,15 @@ STORE(__cached_dev)
 		}
 	}
 
+	if (attr == &sysfs_readahead_cache_policy) {
+		v = __sysfs_match_string(bch_reada_cache_policies, -1, buf);
+		if (v < 0)
+			return v;
+
+		if ((unsigned int) v != dc->cache_readahead_policy)
+			dc->cache_readahead_policy = v;
+	}
+
 	if (attr == &sysfs_stop_when_cache_set_failed) {
 		v = __sysfs_match_string(bch_stop_on_failure_modes, -1, buf);
 		if (v < 0)
@@ -467,6 +488,7 @@ static struct attribute *bch_cached_dev_files[] = {
 	&sysfs_data_csum,
 #endif
 	&sysfs_cache_mode,
+	&sysfs_readahead_cache_policy,
 	&sysfs_stop_when_cache_set_failed,
 	&sysfs_writeback_metadata,
 	&sysfs_writeback_running,

drivers/nvme/host/pci.c

@@ -167,7 +167,6 @@ struct nvme_queue {
 	 /* only used for poll queues: */
 	spinlock_t cq_poll_lock ____cacheline_aligned_in_smp;
 	volatile struct nvme_completion *cqes;
-	struct blk_mq_tags **tags;
 	dma_addr_t sq_dma_addr;
 	dma_addr_t cq_dma_addr;
 	u32 __iomem *q_db;
@@ -376,29 +375,17 @@ static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 
 	WARN_ON(hctx_idx != 0);
 	WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
-	WARN_ON(nvmeq->tags);
 
 	hctx->driver_data = nvmeq;
-	nvmeq->tags = &dev->admin_tagset.tags[0];
 	return 0;
 }
 
-static void nvme_admin_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
-{
-	struct nvme_queue *nvmeq = hctx->driver_data;
-
-	nvmeq->tags = NULL;
-}
-
 static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 			  unsigned int hctx_idx)
 {
 	struct nvme_dev *dev = data;
 	struct nvme_queue *nvmeq = &dev->queues[hctx_idx + 1];
 
-	if (!nvmeq->tags)
-		nvmeq->tags = &dev->tagset.tags[hctx_idx];
-
 	WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
 	hctx->driver_data = nvmeq;
 	return 0;
@@ -948,6 +935,13 @@ static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
 		writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
 }
 
+static inline struct blk_mq_tags *nvme_queue_tagset(struct nvme_queue *nvmeq)
+{
+	if (!nvmeq->qid)
+		return nvmeq->dev->admin_tagset.tags[0];
+	return nvmeq->dev->tagset.tags[nvmeq->qid - 1];
+}
+
 static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 {
 	volatile struct nvme_completion *cqe = &nvmeq->cqes[idx];
@@ -972,7 +966,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 		return;
 	}
 
-	req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id);
+	req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id);
 	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
 	nvme_end_request(req, cqe->status, cqe->result);
 }
@@ -1572,7 +1566,6 @@ static const struct blk_mq_ops nvme_mq_admin_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_pci_complete_rq,
 	.init_hctx	= nvme_admin_init_hctx,
-	.exit_hctx      = nvme_admin_exit_hctx,
 	.init_request	= nvme_init_request,
 	.timeout	= nvme_timeout,
 };

drivers/nvme/target/core.c

@@ -129,27 +129,8 @@ static u32 nvmet_async_event_result(struct nvmet_async_event *aen)
 	return aen->event_type | (aen->event_info << 8) | (aen->log_page << 16);
 }
 
-static void nvmet_async_events_free(struct nvmet_ctrl *ctrl)
-{
-	struct nvmet_req *req;
-
-	while (1) {
-		mutex_lock(&ctrl->lock);
-		if (!ctrl->nr_async_event_cmds) {
-			mutex_unlock(&ctrl->lock);
-			return;
-		}
-
-		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
-		mutex_unlock(&ctrl->lock);
-		nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR);
-	}
-}
-
-static void nvmet_async_event_work(struct work_struct *work)
+static void nvmet_async_events_process(struct nvmet_ctrl *ctrl, u16 status)
 {
-	struct nvmet_ctrl *ctrl =
-		container_of(work, struct nvmet_ctrl, async_event_work);
 	struct nvmet_async_event *aen;
 	struct nvmet_req *req;
 
@@ -159,18 +140,41 @@ static void nvmet_async_event_work(struct work_struct *work)
 				struct nvmet_async_event, entry);
 		if (!aen || !ctrl->nr_async_event_cmds) {
 			mutex_unlock(&ctrl->lock);
-			return;
+			break;
 		}
 
 		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
-		nvmet_set_result(req, nvmet_async_event_result(aen));
+		if (status == 0)
+			nvmet_set_result(req, nvmet_async_event_result(aen));
 
 		list_del(&aen->entry);
 		kfree(aen);
 
 		mutex_unlock(&ctrl->lock);
-		nvmet_req_complete(req, 0);
+		nvmet_req_complete(req, status);
+	}
+}
+
+static void nvmet_async_events_free(struct nvmet_ctrl *ctrl)
+{
+	struct nvmet_req *req;
+
+	mutex_lock(&ctrl->lock);
+	while (ctrl->nr_async_event_cmds) {
+		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
+		mutex_unlock(&ctrl->lock);
+		nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR);
+		mutex_lock(&ctrl->lock);
 	}
+	mutex_unlock(&ctrl->lock);
+}
+
+static void nvmet_async_event_work(struct work_struct *work)
+{
+	struct nvmet_ctrl *ctrl =
+		container_of(work, struct nvmet_ctrl, async_event_work);
+
+	nvmet_async_events_process(ctrl, 0);
 }
 
 void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
@@ -555,7 +559,8 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 	} else {
 		struct nvmet_ns *old;
 
