Merge branch 'tip/x86/cpu'

The Lunarlake patches rely on the new VFM stuff.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>

13 files changed, 368 insertions, 288 deletions

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index e322cef6596b..558d8e670566 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -29,10 +29,7 @@
 
 /*
  * Each block ramdisk device has a xarray brd_pages of pages that stores
- * the pages containing the block device's contents. A brd page's ->index is
- * its offset in PAGE_SIZE units. This is similar to, but in no way connected
- * with, the kernel's pagecache or buffer cache (which sit above our block
- * device).
+ * the pages containing the block device's contents.
  */
 struct brd_device {
 	int			brd_number;
@@ -51,15 +48,7 @@ struct brd_device {
  */
 static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
 {
-	pgoff_t idx;
-	struct page *page;
-
-	idx = sector >> PAGE_SECTORS_SHIFT; /* sector to page index */
-	page = xa_load(&brd->brd_pages, idx);
-
-	BUG_ON(page && page->index != idx);
-
-	return page;
+	return xa_load(&brd->brd_pages, sector >> PAGE_SECTORS_SHIFT);
 }
 
 /*
@@ -67,8 +56,8 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
  */
 static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp)
 {
-	pgoff_t idx;
-	struct page *page, *cur;
+	pgoff_t idx = sector >> PAGE_SECTORS_SHIFT;
+	struct page *page;
 	int ret = 0;
 
 	page = brd_lookup_page(brd, sector);
@@ -80,23 +69,16 @@ static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp)
 		return -ENOMEM;
 
 	xa_lock(&brd->brd_pages);
-
-	idx = sector >> PAGE_SECTORS_SHIFT;
-	page->index = idx;
-
-	cur = __xa_cmpxchg(&brd->brd_pages, idx, NULL, page, gfp);
-
-	if (unlikely(cur)) {
-		__free_page(page);
-		ret = xa_err(cur);
-		if (!ret && (cur->index != idx))
-			ret = -EIO;
-	} else {
+	ret = __xa_insert(&brd->brd_pages, idx, page, gfp);
+	if (!ret)
 		brd->brd_nr_pages++;
-	}
-
 	xa_unlock(&brd->brd_pages);
 
+	if (ret < 0) {
+		__free_page(page);
+		if (ret == -EBUSY)
+			ret = 0;
+	}
 	return ret;
 }
 
@@ -240,6 +222,23 @@ out:
 	return err;
 }
 
+static void brd_do_discard(struct brd_device *brd, sector_t sector, u32 size)
+{
+	sector_t aligned_sector = (sector + PAGE_SECTORS) & ~PAGE_SECTORS;
+	struct page *page;
+
+	size -= (aligned_sector - sector) * SECTOR_SIZE;
+	xa_lock(&brd->brd_pages);
+	while (size >= PAGE_SIZE && aligned_sector < rd_size * 2) {
+		page = __xa_erase(&brd->brd_pages, aligned_sector >> PAGE_SECTORS_SHIFT);
+		if (page)
+			__free_page(page);
+		aligned_sector += PAGE_SECTORS;
+		size -= PAGE_SIZE;
+	}
+	xa_unlock(&brd->brd_pages);
+}
+
 static void brd_submit_bio(struct bio *bio)
 {
 	struct brd_device *brd = bio->bi_bdev->bd_disk->private_data;
@@ -247,6 +246,12 @@ static void brd_submit_bio(struct bio *bio)
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 
+	if (unlikely(op_is_discard(bio->bi_opf))) {
+		brd_do_discard(brd, sector, bio->bi_iter.bi_size);
+		bio_endio(bio);
+		return;
+	}
+
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 		int err;
@@ -327,6 +332,9 @@ static int brd_alloc(int i)
 		 *  is harmless)
 		 */
 		.physical_block_size	= PAGE_SIZE,
+		.max_hw_discard_sectors	= UINT_MAX,
+		.max_discard_segments	= 1,
+		.discard_granularity	= PAGE_SIZE,
 	};
 
 	list_for_each_entry(brd, &brd_devices, brd_list)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 28a95fd366fe..93780f41646b 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -445,9 +445,9 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
 
 	if (rw == ITER_SOURCE)
-		ret = call_write_iter(file, &cmd->iocb, &iter);
+		ret = file->f_op->write_iter(&cmd->iocb, &iter);
 	else
-		ret = call_read_iter(file, &cmd->iocb, &iter);
+		ret = file->f_op->read_iter(&cmd->iocb, &iter);
 
 	lo_rw_aio_do_completion(cmd);
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 9d4ec9273bf9..22a79a62cc4e 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -222,7 +222,7 @@ static ssize_t pid_show(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
 	struct gendisk *disk = dev_to_disk(dev);
-	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
+	struct nbd_device *nbd = disk->private_data;
 
 	return sprintf(buf, "%d\n", nbd->pid);
 }
@@ -236,7 +236,7 @@ static ssize_t backend_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct gendisk *disk = dev_to_disk(dev);
-	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
+	struct nbd_device *nbd = disk->private_data;
 
 	return sprintf(buf, "%s\n", nbd->backend ?: "");
 }
@@ -588,7 +588,10 @@ static inline int was_interrupted(int result)
 	return result == -ERESTARTSYS || result == -EINTR;
 }
 
-/* always call with the tx_lock held */
+/*
+ * Returns BLK_STS_RESOURCE if the caller should retry after a delay. Returns
+ * -EAGAIN if the caller should requeue @cmd. Returns -EIO if sending failed.
+ */
 static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
@@ -598,13 +601,15 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)};
 	struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)};
 	struct iov_iter from;
-	unsigned long size = blk_rq_bytes(req);
 	struct bio *bio;
 	u64 handle;
 	u32 type;
 	u32 nbd_cmd_flags = 0;
 	int sent = nsock->sent, skip = 0;
 
