Merge tag 'vfs-6.6-merge-2' of ssh://gitolite.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull filesystem freezing updates from Darrick Wong:

New code for 6.6:

 * Allow the kernel to initiate a freeze of a filesystem.  The kernel
   and userspace can both hold a freeze on a filesystem at the same
   time; the freeze is not lifted until /both/ holders lift it.  This
   will enable us to fix a longstanding bug in XFS online fsck.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Message-Id: <20230822182604.GB11286@frogsfrogsfrogs>
Signed-off-by: Christian Brauner <brauner@kernel.org>

7 files changed, 97 insertions, 62 deletions

diff --git a/block/bdev.c b/block/bdev.c
index a20263fa27a462..f3b13aa1b7d428 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -231,9 +231,9 @@ int freeze_bdev(struct block_device *bdev)
 	if (!sb)
 		goto sync;
 	if (sb->s_op->freeze_super)
-		error = sb->s_op->freeze_super(sb);
+		error = sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE);
 	else
-		error = freeze_super(sb);
+		error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
 	deactivate_super(sb);
 
 	if (error) {
@@ -274,9 +274,9 @@ int thaw_bdev(struct block_device *bdev)
 		goto out;
 
 	if (sb->s_op->thaw_super)
-		error = sb->s_op->thaw_super(sb);
+		error = sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE);
 	else
-		error = thaw_super(sb);
+		error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
 	if (error)
 		bdev->bd_fsfreeze_count++;
 	else
diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c
index 2a67d3fb63e5ce..7fabc883e39f1c 100644
--- a/block/blk-crypto-profile.c
+++ b/block/blk-crypto-profile.c
@@ -79,7 +79,14 @@ int blk_crypto_profile_init(struct blk_crypto_profile *profile,
 	unsigned int slot_hashtable_size;
 
 	memset(profile, 0, sizeof(*profile));
-	init_rwsem(&profile->lock);
+
+	/*
+	 * profile->lock of an underlying device can nest inside profile->lock
+	 * of a device-mapper device, so use a dynamic lock class to avoid
+	 * false-positive lockdep reports.
+	 */
+	lockdep_register_key(&profile->lockdep_key);
+	__init_rwsem(&profile->lock, "&profile->lock", &profile->lockdep_key);
 
 	if (num_slots == 0)
 		return 0;
@@ -89,7 +96,7 @@ int blk_crypto_profile_init(struct blk_crypto_profile *profile,
 	profile->slots = kvcalloc(num_slots, sizeof(profile->slots[0]),
 				  GFP_KERNEL);
 	if (!profile->slots)
-		return -ENOMEM;
+		goto err_destroy;
 
 	profile->num_slots = num_slots;
 
@@ -435,6 +442,7 @@ void blk_crypto_profile_destroy(struct blk_crypto_profile *profile)
 {
 	if (!profile)
 		return;
+	lockdep_unregister_key(&profile->lockdep_key);
 	kvfree(profile->slot_hashtable);
 	kvfree_sensitive(profile->slots,
 			 sizeof(profile->slots[0]) * profile->num_slots);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index dba392cf22bec6..8220517c2d67da 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -189,7 +189,7 @@ static void blk_flush_complete_seq(struct request *rq,
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
 		spin_lock(&q->requeue_lock);
-		list_add_tail(&rq->queuelist, &q->flush_list);
+		list_add(&rq->queuelist, &q->requeue_list);
 		spin_unlock(&q->requeue_lock);
 		blk_mq_kick_requeue_list(q);
 		break;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5504719b970d59..d50b1d62a3d923 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -328,8 +328,24 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(blk_rq_init);
 
+/* Set start and alloc time when the allocated request is actually used */
+static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns)
+{
+	if (blk_mq_need_time_stamp(rq))
+		rq->start_time_ns = ktime_get_ns();
+	else
+		rq->start_time_ns = 0;
+
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+	if (blk_queue_rq_alloc_time(rq->q))
+		rq->alloc_time_ns = alloc_time_ns ?: rq->start_time_ns;
+	else
+		rq->alloc_time_ns = 0;
+#endif
+}
+
 static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
-		struct blk_mq_tags *tags, unsigned int tag, u64 alloc_time_ns)
+		struct blk_mq_tags *tags, unsigned int tag)
 {
 	struct blk_mq_ctx *ctx = data->ctx;
 	struct blk_mq_hw_ctx *hctx = data->hctx;
@@ -356,14 +372,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	}
 	rq->timeout = 0;
 