-		list_for_each_entry_rcu(old, &subsys->namespaces, dev_link) {
+		list_for_each_entry_rcu(old, &subsys->namespaces, dev_link,
+					lockdep_is_held(&subsys->lock)) {
 			BUG_ON(ns->nsid == old->nsid);
 			if (ns->nsid < old->nsid)
 				break;
@@ -752,19 +757,24 @@ static void nvmet_confirm_sq(struct percpu_ref *ref)
 
 void nvmet_sq_destroy(struct nvmet_sq *sq)
 {
+	u16 status = NVME_SC_INTERNAL | NVME_SC_DNR;
+	struct nvmet_ctrl *ctrl = sq->ctrl;
+
 	/*
 	 * If this is the admin queue, complete all AERs so that our
 	 * queue doesn't have outstanding requests on it.
 	 */
-	if (sq->ctrl && sq->ctrl->sqs && sq->ctrl->sqs[0] == sq)
-		nvmet_async_events_free(sq->ctrl);
+	if (ctrl && ctrl->sqs && ctrl->sqs[0] == sq) {
+		nvmet_async_events_process(ctrl, status);
+		nvmet_async_events_free(ctrl);
+	}
 	percpu_ref_kill_and_confirm(&sq->ref, nvmet_confirm_sq);
 	wait_for_completion(&sq->confirm_done);
 	wait_for_completion(&sq->free_done);
 	percpu_ref_exit(&sq->ref);
 
-	if (sq->ctrl) {
-		nvmet_ctrl_put(sq->ctrl);
+	if (ctrl) {
+		nvmet_ctrl_put(ctrl);
 		sq->ctrl = NULL; /* allows reusing the queue later */
 	}
 }
@@ -938,6 +948,17 @@ bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len)
 }
 EXPORT_SYMBOL_GPL(nvmet_check_data_len);
 
+bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len)
+{
+	if (unlikely(data_len > req->transfer_len)) {
+		req->error_loc = offsetof(struct nvme_common_command, dptr);
+		nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
+		return false;
+	}
+
+	return true;
+}
+
 int nvmet_req_alloc_sgl(struct nvmet_req *req)
 {
 	struct pci_dev *p2p_dev = NULL;
@@ -1172,7 +1193,8 @@ static void nvmet_setup_p2p_ns_map(struct nvmet_ctrl *ctrl,
 
 	ctrl->p2p_client = get_device(req->p2p_client);
 
-	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link,
+				lockdep_is_held(&ctrl->subsys->lock))
 		nvmet_p2pmem_ns_add_p2p(ctrl, ns);
 }
 

drivers/nvme/target/fabrics-cmd.c

@@ -109,6 +109,7 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 	u16 qid = le16_to_cpu(c->qid);
 	u16 sqsize = le16_to_cpu(c->sqsize);
 	struct nvmet_ctrl *old;
+	u16 ret;
 
 	old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
 	if (old) {
@@ -119,7 +120,8 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 	if (!sqsize) {
 		pr_warn("queue size zero!\n");
 		req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
-		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+		ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+		goto err;
 	}
 
 	/* note: convert queue size from 0's-based value to 1's-based value */
@@ -132,16 +134,19 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 	}
 
 	if (ctrl->ops->install_queue) {
-		u16 ret = ctrl->ops->install_queue(req->sq);
-
+		ret = ctrl->ops->install_queue(req->sq);
 		if (ret) {
 			pr_err("failed to install queue %d cntlid %d ret %x\n",
-				qid, ret, ctrl->cntlid);
-			return ret;
+				qid, ctrl->cntlid, ret);
+			goto err;
 		}
 	}
 
 	return 0;
+
+err:
+	req->sq->ctrl = NULL;
+	return ret;
 }
 
 static void nvmet_execute_admin_connect(struct nvmet_req *req)

drivers/nvme/target/io-cmd-bdev.c

@@ -280,7 +280,7 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req)
 
 static void nvmet_bdev_execute_dsm(struct nvmet_req *req)
 {
-	if (!nvmet_check_data_len(req, nvmet_dsm_len(req)))
+	if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req)))
 		return;
 
 	switch (le32_to_cpu(req->cmd->dsm.attributes)) {

drivers/nvme/target/io-cmd-file.c

@@ -336,7 +336,7 @@ static void nvmet_file_dsm_work(struct work_struct *w)
 
 static void nvmet_file_execute_dsm(struct nvmet_req *req)
 {
-	if (!nvmet_check_data_len(req, nvmet_dsm_len(req)))
+	if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req)))
 		return;
 	INIT_WORK(&req->f.work, nvmet_file_dsm_work);
 	schedule_work(&req->f.work);

drivers/nvme/target/nvmet.h

@@ -374,6 +374,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 		struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops);
 void nvmet_req_uninit(struct nvmet_req *req);
 bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len);
+bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len);
 void nvmet_req_complete(struct nvmet_req *req, u16 status);
 int nvmet_req_alloc_sgl(struct nvmet_req *req);
 void nvmet_req_free_sgl(struct nvmet_req *req);