+	lockdep_assert_held(&cmd->lock);
+	lockdep_assert_held(&nsock->tx_lock);
+
 	iov_iter_kvec(&from, ITER_SOURCE, &iov, 1, sizeof(request));
 
 	type = req_to_nbd_cmd_type(req);
@@ -644,7 +649,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	request.type = htonl(type | nbd_cmd_flags);
 	if (type != NBD_CMD_FLUSH) {
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
-		request.len = htonl(size);
+		request.len = htonl(blk_rq_bytes(req));
 	}
 	handle = nbd_cmd_handle(cmd);
 	request.cookie = cpu_to_be64(handle);
@@ -669,7 +674,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 				nsock->sent = sent;
 			}
 			set_bit(NBD_CMD_REQUEUED, &cmd->flags);
-			return BLK_STS_RESOURCE;
+			return (__force int)BLK_STS_RESOURCE;
 		}
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 			"Send control failed (result %d)\n", result);
@@ -710,7 +715,7 @@ send_pages:
 					nsock->pending = req;
 					nsock->sent = sent;
 					set_bit(NBD_CMD_REQUEUED, &cmd->flags);
-					return BLK_STS_RESOURCE;
+					return (__force int)BLK_STS_RESOURCE;
 				}
 				dev_err(disk_to_dev(nbd->disk),
 					"Send data failed (result %d)\n",
@@ -1007,7 +1012,7 @@ static int wait_for_reconnect(struct nbd_device *nbd)
 	return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags);
 }
 
-static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
+static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
 	struct nbd_device *nbd = cmd->nbd;
@@ -1015,18 +1020,20 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 	struct nbd_sock *nsock;
 	int ret;
 
+	lockdep_assert_held(&cmd->lock);
+
 	config = nbd_get_config_unlocked(nbd);
 	if (!config) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Socks array is empty\n");
-		return -EINVAL;
+		return BLK_STS_IOERR;
 	}
 
 	if (index >= config->num_connections) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Attempted send on invalid socket\n");
 		nbd_config_put(nbd);
-		return -EINVAL;
+		return BLK_STS_IOERR;
 	}
 	cmd->status = BLK_STS_OK;
 again:
@@ -1049,7 +1056,7 @@ again:
 			 */
 			sock_shutdown(nbd);
 			nbd_config_put(nbd);
-			return -EIO;
+			return BLK_STS_IOERR;
 		}
 		goto again;
 	}
@@ -1062,7 +1069,7 @@ again:
 	blk_mq_start_request(req);
 	if (unlikely(nsock->pending && nsock->pending != req)) {
 		nbd_requeue_cmd(cmd);
-		ret = 0;
+		ret = BLK_STS_OK;
 		goto out;
 	}
 	/*
@@ -1081,19 +1088,19 @@ again:
 				    "Request send failed, requeueing\n");
 		nbd_mark_nsock_dead(nbd, nsock, 1);
 		nbd_requeue_cmd(cmd);
-		ret = 0;
+		ret = BLK_STS_OK;
 	}
 out:
 	mutex_unlock(&nsock->tx_lock);
 	nbd_config_put(nbd);
-	return ret;
+	return ret < 0 ? BLK_STS_IOERR : (__force blk_status_t)ret;
 }
 
 static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 			const struct blk_mq_queue_data *bd)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
-	int ret;
+	blk_status_t ret;
 
 	/*
 	 * Since we look at the bio's to send the request over the network we
@@ -1113,10 +1120,6 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * appropriate.
 	 */
 	ret = nbd_handle_cmd(cmd, hctx->queue_num);
-	if (ret < 0)
-		ret = BLK_STS_IOERR;
-	else if (!ret)
-		ret = BLK_STS_OK;
 	mutex_unlock(&cmd->lock);
 
 	return ret;
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index ed33cf7192d2..eb023d267369 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -225,6 +225,10 @@ static unsigned long g_cache_size;
 module_param_named(cache_size, g_cache_size, ulong, 0444);
 MODULE_PARM_DESC(mbps, "Cache size in MiB for memory-backed device. Default: 0 (none)");
 
+static bool g_fua = true;
+module_param_named(fua, g_fua, bool, 0444);
+MODULE_PARM_DESC(zoned, "Enable/disable FUA support when cache_size is used. Default: true");
+
 static unsigned int g_mbps;
 module_param_named(mbps, g_mbps, uint, 0444);
 MODULE_PARM_DESC(mbps, "Limit maximum bandwidth (in MiB/s). Default: 0 (no limit)");
@@ -253,6 +257,11 @@ static unsigned int g_zone_max_active;
 module_param_named(zone_max_active, g_zone_max_active, uint, 0444);
 MODULE_PARM_DESC(zone_max_active, "Maximum number of active zones when block device is zoned. Default: 0 (no limit)");
 
+static int g_zone_append_max_sectors = INT_MAX;
+module_param_named(zone_append_max_sectors, g_zone_append_max_sectors, int, 0444);
+MODULE_PARM_DESC(zone_append_max_sectors,
+		 "Maximum size of a zone append command (in 512B sectors). Specify 0 for zone append emulation");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -404,13 +413,25 @@ static int nullb_update_nr_hw_queues(struct nullb_device *dev,
 static int nullb_apply_submit_queues(struct nullb_device *dev,
 				     unsigned int submit_queues)
 {
-	return nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues);
+	int ret;
+
+	mutex_lock(&lock);
+	ret = nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues);
+	mutex_unlock(&lock);
+
+	return ret;
 }
 
 static int nullb_apply_poll_queues(struct nullb_device *dev,
 				   unsigned int poll_queues)
 {
-	return nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues);
+	int ret;
+
+	mutex_lock(&lock);
+	ret = nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues);
+	mutex_unlock(&lock);
+
+	return ret;
 }
 
 NULLB_DEVICE_ATTR(size, ulong, NULL);
@@ -436,10 +457,12 @@ NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
 NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
+NULLB_DEVICE_ATTR(zone_append_max_sectors, uint, NULL);
 NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tags, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL);
+NULLB_DEVICE_ATTR(fua, bool, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -457,28 +480,31 @@ static ssize_t nullb_device_power_store(struct config_item *item,
 	if (ret < 0)
 		return ret;
 
+	ret = count;
+	mutex_lock(&lock);
 	if (!dev->power && newp) {
 		if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags))
-			return count;
+			goto out;
+
 		ret = null_add_dev(dev);
 		if (ret) {
 			clear_bit(NULLB_DEV_FL_UP, &dev->flags);
-			return ret;
+			goto out;
 		}
 
 		set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 		dev->power = newp;
 	} else if (dev->power && !newp) {
 		if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) {
-			mutex_lock(&lock);
 			dev->power = newp;
 			null_del_dev(dev->nullb);
-			mutex_unlock(&lock);
 		}
 		clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 	}
 