-	if (blk_mq_need_time_stamp(rq))
-		rq->start_time_ns = ktime_get_ns();
-	else
-		rq->start_time_ns = 0;
 	rq->part = NULL;
-#ifdef CONFIG_BLK_RQ_ALLOC_TIME
-	rq->alloc_time_ns = alloc_time_ns;
-#endif
 	rq->io_start_time_ns = 0;
 	rq->stats_sectors = 0;
 	rq->nr_phys_segments = 0;
@@ -393,8 +402,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 }
 
 static inline struct request *
-__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
-		u64 alloc_time_ns)
+__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 {
 	unsigned int tag, tag_offset;
 	struct blk_mq_tags *tags;
@@ -413,7 +421,7 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
 		tag = tag_offset + i;
 		prefetch(tags->static_rqs[tag]);
 		tag_mask &= ~(1UL << i);
-		rq = blk_mq_rq_ctx_init(data, tags, tag, alloc_time_ns);
+		rq = blk_mq_rq_ctx_init(data, tags, tag);
 		rq_list_add(data->cached_rq, rq);
 		nr++;
 	}
@@ -474,9 +482,11 @@ retry:
 	 * Try batched alloc if we want more than 1 tag.
 	 */
 	if (data->nr_tags > 1) {
-		rq = __blk_mq_alloc_requests_batch(data, alloc_time_ns);
-		if (rq)
+		rq = __blk_mq_alloc_requests_batch(data);
+		if (rq) {
+			blk_mq_rq_time_init(rq, alloc_time_ns);
 			return rq;
+		}
 		data->nr_tags = 1;
 	}
 
@@ -499,8 +509,9 @@ retry:
 		goto retry;
 	}
 
-	return blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag,
-					alloc_time_ns);
+	rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag);
+	blk_mq_rq_time_init(rq, alloc_time_ns);
+	return rq;
 }
 
 static struct request *blk_mq_rq_cache_fill(struct request_queue *q,
@@ -555,6 +566,7 @@ static struct request *blk_mq_alloc_cached_request(struct request_queue *q,
 			return NULL;
 
 		plug->cached_rq = rq_list_next(rq);
+		blk_mq_rq_time_init(rq, 0);
 	}
 
 	rq->cmd_flags = opf;
@@ -656,8 +668,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	tag = blk_mq_get_tag(&data);
 	if (tag == BLK_MQ_NO_TAG)
 		goto out_queue_exit;
-	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
-					alloc_time_ns);
+	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag);
+	blk_mq_rq_time_init(rq, alloc_time_ns);
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
@@ -2896,6 +2908,7 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 	plug->cached_rq = rq_list_next(rq);
 	rq_qos_throttle(q, *bio);
 
+	blk_mq_rq_time_init(rq, 0);
 	rq->cmd_flags = (*bio)->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
 	return rq;
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 0f9f97cdddd99c..619ee41a51cc8c 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -442,7 +442,6 @@ struct blk_revalidate_zone_args {
 	unsigned long	*conv_zones_bitmap;
 	unsigned long	*seq_zones_wlock;
 	unsigned int	nr_zones;
-	sector_t	zone_sectors;
 	sector_t	sector;
 };
 
@@ -456,38 +455,34 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 	struct gendisk *disk = args->disk;
 	struct request_queue *q = disk->queue;
 	sector_t capacity = get_capacity(disk);
+	sector_t zone_sectors = q->limits.chunk_sectors;
+
+	/* Check for bad zones and holes in the zone report */
+	if (zone->start != args->sector) {
+		pr_warn("%s: Zone gap at sectors %llu..%llu\n",
+			disk->disk_name, args->sector, zone->start);
+		return -ENODEV;
+	}
+
+	if (zone->start >= capacity || !zone->len) {
+		pr_warn("%s: Invalid zone start %llu, length %llu\n",
+			disk->disk_name, zone->start, zone->len);
+		return -ENODEV;
+	}
 
 	/*
 	 * All zones must have the same size, with the exception on an eventual
 	 * smaller last zone.
 	 */
-	if (zone->start == 0) {
-		if (zone->len == 0 || !is_power_of_2(zone->len)) {
-			pr_warn("%s: Invalid zoned device with non power of two zone size (%llu)\n",
-				disk->disk_name, zone->len);
-			return -ENODEV;
-		}
-
-		args->zone_sectors = zone->len;
-		args->nr_zones = (capacity + zone->len - 1) >> ilog2(zone->len);
-	} else if (zone->start + args->zone_sectors < capacity) {
-		if (zone->len != args->zone_sectors) {
+	if (zone->start + zone->len < capacity) {
+		if (zone->len != zone_sectors) {
 			pr_warn("%s: Invalid zoned device with non constant zone size\n",
 				disk->disk_name);
 			return -ENODEV;
 		}
-	} else {
-		if (zone->len > args->zone_sectors) {
-			pr_warn("%s: Invalid zoned device with larger last zone size\n",
-				disk->disk_name);
-			return -ENODEV;
-		}
-	}
-
-	/* Check for holes in the zone report */
-	if (zone->start != args->sector) {
-		pr_warn("%s: Zone gap at sectors %llu..%llu\n",
-			disk->disk_name, args->sector, zone->start);
+	} else if (zone->len > zone_sectors) {
+		pr_warn("%s: Invalid zoned device with larger last zone size\n",
+			disk->disk_name);
 		return -ENODEV;
 	}
 