-	return count;
+out:
+	mutex_unlock(&lock);
+	return ret;
 }
 
 CONFIGFS_ATTR(nullb_device_, power);
@@ -580,12 +606,14 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_nr_conv,
 	&nullb_device_attr_zone_max_open,
 	&nullb_device_attr_zone_max_active,
+	&nullb_device_attr_zone_append_max_sectors,
 	&nullb_device_attr_zone_readonly,
 	&nullb_device_attr_zone_offline,
 	&nullb_device_attr_virt_boundary,
 	&nullb_device_attr_no_sched,
 	&nullb_device_attr_shared_tags,
 	&nullb_device_attr_shared_tag_bitmap,
+	&nullb_device_attr_fua,
 	NULL,
 };
 
@@ -664,14 +692,14 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
 	return snprintf(page, PAGE_SIZE,
-			"badblocks,blocking,blocksize,cache_size,"
+			"badblocks,blocking,blocksize,cache_size,fua,"
 			"completion_nsec,discard,home_node,hw_queue_depth,"
 			"irqmode,max_sectors,mbps,memory_backed,no_sched,"
 			"poll_queues,power,queue_mode,shared_tag_bitmap,"
 			"shared_tags,size,submit_queues,use_per_node_hctx,"
 			"virt_boundary,zoned,zone_capacity,zone_max_active,"
 			"zone_max_open,zone_nr_conv,zone_offline,zone_readonly,"
-			"zone_size\n");
+			"zone_size,zone_append_max_sectors\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -751,10 +779,13 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->zone_nr_conv = g_zone_nr_conv;
 	dev->zone_max_open = g_zone_max_open;
 	dev->zone_max_active = g_zone_max_active;
+	dev->zone_append_max_sectors = g_zone_append_max_sectors;
 	dev->virt_boundary = g_virt_boundary;
 	dev->no_sched = g_no_sched;
 	dev->shared_tags = g_shared_tags;
 	dev->shared_tag_bitmap = g_shared_tag_bitmap;
+	dev->fua = g_fua;
+
 	return dev;
 }
 
@@ -1151,7 +1182,7 @@ blk_status_t null_handle_discard(struct nullb_device *dev,
 	return BLK_STS_OK;
 }
 
-static int null_handle_flush(struct nullb *nullb)
+static blk_status_t null_handle_flush(struct nullb *nullb)
 {
 	int err;
 
@@ -1168,7 +1199,7 @@ static int null_handle_flush(struct nullb *nullb)
 
 	WARN_ON(!radix_tree_empty(&nullb->dev->cache));
 	spin_unlock_irq(&nullb->lock);
-	return err;
+	return errno_to_blk_status(err);
 }
 
 static int null_transfer(struct nullb *nullb, struct page *page,
@@ -1202,11 +1233,11 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 	return err;
 }
 
-static int null_handle_rq(struct nullb_cmd *cmd)
+static blk_status_t null_handle_rq(struct nullb_cmd *cmd)
 {
 	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb *nullb = cmd->nq->dev->nullb;
-	int err;
+	int err = 0;
 	unsigned int len;
 	sector_t sector = blk_rq_pos(rq);
 	struct req_iterator iter;
@@ -1218,15 +1249,13 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
 				     op_is_write(req_op(rq)), sector,
 				     rq->cmd_flags & REQ_FUA);
-		if (err) {
-			spin_unlock_irq(&nullb->lock);
-			return err;
-		}
+		if (err)
+			break;
 		sector += len >> SECTOR_SHIFT;
 	}
 	spin_unlock_irq(&nullb->lock);
 
-	return 0;
+	return errno_to_blk_status(err);
 }
 
 static inline blk_status_t null_handle_throttled(struct nullb_cmd *cmd)
@@ -1273,8 +1302,8 @@ static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd,
 
 	if (op == REQ_OP_DISCARD)
 		return null_handle_discard(dev, sector, nr_sectors);
-	return errno_to_blk_status(null_handle_rq(cmd));
 
+	return null_handle_rq(cmd);
 }
 
 static void nullb_zero_read_cmd_buffer(struct nullb_cmd *cmd)
@@ -1343,7 +1372,7 @@ static void null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
 	blk_status_t sts;
 
 	if (op == REQ_OP_FLUSH) {
-		cmd->error = errno_to_blk_status(null_handle_flush(nullb));
+		cmd->error = null_handle_flush(nullb);
 		goto out;
 	}
 
@@ -1912,21 +1941,18 @@ static int null_add_dev(struct nullb_device *dev)
 
 	if (dev->cache_size > 0) {
 		set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
-		blk_queue_write_cache(nullb->q, true, true);
+		blk_queue_write_cache(nullb->q, true, dev->fua);
 	}
 
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 
-	mutex_lock(&lock);
 	rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
-	if (rv < 0) {
-		mutex_unlock(&lock);
+	if (rv < 0)
 		goto out_cleanup_disk;
-	}
+
 	nullb->index = rv;
 	dev->index = rv;
-	mutex_unlock(&lock);
 
 	if (config_item_name(&dev->group.cg_item)) {
 		/* Use configfs dir name as the device name */
@@ -1955,9 +1981,7 @@ static int null_add_dev(struct nullb_device *dev)
 	if (rv)
 		goto out_ida_free;
 
-	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
-	mutex_unlock(&lock);
 
 	pr_info("disk %s created\n", nullb->disk_name);
 
@@ -2006,7 +2030,9 @@ static int null_create_dev(void)
 	if (!dev)
 		return -ENOMEM;
 
+	mutex_lock(&lock);
 	ret = null_add_dev(dev);
+	mutex_unlock(&lock);
 	if (ret) {
 		null_free_dev(dev);
 		return ret;
@@ -2113,10 +2139,13 @@ static void __exit null_exit(void)
 
 	if (tag_set.ops)
 		blk_mq_free_tag_set(&tag_set);
+
+	mutex_destroy(&lock);
 }
 
 module_init(null_init);
 module_exit(null_exit);
 
 MODULE_AUTHOR("Jens Axboe <axboe@kernel.dk>");
+MODULE_DESCRIPTION("multi queue aware block test driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 477b97746823..3234e6c85eed 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -82,6 +82,7 @@ struct nullb_device {
 	unsigned int zone_nr_conv; /* number of conventional zones */
 	unsigned int zone_max_open; /* max number of open zones */
 	unsigned int zone_max_active; /* max number of active zones */
+	unsigned int zone_append_max_sectors; /* Max sectors per zone append command */
 	unsigned int submit_queues; /* number of submission queues */
 	unsigned int prev_submit_queues; /* number of submission queues before change */
 	unsigned int poll_queues; /* number of IOPOLL submission queues */
@@ -104,6 +105,7 @@ struct nullb_device {
 	bool no_sched; /* no IO scheduler for the device */
 	bool shared_tags; /* share tag set between devices for blk-mq */
 	bool shared_tag_bitmap; /* use hostwide shared tags */
+	bool fua; /* Support FUA */
 };
 
 struct nullb {
diff --git a/drivers/block/null_blk/trace.h b/drivers/block/null_blk/trace.h
index ef2d05d5f0df..82b8f6a5e5f0 100644
--- a/drivers/block/null_blk/trace.h
+++ b/drivers/block/null_blk/trace.h
@@ -36,7 +36,12 @@ TRACE_EVENT(nullb_zone_op,
 	    TP_ARGS(cmd, zone_no, zone_cond),
 	    TP_STRUCT__entry(
 		__array(char, disk, DISK_NAME_LEN)
-		__field(enum req_op, op)
+		/*
+		 * __field() uses is_signed_type(). is_signed_type() does not
+		 * support bitwise types. Use __field_struct() instead because
+		 * it does not use is_signed_type().
+		 */
+		__field_struct(enum req_op, op)
 		__field(unsigned int, zone_no)
 		__field(unsigned int, zone_cond)
 	    ),
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 1689e2584104..5b5a63adacc1 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -9,6 +9,8 @@
 #undef pr_fmt
 #define pr_fmt(fmt)	"null_blk: " fmt
 
+#define NULL_ZONE_INVALID_WP	((sector_t)-1)
+
 static inline sector_t mb_to_sects(unsigned long mb)
 {
 	return ((sector_t)mb * SZ_1M) >> SECTOR_SHIFT;
@@ -19,18 +21,6 @@ static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
 	return sect >> ilog2(dev->zone_size_sects);
 }
 
-static inline void null_lock_zone_res(struct nullb_device *dev)
-{
-	if (dev->need_zone_res_mgmt)
-		spin_lock_irq(&dev->zone_res_lock);
-}
-
-static inline void null_unlock_zone_res(struct nullb_device *dev)
-{
-	if (dev->need_zone_res_mgmt)
-		spin_unlock_irq(&dev->zone_res_lock);
-}
-
 static inline void null_init_zone_lock(struct nullb_device *dev,
 				       struct nullb_zone *zone)
 {
@@ -103,6 +93,11 @@ int null_init_zoned_dev(struct nullb_device *dev,
 			dev->zone_nr_conv);
 	}
 
+	dev->zone_append_max_sectors =
+		min(ALIGN_DOWN(dev->zone_append_max_sectors,
+			       dev->blocksize >> SECTOR_SHIFT),
+		    zone_capacity_sects);
+
 	/* Max active zones has to be < nbr of seq zones in order to be enforceable */
 	if (dev->zone_max_active >= dev->nr_zones - dev->zone_nr_conv) {
 		dev->zone_max_active = 0;
@@ -154,7 +149,7 @@ int null_init_zoned_dev(struct nullb_device *dev,
 
 	lim->zoned = true;
 	lim->chunk_sectors = dev->zone_size_sects;
-	lim->max_zone_append_sectors = dev->zone_size_sects;
+	lim->max_zone_append_sectors = dev->zone_append_max_sectors;
 	lim->max_open_zones = dev->zone_max_open;
 	lim->max_active_zones = dev->zone_max_active;
 	return 0;
@@ -163,11 +158,16 @@ int null_init_zoned_dev(struct nullb_device *dev,
 int null_register_zoned_dev(struct nullb *nullb)
 {
 	struct request_queue *q = nullb->q;
+	struct gendisk *disk = nullb->disk;
 
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
-	nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0);
-	return blk_revalidate_disk_zones(nullb->disk, NULL);
+	disk->nr_zones = bdev_nr_zones(disk->part0);
+
+	pr_info("%s: using %s zone append\n",
+		disk->disk_name,
+		queue_emulates_zone_append(q) ? "emulated" : "native");
+
+	return blk_revalidate_disk_zones(disk);
 }
 
 void null_free_zoned_dev(struct nullb_device *dev)
@@ -241,35 +241,6 @@ size_t null_zone_valid_read_len(struct nullb *nullb,
 	return (zone->wp - sector) << SECTOR_SHIFT;
 }
 
-static blk_status_t __null_close_zone(struct nullb_device *dev,
-				      struct nullb_zone *zone)
-{
-	switch (zone->cond) {
-	case BLK_ZONE_COND_CLOSED:
-		/* close operation on closed is not an error */
-		return BLK_STS_OK;
-	case BLK_ZONE_COND_IMP_OPEN:
-		dev->nr_zones_imp_open--;
-		break;
-	case BLK_ZONE_COND_EXP_OPEN:
-		dev->nr_zones_exp_open--;
-		break;
-	case BLK_ZONE_COND_EMPTY:
-	case BLK_ZONE_COND_FULL:
-	default:
-		return BLK_STS_IOERR;
-	}
-
-	if (zone->wp == zone->start) {
-		zone->cond = BLK_ZONE_COND_EMPTY;
-	} else {
-		zone->cond = BLK_ZONE_COND_CLOSED;
-		dev->nr_zones_closed++;
-	}
-
-	return BLK_STS_OK;
-}
-
 static void null_close_imp_open_zone(struct nullb_device *dev)
 {
 	struct nullb_zone *zone;
@@ -286,7 +257,13 @@ static void null_close_imp_open_zone(struct nullb_device *dev)
 			zno = dev->zone_nr_conv;
 
 		if (zone->cond == BLK_ZONE_COND_IMP_OPEN) {
-			__null_close_zone(dev, zone);
+			dev->nr_zones_imp_open--;
+			if (zone->wp == zone->start) {
+				zone->cond = BLK_ZONE_COND_EMPTY;
+			} else {
+				zone->cond = BLK_ZONE_COND_CLOSED;
+				dev->nr_zones_closed++;
+			}
 			dev->imp_close_zone_no = zno;
 			return;
 		}
@@ -374,73 +351,73 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 
 	null_lock_zone(dev, zone);
 