@@ -526,11 +521,13 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
  * @disk:	Target disk
  * @update_driver_data:	Callback to update driver data on the frozen disk
  *
- * Helper function for low-level device drivers to (re) allocate and initialize
- * a disk request queue zone bitmaps. This functions should normally be called
- * within the disk ->revalidate method for blk-mq based drivers.  For BIO based
- * drivers only q->nr_zones needs to be updated so that the sysfs exposed value
- * is correct.
+ * Helper function for low-level device drivers to check and (re) allocate and
+ * initialize a disk request queue zone bitmaps. This functions should normally
+ * be called within the disk ->revalidate method for blk-mq based drivers.
+ * Before calling this function, the device driver must already have set the
+ * device zone size (chunk_sector limit) and the max zone append limit.
+ * For BIO based drivers, this function cannot be used. BIO based device drivers
+ * only need to set disk->nr_zones so that the sysfs exposed value is correct.
  * If the @update_driver_data callback function is not NULL, the callback is
  * executed with the device request queue frozen after all zones have been
  * checked.
@@ -539,9 +536,9 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 			      void (*update_driver_data)(struct gendisk *disk))
 {
 	struct request_queue *q = disk->queue;
-	struct blk_revalidate_zone_args args = {
-		.disk		= disk,
-	};
+	sector_t zone_sectors = q->limits.chunk_sectors;
+	sector_t capacity = get_capacity(disk);
+	struct blk_revalidate_zone_args args = { };
 	unsigned int noio_flag;
 	int ret;
 
@@ -550,13 +547,31 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 	if (WARN_ON_ONCE(!queue_is_mq(q)))
 		return -EIO;
 
-	if (!get_capacity(disk))
-		return -EIO;
+	if (!capacity)
+		return -ENODEV;
+
+	/*
+	 * Checks that the device driver indicated a valid zone size and that
+	 * the max zone append limit is set.
+	 */
+	if (!zone_sectors || !is_power_of_2(zone_sectors)) {
+		pr_warn("%s: Invalid non power of two zone size (%llu)\n",
+			disk->disk_name, zone_sectors);
+		return -ENODEV;
+	}
+
+	if (!q->limits.max_zone_append_sectors) {
+		pr_warn("%s: Invalid 0 maximum zone append limit\n",
+			disk->disk_name);
+		return -ENODEV;
+	}
 
 	/*
 	 * Ensure that all memory allocations in this context are done as if
 	 * GFP_NOIO was specified.
 	 */
+	args.disk = disk;
+	args.nr_zones = (capacity + zone_sectors - 1) >> ilog2(zone_sectors);
 	noio_flag = memalloc_noio_save();
 	ret = disk->fops->report_zones(disk, 0, UINT_MAX,
 				       blk_revalidate_zone_cb, &args);
@@ -570,7 +585,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 	 * If zones where reported, make sure that the entire disk capacity
 	 * has been checked.
 	 */
-	if (ret > 0 && args.sector != get_capacity(disk)) {
+	if (ret > 0 && args.sector != capacity) {
 		pr_warn("%s: Missing zones from sector %llu\n",
 			disk->disk_name, args.sector);
 		ret = -ENODEV;
@@ -583,7 +598,6 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 	 */
 	blk_mq_freeze_queue(q);
 	if (ret > 0) {
-		blk_queue_chunk_sectors(q, args.zone_sectors);
 		disk->nr_zones = args.nr_zones;
 		swap(disk->seq_zones_wlock, args.seq_zones_wlock);
 		swap(disk->conv_zones_bitmap, args.conv_zones_bitmap);
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 6aa5daf7ae32f7..02a916ba62ee75 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -176,7 +176,7 @@ static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio,
 	 * zoned writes, start searching from the start of a zone.
 	 */
 	if (blk_rq_is_seq_zoned_write(rq))
-		pos -= round_down(pos, rq->q->limits.chunk_sectors);
+		pos = round_down(pos, rq->q->limits.chunk_sectors);
 
 	while (node) {
 		rq = rb_entry_rq(node);
diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c
index ed222b9c901bbf..50692109541295 100644
--- a/block/partitions/amiga.c
+++ b/block/partitions/amiga.c
@@ -90,7 +90,7 @@ int amiga_partition(struct parsed_partitions *state)
 	}
 	blk = be32_to_cpu(rdb->rdb_PartitionList);
 	put_dev_sector(sect);
-	for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) {
+	for (part = 1; (s32) blk>0 && part<=16; part++, put_dev_sector(sect)) {
 		/* Read in terms partition table understands */
 		if (check_mul_overflow(blk, (sector_t) blksize, &blk)) {
 			pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n",