-	if (zone->cond == BLK_ZONE_COND_FULL ||
-	    zone->cond == BLK_ZONE_COND_READONLY ||
-	    zone->cond == BLK_ZONE_COND_OFFLINE) {
-		/* Cannot write to the zone */
-		ret = BLK_STS_IOERR;
-		goto unlock;
-	}
-
 	/*
-	 * Regular writes must be at the write pointer position.
-	 * Zone append writes are automatically issued at the write
-	 * pointer and the position returned using the request or BIO
-	 * sector.
+	 * Regular writes must be at the write pointer position. Zone append
+	 * writes are automatically issued at the write pointer and the position
+	 * returned using the request sector. Note that we do not check the zone
+	 * condition because for FULL, READONLY and OFFLINE zones, the sector
+	 * check against the zone write pointer will always result in failing
+	 * the command.
 	 */
 	if (append) {
+		if (WARN_ON_ONCE(!dev->zone_append_max_sectors) ||
+		    zone->wp == NULL_ZONE_INVALID_WP) {
+			ret = BLK_STS_IOERR;
+			goto unlock_zone;
+		}
 		sector = zone->wp;
 		blk_mq_rq_from_pdu(cmd)->__sector = sector;
-	} else if (sector != zone->wp) {
-		ret = BLK_STS_IOERR;
-		goto unlock;
 	}
 
-	if (zone->wp + nr_sectors > zone->start + zone->capacity) {
+	if (sector != zone->wp ||
+	    zone->wp + nr_sectors > zone->start + zone->capacity) {
 		ret = BLK_STS_IOERR;
-		goto unlock;
+		goto unlock_zone;
 	}
 
 	if (zone->cond == BLK_ZONE_COND_CLOSED ||
 	    zone->cond == BLK_ZONE_COND_EMPTY) {
-		null_lock_zone_res(dev);
+		if (dev->need_zone_res_mgmt) {
+			spin_lock(&dev->zone_res_lock);
 
-		ret = null_check_zone_resources(dev, zone);
-		if (ret != BLK_STS_OK) {
-			null_unlock_zone_res(dev);
-			goto unlock;
-		}
-		if (zone->cond == BLK_ZONE_COND_CLOSED) {
-			dev->nr_zones_closed--;
-			dev->nr_zones_imp_open++;
-		} else if (zone->cond == BLK_ZONE_COND_EMPTY) {
-			dev->nr_zones_imp_open++;
-		}
+			ret = null_check_zone_resources(dev, zone);
+			if (ret != BLK_STS_OK) {
+				spin_unlock(&dev->zone_res_lock);
+				goto unlock_zone;
+			}
+			if (zone->cond == BLK_ZONE_COND_CLOSED) {
+				dev->nr_zones_closed--;
+				dev->nr_zones_imp_open++;
+			} else if (zone->cond == BLK_ZONE_COND_EMPTY) {
+				dev->nr_zones_imp_open++;
+			}
 
-		if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
-			zone->cond = BLK_ZONE_COND_IMP_OPEN;
+			spin_unlock(&dev->zone_res_lock);
+		}
 
-		null_unlock_zone_res(dev);
+		zone->cond = BLK_ZONE_COND_IMP_OPEN;
 	}
 
 	ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
 	if (ret != BLK_STS_OK)
-		goto unlock;
+		goto unlock_zone;
 
 	zone->wp += nr_sectors;
 	if (zone->wp == zone->start + zone->capacity) {
-		null_lock_zone_res(dev);
-		if (zone->cond == BLK_ZONE_COND_EXP_OPEN)
-			dev->nr_zones_exp_open--;
-		else if (zone->cond == BLK_ZONE_COND_IMP_OPEN)
-			dev->nr_zones_imp_open--;
+		if (dev->need_zone_res_mgmt) {
+			spin_lock(&dev->zone_res_lock);
+			if (zone->cond == BLK_ZONE_COND_EXP_OPEN)
+				dev->nr_zones_exp_open--;
+			else if (zone->cond == BLK_ZONE_COND_IMP_OPEN)
+				dev->nr_zones_imp_open--;
+			spin_unlock(&dev->zone_res_lock);
+		}
 		zone->cond = BLK_ZONE_COND_FULL;
-		null_unlock_zone_res(dev);
 	}
 
 	ret = BLK_STS_OK;
 
-unlock:
+unlock_zone:
 	null_unlock_zone(dev, zone);
 
 	return ret;
@@ -454,54 +431,100 @@ static blk_status_t null_open_zone(struct nullb_device *dev,
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
-	null_lock_zone_res(dev);
-
 	switch (zone->cond) {
 	case BLK_ZONE_COND_EXP_OPEN:
-		/* open operation on exp open is not an error */
-		goto unlock;
+		/* Open operation on exp open is not an error */
+		return BLK_STS_OK;
 	case BLK_ZONE_COND_EMPTY:
-		ret = null_check_zone_resources(dev, zone);
-		if (ret != BLK_STS_OK)
-			goto unlock;
-		break;
 	case BLK_ZONE_COND_IMP_OPEN:
-		dev->nr_zones_imp_open--;
-		break;
 	case BLK_ZONE_COND_CLOSED:
-		ret = null_check_zone_resources(dev, zone);
-		if (ret != BLK_STS_OK)
-			goto unlock;
-		dev->nr_zones_closed--;
 		break;
 	case BLK_ZONE_COND_FULL:
 	default:
-		ret = BLK_STS_IOERR;
-		goto unlock;
+		return BLK_STS_IOERR;
 	}
 
-	zone->cond = BLK_ZONE_COND_EXP_OPEN;
-	dev->nr_zones_exp_open++;
+	if (dev->need_zone_res_mgmt) {
+		spin_lock(&dev->zone_res_lock);
 
-unlock:
-	null_unlock_zone_res(dev);
+		switch (zone->cond) {
+		case BLK_ZONE_COND_EMPTY:
+			ret = null_check_zone_resources(dev, zone);
+			if (ret != BLK_STS_OK) {
+				spin_unlock(&dev->zone_res_lock);
+				return ret;
+			}
+			break;
+		case BLK_ZONE_COND_IMP_OPEN:
+			dev->nr_zones_imp_open--;
+			break;
+		case BLK_ZONE_COND_CLOSED:
+			ret = null_check_zone_resources(dev, zone);
+			if (ret != BLK_STS_OK) {
+				spin_unlock(&dev->zone_res_lock);
+				return ret;
+			}
+			dev->nr_zones_closed--;
+			break;
+		default:
+			break;
+		}
 
-	return ret;
+		dev->nr_zones_exp_open++;
+
+		spin_unlock(&dev->zone_res_lock);
+	}
+
+	zone->cond = BLK_ZONE_COND_EXP_OPEN;
+
+	return BLK_STS_OK;
 }
 
 static blk_status_t null_close_zone(struct nullb_device *dev,
 				    struct nullb_zone *zone)
 {
-	blk_status_t ret;
-
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
-	null_lock_zone_res(dev);
-	ret = __null_close_zone(dev, zone);
-	null_unlock_zone_res(dev);
+	switch (zone->cond) {
+	case BLK_ZONE_COND_CLOSED:
+		/* close operation on closed is not an error */
+		return BLK_STS_OK;
+	case BLK_ZONE_COND_IMP_OPEN:
+	case BLK_ZONE_COND_EXP_OPEN:
+		break;
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_FULL:
+	default:
+		return BLK_STS_IOERR;
+	}
+
+	if (dev->need_zone_res_mgmt) {
+		spin_lock(&dev->zone_res_lock);
 
-	return ret;
+		switch (zone->cond) {
+		case BLK_ZONE_COND_IMP_OPEN:
+			dev->nr_zones_imp_open--;
+			break;
+		case BLK_ZONE_COND_EXP_OPEN:
+			dev->nr_zones_exp_open--;
+			break;
+		default:
+			break;
+		}
+
+		if (zone->wp > zone->start)
+			dev->nr_zones_closed++;
+
+		spin_unlock(&dev->zone_res_lock);
+	}
+
+	if (zone->wp == zone->start)
+		zone->cond = BLK_ZONE_COND_EMPTY;
+	else
+		zone->cond = BLK_ZONE_COND_CLOSED;
+
+	return BLK_STS_OK;
 }
 
 static blk_status_t null_finish_zone(struct nullb_device *dev,
@@ -512,41 +535,47 @@ static blk_status_t null_finish_zone(struct nullb_device *dev,
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
-	null_lock_zone_res(dev);
+	if (dev->need_zone_res_mgmt) {
+		spin_lock(&dev->zone_res_lock);
 
-	switch (zone->cond) {
-	case BLK_ZONE_COND_FULL:
-		/* finish operation on full is not an error */
-		goto unlock;
-	case BLK_ZONE_COND_EMPTY:
-		ret = null_check_zone_resources(dev, zone);
-		if (ret != BLK_STS_OK)
-			goto unlock;
-		break;
-	case BLK_ZONE_COND_IMP_OPEN:
-		dev->nr_zones_imp_open--;
-		break;
-	case BLK_ZONE_COND_EXP_OPEN:
-		dev->nr_zones_exp_open--;
-		break;
-	case BLK_ZONE_COND_CLOSED:
-		ret = null_check_zone_resources(dev, zone);
-		if (ret != BLK_STS_OK)
-			goto unlock;
-		dev->nr_zones_closed--;
-		break;
-	default:
-		ret = BLK_STS_IOERR;
-		goto unlock;
+		switch (zone->cond) {
+		case BLK_ZONE_COND_FULL:
+			/* Finish operation on full is not an error */
+			spin_unlock(&dev->zone_res_lock);
+			return BLK_STS_OK;
+		case BLK_ZONE_COND_EMPTY:
+			ret = null_check_zone_resources(dev, zone);
+			if (ret != BLK_STS_OK) {
+				spin_unlock(&dev->zone_res_lock);
+				return ret;
+			}
+			break;
+		case BLK_ZONE_COND_IMP_OPEN:
+			dev->nr_zones_imp_open--;
+			break;
+		case BLK_ZONE_COND_EXP_OPEN:
+			dev->nr_zones_exp_open--;
+			break;
+		case BLK_ZONE_COND_CLOSED:
+			ret = null_check_zone_resources(dev, zone);
+			if (ret != BLK_STS_OK) {
+				spin_unlock(&dev->zone_res_lock);
+				return ret;
+			}
+			dev->nr_zones_closed--;
+			break;
+		default:
+			spin_unlock(&dev->zone_res_lock);
+			return BLK_STS_IOERR;
+		}
+
+		spin_unlock(&dev->zone_res_lock);
 	}
 
 	zone->cond = BLK_ZONE_COND_FULL;
 	zone->wp = zone->start + zone->len;
 
-unlock:
-	null_unlock_zone_res(dev);
-
-	return ret;
+	return BLK_STS_OK;
 }
 
 static blk_status_t null_reset_zone(struct nullb_device *dev,
@@ -555,34 +584,33 @@ static blk_status_t null_reset_zone(struct nullb_device *dev,
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
-	null_lock_zone_res(dev);
+	if (dev->need_zone_res_mgmt) {
+		spin_lock(&dev->zone_res_lock);
 
-	switch (zone->cond) {
-	case BLK_ZONE_COND_EMPTY:
-		/* reset operation on empty is not an error */
-		null_unlock_zone_res(dev);
-		return BLK_STS_OK;
-	case BLK_ZONE_COND_IMP_OPEN:
-		dev->nr_zones_imp_open--;
-		break;
-	case BLK_ZONE_COND_EXP_OPEN:
-		dev->nr_zones_exp_open--;
-		break;
-	case BLK_ZONE_COND_CLOSED:
-		dev->nr_zones_closed--;
-		break;
-	case BLK_ZONE_COND_FULL:
-		break;
-	default:
-		null_unlock_zone_res(dev);
-		return BLK_STS_IOERR;
+		switch (zone->cond) {
+		case BLK_ZONE_COND_IMP_OPEN:
+			dev->nr_zones_imp_open--;
+			break;
+		case BLK_ZONE_COND_EXP_OPEN:
+			dev->nr_zones_exp_open--;
+			break;
+		case BLK_ZONE_COND_CLOSED:
+			dev->nr_zones_closed--;
+			break;
+		case BLK_ZONE_COND_EMPTY:
+		case BLK_ZONE_COND_FULL:
+			break;
+		default:
+			spin_unlock(&dev->zone_res_lock);
+			return BLK_STS_IOERR;
+		}
+
+		spin_unlock(&dev->zone_res_lock);
 	}
 
 	zone->cond = BLK_ZONE_COND_EMPTY;
 	zone->wp = zone->start;
 
-	null_unlock_zone_res(dev);
-
 	if (dev->memory_backed)
 		return null_handle_discard(dev, zone->start, zone->len);
 
@@ -711,7 +739,7 @@ static void null_set_zone_cond(struct nullb_device *dev,
 		    zone->cond != BLK_ZONE_COND_OFFLINE)
 			null_finish_zone(dev, zone);
 		zone->cond = cond;
-		zone->wp = (sector_t)-1;
+		zone->wp = NULL_ZONE_INVALID_WP;
 	}
 
 	null_unlock_zone(dev, zone);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 21728e9ea5c3..8a2ce8070010 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2215,6 +2215,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
 		}
 		dev_info(ddev, "%lukB available on disc\n", lba << 1);
 	}
+	set_blocksize(bdev_file, CD_FRAMESIZE);
 
 	return 0;
 
@@ -2278,11 +2279,6 @@ static int pkt_open(struct gendisk *disk, blk_mode_t mode)
 		ret = pkt_open_dev(pd, mode & BLK_OPEN_WRITE);
 		if (ret)
 			goto out_dec;
-		/*
-		 * needed here as well, since ext2 (among others) may change
-		 * the blocksize at mount time
-		 */
-		set_blocksize(disk->part0, CD_FRAMESIZE);
 	}
 	mutex_unlock(&ctl_mutex);
 	mutex_unlock(&pktcdvd_mutex);
@@ -2526,7 +2522,6 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	__module_get(THIS_MODULE);
 
 	pd->bdev_file = bdev_file;
-	set_blocksize(file_bdev(bdev_file), CD_FRAMESIZE);
 
 	atomic_set(&pd->cdrw.pending_bios, 0);
 	pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name);
diff --git a/drivers/block/rnbd/rnbd-srv-trace.h b/drivers/block/rnbd/rnbd-srv-trace.h
index 8dedf73bdd28..89d0bcb17195 100644
--- a/drivers/block/rnbd/rnbd-srv-trace.h
+++ b/drivers/block/rnbd/rnbd-srv-trace.h
@@ -27,7 +27,7 @@ DECLARE_EVENT_CLASS(rnbd_srv_link_class,
 
 	TP_fast_assign(
 		__entry->qdepth = srv->queue_depth;
-		__assign_str(sessname, srv->sessname);
+		__assign_str(sessname);
 	),
 
 	TP_printk("sessname: %s qdepth: %d",
@@ -85,7 +85,7 @@ TRACE_EVENT(process_rdma,
 	),
 
 	TP_fast_assign(
-		__assign_str(sessname, srv->sessname);
+		__assign_str(sessname);
 		__entry->dir = id->dir;
 		__entry->ver = srv->ver;
 		__entry->device_id = le32_to_cpu(msg->device_id);
@@ -130,7 +130,7 @@ TRACE_EVENT(process_msg_sess_info,
 		__entry->proto_ver = srv->ver;
 		__entry->clt_ver = msg->ver;
 		__entry->srv_ver = RNBD_PROTO_VER_MAJOR;
-		__assign_str(sessname, srv->sessname);
+		__assign_str(sessname);
 	),
 
 	TP_printk("Session %s using proto-ver %d (clt-ver: %d, srv-ver: %d)",
@@ -165,8 +165,8 @@ TRACE_EVENT(process_msg_open,
 
 	TP_fast_assign(
 		__entry->access_mode = msg->access_mode;
-		__assign_str(sessname, srv->sessname);
-		__assign_str(dev_name, msg->dev_name);
+		__assign_str(sessname);
+		__assign_str(dev_name);
 	),
 
 	TP_printk("Open message received: session='%s' path='%s' access_mode=%s",
@@ -189,7 +189,7 @@ TRACE_EVENT(process_msg_close,
 
 	TP_fast_assign(
 		__entry->device_id = le32_to_cpu(msg->device_id);
-		__assign_str(sessname, srv->sessname);
+		__assign_str(sessname);
 	),
 
 	TP_printk("Close message received: session='%s' device id='%d'",
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index bea3d5cf8a83..4e159948c912 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -221,7 +221,7 @@ static int ublk_get_nr_zones(const struct ublk_device *ub)
 
 static int ublk_revalidate_disk_zones(struct ublk_device *ub)
 {
-	return blk_revalidate_disk_zones(ub->ub_disk, NULL);
+	return blk_revalidate_disk_zones(ub->ub_disk);
 }
 
 static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
@@ -249,8 +249,7 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
-	blk_queue_required_elevator_features(ub->ub_disk->queue,
-					     ELEVATOR_F_ZBD_SEQ_WRITE);
+
 	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
 }
 
@@ -2177,7 +2176,9 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 		.max_hw_sectors		= p->max_sectors,
 		.chunk_sectors		= p->chunk_sectors,
 		.virt_boundary_mask	= p->virt_boundary_mask,
-
+		.max_segments		= USHRT_MAX,
+		.max_segment_size	= UINT_MAX,
+		.dma_alignment		= 3,
 	};
 	struct gendisk *disk;
 	int ret = -EINVAL;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 42dea7601d87..2351f411fa46 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -1543,7 +1543,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	 */
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) {
 		blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue);
-		err = blk_revalidate_disk_zones(vblk->disk, NULL);
+		err = blk_revalidate_disk_zones(vblk->disk);
 		if (err)
 			goto out_cleanup_disk;
 	}
@@ -1658,7 +1658,6 @@ static struct virtio_driver virtio_blk = {
 	.feature_table_legacy		= features_legacy,
 	.feature_table_size_legacy	= ARRAY_SIZE(features_legacy),
 	.driver.name			= KBUILD_MODNAME,
-	.driver.owner			= THIS_MODULE,
 	.id_table			= id_table,
 	.probe				= virtblk_probe,
 	.remove				= virtblk_remove,
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index f0639df6cd18..3acd7006ad2c 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -426,11 +426,10 @@ static void reset_bdev(struct zram *zram)
 	if (!zram->backing_dev)
 		return;
 
-	fput(zram->bdev_file);
 	/* hope filp_close flush all of IO */
 	filp_close(zram->backing_dev, NULL);
 	zram->backing_dev = NULL;
-	zram->bdev_file = NULL;
+	zram->bdev = NULL;
 	zram->disk->fops = &zram_devops;
 	kvfree(zram->bitmap);
 	zram->bitmap = NULL;
@@ -473,10 +472,8 @@ static ssize_t backing_dev_store(struct device *dev,
 	size_t sz;
 	struct file *backing_dev = NULL;
 	struct inode *inode;
-	struct address_space *mapping;
 	unsigned int bitmap_sz;
 	unsigned long nr_pages, *bitmap = NULL;
-	struct file *bdev_file = NULL;
 	int err;
 	struct zram *zram = dev_to_zram(dev);
 
@@ -497,15 +494,14 @@ static ssize_t backing_dev_store(struct device *dev,
 	if (sz > 0 && file_name[sz - 1] == '\n')
 		file_name[sz - 1] = 0x00;
 
-	backing_dev = filp_open(file_name, O_RDWR|O_LARGEFILE, 0);
+	backing_dev = filp_open(file_name, O_RDWR | O_LARGEFILE | O_EXCL, 0);
 	if (IS_ERR(backing_dev)) {
 		err = PTR_ERR(backing_dev);
 		backing_dev = NULL;
 		goto out;
 	}
 
-	mapping = backing_dev->f_mapping;
-	inode = mapping->host;
+	inode = backing_dev->f_mapping->host;
 
 	/* Support only block device in this moment */
 	if (!S_ISBLK(inode->i_mode)) {
@@ -513,14 +509,6 @@ static ssize_t backing_dev_store(struct device *dev,
 		goto out;
 	}
 
-	bdev_file = bdev_file_open_by_dev(inode->i_rdev,
-				BLK_OPEN_READ | BLK_OPEN_WRITE, zram, NULL);
-	if (IS_ERR(bdev_file)) {
-		err = PTR_ERR(bdev_file);
-		bdev_file = NULL;
-		goto out;
-	}
-
 	nr_pages = i_size_read(inode) >> PAGE_SHIFT;
 	bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long);
 	bitmap = kvzalloc(bitmap_sz, GFP_KERNEL);
@@ -531,7 +519,7 @@ static ssize_t backing_dev_store(struct device *dev,
 
 	reset_bdev(zram);
 
-	zram->bdev_file = bdev_file;
+	zram->bdev = I_BDEV(inode);
 	zram->backing_dev = backing_dev;
 	zram->bitmap = bitmap;
 	zram->nr_pages = nr_pages;
@@ -544,9 +532,6 @@ static ssize_t backing_dev_store(struct device *dev,
 out:
 	kvfree(bitmap);
 
-	if (bdev_file)
-		fput(bdev_file);
-
 	if (backing_dev)
 		filp_close(backing_dev, NULL);
 
@@ -587,7 +572,7 @@ static void read_from_bdev_async(struct zram *zram, struct page *page,
 {
 	struct bio *bio;
 
-	bio = bio_alloc(file_bdev(zram->bdev_file), 1, parent->bi_opf, GFP_NOIO);
+	bio = bio_alloc(zram->bdev, 1, parent->bi_opf, GFP_NOIO);
 	bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
 	__bio_add_page(bio, page, PAGE_SIZE, 0);
 	bio_chain(bio, parent);
@@ -703,7 +688,7 @@ static ssize_t writeback_store(struct device *dev,
 			continue;
 		}
 
-		bio_init(&bio, file_bdev(zram->bdev_file), &bio_vec, 1,
+		bio_init(&bio, zram->bdev, &bio_vec, 1,
 			 REQ_OP_WRITE | REQ_SYNC);
 		bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9);
 		__bio_add_page(&bio, page, PAGE_SIZE, 0);
@@ -785,7 +770,7 @@ static void zram_sync_read(struct work_struct *work)
 	struct bio_vec bv;
 	struct bio bio;
 
-	bio_init(&bio, file_bdev(zw->zram->bdev_file), &bv, 1, REQ_OP_READ);
+	bio_init(&bio, zw->zram->bdev, &bv, 1, REQ_OP_READ);
 	bio.bi_iter.bi_sector = zw->entry * (PAGE_SIZE >> 9);
 	__bio_add_page(&bio, zw->page, PAGE_SIZE, 0);
 	zw->error = submit_bio_wait(&bio);
@@ -1568,7 +1553,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
  * Corresponding ZRAM slot should be locked.
  */
 static int zram_recompress(struct zram *zram, u32 index, struct page *page,
-			   u32 threshold, u32 prio, u32 prio_max)
+			   u64 *num_recomp_pages, u32 threshold, u32 prio,
+			   u32 prio_max)
 {
 	struct zcomp_strm *zstrm = NULL;
 	unsigned long handle_old;
@@ -1645,6 +1631,15 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page,
 	if (!zstrm)
 		return 0;
 
+	/*
+	 * Decrement the limit (if set) on pages we can recompress, even
+	 * when current recompression was unsuccessful or did not compress
+	 * the page below the threshold, because we still spent resources
+	 * on it.
+	 */
+	if (*num_recomp_pages)
+		*num_recomp_pages -= 1;
+
 	if (class_index_new >= class_index_old) {
 		/*
 		 * Secondary algorithms failed to re-compress the page
@@ -1710,6 +1705,7 @@ static ssize_t recompress_store(struct device *dev,
 	struct zram *zram = dev_to_zram(dev);
 	unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
 	char *args, *param, *val, *algo = NULL;
+	u64 num_recomp_pages = ULLONG_MAX;
 	u32 mode = 0, threshold = 0;
 	unsigned long index;
 	struct page *page;
@@ -1732,6 +1728,17 @@ static ssize_t recompress_store(struct device *dev,
 			continue;
 		}
 
+		if (!strcmp(param, "max_pages")) {
+			/*
+			 * Limit the number of entries (pages) we attempt to
+			 * recompress.
+			 */
+			ret = kstrtoull(val, 10, &num_recomp_pages);
+			if (ret)
+				return ret;
+			continue;
+		}
+
 		if (!strcmp(param, "threshold")) {
 			/*
 			 * We will re-compress only idle objects equal or
@@ -1788,6 +1795,9 @@ static ssize_t recompress_store(struct device *dev,
 	for (index = 0; index < nr_pages; index++) {
 		int err = 0;
 
+		if (!num_recomp_pages)
+			break;
+
 		zram_slot_lock(zram, index);
 
 		if (!zram_allocated(zram, index))
@@ -1807,8 +1817,8 @@ static ssize_t recompress_store(struct device *dev,
 		    zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
 			goto next;
 
-		err = zram_recompress(zram, index, page, threshold,
-				      prio, prio_max);
+		err = zram_recompress(zram, index, page, &num_recomp_pages,
+				      threshold, prio, prio_max);
 next:
 		zram_slot_unlock(zram, index);
 		if (err) {
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 37bf29f34d26..35e322144629 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -132,7 +132,7 @@ struct zram {
 	spinlock_t wb_limit_lock;
 	bool wb_limit_enable;
 	u64 bd_wb_limit;
-	struct file *bdev_file;
+	struct block_device *bdev;
 	unsigned long *bitmap;
 	unsigned long nr_pages;
 #endif